Machine learning-based sns marketing performance analysis system

Abstract

A method performed in a machine learning-based SNS marketing performance analysis system according to one embodiment of the present disclosure may include: (a) collecting content and advertising data from a social media platform; (b) performing a preprocessing and cleaning step of the collected data; (c) predicting marketing performance using a machine learning model; (d) recommending an optimal content creator according to a marketing performance goal set by an advertiser; (e) performing real-time marketing performance monitoring and ROI analysis; and (f) providing feedback for advertising optimization based on the analyzed results.

Description

Technology Field

[0001] The present disclosure relates to a machine learning-based social media marketing performance analysis system. Background Technology

[0002] Social media has established itself as an essential element in modern marketing, and companies and individual advertisers are utilizing it to conduct various advertising campaigns. Compared to traditional advertising methods, marketing through social media offers the advantage of allowing for more direct interaction with consumers and the effective targeting of specific demographics.

[0003] However, measuring and analyzing the performance of social media marketing remains a challenging task. Existing performance analysis methods often rely on individual metrics such as ad reach, clicks, and conversion rates, and have limitations in comprehensively evaluating overall campaign performance.

[0004] Furthermore, advertisers face difficulties in selecting influencers suitable for each platform, and there are no clear criteria for objectively evaluating an influencer's influence. In particular, the existing method of measuring an influencer's effectiveness based solely on follower count can be inaccurate due to issues such as fake followers or low engagement rates.

[0005] Therefore, there is a need for a system that applies more sophisticated analysis techniques to effectively evaluate social media marketing performance and supports advertisers in establishing optimal marketing strategies. The problem to be solved

[0006] The present invention is a machine learning-based SNS marketing performance analysis system developed to solve the above-mentioned problems, and its main objectives are as follows.

[0007] Automation of Social Media Marketing Performance Analysis: By applying machine learning-based performance prediction models, it enables the automatic analysis of marketing effectiveness and the quantitative evaluation of campaign performance.

[0008] Provision of an accurate influencer recommendation system: Maximizes marketing performance by recommending optimal content creators through learning the characteristics of advertised products and social media user data.

[0009] Provides real-time marketing performance monitoring features: Allows for real-time tracking of social media advertising campaign progress and enables the establishment of optimized advertising strategies through ROI (Return on Investment) analysis utilizing machine learning.

[0010] Support for integration with various platforms: Collect marketing data in real-time through social media platforms (API integration or data crawling) and enable the analysis of performance differences by platform.

[0011] Through these features, advertisers can formulate more sophisticated and effective marketing strategies, and influencers can have their influence evaluated more objectively.

[0012] 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

[0013] A method performed in a machine learning-based SNS marketing performance analysis system according to one embodiment of the present disclosure may include: (a) collecting content and advertising data from a social media platform; (b) performing a preprocessing and cleaning step of the collected data; (c) predicting marketing performance using a machine learning model; (d) recommending an optimal content creator according to a marketing performance goal set by an advertiser; (e) performing real-time marketing performance monitoring and ROI analysis; and (f) providing feedback for advertising optimization based on the analyzed results. Effects of the invention

[0014] The machine learning-based SNS marketing performance analysis system according to the present invention can provide the effect of improving the accuracy of SNS marketing performance analysis. By utilizing machine learning algorithms more sophisticated than existing methods, performance metrics such as reach, conversion rate, and engagement can be predicted and measured more accurately, thereby enabling advertisers to secure more reliable performance data. Furthermore, it provides a function to recommend optimal influencers to advertisers. By analyzing follower characteristics, content tendencies, and engagement rates based on machine learning, the system automatically recommends content creators most suitable for the target audience, thereby maximizing marketing effectiveness.

[0015] Furthermore, it supports real-time performance monitoring and ad optimization features to analyze real-time data from marketing campaigns and automatically calculate ROI (Return on Investment), helping to establish more effective advertising strategies. Integration with various social media platforms is also possible. Through API integration, data can be collected from major social media platforms such as Facebook, Instagram, and YouTube, enabling cross-platform performance comparisons and allowing for broader analysis.

