CN115809362A - Content recommendation method and electronic equipment - Google Patents

Abstract

The method comprises the steps of obtaining user data, determining target application according to the user data, sending a recommendation request comprising the user data to the target application, receiving recommendation content returned by the target application in response to the recommendation request, and outputting the recommendation content to a user. The content recommendation can be carried out to the user by means of the recommendation capability of the application, the cost of developing and maintaining the content recommendation algorithm corresponding to the field is reduced, and the cost of paying the producer of the content is also reduced.

Description

Content recommendation method and electronic equipment

Technical Field

The embodiment of the application relates to the field of information processing, in particular to a content recommendation method and electronic equipment.

Background

Existing content recommendation systems (e.g., advertisement recommendation systems, information recommendation systems, hotel search recommendation systems, e-commerce recommendation systems, music recommendation systems, or short video recommendation systems, etc.) all need to analyze and understand the needs of users, and filter information based on the needs of users, so as to recommend content meeting the needs of users to users. Each content recommendation system recommends content in a certain field, for example, a music recommendation system recommends only content in a music field, a short video recommendation system recommends only content in a short video field, a content recommendation algorithm corresponding to the field is often required to be developed and maintained, and in some scenes, remuneration needs to be paid to a producer of the content, such as music, film and television copyright, video playing profit, and the like.

Disclosure of Invention

The embodiment of the application discloses a content recommendation method and electronic equipment, which can recommend content to a user by means of recommendation capability of an application, reduce the cost of developing and maintaining a content recommendation algorithm corresponding to the field, and reduce the cost of paying remuneration to a content producer.

In a first aspect, an embodiment of the present application provides a content recommendation method, including: the method comprises the steps of obtaining user data, determining target application according to the user data, sending a recommendation request including the user data to the target application, receiving recommendation content returned by the target application responding to the recommendation request, and outputting the recommendation content to a user.

In the embodiment of the application, a target application can be determined according to user data, recommended contents recommended by different applications are different, the target application has recommendation capability, input and output specifications are well defined with the target application, received user data are transmitted to the target application according to the well-defined input specifications, the target application can recommend corresponding recommended contents by combining the user data and a content recommendation algorithm of the target application after receiving the user data, the recommended contents output by the target application are received according to the well-defined output specifications, and the recommended contents are output to a user. The content recommendation method and the content recommendation system can recommend the content to the user by means of the recommendation capability of the application, do not need to perform content recommendation after screening and filtering information based on the requirement of the user, reduce the cost of developing and maintaining a content recommendation algorithm corresponding to the field, and reduce the cost of paying the remuneration to the producer of the content.

In one possible implementation manner, the receiving the recommended content returned by the target application in response to the recommendation request includes: receiving the recommended content and the recommendation reason returned by the target application in response to the recommendation request, wherein the outputting the recommended content to the user includes: and sorting the recommended contents according to the recommendation reason, and outputting the sorted recommended contents to the user.

In one possible implementation manner, the determining a target application according to the user data includes: and mapping the user data to corresponding domain labels, wherein each domain label corresponds to a class of applications, and determining a first application corresponding to the domain label as a target application.

In one possible implementation manner, the domain label includes a plurality of domain labels, and the first application corresponding to each domain label is different.

In one possible implementation manner, the sending the recommendation request including the user data to the target application includes: determining a corresponding user intention according to the user data, determining a feature tag of a field corresponding to the field tag according to the user data, and sending a recommendation request to the target application, wherein the recommendation request comprises the user intention and the feature tag related to the field tag corresponding to the target application.

In one possible implementation, the method further includes: establishing an intention system and a label system, wherein the intention system comprises the user data and the corresponding user intention, and the label system comprises the user data and the corresponding domain label and the feature label.

In one possible implementation manner, the sorting the recommended content according to the reason for recommendation and outputting the sorted recommended content to the user includes: calculating the matching degree of the user data, the recommended content and the recommendation reason; and sequencing the recommended contents according to the matching degree.

In one possible implementation manner, the method further includes: and obtaining feedback of the user after the recommended content is output to the user, and scoring the target application outputting the recommended content according to the feedback of the user.

In one possible implementation, the method further includes: setting a corresponding feedback scoring mode according to the target application, wherein scoring the target application outputting the recommended content according to the feedback of the user comprises obtaining the feedback scoring mode corresponding to the target application, and scoring the target application outputting the recommended content according to the feedback of the user and the feedback scoring mode.

In one possible implementation manner, the method further includes: after the recommended content is output to the user, the grade of the user on the recommended content is periodically sampled to obtain a first grade, and the target application is scored according to the first grade.

In one possible implementation manner, the method further includes: after the recommended content is output to a user, the user data and the corresponding recommended content are sampled periodically, the matching degree of the user data and the corresponding recommended content is calculated, a first matching degree is obtained, and the target application is scored according to the first matching degree.

In one possible implementation manner, the method further includes: after the recommended content is output to the user, the recommended content and the corresponding recommendation reason are periodically sampled, the matching degree of the recommended content and the corresponding recommendation reason is calculated, a second matching degree is obtained, and the target application is scored according to the second matching degree.

In a second aspect, embodiments of the present application provide a computer-readable storage medium containing computer-executable instructions for performing the above-described method.

In a third aspect, an embodiment of the present application provides a system, where the system includes: the computer-readable storage medium described above; and a processor capable of executing the computer-executable instructions.

In a fifth aspect, an embodiment of the present application provides an electronic device, including: at least one memory for storing a program; and at least one processor for executing the memory-stored program, the processor for performing the method as described above when the memory-stored program is executed.

For the advantageous effects of the other aspects, reference may be made to the description of the advantageous effects of the method aspects, which is not repeated herein.

Drawings

Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Fig. 2 is a schematic structural diagram of a content recommendation system according to an embodiment of the present application.

Fig. 3 is a schematic diagram of an operation of a request module according to an embodiment of the present application.

Fig. 4 is a schematic working diagram of a monitoring module according to an embodiment of the present application.

Fig. 5 is a schematic flow chart of a content recommendation method according to an embodiment of the present application.

Fig. 6 is a flowchart illustrating another content recommendation method according to an embodiment of the present application.

Fig. 7 is a flowchart illustrating another content recommendation method according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. In the description of the embodiments herein, "/" means "or" unless otherwise specified, for example, a/B may mean a or B; "and/or" herein is merely an association relationship describing an associated object, and means that there may be three relationships, for example, a and/or B, and may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "a plurality" means two or more than two.

In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present embodiment, "a plurality" means two or more unless otherwise specified.

In the embodiments of the present application, words such as "exemplary," "for example," or "in some examples," etc., are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "exemplary," "e.g.," or "in some examples," etc., are intended to present relevant concepts in a concrete fashion.

To how multi-domain content recommendation is implemented as described above. The embodiment of the application provides a content recommendation method, which includes the steps of obtaining user data, such as at least one of personal data, behavior information, user portrait and real-time context related information of a user, determining a target application according to the user data, wherein the target application has content recommendation capability, transmitting the user data to the target application to request the target application to recommend corresponding content according to the user data, obtaining recommended content and recommendation reasons output by the target application, sequencing the recommended content of each target application according to content description and the user data, and outputting the recommended content which is ranked in the front.

The electronic device in the embodiment of the application may be a portable computer (e.g., a mobile phone), a notebook computer, a Personal Computer (PC), a wearable electronic device (e.g., an intelligent watch), a tablet computer, an intelligent home device, an Augmented Reality (AR) \ Virtual Reality (VR) device, an Artificial Intelligence (AI) terminal (e.g., an intelligent robot), a vehicle-mounted computer, or the like, and the following embodiment does not specially limit the specific form of the electronic device.

Taking an electronic device as an example of a mobile phone, fig. 1 shows a schematic structural diagram of the electronic device.

The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a Universal Serial Bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, a Subscriber Identity Module (SIM) card interface 195, and the like. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, and the like.

It is to be understood that the illustrated structure of the embodiment of the present application does not specifically limit the electronic device 100. In other embodiments of the present application, electronic device 100 may include more or fewer components than shown, or some components may be combined, some components may be split, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

Processor 110 may include one or more processing units, such as: the processor 110 may include an Application Processor (AP), a modem processor, a Graphics Processor (GPU), an Image Signal Processor (ISP), a controller, a video codec, a Digital Signal Processor (DSP), a baseband processor, and/or a neural-Network Processing Unit (NPU), among others. The different processing units may be separate devices or may be integrated into one or more processors.

The controller can generate an operation control signal according to the instruction operation code and the timing signal to complete the control of instruction fetching and instruction execution.

A memory may also be provided in processor 110 for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may hold instructions or data that have just been used or recycled by the processor 110. If the processor 110 needs to reuse the instruction or data, it can be called directly from memory. Avoiding repeated accesses reduces the latency of the processor 110, thereby increasing the efficiency of the system.

In some embodiments, processor 110 may include one or more interfaces. The interface may include an integrated circuit (I2C) interface, an integrated circuit built-in audio (I2S) interface, a Pulse Code Modulation (PCM) interface, a universal asynchronous receiver/transmitter (UART) interface, a mobile industry processor interface (mobile industry processor interface, MIPI), a general-purpose-input/output (GPIO) interface, a Subscriber Identity Module (SIM) interface, and/or a Universal Serial Bus (USB) interface, etc.

The I2C interface is a bidirectional synchronous serial bus including a serial data line (SDA) and a Serial Clock Line (SCL). In some embodiments, processor 110 may include multiple sets of I2C buses. The processor 110 may be coupled to the touch sensor 180K, the charger, the flash, the camera 193, etc. through different I2C bus interfaces, respectively. For example: the processor 110 may be coupled to the touch sensor 180K through an I2C interface, so that the processor 110 and the touch sensor 180K communicate through an I2C bus interface to implement a touch function of the electronic device 100.

The I2S interface may be used for audio communication. In some embodiments, processor 110 may include multiple sets of I2S buses. The processor 110 may be coupled to the audio module 170 through an I2S bus to enable communication between the processor 110 and the audio module 170. In some embodiments, the audio module 170 may transmit the audio signal to the wireless communication module 160 through the I2S interface, so as to implement a function of receiving a call through a bluetooth headset.

The PCM interface may also be used for audio communication, sampling, quantizing and encoding analog signals. In some embodiments, the audio module 170 and the wireless communication module 160 may be coupled by a PCM bus interface. In some embodiments, the audio module 170 may also transmit the audio signal to the wireless communication module 160 through the PCM interface, so as to implement the function of answering a call through the bluetooth headset. Both the I2S interface and the PCM interface may be used for audio communication.

