CN113468372A

CN113468372A - Intelligent mirror and video recommendation method

Info

Publication number: CN113468372A
Application number: CN202010682924.XA
Authority: CN
Inventors: 孙锦; 杨雪洁; 刘帅帅; 杨斌; 黄利; 刘晓潇; 陈维强; 高雪松; 李广琴
Original assignee: Qingdao Hisense Electronic Industry Holdings Co Ltd
Current assignee: Qingdao Hisense Electronic Industry Holdings Co Ltd
Priority date: 2020-07-15
Filing date: 2020-07-15
Publication date: 2021-10-01

Abstract

The application provides an intelligent mirror and a video recommendation method. The intelligent mirror comprises a display screen for displaying images or videos; a processor configured to: determining target key information based on target information corresponding to a target user and preset key information received within preset time, wherein the target information comprises text information obtained by triggering a preset key of a response social interface and/or text information obtained by triggering a preset key of a response object display interface; the method comprises the steps of determining a recommended video according to key information of a preset video and the target key information, and displaying the recommended video through the display screen, wherein the key information of the preset video is obtained based on text information corresponding to the preset video and the preset key information, so that a proper video is accurately determined and displayed, and the makeup experience of a user is improved.

Description

Intelligent mirror and video recommendation method

Technical Field

The application relates to the technical field of intelligent household equipment, in particular to an intelligent mirror and a video recommendation method.

Background

Along with the improvement of people's standard of living, the intelligence mirror also enters into people's daily life gradually, and the video of making up can be broadcast through the display screen to the intelligence mirror, makes up the user, still can watch the video through the display screen.

In the related art, the intelligent mirror can play the makeup video corresponding to the instruction through the display screen based on the selection instruction for the makeup video.

In summary, there is a need for an intelligent mirror and a video recommendation method to accurately determine and display a suitable video.

Disclosure of Invention

The exemplary embodiments of the present application provide an intelligent mirror and a video recommendation method, so as to accurately determine and display a suitable video.

In a first aspect, an exemplary embodiment of the present application provides a smart mirror, including:

the display screen is used for displaying images or videos and has a mirror function;

a processor configured to:

determining target key information based on target information corresponding to a target user and preset key information received within preset time, wherein the target information comprises text information obtained by triggering a preset key of a response social interface and/or text information obtained by triggering a preset key of a response object display interface;

determining a recommended video according to key information of a preset video and the target key information, and displaying the recommended video through the display screen, wherein the key information of the preset video is obtained based on text information corresponding to the preset video and the preset key information.

According to the scheme, the user can accurately reflect the user preference through interaction between the user and the social interface and the object display interface, and the information which is interesting to the target user within the preset time can be conveniently and accurately determined through the text information which is obtained by triggering the preset key of the response social interface by the target user within the preset time and/or the text information which is obtained by triggering the preset key of the response object display interface by the target user and the preset key information; based on the text information and the preset key information corresponding to the preset video, the related information corresponding to the preset video can be obtained through a small amount of calculation, and the processing pressure of the processor is reduced; through the related information of the preset video and the information which the target user is interested in within the preset time, the video which the target user is interested in can be recommended to the target user.

In some embodiments of the present application, the number of target users is plural, and the processor is configured to:

one or more preset key information contained in the target information of each target user is used as the key information of the corresponding target user;

taking key information of which the occurrence frequency is greater than a preset frequency threshold value in the target information of all target users as the target key information; or determining the selection proportion of the key information of each target user according to the level of each target user, and selecting the target key information from the key information of each target user based on the selection proportion.

According to the scheme, one or more preset key information contained in the target information of each target user is used as the key information of the corresponding target user aiming at a scene with a plurality of target users, and the key information with the frequency larger than a preset frequency threshold value in the target information of all the target users is used as the target key information, so that the preference of all the target users can be considered in a balanced manner; by selecting the target key information from the key information of each target user according to the selection proportion corresponding to the grade of each target user, the preference of the target user with high grade can be considered in a key way.

In some embodiments of the present application, the smart mirror further comprises: the image collector is used for collecting the face information of the user to obtain a reference image and transmitting the reference image to the processor;

the processor is configured to: and determining preset face information of which the similarity with the face information of the user contained in the reference image reaches a preset similarity threshold, and taking a preset user corresponding to the preset face information as the target user.

According to the scheme, the target user in front of the intelligent mirror can be accurately determined through the reference image collected by the image collector.