[0016] Furthermore, it can contribute to optimizing advertising budgets and maximizing performance. By utilizing machine learning algorithms to efficiently allocate advertising budgets and automatically recommending high-performing advertising channels, it supports achieving maximum effectiveness relative to advertising costs. Consequently, the present invention can contribute to maximizing marketing performance by maximizing the efficiency of social media marketing and supporting optimized matching between advertisers and content creators.

[0017] 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

[0018] The drawings are intended to aid in understanding the invention and illustrate specific embodiments, and do not limit the technical scope of the invention. FIG. 1 may be a configuration diagram of a machine learning-based SNS marketing performance analysis system according to one embodiment of the present invention. FIG. 2 may be a block diagram showing the detailed configuration of a machine learning-based marketing analysis server according to one embodiment of the present invention. FIG. 3 may be a diagram illustrating the overall structure of a machine learning-based marketing analysis service according to an embodiment of the present invention. FIG. 4 is a flowchart of a machine learning-based marketing performance analysis method according to an embodiment of the present invention. Specific details for implementing the invention

[0019] Various embodiments and / or aspects are now disclosed with reference to the drawings. For illustrative purposes, numerous specific details are disclosed in the following description to aid in a general understanding of one or more aspects. However, it will be apparent to those skilled in the art that these aspects may be practiced without such specific details. The following description and the accompanying drawings describe specific exemplary aspects of one or more aspects in detail. However, these aspects are exemplary, and some of the various methods in the principles of the various aspects may be used, and the descriptions are intended to include all such aspects and their equivalents. Specifically, terms such as “exemplary,” “example,” “aspect,” “example,” etc. as used herein may not be interpreted as implying that any described aspect or design is superior or advantageous to other aspects or designs.

[0020] Hereinafter, identical or similar components are assigned the same reference numeral regardless of drawing symbols, and redundant descriptions thereof are omitted. Furthermore, in describing the embodiments disclosed in this specification, detailed descriptions of related prior art are omitted if it is determined that such detailed descriptions may obscure the essence of the embodiments disclosed in this specification. Additionally, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification, and the technical concept disclosed in this specification is not limited by the attached drawings.

[0021] Although terms such as first, second, etc. are used to describe various elements or components, it goes without saying that these elements or components are not limited by these terms. These terms are used merely to distinguish one element or component from another. Therefore, it goes without saying that the first element or component mentioned below may be the second element or component within the technical scope of the present invention.

[0022] Unless otherwise defined, all terms used in this specification (including technical and scientific terms) may be used in a meaning that is commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0023] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items.

[0024] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that such features and / or components are present, but not to exclude the presence or addition of one or more other features, components, and / or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0025] When it is stated that one component is “connected” or “connected” to another component, it should be understood that it may be directly connected or connected to that other component, or that there may be other components in between. On the other hand, when it is stated that one component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

[0026] When elements or layers are referred to as being "on" or "on" another element or layer, it includes not only being directly on top of the other element or layer but also cases where another layer or element is interposed in between. On the other hand, when a component is referred to as being "directly on" or "immediately on," it indicates that no other element or layer is interposed in between.

[0027] Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" may be used to easily describe the relationship between one component or other components as illustrated in the drawings. Spatially relative terms should be understood as encompassing different orientations of the element during use or operation, in addition to the directions illustrated in the drawings.

[0028] The objectives and effects of the present invention, and the technical configurations for achieving them, will become clear by referring to the embodiments described in detail below in conjunction with the accompanying drawings. In describing the present invention, if it is determined that a detailed description of known functions or configurations may unnecessarily obscure the essence of the invention, such detailed description will be omitted. Furthermore, the terms described below are defined considering their functions in the present invention, and these may vary depending on the intentions or conventions of the user or operator.

