Method and system for ai-based content evaluation

Abstract

An AI-based content evaluation method is disclosed. The method comprises the steps of: acquiring data related to a first content based on user input; inputting the data related to the first content into a content analysis model to acquire analysis information of the first content and evaluating whether the theme and story flow of the first content match; using the analysis information of the first content, selecting a content group corresponding to the first content from among a plurality of content groups; acquiring analysis information of a second content included in the selected content group; dividing the selected content group into a plurality of sub-groups based on the analysis information of the second content; recombining only some of the groups among the plurality of sub-groups based on the analysis information of the first content to reconstruct the second content; comparing the analysis information of the first content with the analysis information of the reconstructed second content to determine positive elements and negative elements corresponding to the success probability and / or risk of the first content; and generating content verification information including the positive elements and negative elements of the first content, wherein the elements of the content verification information are configured such that the negative elements are prioritized over the positive elements. It may include a step of outputting content verification information of the first content; and a step of evaluating whether a scenario for content production is valid based on the verification information.

Description

Technology Field

[0001] The present disclosure relates to a method for analyzing content based on artificial intelligence and evaluating content by comparing the analysis results with content to be compared. Background Technology

[0002] In the pre-production review stage of video content such as movies or dramas, the volume of initial materials—including planning proposals, scenarios, and scripts—is substantial, and the time and cost involved are significant. Furthermore, since the review process is conducted by humans, judgments are often subjective and rely on intuition. There is a need for technology that reduces time and costs for better planning and production by analyzing current projects based on past initial planning materials—such as planning proposals, scripts, and scenarios—as well as box office results and trends of the times regarding works that have already been produced or screened. This involves suggesting areas for improvement through comparison with similar past works and presenting the probability of success to producers, planners, and original creators using reliable numerical data. Prior art literature

[0003] (Registered Patent Publication) No. 10-2617657 The problem to be solved

[0004] The problem that the present disclosure aims to solve is to provide results of analyzing and evaluating the potential for success and risks of content during the production and planning stages. Additionally, it provides a method for precisely determining content to be compared for content analysis. means of solving the problem

[0005] According to one aspect of the present disclosure, an AI-based content evaluation method comprises: a step of obtaining data related to a first content based on user input; a step of inputting the data related to the first content into a content analysis model to obtain analysis information of the first content and evaluating whether the theme and story flow of the first content match; a step of selecting a content group corresponding to the first content from among a plurality of content groups using the analysis information of the first content; a step of obtaining analysis information of a second content included in the selected content group; a step of dividing the selected content group into a plurality of sub-groups based on the analysis information of the second content; a step of reconstructing the second content by recombining only some of the groups among the plurality of sub-groups based on the analysis information of the first content; a step of determining positive elements and negative elements corresponding to the success probability and / or risk of the first content by comparing the analysis information of the first content with the analysis information of the reconstructed second content; and a step of generating content verification information including the positive elements and the negative elements of the first content, wherein the elements of the content verification information are configured such that the negative elements are prioritized over the positive elements. It may include a step of outputting content verification information of the first content; and a step of evaluating whether a scenario for content production is valid based on the verification information.

[0006] The above positive factors include whether the subject or genre of the content aligns with popular social trends, or the originality of the story, and the above negative factors may include a competitive market environment, the staleness of the story, or a copyright list.

[0007] Based on the analysis information of the first content, the originality of the first content is calculated as a score using the analysis information of the second content, and based on the score for each element of the verification information, negative elements and positive elements may be included in the verification information in order of highest score.

[0008] The above method may include the step of dividing the selected content group into a plurality of subgroups based on analysis information of the second content; and the step of reconstructing the second content by recombining only some of the plurality of subgroups based on analysis information of the first content.

[0009] The above method may include: a step of identifying a lower-priority content group corresponding to the first content; a step of dividing the lower-priority content group into a plurality of lower-priority subgroups based on analysis information of the content included in the lower-priority content group; and a step of selecting some of the plurality of lower-priority subgroups based on analysis information of the first content and including the content included in the selected lower-priority subgroups in the second content.