In certain embodiments of the present application, the processor is configured to:

if the text information corresponding to the preset video comprises the subtitle text corresponding to the preset video, selecting a target image from each preset video based on a preset time interval;

selecting images containing characteristic values of the same subtitle text from target images of all preset videos for filtering;

and taking the subtitle text contained in the target image after filtering each preset video as the subtitle text corresponding to each preset video.

According to the scheme, the target image is selected from each preset video based on the preset time interval, so that the calculation amount for subsequently acquiring the caption text can be reduced while the content is ensured to be complete; selecting images containing the feature values of the same subtitle text from the target images of the preset videos for filtering, namely only retaining one frame of target images containing the feature values of the same subtitle text, and further reducing the calculation amount of the subtitle text obtained subsequently; the caption text contained in the filtered target image can comprehensively and accurately reflect the corresponding preset video related information.

In some embodiments of the present application, the text information corresponding to the preset video includes at least one of a subtitle text, a title, an author, a comment, and a bullet screen corresponding to the preset video.

The processor is configured to:

and taking one or more pieces of preset key information contained in the text information corresponding to the preset video as the key information corresponding to the preset video.

According to the scheme, one or more items of subtitle texts, titles, authors, comments and barrages corresponding to the preset videos are selected as text information of the subtitle texts, the titles, the authors, the comments and the barrages according to actual application scenes, and requirements of different scenes are met; one or more pieces of preset key information contained in the text information corresponding to the preset video are used as the key information corresponding to the preset video, so that the key information of the preset video can be accurately obtained through a small calculation amount, the processing pressure of the processor is reduced, and the accuracy of obtaining the key information of the preset video is ensured.

determining the contact ratio of the key information of each preset video and the target key information, and taking the preset video with the contact ratio reaching a preset contact ratio threshold value as the recommended video;

or, the preset videos are sorted according to the contact ratio from high to low, the ranking of the preset videos is determined, and the preset video before the preset ranking is used as the recommended video.

According to the scheme, the contact ratio of the key information of each preset video and the target key information is determined, all the preset videos with the contact ratio reaching the preset contact ratio threshold value are selected as the recommended videos, or a certain number of preset videos with high contact ratios are selected as the recommended videos, so that the recommended videos are determined in a proper mode according to the actual application scene.

In some embodiments of the present application, the preset key information includes at least one type of makeup information.

According to the scheme, the preset key information comprises at least one type of makeup information, so that the makeup information interested by the target user can be determined, and the information corresponding to the preset video and related to the makeup can be obtained, so that the method is more suitable for the makeup scene.

In a second aspect, an exemplary embodiment of the present application provides a video recommendation method, including:

determining a recommended video according to key information of a preset video and the target key information, and displaying the recommended video, wherein the key information of the preset video is obtained based on text information corresponding to the preset video and the preset key information.

In some embodiments of the present application, the number of the target users is multiple, and determining the target key information based on the target information corresponding to the target user received within the preset time and the preset key information includes:

In some embodiments of the present application, before determining the target key information, the method further includes:

determining preset face information of which the similarity with the face information of the user contained in a reference image reaches a preset similarity threshold, wherein the reference image is obtained by collecting the face information of the user through an image collector;

and taking a preset user corresponding to the preset face information as the target user.

In some embodiments of the present application, if the text information corresponding to the preset video includes a subtitle text corresponding to the preset video, the subtitle text corresponding to the preset video is obtained by:

selecting a target image from each preset video based on a preset time interval;

In some embodiments of the present application, the text information corresponding to the preset video includes at least one of a subtitle text, a title, an author, a comment, and a barrage corresponding to the preset video, and the key information of the preset video is obtained by:

In some embodiments of the present application, the determining a recommended video according to the key information of the preset video and the target key information includes:

In a third aspect, the present application further provides a video recommendation apparatus, including:

the determining module is used for determining target key information based on target information and preset key information corresponding to a target user received within preset time, wherein the target information comprises text information obtained by triggering a preset key of a response social interface and/or text information obtained by triggering a preset key of a response object display interface;

and the video recommending module is used for determining a recommended video according to the key information of a preset video and the target key information and displaying the recommended video, wherein the key information of the preset video is obtained by the determining module based on the text information corresponding to the preset video and the preset key information.

In a fourth aspect, the present application also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the second aspect.

In addition, for technical effects brought by any one implementation manner in the second to fourth aspects, reference may be made to technical effects brought by different implementation manners in the first aspect, and details are not described here.

