Recommended item provision method and electronic device for performing said method

Abstract

Disclosed are a recommended item provision method and an electronic device for performing the method. The electronic device according to various embodiments may comprise: a processor; and a memory that is electrically coupled to the processor and stores instructions executable by the processor. The processor may, when the instructions are executed, cause the electronic device to receive a recommended item list from a server. The processor may allow a model score to be determined by inputting the recommended item list and user information into a trained recommendation model. The processor may allow the model score to be transmitted to the server. The processor may allow an extended score of a first recommended item determined by the server to be received from the server. The processor may allow a second recommended item to be determined on the basis of the extended score of the first recommended item. The processor may allow the second recommended item to be provided to a user.

Description

Method for providing recommended items and electronic device for performing said method

[0001] The disclosure below relates to a method for providing recommended items and an electronic device performing the method.

[0002] In an on-device recommendation system, an electronic device can determine recommended items to provide to a user from the output results of a recommendation model.

[0003] On-device recommendation systems are a type of recommendation system that is well-suited to the recent trend of placing great importance on privacy, as they can provide personalized recommendations without sending user information to the server.

[0004] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above is applicable as prior art related to the present disclosure.

[0005] An electronic device according to various embodiments may include a processor and a memory electrically coupled to the processor and storing instructions executable by the processor. The processor, when the instructions are executed, may cause the electronic device to receive a list of recommended items from a server. The processor may input the list of recommended items and user information into a learned recommendation model to determine a model score. The processor may transmit the model score to the server. The processor may receive, from the server, an expanded score of a first recommended item determined by the server. The processor may determine a second recommended item based on the expanded score of the first recommended item. The processor may provide the second recommended item to a user.

[0006] An electronic device according to various embodiments may include a processor and a memory electrically coupled to the processor and storing instructions executable by the processor. The processor, when the instructions are executed, may cause the electronic device to receive a list of recommended items from a server. The processor may input the list of recommended items and user information into a learned recommendation model to determine a model score. The processor may receive statistical information corresponding to the list of recommended items from the server. The processor may calculate an expanded score for the list of recommended items based on the model score and the statistical information. The processor may determine a first recommended item based on the expanded score. The processor may determine a second recommended item based on the expanded score of the first recommended item. The processor may provide the second recommended item to a user.

[0007] A method for providing recommended items according to various embodiments may include an operation of receiving a list of recommended items from a server, an operation of inputting the list of recommended items and user information into a learned recommendation model to determine a model score, an operation of transmitting the model score to a server, an operation of receiving, from the server, an operation of determining a second recommended item based on the expanded score of the first recommended item, and an operation of providing the second recommended item to a user.

[0008] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0009] FIG. 2 is a schematic block diagram of a recommendation system according to various embodiments.

[0010] Figure 3 is a flowchart of a method for providing recommended items according to various embodiments.

[0011] Figures 4a, 4b, 4c and 4d are tables showing model scores, extension scores and final scores according to various embodiments.

[0012] Figure 4e is a table for updating weights according to various embodiments.

[0013] Figure 5 is a schematic block diagram of a recommendation system according to various embodiments.

[0014] Figure 6 is a flowchart of a method for providing recommended items according to various embodiments.

[0015] Figures 7 and 8 are schematic block diagrams of a recommendation system according to various embodiments.

[0016] FIG. 9 is a diagram illustrating an interface for updating weights according to various embodiments.

[0017] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are assigned the same reference numerals regardless of the drawing numbers, and redundant descriptions thereof will be omitted.

[0018] In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" may include any one of the items listed together in that phrase, or all possible combinations thereof.

[0019]

[0020] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with the electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (104) or the server (108) via 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) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), 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 connection terminal (178), 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). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0021] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0022] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, 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. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can 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 can include multiple artificial neural network layers.The artificial neural network may be one of 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, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0023] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0024] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0025] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0026] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0027] The display module (160) can visually provide information to an external party (e.g., a 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 the 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 a force generated by the touch.

[0028] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0029] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0030] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In 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.

[0031] The connection terminal (178) may include a connector through which the electronic device (101) may 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).

[0032] The haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0033] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0034] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0035] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0036] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the 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 operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that 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., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as 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 can 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 verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0037] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), 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), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the 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 eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0038] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In 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 the first network (198) or the second network (199), may be selected from the plurality of antennas, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0039] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0040] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0041] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an 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 process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the 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.

[0042]

[0043] FIG. 2 is a schematic block diagram of a recommendation system (200) according to various embodiments.

[0044] An electronic device (101) according to various embodiments can improve the performance of recommendations by determining recommended items using an extended score (245) for the recommended items. The electronic device (101) can increase the diversity of recommendations and enhance the reliability of recommendations by using additional information other than the model score (225).

