CN117807123A

CN117807123A - Service card recommendation method and electronic equipment

Info

Publication number: CN117807123A
Application number: CN202211211851.1A
Authority: CN
Inventors: 周艳; 李毅; 付家慧; 郑红超; 张乐韶; 张丽; 王鹏
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2022-09-30
Filing date: 2022-09-30
Publication date: 2024-04-02
Also published as: WO2024067293A1

Abstract

The application provides a method and electronic equipment for recommending service cards, wherein the method is applied to the electronic equipment and comprises the following steps: identifying an intention corresponding to a target text in response to a first operation of a user on the electronic equipment; determining a plurality of service cards according to the intention, wherein the service cards provide services corresponding to the intention; displaying the plurality of service cards. According to the scheme provided by the embodiment of the application, the operation flow of manually selecting a plurality of different services by a user can be saved, and the interaction efficiency is improved.

Description

Service card recommendation method and electronic equipment

Technical Field

The embodiment of the application relates to the field of electronic equipment, in particular to a service card recommending method and electronic equipment.

Background

With the rapid development of mobile internet technology, intelligent terminal devices (such as smart phones) are used as an indispensable tool in daily life of users, and almost everyone opens the mobile phone every day to conduct social interaction, learning, entertainment and the like. Because the preference and habit of the user are different, different applications are often installed on the smart phones of different users, different smart phones (such as a working mobile phone and an entertainment mobile phone) of the same user also can install different applications, and frequent interaction behaviors exist between the user and the smart phones. For a certain intention, the smart phone can recommend corresponding results to the user, and the user can select a desired result from the recommended results; however, sometimes implementation of an intention may be performed by relying on multiple service functions, in which case, the user still needs to open different applications to manually select multiple different services to implement the corresponding intention, which is complicated in operation procedure and low in interaction efficiency.

Disclosure of Invention

The embodiment of the application provides a service card recommending method and electronic equipment, which can save the operation flow of manually selecting a plurality of different services by a user and improve the interaction efficiency.

In a first aspect, a method of service card recommendation is provided, the method comprising: identifying an intention corresponding to a target text in response to a first operation of a user on the electronic equipment; determining a plurality of service cards according to the intention, wherein the service cards provide services corresponding to the intention; displaying the plurality of service cards.

According to the scheme provided by the embodiment of the application, the electronic equipment can identify the intention corresponding to the target text selected by the user in response to the first operation of the user on the electronic equipment, a plurality of service functions required by the user can be extracted according to the identified intention, and a plurality of service cards are recommended to the user.

With reference to the first aspect, in some possible implementations, the determining a plurality of service cards according to the intent includes: and combining the interaction path patterns of the user, and determining the plurality of service cards according to the intention, wherein the interaction path patterns of the user are used for describing the operation habit or personal preference of the user when the electronic equipment is used.

According to the scheme provided by the embodiment of the application, the electronic equipment can combine the interaction path map of the user, and a plurality of service cards recommended to the user are determined according to the identified intention, and because the interaction path map is the interaction path map of the user and is strongly related to the historical behavior of the user and the user image, the plurality of service cards recommended by the electronic equipment can accurately provide the service required by the user to the user, so that the recommendation accuracy can be improved.

With reference to the first aspect, in some possible implementations, the interaction path map includes a plurality of nodes and weight coefficients between the nodes, where the nodes represent single-step interaction behavior points of the user, and the weight coefficients represent strengths of cascade relationships between the nodes.

With reference to the first aspect, in some possible implementations, the plurality of service cards include a first service card including a first recommendation corresponding to one of the intents and a second service card including a second recommendation corresponding to the other of the intents, the method further includes: responding to a second operation of clicking the sub-content under the first recommendation result by the user, and displaying a service function corresponding to the sub-content under the first recommendation result; and responding to a third operation of clicking the sub-content under the second recommendation result by the user, and displaying a service function corresponding to the sub-content under the second recommendation result.

According to the scheme provided by the embodiment of the application, the electronic equipment recommends a plurality of service cards to the user according to the intention, the user can select the wanted service based on the service cards, and the user can select the corresponding service only after independently entering each application in the prior art.

With reference to the first aspect, in some possible implementations, the plurality of service cards include a first service card, where the first service card includes a first recommendation corresponding to one of the intents and a first control, where the first control is used to control display of a recommendation including the first recommendation, and the method further includes:

responding to a fourth operation of clicking the first control by the user, and displaying a recommendation result corresponding to one of the intentions; and responding to a fifth operation of selecting a third recommendation result from the recommendation results by the user, and displaying sub-content of the third recommendation result.

According to the scheme provided by the embodiment of the application, the electronic equipment can dynamically understand the intention of the user according to the operation of the user, and display the corresponding recommendation result according to the intention which is dynamically understood, so that the recommendation accuracy can be improved, the requirement of the user is met, and the user experience is improved.

With reference to the first aspect, in some possible implementations, the displaying, in response to a fifth operation of the user selecting a third recommendation from the recommendation results, sub-content of the third recommendation result includes: responding to a fifth operation of selecting a third recommendation result from the recommendation results by the user, and searching sub-content of the third recommendation result from a target service information base according to the position of the third recommendation result in an interaction path map of the user, wherein the target service information base is a service information base corresponding to the third recommendation result; and displaying the sub-content of the third recommendation result according to the interaction path map of the user.

According to the scheme provided by the embodiment of the application, in response to the fifth operation of selecting the third recommendation result from the recommendation results by the user, the intelligent recommendation engine module can search the sub-content of the third recommendation result from the target service information base according to the position of the third recommendation result in the interaction path map of the user, in other words, the intelligent recommendation engine module only needs to search the content related to the third recommendation result, does not need to search the content related to all recommendation results in a large range, can reduce the search range, and improves the search efficiency and the accuracy.

With reference to the first aspect, in some possible implementations, the method further includes: and updating the interaction path map of the user according to the fifth operation.

In this embodiment of the present invention, after the user selects the third recommendation result from the recommendation results, the system may update the interaction path map of the user according to the operation, so as to provide a more accurate recommendation result for the user.

With reference to the first aspect, in some possible implementations, the plurality of service cards includes a first service card including a second control for canceling the first service card, and the method further includes: and responding to a sixth operation of clicking the second control by the user, and canceling the display of the first service card on the electronic equipment.

According to the scheme provided by the embodiment of the application, for the service which is not needed by the user, the user can cancel the service card which is not needed by the user through the second control, so that the user experience can be improved.

With reference to the first aspect, in some possible implementations, the method further includes: constructing a universal interaction path map; and modifying the universal interaction path map according to the information of the user, and assigning weights among nodes of the modified universal interaction path map to obtain the interaction path map of the user.

According to the scheme provided by the embodiment of the application, on the basis of the universal interaction path map, the system can modify the universal interaction path map according to the information of the user, and the user interaction path map is obtained after the weight of the modified universal interaction path map is assigned, so that the intelligent recommendation engine module can recommend corresponding services to the user according to the user interaction path map, and the recommendation accuracy can be improved.

In a second aspect, an apparatus is provided, the apparatus being included in an electronic device, the apparatus having functionality to implement the above aspect and possible implementations of the above aspect. The functions may be realized by hardware, or may be realized by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the functions described above.

In a third aspect, an electronic device is provided, comprising: one or more processors; a memory; one or more applications; and one or more computer programs. Wherein one or more computer programs are stored in the memory, the one or more computer programs comprising instructions. The instructions, when executed by an electronic device, cause the electronic device to perform the method in any of the possible implementations of the first aspect described above.

In a fourth aspect, there is provided a system on a chip comprising at least one processor, wherein program instructions, when executed in the at least one processor, cause the functions of the method of any one of the possible implementations of the first aspect to be implemented on the electronic device.

In a fifth aspect, there is provided a computer storage medium comprising computer instructions which, when run on an electronic device, cause the electronic device to perform the method of any one of the possible implementations of the first aspect.

In a sixth aspect, there is provided a computer program product for, when run on an electronic device, causing the electronic device to perform the method of any one of the possible designs of the first aspect.

Drawings

Fig. 1 is a schematic hardware structure of an electronic device provided in the present application.

Fig. 2 is a schematic software structure of an electronic device provided in the present application.

FIG. 3 is a schematic diagram of a set of GUIs provided in an embodiment of the present application.

Fig. 4 is a schematic diagram of another set of GUIs provided in an embodiment of the present application.

Fig. 5 is a schematic diagram of a system architecture to which embodiments of the present application may be applied.

Fig. 6 is a schematic diagram of service information division according to an embodiment of the present application.

FIG. 7 is a schematic diagram of a constructed user representation provided in an embodiment of the present application.

Fig. 8 is a schematic diagram of a method for constructing a user portrait according to an embodiment of the present application.

Fig. 9 is a schematic diagram of an interaction path map according to an embodiment of the present application.

Fig. 10 is a schematic diagram of correction compensation information according to an embodiment of the present application.

Fig. 11 is a schematic diagram of a result recommendation provided in an embodiment of the present application.

Fig. 12 is a schematic diagram of an optimal service recommendation provided in an embodiment of the present application.

Fig. 13 is a schematic diagram of a combined service recommendation provided in an embodiment of the present application.

Fig. 14 is a schematic diagram of one or more interaction schemes according to an embodiment of the present application.