Drawings

In order to more clearly illustrate the technical solutions of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1A is a schematic external view of an intelligent mirror provided in some embodiments of the present application;

fig. 1B is a block diagram of a hardware configuration of an intelligent mirror according to some embodiments of the present application;

fig. 2 is a block diagram of a software configuration of an intelligent mirror according to some embodiments of the present application;

FIG. 3 is a schematic diagram of a user interface of an intelligent mirror provided in some embodiments of the present application;

fig. 4 is a schematic flowchart of a video recommendation method according to some embodiments of the present application;

FIG. 5A is a schematic illustration of a social interface of a smart mirror according to some embodiments of the present application;

FIG. 5B is a schematic illustration of a social interface of another smart mirror provided in some embodiments of the present application;

FIG. 5C is a schematic illustration of a social interface of yet another smart mirror provided in some embodiments of the present application;

FIG. 6A is a schematic view of a mall interface of an intelligent mirror according to some embodiments of the present application;

FIG. 6B is a schematic view of a video display interface of a smart mirror according to some embodiments of the present application;

fig. 7 is a schematic flow chart of another video recommendation method according to some embodiments of the present application;

fig. 8 is a schematic flowchart of another video recommendation method according to some embodiments of the present application;

fig. 9 is a schematic view of a video recommendation apparatus according to some embodiments of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Fig. 1A schematically illustrates an appearance of an intelligent mirror provided in an embodiment of the present application. As shown in fig. 1A, the external structure of the smart mirror includes: a mirror body 101, a support structure 102 for supporting the mirror body, and in some embodiments, an external structure of the smart mirror further comprises a detector 120, the detector 120 being disposed at a top-middle position of the mirror body 101 in fig. 1A.

The positions and shapes of the mirror 101, the support structure 102 and the detector 120 in fig. 1A are only examples, and the positions and shapes may be set according to practical applications, for example, the mirror 101 may be rectangular or elliptical, the detector 120 may also be set on the left side or the right side of the top of the mirror 101, and so on, and thus, details are not described here.

Fig. 1B schematically shows a block diagram of a hardware configuration of an intelligent mirror provided in an embodiment of the present application. As shown in fig. 1B, the smart mirror 100 includes a processor 110, a detector 120, a communication interface 130, a display 140, a lighting lamp 150, an audio output interface 160, a memory 170, and a power supply 180.

The processor 110 includes a CPU processor 111, a RAM112, a ROM113, a graphic processor 114, a communication interface, a video processor 116, an audio processor 117, and a communication bus. Wherein, the RAM112 and the ROM113, the CPU processor 111, the graphic processor 114, the communication interface, the video processor 116, and the audio processor 117 are connected by a communication bus; the communication interfaces may include a first interface 115-1 through an nth interface 115-n. These interfaces may also be network interfaces that are connected to external devices via a network.

A ROM113 for storing instructions for various system boots. If the power of the smart mirror 100 starts to be started when the power-on signal is received, the CPU processor 111 executes a system start instruction in the ROM, and copies the operating system stored in the memory 170 into the RAM112, so as to start to execute the start operating system. After the start of the operating system is completed, the CPU processor 111 copies the various application programs in the memory 170 to the RAM112, and then starts running and starting the various application programs.

A graphics processor 114 for generating various graphics objects, such as: icons, operation menus, user input instruction display graphics, and the like. The display device comprises an arithmetic unit which carries out operation by receiving various interactive instructions input by a user and displays various objects according to display attributes. And a renderer for generating various objects based on the operator, and displaying the rendered result on the display screen 140.

A CPU processor 111 for executing operating system and application program instructions stored in memory 170. And executing various application programs, data and contents according to various interactive instructions received from the outside so as to finally display and play various audio and video contents.

In some exemplary embodiments, the CPU processor 111 may include a plurality of processors. The plurality of processors may include one main processor and a plurality of or one sub-processor. A main processor for performing some operations of the intelligent mirror 100 in a pre-power-up mode, and/or operations of displaying an image in a normal mode. A plurality of or one sub-processor for one operation in a standby mode or the like.

The video processor 116 is configured to receive an external video signal, and perform video processing such as decompression, decoding, scaling, noise reduction, frame rate conversion, resolution conversion, and image synthesis according to a standard codec protocol of the input signal, so as to obtain a signal that is directly displayed or played on the display screen 140.

Illustratively, the video processor 116 includes a demultiplexing module, a video decoding module, an image synthesizing module, a frame rate conversion module, a display formatting module, and the like.

