Computing device and operating method thereof

Abstract

Disclosed are a computing device and an operating method thereof. The computing device for recommending user-customized content according to at least one of various embodiments of the present disclosure comprises: a storage module; and a processor for communicating with the storage module to transmit and receive data. The processor: acquires a personalized recommendation content list generated by learning and inference through an artificial intelligence engine including a plurality of recommended algorithm models on the basis of first data related to a user and second data pertaining to content; and controls so that a user interface generated on the basis of the personalized recommendation content list is provided by means of a screen of a display device, wherein the artificial intelligence engine processes, in parallel, a plurality of algorithms for generating the personalized recommendation content list.

Description

Computing device and its method of operation

[0001] The present disclosure relates to a computing device and a method of operating the same.

[0002] Recently, the functions of mobile devices have become more diverse; for example, they include data and voice communication, taking photos and videos via a camera, voice recording, playing music files through a speaker system, and the ability to display images or videos on a screen.

[0003] Some terminals have added electronic game play capabilities or perform multimedia player functions.

[0004] As such terminals become more diverse in their functions, they are being implemented in the form of multimedia players equipped with complex functions, such as taking photos or videos, playing music or video files, playing games, and receiving broadcasts.

[0005] We live in an era where content is overflowing due to a flood of information. Consequently, users of display devices face the problem of spending too much time searching for and watching desired content. Although various search tools are available, the process of finding specific content through them is complex and time-consuming, causing inconvenience in their use.

[0006] The present disclosure has as its objective to enhance the user's convenience and satisfaction with the use of a display device by providing a personalized list of recommended content to a display device through a computing device utilizing artificial intelligence technology.

[0007] A computing device for user-customized content recommendation according to at least one of the various embodiments of the present disclosure comprises: a storage module; and a processor that communicates with the storage module to exchange data, wherein the processor obtains a personalized recommended content list generated by learning and inferring through an artificial intelligence engine that includes a plurality of recommendation algorithm models based on first data related to a user and second data related to content, and controls a user interface generated based on the personalized recommended content list to be provided through the screen of a display device, wherein the artificial intelligence engine processes a plurality of algorithms for generating the personalized recommended content list in parallel.

[0008] A method of operation of a computing device according to an embodiment of the present disclosure comprises: reading first data related to a user and second data related to content from respective repositories; learning and inferring through an artificial intelligence engine including a plurality of recommendation algorithm models based on the first data and second data read; generating a personalized recommended content list based on the learning and inference through the artificial intelligence engine; and controlling a user interface generated based on the personalized recommended content list to be provided through the screen of a display device. In this case, the artificial intelligence engine processes a plurality of algorithms for generating the personalized recommended content list in parallel.

[0009] According to at least one of the various embodiments of the present disclosure, by providing a personalized content list for the user using artificial intelligence technology, the user's satisfaction with using the display device can be increased.

[0010] FIG. 1 is a block diagram illustrating the configuration of a display device according to one embodiment of the present disclosure.

[0011] FIG. 2 is a block diagram of a remote control device according to an embodiment of the present disclosure.

[0012] FIG. 3 shows an example of the actual configuration of a remote control device according to one embodiment of the present disclosure.

[0013] FIG. 4 shows an example of utilizing a remote control device according to an embodiment of the present disclosure.

[0014] FIG. 5 is a schematic diagram of a personalized recommendation system according to one embodiment of the present disclosure.

[0015] Figure 6 is a configuration block diagram of the computing device of Figure 5.

[0016] FIG. 7 is a schematic diagram of a personalized recommendation system according to another embodiment of the present disclosure.

[0017] Figure 8 is a diagram illustrating an example of the configuration of the first artificial intelligence engine and the second artificial intelligence engine.

[0018] Figure 9 is a detailed block diagram of Figure 7.

[0019] FIG. 10 is a diagram illustrating a sequence diagram of a first artificial intelligence engine according to an embodiment of the present disclosure.

[0020] FIG. 11 is a diagram illustrating a sequence diagram of a second artificial intelligence engine according to an embodiment of the present disclosure.

[0021] FIG. 12 is a diagram illustrating an example of a list of recommended content provided in each group unit through an A / N framework, which is a personalized recommendation system according to the present disclosure.

[0022] FIG. 13 is a drawing illustrating an example of a user interface (UI) visualized to allow real-time verification of the performance of a recommendation algorithm according to an embodiment of the present disclosure.

[0023] Hereinafter, embodiments related to the present disclosure will be described in more detail with reference to the drawings. The suffixes “module” and “part” for components used in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not have distinct meanings or roles in themselves.

[0024] FIG. 1 is a block diagram illustrating the configuration of a display device (100) according to one embodiment of the present disclosure.

[0025] Referring to FIG. 1, the display device (100) may include a broadcast receiver (130), an external device interface (135), a storage unit (140), a user input interface (150), a control unit (170), a wireless communication unit (173), a voice acquisition unit (175), a display (180), a speaker (185), a power supply unit (190), etc.

[0026] The broadcast receiver (130) may include a tuner (131), a demodulator (132), and a network interface (133).

[0027] The tuner (131) can tune to a specific broadcast channel according to a channel tuning command. The tuner (131) can receive a broadcast signal for the tuned specific broadcast channel.

[0028] The demodulator (132) can separate the received broadcast signal into a video signal, an audio signal, and a data signal related to the broadcast program, and can restore the separated video signal, audio signal, and data signal into a form that can be output.

[0029] The network interface (133) may provide an interface for connecting the display device (100) to a wired / wireless network including the Internet. The network interface (133) may transmit or receive data to or from other users or other electronic devices through the connected network or another network linked to the connected network.

[0030] The network interface (133) can access a specific web page through a connected network or another network linked to the connected network. That is, it can access a specific web page through a network and transmit or receive data with the corresponding server.

[0031] And, the network interface (133) can receive content or data provided by a content provider or network operator. That is, the network interface (133) can receive content such as movies, advertisements, games, VoD (Video on Demand), broadcast signals, and related information provided by a content provider or network provider through a network.

[0032] Additionally, the network interface (133) can receive firmware update information and update files provided by the network operator, and can transmit data to the internet or a content provider or network operator.

[0033] The network interface (133) can select and receive a desired application among the applications that are open to the public through the network.

[0034] The external device interface (135) can receive an application or a list of applications within an adjacent external device and transmit it to the control unit (170) or storage unit (140).