The UART interface is a universal serial data bus used for asynchronous communications. The bus may be a bidirectional communication bus. It converts the data to be transmitted between serial communication and parallel communication. In some embodiments, a UART interface is generally used to connect the processor 110 with the wireless communication module 160. For example: the processor 110 communicates with a bluetooth module in the wireless communication module 160 through a UART interface to implement a bluetooth function. In some embodiments, the audio module 170 may transmit the audio signal to the wireless communication module 160 through a UART interface, so as to implement the function of playing music through a bluetooth headset.

MIPI interfaces may be used to connect processor 110 with peripheral devices such as display screen 194, camera 193, and the like. The MIPI interface includes a Camera Serial Interface (CSI), a Display Serial Interface (DSI), and the like. In some embodiments, processor 110 and camera 193 communicate through a CSI interface to implement the capture functionality of electronic device 100. The processor 110 and the display screen 194 communicate through the DSI interface to implement the display function of the electronic device 100.

The GPIO interface may be configured by software. The GPIO interface may be configured as a control signal and may also be configured as a data signal. In some embodiments, a GPIO interface may be used to connect the processor 110 with the camera 193, the display 194, the wireless communication module 160, the audio module 170, the sensor module 180, and the like. The GPIO interface may also be configured as an I2C interface, I2S interface, UART interface, MIPI interface, and the like.

The USB interface 130 is an interface conforming to the USB standard specification, and may specifically be a Mini USB interface, a Micro USB interface, a USB Type C interface, or the like. The USB interface 130 may be used to connect a charger to charge the electronic device 100, and may also be used to transmit data between the electronic device 100 and a peripheral device. And the earphone can also be used for connecting an earphone and playing audio through the earphone. The interface may also be used to connect other electronic devices, such as AR devices and the like.

It should be understood that the interface connection relationship between the modules illustrated in the embodiments of the present application is only an illustration, and does not limit the structure of the electronic device 100. In other embodiments of the present application, the electronic device 100 may also adopt different interface connection manners or a combination of multiple interface connection manners in the above embodiments.

The charging management module 140 is configured to receive charging input from a charger. The charger may be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 may receive charging input from a wired charger via the USB interface 130. In some wireless charging embodiments, the charging management module 140 may receive a wireless charging input through a wireless charging coil of the electronic device 100. The charging management module 140 may also supply power to the electronic device through the power management module 141 while charging the battery 142.

The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and/or the charge management module 140, and supplies power to the processor 110, the internal memory 121, the display 194, the camera 193, the wireless communication module 160, and the like. The power management module 141 may also be used to monitor parameters such as battery capacity, battery cycle count, battery state of health (leakage, impedance), etc. In some other embodiments, the power management module 141 may also be disposed in the processor 110. In other embodiments, the power management module 141 and the charging management module 140 may also be disposed in the same device.

The wireless communication function of the electronic device 100 may be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, a modem processor, a baseband processor, and the like.

The antennas 1 and 2 are used for transmitting and receiving electromagnetic wave signals. Each antenna in the electronic device 100 may be used to cover a single or multiple communication bands. Different antennas can also be multiplexed to improve the utilization of the antennas. For example: the antenna 1 may be multiplexed as a diversity antenna of a wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

The mobile communication module 150 may provide a solution including 2G/3G/4G/5G wireless communication applied to the electronic device 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a Low Noise Amplifier (LNA), and the like. The mobile communication module 150 may receive the electromagnetic wave from the antenna 1, filter, amplify, etc. the received electromagnetic wave, and transmit the electromagnetic wave to the modem processor for demodulation. The mobile communication module 150 may also amplify the signal modulated by the modem processor, and convert the signal into electromagnetic wave through the antenna 1 to radiate the electromagnetic wave. In some embodiments, at least some of the functional modules of the mobile communication module 150 may be disposed in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 may be disposed in the same device as at least some of the modules of the processor 110.

The modem processor may include a modulator and a demodulator. The modulator is used for modulating a low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used for demodulating the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then passes the demodulated low frequency baseband signal to a baseband processor for processing. The low frequency baseband signal is processed by the baseband processor and then transferred to the application processor. The application processor outputs a sound signal through an audio device (not limited to the speaker 170A, the receiver 170B, etc.) or displays an image or video through the display screen 194. In some embodiments, the modem processor may be a stand-alone device. In other embodiments, the modem processor may be provided in the same device as the mobile communication module 150 or other functional modules, independent of the processor 110.

The wireless communication module 160 may provide a solution for wireless communication applied to the electronic device 100, including Wireless Local Area Networks (WLANs) (e.g., wireless fidelity (Wi-Fi) networks), bluetooth (bluetooth, BT), global Navigation Satellite System (GNSS), frequency Modulation (FM), near Field Communication (NFC), infrared (IR), and the like. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, performs frequency modulation and filtering processing on electromagnetic wave signals, and transmits the processed signals to the processor 110. The wireless communication module 160 may also receive a signal to be transmitted from the processor 110, perform frequency modulation and amplification on the signal, and convert the signal into electromagnetic waves via the antenna 2 to radiate the electromagnetic waves.

In some embodiments, antenna 1 of electronic device 100 is coupled to mobile communication module 150 and antenna 2 is coupled to wireless communication module 160 so that electronic device 100 can communicate with networks and other devices through wireless communication techniques. The wireless communication technology may include global system for mobile communications (GSM), general Packet Radio Service (GPRS), code division multiple access (code division multiple access, CDMA), wideband Code Division Multiple Access (WCDMA), time-division code division multiple access (time-division code division multiple access, TD-SCDMA), long Term Evolution (LTE), LTE, BT, GNSS, WLAN, NFC, FM, and/or IR technologies, etc. GNSS may include Global Positioning System (GPS), global navigation satellite system (GLONASS), beidou satellite navigation system (BDS), quasi-zenith satellite system (QZSS), and/or Satellite Based Augmentation System (SBAS).

The electronic device 100 implements display functions via the GPU, the display screen 194, and the application processor. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.

The display screen 194 is used to display images, video, and the like. The display screen 194 includes a display panel. The display panel may be a Liquid Crystal Display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (active-matrix organic light-emitting diode, AMOLED), a flexible light-emitting diode (FLED), a miniature, a Micro-oeld, a quantum dot light-emitting diode (QLED), or the like. In some embodiments, the electronic device 100 may include 1 or N display screens 194, N being a positive integer greater than 1.

The electronic device 100 may implement a shooting function through the ISP, the camera 193, the video codec, the GPU, the display 194, the application processor, and the like.

The ISP is used to process the data fed back by the camera 193. For example, when a photo is taken, the shutter is opened, light is transmitted to the camera photosensitive element through the lens, the optical signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing and converting into an image visible to naked eyes. The ISP can also carry out algorithm optimization on noise, brightness and skin color of the image. The ISP can also optimize parameters such as exposure, color temperature and the like of a shooting scene. In some embodiments, the ISP may be provided in camera 193.

The camera 193 is used to capture still images or video. The object generates an optical image through the lens and projects the optical image to the photosensitive element. The photosensitive element may be a Charge Coupled Device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The light sensing element converts the optical signal into an electrical signal, which is then passed to the ISP where it is converted into a digital image signal. And the ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into image signal in standard RGB, YUV and other formats. In some embodiments, electronic device 100 may include 1 or N cameras 193, N being a positive integer greater than 1.

The digital signal processor is used for processing digital signals, and can process digital image signals and other digital signals. For example, when the electronic device 100 selects a frequency bin, the digital signal processor is used to perform fourier transform or the like on the frequency bin energy.

Video codecs are used to compress or decompress digital video. The electronic device 100 may support one or more video codecs. In this way, the electronic device 100 may play or record video in a variety of encoding formats, such as: moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, MPEG4, and the like.

The NPU is a neural-network (NN) computing processor that processes input information quickly by using a biological neural network structure, for example, by using a transfer mode between neurons of a human brain, and can also learn by itself continuously. Applications such as intelligent recognition of the electronic device 100 can be realized through the NPU, for example: image recognition, face recognition, speech recognition, text understanding, and the like.

The internal memory 121 may include one or more Random Access Memories (RAMs) and one or more non-volatile memories (NVMs).

The random access memory may include static random-access memory (SRAM), dynamic random-access memory (DRAM), synchronous dynamic random-access memory (SDRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM), such as fifth generation DDR SDRAM generally referred to as DDR5 SDRAM, and the like;

the nonvolatile memory may include a magnetic disk storage device, a flash memory (flash memory).

The FLASH memory may include NOR FLASH, NAND FLASH, 3D NAND FLASH, etc. according to the operation principle, may include single-level cell (SLC), multi-level cell (MLC), triple-level cell (TLC), quad-level cell (QLC), etc. according to the level order of the memory cell, and may include universal FLASH memory (english: UFS), embedded multimedia memory Card (mc em), etc. according to the storage specification.

The random access memory may be read and written directly by the processor 110, may be used to store executable programs (e.g., machine instructions) of an operating system or other programs in operation, and may also be used to store data of users and applications, etc.

The nonvolatile memory may also store executable programs, data of users and application programs, and the like, and may be loaded in advance into the random access memory for the processor 110 to directly read and write.

The external memory interface 120 may be used to connect an external nonvolatile memory, so as to expand the storage capability of the electronic device 100. The external non-volatile memory communicates with the processor 110 through the external memory interface 120 to implement data storage functions. For example, files such as music, video, etc. are saved in an external nonvolatile memory.

The electronic device 100 may implement audio functions via the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone interface 170D, and the application processor. Such as music playing, recording, etc.

The audio module 170 is used to convert digital audio information into analog audio signals for output, and also used to convert analog audio inputs into digital audio signals. The audio module 170 may also be used to encode and decode audio signals. In some embodiments, the audio module 170 may be disposed in the processor 110, or some functional modules of the audio module 170 may be disposed in the processor 110.

The speaker 170A, also called a "horn", is used to convert the audio electrical signal into an acoustic signal. The electronic apparatus 100 can listen to music through the speaker 170A or listen to a handsfree call.

The receiver 170B, also called "earpiece", is used to convert the electrical audio signal into an acoustic signal. When the electronic apparatus 100 receives a call or voice information, it can receive voice by placing the receiver 170B close to the ear of the person.