The demultiplexing module is used for demultiplexing the input audio and video data stream, and if the input MPEG-2 is input, the demultiplexing module demultiplexes the input audio and video data stream into a video signal and an audio signal.

And the video decoding module is used for processing the video signal after demultiplexing, including decoding, scaling and the like.

And the image synthesis module is used for carrying out superposition mixing processing on the GUI signal input by the user or generated by the user and the video image after the zooming processing by the graphic generator so as to generate an image signal for display.

The frame rate conversion module is configured to convert an input video frame rate, such as a 60Hz frame rate into a 120Hz frame rate or a 240Hz frame rate, and the normal format is implemented in, for example, an interpolation frame mode.

The display format module is used for converting the received video output signal after the frame rate conversion, and changing the signal to conform to the signal of the display format, such as outputting an RGB data signal.

And an audio processor 117 for receiving an external audio signal, decompressing and decoding the audio signal according to a standard codec protocol of the input signal, and performing noise reduction, digital-to-analog conversion, amplification and other processing to obtain an audio signal that can be played in the speaker.

In other exemplary embodiments, the video processor 116 may comprise one or more chips. The audio processor 117 may also include one or more chips. And in other exemplary embodiments, the video processor 116 and the audio processor 117 may be separate chips, or may be integrated with the processor 110 in one or more chips.

The detector 120, which is a smart mirror 100, collects signals of the external environment or interaction with the outside. The detector 120 includes an image collector 121, such as a camera, a video camera, etc., which can be used to collect external environment scenes and to collect attributes of the user or facial images of the user.

In other exemplary embodiments, the detector 120, which may also include a sound collector 122, such as a microphone, may be used to receive a user's voice, a voice signal including a control instruction for the user to control the smart mirror 100, or collect an ambient sound for identifying an ambient scene type.

In some other exemplary embodiments, the detector 120 may further include a weather collector 123, such as a temperature detector, for collecting the current weather temperature, or collecting weather attribute data such as the current season.

A communication interface 130 for components that communicate with external devices or external servers according to various communication protocol types. For example: the communication interface 130 may be a Wifi module 131, a bluetooth module 132, a wired ethernet module 133, a USB134, or other network communication protocol modules or near field communication protocol modules.

The smart mirror 100 may establish control signal and data signal transmission and reception with an external control device or a content providing device through the communication interface 130.

And the display screen 140 is used for receiving the image signal input from the video processor 116 and displaying video content, images and a menu control interface. The display screen 140 includes a display screen assembly for presenting images and a driving assembly for driving the display of the images. The video content may be displayed from video content stored in the memory 170 or from video content input by the communication interface 130. Further, a display screen 140 displaying a user manipulation UI interface generated in the smart mirror 100 and used to control the smart mirror 100; the user may also input an operation command of the user on a Graphical User Interface (GUI) displayed on the display screen 140. In addition, the display screen 140 has a mirror function, which can be seen in the embodiment of fig. 3.

And the illuminating lamp 150 is used for providing light supplement for a user when the user uses the intelligent mirror 100 to learn makeup.

The audio output interface 160 is configured to receive an audio signal output by the audio processor 117, and the audio output interface 160 may include a speaker 161 (such as a speaker) carried by itself or an external sound output terminal 162 of a generating device for outputting to an external device, such as an external sound interface, an earphone interface, and the like.

The memory 170 is used to store various operation programs, data and applications for driving and controlling the smart mirror 100. The memory 170 may store various control signal commands input by a user. Including storing various software modules for driving the smart mirror 100. Such as: various software modules stored in the memory 170, including: the device comprises a basic module, a detection module, a display control module, a communication module and the like.

The basic module is a bottom layer software module which is used for signal communication among hardware in the intelligent mirror 100 and sending processing and control signals to an upper layer module; the detection module is used for collecting various information from various detectors or user input interfaces and carrying out digital-to-analog conversion and analysis management; the display control module is a module for controlling the display screen 140 to display image content, and may be used to play information such as multimedia image content and UI interface. And the communication module is used for carrying out control and data communication with external equipment.

Meanwhile, the memory 170 may also be used to store received external data and user data, images in various user interfaces, and visual effect maps, etc.

In addition, the memory 170 is specifically used for storing an operating program for driving the processor 110 in the smart mirror 100, and storing various application programs built in the smart mirror 100, various application programs downloaded by a user from an external device, various graphical user interfaces related to the applications, various objects related to the graphical user interfaces, user data information, and internal data of various supported applications. The memory 170 is also used to store system software such as OS kernel, middleware and applications, as well as drivers and related data for the display screen 140, the communication interface 130, the input/output interface of the detector 120, or other user data.

