Ai system that evaluates the value of artist IP content based on cross-platform standardized data

Abstract

The present invention relates to an artificial intelligence system for calculating the value of cross-platform standardized data-based artist IP content. The system of the present invention may be characterized by comprising: a data integration processing module that collects raw data from multiple platforms regarding specific content, converts it into ontology-based entities, and then standardizes it to generate standard indicator data for multiple platforms regarding specific content; a data consistency management module that records the processing history of collecting, converting, and standardizing raw data regarding specific content based on lineage and detects abnormal patterns; and a performance prediction module that processes advertising expenditure costs from multiple platforms and standard indicator data for multiple platforms regarding specific content to predict the fandom growth rate relative to advertising expenditure costs.

Description

Technology Field

[0001] The present invention relates to an artificial intelligence system for calculating the value of cross-platform standardized data-based artist IP content. Background Technology

[0002] In the entertainment industry, cross-platform comparisons are difficult because metrics such as views, streams, engagement, reach, and ad spending generated on different platforms like YouTube, TikTok, Spotify, and Meta use different definitions and filtering rules; consequently, it is limited to objectively analyze an artist's actual popularity or the performance of their music.

[0003] Furthermore, data collection, organization, and report generation are mostly performed manually, which is time-consuming; additionally, the lack of a structure to integrate platform-specific metrics into a single standard or quantify growth trajectories makes it difficult to formulate accurate strategies.

[0004] Existing analysis tools are limited to displaying historical data and do not provide features to predict how results, such as views or streams, will change when a budget is invested in a specific platform, or to compare various budget allocation scenarios, thus having limitations as practical decision-making tools.

[0005] In particular, while artists and music IP are significantly influenced by intangible assets such as fandom growth rates, engagement, and content responsiveness, labels and agencies face difficulties in making IP-based management and investment decisions because there is no indicator system to quantify and express these values.

[0006] Furthermore, there is also a lack of technology capable of automatically detecting data outliers that undermine reliability, such as sudden increases in view counts or abnormal patterns, and correcting the accuracy of analysis models.

[0007] Against this technological backdrop, there is a growing need for an integrated system that semantically maps data from different platforms into an ontology structure to consolidate them into a single standard metric, and based on this, can predict the future performance of artists and music and automatically generate budget allocation scenarios. The problem to be solved

[0008] The problem that the present invention aims to solve is to provide an artificial intelligence system that calculates the value of cross-platform standardized data-based artist IP content.

[0009] The problems that the present invention aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0010] The system of the present invention for solving the aforementioned problem may be characterized by comprising: a data integration processing module that collects raw data from multiple platforms regarding specific content, converts it into ontology-based entities, and then standardizes it to generate standard indicator data for multiple platforms regarding specific content; a data consistency management module that records the processing history of collecting, converting, and standardizing raw data regarding specific content based on lineage and detects abnormal patterns; and a performance prediction module that processes advertising expenditure costs from multiple platforms and standard indicator data for multiple platforms regarding specific content to predict the fandom growth rate relative to advertising expenditure costs.

[0011] The raw data of multiple platforms may be characterized as data regarding the content artist, content type, and content performance indicators for the content uploaded to multiple platforms.

[0012] The above performance prediction module may be characterized by including a predictive artificial intelligence trained on training data in which the advertising expenditure cost of each of a plurality of platforms, standard data for content types and standard data for content performance indicators of each of a plurality of platforms are set as feature values, and the fandom growth rate relative to the advertising expenditure cost is set as a label value.

[0013] The above data integration processing module may be characterized by inputting the current advertising expenditure costs of each of the multiple platforms, standard data for content types of each of the multiple platforms, and standard data for content performance indicators into the performance prediction module, thereby outputting a predicted value of the fandom growth rate relative to the advertising expenditure costs.

[0014] It may further include a value calculation module that calculates the IP price of specific content by processing standard indicator data from multiple platforms for specific content and the predicted value of the fandom growth rate relative to advertising expenditure output from the performance prediction module. Effects of the invention

[0015] According to the present invention, by integrating unstructured data such as views, streams, engagement, and advertising expenditures generated on different platforms based on an ontology, the problems of incomparability and analysis distortion caused by differences in metric definitions by platform are resolved, and a standard metric based on a single criterion is generated, thereby enabling the evaluation of artist and music performance based on objective and consistent standards.