[0045] For example, an electronic device (101) (e.g., the electronic device (101) of FIG. 1) may receive a list of recommended items (215) from a server (108) (e.g., the server (108) of FIG. 1). For example, a recommendation service (210) of the server (108) may determine the list of recommended items (215). The server (108) may transmit the generated list of recommended items (215) to the electronic device (101).

[0046] For example, the electronic device (101) may input a list of recommended items (215) and user information (230) into a trained recommendation model (220) to determine a model score (225). For example, the model score (225) may be an output of the recommendation model (220) and may indicate the user's level of interest or preference for each item. For example, the higher the model score (225) for an item, the higher the user's level of interest or preference for that item.

[0047] For example, user information (230) may include at least one of the user's past item consumption history, the type of recommended model, and the user profile, or a combination thereof. For example, the electronic device (101) may store the user's item consumption history in memory. The user profile may represent information stored in the memory of the electronic device (101) as information about the user, such as the user's name, gender, age, and address.

[0048] For example, a recommendation model (220) can be trained to input a list of recommended items (215) and user information (230) and output model scores (225) for items included in the list of recommended items (215).

[0049] For example, the electronic device (101) can transmit a model score (225) to a server (108).

[0050] For example, the server (108) may receive model scores (225) from the electronic device (101) and a plurality of external electronic devices. The server (108) may use the model scores (225) received from the electronic device (101) and a plurality of external electronic devices to determine statistical information (235) about items. For example, the statistical information (235) may include the distribution of model scores (225) for each item.

[0051] For example, the server (108) can generate a model score (225) matrix of size MXN as statistical information (235) using model scores (225) for N items for M users.

[0052] For example, the server (108) may determine an additional measure (240) using statistical information (235). For example, the additional measure (240) may be determined for each user of the electronic device (101) and multiple external electronic devices. The additional measure (240) may include a rank within the group (or ranks) and a standard score of the model score (225) for each user.

[0053] For example, the rank within a group may indicate what rank the model score (225) for a user's item ranks in the distribution of model scores (225) for all users (e.g., users of the electronic device (101) and multiple external electronic devices).

[0054] For example, the standard score can be calculated from the distribution of model scores (225) of all users, using the user's model score (225).

[0055] For example, if there are D additional scales (240), the server (108) can generate D additional scale (240) matrices of MXN size for each additional scale (240).

[0056] The above additional scale (240) is exemplary and is not limited to the above examples. For example, the additional scale (240) may include various items other than within-group ranking and standard scores.

[0057] For example, the server (108) may use an additional metric (240) to calculate an extended score (245) for each user's items. For example, the extended score (245) may include a model score (225) for the item, a rank within the group, and a standard score.

[0058] The extended score (245) can be expressed as a multidimensional real number vector. For example, if there are D additional measures (240), the extended score (245) for each item can be a (D+1)-dimensional real number vector.

[0059] For example, the server (108) may use the extended score (245) to determine the primary recommended item (250) (or the first recommended item (250)) for each user. For example, the server (108) may use the Pareto optimal solution calculated using the model score (225), the group rank, and the standard score included in the extended score (245) to determine the first recommended item (250).

[0060] For example, Pareto optimality can represent the definition of an optimal solution in a multi-objective optimization problem with multiple targets to be optimized. For example, the server (108) can determine a first recommended item (250) using the Pareto optimal solution for the model score (225), group rank, and standard score included in the expanded score (245) of each item.

[0061] For example, the electronic device (101) may receive a first recommended item (250) and / or an extended score (245) for the first recommended item (250) from the server (108).

[0062] For example, the electronic device (101) may determine a second recommended item (255) based on the extended score (245) of the first recommended item (250). For example, the electronic device (101) may apply a weight (260) to the extended score (245) of the first recommended item (250) to determine a second recommended item (255) (or a second recommended item (255)) among the first recommended items (250).

[0063] For example, the electronic device (101) can determine the final score by using the component-specific weights (260) of the extended score (245). For example, if the extended score (245) includes a model score (225), a rank within the group, and a standard score, the electronic device (101) can determine the final score for each item by using a first weight set for the model score (225), a second weight set for the rank within the group, and a third weight set for the standard score.

[0064] The electronic device (101) can calculate the final score using the sum of the product of the weights (260) corresponding to each component of the extended score (245). For example, the electronic device (101) can determine ((model score (225)) X (first weight) + (-) * (rank within group) * (second weight) + (standard score) * (third weight)) as the final score for each first recommended item (250).

[0065] For example, the electronic device (101) may determine a set number of second recommendation items (255) using the final scores of each first recommendation item (250). The electronic device (101) may determine the set number of first recommendation items (250) with the highest final scores among the first recommendation items (250) as the second recommendation items (255).

[0066] For example, the electronic device (101) may provide a second recommended item (255) to the user. For example, the electronic device (101) may display a list of items included in the second recommended item (255) through a display module (e.g., the display module (160) of FIG. 1).