Fig. 15 is a schematic diagram of a method for recommending service cards according to an embodiment of the present application.

Fig. 16 is a schematic block diagram of an electronic device according to an embodiment of the present application.

Fig. 17 is a schematic block diagram of another electronic device provided in 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. Wherein, in the description of the embodiments of the present application, "/" means or is meant unless otherwise indicated, for example, a/B may represent a or B; "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, in the description of the embodiments of the present application, "plurality" means two or more than two.

The terms "first" and "second" are used below for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.

The scheme provided by the application can be applied to electronic devices such as mobile phones, tablet computers, personal computers (personal computer, PC), wearable devices, vehicle-mounted devices, augmented reality (augmented reality, AR)/Virtual Reality (VR) devices, notebook computers, ultra-mobile personal computer (UMPC), netbooks, personal digital assistants (personal digital assistant, PDA) and the like, and the specific types of the electronic devices are not limited.

By way of example, fig. 1 shows a schematic diagram of an electronic device 100. The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (universal serial bus, USB) interface 130, a charge 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, keys 190, a motor 191, an indicator 192, a camera 193, a display 194, and a subscriber identity module (subscriber identification module, SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyro sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity 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 structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, electronic device 100 may include more or fewer components than shown, or certain components may be combined, or certain components may be split, or different arrangements of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

The processor 110 may include one or more processing units, such as: the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a memory, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and/or a neural network processor (neural-network processing unit, NPU), etc. Wherein the different processing units may be separate devices or may be integrated in one or more processors.

The controller may be a neural hub and a command center of the electronic device 100, among others. The controller can generate operation control signals according to the instruction operation codes and the time sequence signals to finish the control of instruction fetching and instruction execution.

A memory may also be provided in the 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 the processor 110 has just used or recycled. If the processor 110 needs to reuse the instruction or data, it can be called directly from the memory. Repeated accesses are avoided and the latency of the processor 110 is reduced, thereby improving the efficiency of the system.

In some embodiments, the processor 110 may include one or more interfaces. The interfaces may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver transmitter (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 (subscriber identity module, SIM) interface, and/or a universal serial bus (universal serial bus, USB) interface, among others.

It should be understood that the interfacing relationship between the modules illustrated in the embodiments of the present application is only illustrative, and does not limit the structure of the electronic device 100. In other embodiments of the present application, the electronic device 100 may also use different interfacing manners, or a combination of multiple interfacing manners in the foregoing embodiments.

The charge management module 140 is configured to receive a charge input from a charger. The charger can be a wireless charger or a wired charger. In some wired charging embodiments, the charge management module 140 may receive a charging input of a wired charger through the USB interface 130. In some wireless charging embodiments, the charge management module 140 may receive 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 for connecting the battery 142, and the charge 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 provides power to the processor 110, the internal memory 121, the external memory, the display 194, the camera 193, the wireless communication module 160, and the like. The power management module 141 may also be configured to monitor battery capacity, battery cycle number, battery health (leakage, impedance) and other parameters. In other embodiments, the power management module 141 may also be provided in the processor 110. In other embodiments, the power management module 141 and the charge management module 140 may 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 may also be multiplexed to improve the utilization of the antennas. For example: the antenna 1 may be multiplexed into 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 for wireless communication including 2G/3G/4G/5G, etc., applied to the electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA), etc. The mobile communication module 150 may receive electromagnetic waves from the antenna 1, perform processes such as filtering, amplifying, and the like on the received electromagnetic waves, and transmit the processed electromagnetic waves to the modem processor for demodulation. The mobile communication module 150 can amplify the signal modulated by the modem processor, and convert the signal into electromagnetic waves through the antenna 1 to radiate. 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 provided 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 the 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 transmits the demodulated low frequency baseband signal to the 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 sound signals through an audio device (not limited to the speaker 170A, the receiver 170B, etc.), or displays images 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 module, independent of the processor 110.

The wireless communication module 160 may provide solutions for wireless communication including wireless local area network (wireless local area networks, WLAN) (e.g., wireless fidelity (wireless fidelity, wi-Fi) network), bluetooth (BT), global navigation satellite system (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field wireless communication technology (near field communication, NFC), infrared technology (IR), etc., as applied to the electronic device 100. The wireless communication module 160 may be one or more devices that integrate at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the electromagnetic wave signals, filters the 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, frequency modulate it, amplify it, and convert it to electromagnetic waves for radiation via the antenna 2.

In some embodiments, antenna 1 and mobile communication module 150 of electronic device 100 are coupled, and antenna 2 and wireless communication module 160 are coupled, such that electronic device 100 may communicate with a network and other devices through wireless communication techniques. The wireless communication techniques may include the Global System for Mobile communications (global system for mobile communications, GSM), general packet radio service (general packet radio service, GPRS), code division multiple access (code division multiple access, CDMA), wideband code division multiple access (wideband code division multiple access, WCDMA), time division code division multiple access (time-division code division multiple access, TD-SCDMA), long term evolution (long term evolution, LTE), BT, GNSS, WLAN, NFC, FM, and/or IR techniques, among others. The GNSS may include a global satellite positioning system (global positioning system, GPS), a global navigation satellite system (global navigation satellite system, GLONASS), a beidou satellite navigation system (beidou navigation satellite system, BDS), a quasi zenith satellite system (quasi-zenith satellite system, QZSS) and/or a satellite based augmentation system (satellite based augmentation systems, SBAS).

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

The display screen 194 is used to display images, videos, and the like. The display 194 includes a display panel. The display panel may employ a liquid crystal display (liquid crystal display, LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED) or an active-matrix organic light-emitting diode (matrix organic light emitting diode), a flexible light-emitting diode (flex), a mini, a Micro led, a Micro-OLED, a quantum dot light-emitting diode (quantum dot light emitting diodes, 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 photographing functions through an ISP, a camera 193, a video codec, a GPU, a display screen 194, an application processor, and the like.

The ISP is used to process data fed back by the camera 193. For example, when photographing, the shutter is opened, light is transmitted to the camera photosensitive element through the lens, the optical signal is converted into an electric signal, and the camera photosensitive element transmits the electric signal to the ISP for processing and is converted into an image visible to naked eyes. ISP can also optimize the 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 the 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 onto the photosensitive element. The photosensitive element may be a charge coupled device (charge coupled device, CCD) or a Complementary Metal Oxide Semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, which is then transferred to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV, or the like format. 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 other digital signals besides digital image signals. For example, when the electronic device 100 selects a frequency bin, the digital signal processor is used to fourier transform the frequency bin energy, or the like.

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: dynamic picture experts group (moving picture experts group, MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

The NPU is a neural-network (NN) computing processor, and can rapidly process input information by referencing a biological neural network structure, for example, referencing a transmission mode between human brain neurons, and can also continuously perform self-learning. Applications such as intelligent awareness of the electronic device 100 may be implemented through the NPU, for example: image recognition, face recognition, speech recognition, text understanding, etc.

The external memory interface 120 may be used to connect an external memory card, such as a Micro SD card, to enable expansion of the memory capabilities of the electronic device 100. The external memory card communicates with the processor 110 through an external memory interface 120 to implement data storage functions. For example, files such as music, video, etc. are stored in an external memory card.

The internal memory 121 may be used to store computer executable program code including instructions. The processor 110 executes various functional applications of the electronic device 100 and data processing by executing instructions stored in the internal memory 121. The internal memory 121 may include a storage program area and a storage data area. The storage program area may store an application program (such as a sound playing function, an image playing function, etc.) required for at least one function of the operating system, etc. The storage data area may store data created during use of the electronic device 100 (e.g., audio data, phonebook, etc.), and so on. In addition, the internal memory 121 may include a high-speed random access memory, and may further include a nonvolatile memory such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (universal flash storage, UFS), and the like.

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

The pressure sensor 180A is used to sense a pressure signal, and may 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 is of various types, such as a resistive pressure sensor, an inductive pressure sensor, a capacitive pressure sensor, and the like. The capacitive pressure sensor may be a capacitive pressure sensor comprising at least two parallel plates with conductive material. The capacitance between the electrodes changes when a force is applied to the pressure sensor 180A. 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 touch operation intensity according to the pressure sensor 180A. The electronic device 100 may also calculate the location of the touch based on the detection signal of the pressure sensor 180A. In some embodiments, touch operations that act on the same touch location, but at different touch operation strengths, may correspond to different operation instructions. For example: and executing an instruction for checking the short message when the touch operation with the touch operation intensity smaller than the first pressure threshold acts on the short message application icon. And executing an instruction for newly creating the short message when the touch operation with the touch operation intensity being greater than or equal to the first pressure threshold acts on the short message application icon.

The gyro sensor 180B may be used to determine a motion gesture of the electronic device 100. The air pressure sensor 180C is used to measure air pressure. The magnetic sensor 180D includes a hall sensor. The electronic device 100 may detect the opening and closing of the flip cover using the magnetic sensor 180D. 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 may be detected when the electronic device 100 is stationary. A distance sensor 180F for measuring a distance. The electronic device 100 may measure the distance by infrared or laser. 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 ambient light sensor 180L is used to sense ambient light level. The electronic device 100 may adaptively adjust the brightness of the display 194 based on the perceived ambient light level. The fingerprint sensor 180H is used to collect a fingerprint. The temperature sensor 180J is for detecting temperature. The touch sensor 180K, also referred to as a "touch panel". The touch sensor 180K may be disposed on the display screen 194, and the touch sensor 180K and the display screen 194 form a touch screen, which is also called a "touch screen". The bone conduction sensor 180M may acquire a vibration signal. In some embodiments, bone conduction sensor 180M may acquire a vibration signal of a human vocal tract vibrating bone pieces.