[0010] The above method further includes the step of obtaining the priority of the elements of the analysis information of the first content, and the step of dividing the selected content group into a plurality of sub-groups may be to apply weights to the analysis information of the second content based on the priority.

[0011] The above method further includes the step of obtaining a verification parameter representing the verification strength of the first content based on user input, and the step of generating the verification information may include the step of applying weights to the elements of the verification information based on the verification parameter.

[0012] The step of outputting verification information of the first content above may involve outputting verification information without weights and verification information with weights applied together.

[0013] The step of outputting verification information of the first content may include the step of displaying prediction results for a plurality of content platforms together with the verification information. Effects of the invention

[0014] According to the disclosed embodiment, during the content production and planning stages, results of an analysis and evaluation of the potential for success and risks of the content can be received. Additionally, the content to be compared can be precisely determined to ensure that accurate analysis results are obtained. Brief explanation of the drawing

[0015] FIG. 1 is a diagram for schematically explaining the operation of a server according to one embodiment of the present disclosure. FIG. 2 is a flowchart for explaining the operation of a server according to one embodiment of the present disclosure. FIG. 3 is a diagram illustrating the operation of a server determining a second content for analyzing a first content according to one embodiment of the present disclosure. FIG. 4 is a diagram illustrating the operation of a server determining a second content for analyzing a first content according to one embodiment of the present disclosure. FIG. 5 is a diagram illustrating the operation of a server applying weights to analysis information of a second content according to one embodiment of the present disclosure. FIG. 6 is a diagram illustrating the operation of a server using verification parameters according to one embodiment of the present disclosure. FIG. 7 is a block diagram illustrating the configuration of a server according to one embodiment of the present disclosure. Specific details for implementing the invention

[0016] Hereinafter, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights.

[0017] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed forms, and the scope of this specification includes modifications, equivalents, or substitutions that fall within the technical concept.

[0018] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0019] Furthermore, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly and specifically defined otherwise. In certain cases, terms have been selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant explanatory sections. Accordingly, terms used in this disclosure should be defined not merely by their names, but based on their meanings and the content throughout this disclosure.

[0020] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or joined to that other component, or that there may be other components in between.

[0021] The terms used in the embodiments are for illustrative purposes only and should not be interpreted as intended to be limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0022] Throughout this specification, when a part is described as “comprising” a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, the singular form used in this specification includes the plural form unless specifically stated otherwise in the text. Additionally, the expression “at least one of b and c” described throughout this specification may encompass ‘a alone,’ ‘b alone,’ ‘c alone,’ ‘a and b,’ ‘a and c,’ ‘b and c,’ or ‘a, b, and c all.’

[0023] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0024] Additionally, terms such as “…part,” “…module,” etc., as described in this specification refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software. Furthermore, embodiments of the present disclosure may be represented by functional block configurations and various processing steps. These functional blocks may be implemented by various numbers of hardware and / or software configurations that execute specific functions. For example, embodiments of the present disclosure may employ integrated circuit configurations such as memory, processing, logic, look-up tables, etc., which can execute various functions under the control of one or more microprocessors or other control devices.

[0025] Each block of the process flow diagrams attached to this specification and combinations of the flow diagrams may be executed by computer program instructions. Since these computer program instructions may be loaded into the processor of a general-purpose computer, a computer for special purposes, or other programmable data processing equipment, the instructions executed through the processor of the computer or other programmable data processing equipment create means for performing the functions described in the flow diagram block(s).

[0026] These computer program instructions may be stored in computer-available or computer-readable memory that can be directed toward a computer or other programmable data processing equipment to implement a function in a specific way, and the instructions stored in said computer-available or computer-readable memory may also produce a manufactured item containing instruction means that performs the function described in the flowchart block(s).

[0027] Since computer program instructions can be loaded onto a computer or other programmable data processing equipment, instructions that perform a series of operation steps on the computer or other programmable data processing equipment to create a process executed by the computer can also provide steps for executing the functions described in the flowchart block(s).