[0067] For example, the electronic device (101) may receive user feedback (265). For example, the user feedback (265) may represent a user input for selecting at least one item from among the second recommended items (255). For example, the user feedback (265) may include an action of looking at an item included in the second recommended items (255). For example, when the user looks at the display module (160) while information about a specific item included in the second recommended items (255) is displayed on the display module (160), the electronic device (101) may receive user feedback (265) for the specific item.

[0068] The electronic device (101) may update the weight (260) based on user feedback (265). For example, the electronic device (101) may update the weight (260) in a direction that increases the final score of the selected item based on the user feedback (265). For example, the electronic device (101) may update the weight (260) according to a gradient ascent method to increase the final score of the selected item.

[0069] For example, when determining recommended items based on the Top-K recommendation method in an on-device recommendation system, there may be a problem of the recommended items becoming simple because the final recommended items are likely to be similar to items that the user has preferred in the past.

[0070] As illustrated in FIG. 2 , the electronic device (101) may determine a second recommended item (255) based on the expanded score (245) of the first recommended item (250) and provide the determined second recommended item (255) to the user. The expanded score (245) may include a rank (or rank within a group) or a standard score. For example, the electronic device (101) may determine an item with a high model score (225), a high rank, or a high standard score as the second recommended item (255).

[0071] For example, an item with a high model score (225) may indicate an item with a high user preference or interest. A high-ranking item may indicate a user's preference or interest in the item is higher than that of other users. An item with a high standard score may indicate an item with a high user preference within the overall user preference distribution.

[0072] As described above, the electronic device (101) can determine a user's preference or level of interest in an item by considering not only the model score (225) but also the ranking and / or standard score. The electronic device (101) can determine a second recommended item (255) to recommend to the user based on the extended score (245), thereby providing the user with more appropriate recommended items.

[0073]

[0074] Figure 3 is a flowchart of a method for providing recommended items according to various embodiments.

[0075] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0076] According to one embodiment, operations (610) to (670) may be understood to be performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (101) (e.g., electronic device (101) of FIG. 1, FIG. 2).

[0077] For example, the electronic device (101) may receive a list of recommended items (215) from a server (e.g., server (108) of FIGS. 1 and 2) in operation (310). For example, a recommendation service (e.g., recommendation service (210) of FIG. 2) of the server (108) may generate a list of recommended items (e.g., list of recommended items (215) of FIG. 2).

[0078] For example, the electronic device (101) may input a list of recommended items (215) and user information (e.g., user information (230) of FIG. 2) in operation (320) into a learned recommendation model (e.g., recommendation model (220) of FIG. 2) to determine a model score (e.g., model score (225) of FIG. 2).

[0079] For example, user information (230) may include at least one of the user's past item consumption history, the type of recommendation model, and the user profile, or a combination thereof. For example, the type of recommendation model may be determined based on the nature and characteristics of the recommended item list, such as the type, category, and purpose of the items included in the recommended item list.

[0080] For example, the electronic device (101) can transmit the model score (225) to the server (108) in operation (330).

[0081] For example, the electronic device (101) may receive an extended score (e.g., extended score (245) of FIG. 2) of a first recommended item (e.g., first recommended item (250) of FIG. 2) determined by the server (108) from the server (108) in operation (340).

[0082] For example, the server (108) may receive model scores (225) from multiple external electronic devices and the electronic device (101) to generate statistical information (e.g., statistical information (235) of FIG. 2).

[0083] For example, the extended score (245) may include the rank and standard score of the model score (225) calculated for each item score group. The item score group may include model scores (225) received from the electronic device (101) and multiple external electronic devices (or multiple user terminals) for a specific item. The server (108) may use the item score group to calculate the rank (or rank within the group) and standard score of the model score (225) for the user's item.

[0084] The server (108) may calculate additional measures including ranks and standard scores (e.g., additional measures (240) of FIG. 2), and may calculate an extended score (245) for each item per user.

[0085] For example, the electronic device (101) may determine a second recommended item (e.g., the second recommended item (255) of FIG. 2) based on the expanded score (245) of the first recommended item (250) in operation (350). For example, the first recommended item (250) may represent a Pareto optimal solution calculated using the expanded scores (245) of items included in the recommended item list (215).

[0086] For example, the electronic device (101) may apply a weight (e.g., a weight (260) of FIG. 2) to the extended score (245) for the first recommended item (250) to determine the second recommended item (255) from among the first recommended items (250). For example, the electronic device (101) may determine the final score for each of the first recommended items (250) as the sum of the product of the weights (260) set for each component of the extended score (245) for the first recommended item (250). The electronic device (101) may determine the first recommended items (250) in a number set in descending order of final scores as the second recommended items (255).

[0087] For example, the electronic device (101) may provide the user with a second recommended item (255) in operation (360). For example, the electronic device (101) may provide the user with a list of second recommended items (255), information about the second recommended items (255), and link information for purchasing the second recommended items (255).