The software system of the electronic device 100 may employ a layered architecture, an event driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture. In this embodiment, taking an Android system with a layered architecture as an example, a software structure of the electronic device 100 is illustrated.

Fig. 2 is a software configuration block diagram of the electronic device 100 according to the embodiment of the present application. The layered architecture divides the software into several layers, each with distinct roles and branches. The layers communicate with each other through a software interface. In some embodiments, the android system is divided into four layers, from top to bottom, an application layer, an application framework layer, an Zhuoyun row (android run) and system libraries, and a kernel layer, respectively. The application layer may include a series of application packages.

As shown in FIG. 2, the application framework layer may include a window manager, a content provider, a view system, a telephony manager, a resource manager, a notification manager, and the like.

The window manager is used for managing window programs. The window manager can acquire the size of the display screen, judge whether a status bar exists, lock the screen, intercept the screen and the like.

The content provider is used to store and retrieve data and make such data accessible to applications. The data may include video, images, audio, calls made and received, browsing history and bookmarks, phonebooks, etc.

The view system includes visual controls, such as controls to display text, controls to display pictures, and the like. The view system may be used to build applications. The display interface may be composed of one or more views. For example, a display interface including a text message notification icon may include a view displaying text and a view displaying a picture.

The resource manager provides various resources for the application program, such as localization strings, icons, pictures, layout files, video files, and the like.

The notification manager allows the application to display notification information in a status bar, can be used to communicate notification type messages, can automatically disappear after a short dwell, and does not require user interaction. Such as notification manager is used to inform that the download is complete, message alerts, etc. The notification manager may also be a notification in the form of a chart or scroll bar text that appears on the system top status bar, such as a notification of a background running application, or a notification that appears on the screen in the form of a dialog window. For example, a text message is prompted in a status bar, a prompt tone is emitted, the electronic device vibrates, and an indicator light blinks, etc.

The android runtime includes a core library and virtual machines. And the android running time is responsible for scheduling and managing an android system.

The core library consists of two parts: one part is a function which needs to be called by java language, and the other part is a core library of android.

For ease of understanding, the background art related to the present application is first described below.

In order to solve the problem, the application provides a service card recommendation method, when an intention needs to be completed by means of a plurality of service functions, a system can conduct combined recommendation to a user, namely, a plurality of service cards are simultaneously recommended to the user, and the user can select corresponding service cards according to own requirements. When a user selects a certain service card, the user can select a corresponding service according to a recommendation result recommended by the system, so that the operation flow of manually selecting a plurality of different services by the user can be saved, and the interaction efficiency is improved.

In addition, during the interaction of the user with the smartphone, the smartphone may recommend corresponding information or functions to the user according to the identified user intent. However, the recommendation mode is realized based on an intelligent recommendation technology, is mostly used for a recommendation scene of 'one-key direct', and returns a final recommendation result through a series of processes of recalling, filtering, fine arranging, mixed arranging, strong rules and the like on the content in the information base, so that the process is complex, the calculation is complex, and the recommendation result is often inaccurate and the requirement of a user is difficult to meet due to the reasons of serious data long tail distribution, complex dependency, difficult coverage of modeling and the like.

The other mode is to construct a complete knowledge graph aiming at a specific scene, describe the information and the corresponding relation of all the related nodes, extract the retrieval vector from the input information of the user, obtain the best matching result in the knowledge graph and recommend the best matching result to the user. However, the technology is realized by a knowledge graph method, can only be suitable for scenes with clear cascade relations, is also a one-key direct type recommendation technology in essence, and the recommendation result is often inaccurate.

In order to solve the technical problem, the embodiment of the application also provides a dynamic correction compensation technology, in the gradual interaction process of the user and the intelligent equipment, the intelligent equipment can dynamically identify the user intention according to the real-time operation behavior of the user and update the recommendation result according to the dynamically identified intention, and the recommendation accuracy can be improved, so that the user requirement is met.

The embodiment of the application can be applied to scenes where the user frequently interacts with the intelligent device, such as combined service recommendation, takeaway order, intelligent navigation, chat conversation, global search, voice conversation and the like.

The following embodiments of the present application will take an electronic device having a structure shown in fig. 1 and fig. 2 as an example, and specifically describe a method for recommending services provided in the embodiments of the present application in conjunction with the accompanying drawings and application scenarios.

Fig. 3 shows a set of graphical user interfaces (graphical user interface, GUI) of the handset, where from (a) in fig. 3 to (p) in fig. 3 shows that a first application in the handset initially identifies user intent to make a combined service recommendation to the user and dynamically identifies user intent in conjunction with the user's real-time operational behavior and updates the recommendation results based on the dynamically identified intent.

See the GUI shown in fig. 3 (a), which is the desktop of the handset. When the mobile phone detects that the user clicks on the icon 301 of the first application on the desktop, the first application may be started, and a GUI, which may be referred to as a main interface of the first application, is displayed as shown in (b) of fig. 3.

Referring to the GUI shown in fig. 3 (b), there is shown: a primary interface of a first application that includes a plurality of contacts, such as Zhang three, lifour, and the like. When the handset detects that the user clicks on the icon 302 of contact three, a GUI as shown in fig. 3 (c) may be displayed.

Referring to the GUI shown in fig. 3 (c), the interface displays chat content of the user with Zhang san. The user sends a chat content of 'eight and a half of every day after work take meal together at Li Gucun ten thousand times' to Zhang san, and receives a good content of Zhang san reply. At this time, the user may select and long press the content of "eat meal together at Li Gucun ten thousand times after the shift, and when the mobile phone detects that the user long presses the icon 303 of the selected chat content, the user's intention may be recognized, and the intelligent recommendation engine module may make a combined recommendation to the user according to the recognized intention, and may display a GUI as shown in (d) of fig. 3.

Referring to the GUI shown in (d) of fig. 3, it can be seen that the selected content that the user presses long has been filled in gray at this time, and furthermore, a plurality of boxes including a food recommendation, a travel recommendation, and a schedule reminder are displayed under the interface. The user can select or cancel the corresponding bullet frame according to the own requirement. By way of example, taking travel recommendations as an example, assuming that the user is not driving to work today, a reservation vehicle may be needed, a vehicle may be reserved by a recommended drop out, and an icon in the upper right corner of the drop out box may be clicked Amplifying the bullet frame of travel recommendation and reserving; assuming that the user is working on duty today, the user does not need to reserve the vehicle by dripping, and can click the icon at the upper right corner of the box of dripping by cancelling the box of dripping. When the mobile phone detects that the user clicks the top right corner +.>After the operation of icon 304, a GUI as shown in (e) of fig. 3 may be displayed.

Referring to the GUI shown in fig. 3 (e), the interface displays an enlarged popup comment frame, and at this time, the popup comment recommends to the user a food of the hamburger western style, and displays the recommended western style food 1 and 2 at the lower side, and the user can click on the western style food that he wants to enjoy to make a reservation or order, etc.; the user may also select a store where the user wants to eat by sliding about a western style meal that displays more categories or stores. If the user does not want to eat western style foods today, the user can also click on the drop down menu on the right side of the icon hamburger western style food to select the desired food category. When the mobile phone detects that the user clicks a drop-down menu on the right side of a hamburger western-style foodAfter the operation of the icon 305 of (a), a GUI as shown in (f) of fig. 3 may be displayed.

Referring to the GUI shown in fig. 3 (f), it can be seen that various kinds of delicacies, such as hamburger western-style food, chinese meal, japanese and korean cuisine, dessert drinks, fried-in-sauce snacks, and others, are displayed in the list of the pull-down menu. The user may click on an icon of any kind of food, and when the mobile phone detects an operation of clicking on the icon 306 of the chinese meal by the user, the GUI shown in fig. 3 (g) may be displayed.

In combination with the GUI shown in fig. 3 (g), at this time, the public comment that the frame is displaying Chinese meal, and at the same time, the recommended Chinese meal 1 and Chinese meal 2 are displayed below the Chinese meal, so that the user can click the Chinese meal to be eaten to make a reservation for ordering, etc.; if Chinese 1 and Chinese 2 are not desired, the user can also display more kinds or stores of Chinese by sliding left and right and can make a reservation for ordering after selecting a certain Chinese (such as Chinese 3). After all the food operations are completed, the user can click on the iconThe popup criticizing bullet frame is reduced. When the mobile phone detects that the user clicks the icon +.>307, the interface displays the GUI shown in (h) of fig. 3.

Referring to the GUI shown in (h) of fig. 3, a plurality of boxes including food recommendations, travel recommendations, and schedule reminders are displayed under the interface. Also, for the food recommendation, the public critique this box shows the Chinese meal 3 that the user has selected and the reservation has been completed in this Chinese meal 3. If the user needs to recommend the drip reservation vehicle through the intelligent recommendation engine module, the user can click the icon at the upper right corner of the drip frameWhen the mobile phone detects that the user clicks the upper right corner of the bullet frame, the user clicks the dripping hole >After the operation of icon 308 of (c), the interface displays a GUI as shown in fig. 3 (i).