The microphone 170C, also referred to as a "microphone," is used to convert sound signals into electrical signals. When making a call or transmitting voice information, the user can input a voice signal to the microphone 170C by speaking near the microphone 170C through the mouth. The electronic device 100 may be provided with at least one microphone 170C. In other embodiments, the electronic device 100 may be provided with two microphones 170C to achieve a noise reduction function in addition to collecting sound signals. In other embodiments, the electronic device 100 may further include three, four or more microphones 170C to collect sound signals, reduce noise, identify sound sources, perform directional recording, and so on.

The earphone interface 170D is used to connect a wired earphone. The headset interface 170D may be the USB interface 130, or may be a 3.5mm open mobile electronic device platform (OMTP) standard interface, a cellular telecommunications industry association (cellular telecommunications industry association of the USA, CTIA) standard interface.

The pressure sensor 180A is used for sensing a pressure signal, and can convert the pressure signal into an electrical signal. In some embodiments, the pressure sensor 180A may be disposed on the display screen 194. The pressure sensor 180A can be of a wide variety, such as a resistive pressure sensor, an inductive pressure sensor, a capacitive pressure sensor, and the like. The capacitive pressure sensor may be a sensor comprising at least two parallel plates having an electrically conductive material. When a force acts on the pressure sensor 180A, the capacitance between the electrodes changes. The electronic device 100 determines the strength of the pressure from the change in capacitance. When a touch operation is applied to the display screen 194, the electronic apparatus 100 detects the intensity of the touch operation according to the pressure sensor 180A. The electronic apparatus 100 may also calculate the touched position from the detection signal of the pressure sensor 180A. In some embodiments, the touch operations that are applied to the same touch position but different touch operation intensities may correspond to different operation instructions. For example: and when the touch operation with the touch operation intensity smaller than the first pressure threshold value acts on the short message application icon, executing an instruction for viewing the short message. And when the touch operation with the touch operation intensity larger than or equal to the first pressure threshold value acts on the short message application icon, executing an instruction of newly building the short message.

The gyro sensor 180B may be used to determine the motion attitude of the electronic device 100. In some embodiments, the angular velocity of electronic device 100 about three axes (i.e., the x, y, and z axes) may be determined by gyroscope sensor 180B. The gyro sensor 180B may be used for photographing anti-shake. Illustratively, when the shutter is pressed, the gyro sensor 180B detects a shake angle of the electronic device 100, calculates a distance to be compensated for the lens module according to the shake angle, and allows the lens to counteract the shake of the electronic device 100 through a reverse movement, thereby achieving anti-shake. The gyroscope sensor 180B may also be used for navigation, somatosensory gaming scenes.

The air pressure sensor 180C is used to measure air pressure. In some embodiments, electronic device 100 calculates altitude, aiding in positioning and navigation, from barometric pressure values measured by barometric pressure sensor 180C.

The magnetic sensor 180D includes a hall sensor. The electronic device 100 may detect the opening and closing of the flip holster using the magnetic sensor 180D. In some embodiments, when the electronic device 100 is a flip phone, the electronic device 100 may detect the opening and closing of the flip according to the magnetic sensor 180D. And then according to the opening and closing state of the leather sheath or the opening and closing state of the flip cover, the automatic unlocking of the flip cover is set.

The acceleration sensor 180E may detect the magnitude of acceleration of the electronic device 100 in various directions (typically three axes). The magnitude and direction of gravity can be detected when the electronic device 100 is stationary. The method can also be used for recognizing the posture of the electronic equipment, and is applied to horizontal and vertical screen switching, pedometers and other applications.

A distance sensor 180F for measuring a distance. The electronic device 100 may measure the distance by infrared or laser. In some embodiments, taking a picture of a scene, electronic device 100 may utilize range sensor 180F to range for fast focus.

The proximity light sensor 180G may include, for example, a Light Emitting Diode (LED) and a light detector, such as a photodiode. The light emitting diode may be an infrared light emitting diode. The electronic apparatus 100 emits infrared light to the outside through the light emitting diode. The electronic device 100 detects infrared reflected light from nearby objects using a photodiode. When sufficient reflected light is detected, it can be determined that there is an object near the electronic device 100. When insufficient reflected light is detected, the electronic device 100 may determine that there are no objects near the electronic device 100. The electronic device 100 can utilize the proximity light sensor 180G to detect that the user holds the electronic device 100 close to the ear for talking, so as to automatically turn off the screen to achieve the purpose of saving power. The proximity light sensor 180G may also be used in a holster mode, a pocket mode automatically unlocks and locks the screen.

The ambient light sensor 180L is used to sense ambient light brightness. Electronic device 100 may adaptively adjust the brightness of display screen 194 based on the perceived ambient light level. The ambient light sensor 180L may also be used to automatically adjust the white balance when taking a picture. The ambient light sensor 180L may also cooperate with the proximity light sensor 180G to detect whether the electronic device 100 is in a pocket to prevent accidental touches.

The fingerprint sensor 180H is used to collect a fingerprint. The electronic device 100 can utilize the collected fingerprint characteristics to unlock the fingerprint, access the application lock, photograph the fingerprint, answer an incoming call with the fingerprint, and so on.

The temperature sensor 180J is used to detect temperature. In some embodiments, electronic device 100 implements a temperature processing strategy using the temperature detected by temperature sensor 180J. For example, when the temperature reported by the temperature sensor 180J exceeds a threshold, the electronic device 100 performs a reduction in performance of a processor located near the temperature sensor 180J, so as to reduce power consumption and implement thermal protection. In other embodiments, the electronic device 100 heats the battery 142 when the temperature is below another threshold to avoid the low temperature causing the electronic device 100 to shut down abnormally. In other embodiments, when the temperature is lower than a further threshold, the electronic device 100 performs boosting on the output voltage of the battery 142 to avoid abnormal shutdown due to low temperature.

The touch sensor 180K is also called a "touch device". The touch sensor 180K may be disposed on the display screen 194, and the touch screen includes the touch sensor 180K and the display screen 194, which is also referred to as a "touch screen". The touch sensor 180K is used to detect a touch operation applied thereto or nearby. The touch sensor can communicate the detected touch operation to the application processor to determine the touch event type. Visual output associated with the touch operation may be provided through the display screen 194. In other embodiments, the touch sensor 180K may be disposed on a surface of the electronic device 100, different from the position of the display screen 194.

The bone conduction sensor 180M can acquire a vibration signal. In some embodiments, the bone conduction sensor 180M may acquire a vibration signal of the human voice vibrating a bone mass. The bone conduction sensor 180M may also contact the human pulse to receive the blood pressure pulsation signal. In some embodiments, the bone conduction sensor 180M may also be disposed in a headset, integrated into a bone conduction headset. The audio module 170 may analyze a voice signal based on the vibration signal of the bone mass vibrated by the sound part acquired by the bone conduction sensor 180M, so as to implement a voice function. The application processor can analyze heart rate information based on the blood pressure beating signals acquired by the bone conduction sensor 180M, and the heart rate detection function is realized.

The keys 190 include a power-on key, a volume key, and the like. The keys 190 may be mechanical keys. Or may be touch keys. The electronic apparatus 100 may receive a key input, and generate a key signal input related to user setting and function control of the electronic apparatus 100.

The motor 191 may generate a vibration cue. The motor 191 may be used for incoming call vibration cues, as well as for touch vibration feedback. For example, touch operations applied to different applications (e.g., photographing, audio playing, etc.) may correspond to different vibration feedback effects. The motor 191 may also respond to different vibration feedback effects for touch operations applied to different areas of the display screen 194. Different application scenes (such as time reminding, receiving information, alarm clock, game and the like) can also correspond to different vibration feedback effects. The touch vibration feedback effect may also support customization.

Indicator 192 may be an indicator light that may be used to indicate a state of charge, a change in charge, or a message, missed call, notification, etc.

The SIM card interface 195 is used to connect a SIM card. The SIM card can be brought into and out of contact with the electronic apparatus 100 by being inserted into the SIM card interface 195 or being pulled out of the SIM card interface 195. The electronic device 100 may support 1 or N SIM card interfaces, N being a positive integer greater than 1. The SIM card interface 195 may support a Nano SIM card, a Micro SIM card, a SIM card, etc. The same SIM card interface 195 can be inserted with multiple cards at the same time. The types of the plurality of cards may be the same or different. The SIM card interface 195 is also compatible with different types of SIM cards. The SIM card interface 195 may also be compatible with external memory cards. The electronic device 100 interacts with the network through the SIM card to implement functions such as communication and data communication. In some embodiments, the electronic device 100 employs esims, namely: an embedded SIM card. The eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100.

Fig. 2 is a functional architecture diagram of a content recommendation system according to an embodiment of the present application. The following description is provided for each functional module in the content recommendation system 200, and as shown in fig. 2, the content recommendation system 200 includes a fusion perception module 20, a user representation construction module 21, an intention analysis module 22, a tag analysis module 23, a request module 24, and an output module 25.

The fusion awareness module 20 is used for collecting data including one or more of user behavior data, user context data, and user personal data, wherein: the user behavior data includes information on operational behaviors of a user of the electronic device on the electronic device, the user context data includes information on a context in which the user of the electronic device is located including a physical environment, a network environment, a terminal environment, and the like, and the user personal data includes information on items of content including pictures, texts, videos, voices, search content, gestures, applications, and the like, which are locally stored by the user of the electronic device.

Exemplary characterization of the various data described above is described below.

(1) The user behavior data may contain various information about the operation behavior of the user on the electronic device, including information about the operation behavior of an information carrier (e.g., an application interface) carried on the electronic device, information about the operation behavior of a hardware device (e.g., a camera) of the electronic device, and the like.

Illustratively, the user behavior data may include a behavior type, a start time, an operation duration, an operation content, an operation frequency, and the like, wherein the behavior type is a type of a user operation behavior, and the user operation behavior includes, but is not limited to, retrieving, browsing, clicking, sliding, touching, saving, pressing, and the like, such as opening an application, browsing the application, pressing a touch key, and the like. The starting time is the time when the user operation behavior starts, and is used for determining the time point of the user operation behavior. The operation duration is the duration of the user operation behavior. The operation content is specific content of user operation behavior, such as WeChat usage, sports news browsing, music playing, and the like. The operation frequency is the frequency of the user operation behavior, and is the frequency of the occurrence of a certain user behavior type in a preset period, and the user behavior type corresponds to the user behavior frequency.