[0028] Additionally, each block may represent a module, segment, or part of code containing one or more executable instructions for executing a specified logical function(s). Furthermore, in some alternative execution examples, the functions mentioned in the blocks may occur out of order. For instance, two blocks described in succession may actually be executed substantially simultaneously, or the blocks may be executed in reverse order according to their corresponding functions.

[0029] In addition, when describing with reference to the attached drawings, identical components are assigned the same reference numeral regardless of drawing symbols, and redundant descriptions thereof are omitted. In describing the embodiments, if it is determined that a detailed description of related prior art could unnecessarily obscure the essence of the embodiments, such detailed description is omitted.

[0030] FIG. 1 is a diagram for schematically explaining the operation of a server according to one embodiment of the present disclosure.

[0031] A server (100) according to one embodiment may provide a content verification platform (102). The content verification platform (102) may be a platform that provides a service for evaluating whether a scenario, budget, plan, etc., for content production are valid and effective in the initial stage of creating content. The user of the content verification platform (102) may be a user who wishes to verify content in order to produce content, such as a content writer, a content planner, or a content writer. The user may access the content verification platform (102) using a user device (101).

[0032] In one embodiment, a user may upload data related to content to a content verification platform (102). A server (100) may obtain data related to content from a user and analyze the data related to content to generate content verification information indicating the probability of success and / or risk.

[0033] The user can check the verification results displayed on the content verification platform (102) through the user device (101) and decide whether to produce, invest in, or modify the content based on the verification results. For example, the verification results may include positive and negative factors that evaluate the distinctiveness, potential for success, and copyright infringement of the content.

[0034] A server (100) according to one embodiment may analyze data related to content using an artificial intelligence model to verify the validity of whether the content has specificity and marketability suitable for production based on the data. In addition, the server (100) may precisely select and process comparison data for evaluating content, thereby enabling the user to easily check evaluation results for the content and modify / supplement the plan for content production.

[0035] A series of processes for a content analysis and evaluation method, which are carried out through a content verification platform (102) provided by the server (100) of the present disclosure, will be understood in more detail by referring to the drawings and corresponding descriptions described below.

[0036] FIG. 2 is a flowchart for explaining the operation of a server according to one embodiment of the present disclosure.

[0037] In operation S210, the server (100) can obtain data related to the first content based on user input. The data related to the first content can be obtained through a user device connected to the content verification platform. For example, the user uploads data to the platform using the user device, and the server (100) can obtain the uploaded data. The data related to the content may include text data such as a script or a scenario plan. The data related to the content may include image data such as illustrations, character designs, concept art, etc.

[0038] In operation S220, the server (100) can obtain analysis information of the first content by inputting data related to the first content into a content analysis model.

[0039] In one embodiment, the content analysis model may be a text analysis model utilizing natural language processing. The content analysis model for text analysis may be composed of multiple models that perform subdivided tasks according to various purposes. Depending on the subdivided tasks of the content analysis model, post-processing may be applied to process the inference results of the content analysis model into appropriate analysis information. The content analysis model generates output data based on input data according to the subdivided tasks. The content analysis model may be a model that has completed training based on training data for performing subdivided tasks. For example, for a sentiment analysis model, the training data may be text labeled with sentiment information; the text may be text such as scripts or scenarios, but is not limited thereto. Since the architecture, training, and inference methods of the content analysis model can be applied by employing known artificial intelligence technologies or through modifications of known artificial intelligence technologies, a detailed description is omitted.

[0040] For example, the content analysis model may include a model for sentiment analysis. The sentiment analysis model can understand the sentiment of each scene or line of dialogue by analyzing the sentiments of the sentences used in the scenario or script. For example, the sentiment analysis model can identify the sentiment of the content by recognizing positive, negative, and neutral sentiments. Based on the results of the sentiment analysis model, the server (100) can obtain analysis information indicating the main sentiment of the content, the sentiment by time period, and the flow of the sentiment development.

[0041] For example, the content analysis model may include a protagonist analysis model. The protagonist analysis model can analyze the characteristics, personality, and emotional changes of the main protagonist appearing in the scenario or script. For example, the protagonist analysis model can identify the protagonist's role, personality development, and behavioral patterns to evaluate whether they match the theme of the content. Based on the results of the protagonist analysis model, the server (100) can obtain analysis information indicating the number of protagonists, the number of surrounding characters, relationships between characters, the personalities of the characters, appearance rates, and appearance times.