[0035] The external device interface (135) can provide a connection path between the display device (100) and an external device. The external device interface (135) can receive one or more of video and audio output from an external device connected to the display device (100) wirelessly or via a wired connection, and transmit them to the control unit (170). The external device interface (135) may include a plurality of external input terminals. The plurality of external input terminals may include an RGB terminal, one or more HDMI (High Definition Multimedia Interface) terminals, and a component terminal.

[0036] The voice signal of an external device input through the external device interface (135) can be output through the display (180). The voice signal of an external device input through the external device interface (135) can be output through the speaker (185).

[0037] The external device that can be connected to the external device interface (135) may be any one of a set-top box, Blu-ray player, DVD player, game console, soundbar, smartphone, PC, USB memory, or home theater, but this is merely an example.

[0038] In addition, some content data stored in the display device (100) can be transmitted to another user or other electronic device selected among other users or other electronic devices that are previously registered in the display device (100).

[0039] The storage unit (140) can store programs for each signal processing and control within the control unit (170), and can store signal-processed video, audio, or data signals.

[0040] Additionally, the storage unit (140) may perform the function of temporarily storing video, audio, or data signals input from an external device interface (135) or a network interface (133), and may also store information regarding a predetermined image through a channel memory function.

[0041] The storage unit (140) can store an application or a list of applications input from an external device interface (135) or a network interface (133).

[0042] The display device (100) can play content files (video files, still image files, music files, document files, application files, etc.) stored in the storage unit (140) and provide them to the user.

[0043] The user input interface unit (150) can transmit a signal input by the user to the control unit (170) or transmit a signal from the control unit (170) to the user. For example, the user input interface unit (150) can receive and process control signals such as power on / off, channel selection, and screen setting from the remote control device (200) according to various communication methods such as Bluetooth, Ultra Wideband (UWB), ZigBee, Radio Frequency (RF) communication, or Infrared (IR) communication, or process to transmit control signals from the control unit (170) to the remote control device (200).

[0044] Additionally, the user input interface unit (150) can transmit control signals input from local keys (not shown), such as power key, channel key, volume key, and setting value, to the control unit (170).

[0045] The image signal processed by the control unit (170) can be input to the display (180) and displayed as an image corresponding to the image signal. Additionally, the image signal processed by the control unit (170) can be input to an external output device through the external device interface (135).

[0046] The voice signal processed by the control unit (170) can be output as audio to the speaker (185). Additionally, the voice signal processed by the control unit (170) can be input to an external output device through the external device interface (135).

[0047] In addition, the control unit (170) can control the overall operation within the display device (100).

[0048] Additionally, the control unit (170) can control the display device (100) by means of a user command or internal program input through the user input interface unit (150), and can connect to a network to allow the user to download an application or a list of applications desired by the user into the display device (100).

[0049] The control unit (170) enables the processed video or audio signal, such as channel information selected by the user, to be output through the display (180) or speaker (185).

[0050] Additionally, the control unit (170) enables a video signal or audio signal from an external device, such as a camera or camcorder, input through the external device interface (135) according to an external device video playback command received through the user input interface unit (150), to be output through the display (180) or speaker (185).

[0051] Meanwhile, the control unit (170) can control the display (180) to display an image, for example, a broadcast image input through the tuner (131), an external input image input through the external device interface (135), an image input through the network interface, or an image stored in the storage unit (140) can be controlled to be displayed on the display (180). In this case, the image displayed on the display (180) may be a still image or a video, and may be a 2D image or a 3D image.

[0052] Additionally, the control unit (170) can control the playback of content stored in the display device (100), received broadcast content, or external input content input from the outside, and the content may be in various forms such as broadcast video, external input video, audio file, still image, connected web screen, and document file.

[0053] The wireless communication unit (173) can communicate with an external device via wired or wireless communication. The wireless communication unit (173) can perform short-range communication with an external device. To this end, the wireless communication unit (173) can support short-range communication by using at least one of Bluetooth™, BLE (Bluetooth Low Energy), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies. This wireless communication unit (173) can support wireless communication between a display device (100) and a wireless communication system, between a display device (100) and another display device (100), or between a display device (100) and a network where a display device (100, or an external server) is located, through a wireless area network. The wireless area network may be a wireless personal area network.

[0054] Here, another display device (100) may be a wearable device (e.g., a smart watch, smart glass, HMD (head mounted display), or mobile terminal such as a smartphone) capable of exchanging (or interacting with) data with the display device (100) according to the present disclosure. A wireless communication unit (173) may detect (or recognize) a wearable device capable of communication around the display device (100). Furthermore, if the detected wearable device is an authenticated device to communicate with the display device (100) according to the present disclosure, the control unit (170) may transmit at least a portion of the data processed by the display device (100) to the wearable device through the wireless communication unit (173). Accordingly, the user of the wearable device may use the data processed by the display device (100) through the wearable device.

[0055] The voice acquisition unit (175) can acquire audio. The voice acquisition unit (175) may include at least one microphone (not shown) and can acquire audio around the display device (100) through the microphone (not shown).

[0056] The display (180) can generate a driving signal by converting the video signal, data signal, OSD signal processed by the control unit (170) or the video signal, data signal, etc. received from the external device interface (135) into R, G, and B signals, respectively.

[0057] Meanwhile, since the display device (100) illustrated in FIG. 1 is merely an embodiment of the present disclosure, some of the illustrated components may be integrated, added, or omitted depending on the specifications of the actual implemented display device (100).

[0058] That is, as needed, two or more components may be combined into a single component, or a single component may be subdivided into two or more components. In addition, the function performed in each block is intended to explain the embodiments of the present disclosure, and the specific operation or device does not limit the scope of the rights of the present disclosure.

[0059] According to another embodiment of the present disclosure, the display device (100) may receive and play an image through a network interface (133) or an external device interface (135) without having a tuner (131) and a demodulator (132), unlike as shown in FIG. 1.

[0060] For example, the display device (100) may be implemented by separating it into a video processing device, such as a set-top box, for receiving broadcast signals or content according to various network services, and a content playback device for playing content input from the video processing device.

[0061] In this case, the method of operation of a display device according to an embodiment of the present disclosure described below may be performed not only by the display device (100) described with reference to FIG. 1, but also by any one of an image processing device such as a separated set-top box, or a content playback device having a display (180) and a speaker (185).

[0062] The speaker (185) receives a voice-processed signal from the control unit (170) and outputs it as voice.

[0063] The power supply unit (190) supplies power throughout the display device (100). In particular, it can supply power to a control unit (170) that can be implemented in the form of a System On Chip (SOC), a display (180) for displaying images, a speaker (185) for audio output, etc.

[0064] Specifically, the power supply unit (190) may be equipped with a converter that converts AC power into DC power and a DC / DC converter that converts the level of DC power.