(2) The user context data may comprise information about the context in which the user of the electronic device is located, including physical environment data, terminal state data, user state data, etc.

Illustratively, the user context data may include, but is not limited to, day of the week (e.g., monday, tuesday, or wednesday, etc.), whether to holiday, time (e.g., time period "3 o 'clock to 6 o' clock," or time "3 o 'clock"), location (e.g., city name, street, or longitude and latitude), location category (e.g., home, company, entertainment venue, or shopping mall, etc.), weather (e.g., sunny day, rainy day, rainstorm, etc.), air temperature (e.g., 33 o' clock, etc.), occasion (e.g., party, meeting, etc.), remaining battery capacity (e.g., 50 percent), network (e.g., the network type may be WIFI, 4G, or 5G), available memory (e.g., 50 percent), remaining disk (e.g., 10 percent), whether to plug in headphones, user status (e.g., riding, walking, lying at home, having lunch break, sleeping, listening to a song, or watching a series), and the like.

(3) The user personal data may contain relevant information about items of content that are stored locally by the user of the electronic device.

Illustratively, the user personal data includes, but is not limited to, category, sub-category, quantity, size, time-of-use data or size, frequency of viewing, and length of viewing time. The categories are categories of personal data of the user, including texts (such as chat word records, documents, web browsing records), pictures (such as pictures downloaded and saved from a web page), audios (such as music files downloaded from music software and local audio recording), and the like, the sub-categories are sub-categories of personal data of the user, such as literature, military, landscape, architecture, rock, ballad, and the like, the number is the number of files related to each sub-category, the size is the size of files related to each sub-category, the time sharing data or the size is the size of files related to each sub-category, the number and the size related to each sub-category are counted in time sharing periods, the frequency is the frequency of the user for viewing files of each category, and the viewing duration is the duration of the user for viewing files of each type.

In this embodiment of the application, the fusion sensing module 20 detects the surrounding environment of the electronic device through a sensor or other sensing devices to obtain information of the electronic device in the surrounding environment, and then processes multiple sets of sensing information from different sources through a specific manner (e.g., a fusion algorithm) to obtain a set of sensing information.

Illustratively, the fusion sensing module 20 collects and fuses sensing sources of sensing devices by means of a hong meng operating system (harmony os) distributed capability, and accurately senses a spatial state, a movement state, a gesture, a health state, and the like of a user, so as to obtain user behavior data and user context data. Further, in a specific embodiment, information of the change of the environment around the electronic device, the use state of the electronic device, and the user behavior may be determined based on data of sensors or peripherals of the electronic device, such as: the electronic equipment can perform environment recognition according to the audio data detected by the microphone and the video data collected by the camera, and recognize that the user is currently in a video conference and the like. Another example is: the electronic device may also determine user context data according to data of sensors such as an acceleration sensor, a gyroscope, a proximity sensor, and an acceleration sensor, for example: user context data such as walking, running, driving, etc.

In one possible implementation, the fusion awareness module 20 may further be configured to store historical data of the user, that is, historical user behavior data, historical user context data, and the like.

User representation construction module 21 is for constructing a user representation of a user. A user representation is a visual representation of data associated with the user, i.e., user information tagging. User portrayal can be simply understood as labels of mass data, the user can be distinguished into different types according to the difference of the target, the behavior and the viewpoint of the user, then typical features are extracted from each type, names, photos, some demographic elements, scenes and the like are given to the typical features, and a character prototype (personas) is formed. In other words, the user representation includes a multi-dimensionally established descriptive label for the user, which can represent various attributes of the user. For example, the user representation may include age, gender, whether to buy a house, whether to have children, financial resistance to risk, and the like.

In the embodiment of the present application, the user image constructing module 21 receives the data collected by the fusion sensing module 20, and analyzes the data collected by the fusion sensing module 20 to construct the user image of the user. For example, user representation construction module 21 may abstract a user's tab set by collecting and analyzing data of main information such as user attributes, living habits, and consumption behaviors, and the tab set of the user constructs a user representation. User attributes include, but are not limited to: age, gender, marriage, family population, hobbies, scholars, native place, place of residence, place of employment, industry to which work belongs, etc.

In one embodiment, user representation construction module 21 may analyze a user's historical data, such as historical behavior data or a browsing history of historical content. Further, in a specific embodiment, the user representation constructing module 21 respectively reads browsing information such as browsing times, browsing duration and the like of each content according to browsing records of historical contents of the user, and filters the browsing information based on the browsing times, browsing duration and the like to obtain an interested content set and an uninteresting content set of the user; further, the user portrait building module 21 generates an interested content tag of the user based on tags of each content in the interested content set of the user, and generates an uninteresting content tag of the user according to tags of each video in the uninteresting video set, thereby obtaining the user portrait. In other embodiments, the user representation may be implemented in other ways.

In the embodiment of the present application, the user preference may be known through the user portrait, including but not limited to: users generally like to browse which types of content and dislike browsing which types of content; for example, users are often interested in popular science, sports, news, and the like, but not in entertainment bagua, movie presentations, and the like.

In one possible implementation, user representation construction module 21 may store historical preference data of the user, including preferred services and content, i.e., preferred application types, etc.

The intention analysis module 22 is used to analyze the user intention of the user. Herein, "user intent" may be understood as a specific purpose of the user during performance of an operation, i.e., an object or goal that is intended or intended to be achieved. User intent, refers to the electronic device identifying what the user's actual or potential needs are. The user intent and the slot together constitute a "user action" that the electronic device cannot directly understand the user input, and thus the user intent recognition functions to map natural language or operations to machine-understandable structured semantic representations. Fundamentally, the intent analysis module 22 is a classifier that classifies user needs into certain categories. For the complex situation that the same system handles multiple tasks, one optimized strategy is to define a higher-level domain, such as to attribute the "inquire weather" intention and the "inquire temperature" intention to the "weather" domain. In this case, the domain may be simply understood as a set of intents (a candidate intention set). The advantages of defining the domain and performing domain identification first are that the domain knowledge range can be constrained, and the subsequent search space of user intention identification and slot filling is reduced.

The user's intent is often associated with the service that is desired to be used and the user's current interests. For service content recommendation, however, an efficient user intent recognition may define areas of user interest while helping to determine the user's current preferred services and content. For example, when the user has a nap intention, the user is likely to watch a video or listen to a music, the video may be a short video of a drama or a recommended number of dramas that have not been watched last time, and the music may be a number of music for aiding sleep. The intention analysis module 22 can analyze the services that the user may currently use and the services of interest by guessing the user's intention. Particularly, for content recommendation related to multiple fields, the establishment of the intention system can also quickly reduce the candidate fields, reduce the candidate set of the service field and help to narrow the content recommendation range.

In an embodiment of the present application, the intention analysis module 22 constructs an intention system, wherein the intention system includes a plurality of intention tags and user data corresponding to each intention tag, wherein the user data includes at least one of personal data, behavior information, portrait information, and real-time context-related information of a user using the electronic device, i.e., the user data includes one or more of user behavior data, user context data, user personal data, and user portrait data, a set of user data may correspond to a plurality of different intention tags, and an intention tag may correspond to one or more sets of user data, wherein a set of user data may include one or more user data.

In the embodiment of the present application, the intention analysis module 22 receives the data collected by the fusion perception module 20, and classifies the received user data according to the constructed intention system to obtain the current user intention of the user. The fusion sensing module 20 can obtain real-time data of the user, that is, real-time feedback data of the user, where the real-time data of the user (that is, the real-time feedback data) can reflect real-time intention of the user.

In one possible implementation, the intention analysis module 22 may obtain a user representation of the user, historical data of the user (e.g., historical user behavior data, historical user context data, etc.), historical preference data of the user, etc., and classify the received user data according to the constructed intention system to obtain the user intention.

The tag analysis module 23 is configured to analyze a tag corresponding to the current user data. The tag analysis module 23 may obtain data of the fusion perception module 20 and/or the user portrait construction module 21, that is, the tag analysis module 23 may obtain data of the fusion perception module 20, data of the user portrait construction module 21, or data of the fusion perception module 20 and the user portrait construction module 21, that is, obtain user data, and analyze the user data to determine a currently preferred tag.

In the embodiment of the present application, the tag analysis module 23 may be used to construct a tag system. A common recommendation method for content recommendation in different fields is feature tag-based recommendation. Various labels in the field are firstly combed through the field knowledge/expert knowledge, and all the contents in the field are marked with different labels, namely, each field corresponds to different characteristic labels. During recommendation, the content corresponding to the label can be recommended to the user according to the label preferred by the user. For example, in the video/movie field, the feature tags thereof have various feature tags such as region, rating, online time, goodness, scenario, and star classification. For a viewer who likes fun, harbor stage, zhou Xingchi and old drama, he can recommend Zhou Xingchi kungfu football, which the APP has just purchased copyright.

The design of the label is closely related to the field of the label, and the field label and the characteristic label of each field are different, so that the design of the label needs to be graded for content recommendation of multiple fields. The label analysis module 23 constructs a second-level label system, and the first level is a domain label, such as "music", "video", "movie", "game" and "food" and so on. The fields corresponding to the tags in different fields are different, and the first applications corresponding to different fields may be different, and the fields may be understood as a set of a certain type of first applications, and the tags in the fields are tags of a certain type of first applications. Illustratively, the first application corresponding to the domain tag being "music tag" may include "first music app", "second music app", and the like. The first application corresponding to the domain tag being a "video tag" may include "first video app", "huazi video", and the like. The second level is tags in the field, namely feature tags, the feature tags in the music field are obviously different from those in the video field, and for music, the tags include 'light music', 'Japanese system', 'European and American leaderboard', and the like; for video, there are "domestic", "newest up-line", "Zhou Xingchi", "fun", and so on. It is understood that the feature labels of different domains may be the same, for example, for a person, the corresponding video content may also have corresponding music content, for example, the feature label of the person a may be in the music domain, and the feature label of the person a may also be in the video domain.