[0088] For example, the electronic device (101) may receive user feedback (e.g., user feedback (265) of FIG. 2) regarding at least one of the second recommended items (255). The user feedback (265) may include, but is not limited to, a user input selecting an item included in the second recommended items (255). For example, the user feedback (265) may include various information that may be obtained from the user while providing the second recommended items (255) to the user.

[0089] For example, the electronic device (101) may update a weight (260) based on the expanded score (245) of a second recommended item (255) selected by the user from among the second recommended items (255). The electronic device (101) may update the weight (260) based on user feedback (265). For example, the electronic device (101) may update the weight (260) to increase the expanded score (245) of an item that is the target of user feedback (265).

[0090]

[0091] FIGS. 4A, 4B, 4C, and 4D are tables showing model scores (e.g., model scores (225) of FIG. 2), extended scores (e.g., extended scores (245) of FIG. 2), and final scores according to various embodiments.

[0092] FIG. 4a is a table (410) showing model scores (225) according to various embodiments.

[0093] As shown in FIG. 4A, an electronic device (e.g., the electronic device (101) of FIGS. 1 and 2) can determine a model score (225) for each item included in a list of recommended items (e.g., the list of recommended items (215) of FIG. 2) using a recommendation model (e.g., the recommendation model (220) of FIG. 2). For example, the model score (225) can be determined within a range of 0 or more and 1 or less. The electronic device (101) can input the list of recommended items (215) and user information (e.g., the user information (230) of FIG. 2) into the recommendation model (220) to determine the model score (225).

[0094] FIG. 4B is a table (420) showing model scores (225) and additional measures (e.g., additional measures (240) of FIG. 2) according to various embodiments. The table (420) of FIG. 4B only shows additional measures (240) (rank within group, standard score) for user 1, but this is not limited thereto, and additional measures (240) for other users may be calculated.

[0095] For example, the server (108) may receive model scores (225) from the electronic device (101) and multiple external electronic devices, and generate statistical information (e.g., statistical information (235) of FIG. 2). For example, the statistical information (235) may include model scores (225) received from the electronic device (101) and multiple external electronic devices for each item.

[0096] For example, the server (108) can use a group of item scores to calculate an additional measure (240). The group of item scores can represent model scores (225) received from the electronic device (101) and multiple external electronic devices for a specific item.

[0097] For example, in table (420), the model score (225) for item 1 of user 1 is 0.93. The model score (225) for item 1 of user 1 may be the 20th highest score among the model scores for item 1 (or the group of item 1 scores). The model score (225) for item 1 of user 1 may correspond to a standard score of 2.5 in the distribution of the model scores for item 1 (or the group of item 1 scores). The server (108) may use the model score (225) for item 1 of user 1 and the distribution of the group of item 1 scores to calculate a rank and / or a standard score of the model score (225) for item 1 of user 1. The additional measure (240) for items 2 through N of user 1 may be determined to be substantially the same as the additional measure (240) for item 1 of user 1.

[0098] FIG. 4c is a table (430) showing expansion scores (245) according to various embodiments.

[0099] As shown in Table (430), the extended score (245) can be expressed as a (D+1)-dimensional real number vector. D can represent the number of additional measures (240).

[0100] For example, the server (108) can calculate an extended score (245) for each user and each item. As shown in Table (430), the server (108) can calculate an extended score (245) for each item for User 1. For example, the server (108) can calculate the extended score (245) for Item 1 of User 1 as (0.93, 20, 2.5). The server (108) can calculate an extended score (245) for each item for Users 2 through M, respectively.

[0101] FIG. 4d is a table (440) showing final scores according to various embodiments.

[0102] Table (440) shows an example of calculating the final score for each item (e.g., item 1 to item N) included in the first recommended item (250) when the weight set for the model score (225) (e.g., the weight (260) of FIG. 2) is 10.0, the weight set for the rank (260) is 1.0, and the weight set for the standard score (260) is 1.0. In table (440), since a higher final score indicates a higher user preference or interest in the item, the final score can be calculated by multiplying the rank of the extended score (245) by (-).

[0103] For example, the electronic device (101) can calculate the final score by using the sum (weighted sum) obtained by multiplying the weight (260) set as in table (440) by the components of the extended score (245) of each of the first recommended items (250).

[0104] The electronic device (101) can determine a set number of first recommendation items (250) with high final scores among N first recommendation items (250) as second recommendation items (255).

[0105] FIG. 4e is a table (450) for updating weights (260) according to various embodiments.

[0106] Table (450) shows an example of updating the weight (260) when Item 2 is selected by the user (or when the item corresponding to user feedback (e.g., user feedback (265) of FIG. 2) is Item 2).

[0107] In Table (450), can represent the weight (260) set for each component of the extended score (245). For example, The first weight set with respect to the model score (225), is the second weight set with respect to the ranking, may represent a third weight set with respect to the standard score.

