User response analysis-based real-time monitoring and optimal combination selection and distribution-based marketing optimization apparatus

Abstract

The embodiments relate to a system and method for maximizing marketing efficiency by automatically matching marketing content and media according to customer preferences and optimizing the budget. In particular, it provides a function that analyzes behavior-based customer data to calculate preference scores for each content and medium, and automatically distributes matching scores and advertising budgets based on these scores and predicted costs.

Description

Technology Field

[0001] Embodiments of the present invention relate to a system and a method of operation that automatically matches marketing content and media channels based on customer preferences and marketing efficiency, and maximizes advertising efficiency through optimized cost distribution. Background Technology

[0003] Traditional marketing methods made it difficult to accurately identify customer preferences. Inefficiencies were prone to arising during the manual process of matching marketing content with media channels. Furthermore, the difficulty in optimizing advertising budget allocation led to reduced advertising efficiency, and the lack of immediate improvement through real-time performance feedback resulted in marketing waste. These factors lowered companies' return on investment (ROI) and made it difficult to provide personalized experiences to customers. The problem to be solved

[0005] The embodiments can provide a technology that enables efficient advertising execution by accurately evaluating customer preferences and automatically matching marketing content and media channels based on them.

[0006] The technical problems to be solved in the embodiments are not limited to those mentioned above, and other unmentioned technical problems may be considered by those skilled in the art from the various embodiments described below. means of solving the problem

[0007] According to embodiments, an electronic device is provided comprising: a memory; a communication unit; and at least one processor connected to the memory and the communication unit, wherein the processor collects raw customer data including web logs, CRM (Customer Relationship Management) data, social media activity data, or satisfaction response data from one or more external servers, analyzes the raw customer data to obtain refined customer data including content response data representing a customer's response to content and media response data representing a customer's response to media, evaluates a customer's preference for one or more content based on the content response data, evaluates a customer's preference for one or more media based on the media response data, calculates a predicted cost for one or more combination candidates consisting of pairs of each content and each media, and distributes a total advertising budget to each combination candidate based on the evaluation result of the customer's preference for one or more content, the evaluation result of the customer's preference for one or more media, and the predicted cost.

[0008] The processor can calculate a content preference score representing a customer's preference for one or more contents based on the content response data.

[0009] The above processor can calculate a media preference score representing a customer's preference for one or more media based on the media response data. Effects of the invention

[0010] According to the embodiments, by quantitatively evaluating customer preferences and optimally matching content and media based on them, marketing resources can be concentrated on the most effective combinations, thereby maximizing advertising efficiency. By efficiently distributing the total advertising budget by considering predicted costs and matching scores, unnecessary budget waste is reduced, and the campaign ROI (Return on Investment) is increased. Through conditional filtering based on content and media preference scores, unnecessary computations for low-priority combinations are eliminated, thereby drastically reducing the system computation load and improving processing speed.

[0011] The effects obtainable from the embodiments are not limited to those mentioned above, and other unmentioned effects can be clearly derived and understood by a person skilled in the art based on the detailed description below. Brief explanation of the drawing

[0013] The accompanying drawings, included as part of the detailed description to aid in understanding the embodiments, provide various embodiments and explain the technical features of the various embodiments together with the detailed description. FIG. 1 is a diagram showing the configuration of an electronic device according to one embodiment. FIG. 2 is a diagram showing the configuration of a program according to one embodiment. FIG. 3 is a diagram illustrating the overall configuration of a system according to one embodiment. FIG. 4 is a flowchart illustrating the operation of an electronic device according to one embodiment. FIG. 5 is a diagram illustrating an example of distributing total marketing costs to each combination according to one embodiment. Specific details for implementing the invention

[0014] The following embodiments are combinations of the components and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless otherwise explicitly stated. Each component or feature may be implemented in a form not combined with other components or features. Additionally, various embodiments may be constructed by combining some components and / or features. The order of operations described in various embodiments may be changed. Some components or features of one embodiment may be included in another embodiment, or may be replaced with corresponding components or features of another embodiment.

[0015] In the description of the drawings, procedures or steps that could obscure the essence of the various embodiments were not described, nor were procedures or steps that can be understood by a person of ordinary knowledge in the relevant technical field described.

[0016] Throughout the specification, when a part is described as "comprising" or "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "...part," "...unit," and "module" as used in the specification refer to a unit that performs at least one function or operation, and this may be implemented in hardware, software, or a combination of hardware and software. Additionally, "one (a or an)," "one," "the," and similar related terms may be used in the context describing various embodiments (particularly in the context of the following claims) in both singular and plural forms, unless otherwise indicated in the specification or clearly contradicted by the context.

[0017] Hereinafter, embodiments according to various examples will be described in detail with reference to the accompanying drawings. The detailed description disclosed below, together with the accompanying drawings, is intended to describe exemplary embodiments of various examples and is not intended to represent the only embodiment.

[0018] In addition, specific terms used in various embodiments are provided to aid in understanding the various embodiments, and the use of such specific terms may be modified in other forms within the scope of not departing from the technical concept of the various embodiments.

[0020] FIG. 1 is a diagram showing the configuration of an electronic device according to one embodiment.

[0021] FIG. 1 is a block diagram of an electronic device (101) in a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or may communicate with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through a server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)). The electronic device (101) may be referred to as a client, terminal, or peer.

[0022] The processor (120) can control at least one other component (e.g., hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., program (140)), for example, and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., sensor module (176) or communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., central processing unit or application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., graphics processing unit, neural processing unit (NPU), image signal processor, sensor hub processor, or communication processor). For example, if the electronic device (101) includes a main processor (121) and an auxiliary processor (123), the auxiliary processor (123) may be configured to use lower power than the main processor (121) or to be specialized for a designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0023] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or through a separate server (e.g., server (108)). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers.An artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0024] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, input data or output data for software (e.g., program (140)) and related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0025] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0026] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0027] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0028] The display module (160) can visually provide information to an external (e.g., user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling said device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of the force generated by said touch.

[0029] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0030] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0031] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0032] The connection terminal (178) may include a connector through which the electronic device (101) can be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0033] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0034] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0035] The power management module (188) can manage the power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0036] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0037] The communication module (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0038] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), full-dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large-scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), external electronic device (e.g., electronic device (104)), or network system (e.g., second network (199)). According to one embodiment, the wireless communication module (192) can support a Peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mMTC, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for realizing URLLC.