[0042] For example, the content analysis model may include a dialogue analysis model. The dialogue analysis model can analyze the spelling, naturalness, vocabulary, tone, etc., of dialogue, explanatory text, narration, etc., that appear in a scenario or script. Based on the results of the sentence quality analysis model, the server (100) can obtain analysis information indicating whether the vocabulary, tone, etc., of each character's dialogue matches the character's personality, the number of lines of dialogue per character, the proportion of dialogue, and whether there is any unnatural dialogue.

[0043] For example, the content analysis model may include a story structure analysis model. The story structure analysis model analyzes the story structure of a scenario or script to analyze scenes such as the flow of development, events, resolution, and climax, and can evaluate the connectivity between scenes and the overall story flow. Based on the results of the story structure analysis model, the server (100) can obtain analysis information indicating whether the development between events is natural, whether the events and scenes included in the story are appropriate, and whether the genre, theme, concept, and theme of the story are well revealed.

[0044] Content analysis models for text processing can be implemented by adopting various known architectures based on natural language processing algorithms or through variations of various known architectures. Examples include Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Transformers, Generative Pre-trained Transformer (GPT), Bidirectional Encoder Representations from Transformers (BERT), Named Entity Recognition (NER), and Latent Dirichlet Allocation (LDA).

[0045] In operation S230, the server (100) can select a content group corresponding to the first content from among a plurality of content groups using analysis information of the first content.

[0046] In the disclosed embodiment, a plurality of content groups refers to grouping similar content based on data and / or content analysis information related to the content of other content in addition to the first content.

[0047] In one embodiment, the server (100) may acquire data related to the content of other content and acquire content analysis information for each content. The server may acquire analysis information for each content by using a content analysis model. In one embodiment, other content that has already been completed, released, and distributed may include metadata. For example, the content's genre, release date, title, plot, director, actors, viewing rating, etc. may be included. The server (100) may include metadata in the analysis information of other content.

[0048] The server (100) can generate multiple content groups using analysis information of the content. For example, the server (100) can generate content groups by grouping multiple contents into similar characteristics using various criteria such as genre, theme, target audience, popularity, rating, content type (e.g., movie, drama, documentary, entertainment program, etc.), cast, and release year. However, the criteria for generating content groups by the server (100) are not limited to the examples described above.

[0049] The server (100) can select a content group corresponding to the first content based on the analysis information of the first content. For example, the server (100) can cluster the analysis information of the first content with the analysis information of other content to identify the cluster in which the first content is classified and select a content group corresponding to the cluster. For example, the server (100) can select a content group corresponding to the first content by comparing the analysis information of the first content with the characteristic information of the content group. The characteristic information of the content group may include, for example, the average of the content analysis information included in the content group or information regarding the criteria used to create the content group, but is not limited thereto.

[0050] In operation S240, the server (100) can obtain analysis information of the second content included in the selected content group.

[0051] For example, when content group A is selected, the server (100) can obtain analysis information of second content, which is content included in content group A. The analysis information of second content may have been obtained at a previous time by the server (100) using a content analysis model.

[0052] In operation S250, the server (100) can compare the analysis information of the first content with the analysis information of the second content to determine positive and negative factors corresponding to the success probability and / or risk of the first content.

[0053] Positive factors indicating the potential for success of the first content may include, for example, whether the content's theme or genre aligns with popular social trends, and the originality and creativity of the content's story or theme. Negative factors indicating the risk of the first content may include, for example, a competitive market environment, the staleness of the content's story or theme, and copyright risk; however, the positive and negative factors obtainable by comparing analysis information are not limited to the examples mentioned above.

[0054] In operation S260, the server (100) can generate content verification information including positive elements and negative elements of the first content.