[0029] 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 make the present invention complete and to fully inform those skilled in the art of the scope of the disclosure, and the present invention is defined only by the scope of the claims. Therefore, such definition should be based on the content throughout this specification.

[0030] FIG. 1 may be a configuration diagram of a machine learning-based SNS marketing performance analysis system according to one embodiment of the present invention.

[0031] Referring to FIG. 1, the machine learning-based SNS marketing performance analysis method according to an embodiment of the present invention may be executed on a fixed computing device that has sufficient storage capacity and can be connected to the Internet, such as a desktop computer, or on a portable terminal such as a mobile device. In this case, the machine learning-based SNS marketing performance analysis service may be executed after a software application in which the service is implemented is downloaded from an official app store and installed on the portable terminal.

[0032] In addition, the machine learning-based SNS marketing performance analysis service described above may be executed by connecting it to a computing device while stored on an external storage medium, or by copying it from the external storage medium to the internal storage of the computing device. For example, the external storage medium may be an optical disc, a semiconductor memory device, or an external hard disk.

[0033] Meanwhile, if the above computing device or portable terminal can connect to a cloud server, the machine learning-based SNS marketing performance analysis service can be executed on a cloud basis.

[0034] In one embodiment, the system may include a content creator terminal (110, 120), an advertising client terminal (130), and a machine learning-based marketing analysis server (140) (hereinafter, analysis server (140)). The system may also be linked with various social media platform servers.

[0035] The content creator terminal (110, 120) and the advertising client terminal (130) can be implemented as various types of computing devices. For example, they may be smartphones, tablet PCs, laptops, desktop computers, smart display devices, or wearable devices. As another example, the terminal may be an embedded system equipped with computing power and memory capable of executing machine learning models.

[0036] The analysis server (140) communicates with content creator terminals (110, 120) and advertising client terminals (130) via a network and may be implemented as one or more server computers that provide machine learning-based analysis services. The network may be a communication network including wired internet, wireless internet, mobile communication networks, and combinations thereof.

[0037] In one embodiment, the analysis server (140) may provide an installation file of a machine learning-based analysis application to terminals connected via a network. In this case, each terminal may install the application using the received installation file.

[0038] In another embodiment, the analysis server (140) may provide a cloud-based analysis service accessible through a web browser. In this case, a separate application installation may not be required on the terminal.

[0039] Wireless communication can be achieved through various short-range communication protocols. For example, communication protocols such as Wi-Fi, Bluetooth, BLE (Bluetooth Low Energy), UWB (Ultra-WideBand), and NFC (Near Field Communication) can be used.

[0040] FIG. 2 may be a block diagram showing the detailed configuration of a machine learning-based marketing analysis server according to one embodiment of the present invention.

[0041] Referring to FIG. 2, the analysis server (200) may include a communication module (210), a computation processor (220), and a database (230). Only the major components related to the embodiment are illustrated in this drawing, and those skilled in the art will understand that other general-purpose components not illustrated herein may be added.

[0042] The communication module (210) may include one or more communication interfaces that perform bidirectional data communication with terminals. For example, the communication module (210) may include a short-range communication unit, a mobile communication unit, or an Ethernet communication unit.

[0043] The database (230) may be a storage device that stores various data and machine learning models processed within the analysis server (200). In one embodiment, the database (230) may hierarchically include memory capable of high-speed access and a non-volatile storage device capable of large-capacity storage. For example, volatile memory such as DRAM and SRAM and non-volatile storage devices such as SSD and HDD may be hierarchically configured.

[0044] The computation processor (220) can control the overall operation of the analysis server (200) and perform machine learning computations. In one embodiment, the computation processor (220) may include a general-purpose CPU and a machine learning accelerator. In another embodiment, the computation processor (220) may be implemented with dedicated hardware such as an ASIC, FPGA, or neural network processor.