[0039] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module (197).

[0040] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0041] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0042] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) through a server (108) connected to a second network (199). Each of the external electronic devices (102, or 104) may be the same or different type of device as the electronic device (101). According to one embodiment, all or part of the operations performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within a second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0043] A server (108) is connected to an electronic device (101) and can provide services to the connected electronic device (101). Additionally, the server (108) may proceed with a membership registration process, store and manage various information of users who have registered as members accordingly, and provide various purchasing and payment functions related to the service. Furthermore, the server (108) may share execution data of service applications running on each of multiple electronic devices (101) in real time so that services can be shared among users. In terms of hardware, this server (108) may have the same configuration as a conventional web server or WAP server. However, in terms of software, it may include program modules that perform various functions and are implemented through any language such as C, C++, Java, Visual Basic, Visual C, etc. Additionally, the server (108) generally refers to a computer system that is connected to an unspecified number of clients and / or other servers through an open computer network such as the Internet, receives requests for task execution from clients or other servers, and derives and provides the results of the task, as well as computer software (server program) installed for this purpose. Furthermore, the server (108) should be understood as a broad concept that includes, in addition to the aforementioned server program, a series of application programs running on the server (108) and, in some cases, various databases (DB: Database, hereinafter referred to as "DB") built internally or externally. Accordingly, the server (108) classifies membership registration information and various information and data regarding games, stores them in the DB, and manages them; such DB can be implemented internally or externally of the server (108).Additionally, the server (108) can be implemented using server programs provided for various operating systems such as DOS, Windows, Linux, UNIX, and Macintosh on general server hardware. Representative examples include Website and IIS (Internet Information Server) used in Windows environments, and CERN, NCSA, and APPACH used in UNIX environments. Additionally, the server (108) may be linked with an authentication system and a payment system for user authentication of the service or purchase payment related to the service.

[0044] The first network (198) and the second network (199) refer to a connection structure capable of exchanging information between each node, such as terminals and servers, or a network connecting a server (108) and electronic devices (101, 104). The first network (198) and the second network (199) include, but are not limited to, the Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), 3G, 4G, LTE, 5G, Wi-Fi, etc. The first network (198) and the second network (199) may be closed types such as LAN, WAN, etc., but it is preferable that they be open types such as the Internet. The Internet refers to a global open computer first network (198) and second network (199) structure that provides the TCP / IP protocol and various services existing in the upper layer, namely HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), SNMP (Simple Network Management Protocol), NFS (Network File Service), and NIS (Network Information Service).

[0045] A database may have a general data structure implemented in the storage space (hard disk or memory) of a computer system using a database management program (DBMS). A database may have a data storage form that allows for the free retrieval (extraction), deletion, editing, and addition of data. A database may be implemented to suit the purpose of an embodiment of the present disclosure using a relational database management system (RDBMS) such as Oracle, Informix, Sybase, and DB2, an object-oriented database management system (OODBMS) such as Gemston, Orion, and O2, and an XML native database such as Excelon, Tamino, and Sekaiju, and may have appropriate fields or elements to achieve its functions.

[0047] FIG. 2 is a diagram showing the configuration of a program according to one embodiment.

[0048] FIG. 2 is a block diagram (200) illustrating a program (140) according to various embodiments. According to one embodiment, the program (140) may include an operating system (142), middleware (144), or an application (146) executable on the operating system (142) for controlling one or more resources of an electronic device (101). The operating system (142) may include, for example, Android™, iOS™, Windows™, Symbian™, Tizen™, or Bada™. At least some of the programs (140) may be preloaded into the electronic device (101) at manufacturing time, for example, or downloaded or updated from an external electronic device (e.g., electronic device (102 or 104), or server (108)) when used by a user. All or part of the program (140) may include a neural network.

[0049] The operating system (142) can control the management (e.g., allocation or reclamation) of one or more system resources (e.g., processes, memory, or power) of the electronic device (101). The operating system (142) may additionally or substantially include one or more driver programs for driving other hardware devices of the electronic device (101), e.g., an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197).

[0050] Middleware (144) may provide various functions to an application (146) so that functions or information provided from one or more resources of an electronic device (101) can be used by the application (146). Middleware (144) may include, for example, an application manager (201), a window manager (203), a multimedia manager (205), a resource manager (207), a power manager (209), a database manager (211), a package manager (213), a connectivity manager (215), a notification manager (217), a location manager (219), a graphics manager (221), a security manager (223), a call manager (225), or a voice recognition manager (227).

[0051] The application manager (201) can, for example, manage the life cycle of the application (146). The window manager (203) can, for example, manage one or more GUI resources used on the screen. The multimedia manager (205) can, for example, identify one or more formats required for the playback of media files and perform encoding or decoding of the corresponding media files among the media files using a codec that matches the selected corresponding format. The resource manager (207) can, for example, manage the source code of the application (146) or the memory space of the memory (130). The power manager (209) can, for example, manage the capacity, temperature, or power of the battery (189) and, using the relevant information, determine or provide relevant information required for the operation of the electronic device (101). According to one embodiment, the power manager (209) can interact with the BIOS (basic input / output system) (not shown) of the electronic device (101).

[0052] The database manager (211) can, for example, create, search, or modify a database to be used by the application (146). The package manager (213) can, for example, manage the installation or update of the application distributed in the form of a package file. The connectivity manager (215) can, for example, manage a wireless or direct connection between the electronic device (101) and an external electronic device. The notification manager (217) can, for example, provide a function to notify the user of the occurrence of a specified event (e.g., an incoming call, a message, or an alarm). The location manager (219) can, for example, manage location information of the electronic device (101). The graphics manager (221) can, for example, manage one or more graphic effects or related user interfaces to be provided to the user.

[0053] The security manager (223) may, for example, provide system security or user authentication. The telephony manager (225) may, for example, manage voice call functions or video call functions provided by the electronic device (101). The voice recognition manager (227) may, for example, transmit user voice data to the server (108) and receive from the server (108) a command corresponding to a function to be performed on the electronic device (101) based on at least part of the voice data, or text data converted based on at least part of the voice data. According to one embodiment, the middleware (244) may dynamically delete some existing components or add new components. According to one embodiment, at least part of the middleware (144) may be included as part of the operating system (142) or implemented as separate software different from the operating system (142).