[0065] Next, with reference to FIGS. 2 and 3, a remote control device according to an embodiment of the present disclosure will be described.

[0066] FIG. 2 is a block diagram of a remote control device according to an embodiment of the present disclosure, and FIG. 3 shows an example of an actual configuration of a remote control device according to an embodiment of the present disclosure.

[0067] First, referring to FIG. 2, the remote control device (200) may include a fingerprint recognition unit (210), a wireless communication unit (220), a user input interface (230), a sensor unit (240), an output unit (250), a power supply unit (260), a storage unit (270), a control unit (280), and a voice acquisition unit (290).

[0068] Referring to FIG. 2, the wireless communication unit (220) transmits and receives a signal with any one of the display devices according to the embodiments of the present disclosure described above.

[0069] The remote control device (200) is equipped with an RF module (221) capable of transmitting and receiving signals to and from a display device (100) according to an RF communication standard, and may be equipped with an IR module (223) capable of transmitting and receiving signals to and from a display device (100) according to an IR communication standard. Additionally, the remote control device (200) may be equipped with a Bluetooth module (225) capable of transmitting and receiving signals to and from a display device (100) according to a Bluetooth communication standard. Furthermore, the remote control device (200) may be equipped with an NFC module (227) capable of transmitting and receiving signals to and from a display device (100) according to an NFC (Near Field Communication) communication standard, and may be equipped with a WLAN module (229) capable of transmitting and receiving signals to and from a display device (100) according to a WLAN (Wireless LAN) communication standard.

[0070] Additionally, the remote control device (200) transmits a signal containing information regarding the movement of the remote control device (200), etc., to the display device (100) through the wireless communication unit (220).

[0071] Meanwhile, the remote control device (200) can receive a signal transmitted by the display device (100) through the RF module (221), and, if necessary, can transmit commands regarding power on / off, channel change, volume change, etc. to the display device (100) through the IR module (223).

[0072] The user input interface (230) may be composed of a keypad, buttons, a touchpad, or a touch screen. The user can input commands related to the display device (100) to the remote control device (200) by operating the user input interface (230). If the user input interface (230) is equipped with a hard key button, the user can input commands related to the display device (100) to the remote control device (200) through a push operation of the hard key button. This will be explained with reference to FIG. 3.

[0073] Referring to FIG. 3, the remote control device (200) may include a plurality of buttons. The plurality of buttons may include a fingerprint recognition button (212), a power button (231), a home button (232), a live button (233), an external input button (234), a volume control button (235), a voice recognition button (236), a channel change button (237), a confirmation button (238), and a back button (239).

[0074] The fingerprint recognition button (212) may be a button for recognizing a user's fingerprint. In one embodiment, the fingerprint recognition button (212) may be capable of a push operation and may receive a push operation and a fingerprint recognition operation.

[0075] The power button (231) may be a button for turning the power of the display device (100) on / off.

[0076] The home button (232) may be a button for moving to the home screen of the display device (100).

[0077] The live button (233) may be a button for displaying a live broadcast program.

[0078] The external input button (234) may be a button for receiving an external input connected to the display device (100).

[0079] The volume control button (235) may be a button for adjusting the volume output by the display device (100).

[0080] The voice recognition button (236) may be a button for receiving the user's voice and recognizing the received voice.

[0081] The channel change button (237) may be a button for receiving a broadcast signal of a specific broadcast channel.

[0082] The confirmation button (238) may be a button for selecting a specific function, and the back button (239) may be a button for returning to the previous screen.

[0083] Figure 2 is explained again.

[0084] If the user input interface (230) is equipped with a touchscreen, the user can input commands related to the display device (100) to the remote control device (200) by touching the soft keys on the touchscreen. Additionally, the user input interface (230) may be equipped with various types of input devices that the user can operate, such as scroll keys or jog keys, and this embodiment does not limit the scope of the rights of this disclosure.

[0085] The sensor unit (240) may be equipped with a gyroscope sensor (241) or an accelerometer sensor (243), and the gyroscope sensor (241) may sense information regarding the movement of the remote control device (200).

[0086] For example, the gyroscope sensor (241) can sense information regarding the operation of the remote control device (200) based on the x, y, and z axes, and the accelerometer sensor (243) can sense information regarding the movement speed of the remote control device (200). Meanwhile, the remote control device (200) may further be equipped with a distance measuring sensor to sense the distance to the display (180) of the display device (100).

[0087] The output unit (250) can output a video or audio signal corresponding to the operation of the user input interface (230) or a signal transmitted from the display device (100). Through the output unit (250), the user can recognize whether the user input interface (230) is operated or whether the display device (100) is controlled.

[0088] For example, the output unit (250) may be equipped with an LED module (251) that lights up when the user input interface (230) is operated or when a signal is transmitted or received with the display device (100) through the wireless communication unit (220), a vibration module (253) that generates vibration, a sound output module (255) that outputs sound, or a display module (257) that outputs video.

[0089] Additionally, the power supply unit (260) supplies power to the remote control device (200), and can reduce power waste by stopping the power supply when the remote control device (200) does not move for a predetermined period of time. The power supply unit (260) can resume power supply when a predetermined key provided in the remote control device (200) is operated.

[0090] The storage unit (270) may store various types of programs, application data, etc., necessary for the control or operation of the remote control device (200). If the remote control device (200) transmits and receives signals wirelessly through the display device (100) and the RF module (221), the remote control device (200) and the display device (100) transmit and receive signals through a predetermined frequency band.

[0091] The control unit (280) of the remote control device (200) can store and refer to information regarding frequency bands, etc., that can wirelessly transmit and receive signals with the display device (100) paired with the remote control device (200) in the storage unit (270).

[0092] The control unit (280) controls all matters related to the control of the remote control device (200). The control unit (280) can transmit a signal corresponding to a predetermined key operation of the user input interface (230) or a signal corresponding to the movement of the remote control device (200) sensed by the sensor unit (240) to the display device (100) through the wireless communication unit (220).

[0093] In addition, the voice acquisition unit (290) of the remote control device (200) can acquire voice.

[0094] The voice acquisition unit (290) can acquire voice through at least one microphone.

[0095] Next, Figure 4 is explained.

[0096] FIG. 4 shows an example of utilizing a remote control device according to an embodiment of the present disclosure.

[0097] FIG. 4(a) illustrates a pointer (205) corresponding to a remote control device (200) being displayed on a display (180).