[0016] In addition, the data consistency verification function automatically detects factors that undermine analysis reliability, such as missing data, schema inconsistencies, and abnormal patterns, thereby ensuring the transparency and accuracy of the entire data flow.

[0017] Furthermore, by combining time-series-based forecasting models with budget-performance correlation models, it is possible to quantitatively predict changes in artist growth rates, music stream trends, and fandom metrics, enabling future-oriented analysis and performance forecasting that existing tools could not provide.

[0018] In particular, the present invention allows users to immediately compare the effects of various expenditure combinations through a function that automatically calculates platform-specific budget allocation scenarios for achieving target performance, thereby significantly improving the efficiency of marketing strategy formulation and the possibility of achieving performance.

[0019] In addition, the stability and reliability of the model are increased by automatically detecting sudden surges in views or abnormal usage patterns and reflecting them in the predicted values, and a new indicator system is provided that can evaluate the intangible asset value of artists or music content based on data, as an IP value index is calculated that comprehensively reflects the fandom growth rate, engagement, and the life cycle of the music.

[0020] Therefore, the present invention can be utilized in various areas throughout the entertainment industry, such as data standardization, performance analysis, strategy formulation, report automation, and content IP assetization, and has industrial effects that simultaneously improve the speed and accuracy of decision-making for artists, labels, and management teams.

[0021] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0022] Figure 1 is a configuration diagram showing the system of the present invention. FIGS. 2 and FIGS. 3 are conceptual diagrams showing an app / web page in which the system of the present invention is implemented. Specific details for implementing the invention

[0023] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the present invention, and the present invention is defined only by the scope of the claims.

[0024] The terms used in this specification are for describing embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. The terms "comprises" and / or "comprising" used in this specification do not exclude the presence or addition of one or more other components in addition to the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and "and / or" includes each of the mentioned components and all combinations of one or more. Although terms such as "first," "second," etc., are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another. Therefore, the first component mentioned below may be the second component within the technical scope of the invention.

[0025] Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0027] Hereinafter, the system (100) of the present invention will be described with reference to the drawings. FIG. 1 is a configuration diagram showing the system of the present invention, and FIG. 2 and FIG. 3 are conceptual diagrams showing an app / web page in which the system of the present invention is implemented.

[0028] The system (100) of the present invention may be configured to collect raw data provided from a plurality of platforms, standardize the collected data by integrally correcting structural differences, and then predict performance relative to advertising expenditure based on standard indicator data.

[0029] The system (100) of the present invention includes a data integration processing module (10), a data consistency management module (20), and a performance prediction module (30), and each module is interconnected so that the entire data flow is automatically processed and prediction and analysis functions are performed while reliability is ensured.

[0030] The data integration processing module (10) can collect raw data from multiple platforms for specific content, convert it into an ontology-based entity, and then standardize it to generate standard indicator data for multiple platforms for specific content.

[0031] The data integration processing module (10) can collect raw data by setting a collection API and a raw data update cycle to collect raw data from multiple platforms. In this case, the raw data from multiple platforms for a specific content may be data regarding the content artist, content type (genre, concept, target country, etc.), and content performance indicators for the specific content uploaded to multiple platforms.

[0032] For example, raw data on platform A for specific content may indicate the content artist as "BTS", the content type as "Fire Live Performance_20250919", and the content performance indicator as "number of views per week", whereas, raw data on platform B for specific content may indicate the content artist as "BTS", the content type as "Fire Concert Video, September 19, 2025", and the content performance indicator as "number of clicks per hour".

[0033] The data integration processing module (10) can convert mutually different raw data for specific content across multiple platforms into ontology-based entities. That is, the data integration processing module (10) can convert all raw data that have the same meaning but different representations (notations) into a single common concept (ontology entity).

[0034] The data integration processing module (10) can map raw data collected from multiple platforms for specific content to the framework of an ontology concept. In this case, the ontology-based entities may be defined as concepts such as content artist entities, content type entities, and content performance indicator entities, and the ontology-based entities may have attributes of identifiers (e.g., ISRC, UPC).