[0108] In Table (450), can represent the update rate (or learning rate) set for each component. For example, is the first weight The update rate set for, is the second weight The update rate set for, is the third weight It can indicate the update rate set for .

[0109] In Table (450), can represent the final score of item i, can represent the final score of item 2 selected by the user.

[0110] As shown in Table (450), the electronic device (101) displays the final score of item 2 selected by the user. To increase the weight (260), the electronic device (101) can be updated as shown in the table (450). and calculate, to the new weight (260) can be updated.

[0111] Although the above-described FIGS. 2, 3, 4a, 4b, 4c, 4d, and 4e illustrate examples in which the server (108) processes statistical information (235) to calculate an additional measure (240) and / or an extended score (245), the present invention is not limited thereto. For example, the electronic device (101) may receive statistical information (235) from the server (108) and calculate an additional measure (240) using the received statistical information (235) and model score (225). The electronic device (101) may calculate an extended score (245) for each item using the calculated additional measure (240) and determine a first recommended item (250). The electronic device (101) can determine a second recommended item (255) by applying a weight (260) to each component of the extended score (245) of the determined first recommended item (250).

[0112]

[0113] FIG. 5 is a schematic block diagram of a recommendation system (500) according to various embodiments.

[0114] The recommendation system (500) illustrated in FIG. 5 is a diagram showing an example in which an electronic device (e.g., electronic device (101) of FIG. 1) receives statistical information (235) from a server (e.g., server (108) of FIG. 1) and calculates an extension score (245) using the received statistical information (235).

[0115] With respect to the description of the electronic device (101) and the server (108) illustrated in FIG. 5, descriptions that are substantially the same as those of the electronic device (101) and the server (108) illustrated in FIG. 2 may be omitted. Accordingly, even if the descriptions of the electronic device (101) and the server (108) illustrated in FIG. 5 are omitted, the contents described with respect to the electronic device (101) and the server (108) illustrated in FIG. 2 may be substantially identically applied with respect to the electronic device (101) and the server (108) illustrated in FIG. 5.

[0116] For example, the electronic device (101) may receive a list of recommended items (215) from the server (108). For example, the server (108) may generate the list of recommended items (215) using a recommendation system. The server (108) may transmit the list of recommended items (215) to the electronic device (101).

[0117] For example, the electronic device (101) can input a list of recommended items (215) and user information (230) into a learned recommendation model (220) to determine a model score (225).

[0118] For example, the electronic device (101) may receive statistical information (235) corresponding to the recommended item list (215) from the server (108). For example, the statistical information (235) may include model scores (225) collected and / or received from a plurality of external electronic devices (or a plurality of user terminals) for items included in the recommended item list (215). For example, the statistical information (235) may include a distribution of model scores (225) for items included in the recommended item list (215). User information (230) regarding a plurality of external electronic devices may be deleted or excluded from the statistical information (235).

[0119] For example, the electronic device (101) may calculate an extended score (245) for the recommended item list (215) based on the model score (225) and statistical information (235). For example, the electronic device (101) may calculate additional measures (240), such as a rank or standard score, of the model score (225) using the scores of each group of items included in the statistical information (235).

[0120] For example, the electronic device (101) can use additional measures (240) to calculate an extended score (245) for each item regarding the user of the electronic device (101). For example, when there are D additional measures (240), the extended score (245) can be expressed as a (D+1)-dimensional real number vector.

[0121] For example, the electronic device (101) may determine a primary recommended item (250) (or a first recommended item (250)) based on the extended score (245). For example, the first recommended item (250) may correspond to a Pareto optimal solution calculated using the model score (225), rank, and standard score.

[0122] For example, the electronic device (101) may determine a second recommended item (255) based on the extended score (245) of the first recommended item (250). For example, the electronic device (101) may determine a second recommended item (or a second recommended item (255)) by applying a weight (260) to each component of the extended score (245) of the first recommended item (250).

[0123] For example, the electronic device (101) can provide a second recommended item (255) to the user.

[0124] For example, the electronic device (101) can receive user feedback (265). The electronic device (101) can use the user feedback (265) to update the weights (260).

[0125]

[0126] Figure 6 is a flowchart of a method for providing recommended items according to various embodiments.

[0127] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0128] According to one embodiment, operations (610) to (670) may be understood to be performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (101) (e.g., electronic device (101) of FIG. 1, FIG. 5).

[0129] For example, the electronic device (101) may receive a list of recommended items (e.g., the list of recommended items (215) of FIG. 5) from a server (e.g., the server (108) of FIG. 1 and FIG. 5) in operation (610).

[0130] For example, the electronic device (101) may input a list of recommended items (215) and user information (e.g., user information (230) of FIG. 5) into a learned recommendation model (e.g., recommendation model (220) of FIG. 5) in operation (620) to determine a model score (e.g., model score (225) of FIG. 5).