[0045] The database (230) can store a number of instructions executed by the computation processor (220). The instructions can implement the following functions:

[0046] It may include a function for receiving marketing performance target grades and advertising target product information from the advertising client's terminal, a function for selecting a group of content creators suitable for the target grade using a machine learning model, a function for recommending creators optimized for product characteristics within the selected group, and a function for supporting the conclusion of a contract between the matched advertiser and the creator.

[0047] Here, a machine learning model for content creator recommendations can analyze the following data: view statistics by gender and age group for each creator's posts, content creation history by product category, and average reach and engagement metrics over a certain period.

[0048] In one embodiment, the marketing performance target grade may define a performance standard relative to the market average. For example, the grade may be set based on key performance indicators (KPIs) such as reach, conversion rate, and engagement.

[0049] In another embodiment, the advertising request information may include campaign period and budget information. In this case, the budget information may be determined within a standard unit price range set for each performance target grade.

[0050] FIG. 3 may be a diagram illustrating the overall structure of a machine learning-based marketing analysis service according to an embodiment of the present invention.

[0051] Referring to FIG. 3, the service may include the following major functional areas:

[0052] Content Performance Analysis: Content performance by social media platform can be automatically measured and analyzed by utilizing machine learning algorithms. In one embodiment, the quality of content and brand suitability can be evaluated by combining text mining and image recognition technologies.

[0053] Traffic analysis: Through AI-based analysis of user behavior patterns, entry paths, dwell time, and conversion rates for each content can be measured. In one embodiment, a deep learning model can be used to predict users' interests and purchase intentions.

[0054] In another embodiment, the real-time ROI tracking system can automatically calculate and visualize the return on investment for each marketing channel. For example, a machine learning algorithm can calculate the ROI by integrating and analyzing advertising costs, reach, conversion rates, and sales data.

[0055] Influencer Analysis: Social media data can be collected to quantitatively evaluate the influence and engagement of influencers. In one embodiment, natural language processing technology can be utilized to analyze the sentiment of followers' comments and calculate an authenticity index.

[0056] FIG. 4 is a flowchart of a machine learning-based marketing performance analysis method according to an embodiment of the present invention.

[0057] FIG. 4 is a flowchart of a machine learning-based marketing performance analysis method according to an embodiment of the present invention.

[0058] Referring to FIG. 4, the machine learning-based marketing performance analysis method of the present invention may include a collection and initialization step (410), a machine learning analysis step (420), a performance goal matching step (430), a content creator recommendation step (440), and a real-time performance monitoring step (450).

[0059] The collection and initialization step (410) is a step of receiving marketing performance goals and budget information from the advertising client's terminal and collecting relevant data from various social media platforms.

[0060] In the collection and initialization step (410), the system may receive marketing performance goals and budget information from the advertising client's terminal. In this step, the system may collect relevant data from various social media platforms. In one embodiment, the system may collect data in real time via an API. In another embodiment, the system may periodically crawl and collect data.

[0061] The machine learning analysis step (420) is a step that evaluates the quality of content by combining text mining and image recognition technology and analyzes AI-based user behavior patterns. For example, deep learning models can be used to predict users' interests and purchase intentions.

[0062] In the machine learning analysis step (420), the system can evaluate the quality of the content by combining text mining and image recognition technology. Additionally, the system can analyze AI-based user behavior patterns. For example, the system can predict users' interests and purchase intentions by utilizing deep learning models. As another example, the system can analyze the sentiment of user reviews and comments using natural language processing technology.

[0063] The performance goal matching step (430) is a step of defining performance standards relative to the market average and setting target grades based on key performance indicators (KPIs) such as reach, conversion rate, and engagement. At this time, budget information can be determined within the standard unit price range set for each performance goal grade.

[0064] In the performance goal matching step (430), the system may define a performance standard relative to the market average. In this step, the system may set a target grade based on key performance indicators (KPIs) such as reach, conversion rate, and engagement. In one embodiment, the system may determine budget information within a standard unit price range set for each performance goal grade. In another embodiment, the system may propose an optimal budget allocation using a machine learning algorithm.