In the embodiment of the present application, when content recommendation is performed, the tag analysis module 23 may also utilize the constructed second-level tag system, and first recommend a domain in which the user is interested according to the first-level tag, that is, determine a domain tag, and select a corresponding target application according to the domain tags. And then, the feature labels of the second level are used as features to be transmitted to each target application, and then each target application is used for content recommendation. Specifically, the tag analysis module 23 determines a domain tag and a feature tag according to the user data, and determines a target application from a candidate application set according to the domain tag, where the feature tag is to be transmitted as a feature to the target application, the candidate application set includes a plurality of first applications, that is, one or more target applications are determined from the plurality of first applications according to the determined domain tag, and if "music tag" and "video tag" are determined according to the user data, the "music tag" corresponds to the first application in the candidate application set and includes "first music app" and "second music app", and the "video tag" corresponds to the first application in the candidate application set and includes "hua as video" and "video app1", then it may be determined that the target application includes "first music app", "second music app", "hua as video", and "video app1". The first application is an application programming interface provided by the content recommendation system 200 according to the embodiment of the present application, has content recommendation capability, and is focused on one or more fields for recommendation, such as one or more fields of music, video/short video, games, dining, traveling, hotels, and news. When a first application can recommend content in multiple domains, the first application can correspond to multiple different domain tags.

In one possible implementation manner, the first application may be a three-party application, and the first application may preferably be a head application, that is, the first application may be a head application in various fields, such as a first application in a short video field may include app1, app2, app3, and the like, the first application in a catering field may include app4, app5, and the like, and app1, app2, app3, app4, app5 are different applications.

The request module 24 is configured to send a recommendation request to the target application to request the target application to recommend content, and receive recommended content and a recommendation reason returned by the target application in response to the recommendation request.

In this embodiment of the application, the request module 24 provides a set of complete Open application programming interfaces (OpenAPI), and the first application modifies the service logic code according to an access protocol of the provided Open application programming interfaces (OpenAPI), and calls the service logic code together with the platform of the content recommendation system 200 to be logged in to pay, the relationship chain, and other application programming interfaces, and then finds a new machine deployment service code to be online after the connection is passed, so that the request module 24 can call the corresponding application programming interface to interact with the first application.

Illustratively, as the tag analysis module 23 determines that the domain tags are "music tags" and "video tags" and the corresponding target applications include "first music app", "second music app", "hua video" and "video app1", respectively, the request module 24 calls application programming interfaces corresponding to the "first music app", "second music app", "hua video" and "video app1" to send recommendation requests to the "first music app", "second music app", "hua video" and "video app1", respectively.

In the embodiment of the application, the interface opening mainly comprises an input interface and an output interface. For the input interface, the intelligent assistant may define a set of feature transmission interfaces including, but not limited to, user behavior data, user context data, user personal data, user representation data, user intent, domain tags, feature tags, and desensitization feature data of the user. For the output interface, a return format of the recommended content of the first application is defined, including but not limited to the content to be recommended and a recommendation reason corresponding to the recommended content.

In this embodiment of the application, the request module 24 may obtain the domain tag determined by the tag analysis module 23, and may trigger a plurality of target applications simultaneously according to the domain tag, and convert the intention analysis module 22 into desensitization feature data (i.e., desensitization feature data obtained by desensitizing the data sensed by the fusion sensing module 20, the user portrait data analyzed by the user portrait construction module 21, the user historical behavior data, and the like) obtained by desensitizing the potential user intention of the user in combination with the user data according to the user data, and send the desensitization feature data to the target applications along with the recommendation request, that is, when the request module 24 sends the recommendation request to the plurality of target applications, the request module also transmits the user intention, the secondary tag data, the desensitization feature data, and the like to the target applications.

In one of the possible implementations, desensitizing the user data may be hash coding the user data.

In the embodiment of the present application, the characteristics transmitted to the target application by the request module 24 along with the recommendation request may be issued to the terminal electronic device side through the configuration file for updating, and the data to be transmitted to the target application, including the characteristic tag, the user intention, the desensitization characteristic data, and the like, will be updated after the terminal electronic device side frame updates the configuration file. For example, the data transmitted to the target application is updated through the distribution file, and the historical data of the user transmitted to the target application is increased, after the update, the request module 24 increases the historical data of the user transmitted to the target application when sending the recommendation request to the target application.

In this embodiment of the application, when the request module 24 sends a recommendation request to the target application, the engagement target application responds to a return format of the content returned by the recommendation request, that is, after receiving the user data sent with the recommendation request, the engagement target application makes an agreement. The target application responds to the recommendation request, returns corresponding recommendation content to the request module 24 according to the user data, and attaches a recommendation reason corresponding to the recommendation content.

In the embodiment of the application, a corresponding recommendation reason template can be independently generated according to each tag field, the same recommendation reason can correspond to a plurality of field tags, the same field tag can correspond to a plurality of recommendation reasons, for example, the recommendation reasons for video content include latest projection, latest watching, director xxx, actor xxx, director xxx, martial arts, hallucinations, heat list, drama, short video, funny … and the like, and the recommendation reasons for music content include new albums, singers, compositions, latest playing, europe and america, solar system, latest playing, user liking, relaxation, ignition system, violent promotion and the like. When the target application can return the recommendation reason, the corresponding recommendation reason template can be inquired according to the current domain tag, and an appropriate recommendation reason can be selected from the corresponding recommendation reason template.

Referring to fig. 3, fig. 3 is a schematic diagram illustrating an operation of a request module according to an embodiment of the present disclosure.

The candidate application set includes first applications that have access to the content recommendation system 200 provided in the embodiment of the present application, such as a music domain application, a food domain application, a video domain application, a game domain application, and a travel domain application. The request module 24 receives desensitization feature data after desensitization of the data acquired by the fusion sensing module 20, user portrait data, user intention, domain tags and corresponding feature tags, and the tag analysis module 23 may output a plurality of domain tags, may sort the plurality of domain tags, that is, sort a plurality of domains that may be interested by the user, and output the domain tags that are sorted in the front to the request module 24. The request module 24 determines a corresponding target application according to the top-ranked domain tag, if the top-ranked domain tag includes a music domain, a video domain and a game domain, the request module 24 sends a recommendation request to a first application corresponding to the music domain, the video domain and the game domain, the recommendation request includes desensitization feature data, user portrait data, a user intention, a corresponding feature tag and the like, and the recommendation request is used for requesting the target application to recommend corresponding content according to the desensitization feature data, the user portrait data, the user intention, the corresponding feature tag and the like. And the target application returns the recommended content and the corresponding recommendation reason in response to the recommendation request. If the target applications corresponding to the music field are the "first music app" and the "second music app", the request module 24 calls application program interfaces corresponding to the "first music app" and the "second music app", and sends recommendation requests respectively. As shown in fig. 3, the first music app returns the recommended content of Zhou Jielun song in response to the recommendation request, that is, the detailed page content of Zhou Jielun song in the first music app, the corresponding recommendation reason is "recently listened to", and the second music app returns the recommended content of light music in response to the recommendation request, that is, the detailed page content of "second music app" about light music, the corresponding recommendation reason is "recently collected". In the embodiment of the present application, the content recommendation system 200 may be only responsible for recommending common applications, and provide necessary features to the applications by using the agreed application program interface specification and the feature parameter specification transmitted together with the recommendation request.

The output module 25 is used for outputting the recommended content to the user. The output module 25 may display a recommendation interface on which the recommended content is displayed in a refreshed manner. The recommended content may be a certain service content of the target application, such as a certain detail page content, and the recommended content may be in a format of a hyperlink, a direct service, text, voice, and the like.

After the target application received by the request module 24 responds to the recommended content and the reason for recommendation returned by the recommendation request, the recommended content and the reason for recommendation are output to the output module 25, so that the output module 25 outputs the recommended content to the user.

Illustratively, if the content recommendation system 200 is implemented as a recommendation module Hua as an intelligent assistant "art proposal", music FA (Feature abstraction) is presented on the recommendation interface, which is a UI-interface program entity supporting Harmony OS and capable of being developed by three parties based on a meta-capability framework and realizing a single function. Illustratively, specifically a Zhou Jielun menu. The FA of the Youku video is specifically the homepage of the television series named people, and the like. Wherein art suggestions currently support recommending applications, through services, hong meng FAs (Feature accessibility), etc., wherein recommendations for FAs usually show some content information related to FAs. For example, the art suggests an FA that recommends a schedule, schedule-related information is shown in the FA, and if an FA of app1 is recommended, a short video of app1 is shown in the app1 FA. The schedule-related information and the app1 short video are content information attached to the recommended FA. Obviously, the more content recommended by an FA meets the user's desire, the more likely the pushed FA is to be clicked. When recommending the first music appFA, for a user who likes Zhou Jielun songs, the FA content would have a higher click rate if the menu showing Zhou Jielun shows than other menus. For a user with a habit of nap, the music content for promoting sleep, such as music, recommended to the user in the noon break has a higher click rate than the song list such as the European and American leaderboard. Therefore, the content recommendation system presents the content closer to the user intention to the user by combining the user preference, the user state and the FA characteristics, and is a key factor for recommending the FA and improving the click rate of the art suggestion.

Optionally, the content recommendation system 200 may further include a ranking module 26. The request module 24 outputs the recommended content and the reason for recommendation to the sorting module 26 after receiving the recommended content and the reason for recommendation returned by the target application responding to the recommendation request, and the sorting module 26 is configured to receive the reason for recommendation and the recommended content output by the request module 24, sort the recommended content according to the reason for recommendation, and obtain a sorting result. The ranking result includes which recommended content is output to the user and the ranking condition of the recommended content output to the user.

In one possible implementation manner, the sorting module 26 may be further configured to sort the recommended content according to the user intention, the feature tag, the recommendation reason, and desensitization feature data, that is, desensitization feature data obtained by desensitizing the user data (including desensitization feature data obtained by desensitizing data sensed by the fusion sensing module 20, user portrait data analyzed by the user portrait construction module 21, and user historical behavior data), that is, the recommended content is sorted after being scored.

In this embodiment, the output module 25 may output the recommended content ranked in the top according to the ranking result output by the ranking module 26.

Optionally, the content recommendation system 200 may further comprise a monitoring module 27. The monitoring module 27 is configured to monitor the recommendation quality of the target application, that is, monitor the accuracy of the recommended content and the recommendation reason recommended by the target application, so as to analyze whether the recommended content recommended by the target application is good, and the target application with good quality and accurate description is recommended preferentially.

In one possible implementation manner, the monitoring module 27 may score the target applications according to the monitoring of the recommended content and the recommendation reason of the target applications to obtain the scoring results of the target applications, and output the scoring results to the sorting module 26, so that the sorting module 26 may also sort according to the scoring results of the respective target applications, and the recommended content recommended by the target application with a high scoring result may be preferentially output.

For example, please refer to fig. 4, where fig. 4 is a schematic diagram of an operation of a monitoring module according to an embodiment of the present application.