Referring to the GUI shown in fig. 3 (i), it can be seen that the interface displays an enlarged drop out box, and the estimated cost of this trip is 20-80 yuan below the box. When the mobile phone detects an operation of clicking on the fee 309 by the user, the interface displays a GUI as shown in (j) in fig. 3.

Referring to the GUI shown in (j) of fig. 3, at this time, the user is recommended to the user to be a express car, and the estimated cost of taking the express car is 28 yuan, if the user wants to take the express car, the user can click the function button "reserving the express car" displayed below the interface; if the user does not want to take the express way, the user can click on the drop-down menu on the right side of the express wayWhen the mobile phone detects that the user clicks the drop-down menu on the right side of the express car +.>After the operation of icon 310, the interface displays a GUI as shown in (k) of fig. 3. />

Referring to the GUI shown in (k) of fig. 3, a list of the drop-down menu displays a plurality of vehicles that can be taken and corresponding estimated fees, for example, 80 yuan for a luxury vehicle and the corresponding estimated fees for the vehicle, 20 yuan for a taxi and the corresponding estimated fees for the vehicle, 35 yuan for a special vehicle and the corresponding estimated fees for the vehicle, and 28 yuan for a express vehicle and the corresponding estimated fees for the vehicle. The user can select any one of the vehicles to be reserved, and when the mobile phone detects an operation of clicking the icon 311 of the taxi by the user, the interface displays a GUI as shown in (l) of fig. 3.

Referring to the GUI shown in fig. 3 (l), the interface displays the taxi and the corresponding estimated cost of 20 yuan, and the interface is replaced by "reserved taxi" at the same time, and after the mobile phone detects the operation of the user clicking the icon 312 of the function button of "reserved taxi", the interface displays the GUI shown in fig. 3 (m).

Referring to the GUI shown in FIG. 3 (m), the interface displays the user's reserved taxis and the corresponding fare forecast as 20 yuan, at which point the user may click on the iconThe elastic frame for the dropping out of the water tank is reduced. When the mobile phone detects that the user clicks the icon +.>313, the interface displays the GUI shown in (n) of fig. 3.

Referring to the GUI shown in fig. 3 (n), a plurality of boxes including food recommendations, travel recommendations, and schedule reminders are displayed under the interface. And for travel recommendation, displaying the taxi reserved by the user and the estimated cost in the bullet box of the drip-out travel. If the user needs to remind himself through the new schedule recommended by the intelligent recommendation engine module, the icon at the upper right corner of the new schedule frame can be clickedWhen the mobile phone detects that the user clicks the upper right corner of the new schedule drop outlet box >After the operation of icon 314, the interface displays a GUI as shown in (o) of fig. 3.

Referring to the GUI shown in (o) of fig. 3, the interface displays an enlarged new calendar as a box, and two function buttons of "ok" and "cancel" are displayed below the box, and the user may click the ok function button to set up a calendar reminder, or may click the cancel function button to cancel the calendar reminder. When the handset detects a user click on the ok this function button 315, the interface displays a GUI as shown in (p) of fig. 3.

Referring to the GUI shown in (p) of fig. 3, a plurality of boxes including food recommendations, travel recommendations, and schedule reminders are displayed under the interface. And for food recommendation, travel recommendation and schedule reminding, the public critique is that the bullet frame displays user reservation, and the bullet frame displays user establishment.

According to the scheme provided by the embodiment of the application, after the user presses the selected content for a long time, the intelligent device can identify the intention of the content selected by the user, a plurality of service functions required by the user can be extracted according to the identified intention, the optimal combined service is recommended, and the user can select the corresponding service according to the self demand. In addition, in the interaction process of the user and the intelligent equipment, the intelligent equipment can dynamically identify the user intention by combining with the real-time operation behavior of the user and update the recommendation result according to the dynamically identified intention.

Fig. 4 shows a set of GUIs for a handset, where from (a) in fig. 4 to (d) in fig. 4 show that the handset initially recognizes that the user intends to make a combined service recommendation to the user.

See the GUI shown in fig. 4 (a), which is the desktop of the handset. When the mobile phone detects that the user's finger is slid leftward in the direction shown in the figure, a GUI shown in (b) of fig. 4 is displayed.

Referring to the GUI shown in (b) of fig. 4, the interface displays a list including a plurality of tags such as notification, epidemic prevention code, news, weather, food, trip, shopping, entertainment, etc. The user can input the content by voice, and the mobile phone can recognize the voice input by the user after detecting the operation of the user pressing the power key 401 for a long time and inputting the content by voice on the assumption that the user inputs "eight and a half of the time and Zhang san together eat meal at Li Gucun ten thousand", and the interface displays the GUI as shown in (c) of fig. 4.

Referring to the GUI shown in fig. 4 (c), the interface displays the text "eight-half after the next shift and Zhang Sanzhang eat meal together at Li Gucun, at which time the user may select the content of" eight-half after the next shift and Zhang Sanzhang eat meal together at Li Gucun ", and when the mobile phone detects the operation of the user's long pressing the icon 402 of the selected content, the user's intention may be recognized, the intelligent recommendation engine module may make a combined recommendation to the user according to the recognized intention, and the GUI shown in fig. 4 (d) may be displayed.

Referring to the GUI shown in (d) of fig. 4, it can be seen that the selected content that the user presses long has been filled in gray at this time, and furthermore, a plurality of boxes including a food recommendation, a travel recommendation, and a schedule reminder are displayed on the right side of the interface. The user can select or cancel the corresponding bullet frame according to the own requirement. By way of example, taking travel recommendations as an example, assuming that the user is not driving to work today, a reservation vehicle may be needed, a vehicle may be reserved by a recommended drop out, and an icon in the upper right corner of the drop out box may be clickedAmplifying the bullet frame of travel recommendation and reserving; assuming that the user is working on duty today, the user does not need to reserve the vehicle by dripping, and can click the icon at the upper right corner of the box of dripping by cancelling the box of dripping. The subsequent operations may be referred to the GUI shown in fig. 3 (e) to fig. 3 (p), and will not be described again.

Of course, in some possible implementation manners, the user may directly input the content by voice, the mobile phone recognizes the voice input by the user and then displays the corresponding text, when the mobile phone detects that the user presses the icon of the selected content for a long time, the user's intention can be recognized, and the intelligent recommendation engine module can make a combined recommendation to the user according to the recognized intention.

According to the scheme provided by the embodiment of the application, the intelligent device can identify the content input by the user through voice and display the text of the corresponding content, after the user presses the selected content for a long time, the intelligent device can identify the intention of the content selected by the user, extract a plurality of service functions required by the user according to the identified intention and recommend the optimal combined service, and the user can select the corresponding service according to the own requirement. In addition, in the interaction process of the user and the intelligent equipment, the intelligent equipment can dynamically identify the user intention by combining with the real-time operation behavior of the user and update the recommendation result according to the dynamically identified intention.

The system architecture to which the embodiments of the present application may be applied is shown in fig. 5, where the system architecture mainly includes three modules: the system comprises a service library construction module, a progressive interaction module and an intelligent recommendation engine module.

The service library construction module is mainly used for acquiring data information of the intelligent equipment end, such as user historical behavior information, full service capability information, basic information (the basic information includes but is not limited to information such as current time and geographic position), and the like, and can analyze and model users, services and dependency relationships thereof according to the data information, label complex data information, construct an intelligent recommendation service information library, and uniformly provide the intelligent recommendation service information library as input for a follow-up intelligent recommendation engine module and a progressive interaction module to use.

The progressive interaction module mainly constructs a user interaction path map according to the clustering division result of the intelligent recommendation service information base constructed by the service base construction module, and traversals and symbolizes the interaction path. And then, according to the constructed interaction path map, acquiring correction compensation information by combining the real-time interaction behaviors of the user, and providing the correction compensation information as important guiding information for an intelligent recommendation engine module.

The intelligent recommendation engine module is mainly a search recommendation engine based on user interaction behaviors, and implicitly guides the weight model reasoning process of the intelligent recommendation engine by combining the user interaction path spectrum and the correction compensation characteristic information, searches in a service information base with association relation with the current interaction node instead of searching in the whole service information base, so that user intention can be quickly and accurately identified.

The specific process of implementing the embodiment of the application through the above three modules is described below by taking the smart device as an example of a mobile phone.

1. Service library construction module

The service library construction module comprises three sub-functions, namely service capability library construction, user portrait construction and basic information acquisition.

(1) And (3) constructing a service capability library: the service library construction module can collect the total service information in the mobile phone, wherein the service can comprise system-level services (such as self-contained services when the mobile phone leaves the factory, such as video, music, gallery, weather and the like) and three-party services (such as services for users to download applications by themselves, such as WeChat)Instant messaging service, beauty group->Is a take-out order service, taobao +.>Or Beijing dong->And the like), the service library construction module can perform multi-level service clustering division on the total service information by combining the service scene and the service label information so as to construct a total service information library.

Referring to fig. 6, the service library construction module may divide service information into a plurality of tags, such as a primary tag, a secondary tag, a tertiary tag, and the like. The primary labels may include travel, entertainment, food, shopping, etc., and for each primary label, there may be a corresponding secondary label. For example, for travel this primary label, its secondary label may include traffic, attractions, driving, navigation, etc.; for entertainment this primary tag, its secondary tag may include games, music, video, reading, etc.; the tertiary tag may include payment; similarly, a full library of service information may be built.