[0098] The user can move or rotate the remote control device (200) up and down, left and right. The pointer (205) displayed on the display (180) of the display device (100) corresponds to the movement of the remote control device (200). Since the pointer (205) of the remote control device (200) moves and is displayed according to the movement in 3D space as shown in the drawing, it can be named a spatial remote control.

[0099] FIG. 4(b) illustrates that when a user moves the remote control device (200) to the left, the pointer (205) displayed on the display (180) of the display device (100) also moves to the left in response.

[0100] Information regarding the movement of the remote control device (200) detected through the sensor of the remote control device (200) is transmitted to the display device (100). The display device (100) can calculate the coordinates of the pointer (205) from the information regarding the movement of the remote control device (200). The display device (100) can display the pointer (205) to correspond to the calculated coordinates.

[0101] FIG. 4(c) illustrates a case where, while pressing a specific button within the remote control device (200), the user moves the remote control device (200) away from the display (180). By doing so, the selected area within the display (180) corresponding to the pointer (205) can be zoomed in and enlarged.

[0102] Conversely, when the user moves the remote control device (200) closer to the display (180), the selected area within the display (180) corresponding to the pointer (205) can be zoomed out and reduced in size.

[0103] Meanwhile, when the remote control device (200) moves away from the display (180), the selection area may be zoomed out, and when the remote control device (200) moves closer to the display (180), the selection area may be zoomed in.

[0104] Additionally, when a specific button within the remote control device (200) is pressed, recognition of up-down and left-right movement may be excluded. That is, when the remote control device (200) moves away from or closer to the display (180), up-down, left-right movement is not recognized, and only forward-backward movement is recognized. When the specific button within the remote control device (200) is not pressed, only the pointer (205) moves according to the up-down, left-right movement of the remote control device (200).

[0105] Meanwhile, the movement speed or direction of movement of the pointer (205) can correspond to the movement speed or direction of movement of the remote control device (200).

[0106] Meanwhile, the pointer in this specification refers to an object displayed on the display (180) in response to the operation of the remote control device (200). Accordingly, the pointer (205) can be an object of various shapes other than the arrow shape shown in the drawing. For example, it may be a concept including a dot, a cursor, a prompt, a thick outline, etc. Furthermore, the pointer (205) can be displayed corresponding to a single dot on either the horizontal or vertical axis on the display (180), and it can also be displayed corresponding to multiple points such as a line or a surface.

[0107] Below, the customized personalized recommendation system (500) is described in more detail.

[0108] A computing device provides a service platform, and through the service platform, a display device can provide a user-customized personalized recommendation service. According to an embodiment, at least a part of the computing device may be embedded in or included in the display device.

[0109] This specification discloses a service structure of a personalized recommendation system that provides a personalized, optimized list of recommended content based on artificial intelligence technologies, such as machine learning (ML) and deep learning (DL) algorithms. However, the algorithms may not be limited to use only in a personalized recommendation system.

[0110] In addition, the present specification discloses an A / N framework service structure diagram in which multiple recommendation algorithms are executed in parallel and multiple A / B tests that perform real-time comparative analysis are simultaneously supported.

[0111] In addition, the present specification discloses a pipeline service structure that more easily interfaces with the aforementioned multiple recommendation algorithms by obtaining feature data, such as various data representing user behavior patterns for a predefined application (e.g., Channels app) and content metadata.

[0112] As mentioned above, various data may include, for example, user viewing information and user-specific keyword preference data.

[0113] And content metadata may include, for example, content-specific descriptions, titles, keywords, genres, person information, etc.

[0114] Meanwhile, the pipeline service structure mentioned above may include, for example, a big data pipeline service structure.

[0115] However, the foregoing is merely an example, and the present disclosure is not limited thereto.

[0116] FIG. 5 is a schematic diagram of a personalized recommendation system (500) according to an embodiment of the present disclosure. FIG. 6 is a block diagram of the configuration of a computing device (400) of FIG. 5.

[0117] Referring to FIG. 5, a personalized recommendation system (500) according to one embodiment of the present disclosure may be configured to include a display device (100) and a computing device (400).

[0118] Here, the display device (100) may be the same as the display device described in FIGS. 1, 2, and 4 above. Accordingly, the description regarding the configuration of the display device (100) shown in FIG. 5 refers to the above content, and redundant descriptions are omitted here. However, among the configurations of the display device (100), the configuration related to personalized recommendations will be described separately.

[0119] The computing device (400) can create and build a service platform to provide personalized recommendation services to the display device (100).

[0120] The computing device (400) can be called by various names, such as a server in that it provides a platform, a processor in that it processes data regarding personalized recommendations, and a controller in that it controls the operation of the personalized system.

[0121] In FIG. 5, only one display device (100) and one computing device (400) are shown, but there may be multiple of each. For example, display devices may be connected to one computing device (400), and each display device may receive a personalized recommendation service from the one computing device (400). In this case, depending on the embodiment, some of the display devices may be grouped together to receive the same or similar personalized recommendation service (or list) from the computing device (400).

[0122] Referring to FIGS. 5 and 6, the computing device (400) can be largely configured to include memory and a processor.

[0123] At this time, the memory may correspond to the storage module (660) of FIG. 6 or represent a configuration including it.

[0124] Meanwhile, the memory does not necessarily have to be a component of the computing device (400), and it is sufficient if it is formed externally and can exchange data with the computing device (400).

[0125] In the above, the processor may be configured to include a communication interface module (610), a data classification and preprocessing module (620), an artificial intelligence processing module (630), a personalized recommendation service generation and processing module (640), a control module (650), etc.

[0126] The communication interface module (610) provides a communication interface environment that allows data to be exchanged with at least one internal or / and external device.

[0127] The communication interface module (610) can receive information about a connected terminal, such as a display device (100), information about a connected terminal user, etc.

[0128] The communication interface module (610) can receive data necessary for training, inference, etc. from the artificial intelligence processing module (630).

[0129] The data classification and preprocessing module (620) can classify data received through the communication interface module (610). At this time, the classified data may include, for example, data required for training, inference, etc. in the artificial intelligence processing module (630) described later.

[0130] The data classification and preprocessing module (620) may perform pre-processing operations as needed, depending on the type, nature, or attributes of the classified data. Such pre-processing operations may be for processing in the artificial intelligence processing module (630) described later. Therefore, if the classified data is not an input for the artificial intelligence processing module (630), the pre-processing operation may not be performed.

[0131] The artificial intelligence processing module (630) may include at least two artificial intelligence engines, for example, as shown in FIG. 7 described later.

[0132] The artificial intelligence processing module (630) can train learning model(s) using the first artificial intelligence engine (720 in FIG. 7).