[0055] When the server (100) generates verification information for the first content, it may configure and display negative elements with higher priority than positive elements so that the user can refer to and supplement the first content when creating it. Additionally, the server (100) may generate verification information for the first content such that negative elements are displayed more than positive elements. For example, the server (100) may generate verification information in which the first negative element, the second negative element, and the third negative element are displayed first, and the first positive element and the second positive element are included.

[0056] In one embodiment, the server (100) can calculate a score for each element of the verification information. For example, based on the analysis information of the first content, the novelty of the first content can be calculated as a score using the analysis information of the second content. Based on the scores for each element of the verification information, the server (100) can include negative elements and positive elements in the verification information in order of highest score.

[0057] In operation S270, the server (100) can output verification information for the first content. The output verification information can be displayed through the platform. The user can check the verification information for the first content while connected to the platform using a user device.

[0058] In one embodiment, the server (100) may output verification information obtained by a plurality of different methods together. For example, the server (100) may output verification information without weights applied and verification information with weights applied together. The application of weights will be described later.

[0059] In one embodiment, the server (100) may display prediction results for a plurality of content platforms along with verification information. For example, the server (100) may display the predicted probability of success / risk when releasing content on a first content platform (e.g., OTT A) and the predicted probability of success / risk when releasing content on a second content platform (e.g., OTT B), respectively. In this case, the server (100) may analyze the content provided on each platform as the second content in order to provide prediction results for the plurality of content platforms. For example, the server (100) may determine the second content by determining a plurality of content groups, sub-groups, lower priority groups, lower priority sub-groups, etc., based on the content provided on the first content platform, and generate verification information corresponding to the first content platform by comparing the first content analysis information with the second content analysis information.

[0060] FIG. 3 is a diagram illustrating the operation of a server determining a second content for analyzing a first content according to one embodiment of the present disclosure.

[0061] Operation S310 can be performed after operation S240 is performed. In operation S310, the server (100) can divide the selected content group into a plurality of sub-groups based on the analysis information of the second content.

[0062] In one embodiment, the content groups previously generated by the server (100) may be the result of a comprehensive classification operation based on previously set criteria. In this case, the server (100) may further classify the content included within the content group according to detailed classification criteria in order to more precisely determine the second content to be compared with the first content.

[0063] For example, a content group selected to correspond to the first content may include content corresponding to the 'thriller' genre. The server (100) may divide the content group into multiple subgroups based on content analysis information of the second content included in the selected content group. For example, the server (100) may create various subgroups for the second content, which is 'thriller' content, based on classification criteria such as year, content type (e.g., movie, drama, etc.), country, box office score, uploaded platform (e.g., OTT A, OTT B, etc.), and production cost. In this case, specific content may be included in two or more subgroups. However, the selection of the content group is not limited to being based on the genre of the example described above.

[0064] When multiple subgroups are created, the server (100) can reconstruct the second content by recombining only some of the multiple subgroups based on the analysis information of the first content. For example, the server (100) can reconstruct the second content by recombining only the subgroups for a predetermined period (e.g., the last N years) based on subgroups reclassified by year. Also, for example, the server (100) can reconstruct the second content by recombining only the subgroups of a specific type (e.g., movies) based on subgroups reclassified by type (e.g., movies, dramas, etc.). Also, for example, the server (100) can reconstruct the second content by recombining only the subgroups of content included on the platform (e.g., OTT A) where the first content is to be released.

[0065] The server (100) can precisely determine the second content suitable for verifying the first content by dividing the content group into subgroups based on the analysis information of the second content and recombining only some of the subgroups divided based on the analysis information of the first content.

[0066] When the second content is updated through the aforementioned operations, the server (100) can analyze the success probability / risk of the first content based on the analysis information of the updated second content.

[0067] FIG. 4 is a diagram illustrating the operation of a server determining a second content for analyzing a first content according to one embodiment of the present disclosure.

[0068] Operation S410 can be performed after operation S240 has been performed. It can also be performed in parallel with the operations described in FIG. 3. In operation S410, the server (100) can identify a lower-priority content group corresponding to the first content.