[0065] The content creator recommendation step (440) is a step of collecting social media data to quantitatively evaluate the influence and engagement of influencers and recommending creators optimized for product characteristics. In one embodiment, natural language processing technology can be used to analyze the sentiment of followers' comments and calculate an authenticity index.

[0066] In the content creator recommendation step (440), the system can collect social media data to quantitatively evaluate the influence and engagement of influencers. In this step, the system can recommend creators optimized for product characteristics. In one embodiment, the system can utilize natural language processing technology to analyze the sentiment of followers' comments and calculate an authenticity index. In another embodiment, the system can use image recognition technology to analyze the visual content style of influencers and evaluate brand suitability.

[0067] The real-time performance monitoring step (450) is a step for automatically calculating and visualizing the return on investment for each marketing channel. For example, a machine learning algorithm can calculate the ROI by integrating and analyzing advertising costs, reach, conversion rates, and sales data, and provide feedback for continuous performance improvement based on this.

[0068] In the real-time performance monitoring stage (450), the system can automatically calculate and visualize the return on investment for each marketing channel. For example, the system can calculate ROI by using machine learning algorithms to integrate and analyze advertising costs, reach, conversion rates, and sales data. As another example, the system can use a predictive model to predict future performance and provide optimization suggestions. Based on this, the system can provide feedback for continuous performance improvement.

[0069] In one embodiment, the marketing performance analysis system may provide the following automated analysis functions:

[0070] Trend Prediction: Through time series analysis and predictive modeling, future marketing trends can be predicted and optimal campaign timing recommended. For example, LSTM networks can be utilized to learn and predict performance patterns by season, day of the week, and time of day.

[0071] Competitor Analysis: A machine learning-based crawling system can monitor the social media activities of competitors and derive benchmarking insights. In one embodiment, computer vision technology can be utilized to analyze the visual content strategies of competitors.

[0072] In another embodiment, the target audience analysis system can derive optimal target segments by analyzing the profiles and behavioral data of social media users. For example, it can identify user groups with similar interests and purchasing patterns by utilizing a clustering algorithm.

[0073] Content Optimization: An AI-based content recommendation engine can learn past performance data to suggest optimal content formats and publishing strategies. In one embodiment, a reinforcement learning model can be utilized to optimize the timing and frequency of content publication.

[0074] Dashboard Visualization: A real-time data processing engine can integrate various performance indicators and present them as an intuitive dashboard. For example, the dashboard can automatically visualize insights derived from machine learning models and generate reports.

[0075] Automated A / B Testing: Machine learning algorithms can test combinations of various marketing variables and derive the optimal strategy. In one embodiment, test efficiency can be maximized by utilizing Bayesian optimization techniques.

[0076] Budget Optimization: A machine learning-based budget allocation system can automatically adjust the budget by channel by analyzing real-time performance data. In one embodiment, a budget allocation strategy that maximizes ROI can be derived by combining linear programming and reinforcement learning.

[0077] In another embodiment, the anomaly detection system can detect sudden changes or abnormal patterns in performance indicators in real time and provide notifications. For example, an anomaly detection algorithm can automatically detect changes such as a surge in traffic or a decline in engagement.

[0078] API Integration: The system can automatically collect and analyze data by linking with APIs of various social media platforms. In one embodiment, an ETL pipeline can collect, transform, and load data in real time for use in analysis.

[0079] Security and Compliance: Through data encryption and access control systems, marketing data can be secured and privacy regulations complied with. For example, by applying differential privacy technology, meaningful analytical results can be derived while protecting personal information.

[0080] Customized Reporting: Differentiated analysis reports can be automatically generated and distributed based on the user's role and authority. In one embodiment, data insights can be explained in natural sentences by utilizing a natural language generation model.