[0054] The application (146) may include, for example, a home (251), a dialer (253), an SMS / MMS (255), an IM (instant message) (257), a browser (259), a camera (261), an alarm (263), a contact (265), a voice recognition (267), an email (269), a calendar (271), a media player (273), an album (275), a watch (277), a health (279) (e.g., measuring biometric information such as exercise volume or blood sugar), or an environmental information (281) (e.g., measuring atmospheric pressure, humidity, or temperature information). According to one embodiment, the application (146) may further include an information exchange application (not shown) capable of supporting information exchange between the electronic device (101) and an external electronic device. The information exchange application may include, for example, a notification relay application configured to transmit information (e.g., a call, a message, or an alarm) designated to an external electronic device, or a device management application configured to manage the external electronic device. The notification relay application may transmit notification information corresponding to a designated event (e.g., receiving mail) generated in another application of the electronic device (101) (e.g., an email application (269)) to the external electronic device. Additionally or alternatively, the notification relay application may receive notification information from the external electronic device and provide it to the user of the electronic device (101).

[0055] A device management application can control the power (e.g., turn-on or turn-off) or function (e.g., brightness, resolution, or focus) of an external electronic device or a part of its components (e.g., a display module or camera module of the external electronic device) that communicates with the electronic device (101). The device management application can additionally or substantially support the installation, deletion, or updating of applications running on the external electronic device.

[0056] Throughout this specification, the terms neural network, neural network, and network function may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may generally be referred to as "nodes." These "nodes" may also be referred to as "neurons." A neural network is composed of at least two nodes. The nodes (or neurons) constituting neural networks may be interconnected by one or more "links."

[0057] In a neural network, two or more nodes connected via links can form a relative relationship between an input node and an output node. The concepts of input and output nodes are relative; any node in an output node relationship with respect to one node may be in an input node relationship with respect to another node, and vice versa. As previously mentioned, the input node versus output node relationship can be generated based on links. One or more output nodes may be connected to a single input node via links, and vice versa.

[0058] In a relationship between an input node and an output node connected through a single link, the value of the output node can be determined based on data input to the input node. Here, the nodes interconnecting the input node and the output node may have weights. The weights may be variable and may be varied by a user or an algorithm to enable the neural network to perform the desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node value may be determined based on the values ​​input to the input nodes connected to the output node and the weights set on the links corresponding to each input node.

[0059] As described above, a neural network is formed in which two or more nodes are interconnected through one or more links to create input-output node relationships within the network. The characteristics of a neural network can be determined by the number of nodes and links within the network, the relationships between the nodes and links, and the weight values ​​assigned to each link. For example, if two neural networks exist with the same number of nodes and links but different weight values ​​between the links, the two neural networks can be recognized as being different from each other.

[0061] FIG. 3 is a diagram illustrating the overall configuration of a system according to one embodiment.

[0062] According to one embodiment, the system can automatically match and distribute marketing content and media channels based on customer preferences, and maximize advertising efficiency through cost optimization and real-time performance feedback.

[0063] The system is organically linked with multiple external servers (331, 333, 335) and customer terminals (341~346) connected thereto through a network (320) centered on an electronic device (310), and based on this structure, the electronic device (310) performs preference evaluation and matching score calculation using collected customer data, and thereby performs the role of quantitatively analyzing and efficiently distributing total marketing costs.

[0064] First, customer terminals (341–346) generate various behavior-based data such as user clicks, viewing time, purchase history, and reaction patterns, and this information is transmitted to an electronic device (310) via an external server (331, 333, 335). The electronic device (310) collects this customer data in real-time or asynchronously and quantifies each customer's content consumption patterns, media usage paths, and reaction sensitivity through an internal profiling algorithm or AI model. The results of this analysis are converted into preference indices by content or media and serve as the basis for deriving matching scores in the form of content-media combinations.

[0065] This matching score is a numerical indicator of how effectively specific content can reach customers through a specific medium, allowing for the prediction of marketing efficiency for each combination in advance. The electronic device (310) performs an optimization operation to distribute resources in proportion to this matching score under a budget constraint of total marketing costs. For example, the ROI of the entire campaign can be maximized by allocating relatively high costs to content-medium combinations with high matching scores, and suppressing or excluding cost allocation to combinations with low efficiency.

[0066] The electronic device (310) transmits this result to an external server (331-335) so that it is reflected in actual marketing execution. Subsequently, the external server provides customized content or advertisements to the corresponding customer terminals, collects the customer's response to the provided result, and returns it to the electronic device (310) as feedback data.

[0067] Through this process, the entire system evolves beyond simply transmitting content to quantitatively considering actual user preferences and media reachability, focusing costs on the most effective combinations. This reduces marketing waste, increases conversion rates, and provides personalized customer experiences, thereby simultaneously enhancing corporate marketing efficiency and customer satisfaction.

[0068] To this end, according to one embodiment, the system may include an electronic device (310), a network (320), one or more external servers (331, 333, 335), and one or more customer terminals (341, 342, 343, 344, 345, 346) connected to each external server (331, 333, 335). Here, the electronic device (310) may correspond to the electronic device (101) of FIG. 1. The network (320) may correspond to the second network (199) of FIG. 1. The external servers (331, 333, 335) may correspond to the server (108) of FIG. 1.

[0069] According to one embodiment, the electronic device (310) may include one or more memories, one or more processors, and a communication unit in terms of hardware. The memory corresponds to the memory (130) of FIG. 1, the processor corresponds to the processor (120) of FIG. 1, and the communication unit corresponds to the communication module (190) of FIG. 1.

[0070] According to one embodiment, the electronic device (310) may include a data collection unit, a profiling unit, an optimization engine, a distribution module, a monitoring unit, and a feedback engine in terms of processing operations. The data collection unit, the profiling unit, the optimization engine, the distribution module, the monitoring unit, and the feedback engine may be implemented in various ways at the hardware and software layers according to the system architecture design. First, each of these components may exist as a single physical processor integrated in hardware. In this case, all functions are concentrated in a single central processing unit (CPU) or system-on-chip (SoC), and each function is implemented as a logically separated software module. For example, the data collection unit is executed as a module associated with a specific I / O handler, and the profiling unit is driven by thread-based software that includes an algorithm for refining and analyzing collected data. At this time, each unit is isolated at the level of a thread, process, or container and may be operated in parallel through resource allocation and scheduling at the OS level.