[0035] The data integration processing module (10) can determine the meaning of the content artist, the meaning of the content type, and the meaning of the content performance indicator of the raw data using LLM and sLLM and map them to a pre-set identifier.

[0036] For example, raw data for content on platform A can be mapped from the content artist object to "B (identifier for BTS, Bangtan Boys, etc.)", from the content type object to "L25919 (identifier for live content on September 19, 2025)", and from the content performance metric object to "VW2100 (identifier for average of 2100 views per week)".

[0037] In addition, raw data for content on platform B can be mapped to "B (identifier for BTS, Bangtan Boys, etc.)" in the content artist object, to "L25919 (identifier for live content on September 19, 2025)" in the content type object, and to "VH20 (identifier for average of 20 views per hour)" in the content performance indicator object.

[0038] The data integration processing module (10) can generate standard indicator data for multiple platforms by standardizing the ontology object from which the raw data has been converted. In this case, the standard indicator data for multiple platforms can be divided into content artist standard data, content type standard data, and content performance indicator standard data.

[0039] The data integration processing module (10) can reflect the identifier of the content artist object as is into the content artist standard data, and the identifier of the content type object as is into the content type standard data.

[0040] In contrast, the data integration processing module (10) can generate standard content performance indicator data by undergoing a standardization process that unifies time units between multiple platforms, removes overestimation, and removes duplicate views from the identifier of the content performance indicator object.

[0041] For example, the standard data for content performance indicators of content on Platform A can be set to "VD232" by unifying the time unit to "VD300 (average 300 views per day)", removing overestimation to "VD240 (average 240 views per day)" (removing 20% ​​as it is known that there is a lot of bot traffic on Platform A), and removing duplicate views to "VD232 (average 232 views per day)" (removing suspected duplicate records 8 via IP tracking as the size of the fandom may be overestimated if the same user plays the same content on Platform A and Platform B).

[0042] Likewise, the standard data for content performance indicators of content on Platform B can be set to "VD480 (average 480 views per day)" with the time unit unified, "VD432 (average 432 views per day)" with overestimation removed (10% deduction as bot traffic is known to be moderate on Platform B), and "VD424" with duplicate views removed (8 suspected duplicate records removed via IP tracking as the size of the fandom may be overestimated if the same user plays the same content on Platform A and Platform B).

[0043] The data consistency management module (20) records the processing results generated by the data integration processing module (10) based on lineage and stores the change history that occurred during the data collection, transformation, and standardization stages in chronological order.

[0044] Recorded lineage information provides transparency of data flow and provides supporting data for reliability verification.

[0045] Additionally, the data consistency management module (20) analyzes the time series patterns of standard indicator data from multiple platforms and classifies abnormal fluctuations as abnormal patterns when detected, and automatically detects potential errors such as errors in collecting original data, omission of platform APIs, and abnormal traffic increases in specific time periods. This detection function may use a machine learning-based anomaly detection model or apply criteria for determining fluctuation rate outliers.

[0046] The data consistency management module (20) transmits the results of the consistency evaluation back to the data integration processing module (10) to form a data quality automatic improvement loop and ensures that the performance prediction module (30) can utilize high-quality standard indicator data.

[0047] The performance prediction module (30) can process the advertising expenditure costs of multiple platforms and the standard indicator data of multiple platforms to predict the fandom growth rate relative to the advertising expenditure costs of each of the multiple platforms.

[0048] For example, the performance prediction module (30) may be a prediction artificial intelligence trained with training data in which the advertising expenditure costs of multiple platforms with mutual correlation, standard data for content types of multiple platforms, and standard data for content performance indicators are set as feature values, and the fandom growth rate relative to the advertising expenditure costs is set as a label value.

[0049] In this case, the learning data may consist of arbitrary data set by an administrator in the system (100) of the present invention or history data, and the system (100) of the present invention may separately receive data regarding the fandom growth rate relative to advertising expenditure costs from an advertiser server (entertainment agency server), but is not limited thereto.