(2) User portrayal construction: the service library construction module can conduct behavior modeling by analyzing data information of the user, for example, habit and preference of the user can be mined, and user portraits can be constructed according to the habit and preference of the mined user.

FIG. 7 is a schematic diagram of a constructed user representation according to an embodiment of the present application.

Referring to FIG. 7, the main characterizing dimensions of a user representation may include the following aspects:

(1) population attributes: basic information such as sex, age, occupation, consumption level, education level, etc. of user

(2) Consumption scenario: prediction time, prediction position, demand scene, decision stage, etc

(3) App behavior: activities of user installation, uninstallation and APP usage, etc., wherein the activities of APP usage may include time of first and last use of APP, total duration of use of APP, total number of times of use of APP, time of downloading or uninstalling APP, etc

(4) Interest concerns: user brand preferences, personal interests, and the like

(5) Social attributes: user-active social media and the like

(6) Time attribute: active time of user using mobile phone, active time of user using application, working period, home period, etc

(7) Position attribute: the user is in the city, often in the area, traveling situation, real-time position, etc

The specific information included in each dimension may refer to the content shown in fig. 7, which is not described herein. It should be noted that the specific information included in each dimension shown in fig. 7 is only an example, and other more information may be included. Of course, the depicting dimensions of the user representation may not be limited to those shown in fig. 7, and the dimensions shown in fig. 7 are merely examples and should not be construed as limiting the application in any way.

When the user portrait is specifically constructed, the method can be implemented according to the flow chart shown in fig. 8:

s801, collecting user data.

The user data in the embodiment of the application may include static data and dynamic data, where the static data may mine attribute information such as population attribute, business attribute and the like of the user according to historical registration information, member information and the like of the user; the dynamic information is behavior information of the user, which is changed continuously, and can acquire historical behavior information of the user in a continuous time in a mobile phone system log or a three-party service, including but not limited to browsing information, service use information (installation, uninstallation, login, use duration, frequency and the like), consumption behavior and the like.

In the embodiment of the application, the mobile phone system log (such as album, file manager, video, music and the like of the mobile phone leaving factory) or the third party service (such as panning downloaded by the userJingdong->Lesion (Lesion) Sida>WeChat->) The historical behavior of the user can be recorded, so that the historical behavior information of the user can be obtained through the mobile phone system log or the three-party service.

S802, data standardization is carried out on the user data.

The user data obtained in step S801 is often complex and irregular, and has serious problems such as many data deletions, duplications, errors, and the like, and cannot be directly used. In order to facilitate the subsequent successful modeling, the data can be subjected to standardized processing, such as processing flows of cleaning the data (such as deleting repeated values, cleaning abnormal values, interpolating missing values), normalizing and the like, and the fact label is primarily acquired.

The fact label in the embodiment of the application may be: the duration of using a certain APP by a user, the frequency of using a certain APP by a user in a period of time, the information browsed by a user using a certain APP, and the like.

S803, modeling is conducted based on the fact label, and a user portrait is built.

After the fact label is acquired, the acquired fact label may be modeled to obtain a user representation of the user, e.g., may be modeled using a hybrid modeling approach based on rules and machine learning.

Firstly, the fact label can be counted based on rules (such as a digital counting rule) to obtain label information of the user, such as a specific label of the user under the first-level label (including shopping, entertainment, food and travel); second, deeper user tag information can be mined based on machine learning modeling.

Specifically, suppose that the user uses the curiosityCool dog music->The king glows->Hero alliance->And the number of times of APP with entertainment function is more, the primary label of the user can be listed as the label of entertainment,i.e. the user belongs to an entertainment type user; furthermore, tag information based on rule statistics can be combed according to a data format of user identification+time+place+behavior type+contact point (website+content), the tag information is taken as a data prototype of a user portrait, the user is vectorized by using Bert, the tag information is taken as input of a long short-term memory (LSTM) model, vector characterization is obtained, a multi-tag classification algorithm is combined, user preference is mined deeply, further tag information of a deeper level is obtained, for example, the user likes one or more of games, music listening, video watching and reading, and the like, and if the user is used for listening to music for most of the time, the two types of tags of the user can be listed as the tag of music.

S804, updating and perfecting the user portrait based on continuous interaction with the user.

After the user portrait of the user is constructed, new tag data can be further supplemented through continuous interaction of the subsequent user, so that the user portrait is perfected and updated.

(3) Basic information acquisition

Basic information of the current user is acquired from the mobile phone terminal, including but not limited to geographic position coordinates, time, weather and the like, and the information can be obtained by calling a mobile phone system log or a three-party service.

2. Progressive interaction module

The progressive interaction module comprises two sub-functions, namely interaction path map construction of a user and progressive interaction correction compensation.

(1) Constructing an interaction path map of a user: the progressive interaction module can construct an interaction path map of the user according to the historical behaviors of the user, the clustering of service information and the interaction cascade relation.

Interaction path map: the method can characterize the operation habit or personal preference of the user when using intelligent equipment such as a mobile phone.

The interaction path map consists of nodes and node weight coefficients, wherein the nodes represent single-step interaction behavior points (functional points which can be reached by a user) of the user, and the node weight coefficients describe the strength of interaction relation between the nodes and surrounding nodes (nodes with direct interaction relation).

In the construction of the interaction path map, firstly, an orderly rule can be extracted from interaction behavior analysis of a large number of users, a general interaction path map is constructed, and node weight coefficients are assigned according to the historical behaviors of the users and user images; and secondly, the nodes and the node weights are perfected and updated on line based on a correction compensation technology in the use process of the user.

Referring to fig. 9, the interaction path graph includes a plurality of nodes and weight coefficients, such as node 1-1, node 1-2, node 1-3, etc., and a weight coefficient of 60% between the nodes 1-2 and the user's connection line.

If the current node is a user, then nodes 1-1, 1-2, 1-3, and 1 recommendation can be selected, then the probability of the user selecting node 1 is 60% and can be represented by P (node 1-1|user) =60%.

If the current node is 1-1, then the user can select node 2-1, node 2-2, and recommendation 2, and the probability of selecting node 2-1 by the user is 50%, which can be represented by P (node 2-1|node 1-1) =50%.

If the current node is 2-1, then the user can select node 3-1, node 3-2, node 3-3, and recommendation 3, then the probability of selecting node 3-1 by the user is 50%, which can be represented by P (node 3-1|node 2-1) =50%.

Wherein the sum of the probabilities of all nodes in each layer is 100%, if the current node is node 2-1, the probability that the user selects node 3-1, node 3-2 and node 3-3 next is respectively 50%, 30% and 20% in sequence, and the sum of the three probabilities is 100%, namely, P (node 3-1|node 2-1) +p (node 3-2|node 2-1) +p (node 3-3|node 2-1) =100%.

Whereas for the current node being node 2-1, the probability of the user selecting recommendation 3 next is 45%, this value can be obtained by the product of P (node 3-1|node 2-1) =50% and P (recommendation 4|node 3-1) =90%, indicating that the probability of the user selecting node 3-1 next and recommendation 4 next is 45% with the current node being 2-1.

Similarly, for a current node of node 1-1, the probability that the user will select recommendation 2 is 22.5%, which can be obtained by multiplying P (node 2-1|node 1-1) =50% by P (recommendation 3|node 2-1) =45%, indicating that the probability that the user will select node 2-1 and select recommendation 3 is 22.5% with the current node of 1-1.

(2) Progressive interactive correction compensation: the progressive interaction module can also correct and compensate the prediction result of the intelligent recommendation engine module in real time according to the interaction feedback information obtained by the user interaction interface and the interaction path map of the user, so that the path is shorter and the result is more accurate.

In the gradual interaction process of the user and the mobile phone, the gradual interaction module can dynamically understand the user intention and update the nodes and the node weights of the interaction map by combining the real-time operation behaviors of the user, and the correction compensation information is used as an implicit characteristic to guide the intelligent recommendation engine module to give a corrected recommendation result in real time. For example, as shown in FIG. 9 above, the progressive interaction module may modify the weight coefficient between node 1-1 and node 2-1 to 70% and the weight coefficient between node 1-1 and node 2-2 to 30%.

In the specific correction process, feature processing is carried out on the current node information and the associated node information, and the feature processing is used for implicitly guiding the intelligent recommendation engine module to learn and infer, so that the search range can be effectively reduced, and the accuracy of the recommendation result is improved.

Specifically, the method can be implemented according to the flow chart shown in fig. 10:

s1010, acquiring interface interaction behavior information.

In this embodiment of the present application, it is assumed that the intelligent recommendation engine module recommends a certain content to the user, if the user does not like the recommended content, the user may reselect the favorite or interested content on the current interface, and at this time, the progressive interaction module may obtain the interface interaction behavior information of the user according to the operation of the user, for example, the progressive interaction module may obtain the interface interaction behavior information of the user in a system log or a three-party service.

As shown in fig. 9 described above, it is assumed that the intelligent recommendation engine module recommends a certain content to the user, which corresponds to the node 2-2 in fig. 9, but the user does not like, and when the user reselects the content that he likes or is interested in at the current interface, the reselected content may correspond to the node 2-1 in fig. 9.

S1020, extracting interaction path map node information of the user.