[0133] The artificial intelligence processing module (630) can perform inference based on the learned model using the second artificial intelligence engine (730 in FIG. 7).

[0134] In the above, the operation of the data classification and preprocessing module (620) and the artificial intelligence processing module (630) is for personalized content recommendation according to an embodiment of the present disclosure.

[0135] In relation to the present disclosure, it should be noted in advance that known technologies are used regarding data classification, data preprocessing, artificial intelligence models, etc., unless otherwise mentioned. Accordingly, separate detailed descriptions thereof are omitted except where necessary.

[0136] The personalized recommendation service generation and processing module (640) can perform processing operations such as generating and transmitting real-time or non-real-time user-customized personalized recommendation services based on results inferred from the model(s) learned in the aforementioned artificial intelligence processing module (630).

[0137] The storage module (660) can temporarily store data that is acquired, processed, etc., by the processor.

[0138] The storage module (660) can store data related to at least two artificial intelligence engines (720, 730) included in the artificial intelligence processing module (630). The storage module (660) can update the previously stored data related to the artificial intelligence engines (720, 730) under the control of the control module (650).

[0139] The control module (650) can control the operation of each component of the computing device (400) or processor.

[0140] Software such as various algorithms, applications, and programs used in the artificial intelligence processing module (630) in the present disclosure can be stored in the storage module (660) under the control of the control module (650).

[0141] FIG. 7 is a schematic diagram of a personalized recommendation system according to another embodiment of the present disclosure, FIG. 8 is a diagram illustrating an example of the configuration of a first artificial intelligence engine and a second artificial intelligence engine, FIG. 9 is a detailed block diagram of FIG. 7, FIG. 10 is a diagram illustrating a sequence diagram of a first artificial intelligence engine according to an embodiment of the present disclosure, and FIG. 11 is a diagram illustrating a sequence diagram of a second artificial intelligence engine according to an embodiment of the present disclosure.

[0142] Referring to FIG. 7, a personalized recommendation system may be configured to include a computing device (400) including a data store (710) and an artificial intelligence engine (720) and a display device (100).

[0143] Referring to FIG. 7, the personalized recommendation system according to an embodiment of the present disclosure can be optimized for server configuration according to hardware resource requirements such as a central processing unit (CPU), memory, disk space, graphics processing unit (GPU), and graphics processing unit memory (GPU memory) for each module.

[0144] For the above optimization, the present disclosure, for example, independently partitioned the hardware resources constituting the computing device (400). However, the present disclosure is not necessarily limited thereto.

[0145] Meanwhile, it is desirable to design each hardware resource so that various algorithms can be added internally as needed.

[0146] Referring to FIGS. 7 through 9, the artificial intelligence engine may be composed of at least two artificial intelligence engines as described above. At this time, the at least two artificial intelligence engines may each be classified as an engine for training and an engine for inference. Hereinafter, the engine for training is referred to as the first artificial intelligence engine (720) and the engine for inference is referred to as the second artificial intelligence engine (730).

[0147] Meanwhile, in FIGS. 7 and 9, only one first artificial intelligence engine (720) for training and one second artificial intelligence engine (730) for inference are shown, but this is not limited to multiple engines, and there may be multiple engines.

[0148] The data store (710) can preprocess input data and transmit it to both the first artificial intelligence engine (720) and the second artificial intelligence engine (730), or at least one of them.

[0149] The input data described above may include first data and second data. Meanwhile, the first data is primarily data unrelated to the content, but is not necessarily limited thereto. Additionally, the second data is primarily data related to the content (e.g., metadata), but is not necessarily limited thereto.

[0150] Referring to FIGS. 7 and 9, the data store (710) is described in more detail as follows.

[0151] The data store (710) can be divided into a resource for first data processing (for convenience, the first resource) and a resource for second data processing (for convenience, the second resource).

[0152] The first resource may be configured to include a first data feed module, a first data pre-processing module, etc., and the second resource may also be configured to include a second data feed module, a second data pre-processing module, etc. In this case, the performance, etc., of the data feed module and the data pre-processing module included in each resource may or may not be identical.

[0153] Meanwhile, in FIG. 9, only one first resource and one second resource are shown, but each may be multiple as needed.

[0154] First, I will explain the first resource.

[0155] The first data feed module can read various raw data used for training a recommendation algorithm model included in an artificial intelligence engine described later, for example, from the first storage (910).

[0156] The first data feed module can read raw data from the first storage (910) periodically or non-periodically. In the former case, for example, a fixed daily unit, hourly unit, etc. may be indicated. However, it is not limited thereto.

[0157] The first data feed module can read raw data corresponding to a specific time interval from the first storage (910). In the above, the specific time interval may refer to the aforementioned daily unit, hourly unit (e.g., 1 hour, etc.), etc. However, it is not limited thereto. For example, in order to prevent a time delay that occurs when reading a large amount of data sequentially from the first storage (910), the data feed module may divide the time interval (e.g., 1 day) into smaller time slots (e.g., 24 times, each one hour) and retrieval the data in parallel.

[0158] In this specification, the term "storage" refers to a configuration that stores data, such as a storage medium or a database (DB), and is not limited to the examples given above.

[0159] Meanwhile, the raw data read from the first storage (910) by the first data feed module above may include, for example, user-specific data, MAC address-specific data, device-specific data, user-specific keyword preference data, content-specific description, keyword, genre, person information, etc.

[0160] The first data preprocessing module can transform, i.e., preprocess, the raw data read through the first data feed module into a form that can be used by the artificial intelligence engine (e.g., recommendation algorithm, etc.) described later. Here, according to the transformation or preprocessing, it is possible to extract, for example, sequential information of the user's latest viewing time, vector values ​​of text information about the content, etc. from the raw data. The first data preprocessing module can temporarily store the preprocessed data or transmit it to be stored in the third storage (930).

[0161] The first resource can be connected to multiple users or multiple repositories. In this case, for each resource, instead of processing data sequentially, for example, by user / mac / device, the entire user / mac / device identifier (id) values ​​can be divided into multiple disjoint subsets, and each of these divided subsets can be processed in parallel so that the processing speed is not delayed and processing can be done quickly.

[0162] Next, the second resource is similar to the first resource described above. However, while the first resource reads raw data from the first storage (910) in the first data feed module, the second resource differs in that the second data feed module reads raw data from the second storage (920), processes it in the second data preprocessing module, and transmits it to be stored in the third storage (930).

[0163] Meanwhile, the second storage (920) may be a storage that stores data different from that of the first storage (910). For example, unlike the first storage (910), the second storage (920) may be a storage that stores only content data.