The monitoring module 27 comprises one or more of a first monitoring unit 271 and a second monitoring unit 272, wherein the first monitoring unit 271 may be applied to the end side, i.e. monitoring the recommendation of the target application based on the user feedback is performed at the terminal side. The second monitoring unit 272 may be applied to the server side, i.e. the server side monitors the recommendation of the target application based on the recommended content, the reason for the recommendation, and the user data.

After the output module 25 outputs the recommended content, the first monitoring unit 271 determines which application recommended content is better according to the user feedback information, such as the click, exposure, and recommended content viewing time of the user on the content output by the output module 25, and the direct feedback of the user on the recommended content (for example, the recommended interface can be provided for a module for evaluating the recommended content by the user, and the direct feedback of the user on the recommended content), so as to score the target application.

In one possible implementation manner, since the content recommendation system 200 provided in the embodiment of the present application relates to multiple fields, the recommended content evaluation criteria in different fields are different, for example, the short video may use the viewing duration as an average criterion, and the taxi taking whether to initiate a taxi taking order is used as a criterion. Therefore, the invention provides a feedback design based on the domain label, and different feedback modes are designed for contents in different domains.

The second monitoring unit 272 may obtain the regularly sampled recommended content, the recommended reason, and the cloud of the user data, and evaluate whether the recommended content is matched with the recommended reason or not according to various manners such as rules, models, expert knowledge, and manual work, and whether the recommended reason can accurately describe the recommended content, so as to evaluate the target application. And evaluating whether the recommended content is matched with the user data or not according to various modes such as rules, models, expert knowledge, manual work and the like, and whether the recommended content can accurately correspond to the user data or not so as to evaluate the target application. Meanwhile, the quality of the recommended content is controlled, and the server can track the total click, good comment, bad comment and other information of the recommended content of the target application for a long time to analyze whether the recommended content of the target is high in quality or not. And according to the acquisition and analysis of the recommended content in a period of time, the target application is scored, the score is issued to the end side, and the content recommended by the target application with high score can be recommended preferentially. Meanwhile, in order to avoid the worst experience, the recommended content of the target application with the score lower than a threshold value is filtered out finally and is not recommended to the user. And the recommended content can be cached, whether the three-party recommended content is high in quality or not is analyzed according to the subsequent click rate, the good evaluation and poor evaluation proportion and the like of the whole network of the content, and the application which is high in quality and accurate in description is preferentially recommended.

In some embodiments, some of the modules and functions of the content recommendation system 200 may be divided into a server portion and a client portion, where the client portion may be located on an electronic device as shown in fig. 1, such as the convergence awareness module 20, the output module 25, and the request module 24 may be deployed on an electronic device of a terminal. Wherein the server portion may be implemented on one or more stand-alone data processing apparatuses or a distributed network of computers. In some embodiments, the server portion may also employ various virtual devices and/or services of a third party service provider (e.g., a third party cloud service provider) to provide the underlying computing resources and/or infrastructure resources of the server portion. Such as user representation construction module 21, intent analysis module 22, tag analysis module 23, and ranking module 26, may be deployed on virtual devices of third party service providers. The client portion may communicate with the server portion over one or more networks.

Furthermore, the division of functionality between the client portion and the server portion of content recommendations may be different in different implementations. For example, in some embodiments, the client portion may be a thin client that provides only user-oriented input and output processing functions, and delegates all other functions of content recommendation to a backend server.

In some embodiments, the modules and functionality of the content recommendation system 200 may be deployed on the client side.

In other embodiments, the content recommendation system 200 may implement content recommendations on a stand-alone computer system, such as an intelligent service robot or the like.

In other examples, the content recommendation system 200 may be distributed across multiple computers.

In other embodiments, the functionality of the content recommendation system 200 may be implemented as a standalone Application (APP) installed on the electronic device. The application program may be an embedded application program in the electronic device (i.e., a system application of the electronic device), or may be a downloadable application program. An embedded application is an application provided as part of an implementation of an electronic device, such as a cell phone. For example, the embedded application may be a "settings" application, a "short message" application, a "camera" application, and the like. The downloadable application is an application that may provide its own internet protocol multimedia subsystem (IMS) connection, and may be an application that is pre-installed in the electronic device or a third party application that may be downloaded by a user and installed in the electronic device. For example, the downloadable application may be a "WeChat" application, a "Payment treasures" application, a "mail" application, and the like.

In other embodiments, the functionality of the content recommendation system 200 may be implemented as a content recommendation module for a standalone application installed on an electronic device, such as one implemented as a smart assistant "art suggestion" on a mobile phone.

In other examples, the content recommendation system 200 may be a cloud server, or the content recommendation system 200 may be a content recommendation service Application Programming Interface (API) on the cloud server.

In other examples, the content recommendation system 200 may be a content recommendation service API on a public cloud, or a functional module embedded in a content recommendation product, such as a content recommendation module in a content recommendation APP on a mobile phone.

It is to be understood that the product forms set forth herein are illustrative and should not be construed as limiting the present application in any way.

It should be noted that the content recommendation may have more or fewer components than illustrated, may combine two or more components, or may have a different configuration or layout of components. The various functional blocks shown in fig. 2 may be implemented in hardware, software instructions for execution by one or more processors, firmware including one or more signal processing integrated circuits and/or application specific integrated circuits, or a combination thereof.

The technical solutions in the following embodiments may be implemented in an electronic device having the above hardware architecture. The content recommendation method provided in the present embodiment is described in detail below with reference to the accompanying drawings and application scenarios. The contents of the above embodiments are all applicable to the method shown in fig. 5, and are not described herein again. It should be noted that the following embodiments are exemplified by the application of the intelligent assistant "Xiaoyi suggestion".

Referring to fig. 5, fig. 5 is a schematic flow chart of a content recommendation method according to an embodiment of the present application. The execution subject of the method may be a device with processing capabilities: a server or system or an electronic device, for example, an electronic device as shown in fig. 1. As shown in fig. 5, the method specifically includes:

step S51: user data is acquired.

In this embodiment, the user data may be user data collected from an electronic device of a user based on the fusion perception module shown in fig. 2, or user portrait data analyzed and constructed based on a user portrait construction module, that is, the user data is at least one of personal data, behavior information, portrait information, and real-time context related information of a user using the electronic device. The detailed description of the user data is described with reference to fig. 2, and will not be repeated herein.

Specifically, a user starts a Huacheng smart assistant 'Xiaoyi suggestion' on a mobile phone, user data can be obtained based on a fusion perception module and a user portrait construction module in the running process of the Xiaoyi suggestion, and then the content recommendation method provided by the embodiment of the application is executed according to the currently obtained user data to obtain recommended content recommended by a target application.

The small art recommendation recommends some FA cards to the user, and the FA cards have some service contents of corresponding applications. The more accurate these service content recommendations are, the higher the click-through rate will be. Meanwhile, the art proposal is one of the main recommended entrances of Hongmon mobile phones, so that the method relates to a plurality of fields, and head applications in each field cannot simply share all the contents of the user to the art proposal. Therefore, when the content recommendation method provided by the embodiment of the application is implemented, a set of complete interfaces needs to be designed first, and the recommendation main entry opens an interface for each application. For the input interface, the art suggestion can define a set of feature introduction interfaces, including but not limited to user state information collected by using the fusion perception capability of the Hongmon system, desensitization portrait information of the user, historical preference information of the user, current preference labels of the user, current intention labels of the user and the like, and the head application receives the features of the user and combines with data of the head application to recommend content. And for the output interface, a return format of the head application recommended content is well defined, the head application recommended content comprises the content to be recommended and a corresponding recommendation reason, and the artistic recommendation reorders the recommended content according to the recommendation reason. By means of the definition of the input and output interfaces, the service content recommendation can be realized by means of the application recommendation capability through the artistic suggestions.

Step S53: the target application is determined from the user data.

In embodiments of the present application, the user data may be a set of one or more user data samples, each user data sample comprising one or more of user behavior data, user context data, user personal data, and user profile data collected at the same time.

In this embodiment of the application, step S53 may be executed by an application program cookie installed on the huahua-shi mobile phone, the cookie may access a plurality of first applications, the first applications satisfy a preset defined access specification, and the fields corresponding to the applications are divided, for example, hua-shi video, video app1, video app2, and the like may be classified as video fields, and the corresponding field labels are video fields. Thus, a currently preferred domain tag may be determined according to the user data, i.e. a domain that the user may be interested in at present, such as a video domain, a food domain or a music domain, and then a corresponding target application may be determined according to the domain tag.

In the embodiment of the present application, determining the target application according to the user data includes, but is not limited to, the following ways:

in the first mode, a user scene is determined according to user data, and then a target application is determined according to the user scene.

In the embodiment of the application, the art suggestions can set and save various user scenes, such as working days and morning scenes, driving scenes from work and the like. Each user scenario may correspond to multiple domain tags, and each domain tag may correspond to multiple user scenarios. The user scenario (hereinafter, the embodiment of the present application is also simply referred to as "scenario") indicates a situation in which a user using the electronic device is located. The user context (context), also referred to as context, refers to any information describing the state of an entity, including the location, time, surrounding environment, activity, preference, etc. of the entity. In the present application, the user scenario is used for any information describing the state of the user, including the location, time, surrounding environment, activities performed by the user, and the like of the user.

When the user scene is identified, information such as change of the surrounding environment of the electronic equipment, the use state of the electronic equipment, user behaviors and the like can be determined based on data such as a sensor or peripheral equipment of the electronic equipment, and various data obtained by comprehensive utilization are analyzed to determine the current user scene of the user.

In one possible implementation manner, data of other applications or services may also be acquired by interacting with the other applications or services in the electronic device, and user scene recognition may be performed in combination with the data of the other applications or services. For example: geo-fencing is an application of Location Based Service (LBS), i.e., a virtual fence that encloses a virtual geographic boundary. The electronic device may receive automatic notifications and alerts when the electronic device enters, leaves, or is active within a particular geographic area. Then, data in the geo-fence application may be acquired, determining user scenarios where the user is at a company, at an airport, at a station, at a mall, and so forth. Another example is: the user's behavior, e.g. in a meeting, on a plane, on a train, etc., can also be determined from the schedule in the calendar. The method can also interact with other electronic equipment (such as a smart watch, a bracelet and the like) connected with the electronic equipment to acquire relevant information of the other electronic equipment for user scene recognition. It should be noted that, in the embodiment of the present application, no limitation is imposed on a software module, a hardware device, and a peripheral device that are called when a user scene is identified.