[0069] For example, a content group selected to correspond to the first content may include content corresponding to the 'thriller' genre. Next, there may be content groups that are less related than the selected content group but are related to the first content group. For example, a group corresponding to the 'horror' genre may be identified as a lower-priority content group. Or, a group corresponding to the 'war' genre may be identified as a lower-priority content group. However, the selection of a lower-priority content group is not limited to being based on the genres of the aforementioned examples.

[0070] In operation S420, the server (100) may divide the lower-priority content group into multiple lower-priority sub-groups based on analysis information of the content included in the lower-priority content group. The operation of the server (100) dividing the lower-priority content group into multiple sub-groups may be performed in the same or similar manner as operation S310 of FIG. 3. Therefore, for brevity, repetitive descriptions are omitted.

[0071] In operation S430, the server (100) may select some of the multiple lower-priority subgroups based on the analysis information of the first content and add the content included in the selected lower-priority subgroups to the second content. The operation of the server (100) combining only some of the lower-priority server groups and adding them to the second content may be performed in the same or similar manner as in operation S320. Therefore, for brevity, repetitive descriptions are omitted.

[0072] By utilizing the lower-priority content group, the server (100) can enrich the second content that can be compared with the first content. For example, rather than comparing only content included in the 'thriller' genre to verify the first content, content that is not included in the 'thriller' genre but is included in the 'horror' genre may be suitable for analyzing the success potential / risk of the first content. The server (100) can use the lower-priority content group to complement the selection of the second content within the selected content group. That is, the server (100) can precisely determine the second content suitable for verifying the first content by dividing the content group into lower-priority subgroups based on the analysis information of the content included in the lower-priority content group, and by adding content included in only some of the lower-priority subgroups divided based on the analysis information of the first content to the second content.

[0073] In one embodiment, the server (100) may apply different weights to content included in a priority content group and content included in a lower-priority content group. For example, the server (100) may apply a first weight when content included in a priority content group is analyzed as second content, and apply a second weight when content included in a lower-priority content group is analyzed as second content. In this case, the first weight may be a greater value than the second weight.

[0074] FIG. 5 is a diagram illustrating the operation of a server applying weights to analysis information of a second content according to one embodiment of the present disclosure.

[0075] In operation S510, the server (100) can obtain the priority of the elements of the analysis information of the first content. The priority of the elements of the analysis information may be one that is already stored in the server (100) or may be obtained through user input.

[0076] For example, among the analysis elements of the first content, the relative importance of the analysis elements may differ. For example, the importance of the first element may be higher than the importance of the second element. In this case, the server (100) can obtain an analysis information priority that indicates the relatively different importance of the analysis elements.

[0077] In operation S520, the server (100) may apply weights to the analysis information of the second content based on priority. The server (100) may apply weights to the analysis information of the second content based on priority when dividing a selected content group into multiple subgroups. For example, when the server (100) divides a content group into multiple subgroups, it may create a first subgroup based on a first analysis element and create a second subgroup based on a second analysis element. In this case, if the priority of the first subgroup is higher than the priority of the second subgroup, the server (100) may apply weights so that the second content included in the first subgroup is reflected more in the analysis. Also, for example, the server (100) may apply weights based on priority when dividing a lower-priority content group into multiple lower-priority subgroups. In this case, a first weight may be applied to the higher-priority content group and a second weight may be applied to the lower-priority content group. The first weight may be a greater value than the second weight.

[0078] In one embodiment, the server (100) may determine the number of contents to be included in subgroups based on priority. For example, the first subgroup generated based on the first analysis element may include N contents, and the second subgroup generated based on the second analysis element may include M contents. In this case, the values ​​may be such that N > M. Additionally, for example, the server (100) may determine the number of contents to be included in lower-priority subgroups based on priority. Since this is identical or similar to determining the number of contents to be included in higher-priority subgroups, a repetitive explanation is omitted. The server (100) may allow the second contents to be determined more precisely by adjusting the number of contents to be included in the subgroups and lower-priority subgroups to different scales.

[0079] FIG. 6 is a diagram illustrating the operation of a server using verification parameters according to one embodiment of the present disclosure.