And the power supply 180 is used for providing power support for starting and running of each element in the intelligent mirror 100. In the form of a battery and associated control circuitry. Under the operation of a user, the power input by the external power supply provides power supply support for the intelligent mirror 100. The power supply 180 may include a built-in power supply circuit installed inside the smart mirror 100, or may be a power supply interface installed outside the smart mirror 100 to provide an external power supply in the smart mirror 100.

Fig. 2 is a block diagram schematically illustrating a software configuration of an intelligent mirror provided in an embodiment of the present application. As shown in fig. 2, may include an operating system 171, an interface layout management module 172, an event transmission system 173, and an application program 174.

The operating system 171, which includes executing operating software for handling various basic system services and for performing hardware-related tasks, acts as an intermediary for data processing performed between applications and hardware components, such as the android operating system. In some embodiments, a portion of the operating system kernel may contain a series of software to manage the hardware resources of the smart mirror 100 and provide services to other programs or software code.

In other embodiments, portions of the operating system kernel may include one or more device drivers, which may be a set of software code in the operating system that assists in operating or controlling the smart mirror associated device or hardware. The drivers may contain code that operates the video, audio, and/or other multimedia components. Examples include display screens, cameras, Flash, and WiFi.

Wherein, the accessibility module 1711 is used for accessing or modifying the application program to realize the accessibility of the application program and the operability of the display content of the application program.

A communication module 1712 for connection with other peripherals via the relevant communication interfaces and communication networks.

The user interface module 1713 is configured to provide an object for displaying a user interface, so that each application program can access the object, and operability of the user can be achieved. Such as the front-end interactive interface of a smart mirror.

Control applications 1714 for controlling process management, including runtime applications and the like.

The event transfer system 173, which may be implemented within the operating system 171 or within the application programs 174, is implemented in some embodiments, on the one hand, within the operating system 171 and, in the meantime, within the application programs 174, for listening for various user-entered events and, depending on the various events, referring to handlers that are responsive to the recognition of various types of events or sub-events, perform one or more sets of predefined operations.

The event monitoring module 1731 is configured to monitor an event or a sub-event input by the user input interface; event recognition module 1732 is used to input various event definitions for various user input interfaces, recognize various events or sub-events, and transmit them to processor 110 for execution of one or more corresponding sets of handlers. Such as the processor 110, processes the corresponding event or sub-event according to the logic program and core algorithm stored in the smart mirror 100 and presents the processed results on the display screen 140.

Where an event or sub-event refers to an input detected by one or more detectors in the smart mirror 100. Such as various sub-events of a user's voice input or various sub-events of an operation input on a display screen.

The interface layout management module 172 receives, directly or indirectly, the events or sub-events intercepted by the event transmission system 173 and input by the respective users, and is configured to update the layout of the user interface, including but not limited to the positions of the respective controls or sub-controls in the interface, and the size, position, and hierarchy of the container, which are various execution operations related to the interface layout.

Fig. 3 is a schematic diagram schematically illustrating a user interface of an intelligent mirror provided by an embodiment of the present application. As shown in fig. 3, the user interface includes a plurality of view display areas, for example, when the user clicks a video recommendation video that the user wants to learn, the smart mirror is automatically split into two upper and lower areas, namely a first view display area 301 and a second view display area 302, the first view display area 301 is used for the user to make up the mirror, and the second view display area 302 is used for playing the video recommendation video learned by the user. The display screen (such as a mirror surface) of the intelligent mirror can be in a full-screen mode so that a user can browse a corresponding cosmetic shop or a social interface conveniently, or can be in a full-mirror mode so that the user can look at the mirror or make up for other purposes, or can be in a half-mirror mode so that the user can watch the video and recommend the video and learn to make up or use for other purposes; each view display area includes a layout of one or more different items and a selector in the user interface indicating that any of the items is selected.

It should be noted that the plurality of view display areas may be visible boundaries or invisible boundaries. For example, different view display areas can be identified by different background colors of the view display areas, visible identification can be achieved through boundary lines and the like, and invisible boundaries can be provided. It is also possible that no visible or non-visible border exists and that only the associated view in a certain area is displayed on the screen, having the same change attribute in size and/or arrangement, which certain area is seen as the existence of a border for the same view section.