The progressive interaction module can rapidly detect the position of the current node in the interaction path map according to the acquired interface interaction behavior information of the user, and extract the information of the node with a direct association relation with the current node.

As shown in FIG. 9 above, assuming that the progressive interaction module locates the current node at node 2-1 according to the acquired interface interaction behavior information of the user, the nodes having a direct association relationship with the current node 2-1 include node 3-1, node 3-2, node 3-3, recommendation 3, and node 1-1.

S1030, acquiring a node reachable path.

After the information of the node with the direct association relation with the current node is extracted, traversing the interaction path map downwards to obtain the total number of node reachable paths, and taking the total number of node reachable paths as the guidance information of the neural network output layer weight in the intelligent recommendation engine.

Still taking fig. 9 as an example, where the current node is node 2-1, the node reachable path includes: node 2-1- > node 3-1- > recommendation 4, node 2-1- > node 3-1- > others, node 2-1- > node 3-2, node 2-1- > node 3-3, node 2-1- > recommendation 3.

S1040, node information one-hot (one-hot) vector characterization.

Based on the results obtained in the above steps S1020 and S1030, one-hot vector characterization may be performed on the current node information and the node associated with the current node information.

For ease of understanding, a brief description of one-hot vector characterization is provided below.

one-hot vector characterization is the simplest and more common text feature representation method. In terms of word feature representation, it is essential that the subscript of a word in a word set be directly taken as a representation of that word.

Illustratively, for word collections [ I am, you, like, apple, banana ]

The one-hot vector for these several words can be expressed as:

i: [10000]

You: [01000]

Like: [00100]

Apple: [00010]

Bananas: [00001]

Thus, for the phrase "I like apple, you like banana" we can express: [100000010000001010000010000001].

In the embodiment of the application, the one-hot vector can be used for representing the current node information and the node associated with the current node information.

For example, in the embodiment of the present application, the current node is node 2-1, and the nodes associated with the current node 2-1 include node 3-1, node 3-2, node 3-3, and recommendation 3. The above node may be represented by a one-hot vector:

node 2-1: [1000 0]

Node 3-1: [01000]

Node 3-2: [00100]

Node 3-3: [00010]

Recommendation 3: [00001]

The path for path node 2-1 to node 3-1 may be represented as [1000 00100 0], the path for node 2-1 to node 3-2 may be represented as [1000 00010 0], the path for node 2-1 to node 3-3 may be represented as [1000 00001 0], and the path for node 2-1 to recommended 3 may be represented as [1000 0000 01 ].

S1050, feature vector fusion.

After the node information is subjected to one-hot vector characterization, the one-hot vectors can be spliced and fused. For example, still taking the above example as an example, all reachable paths of the current node 2-1 after the one-hot vector characterization may be spliced and fused, and the fused result may be:

the fused results can serve as input to the intelligent recommendation engine module.

In the embodiment of the application, the real-time operation of the user is combined, the progressive interaction correction compensation information can be realized and used as important input information of the intelligent recommendation engine module, and the learning and reasoning process of the intelligent recommendation engine module is guided. It can be appreciated that the essence of the correction compensation is to provide more implicit characteristic information abstracted from the user interaction behavior for the intelligent recommendation engine module, so that the whole retrieved object is changed from the whole service information base to the service information base of the service node having the association relation with the current interaction behavior.

3. Intelligent recommendation engine module

The intelligent recommendation engine module is mainly used for constructing a search recommendation engine taking user interaction behavior as a core, and the user intention is rapidly and accurately identified by feature mining of user portraits and basic information and fusion of compensation information in the interaction module.

Specifically, the method can be implemented according to the flow chart shown in fig. 11:

s1110, extracting the feature vector.

In this embodiment of the present application, feature vector extraction may be performed on the basic information and the user portrait information acquired by the service library construction module, for example, a word vector characterization (word unbedding) method may be used to perform feature vector extraction, and in this embodiment of the present application, a word2vec lightweight neural network may be used to obtain word vector characterization.

The core of word casting is a mapping relationship, which mainly comprises two modes: one is one-hot vector characterization and the other is word2vec. word2vec can be understood as a dimensionality reduction process for one-hot vectors, which converts an n-dimensional one-hot vector into an m-dimensional spatial real vector through a mapping relationship.

In the embodiment of the application, it is assumed that the user portrait constructed by the service library construction module includes K dimensions, and each dimension includes K _i The user representation may include K x K _i Information; in addition, if the basic information acquired by the service library construction module includes N pieces of information, if the one-hot vector is used to characterize the information, the information may be expressed as kxk _i +N-dimensional one-hot vector, K can be determined by word2vec _i The +N-dimensional one-hot vector is converted into an M-dimensional vector, and K X K _i +N<M。

S1120, multi-dimensional feature fusion.

The multidimensional feature vectors are spliced and fused, and the multidimensional feature vectors comprise the corrected compensation feature vectors obtained in the step S1050 and the word representation vectors derived from the user portrait and the basic information and obtained in the step S1110. Before the multi-dimensional feature vectors are fused, the multi-dimensional vectors can be converted into one-dimensional vectors, and then a plurality of one-dimensional vectors are spliced and fused to obtain one-dimensional long vectors, which are used as the input of the weight prediction model based on the deep learning in step 1130.

Illustratively, in the step S1050, a 4-dimensional vector is obtained, where the 4-dimensional vector may be converted into a one-dimensional vector, for example, a 2 nd row vector of the 4-dimensional vector may be placed at the end of a 1 st row vector, a 3 rd row vector may be placed at the end of the 2 nd row vector, and a 4 th row vector may be placed at the end of the 3 rd row vector, and the result after conversion is [ 10 0 0 0 0 10 0 0,1 0 0 0 0 0 0 10 0,1 0 0 0 0 0 0 0 10,1 0 0 0 0 0 0 0 0 1]. And then, splicing and fusing the one-dimensional vector obtained after conversion and the one-dimensional vector obtained in the step S1110 again to obtain a one-dimensional long vector.

S1130, reasoning a weight prediction model based on deep learning.

The deep learning network is constructed and mainly consists of a full connection layer, an activation layer and a softmax layer, and the effective length of the output layer is the total amount of the node path which the current node extends downwards. And (3) inputting the one-dimensional long vector obtained in the step (S1120) into a weight prediction model based on deep learning, wherein the model outputs weight values corresponding to paths of all branches, namely the probability value of each branch selected by a user under the current interaction node.

S1140, the weight is ordered, and the node information is output.

And sequencing the branches according to the weight values, judging whether the weight value corresponding to each branch is greater than or equal to a threshold value, if so, selecting the branch with the largest weight value in the conditions, and if not, selecting the adjacent node with the largest weight value for returning.

Still taking the above fig. 9 as an example, if the current node is node 2-1, and the nodes adjacent to the current node include node 3-1, node 3-2 and recommendation 3, and if the threshold is 40%, the weight of the adjacent node 3-1 is greater than the threshold, a path from node 2-1 to node 3-1 to recommendation 4 may be selected, and the end node of the path is returned to the user, that is, the node of recommendation 4 is returned; assuming that the threshold is 70%, the weights of all nodes in the nodes adjacent to the node 2-1 are smaller than the threshold, then the node with the largest weight in the adjacent nodes can be selected, and the node with the largest weight in the adjacent nodes is the node 3-1, so that the node 3-1 can be returned to the user.

Based on this, the functions of the service library construction module, the progressive interaction module and the intelligent recommendation engine module are described in the embodiments of the present application, and the complete flow of the embodiments of the present application is described below with reference to fig. 12.

When a user operates the mobile phone, firstly, extracting feature vectors of the obtained basic information and the user portrait to obtain word feature vectors, for example, extracting the feature vectors of the basic information and the user portrait by a word embedding technology to obtain the word feature vectors; then, the progressive interaction module can acquire a plurality of interaction behavior paths based on the current node according to the current interaction behavior node of the user, for example, the progressive interaction module can judge the position of the current interaction behavior node in the interaction path graph of the user by combining the constructed interaction path graph of the user, so as to acquire a plurality of interaction behavior paths based on the current node, and meanwhile, the information of the paths can be converted into one-hot vectors, and the one-hot vectors and the obtained word feature vectors are fused and combined into a multi-dimensional fusion feature to guide the intelligent recommendation engine module to output a predicted weight result; the intelligent recommendation engine module can splice based on the multi-dimensional fusion characteristics to obtain a one-dimensional long vector, takes the one-dimensional long vector as the input of the weight prediction model, outputs weight values corresponding to all paths, selects paths meeting the conditions according to the weight values, and presents key nodes of the paths on the interactive interface for a user to select.

The following describes aspects of embodiments of the present application in connection with specific examples.

Still taking the example of the user going out for dinner in fig. 3, after the mobile phone recognizes that the user long presses the text content of "eight and a half take dinner together in Li Gucun ten thousand after going out for work", the intention of the user going out for dinner can be recognized according to the text content, and meanwhile, the following several requirements may be recognized for the user according to the interaction path map of the user:

(1) Travel tool selection: the user needs to select what kind of transportation means to take to go from company to destination, and there are self-driving (navigation), public transportation (public transportation, subway, etc.), driving (drop-by-drop)Etc.), recommending a path of getting a droplet to the user according to the habit system of the user;

(2) Party type selection: the user needs to select what kind of party, predicts the mode that the user will select the party with high probability by combining the habit of the user, recommends corresponding service information such as food and coupons to the user by combining the taste preference of the user and other habits, and pushes the functions such as food reservation, ordering in advance and the like in time after the user receives the recommended nodes;

(3) Calendar reminding function: the schedule reminder can be established in combination with the time scheduled by the user, and a reminder message is sent to the user in advance for one hour or half an hour, so that the user is prevented from forgetting to meet with friends.