[0071] On the other hand, depending on system scalability, processing performance, or security requirements, each component may be deployed on its own dedicated hardware processor. In this case, each unit runs on an independent processor—for example, an independent node within a multi-server environment or cluster structure—and each processor may be a physically separated device or a logical device based on virtualization technology. In such cases, each unit is interconnected via network or bus-based communication and transmits and receives data through REST APIs, message queues, RPC, gRPC, or Pub / Sub systems. For example, the data collection unit may be implemented by a web server or IoT gateway, the profiling unit may run on a dedicated data analysis server utilizing GPUs, and the optimization engine runs on a high-performance processor capable of handling large-scale computations. The distribution module operates independently in conjunction with a Content Delivery Network (CDN) or cloud edge nodes, and the monitoring unit and feedback engine may operate independently in separate processor environments based on a log collection system, an alert system, or an AI-based feedback loop structure.

[0072] The terms below are defined as follows.

[0073] Raw customer data refers to web logs, CRM (Customer Relationship Management) data, social media activity data, or satisfaction response data collected from one or more external servers. This is customer information in its raw, unprocessed form among various behavior-based data generated from customer devices, and may include user click records, website visit logs, social media posts and comments, purchase history and inquiry records recorded in customer relationship management systems, and survey response data.

[0074] CRM data refers to all customer-related information collected by a company to manage and improve relationships with customers. It is a type of raw customer data that includes customers' personal information, purchase history, service usage history, consultation records, complaints, preferred product or service types, and more.

[0075] Social media activity data refers to all data generated by or interacted with by customers on social media platforms. It is a type of raw customer data that includes customer posts, likes, comments, shares, follow / follower information, viewing time for specific content, ad click records, and more.

[0076] Satisfaction response data is explicit feedback data directly provided by customers to express their satisfaction with a product or service. It is a type of raw customer data that includes customer survey responses, ratings, reviews, and feedback form submissions.

[0077] Refined customer data is data that includes content response data and media response data obtained by analyzing raw customer data. It is structured information regarding customer behavior patterns obtained by removing unnecessary or redundant information from raw customer data and processing it into a form suitable for analysis, and it may include meaningful indicators extracted based on raw data, such as the number of times specific content was clicked, the time spent exposed on the media, and ratings assigned by users.

[0078] Content response data is a type of refined customer data that refers to quantitative metrics regarding how customers interacted with specific marketing content. It includes viewing time, user ratings, content click counts, and content impressions.

[0079] Watch time is a metric included in content response data that refers to the total time customers actually spent watching specific video content, indirectly indicating their level of engagement and interest in the content.

[0080] User ratings are metrics included in content response data and refer to satisfaction scores or feedback explicitly given by customers regarding specific content. These can include star ratings given on a scale of 0 to 5, reactions such as 'like' or 'dislike', review text, etc.

[0081] Content click count is a metric included in content response data, referring to the total number of times specific content (e.g., ad banners, article links) is actually clicked after being exposed to customers.

[0082] Content impressions is a metric included in content response data, referring to the total number of times specific content (e.g., advertisements, posts) appeared on a customer's screen and was recognized by the customer.

[0083] Media response data is a type of refined customer data that refers to quantitative indicators regarding how customers interacted with specific marketing media (platforms, channels). It includes the number of media impressions, the time of the last exposure, and the number of times the media was shared.

[0084] Media exposure count is an indicator included in media response data, referring to the total number of times a specific medium (e.g., Instagram feed, YouTube channel) is exposed to customers.

[0085] The time of last media exposure is an indicator included in media response data that refers to the point in time when a customer last interacted with a specific medium, serving as a criterion for judging the recency of media usage.

[0086] The number of shares is an indicator included in media response data, referring to the total number of times a specific medium (or content within the medium) is recommended to or spread to others by customers.

[0087] Predicted cost is the cost calculated for one or more candidate combinations consisting of pairs of each content and each medium. It refers to the estimated marketing expenditure calculated based on expected click-through rates (CTR), conversion rates, unit costs (CPM / CPC, etc.), etc., when executing marketing through a specific content-medium combination.

[0088] The content preference score is a score representing a customer's preference for one or more pieces of content based on content response data. It is an indicator that quantifies the likelihood of a customer preferring a specific piece of content as a value between 0 and 1, and is calculated by comprehensively considering factors such as customer viewing time, user ratings, and content click-through rates.

[0089] The media preference score is a score that indicates a customer's preference for one or more media based on media response data. It is an indicator that quantifies the likelihood of a customer preferring a specific media (platform / channel) as a value between 0 and 1, and is calculated by comprehensively considering factors such as media exposure frequency, the time of recent exposure, and the degree of social sharing.

[0091] FIG. 4 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0092] According to one embodiment, in operation (401), the processor may collect raw customer data including web logs, CRM (Customer Relationship Management) data, social media activity data, or satisfaction response data from one or more external servers.

[0093] The data collection unit can collect customer web logs, CRM data, social media activity, survey responses, etc., in real time. The data collection unit can collect raw customer data from customer web logs, CRM data, social media activity, survey responses, etc. The collected data is input into the profiling unit and optimization engine in subsequent stages.

[0094] According to one embodiment, in operation (403), the processor can analyze the raw customer data to obtain refined customer data including content response data representing the customer's response to content and media response data representing the customer's response to media.

[0095] The profiling unit can obtain content response data indicating customer reactions to content by analyzing raw customer data. The profiling unit can obtain viewing time, user ratings, content click counts, and content impression counts by analyzing raw customer data.

[0096] The profiling unit can obtain media response data indicating customer reactions to the media by analyzing raw customer data. The profiling unit can obtain the number of media exposures, the time of the last media exposure, and the number of media shares by analyzing raw customer data.

[0097] According to one embodiment, in operation (405), the processor may evaluate a customer's preference for one or more contents based on the content response data. The profiling unit may calculate a content preference score representing a customer's preference for one or more contents based on the content response data, which includes viewing time, the user evaluation, the number of clicks on the content, and the number of exposures to the content.

[0098] The profiling department can calculate content preference scores through the following three main steps.

[0099] In the first step, the profiling unit can analyze viewing time. The profiling unit can obtain the total viewing time of the relevant content. The profiling unit can normalize the measured viewing time by comparing it to a preset maximum viewing time (e.g., 3600 seconds) to a ratio between 0 and 1. If the actual viewing time exceeds the maximum viewing time, it can be considered as 1. The profiling unit can calculate a preference score for viewing time by applying a first parameter to the normalized viewing time and then applying it to a specific function. This function can serve to smoothly adjust the change in preference between short and long viewing times. The first parameter can control the sensitivity of the change in preference according to the normalized viewing time. The larger the value of the first parameter, the greater the change in preference can be even with short changes in viewing time.