[0050] In this case, the fandom growth rate relative to advertising expenditure may be a figure representing the percentage increase in the number of fans for every 1 won of advertising expenditure incurred during a specific period (for example, a certain period from the time the first content was uploaded), but is not limited to this.

[0051] Accordingly, when the current advertising expenditure of multiple platforms, standard data on content types of multiple platforms, and standard data on content performance indicators are input into the performance prediction module (30) from the data integration processing module (10), a predicted value of the fandom growth rate relative to the advertising expenditure can be output. In this case, the data integration processing module (10) may receive the advertising expenditure of multiple platforms from an external advertiser server (entertainment agency server), but is not limited thereto.

[0052] As described above, the system (100) of the present invention has the advantage of being able to standardize data regarding specific content of an artist that is displayed differently on cross-platforms and provide it to an advertiser (entertainment agency).

[0053] In addition, it has the advantage of predicting the fandom growth rate relative to advertising expenditures currently spent across multiple platforms, thereby providing advertisers (entertainment agencies) with a basis for calculating marketing costs associated with the production and publishing of specific content.

[0054] Furthermore, the system (100) of the present invention may further include a value calculation module (40) that calculates the IP price of a specific content by processing standard indicator data of multiple platforms for the specific content and a predicted value of the fandom growth rate relative to advertising expenditure costs.

[0055] The value calculation module (40) may include a first value calculation artificial intelligence trained with training data in which the content type standard data and the predicted value of the fandom growth rate relative to the advertising expenditure cost among the standard indicator data of multiple platforms for a specific content with mutual correlation are set as feature values ​​and the IP price of the specific content is set as a label value; a second value calculation artificial intelligence trained with training data in which the content performance indicator standard data and the predicted value of the fandom growth rate relative to the advertising expenditure cost among the standard indicator data of multiple platforms for a specific content with mutual correlation are set as feature values ​​and the IP price of the specific content is set as a label value; and a third value calculation artificial intelligence trained with training data in which the content type standard data, the content performance indicator standard data and the predicted value of the fandom growth rate relative to the advertising expenditure cost among the standard indicator data of multiple platforms for a specific content with mutual correlation are set as feature values ​​and the IP price of the specific content is set as a label value.

[0056] In this case, among the standard indicator data of multiple platforms for specific content, the standard data for content type, the standard data for content performance indicators, and the predicted value for the fandom growth rate relative to advertising expenditure can be composed of actual past data resulting from the operation of the system (100) of the present invention, and the IP price of specific content may be a price calculated by actually commissioning a professional evaluation agency (intellectual property office, patent law firm, appraisal firm, etc.) to evaluate the IP price of specific content.

[0057] The value calculation module (40) can set the IP price of a specific content as an output value in which the predicted value of the fandom growth rate relative to the advertising expenditure received from the (1) performance prediction module (30) is less than the first reference value, and the content type standard data and content performance indicator standard data among the standard indicator data of multiple platforms for the specific content and the predicted value of the fandom growth rate relative to the advertising expenditure are input into the third value calculation artificial intelligence.

[0058] When the predicted fandom growth rate relative to advertising expenditure is below the first threshold, it corresponds to an early low-performance phase where the content has not yet received a sufficient response in the market or campaign efficiency is very low; therefore, there is a high risk that the IP price will be undervalued or overvalued through regression using only performance indicators.

[0059] Therefore, in this section, a third-party valuation AI utilizing standard data on content types, standard data on content performance indicators, and predicted fandom growth rates is employed to ensure a conservative IP pricing model that considers structural characteristics such as genre, format, and target market, along with limited performance data and growth potential.

[0060] (2) When the predicted value of the fandom growth rate relative to the advertising expenditure received from the performance prediction module (30) is greater than or equal to the first threshold value and less than the second threshold value which is greater than the first threshold value, the IP price of the specific content can be set as an output value by inputting the content type standard data and the predicted value of the fandom growth rate relative to the advertising expenditure among the standard indicator data of multiple platforms for the specific content into the first value calculation artificial intelligence.

[0061] When the predicted fandom growth rate is above the first threshold value and below the second threshold value, it can be seen as an early growth phase where initial verification has been passed to some extent but the influence of market positioning is still significant. Therefore, in this phase, the IP price is calculated using the first value-calculating AI trained on content type standard data and the predicted fandom growth rate, thereby focusing on reflecting premiums based on content types such as genre, concept, and target country.