After the above detailed analysis, it can be seen that if the user needs more interaction steps to achieve the intention, as shown in the interaction scheme 1 in fig. 13, the embodiment of the present application can achieve the intention through fewer interaction steps, as shown in the interaction scheme 2 in fig. 13.

The specific implementation can be shown by referring to the figure 3, when the system recognizes that the user presses the text content of 'eight and a half of the user eat meal together in Li Gucun thousands of days' for a long time, the system can automatically recommend the general ordering service, the dripping taxi calling service and the newly-built schedule alarm clock reminding service, and the user only needs to select the function wanted by the user, so that the operation path of the user for executing the multitasking can be greatly simplified, and the interaction efficiency is improved.

In addition, when a user orders food, the user can select a desired food from a plurality of shops according to own taste preference, or the system can automatically recommend the food to the user according to the preference and historical orders of the user, and when the recommended food to the user is not what the user wants to eat currently, the system can recommend the corresponding food to the user again according to the operation of the user.

Interaction scheme 1: the user uses the conventional operation steps of ordering food by the mobile phone terminal, the interaction steps are complicated, each step needs manual selection of the user, and intelligent recommendation behaviors do not exist in the whole interaction scheme.

Interaction scheme 2: the intelligent recommendation system based on the progressive interaction and the dynamic correction compensation accurately extracts interaction key nodes according to the progressive interaction behavior of the user, can effectively shorten the interaction path and omits intermediate states. If the current node is food, the branch weight product of the system prediction food- > hamburger western-style food is larger than a threshold value, and the node of the hamburger western-style food is returned to the interactive interface for the user to select, so that the path is shortened compared with the interactive scheme 1.

Correction scheme 3: if a user currently wants to take another dish, the embodiment of the application also provides a correction compensation scheme, in the current interaction node, the user can select a Chinese meal, the original path is invalid, the next node needs to predict weight again according to the Chinese meal of the current interaction node, and the next path node is predicted to be a Yonghe King, so that the intelligent recommendation system based on progressive interaction and correction compensation can make effective remedial actions for the user selection change.

The specific implementation can be shown by referring to the above figure 3, after the system recommends "hamburger western style food" to the user, when the system recognizes that the user reselects "Chinese style food", the user can recommends the Chinese style food to the user, and the user can select based on the result of the recommendable system.

As shown in fig. 15, a schematic diagram of a method for recommending service cards according to an embodiment of the present application is provided, the method may be applied to an electronic device, and the method may include steps S1510 to S1530.

S1510, responding to a first operation of a user on the electronic equipment on target text, and identifying the intention corresponding to the target text.

The target text in the embodiment of the application may be "eight and a half together eat meal in Li Gucun ten thousand after working in the present day" shown in fig. 3, and the first operation may be an operation of selecting the target text by the user and pressing the target text for a long time.

The intent in the embodiment of the application can be extracted from the target text, such as the intent that the target text is taken together at Li Gucun kiloda for the eighth point half after working today, and the intent can be extracted from the target text is an outgoing dinner.

In some embodiments, under a first operation of a user on a target text, the electronic device identifying an intent corresponding to the target file may also be understood as identifying the intent of the user.

S1520, determining a plurality of service cards according to the intention, wherein the service cards provide services corresponding to the intention.

The service card in the embodiment of the present application is a card related to an intention, for example, the intention extracted in fig. 3 is an outgoing party, and for the intention of the outgoing party, the service related to the intention may include an order, an outgoing, a schedule reminder, and the like, so that the system may determine the service card related to the order, the service card related to the outgoing, the service card related to the schedule reminder, and the like.

It should be appreciated that the service cards determined by the system may include, but are not limited to, those illustrated above, for example, a service card associated with an epidemic prevention code, which may be opened in time when the user reaches the destination, so as to facilitate the user's passage.

It should also be appreciated that a service card may also be referred to as a card or application component (application widget, app widget) or service component (service widget) or application widget or application gadget, which may be a widget or widget.

S1530, displaying the plurality of service cards.

Optionally, in some embodiments, the determining a plurality of service cards according to the intent includes:

and combining the interaction path patterns of the user, and determining the plurality of service cards according to the intention, wherein the interaction path patterns of the user are used for describing the operation habit or personal preference of the user when the electronic equipment is used.

Optionally, in some embodiments, the interaction path map includes a plurality of nodes and weight coefficients between the nodes, wherein the nodes represent single-step interaction behavior points of the user, and the weight coefficients represent strengths of cascade relationships between the nodes.

The interaction path map of the user in the embodiment of the present application may be shown in fig. 9, where each circle may be a node, and represents a single step interaction behavior point of the user; the numerical value between the nodes is a weight coefficient, and represents the strength of the cascade relation between the nodes.

For example, if the value between node 2-1 and node 3-1 is 50% and the value between node 2-1 and node 3-2 is 30%, then the cascading relationship between node 2-1 and node 3-1 is stronger than the cascading relationship between node 2-1 and node 3-2. In other words, if the current node position is at node 2-1, the probability of the user selecting node 3-1 is greater than the probability of selecting node 3-2.

In addition, a node may be understood as an icon presented by an interface for user operation or displayed after user selection, for example, the hamburger meal shown in (e) of fig. 3 is a node when the user clicks on a drop-down menu on the right side of the hamburger mealAfter the icon of (f) in fig. 3, a GUI is displayed. It can be seen that various delicacies are displayed in the list of drop-down menus, such as hamburger western style food, chinese meal, japanese and korean cuisine, dessert drinks, fried marinated snacks, and others. Any of these categories of food products may be referred to as a node.

When the user selects the middle meal, the GUI shown in (g) of fig. 3 is displayed, and at this time, the recommended Chinese 1 and Chinese 2 are also displayed below the Chinese, and at this time, the specific Chinese is displayed in relation to the weight coefficient, the Chinese 1 and Chinese 2 are recommended by the system, which means that the weight coefficient of Chinese 1 and Chinese 2 is greater than that of the other Chinese, and the weight coefficient of Chinese 1 is greater than that of Chinese 2.

Optionally, in some embodiments, the plurality of service cards includes a first service card including a first recommendation corresponding to one of the intents and a second service card including a second recommendation corresponding to the other of the intents, the method further comprising:

Responding to a second operation of clicking the sub-content under the first recommendation result by the user, and displaying a service function corresponding to the sub-content under the first recommendation result;

and responding to a third operation of clicking the sub-content under the second recommendation result by the user, and displaying a service function corresponding to the sub-content under the second recommendation result.

In this embodiment, the first service card may be a popular comment card, where the card includes a recommendation result of the ordering service. The first recommendation result in the embodiment of the present application may be a hamburger western style meal, which is recommended to the user by the intelligent recommendation engine module according to the interaction path map of the user, and the sub-content of the first recommendation result may include western style meal 1, western style meal 2, and the like. The user may click on western-style meals that the user likes or wants, and make orders, reserve seats, etc.

Similarly, the second service card in the embodiment of the present application may be a card of drip outlet, where the card includes a recommendation result of reserving travel tool services. The second recommendation result in the embodiment of the present application may be a taxi, which is recommended to the user by the intelligent recommendation engine module according to the interaction path map of the user, and the sub-content of the second recommendation result may include a taxi reservation and the like, and the user may reserve a taxi call based on the recommended travel tool.

Optionally, in some embodiments, the plurality of service cards includes a first service card including a first recommendation corresponding to one of the intents and a first control for controlling display of a recommendation including the first recommendation, the method further including:

responding to a fourth operation of clicking the first control by the user, and displaying a recommendation result corresponding to one of the intentions;

and responding to a fifth operation of selecting a third recommendation result from the recommendation results by the user, and displaying sub-content of the third recommendation result.

In this embodiment of the present application, the first control may control display of the recommendation result, and taking fig. 3 as an example, the first control may be an icon shown in fig. 3 (e) When the user clicks the first control, the electronic device may display a recommendation corresponding to one of the intents, which may include: hamburger western-style food, chinese food, japanese and Korean food, etc.; the third recommendation result in the embodiment of the present application may be a Chinese meal, and after the user clicks the recommendation result of the Chinese meal, the electronic device may display sub-content of the Chinese meal, such as Chinese meal 1, chinese meal 2, and so on. />

Optionally, in some embodiments, the displaying sub-content of the third recommendation result in response to a fifth operation of the user selecting the third recommendation result from the recommendation results includes:

responding to a fifth operation of selecting a third recommendation result from the recommendation results by the user, and searching sub-content of the third recommendation result from a target service information base according to the position of the third recommendation result in an interaction path map of the user, wherein the target service information base is a service information base corresponding to the third recommendation result;

And displaying the sub-content of the third recommendation result according to the interaction path map of the user.

In this embodiment of the present application, after the user selects the third recommendation result from the recommendation results, at this time, the intelligent recommendation engine module may search in the target service information base according to the position of the current node in the interaction path map of the user. For example, when the user selects a Chinese meal from a plurality of recommended results, the intelligent recommendation engine module only needs to search for the Chinese meal related food, and the user does not need to search for the Chinese meal in a large range, so that the search range can be reduced, and the search efficiency and the search accuracy can be improved.