[0081] Collaboration Function: The system can support real-time collaboration among marketing team members. In one embodiment, a machine learning-based workflow optimization system can analyze the work patterns of team members and suggest efficient work distribution.

[0082] In another embodiment, the campaign performance prediction system can calculate the expected performance of future campaigns by comprehensively analyzing past data and market conditions. For example, an ensemble learning model can predict the probability of achieving KPIs by considering various variables.

[0083] Social Listening: Brand-related social media conversations can be monitored and analyzed in real time by utilizing natural language processing technology. In one embodiment, a sentiment analysis algorithm can quantify and measure consumer sentiment toward the brand.

[0084] Cross-Channel Attribution Analysis: Machine learning models can analyze interactions between various marketing channels to calculate the contribution of each touchpoint. For example, Markov chain models can be utilized to evaluate the influence of each channel in a complex customer journey.

[0085] Integrated CRM Integration: This system can integrate social media insights and customer data by linking with a company's CRM system. In one embodiment, a machine learning algorithm can derive personalized marketing strategies based on the integrated data.

[0086] Scalability Management: The system can flexibly adjust data processing capacity through a cloud-based scalable architecture. In one embodiment, an automatic scaling algorithm can optimize computing resources by monitoring system load.

[0087] In another embodiment, the multilingual analysis system can comprehensively analyze the performance of global marketing campaigns. For example, a multilingual natural language processing model can compare and analyze the performance of social media content written in different languages.

[0088] Continuous Learning: The machine learning models of this system can be automatically retrained whenever new data is collected to improve performance. In one embodiment, an online learning algorithm can update the model in real time to reflect the latest trends.

[0089] Methods according to the claims or embodiments described in the specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0090] When implemented in software, a computer-readable storage medium may be provided for storing one or more programs (software modules). One or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. One or more programs include instructions that cause the electronic device to execute methods according to the claims or embodiments described in the specification of this disclosure.

[0091] One or more of these programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), magnetic disc storage device, optical storage device (e.g., Compact Disc-ROM (CD-ROM), Digital Versatile Discs (DVDs)), magnetic cassette, or a combination thereof. Or, they may be stored in memory composed of some or all of these. Additionally, the above program may be stored on an attachable storage device accessible via a communication network such as the Internet, Intranet, Local Area Network (LAN), Wide LAN (WLAN), or Storage Area Network (SAN), or a combination thereof. Such a storage device may be connected to a device performing an embodiment of the present disclosure through an external port. Additionally, a separate storage device on a communication network may be connected to a device performing an embodiment of the present disclosure.

[0092] In the specific embodiments of the present disclosure described above, the components of the electronic device included in the present disclosure are expressed in a singular or plural form according to the specific embodiments presented. However, the singular or plural expression of said components is selected to suit the circumstances presented for convenience of explanation, and the present disclosure is not limited to singular or plural components; even if a component is expressed in the plural, it may be composed of a singular form, and even if a component is expressed in the singular form, it may be composed of a plural form.

[0093] Meanwhile, although specific embodiments have been described in the detailed description of the present disclosure, it is understood that various modifications are possible within the scope of the present disclosure. Therefore, the scope of the present disclosure should not be limited to the described embodiments, but should be defined by the claims set forth below as well as equivalents thereof.

[0094] The description of the presented embodiments is provided so that any person skilled in the art may use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the present invention. Thus, the present invention is not limited to the embodiments presented herein, but should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

Claims

Claim 1 A machine learning-based SNS marketing performance analysis method, characterized by comprising: (a) a step of collecting content and advertising data from a social media platform; (b) a step of performing a preprocessing and cleaning step of the collected data; (c) a step of predicting marketing performance using a machine learning model; (d) a step of recommending an optimal content creator according to a marketing performance goal set by an advertiser; (e) a step of performing real-time marketing performance monitoring and ROI analysis; and (f) a step of providing feedback for advertising optimization based on the analyzed results.

Images