[0100] The profiling unit can analyze user evaluations. The profiling unit can collect user evaluation scores for the relevant content. For example, the evaluation scores may have a scale of 0 to 5 points. The profiling unit can normalize the collected evaluation scores to values ​​between 0 and 1. For example, the profiling unit can transform a 5-point scale by dividing it into 1 / 5 increments. The profiling unit can calculate a preference score for user evaluations by applying a second parameter to the normalized evaluation scores and then applying it to a specific function. This function may have the characteristic of assigning high scores to moderate evaluations and low scores to extreme evaluations. The second parameter is a factor that determines the periodic influence of user evaluations on preference, and may ensure maximum preference when the evaluation score is at a median value.

[0101] The profiling unit can analyze the click-through rate (CTR). It can collect the number of times the relevant content was displayed and the number of times users actually clicked on it. The profiling unit can calculate the CTR by dividing the number of clicks by the number of displays. If the CTR exceeds 1, it can be considered as 1. The profiling unit can calculate a preference score for the CTR by applying the calculated CTR to a specific function. This function assigns a high preference score to high CTRs, and the sensitivity of this increase can be determined by a third parameter. The third parameter is a factor that controls the sensitivity of preference changes based on the CTR. The higher the value, the lower the preference remains at low CTRs, but it can increase rapidly above a certain CTR level.

[0102] In the second step, the profiling unit can calculate a single final content preference score by combining the preference scores for the three features (watch time, user ratings, and click-through rate) calculated in the first step. The profiling unit can assign equal weights to the preference scores for each feature. The profiling unit can obtain the final content preference score by adding all the preference scores multiplied by their respective weights and dividing the sum by the total sum of the weights.

[0103] In the third step, the profiling unit can output the content preference score calculated in the second step. The content preference score has a value between 0 and 1, and this value may represent the user's overall preference for the content. The closer it is to 1, the higher the likelihood that the user will prefer the content.

[0104] Through this process, the profiling department analyzes various user behavior data for each piece of content and synthesizes it to derive preference scores that can be used for personalized content recommendations.

[0105] For example, the profiling department can calculate the content preference score using the following mathematical formula 1.

[0106] [Mathematical Formula 1]

[0107]

[0108] is normalized viewing time, and , seconds (0~60 minutes), First -> It can be calculated as.

[0109] is an explicit rating, which can be normalized to a 1 / 5 scale after the user evaluates it on a 0–5 point scale, and It has the range of.

[0110] represents the click-through rate, calculated as min(clicks / impressions,1), and It has a range of but is generally distributed between 0 and 0.2.

[0111] α is the first parameter and can adjust the sensitivity of preference changes according to normalized viewing time. The larger the value, the greater the change in preference can be even with short changes in viewing time. The first parameter is a factor that adjusts the relationship between normalized viewing time and the arctangent function, and has a range of 1 to 5.

[0112] is a second parameter that determines the period of the periodic influence of user ratings on preference, and can ensure maximum preference when the rating score is at the median value. The second parameter is a factor that controls the relationship between the explicit rating and the sine function, and can be, for example, ð.

[0113] γ is the third parameter and is a factor that controls the sensitivity of preference changes according to the click-through rate. The higher the value, the lower the preference remains at low click-through rates, but it can increase rapidly above a certain level. As a factor determining the exponential decay rate of the click-through rate, it ranges from 2 to 10.

[0114] This content preference score model can comprehensively evaluate content preference by utilizing three important user behavior indicators: watch time, user ratings, and click-through rates. Each indicator undergoes a non-linear transformation to be converted into a preference score between 0 and 1, and their average value represents the final content preference. In particular, user ratings are characterized by high preference at the midpoint. This model can be utilized in content recommendation systems to recommend content more suitable for users.

[0115] According to one embodiment, the profiling unit can compare the content preference score with a first threshold. If the content preference score is greater than or equal to the first threshold, the profiling unit can perform an operation (407).

[0116] The profiling unit can automatically filter low-priority combinations by calculating media preference only when the content preference score is above a threshold, and otherwise setting the media preference to 0. For example, the first threshold may be 0.5. If the threshold is not met, the profiling unit registers the content to a content remarketing notification trigger or a review queue to induce additional content creation or improvement work.

[0117] This process can proceed in the following order. The profiling unit calculates the content preference P_c(c) and temporarily stores it. The profiling unit threshold Compared to _c (e.g., 0.5), P_c(c) >= It can determine whether it is _c.

[0118] Condition satisfied (P_c(c) >= In the case of _c), the profiling unit can calculate the media preference score P_m(m). The profiling unit can output the media preference score P_m(m) by performing a numerical-based weighted evaluation of content-media interaction based on the content ID and media-specific interaction data. The profiling unit can register the corresponding combination in the priority recommendation queue. The profiling unit can calculate and register queue priorities based on the content ID, media ID, P_c(c), and P_m(m), and register the content-media combination in the priority recommendation queue. The profiling unit can execute the transmission of logs and notifications to the operator dashboard. The profiling unit can perform real-time log and operator notification transmission by configuring notification messages based on the content ID and log messages and then transmitting them to the dashboard.

[0119] Condition not met (P_c(c) < In the case of _c), the profiling unit can omit media preference calculations and filter the corresponding combinations. The profiling unit can exclude the corresponding content-media combination from recommendations based on the content ID. The corresponding content-media combination can be removed from the priority list. The profiling unit can trigger content remarketing notifications and register for a review queue. Based on the content ID, the profiling unit can activate the remarketing queue and review notifications by flagging the content as a remarketing candidate and executing notifications. The profiling unit can call the AI-based content improvement suggestion module to generate revision proposals. Based on content IDs with poor user response, the profiling unit can use AI to analyze content composition, title, thumbnail, and narrative elements to derive improvement proposals and send them to the operator.

[0120] The content preference score is a key criterion that quantitatively evaluates the likelihood of a specific piece of content receiving a positive response from users, serving as the first gateway and filter of the overall content-media matching structure. The subsequent step of calculating media preference is performed only if the content preference is above a pre-set threshold; otherwise, the media preference itself is set to 0, and the corresponding combination is automatically filtered out. This allows for the efficient allocation of system resources and eliminates unnecessary computations for low-priority combinations.