[0164] Referring to FIGS. 7 and 9, data processed in the data store (710) can be input into the artificial intelligence engine. Referring to FIG. 9, data processed through the data store can be transferred to the artificial intelligence engine from the third storage (930) where the data is stored, or conversely, the artificial intelligence engine can read data from the third storage (930) periodically or non-periodically.

[0165] Referring to Fig. 8, the artificial intelligence engine is described in more detail.

[0166] FIG. 8(a) illustrates a block diagram of a first artificial intelligence engine (720), and FIG. 8(b) illustrates an example of a block diagram of a second artificial intelligence engine (730). This is merely an example, and the present disclosure is not necessarily limited thereto.

[0167] Referring to FIGS. 8(a) and 10, the first artificial intelligence engine (720) may be configured to include a configuration module, a data feed module, a targeting module, an algorithm module, a validation module, etc., for training for personalized recommendations according to the present disclosure.

[0168] A model file containing result data trained in the first artificial intelligence engine (720) can be transferred to and stored in the fourth storage (940).

[0169] The configuration module can read various configuration information regarding the recommendation algorithms to be trained from the administrator terminal (or administrator repository, etc.).

[0170] The configuration module can periodically check the configuration information of registered training target recommendation algorithms (e.g., daily, weekly, monthly, quarterly, etc.).

[0171] The data feed module can read preprocessed data required for recommendation algorithms received through the configuration module from the third storage (930).

[0172] At least two data feed modules are provided for cross-validation, and each can handle data split into a training dataset and a test dataset.

[0173] The targeting module can extract a list of mac / user / devices to which a recommendation algorithm to be applied (e.g., a group that prefers only news channels) to be read from a third storage (930) via a data feed module.

[0174] The targeting module can refer to a combination of segments and a list of mac / user / devices stored in the third storage (930).

[0175] Alternatively, the targeting module may target and extract data read from the third storage (930) by referring to algorithm setting information (e.g., target area range, etc.) read through the configuration module.

[0176] In other words, the targeting module performs the function of targeting and extracting data to be input into the subsequent algorithm for training from among the data processed by the aforementioned data store (710). The number of such targeting modules can also be determined to match one-to-one with the data feed module, but is not limited thereto.

[0177] The algorithm module can set various parameter values ​​based on the list of mac / user / device to which the recommendation algorithm will be applied and the partitioned training dataset, and can train n models (where n is a positive integer).

[0178] The validation module can determine a model and store parameter values ​​for said model after comparing the performance of models trained on a test dataset. In this case, said model may refer, for example, to a model exhibiting the best performance, but is not limited thereto. For example, said model may include at least one model exhibiting a next-highest performance in addition to the best performance, or model(s) exhibiting average performance may be determined.

[0179] The validation module can transfer the model file generated through it to the fourth storage (940) so that it can be stored.

[0180] Referring to FIG. 10, the sequence diagram of the aforementioned first artificial intelligence engine (720), that is, the training engine, is described as follows.

[0181] The configuration module can register the learning target recommendation algorithm, etc. from the administrator terminal. At this time, the configuration module can receive additional information from the administrator terminal regarding the learning start date, learning cycle, target country or region, etc., in addition to the learning target recommendation algorithm (S101).

[0182] The data feed module can read preprocessed data to be used as input for each recommendation algorithm from a third storage (930) (S103). The data feed module can transmit the read data to the algorithm module.

[0183] The targeting module can set selection information for the target device / mac / user, etc. to be used for training in the algorithm module (S105).

[0184] The algorithm module can learn (or infer) a content recommendation list for each device / mac / user based on the data received from the data feed module and the data input by the targeting module, and transmit it to the validation module (S107).

[0185] After the validation module generates a model file containing the determined model and parameter values ​​after performance verification, it can be transmitted to be stored in the fourth repository (940) (S109). Referring to FIGS. 8(b) and 11, the second artificial intelligence engine (730) may be configured to include a configuration module, a data feed module, a targeting module, an algorithm module, a post-processing module, etc., to infer personalized content (or a list of content) according to the present disclosure. At this time, the second artificial intelligence engine (730) may refer to the model file stored in the fourth repository (940).

[0186] Data regarding the results inferred from the second artificial intelligence engine (730) can be transferred to and stored in the fifth storage (950).

[0187] The configuration module can receive various configuration information for inference from the administrator terminal (or administrator repository, etc.).

[0188] For example, the configuration module can set the recommendation algorithm to be applied from the administrator terminal, the country to be applied (e.g., Korea, the United States, etc.), the region to be applied (e.g., East, West, etc.), the scope of application (e.g., sampling rate (e.g., 10% of the total, etc.), the time information to be applied (e.g., date, time zone, day of the week, etc.), the location selection within the application user interface (UI) in a specific application, the division of A / N test groups (A, B, C), the division ratio and the algorithm to be applied for each group, and the application of the finally selected algorithm.

[0189] The configuration module can periodically check the configuration information of registered training target recommendation algorithms (e.g., daily, weekly, monthly, quarterly, etc.).

[0190] The data feed module can also read preprocessed data required for the configured recommendation algorithms received through the configuration module from the third storage (930).

[0191] The targeting module can extract a list of mac / user / devices to which a recommendation algorithm to be applied (e.g., a group that prefers only news channels) read from a third storage (930) via a data feed module.

[0192] The targeting module can refer to a combination of segments and a list of mac / user / devices stored in the third storage (930).

[0193] Alternatively, the targeting module may target and extract data read from the third storage (930) by referring to algorithm setting information (e.g., sampling rate, applicable area range, etc.) read through the configuration module.

[0194] In other words, the targeting module performs the function of targeting and extracting data to be input into the subsequent algorithm for training from among the data processed by the aforementioned data store (710). The number of such targeting modules can also be determined to match one-to-one with the data feed module, but is not limited thereto.

[0195] The algorithm module can read the preprocessed data and the list of mac / user / device to which the recommendation algorithm will be applied, and infer a recommendation list for each device / mac / user. At this time, the algorithm module can receive a model file generated through the aforementioned first artificial intelligence engine (720) and stored in the fourth storage (940) as input and use it as a reference for the inference.

[0196] The algorithm module can reduce latency by utilizing the data of devices / macs / users divided into disjoint subsets from the data store module, and by processing inference in parallel for each device / mac / user divided into disjoint subsets.