[0131] With respect to the above operations (610) and (620), the descriptions regarding operations (310) and (320) of FIG. 3 can be applied substantially identically.

[0132] For example, the electronic device (101) may receive statistical information (e.g., statistical information (235) of FIG. 5) corresponding to the recommended item list (215) from the server (108) in operation (630). For example, the statistical information (235) may indicate information about a plurality of external electronic devices and / or information in which user information has been deleted and / or excluded. The statistical information (235) may include model scores (225) collected or received from a plurality of external electronic devices for items included in the recommended item list (215).

[0133] For example, the electronic device (101) can calculate an extended score (e.g., an extended score (245) of FIG. 5) for a list of recommended items (215) based on the model score (225) and statistical information (235) in operation (640).

[0134] For example, the electronic device (101) can use the model score (225) for each item to calculate an additional measure (e.g., an additional measure (240) of FIG. 5) for each item. For example, the electronic device (101) can use the model score (225) for item i and a group of item i scores to determine a rank and standard score for item i. An extended score (245) can be calculated for each item, and each can include the model score (225) and the additional measure (240).

[0135] For example, the electronic device (101) may determine a first recommended item (e.g., the first recommended item (250) of FIG. 5) based on the extended score (245) in operation (650). For example, the electronic device (101) may determine a Pareto optimal solution calculated based on the components of the extended score (245) as the first recommended item (250).

[0136] For example, the electronic device (101) may determine a second recommended item (e.g., the second recommended item (255) of FIG. 5) based on the expanded score (245) of the first recommended item (250) in operation (660). For example, the electronic device (101) may determine a weighted sum obtained by applying a weight (260) to each component of the expanded score (245) as a final score. The electronic device (101) may determine a set number of first recommended items (250) with high final scores as the second recommended items (255).

[0137] For example, the electronic device (101) may provide a second recommended item (255) to the user in operation (670).

[0138]

[0139] Figures 7 and 8 are schematic block diagrams of a recommendation system according to various embodiments.

[0140] With respect to the description of the electronic device (101) (e.g., the electronic device (101) of FIGS. 1 and 2) and the server (the server (108) of FIGS. 1 and 2) illustrated in FIGS. 7 and 8, descriptions that are substantially the same as those of the electronic device (101) and the server (108) illustrated in FIG. 2 may be omitted. Accordingly, even if the descriptions of the electronic device (101) and the server (108) illustrated in FIGS. 7 and 8 are omitted, the contents described with respect to the electronic device (101) and the server (108) illustrated in FIGS. 2 may be substantially equally applied to the electronic device (101) and the server (108) illustrated in FIGS. 7 and 8.

[0141] The recommendation system (700) of FIG. 7 is an example of a server-centric recommendation system.

[0142] For example, the server (108) can determine a model score (225) using a recommendation model (220). The server (108) can receive and store user information (230) from the electronic device (101). For example, the server (108) can generate a recommendation item list (215) and input the generated recommendation item list (215) and user information (230) into the recommendation model (220) to determine a model score (225).

[0143] For example, the server (108) can generate statistical information (235) using the model score (225).

[0144] The server (108) can calculate an additional measure (240) using statistical information (235). The server (108) can calculate an extended score (245) for each user using the additional measure (240) and the model score (225). The server (108) can use the extended score (245) to determine a primary recommended item (250) (or a first recommended item (250)).

[0145] For example, the electronic device (101) may receive a first recommended item (250) and / or an extended score (245) of the first recommended item (250) from the server (108). The electronic device (101) may use the extended score (245) and weight (260) of the first recommended item (250) to determine a second recommended item (or second recommended item (255)).

[0146] For example, the electronic device (101) can receive user feedback (265). The electronic device (101) can update the weights (260) based on the user feedback (265).

[0147] The recommendation system (800) of FIG. 8 is an example of a hybrid recommendation system that separates the recommendation model (220) into a first recommendation model (220-1) and a second recommendation model (220-2).

[0148] For example, in FIG. 8, the first recommendation model (220-1) may represent a module and / or part that requires data stored in the server (108) or a function performed by the server (108) among the recommendation models (220) of FIG. 2. For example, in FIG. 8, the second recommendation model (220-2) may represent a module and / or part that requires data stored in the electronic device (101) or a function performed by the electronic device (101) among the recommendation models (220) of FIG. 2.

[0149] For example, the server (108) can generate a list of recommended items (215) using the recommendation service (210). The server (108) can input the list of recommended items (215) into the first recommendation model (220-1). The server (108) can transmit the output of the first recommendation model (220-1) to the electronic device (101). The electronic device (101) can input the output of the first recommendation model (220-1) and user information (230) into the second recommendation model (220-2) to determine the model score (225).