[0121] The profiling unit calculates a content preference score based on the user's viewing time, rating, click-through rate, etc., temporarily stores this value, and compares it with a threshold (e.g., 0.5). Conditional branching is performed based on this comparison, and only content that meets the conditions can proceed to the next stage. If the conditions are met, the content becomes subject to media preference calculation, and a full evaluation is conducted to calculate the final combination score. This combination is first registered in the recommendation queue, and logs and notifications are automatically sent to the operator dashboard, enabling real-time monitoring.

[0122] Conversely, content that does not meet the criteria is automatically filtered without media preference calculations and subsequently branches into two paths. One path triggers a content remarketing notification, attempting to re-expose the same content after a certain period or changing targeting conditions to reach new user groups. The other path places the content in a review queue, allowing for analysis and improvement of the content quality itself. Content in the review queue is integrated with an AI-based improvement suggestion module to automatically generate revision proposals across various aspects, such as title, composition, thumbnail, and format, enabling operators to redesign the content based on these results.

[0123] This conditional calculation structure significantly reduces the computational load of the entire marketing recommendation system and prevents unnecessary budget waste, thereby providing a foundation for concentrating resources on high-quality content. Furthermore, by integrating remarketing and AI improvement routines into an automated workflow, it drives improvements in the quality of the content itself, playing a role in enhancing the overall content ecosystem of the system. In other words, the content preference score is not merely a filtering criterion, but a benchmark for comprehensive judgment that connects to subsequent media evaluation, budget allocation, and recommendation strategies; centering on this, a strategic cycle of automated filtering -> remarketing -> improvement is organically established.

[0124] Through this, the profiling unit can reduce system computational load and improve processing speed. The profiling unit can prevent budget waste and concentrate the distribution of high-quality content. The profiling unit can improve content quality through automated remarketing and improvement workflows.

[0125] According to one embodiment, in operation (407), the processor may evaluate a customer's preference for one or more media based on the media response data. The profiling unit may calculate a media preference score representing a customer's preference for one or more media based on the media response data, which includes the number of times the media is exposed, the time of the last exposure of the media, and the number of times the media is shared.

[0126] The profiling department can calculate the media preference score through the following three main steps.

[0127] In the first step, the profiling unit can analyze three characteristics of a specific medium, namely exposure frequency, the time of recent exposure, and the degree of social sharing, respectively, and convert the preference score for each characteristic into a value between 0 and 1.

[0128] First, the profiling unit can perform an exposure frequency analysis. First, the profiling unit identifies the total number of times the medium has been exposed to users. The profiling unit can normalize the identified number of exposures by comparing them to a preset maximum number of exposures (e.g., 1,000) into a ratio between 0 and 1. If the actual number of exposures exceeds the maximum number of exposures, it can be considered as 1. The profiling unit can calculate a preference score for exposure frequency by applying a fourth parameter to the normalized exposure frequency ratio and then applying it to a specific function. This function can model the tendency to assign high scores to appropriate levels of exposure frequency and low scores to exposure frequencies that are too low or too high. The sensitivity of this change in preference can be determined according to the fourth parameter.

[0129] Next, the profiling unit can analyze the time of recent exposure. The profiling unit can measure the time elapsed since the media was last exposed to a user. The profiling unit can calculate a recency indicator using the measured elapsed time. This indicator has a higher value the more recent the time of the last exposure, and may decrease over time. The profiling unit can calculate a preference score for the time of recent exposure by applying the fifth parameter to the calculated recency indicator and then applying it to a specific function. This function reflects a preference for a specific pattern regarding the time of recent exposure, and the period of this pattern can be determined according to the fifth parameter.

[0130] Finally, the profiling unit can analyze the degree of social sharing. The profiling unit can measure how much the medium has spread through friend recommendations or sharing. The profiling unit can normalize the measured number of shares to a value between 0 and 1. The profiling unit can calculate a preference score for the degree of social sharing by applying the normalized social sharing index to the sixth parameter and then applying it to a specific function. This function assigns a high preference score to a high degree of sharing, and the sensitivity of this increase can be determined according to the sixth parameter.

[0131] In the second step, the profiling unit can calculate a final media preference score by combining the preference scores for the three features (exposure frequency, time of recent exposure, and degree of social sharing) calculated in the first step. The profiling unit can assign equal weights to the preference scores for each feature. The profiling unit can add up all the preference scores multiplied by their respective weights. The profiling unit can obtain the media preference score by dividing the added score by the total sum of the weights (3).

[0132] In the third step, the profiling unit can output the finally calculated media preference score. The media preference score has a value between 0 and 1, and this value may represent the user's overall preference for the media. The closer it is to 1, the higher the likelihood that the user will prefer the media.

[0133] The profiling department can calculate the media preference score using the following mathematical formula 2.

[0134] [Mathematical Formula 2]

[0135]

[0136] is the normalized exposure frequency and can be calculated as min(number of media exposures / Emax,1), for example, It can be set to 1000 times. It can have a range of.

[0137] is a recency indicator, and It is calculated as, may refer to the elapsed time (0–24h) since the last exposure. For example, δ could be 0.1, and It can have a range of [0,1].

[0138] represents the social sharing index and can be calculated by measuring the number of friend recommendations and shares from 0 to 100 and then normalizing it. It can have a range of [0,1].

[0139] α' is the fourth parameter that determines the logistic slope, and can be, for example, 5. ' is the fifth parameter that performs cosine periodic control and can be, for example, 1. γ' is the sixth parameter that represents exponential sensitivity and can be, for example, 3.

[0140] Through this process, the profiling unit analyzes various user behavior data for each medium and synthesizes them to derive a preference score that can be used for personalized media recommendations. This media preference calculation model quantitatively evaluates a user's media preference by considering three important factors (exposure frequency, recency, and social sharing index). Each factor is converted into a preference score between 0 and 1 through appropriate functions and hyperparameters, and the average of these values ​​can be determined as the final media preference. Particularly noteworthy is the setting where preference decreases as the recency indicator increases; this model can be utilized in personalized media recommendation systems by integrating various user behavior data.

[0141] According to one embodiment, the profiling unit can compare the media preference score with a second threshold. If the media preference score is greater than or equal to the second threshold, the profiling unit can perform an operation (407).