[0197] The post-processing module can infer and extract a final recommended content list by performing post-processing such as excluding disliked content from the recommendation lists by device / mac / user extracted from the algorithm module, excluding specific content based on contracts with specific content providers, and including new content intended to be shown to users in common. The final recommended content list extracted in this way can be temporarily stored in the fifth storage (950) and then transferred to the sixth storage (960).

[0198] Referring to FIG. 11, the sequence diagram of the aforementioned second artificial intelligence engine (730), that is, the inference engine, is as follows.

[0199] The configuration module can read various configuration information, including recommendation algorithms to be applied, from the administrator terminal. At this time, the configuration module may receive additional configuration information from the administrator terminal, in addition to the recommendation algorithm to be applied, such as the country to be applied (e.g., Korea, the United States, etc.), the region to be applied (e.g., East, West, etc.), the scope of application (e.g., sampling rate (e.g., 10% of the total, etc.), the time information to be applied (e.g., date, time zone, day of the week, etc.), the location selection within the user interface (UI) to be applied within a specific application, the division of A / N test groups (A, B, C), the division ratio and the algorithm to be applied for each group, and the operation application of the finally selected algorithm (S201).

[0200] The data feed module can read preprocessed data to be used as input for each recommendation algorithm from the third storage (930) (S203). The data feed module can transmit the read data to the algorithm module. Additionally, the data feed module can select a recommendation algorithm to be applied and transmit it to the targeting module.

[0201] The targeting module can set selection information for target devices / mac / users, etc. to be used for training, and selection information for target recommendation algorithms received from the data feed module, in the algorithm module (S205).

[0202] The algorithm module can infer a content recommendation list for each device / mac / user based on the data received from the data feed module and the data input by the targeting module and transmit it to the post-processing module (S207).

[0203] The post-processing module can post-process the received recommendation list to generate a recommendation content list for each device / mac / user and transmit it to be stored in the fifth storage (950) (S209).

[0204] The first artificial intelligence engine (720) of FIG. 8(a) can be updated by periodically retraining the model. Additionally, the second artificial intelligence engine (730) of FIG. 8(b) can also periodically update the list of inferred recommendation results. The second artificial intelligence engine (730) can update the list of inferred recommendation results in conjunction whenever a model file updated according to the update of the first artificial intelligence engine (720) is received. Alternatively, the first artificial intelligence engine (720) and the second artificial intelligence engine (730) may each perform update operations at separate intervals.

[0205] Referring to FIG. 9, based on the above description, the list of recommended content for each device / mac / user stored in the fifth storage (950) can be transferred to and stored in the sixth storage (960).

[0206] Thus, the list of recommended content for each device / mac / user stored in the sixth storage (960) can be delivered on a user group basis or on an individual user basis (i.e., display device basis) basis and provided through the screen. At this time, the sixth storage (960) may be, for example, a storage or DB server directly managed by the manufacturer of the display device (100). Meanwhile, the recommended content list provided above is the result of training and inference by different recommendation algorithms for each group, and accordingly, personalized content may be selectively provided differently over time.

[0207] FIG. 12 is a diagram illustrating an example of a list of recommended content provided in each group unit through an A / N framework, which is a personalized recommendation system according to the present disclosure.

[0208] FIG. 12 divides all users of the display device (100) into multiple segments based on genre or other information, and samples segment information corresponding to a specific segment among them for testing through an A / N framework. The computing device (400) divides the whole into disjoint subsets based on the unique ID values ​​of the devices / macs / users, and can selectively apply a recommendation algorithm to each divided subset. Through this, it is possible to compare the performance of multiple recommendation algorithms simultaneously and to compare and apply the algorithm that exhibits the best performance. In this regard, the computing device (400) may manually configure and statically set the application algorithm, time, and target devices / macs / users through an administrator terminal, but it may also be automated through separate logic.

[0209] FIGS. 12(a) to (f) illustrate a group-unit recommended content list being provided through the screen of a display device (100).

[0210] FIG. 12(a) shows a user interface provision screen for Group A (manual scheduling), FIG. 12(b) shows Group B (news genre segment), FIG. 12(c) shows Group B (sports genre segment), FIG. 12(d) shows Group B (comedy genre segment), FIG. 12(e) shows personalized recommendation, and FIG. 12(f) shows a user interface provision screen for Group C (comedy genre segment, manual scheduling).

[0211] FIG. 13 is a drawing illustrating an example of a user interface (UI) (1300) visualized to allow real-time verification of the performance of a recommendation algorithm according to an embodiment of the present disclosure.

[0212] The user interface (UI) (1300) of FIG. 13 may be provided in the same or similar manner to a display device (100) as well as to an administrator terminal, so that the user can directly check their viewing patterns or access or navigate detailed information related to viewing. For example, in the latter case, the user interface (UI) (1300) of FIG. 13 may function as a new type of user interface that replaces conventional flat and standardized formats of EPG and ECG.

[0213] The user interface (1300) of FIG. 13 is implemented in a circular shape, but is not limited thereto.

[0214] The user interface (1300) can be divided into a segmented part (segment 1-segment 6) and a no-segment part.

[0215] The no-segment portion of the user interface (1300) can be divided into a random part and a personalized part. The random part can be referenced for personalized recommendations when the average number of clicks (number of users) increases by a predetermined amount.

[0216] Unlike the aforementioned no-segment part, the segment part of the user interface (1300) can be divided into three main parts. The first part may be a random part, the second part may be a genre preference part, and the third part may be a personalization part.

[0217] If the user interface (1300) is provided to the administrator terminal, each segment may represent a group as described above. Accordingly, each part of each segment may represent information regarding the randomness, genre preference, and personalization of the corresponding group.

[0218] On the other hand, if the user interface (1300) is provided to an individual user through the display device (100), each segment may be matched to the genre of content (sports, news, drama, movies, etc.) that the user has recently been watching. Meanwhile, depending on the number of each segment, they may be listed sequentially starting from the genre that the user has watched the most. Alternatively, each segment may be matched to the user's recent viewing pattern. Or, each segment may be matched to the preferred genres, viewing patterns, or viewing schedules of users (e.g., family units such as a father, mother, son, and daughter) using the display device (100).

[0219] In addition, each segment of the user interface (1300) may be matched to an input. For example, the input may include an external input such as a set-top box or HDMI, an OTT (Over The Top), a registered smartphone, a tablet PC, a personal terminal such as a laptop or PC, etc.

[0220] Meanwhile, each segment of the user interface (1300) may be arranged according to a preset priority, etc., on the corresponding user or display device, and in that case, the size, color, etc. may be processed and provided differently.

[0221] Each segment included in the user interface (1300) may be matched to a list of recommended content provided by the computing device (400) according to the present disclosure.