[0150] The electronic device (101) can transmit the model score (225) to the server (108). The server (108) can calculate an additional measure (240) using the statistical information (235). The server (108) can calculate an extension score (245) using the additional measure (240). The server (108) can determine a primary recommendation item (250) (or a first recommendation item (250)) using the extension score (245). The server (108) can transmit the first recommendation item (250) and / or the extension score (245) of the first recommendation item (250) to the electronic device (101). The electronic device (101) can determine a secondary recommendation item (or a second recommendation item (255)) using the extension score (245) and weight (260) of the first recommendation item (250). The electronic device (101) can update the weights (260) based on user feedback (265).

[0151]

[0152] FIG. 9 is a diagram illustrating an interface (910) for updating weights (260) according to various embodiments. The electronic device (101) may display the interface (910) as shown in the screen (900) to set component-specific weights (260). For example, the electronic device (101) may initially set component-specific weights (260) (e.g., the first weight, the second weight, and the third weight of FIG. 4d or 4e) through the interface (910). For example, the electronic device (101) may adjust component-specific weights (260) through the interface (910).

[0153]

[0154] An electronic device (e.g., an electronic device (101) of FIGS. 1 and 2) according to various embodiments may include a processor (e.g., a processor (120) of FIG. 1) and a memory (e.g., a memory (130) of FIG. 1) electrically coupled to the processor (120) and storing instructions executable by the processor (120). When the instructions are executed, the processor (120) may cause the electronic device (101) to receive a list of recommended items (e.g., a list of recommended items (215) of FIG. 2) from a server (e.g., a server (108) of FIGS. 1 and 2). The processor (120) may input the recommended item list (215) and user information (e.g., user information (230) of FIG. 2) into a learned recommendation model (e.g., recommendation model (220) of FIG. 2) to determine a model score (e.g., model score (225) of FIG. 2). The processor (120) may transmit the model score (225) to the server (108). The processor (120) may receive, from the server (108), an extended score (e.g., extended score (245) of FIG. 2) of a first recommended item (e.g., first recommended item (250) of FIG. 2) determined by the server (108). The processor (120) may determine a second recommended item (e.g., the second recommended item (255) of FIG. 2) based on the extended score (245) of the first recommended item (250). The processor (120) may provide the second recommended item (255) to the user.

[0155] The above-mentioned extended score (245) may include a rank and standard score of the model score (225) calculated for each item score group based on the model scores (225) collected from multiple user terminals.

[0156] The above first recommended item (250) may correspond to a Pareto optimal solution calculated using the model score (225), the ranking, and the standard score for each recommended item included in the extended score (245).

[0157] The processor (120) may apply a weight (260) to the extended score (245) regarding the first recommended item (250) to determine the second recommended item (255) among the first recommended items (250).

[0158] The processor (120) may update the weight (260) based on the extended score (245) of the second recommended item (255) selected by the user among the second recommended items (255).

[0159] The above user information (230) may include at least one of the user's past item consumption history, the type of recommended model, and the user profile.

[0160] An electronic device (e.g., the electronic device (101) of FIGS. 1 and 5) according to various embodiments may include a processor (120) and a memory (130) electrically coupled to the processor (120) and storing instructions executable by the processor (120). When the instructions are executed, the processor (120) may cause the electronic device (101) to receive a list of recommended items (e.g., the list of recommended items (215) of FIG. 5) from a server (108). The processor (120) may input the list of recommended items (215) and user information (e.g., the user information (230) of FIG. 5) into a learned recommendation model (e.g., the recommendation model (220) of FIG. 5) to determine a model score (e.g., the model score (225) of FIG. 5). The processor (120) may receive statistical information (e.g., statistical information (235) of FIG. 5) corresponding to the recommended item list (215) from the server (108). The processor (120) may calculate an extended score (e.g., extended score (245) of FIG. 5) for the recommended item list (215) based on the model score (225) and the statistical information (235). The processor (120) may determine a first recommended item (e.g., extended score (245) of FIG. 5) based on the extended score (245). The processor (120) may determine a second recommended item (e.g., second recommended item (255) of FIG. 5) based on the extended score (245) of the first recommended item (250). The above processor (120) can provide the second recommended item (255) to the user.

[0161] The processor (120) may calculate the extended score (245) including the rank and standard score of the model score (225) calculated for each item score group based on the statistical information (235).

[0162] The above first recommended item (250) may correspond to a Pareto optimal solution calculated using the model score (225), the ranking, and the standard score for each recommended item included in the extended score (245).

[0163] The processor (120) may apply a weight (260) to the extended score (245) regarding the first recommended item (250) to determine the second recommended item (255) among the first recommended items (250).

[0164] The processor (120) may update the weight (260) based on the extended score (245) of the second recommended item (255) selected by the user among the second recommended items (255).

[0165] The above user information (230) may include at least one of the user's past item consumption history, the type of recommended model, and the user profile.