Optionally, in some embodiments, the method further comprises: and updating the interaction path map of the user according to the fifth operation.

Optionally, in some embodiments, the plurality of service cards includes a first service card including a second control therein for canceling the first service card, the method further comprising:

and responding to a sixth operation of clicking the second control by the user, and canceling the display of the first service card on the electronic equipment.

In this embodiment of the present application, the second control may control to cancel the display of the first service card, for example, in fig. 3, where the second control may be an icon "x" in the GUI shown in (e) in fig. 3, and if the user does not need the service card, the user may click on the second control to cancel the display of the service card.

Optionally, in some embodiments, the method further comprises:

constructing a universal interaction path map;

and modifying the universal interaction path map according to the information of the user, and assigning weights among nodes of the modified universal interaction path map to obtain the interaction path map of the user.

The information of the user in the embodiment of the application may include historical behavior information of the user, and based on the information, the system may modify the universal interaction path map into the interaction path map of the user so as to serve the user.

It will be appreciated that the electronic device, in order to achieve the above-described functions, includes corresponding hardware and/or software modules that perform the respective functions. The steps of an algorithm for each example described in connection with the embodiments disclosed herein may be embodied in hardware or a combination of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Those skilled in the art may implement the described functionality using different approaches for each particular application in conjunction with the embodiments, but such implementation is not to be considered as outside the scope of this application.

The present embodiment may divide the functional modules of the electronic device according to the above method example, for example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated modules described above may be implemented in hardware. It should be noted that, in this embodiment, the division of the modules is schematic, only one logic function is divided, and another division manner may be implemented in actual implementation.

In the case of dividing the respective functional modules with the respective functions, fig. 16 shows a schematic diagram of one possible composition of the electronic device 1600 involved in the above-described embodiment, and as shown in fig. 16, the electronic device 1600 may include: an identification module 1610, a determination module 1620, and a display module 1630.

Wherein the identification module 1610 may be used to support the electronic device 1600 to perform step S1510, etc., described above, and/or other processes for the techniques described herein.

The determination module 1620 may be configured to support the electronic device 1600 to perform step S1520, etc., described above, and/or other processes for the techniques described herein.

The display module 1630 may be used to support the electronic device 1600 to perform step S1530, etc., described above, and/or for other processes of the techniques described herein.

It should be noted that, all relevant contents of each step related to the above method embodiment may be cited to the functional description of the corresponding functional module, which is not described herein.

The electronic device provided in this embodiment is configured to perform the method of the present application, so that the same effects as those of the implementation method can be achieved.

In case an integrated unit is employed, the electronic device may comprise a processing module, a storage module and a communication module. The processing module may be configured to control and manage actions of the electronic device, for example, may be configured to support the electronic device to perform steps performed by the foregoing units. The memory module may be used to support the electronic device to execute stored program code, data, etc. And the communication module can be used for supporting the communication between the electronic device and other devices.

Wherein the processing module may be a processor or a controller. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. A processor may also be a combination that performs computing functions, e.g., including one or more microprocessors, digital signal processing (digital signal processing, DSP) and microprocessor combinations, and the like. The memory module may be a memory. The communication module can be a radio frequency circuit, a Bluetooth chip, a Wi-Fi chip and other equipment which interact with other electronic equipment.

In one embodiment, when the processing module is a processor and the storage module is a memory, the electronic device according to this embodiment may be a device having the structure shown in fig. 1.

Fig. 17 shows another possible composition diagram of the electronic device 1400 according to the above embodiment, as shown in fig. 17, the electronic device 1400 may include a communication unit 1410, an input unit 1420, a processing unit 1430, an output unit (or may also be referred to as a display unit) 1440, a peripheral interface 1450, a storage unit 1460, a power supply 1470, a video decoder 1480, and an audio decoder 1490.

The communication unit 1410 is configured to establish a communication channel through which the electronic device 1400 connects to and downloads media data from a remote server. The communication unit 1410 may include a communication module such as a WLAN module, a bluetooth module, an NFC module, a baseband module, and a Radio Frequency (RF) circuit corresponding to the communication module, for performing wireless local area network communication, bluetooth communication, NFC communication, infrared communication, and/or cellular communication system communication, for example, wideband code division multiple access (wideband code division multiple access, W-CDMA) and/or high-speed downlink packet access (high speed downlink packet access, HSDPA). The communication module 1410 is used to control the communication of the components in the electronic device and may support direct memory access.

The input unit 1420 may be used to enable user interaction with and/or information input into an electronic device. In the specific embodiment of the application, the input unit may be a touch panel, or may be other man-machine interaction interfaces, such as an entity input key, a microphone, or other external information capturing devices, such as a camera.

The processing unit 1430 is a control center of the electronic device, and may connect various parts of the entire electronic device using various interfaces and lines, by running or executing software programs and/or modules stored in the storage unit, and invoking data stored in the storage unit to perform various functions of the electronic device and/or process data. Steps S1510, S1520, etc. as described above may be implemented by the processing unit 1430.

The output unit 1440 includes, but is not limited to, an image output unit and a sound output unit. The image output unit is used for outputting characters, pictures and/or videos. In the embodiment of the present application, the touch panel adopted by the input unit 1420 may also be used as the display panel of the output unit 1440. For example, when the touch panel detects a gesture operation of touch or approach thereon, the gesture operation is transmitted to the processing unit to determine the type of the touch event, and then the processing unit provides a corresponding visual output on the display panel according to the type of the touch event. Although in fig. 17, the input unit 1420 and the output unit 1440 implement the input and output functions of the electronic device as two separate components, in some embodiments, the input and output functions of the electronic device may be implemented by integrating a touch panel with a display panel. For example, the image output unit may display various graphical user interfaces as virtual control components, including but not limited to windows, scroll shafts, icons, and scrapbooks, for a user to operate by touch.

The storage unit 1460 may be used to store software programs and modules, and the processing unit executes the software programs and modules stored in the storage unit, thereby performing various functional applications of the electronic device and realizing data processing.

The present embodiment also provides a computer storage medium having stored therein computer instructions which, when executed on an electronic device, cause the electronic device to perform the above-described related method steps to implement the method in the above-described embodiments.

The present embodiment also provides a computer program product which, when run on a computer, causes the computer to perform the above-mentioned related steps to implement the method in the above-mentioned embodiments.

In addition, embodiments of the present application also provide an apparatus, which may be specifically a chip, a component, or a module, and may include a processor and a memory connected to each other; the memory is configured to store computer-executable instructions, and when the device is operated, the processor may execute the computer-executable instructions stored in the memory, so that the chip performs the methods in the above method embodiments.

The electronic device, the computer storage medium, the computer program product, or the chip provided in this embodiment are used to execute the corresponding methods provided above, so that the beneficial effects thereof can be referred to the beneficial effects in the corresponding methods provided above, and will not be described herein.

It will be appreciated by those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another apparatus, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and the parts shown as units may be one physical unit or a plurality of physical units, may be located in one place, or may be distributed in a plurality of different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be essentially or a part contributing to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, including several instructions to cause a device (may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of service card recommendation, the method being applied to an electronic device, the method comprising:

identifying an intention corresponding to a target text in response to a first operation of a user on the electronic equipment;

determining a plurality of service cards according to the intention, wherein the service cards provide services corresponding to the intention;

displaying the plurality of service cards.

2. The method of claim 1, wherein the determining a plurality of service cards from the intent comprises:

3. The method of claim 2, wherein the interaction path graph comprises a plurality of nodes and weight coefficients between the nodes, wherein the nodes represent single-step interaction behavior points of the user, and the weight coefficients represent strengths of cascade relationships between the nodes.

4. The method of any of claims 1-3, wherein the plurality of service cards includes a first service card including a first recommendation corresponding to one of the intents and a second service card including a second recommendation corresponding to the other of the intents, the method further comprising:

5. A method according to any one of claims 1 to 3, wherein the plurality of service cards includes a first service card including a first recommendation corresponding to one of the intents and a first control for controlling display of a recommendation including the first recommendation, the method further comprising:

6. The method of claim 5, wherein displaying sub-content of a third recommendation in response to a fifth operation of the user selecting the third recommendation from the recommendations comprises:

7. The method according to claim 5 or 6, characterized in that the method further comprises:

and updating the interaction path map of the user according to the fifth operation.

8. The method of any of claims 1-7, wherein the plurality of service cards includes a first service card including a second control therein for canceling the first service card, the method further comprising:

9. The method according to any one of claims 1 to 8, further comprising:

constructing a universal interaction path map;

10. An electronic device, comprising:

one or more processors;

one or more memories;

the one or more memories store one or more computer programs comprising instructions that, when executed by the one or more processors, cause the electronic device to perform the method of any of claims 1-9.

11. A chip system comprising at least one processor, wherein program instructions, when executed in the at least one processor, cause the functions of the method of any one of claims 1 to 9 to be carried out on the electronic device.

12. A computer storage medium comprising computer instructions which, when run on an electronic device, cause the electronic device to perform the method of any one of claims 1 to 9.

13. A computer program product, characterized in that the computer program product, when run on a computer, causes the computer to perform the method of any of claims 1 to 9.