[0080] In operation S610, the server (100) can obtain a verification parameter indicating the verification strength of the first content based on user input. If the verification parameter indicates a strong verification value, the server (100) can determine the success probability / risk of the first content more strictly or flexibly.

[0081] In operation S620, the server (100) may apply weights to elements of verification information based on verification parameters. For example, a higher weight may be applied to negative elements of verification information than to positive elements. Specifically, the first negative element may be similarity with another content, such as the second content, and the second negative element may be copyright risk. In this case, copyright is a greater risk factor than similarity in the production of the first content. As the verification intensity increases, the server (100) may generate verification information by giving a higher weight to copyright risk than to similarity, thereby enabling the user to supplement the necessary matters for planning and producing the first content.

[0082] FIG. 7 is a block diagram illustrating the configuration of a server according to one embodiment of the present disclosure.

[0083] Referring to FIG. 7, a server (100) according to one embodiment may include a communication interface (110), a memory (120), and a processor (130).

[0084] The communication interface (110) can perform data communication with a user device or an external server under the control of the processor (130).

[0085] The communication interface (110) may include a communication circuit module for performing wired and wireless communication. Wired communication may include Ethernet. Wireless communication may include Wi-Fi (Wireless Fidelity), LTE (Long-Term Evolution), 5G (Fifth Generation), and satellite communication.

[0086] The communication interface (110) allows the server (100) to operate a content verification platform and to transmit and receive data with a user device and / or an external server to provide verification information of the first content to the user. For example, the server (100) can receive data related to the content from a user device through the communication interface (110). For example, the server (100) can provide content verification information to a user device through the communication interface (110).

[0087] The memory (120) may store instructions, data structures, and program code that can be read by the processor (130). Operations performed by the processor (130) may be implemented by executing the instructions or code of the program stored in the memory (120).

[0088] The memory (120) may include a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a non-volatile memory including at least one of ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, a magnetic disk, and an optical disk, and a volatile memory such as RAM (Random Access Memory) or SRAM (Static Random Access Memory).

[0089] A memory (120) according to one embodiment may store one or more instructions or programs or applications that enable the server (100) to operate to analyze and evaluate content.

[0090] The processor (130) can control the overall operations of the server (100). For example, the processor (130) can control the overall operations that cause the server (100) to analyze and evaluate content by executing one or more instructions stored in memory (120). There may be one or more processors (130).

[0091] The processor (130) may include, for example, at least one of a Central Processing Unit, a microprocessor, a Graphic Processing Unit, ASICs (Application Specific Integrated Circuits), and an Application Processor, but is not limited thereto.

[0092] The operations of the processor (130) have been described in detail in the drawings previously, so a repetitive description is omitted.

[0093] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0094] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0095] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0096] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0097] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A method for evaluating AI-based content comprises: a step of obtaining data related to a first content based on user input; a step of inputting the data related to the first content into a content analysis model to obtain analysis information of the first content and evaluating whether the theme and story flow of the first content match; a step of selecting a content group corresponding to the first content from among a plurality of content groups using the analysis information of the first content; a step of obtaining analysis information of a second content included in the selected content group; a step of dividing the selected content group into a plurality of sub-groups based on the analysis information of the second content; a step of reconstructing the second content by recombining only some of the groups among the plurality of sub-groups based on the analysis information of the first content; a step of determining positive elements and negative elements corresponding to the success probability and / or risk of the first content by comparing the analysis information of the first content with the analysis information of the reconstructed second content; and a step of generating content verification information including the positive elements and the negative elements of the first content, wherein the elements of the content verification information are configured such that the negative elements are prioritized over the positive elements. A method comprising: a step of outputting content verification information of the first content; and a step of evaluating whether a scenario for content production is valid based on the verification information. Claim 2 A method according to claim 1, wherein the positive elements include whether the subject or genre of the content aligns with popular social trends, or the originality of the story, and the negative elements include a competitive market environment, the staleness of the story, or a copyright list. Claim 3 A method according to paragraph 2, wherein the originality of the first content is calculated as a score using the analysis information of the second content based on the analysis information of the first content, and negative elements and positive elements are included in the verification information in order of highest score based on the score for each element of the verification information.

Images