[0062] (3) When the predicted value of the fandom growth rate relative to the advertising expenditure received from the performance prediction module (30) is greater than or equal to the second threshold value and less than the third threshold value which is greater than the second threshold value, the IP price of the specific content can be set as an output value by inputting the content performance indicator standard data among the standard indicator data of multiple platforms for the specific content and the predicted value of the fandom growth rate relative to the advertising expenditure into the second value calculation artificial intelligence.

[0063] When the predicted fandom growth rate is greater than or equal to the second threshold and less than the third threshold, it corresponds to the mid-to-late growth phase where a certain level of fandom and performance indicators occur stably; therefore, at this stage, actual views, streams, and revenue indicators become key explanatory variables of IP price.

[0064] Therefore, in this section, a second valuation AI trained on standard content performance indicator data and predicted fandom growth rates is used to perform sophisticated valuation that finely reflects the time-series trends of performance and fandom growth rates by platform.

[0065] (4) When the predicted value of the fandom growth rate relative to the advertising expenditure received from the performance prediction module (30) is greater than or equal to the third standard value, the IP price of the specific content can be set as an output value by inputting the content type standard data, content performance indicator standard data, and the predicted value of the fandom growth rate relative to the advertising expenditure into the third value calculation artificial intelligence among the standard indicator data of multiple platforms for the specific content.

[0066] Since this corresponds to a phase where content characteristics, along with performance indicators, exert a significant leverage effect on IP prices—such as global hits or explosive growth—a third-party valuation AI is applied at this stage, utilizing standard data on content types, standard data on content performance indicators, and predicted fandom growth rates as inputs. This ensures that high-value IP evaluation is conducted by comprehensively considering qualitative factors such as genre and concept, as well as actual performance and growth rates.

[0067] In this way, by classifying into four cases based on the range of predicted fandom growth rates and selectively applying different valuation AIs, it is possible to effectively reflect the non-linear relationships that appear differently in low, medium, high, and ultra-high performance segments, and to prevent bias in specific segments or prediction distortions that may occur when using a single model, thereby improving the reliability and explanatory power of content IP pricing.

[0069] The method performed in the system (100) of the present invention described above may be implemented as a program (or application) to be executed in combination with a server, which is hardware, and stored on a medium.

[0070] The aforementioned program may include code encoded in a computer language such as C, C++, JAVA, or machine language, which can be read by the computer's processor (CPU) through the computer's device interface, in order for the computer to read the program and execute the methods implemented in the program. Such code may include functional code related to functions that define the necessary functions for executing the methods, and may include control code related to execution procedures necessary for the computer's processor to execute the functions according to a predetermined procedure. Additionally, such code may further include memory reference code regarding where (address) additional information or media necessary for the computer's processor to execute the functions should be referenced in the computer's internal or external memory. In addition, if the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the above functions, the code may further include communication-related code regarding how to communicate with any other computer or server located remotely using the communication module of the computer, and what information or media to transmit or receive during communication.

[0071] The above-mentioned storage medium refers to a medium that stores data semi-permanently and is readable by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the above-mentioned storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the above-mentioned program may be stored on various recording media on various servers that the computer can access, or on various recording media on the user's computer. Additionally, the above-mentioned medium may be distributed across networked computer systems, and computer-readable code may be stored in a distributed manner.

[0072] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0073] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive.