[0142] Regarding combinations of content and media, the profiling unit can generate combination candidates and proceed to the marketing cost prediction stage only if the media preference is above a pre-set second threshold. If the condition is not met, the corresponding combination may be filtered out in advance and moved to the retargeting target queue. The profiling unit can receive a list of content-media combination candidates and preference scores for each media and compare them with the second threshold. The second threshold can be set, for example, to 0.3. For each media, the profiling unit can compare the media preference score with the second threshold and perform branching processing depending on whether the condition is met.

[0143] If the conditions are met, the profiling unit can forward the corresponding content-media combination to the combination candidate generation and cost prediction stage. The profiling unit can register the combination in the priority recommendation queue. The profiling unit can perform log recording and send notifications to the operator dashboard.

[0144] If the conditions are not met, the profiling unit can immediately filter the corresponding combination. The profiling unit can execute a content remarketing target notification trigger and add the media to the review queue.

[0145] The media preference score is a key criterion that numerically evaluates whether a combination of content and media can lead to actual marketing performance. Only when this score exceeds a pre-set threshold is a combination recognized as a candidate and proceeds to the subsequent stages of cost forecasting and marketing resource allocation; if the conditions are not met, the combination is immediately filtered out. At this stage, filtered combinations are not simply discarded but are strategically registered in the retargeting queue or review queue, leaving open the possibility of future utilization.

[0146] The retargeting queue functions to preserve content-media combinations whose media preference scores fall below a second threshold but are deemed to have a potential for re-conversion based on changes in target conditions or timing. This queue records the content ID, media ID, response metrics at the time (e.g., low click-through rate, time to drop), user cluster tags, and filtering reason codes. Registered combinations are reviewed again under the same conditions after a certain period, or become targets for retries with some target conditions (e.g., age group, region, time of exposure, etc.) modified. This process is also utilized as training data for machine learning-based retargeting models, enabling system self-optimization alongside long-term algorithm refinement.

[0147] In contrast, the review queue is intended to re-analyze quality degradation or strategic incompatibility inherent in the content or media itself, rather than a single combination. Items are moved to the review queue if the same content repeatedly fails to meet criteria across multiple media, or if a single medium exhibits poor performance across most content combinations. This queue stores metadata such as content topic, length, format, registration date, recent click-through rates, bounce rates, and user feedback, and is subject to analysis by operators or automated diagnostic algorithms. Based on the analysis results, content may require modifications to titles, descriptions, or visual elements (such as thumbnails), while media may be subject to measures such as changes to targeting settings, adjustments to traffic sources, or temporary exclusion.

[0148] As such, whether the media preference score meets the criteria goes beyond simple branching and is closely linked to the flow of subsequent retargeting and content strategy redesign. Combinations that meet the criteria move to the primary line of marketing execution, while those that do not are transferred to the retargeting and review queues, allowing the system to conserve computational resources while simultaneously implementing mid-to-long-term improvement strategies. Through this, the entire system achieves both short-term efficiency and long-term quality maintenance, enabling the operation of marketing assets in a cyclical rather than a consumptive structure.

[0149] According to one embodiment, in operation (409), the processor can calculate the predicted cost for one or more combination candidates consisting of pairs of each content and each medium.

[0150] The optimization engine generates possible content-media candidate combinations based on the content library and media metadata. The optimization engine predicts the expected click-through rate (CTR), conversion rate, and unit cost (CPM / CPC, etc.) for each candidate combination to determine the cost It is calculated as [0,1].

[0151] The optimization engine performs a core computational process to generate actionable content-media combination candidates for actual marketing campaigns only when content preference and media preference are evaluated above a threshold. This engine uses the content library stored within the system and the metadata of each medium as input to explore and generate all possible valid combinations. The content library includes attribute values ​​such as content ID, category, length, format, target audience, and historical performance data, while the media metadata includes the type of media (e.g., mobile app, social media, web portal, etc.), user reach, historical conversion performance, time of impression, and cost metrics (CPM, CPC, etc.).

[0152] The optimization engine simulates the expected click-through rate (CTR), conversion rate, cost per impression (CPM), or cost per click (CPC) that may occur when each combination is exposed to a specific customer group, based on historical log data or predictive models. The predictive models used can consist of various algorithms, such as statistical regression models, gradient boosting models, and deep learning-based predictive neural networks, and are dynamically inferred according to the different contexts, content types, and media attributes for each combination.

[0153] The predicted values ​​calculated for each combination are normalized into cost scores to be linked with the system's budget allocation logic. These cost scores are calculated as real numbers ranging from 0 to 1; the closer the value is to 1, the more the combination is evaluated as having a high cost burden or being inefficient relative to its expected effects. Conversely, combinations with values ​​close to 0 may be prioritized for placement due to low unit costs or high efficiency. Normalization is calculated by comprehensively reflecting the relative deviation of CPM / CPC per combination and the expected conversion value relative to the budget, and in some cases, it may be implemented as a multi-objective function incorporating weights.

[0154] Through this process, the optimization engine can selectively identify combinations from the entire content-media mix that satisfy specific criteria while simultaneously offering high efficiency relative to the budget. These results are subsequently registered in a priority recommendation queue or forwarded to the marketing execution engine for use in actual content delivery and ad execution. Additionally, these cost prediction results are recorded in log form on the operator dashboard, allowing them to be reused as valuable insights for campaign planning. Ultimately, this stage serves to refine the overall system resource allocation strategy by making data-driven judgments on the balance between cost and efficiency, rather than simply matching content and media.

[0155] According to one embodiment, in operation (411), the processor may distribute the total advertising budget to each combination candidate based on the evaluation results of the customer's preference for the one or more contents, the evaluation results of the customer's preference for the one or more media, and the predicted cost.

[0156] The optimization engine can calculate a matching score for each candidate combination based on the evaluation results of customer preferences for the one or more contents, the evaluation results of customer preferences for the one or more media, and the predicted costs. The optimization engine can determine the most suitable combination by evaluating all possible content-media combinations.

[0157] The optimization engine can compare the matching scores of all combinations and select the combination with the highest matching score as the optimal combination. Through this, the optimization engine can select the content-media combination determined to be the most effective.

[0158] The optimization engine can receive content preference scores, media preference scores, and predicted costs as input data. Content preference scores and media preference scores are pre-calculated preference scores for each content and media combination, and these scores can indicate how effective the corresponding combination will be. Predicted costs refer to the costs incurred in executing each content and media combination.