Typically, a user context relates to a geographical location where the electronic device is located (and usually also the location of the user using the electronic device), such as the user being in a library, a scenic spot or airport, etc., in which case the user context is an abstract representation of the location or area where the user is located, which may be represented by an identification of the location or area, such as an area name, location coordinates, keywords, etc. The corresponding user scene can be determined by sensing the position or the area where the user is located. In addition to the location of the user, in some cases, the user context may also relate to the interconnection status between the electronic devices, such as the device to which the electronic device is currently connected, and at this time, the user context may be represented by the identification of the connected device, such as the device name, the device type, and so on. In some cases, the user context may also relate to time and/or a motion state of the user, for example, the user context may be: the user is at school at night, the user is in gym, and so on.

In one possible implementation manner, the electronic device stores data of different preferences of the user in different user scenarios, i.e. one or more user tags in the user representation. The one or more user tags may be applications that the user prefers to use, i.e., weight values for using the applications in the scenario, etc. Then, after determining the current user scenario of the user, the electronic device may query the user representation to determine one or more corresponding user tags in the user scenario, i.e., applications preferred by the user, and the like.

As shown in table 1, is an example of user preferences stored in an electronic device. It should be noted that the user scenario shown in table 1 is only an example, and in a specific implementation, the user scenario may also be a more detailed user scenario, for example: the current user scenario of the user can be identified as follows: the user is at the company, and this time the user's usual hours of work, and it can be inferred that the user is about to go home. Another example is: the current user scenario of the user can be identified as follows: according to the historical behavior data of the user, the user scene that the user is about to drive home can be deduced when the user is in a parking lot of a company.

For example, if the electronic device identifies a user scenario in which the user is in a parking lot of a company and is about to drive to home, the look-up table 1 may determine that the preference domain tags of the user are a navigation domain and a music domain in the user scenario, and may determine that the target applications are a map app2, a map app1, a first music app, and a second music app.

TABLE 1

Illustratively, obtaining user data of a user through fusion perception includes: the current time is between 7. The corresponding domain label of the working day and morning scene is a video domain, a news domain, a music domain and a game domain, so that the target application can be determined by the working day and morning scene, the target application can comprise a video application capable of providing videos, a news application capable of providing news information, a music application capable of providing music and a game application capable of playing games, and a user can brush videos, brush news, listen to music and play games in the working day and morning scene.

And secondly, determining the field tag which is interested by the user according to the user data, and further determining the corresponding target application according to the field tag which is interested.

In the embodiment of the present application, each first application has its corresponding domain tag, for example, the domain tags corresponding to the first applications "first music app", "second music app", and "third music app" are "music tags", and the domain tags corresponding to the first applications "first music app", "second music app", and "third music app" are "video tags", and the domain tags corresponding to the first applications "video app1", "video app2", "video app3", and "app4" are "video tags".

In the embodiment of the application, the art suggestion can construct a corresponding relation between user data and field tags, a group of user data can correspond to a plurality of field tags, if the user behavior data is that the user browses a webpage again, the user scenario data is that the user is at noon on a weekend, the user is at home, the portrait data of the user is that the user watches a television play at afternoon on a weekend, the personal data of the user comprises videos and music downloaded by the user on the weekend, and the field tags corresponding to the user data comprise a video field, a music field and a food field.

In one possible implementation manner, the art suggestion may create a domain analysis model according to a corresponding relationship between the user data and the domain label, where a process of creating the domain analysis model is a process of dividing a plurality of user data samples into a plurality of domain categories, and associating each domain category with a content feature corresponding to a user data sample belonging to the domain category.

In the embodiment of the application, after the user data is obtained, the user data may be input into the domain analysis model to obtain the corresponding domain tag, or the domain tag corresponding to the user data is determined according to the constructed correspondence between the user data and the domain tag, and then the corresponding target application is determined according to the domain tag.

Step S55: and sending a recommendation request to the target application, wherein the recommendation request comprises the user data.

In this embodiment of the application, step S55 may be performed by a cookie suggestion, and after the cookie suggestion determines the target application, an interface corresponding to the target application may be called, and a recommendation request is sent to the target application to request the target application to recommend the corresponding content. When the recommendation request is sent to the target application, the user data can also be transmitted to the target application, and the user data is transmitted to the target application after feature extraction and desensitization, for example, the data sent to the target application along with the recommendation request may include a feature tag, a user intention, and desensitization feature data. And processing the characteristic label, the user intention and the desensitization characteristic data into characteristic data which can be used by the target application according to a preset input interface specification, and transmitting the characteristic data to the target application. After receiving the characteristic data, the target application analyzes the content owned by the target application based on the rules, models and knowledge of the target application, finally recommends the corresponding content, and provides a recommendation reason for the recommended content according to the convention of the output specification.

In the embodiment of the application, the art suggestions can determine the field tags and the field content tags according to the user data, for example, after the field tags are determined to be music tags and video tags, the music type tags which the user wants to listen to and the video type tags which the user wants to see are analyzed, and illustratively, the user is relaxed at present, the user likes to make a fun at ordinary times, chases a series of Hu Ge, likes to listen to a song of Zhou Jielun, and likes to light music; for the music field, two-level feature labels of Zhou Jielun, light music, relaxation and the like are generated; for the video, hu Ge, fun, relax, play, see at will, and the like secondary feature labels are generated.

In embodiments of the present application, the art suggestions may determine the user's intent based on the current user context, for example, in a weekday morning context, the user may have an intent to work, may also have an intent to drive, or sit on a vehicle, and may have an intent to eat breakfast. In the driving scene, the user may have driving intention, music playing intention and dining intention.

In the embodiment of the application, the art suggestion can construct a corresponding relation between user data and user intentions, for example, the user behavior data is that the user browses a webpage again, the user situation data is that the user is at noon on weekends, the user is at home, the portrait data of the user is that the user watches a television play at home in afternoon on weekends, the personal data of the user comprises videos and music downloaded by the user on the last weekends, and the user intentions corresponding to the user data comprise watching videos, listening music and eating gourmets.

In one possible implementation manner, the artistic recommendation may create an intention analysis model according to the corresponding relationship between the user data and the user intention, and the process of creating the intention analysis model is a process of dividing a plurality of user data samples into a plurality of intention categories and associating each intention category with the content feature corresponding to the user data sample belonging to the intention category.

In the embodiment of the application, after the user data is obtained, the user data can be input into the intention analysis model to obtain the corresponding user intention, or the user intention corresponding to the user data is determined according to the constructed corresponding relationship between the user data and the user intention.

In this embodiment of the present application, multiple target applications may return recommended content together with a reason for recommendation of each recommended content, a recommendation reason template may be separately generated according to each tag field, and each field tag may be repeated, for example, the reason for recommendation in the video field is as follows: latest up-to-date, recent viewing, lead actor xxx, director xxx, martial arts, hallucinations, leader board, scenario, short video, fun, etc., there are recommendation reasons for the music field: new albums, singers, compositions, recent plays, europe and america, solar series, recent plays, user likes, relaxes, fires, spikes, etc. The target application may find the corresponding reason for recommendation from the recommendation reason template according to the corresponding domain tag when returning the recommended content.

Step S57: and receiving the recommended content and the recommended reason returned by the target application in response to the recommendation request.

In this embodiment, step S57 may be performed by a cookie, where the cookie sends a recommendation request to the target application by calling a corresponding interface in step S55, the target application outputs recommended content recommended by the target application in response to the recommendation request and attaches a corresponding reason for recommendation, and the cookie receives the recommended content output by the target application and the reason for recommendation through the interface.

In the embodiment of the application, all target applications splice the recommended content and the recommendation reason according to the preset output specification, and the same format is obtained by processing, so that the recommendations of the target applications can be spliced into a piece of characteristic information which can be used by a framework.

Illustratively, the art suggestions may be the recommended content output by the target application and the corresponding reason for the recommendation, for example, the first music app in the music field recommends "qilixiang", and the reason for the recommendation is: classic, zhou Jielun, common listening, and video app1 in the video field recommends "name of people", the recommendation reason is: drama chase, recent frequent visits, recent searches. Video app2 recommends the up-updated video, recent catch-up, drama, which is of interest to the user. The travel service recommends a two-dimensional code for taking a bus, planning a route for taking a bus and taking a subway. Kendir and mcdonald's are recommended for food and drink. The recommended contents also have attached recommendation reasons, wherein the recommendation reasons of the Zhou Jielun song list are that the user listens frequently, the golden song and the playing amount are high, and the recommendation reasons of the random song list are that the user listens frequently, generates randomly, the playing amount is high, the song is cold and hot. The taxi taking route planning and recommending reason is that the taxi taking route, the user frequently go and the taxi is fast going. Kendyki recommendations are for breakfast, the user often eats, near the company, tuesday membership days, and so forth.

And S59, sorting the recommended contents according to the recommendation reason and outputting the sorted recommended contents to the user.

In this embodiment of the application, step S59 may be performed by a mini-art recommendation, which may construct a re-ranking model, perform matching, scoring, and ranking according to the recommendation reason of the target application recommended content and the user data based on the re-ranking model, and recommend the recommended content ranked earlier to the user according to the final scoring result. That is, the re-ranking model matches the recommended content of each target application and the corresponding recommendation reason with the user data (including one or more of the tag field, the user intention, the user scene, the user behavior data, the user context data, the user personal data and the user portrait) and other characteristics, arranges the returned content of the target application from high to low according to the matching degree, and can select the recommended content with high matching degree to be output to the user.

Specifically, after the recommendation reason and the recommended content are acquired, the content recommended by the target application is filtered and sorted according to the recommendation reason. If the user is walking towards a bus station according to the condition that the mobile phone of the user is not connected with the earphone currently, the two-dimensional codes of music playing, car taking and subway are filtered. And then, judging the scoring of each recommended content by the user according to the matching relation between the user state and the recommended content, wherein the scoring can be realized on the basis of rules or on the basis of a model trained by using the historical behaviors of the user. Based on the rules, the current state features of the user can be used to match with the reason for recommendation. If the user does not eat breakfast, frequent kentucky services can be preferentially recommended to the user. And after the order placement of the user is completed, the catering APP is not recommended any more. Based on the model, the user state can be directly matched with the recommendation reason to calculate the scores of the users for each recommended content, and then the recommended contents are sorted according to the scores.