Claims

Claim 1 A data integration processing module that collects raw data from multiple platforms regarding specific content, converts it into ontology entities, and then standardizes it to generate standard metric data from multiple platforms regarding specific content; and a performance prediction module that processes advertising expenditure costs from multiple platforms and standard metric data from multiple platforms regarding specific content to predict the fandom growth rate relative to advertising expenditure costs. The method includes a valuation module that calculates the IP price of specific content by processing standard indicator data from multiple platforms for specific content and a predicted value of the fandom growth rate relative to advertising expenditure output from the performance prediction module. The raw data consists of data regarding the content artist, content type, and content performance indicator for specific content uploaded to multiple platforms. The ontology entities are defined as content artist entities, content type entities, and content performance indicator entities, with identifier attributes defined. The data integration processing module converts the raw data into ontology entities by using LLM to determine the meaning of the content artist in the raw data and map it to the identifier of the corresponding content artist entity, determine the meaning of the content type in the raw data and map it to the identifier of the corresponding content type entity, and determine the meaning of the content performance indicator in the raw data and map it to the identifier of the corresponding content performance indicator. The method then standardizes the ontology entities converted from the raw data to generate standard indicator data for multiple platforms, wherein the identifier of the content artist entity is reflected as is in the content artist standard data, the identifier of the content type entity is reflected as is in the content type standard data, and the identifier of the content performance indicator entity unifies the time unit across multiple platforms. The content performance indicator standard data is generated through a standardization process, and the performance prediction module above,An artificial intelligence trained with training data in which standard data on advertising expenditure costs, content types, and content performance indicators of multiple intercorrelated platforms are set as feature values, and the fandom growth rate relative to advertising expenditure is set as a label value, wherein when the current standard data on advertising expenditure costs, content types, and content performance indicators of multiple platforms are input into the performance prediction module in the data integration processing module, a predicted value of the fandom growth rate relative to advertising expenditure is output, and the value estimation module comprises: a first value estimation artificial intelligence trained with training data in which standard data on content types of multiple platforms for a specific intercorrelated content and a predicted value regarding the fandom growth rate relative to advertising expenditure are set as feature values, and the IP price of the specific content is set as a label value; a second value estimation artificial intelligence trained with training data in which standard data on content performance indicators of multiple platforms for a specific intercorrelated content and a predicted value regarding the fandom growth rate relative to advertising expenditure are set as feature values, and the IP price of the specific content is set as a label value; and standard data on content types of multiple platforms for a specific intercorrelated content and standard data on content performance indicators and the fandom relative to advertising expenditure of multiple platforms It includes a third value estimation AI trained with training data in which a predicted value for the growth rate is set as a feature value and the IP price of a specific content is set as a label value, and the value estimation module sets the IP price of the specific content as an output value obtained by inputting standard data on content types of multiple platforms for the specific content, standard data on content performance indicators, and a predicted value for the fandom growth rate relative to advertising expenditure received from the performance prediction module, when the predicted value for the fandom growth rate relative to advertising expenditure received is less than a first reference value.If the predicted value regarding the fandom growth rate relative to advertising expenditure received from the above performance prediction module is greater than or equal to the first threshold value and less than the second threshold value which is greater than the first threshold value, the IP price of the specific content is set using the output value obtained by inputting the standard data on content types across multiple platforms for the specific content and the predicted value regarding the fandom growth rate relative to advertising expenditure into the first valuation AI; if the predicted value regarding the fandom growth rate relative to advertising expenditure received from the above performance prediction module is greater than or equal to the second threshold value and less than the third threshold value which is greater than the second threshold value, the IP price of the specific content is set using the output value obtained by inputting the standard data on content performance indicators across multiple platforms for the specific content and the predicted value regarding the fandom growth rate relative to advertising expenditure into the second valuation AI; if the predicted value regarding the fandom growth rate relative to advertising expenditure received from the above performance prediction module is greater than or equal to the third threshold value, the IP price of the specific content is set using the output value obtained by inputting the standard data on content types across multiple platforms for the specific content, standard data on content performance indicators, and the predicted value regarding the fandom growth rate relative to advertising expenditure into the third valuation AI; and the above data integration processing The module collects data by utilizing a collection API to collect raw data from multiple platforms and setting a raw data update cycle, and uses LLM to determine the meaning of the content artist, the meaning of the content type, and the meaning of the content performance indicator in the raw data and maps them to pre-configured identifiers, and the identifier of the ontology entity includes ISRC or UPC as a unique identifier for content identification, and the standard data of content types, standard data of content performance indicators, and the predicted values ​​of the fandom growth rate relative to advertising expenditure included in the training data of the first value estimation AI, the second value estimation AI, and the third value estimation AI are actual historical data accumulated through the operation of the system, andA system characterized in that the IP price of specific content is a price calculated by actually commissioning a professional evaluation agency. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete

Images