[0222] When a user interface (1300) is provided through the screen of a display device (100), the user can access each segment and change its order or arrangement. In this case, the display device (100) may transmit information about the order or arrangement of the changed segments to a computing device (400) and, accordingly, receive a new list of recommended content and provide it to the user.

[0223] As described above, the user interface (1300) may perform a function similar to a content guide (or broadcast program guide) of a display device (100), in which case the no segment may provide various information regarding the source, content, etc., of the current channel or current input (e.g., including at least one of links, images, text, audio information, etc.).

[0224] On the other hand, each segment is distinguished and matched according to source input or genre, and can provide information about representative content of the corresponding source input or genre (including information that enables intuitive recognition of the segment). In this case, when a user accesses at least a part of each segment, more detailed information about the input source or genre included in that segment is provided in the form of a sub-segment or pop-up, allowing for more intuitive and faster recognition and selection.

[0225] When a user accesses, merges, deletes, or adds segments in the user interface (1300), the screen configuration of the user interface (1300) may change accordingly. At this time, the display device (100) may extract information about the user interface (1300) with the changed screen configuration, transmit it to the computing device (400) to use as a reference for updating the artificial intelligence engine, receive a new list of recommended content, and reconstruct and provide the user interface (1300) based on the received new recommended content.

[0226] The user interface (1300) may be individually generated and provided in units of identifiers (IDs) of users using a single display device (100). At this time, it is desirable that information capable of identifying and distinguishing the user be provided in one area of ​​the user interface (1300). Meanwhile, if the display device (100) provides 3D or XR, the user interface (1300) may be configured accordingly.

[0227] Meanwhile, the user interface (1300) may be configured such that, unlike as illustrated in FIG. 13, the color, size, numerical value, etc. of each part of each segment are provided differently from each other based on information for the configuration of the segment. For example, the areas corresponding to the first to third parts in each segment may be different from each other.

[0228] Additionally, although the user interface (1300) is illustrated in FIG. 13 as being implemented in a circular shape, it is not necessarily limited to this and may be configured and provided in different shapes and sizes depending on the device / mac / user.

[0229] Unless specifically mentioned otherwise, the sequence of at least some of the operations disclosed in this disclosure may be performed simultaneously, performed in a different order from the previously described order, or some may be omitted or added.

[0230] According to one embodiment of the present disclosure, the above-described method can be implemented as code that is readable by a processor on a medium on which a program is recorded. Examples of media that are readable by a processor include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0231] The display device described above is not limited to the configuration and method of the embodiments described above; rather, all or part of each embodiment may be selectively combined to allow for various modifications of the embodiments.

[0232] The present disclosure relates to a display device and a method of operating the same, and in particular to various hardware and software for enhancing the convenience of use of a device by providing a personalized list of recommended content tailored to a user utilizing the display device. Since it can be used in various industries in the same or similar manner, there is potential for industrial application.

Claims

1. In a computing device for user-customized content recommendation, Storage module; and It includes a processor that communicates with the above storage module to exchange data, The above processor is, A personalized recommended content list generated by learning and inferring through an artificial intelligence engine including multiple recommendation algorithm models based on first data related to a user and second data related to content, and Control the user interface generated based on the above personalized recommended content list to be provided through the screen of a display device, The above artificial intelligence engine processes multiple algorithms for generating the above personalized recommended content list in parallel, Computing device.

2. In Claim 1, A data store further comprising reading first data related to the above user from a first store and second data related to the above content from a second store, respectively, and preprocessing the data so that it can be processed by the artificial intelligence engine and storing it in a third store. Computing device.

3. In Claim 2, The above artificial intelligence engine is, A first artificial intelligence engine for training to generate the above-mentioned personalized recommended content list, and A second artificial intelligence engine for inferring the above-mentioned personalized recommendation content list, Computing device.

4. In Claim 3, The above-mentioned first artificial intelligence engine is, Receiving setting information regarding the target recommendation algorithm, training start date, training cycle, and target country or region, Computing device.

5. In Claim 4, The above-mentioned second artificial intelligence engine is, Receiving input of the recommendation algorithm to be applied, the country or region to be applied, the scope of application, the application time, and configuration information regarding the selected algorithm, Computing device.

6. In Claim 5, The above-mentioned first artificial intelligence engine is, Dividing the preprocessed data read from the third storage into a training dataset and a test dataset, extracting a list of devices, MACs, and users to which each recommendation algorithm among the plurality of recommendation algorithms will be applied, and combining the segments stored in the storage with the extracted list. Computing device.

7. In Claim 6, The above-mentioned first artificial intelligence engine is, After comparing the performance of models trained with the above test data, saving the best model and parameter values, and generating a model file using the data combined with the above training dataset, Computing device.

8. In Claim 7, The above-mentioned second artificial intelligence engine is, Generating a recommended content list by post-processing content intended to be provided to users in common, while excluding disliked content and content subject to contracts with specific content providers from recommendation lists extracted by device, MAC, and user via an algorithm. Computing device.

9. In Claim 8, The above-mentioned second artificial intelligence engine is, Generating the recommended content list using the model file generated by the first artificial intelligence engine, Computing device.

10. In Claim 3, At least one of the above-mentioned first artificial intelligence engine and second artificial intelligence engine is, Updated periodically or non-periodically, Computing device.

11. In Claim 2, The above data store is A data feed module comprising, respectively, periodically reading raw data corresponding to a specific time interval to be used for training a recommendation algorithm model included in the artificial intelligence engine from the first repository and the second repository, Computing device.

12. In Claim 11, The above data store is, The above specific time interval is divided into multiple time slots for parallel processing, and A data preprocessing module further comprising, for each of the above data feed modules, a data preprocessing module for each of the above data preprocessing raw data read from each of the above repositories. Computing device.

13. In Claim 12, The above data preprocessing module is, In each of the above data feed modules, the raw data read from each of the above repositories is divided into multiple disjoint subsets by device, MAC, and user, and each subset is processed in parallel. Computing device.

14. A step of reading first data related to the user and second data related to the content from each repository; A step of learning and inferring through an artificial intelligence engine including a plurality of recommendation algorithm models based on the first and second data read above; A step of generating a personalized recommended content list based on learning and inference through the artificial intelligence engine; and The method includes a step of controlling a user interface generated based on the above-mentioned personalized recommended content list to be provided through the screen of a display device, wherein The above artificial intelligence engine processes multiple algorithms for generating the above personalized recommended content list in parallel, Method of operation of a computing device.

15. A computer-readable recording medium having a program for implementing the method described in paragraph 14.

Images