[0166] A method for providing recommended items according to various embodiments includes: an operation of receiving a list of recommended items (e.g., a list of recommended items (215) of FIG. 2) from a server (e.g., a server (108) of FIGS. 1 and 2); an operation of inputting the list of recommended items (215) and user information (e.g., user information (230) of FIG. 2) into a learned recommendation model (e.g., a recommendation model (220) of FIG. 2) to determine a model score (e.g., a model score (225) of FIG. 2); an operation of transmitting the model score (225) to the server (108); an operation of receiving, from the server (108), an extended score (e.g., an extended score (245) of FIG. 2) of a first recommended item (e.g., a first recommended item (250) of FIG. 2) determined by the server (108); and, based on the extended score (245) of the first recommended item (250), a second recommended item (e.g., a second recommended item of FIG. 2) It may include an action of determining an item (255) and an action of providing the second recommended item (255) to the user.

[0167] The above-mentioned extended score (245) may include a rank and standard score of the model score (225) calculated for each item score group based on the model scores (225) collected from multiple user terminals.

[0168] The above first recommended item (250) may correspond to a Pareto optimal solution calculated using the model score (225), the ranking, and the standard score for each recommended item included in the extended score (245).

[0169] The operation of determining the second recommended item (255) may include an operation of determining the second recommended item (255) among the first recommended items (250) by applying a weight (260) to the extended score (245) regarding the first recommended item (250).

[0170] The above method for providing recommended items may further include an operation of updating the weight (260) based on the extended score (245) of the second recommended item (255) selected by the user among the second recommended items (255).

[0171] The above user information (230) may include at least one of the user's past item consumption history, the type of recommended model, and the user profile.

[0172]

[0173] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0174] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0175] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0176] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0177] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0178] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device (101), Processor (120); and A memory (130) electrically coupled to the processor (120) and storing instructions executable by the processor (120) Including, The above processor (120) When the above command is executed, the electronic device (101) receives a list of recommended items (215) from the server (108); The above recommended item list (215) and user information (230) are input into the learned recommendation model (220) to determine the model score (225); The above model score (225) is transmitted to the server (108); From the above server (108), receive the extended score (245) of the first recommended item (250) determined by the above server (108); Based on the extended score (245) of the first recommended item (250), a second recommended item (255) is determined; To provide the above second recommended item (255) to the user, Electronic device (101).

2. In paragraph 1, The above extended score (245) is Based on the model scores (225) collected from multiple user terminals, the rank and standard score of the model scores (225) calculated for each item score group are included. Electronic device (101).

3. In paragraph 2, The above first recommended item (250) is Corresponding to the Pareto optimal solution calculated using the model score (225), the rank, and the standard score for each recommended item included in the above extended score (245). Electronic device (101).

4. In any one of paragraphs 1 to 3, The above processor (120) By applying a weight (260) to the extended score (245) of the first recommended item (250), the second recommended item (255) is determined among the first recommended items (250). Electronic device (101).

5. In any one of paragraphs 1 to 4, The above processor (120) To update the weight (260) based on the extended score (245) of the second recommended item (255) selected by the user among the second recommended items (255). Electronic devices (101).

6. In any one of paragraphs 1 to 5, The above user information (230) is Containing at least one of the user's past item consumption history, the type of recommended model (220), and the user profile. Electronic devices (101).

7. An operation of receiving a list of recommended items (215) from a server (108); An operation of inputting the above recommended item list (215) and user information (230) into a learned recommendation model (220) and determining a model score (225); An action of transmitting the above model score (225) to the server (108); An operation of receiving an extended score (245) of a first recommended item (250) determined by the server (108) from the server (108); An operation of determining a second recommended item (255) based on the extended score (245) of the first recommended item (250); and An action of providing the above second recommended item (255) to the user Including, How to provide recommended items.

8. In paragraph 7, The above extended score (245) is Based on the model scores (225) collected from multiple user terminals, the rank and standard score of the model scores (225) calculated for each item score group are included. How to provide recommended items.

9. In paragraph 8, The above first recommended item (250) is Corresponding to the Pareto optimal solution calculated using the model score (225), the rank, and the standard score for each recommended item included in the above extended score (245). How to provide recommended items.

10. In any one of paragraphs 7 to 9, The operation of determining the above second recommended item (255) is as follows: An operation of determining the second recommended item (255) among the first recommended items (250) by applying a weight (260) to the extended score (245) regarding the first recommended item (250) Including, How to provide recommended items.

11. In any one of paragraphs 7 to 10, An operation of updating the weight (260) based on the extended score (245) of the second recommended item (255) selected by the user among the second recommended items (255) Including more, How to provide recommended items.

12. In any one of paragraphs 7 to 11, The above user information (230) is Containing at least one of the user's past item consumption history, the type of recommended model (220), and the user profile. How to provide recommended items.

13. A computer-readable recording medium having recorded thereon a program for executing a method for providing recommended items according to any one of clauses 7 to 12.

Images