[0159] The optimization engine may introduce a content weight index as the seventh parameter, which is a factor indicating how important content preference is in the combination evaluation. The optimization engine may introduce a media weight index as the eighth parameter, which is a factor indicating how important media preference is in the combination evaluation. The optimization engine may introduce a cost sensitivity index as the ninth parameter, which is a factor indicating how much influence combination cost has on the combination evaluation. The optimization engine may introduce a smoothing constant as the tenth parameter, which is a factor to mitigate extreme values ​​that may occur during the calculation of the matching score.

[0160] The optimization engine can calculate a matching score for each content-media combination based on the above parameters and input data. The optimization engine can compare the matching scores of all combinations and select and output the combination with the highest matching score as the optimal combination.

[0161] The optimization engine can calculate the matching score using the following mathematical formula 3.

[0162] [Mathematical Formula 3]

[0163]

[0164] is the content weight index as the seventh parameter, and can be set in the range of, for example, 0.5 to 2. is the eighth parameter, which is a media weighting index and can be set in the range of, for example, 0.5 to 2. ​is the cost sensitivity index as the ninth parameter, and can be set in the range of, for example, 0.5 to 2. is a smoothing constant as the 10th parameter, and can be set in the range of, for example, 0.01 to 0.1.

[0165] The optimization engine can distribute the total advertising budget to each candidate combination based on the matching score. The optimization engine's total advertising budget It is allocated in proportion to the matching score for each content-media combination. The optimization engine can apply a budget sensitivity index to the matching score of each content-media combination. This serves to adjust the 'weight' of each combination. The optimization engine can sum these adjusted matching scores for all possible content-media combinations. This value can represent the total weight sum. The optimization engine can divide the adjusted matching score of a specific content-media combination by the total weight sum. This result can represent the proportion that combination occupies of the total weight. The optimization engine can calculate the budget to be allocated to that content-media combination by multiplying this proportion by the total budget.

[0166] The optimization engine allocates the budget to the combination of content (c) and media (m) based on the following mathematical formula 4. It can calculate.

[0167] [Mathematical Formula 4]

[0168]

[0169] η is the 11th parameter, a budget sensitivity index, and this value controls the effect of the matching score on budget allocation and can be set, for example, in the range of 0.5 to 2. If η > 1, more budget is concentrated on effective combinations, and if η < 1, the budget can be distributed more evenly among combinations. is the total budget, and, for example, can be in units of 10,000. i, j are indices that identify all combinations of N contents and M media. represents the sum of the allocated budget. is the matching score of the content (c) and media (m) combination. This score indicates the effectiveness of the combination, and the higher the score, the higher the likelihood of more budget being allocated.

[0170] According to one embodiment, the monitoring unit can collect performance data of distributed advertisements based on the allocated advertising budget. The monitoring unit collects real-time performance data (CTR, conversion rate, time spent, etc.) of the distributed advertisements.

[0171] According to one embodiment, the feedback engine can update system parameters by analyzing collected performance data. The feedback engine analyzes the collected performance data to update the customer profile ( , Periodically updates ) and various parameters.

[0173] FIG. 5 is a diagram illustrating an example of distributing total marketing costs to each combination according to one embodiment.

[0174] For example, the electronic device (310) can reasonably allocate the budget in situations such as the table below.

[0175] [graph]

[0176]

[0177] With Pc=0.562, showing a watch time of 30 minutes, a rating of 4, and a click-through rate of 10%, the attractiveness of the content itself is above average. The media preference Pm=0.230 reflects an impression frequency of 500, relevance of 2 hours, and a sharing index of 40%; while this is decent, it is lower than the content preference, indicating average media efficiency. The matching score Sc,m=0.369 is a relatively high value resulting from combining the two preferences while considering a cost of 0.3. Allocated budget Bc,m 7,639.8 is the result of approximately 76% of the total 10,000-unit budget being allocated to this combination.

[0178] With Pc=0.434, the content appeal is relatively low, exhibiting a watch time of 5 minutes, low ratings, and a low click-through rate. Media preference Pm=0.197 indicates low media responsiveness, with an impression frequency of 200, an elapsed time of 10 hours, and a sharing index of 20%. The matching score Sc,m=0.114 suggests low efficiency as a result of combining preference and cost of 0.7. Allocated budget Bc,m 2,360.2 is the result of approximately 24% of the remaining budget being allocated to this combination.

[0179] As such, the matching score indicates the relative efficiency of the content and media combinations preferred by the customer, and the higher the matching score, the more budget the electronic device (310) allocates. The budget allocation model is designed to automatically distribute the budget in proportion to the matching score of each combination, thereby concentrating resources on high-efficiency combinations and allocating a low budget to inefficient combinations.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 In an electronic device, memory; communication unit; and includes at least one processor connected to the memory and the communication unit, wherein the processor collects raw customer data including web logs, CRM (Customer Relationship Management) data, social media activity data, or satisfaction response data from one or more external servers, analyzes the raw customer data to obtain refined customer data including content response data representing the customer's response to content and media response data representing the customer's response to media, normalizes the viewing time included in the content response data by comparing it with a preset maximum viewing time, and calculates a preference score for viewing time by applying a first parameter that adjusts the sensitivity of preference change according to the normalized viewing time, normalizes the user evaluation score included in the content response data, and calculates a preference score for user evaluation such that the evaluation score becomes a maximum value when it is a median value by applying a second parameter that determines the period of the periodic influence of user evaluation on preference, and calculates a click-through rate based on the number of impressions and clicks included in the content response data, and calculates a preference score for the click-through rate by applying a third parameter that adjusts the sensitivity of preference change according to the click-through rate, and the preference score for viewing time, the preference score for user evaluation, and the Weights are assigned to preference scores for click-through rates and summed to calculate a content preference score; if the content preference score is greater than or equal to a preset first threshold, the customer's preference for one or more media is evaluated based on the media response data to calculate a media preference score; and if the content preference score is less than the first threshold, the calculation of the media preference score is omitted.An electronic device that triggers a remarketing notification for the content or derives improvement proposals through an AI (Artificial Intelligence)-based content improvement proposal module, calculates a predicted cost for one or more combination candidates consisting of pairs of each content and each media, calculates a matching score for each combination candidate based on the content preference score, the media preference score, and the predicted cost, and outputs a combination candidate corresponding to the highest matching score among the matching scores. Claim 2 delete Claim 3 delete

Images