In the embodiment of the application, the artistic recommendation can refresh the recommendation interface, refresh the recommendation interface at any time according to the target application recommendation content, present the recommendation content on the recommendation interface, and if the interface cannot present the currently obtained recommendation content, can match the recommendation content with high degree or high score on the recommendation interface.

In the embodiment of the application, the novice suggests that the target application is requested for a short time, possibly only once, and then the result obtained by the request is saved locally. And if the mini-art suggestion triggers refreshing according to user operation, user data can be obtained again, a candidate set recommended by the target application is sorted and filtered in real time based on the current latest user data of the user, and the service which is most consistent with the current state of the user is displayed to the user. If the user clicks too early, other breakfast-related services are not displayed, or the user finds that the user takes a vehicle and does not recommend the vehicle-related services.

Based on the method of the embodiment, in addition to recommending the recommended content of the target application according to the user data, the embodiment of the application also provides another content recommendation method, which can monitor the recommendation of the target application. The contents of the above embodiments are all applicable to the method shown in fig. 6, and are not described herein again. Referring to fig. 6, fig. 6 is a schematic flowchart of another content recommendation method according to an embodiment of the present application. The execution subject of the method may be an electronic device as shown in fig. 1, that is, an electronic device on the terminal side. As shown in fig. 6, the method specifically includes:

step S61: feedback of the user is obtained after the recommended content is output to the user.

In the embodiment of the application, after the recommended content is refreshed on the recommendation interface, the electronic device can determine which target application recommended content is better according to the feedback information of the user such as clicking and exposure of the user, and if the user clicks the recommended content recommended by the application A more, the electronic device can determine that the recommended content recommended by the application A is better.

Further, since the target applications may include a plurality of target applications, and each target application may belong to different fields, the artistic proposal may further design different feedback modes for the content in different fields based on the feedback design of the field label, that is, the content evaluation criteria in different fields are also different, for example, the short video field may use the viewing duration as an average criterion, and the taxi taking field may use whether to initiate a taxi taking order as a criterion, etc.

Step S63: and scoring the target application according to the feedback of the user.

In the embodiment of the application, feedback scoring modes of different vertical domains are designed, information such as user clicks, content exposure, exposure time and the like is collected, whether recommended content recommended by target application is high-quality or not is analyzed, and the target application providing high-quality content (with more user clicks) has a high score and is preferentially recommended.

Based on the method of the embodiment, besides recommending the recommended content of the target application according to the user data, the embodiment of the application also provides another content recommending method which can monitor the recommendation of the target application. Referring to fig. 7, fig. 7 is a flowchart illustrating another content recommendation method according to an embodiment of the present application. The execution subject of the method may be a device server having processing capabilities. As shown in fig. 7, the method specifically includes:

step S71: after the recommended content is output to the user, the user data, the recommended content, and the corresponding reason for recommendation are periodically sampled.

In the embodiment of the present application, the content recommendation system may be divided into a server part and a client part, wherein the ranking module is deployed in the server part, and the server executes the content recommendation method shown in fig. 7. After the recommended content is output to the user on the electronic device, the server periodically samples the user data, the recommended content, and a corresponding reason for recommendation.

Step S73: and obtaining the grade of the user on the recommended content to obtain a first grade.

In the embodiment of the application, the recommended content can be presented on the recommendation interface, and meanwhile, the corresponding evaluation control can also be presented, and the user can directly score the recommended content by controlling the control, for example, the user can like, dislike and general, like 100 points, dislike 0 points and general 60 points, or can write scores for different points, such as 60 points, 80 points and 100 points, or the user writes scores by himself to obtain direct feedback of the user on the recommended content.

In one possible implementation manner, the server can also track overall click, goodness, badness and other information of each first application recommended content for a long time to analyze whether the content recommended by the target application is good or not.

Step S75: and calculating the matching degree of the recommended content and the user data to obtain a first matching degree.

In the embodiment of the application, whether the recommended content is matched with the user data or not and whether the recommendation reason can be accurately matched with the current user data or not are evaluated according to various modes such as rules, models, expert knowledge, manpower and the like, so that the first matching degree is obtained.

Step S77: and calculating the matching degree of the recommended content and the recommended reason to obtain a second matching degree.

In the embodiment of the application, whether the recommended content is matched with the reason for recommendation or not is evaluated according to various modes such as rules, models, expert knowledge, manual work and the like, and whether the reason for recommendation can accurately describe the recommended content or not is judged, so that the first matching degree is obtained.

Step S79: and scoring the target application according to one or more of the first score, the first matching degree and the second matching degree.

In the embodiment of the application, the target application can be scored according to content acquisition and analysis in a period of time, the score is sent to the end side, and the content recommended by the target application with high score can be preferentially recommended. Meanwhile, in order to avoid the worst experience, the recommended content of the target application with the score lower than a threshold value is filtered out finally and is not recommended to the user.

In the embodiment of the application, the application recommendation capability is fully utilized, and the recommended content of the target application can be restrained, so that the worst condition caused by low recommendation quality of the target application is avoided. Based on the method, the resource overhead of algorithm development capability brought by sensing of a plurality of fields and the resource overhead of sensing of high-quality service content can be avoided. The method and the device achieve the aim of reducing the overhead and simultaneously keep higher recommendation quality.

Furthermore, a hierarchical label and intention system is introduced, and simultaneously an input/output specification of application access is defined based on the two systems, so that content recommendation by borrowing application recommendation capability becomes possible, and a three-party content supervision scheme is introduced to ensure high quality of recommended content. Development and algorithm teams for recommendation of all fields do not need to be maintained, and meanwhile, recommendation of a plurality of fields with higher levels can be achieved. The target application can be executed according to the appointed output interface, low-value content recommended for the target application can be identified, and worst experience is avoided. The cost of acquisition of the recommended content is almost zero.

While certain exemplary embodiments of the inventive concept have been shown and described, it will be understood by one of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the inventive concept as defined by the following claims. Accordingly, the above-disclosed subject matter is to be considered illustrative, and not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments, which fall within the true spirit and scope of the present inventive concept. Thus, to the maximum extent allowed by law, the scope of the present inventive concept is to be determined by the broadest permissible interpretation of the following claims and their equivalents, and shall not be restricted or limited by the foregoing detailed description.

Embodiments of the present application provide a computer-readable storage medium containing computer-executable instructions for performing the above-described method.

An embodiment of the present application provides a system, including: the computer-readable storage medium described above; and a processor capable of executing the computer-executable instructions.

An embodiment of the present application provides an electronic device, including: at least one memory for storing a program; and at least one processor for executing the memory-stored program, the processor being configured to perform the method as described above when the memory-stored program is executed.

The descriptions of the flows corresponding to the above-mentioned figures have respective emphasis, and for parts not described in detail in a certain flow, reference may be made to the related descriptions of other flows.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. A computer program product for implementing license plate number recognition includes one or more computer instructions for performing license plate number recognition, which when loaded and executed on a computer, cause, in whole or in part, the processes or functions according to fig. 3 of the embodiments of the present application.

The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital Versatile Disk (DVD)), or a semiconductor medium (e.g., solid State Disk (SSD)), among others.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above-mentioned embodiments are provided not to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (15)

1. A content recommendation method, comprising:

acquiring user data;

determining a target application according to the user data;

sending a recommendation request including the user data to the target application;

receiving recommended content returned by the target application in response to the recommendation request;

and outputting the recommended content to the user.

2. The method of claim 1, wherein the receiving the recommended content returned by the target application in response to the recommendation request comprises:

receiving recommended content and a recommendation reason returned by the target application in response to the recommendation request;

the outputting the recommended content to the user includes:

and sorting the recommended contents according to the recommendation reason, and outputting the sorted recommended contents to the user.

3. The method of claim 1 or 2, wherein said determining a target application from said user data comprises:

mapping the user data to corresponding domain tags, wherein each domain tag corresponds to a class of applications;

and determining the first application corresponding to the domain label as a target application.

4. The method of claim 3, wherein the domain label comprises a plurality of domain labels, and wherein the first application is different for each of the domain labels.

5. The method of claim 3 or 4, wherein the sending the recommendation request including the user data to the target application comprises:

determining a corresponding user intention according to the user data;

determining a feature tag of a field corresponding to the field tag according to the user data;

sending a recommendation request to the target application, wherein the recommendation request includes the user intent and the feature tag related to the domain tag corresponding to the target application.

6. The method of any of claims 3 to 5, further comprising:

establishing an intention system and a label system, wherein the intention system comprises the user data and the corresponding user intention, and the label system comprises the user data and the corresponding domain label and the feature label.

7. The method of claim 2, wherein the sorting the recommended content according to the reason for recommendation and outputting the sorted recommended content to the user comprises:

calculating the matching degree of the user data, the recommended content and the recommendation reason;

and sequencing the recommended contents according to the matching degree.

8. The method of any of claims 1 to 7, further comprising:

obtaining feedback of the user after the recommended content is output to the user;

and scoring the target application outputting the recommended content according to the feedback of the user.

9. The method of claim 8, further comprising:

setting a corresponding feedback grading mode according to the target application;

the scoring the target application that outputs the recommended content according to the user's feedback includes:

acquiring a feedback scoring mode corresponding to the target application;

and scoring the target application outputting the recommended content according to the feedback of the user and the feedback scoring mode.

10. The method of any of claims 1 to 9, further comprising:

after the recommended content is output to a user, regularly sampling the score of the user on the recommended content to obtain a first score;

scoring the target application according to the first score.

11. The method of any of claims 1 to 10, further comprising:

after recommended content is output to a user, regularly sampling the user data and the corresponding recommended content;

calculating the matching degree of the user data and the corresponding recommended content to obtain a first matching degree;

and scoring the target application according to the first matching degree.

12. The method of any of claims 1 to 11, further comprising:

after the recommended content is output to a user, periodically sampling the recommended content and the corresponding reason for recommendation;

calculating the matching degree of the recommended content and the corresponding recommendation reason to obtain a second matching degree;

and scoring the target application according to the second matching degree.

13. A computer-readable storage medium containing computer-executable instructions for performing the method of any of claims 1-12.

14. A system, the system comprising:

the computer-readable storage medium of claim 13; and

a processor capable of executing the computer-executable instructions.

15. An electronic device, comprising:

at least one memory for storing a program; and

at least one processor for executing the memory-stored program, the processor for performing the method of any of claims 1-12 when the memory-stored program is executed.

Images