Some embodiments of the present application provide for a smart mirror, wherein the processor is configured to: determining target key information based on target information corresponding to a target user and preset key information received within preset time, wherein the target information comprises text information obtained by triggering a preset key of a response social interface and/or text information obtained by triggering a preset key of a response object display interface;

determining a recommended video according to key information of a preset video and the target key information, and displaying the recommended video through the display screen 140, wherein the key information of the preset video is obtained based on text information corresponding to the preset video and the preset key information.

Optionally, the number of target users is multiple, and the processor is configured to:

Optionally, the image collector 121 is configured to collect face information of the user, obtain a reference image, and transmit the reference image to the processor;

Optionally, the processor is configured to:

Optionally, the text information corresponding to the preset video includes at least one of a subtitle text, a title, an author, a comment, and a bullet screen corresponding to the preset video, and the processor is configured to:

Optionally, the processor is configured to:

Optionally, the preset key information includes at least one type of makeup information.

Fig. 4 is a flowchart illustrating a video recommendation method. This process may be performed by the smart mirror 100.

As shown in fig. 4, the process includes:

step 401, determining target key information based on target information corresponding to a target user received within a preset time and preset key information.

The target information comprises text information obtained by responding to triggering of a preset key of a social interface and/or text information obtained by responding to triggering of a preset key of an object display interface.

In this embodiment, a user watching a video may generate a watching record, but the user watching the video has a certain randomness, particularly for a makeup video. For example, if a user is not interested in viewing a video and quits midway, a viewing record is also generated, so that the user viewing record cannot accurately reflect the user preference. Based on this, it is necessary to accurately determine information reflecting the user's preference.

Illustratively, according to a certain historical time period determined according to an actual application scenario, the preference of the target user in the certain historical time period can be accurately reflected by responding to the text information obtained by triggering the preset key of the social interface by the target user and/or responding to the text information obtained by triggering the preset key of the object display interface by the target user in the certain historical time period. Further, determining information which is interesting to the target user within the preset time through text information and preset key information which are obtained by responding to the triggering of a preset key of a social interface by the target user within the preset time; or determining information which is interesting to the target user within the preset time through text information and preset key information which are obtained by triggering a preset key of the response object display interface within the preset time by the target user.

In order to be more suitable for the smart mirror, in some embodiments, the preset key information includes at least one type of makeup information, for example, the preset key information includes at least one of five types of makeup information, including a brand type, a cosmetic category type, an applicable feature type, an applicable style type, and an applicable occasion type, and the embodiment does not limit what specific information each type includes, for example:

1) the brand types include but are not limited to all common beauty makeup brands and joint brands related to joint makeup, such as joint automobile brands, joint sports brands and the like;

2) cosmetic category types include: blush, lipstick, foundation make-up, lipstick, eyebrow pencil, air cushion, puff, make-up egg, eye shadow, lotion, perfume, sun block, compact, lip liner, lip gloss, etc.;

3) the applicable feature types include: mixing skin, oily skin, dry skin, Liuhai, double-edged eyelid, single-edged eyelid, long hair, short hair, cauda equina, large eye, small eye, large mouth, small mouth, etc.;

4) the applicable style types include: rui, sweet, gentlewoman, girl, fresh, garden, leisure, sports, neutral, commute, OL/business, korean, brief, sensai, sunset, wild, europe, street, hip-hop, punk, college, english, retro, chinese, bosch, lorita, gotten, baroque, padel, etc.;

5) types of applications include: life, work, commute, sports, wedding, banquet, party, stage, military, evening party, travel, interview, meeting, party, mountain climbing, outdoors, shopping, appointments, and the like.

The preset key information is only an example, and other related information may also be used as the preset key information, which is not illustrated herein.

Fig. 5A-C are schematic diagrams illustrating social interfaces of a set of smart mirrors provided by an embodiment of the present application. In some implementations, the social interface shown in fig. 5A shows the dynamics published by all users or interested users (fig. 5A takes dynamic 1, dynamic 2, dynamic 3, dynamic 4, and dynamic 5 as examples, where only the image display of dynamic 1 is shown, and in practical applications, there are also image displays of other dynamics), a user enters the social interface shown in fig. 5B by touching any one of the dynamics on the social interface shown in fig. 5A, the user approves the dynamics by touching a "approve" icon on the social interface shown in fig. 5B, and the user comments the dynamics by entering comment information in a comment frame on the social interface shown in fig. 5B; the user can type query information into a search box on the social interface shown in fig. 5A, and the intelligent mirror displays the determined content based on the query information; the user enters the social interface shown in fig. 5C by touching the "camera" icon on the social interface shown in fig. 5A, and can perform dynamic distribution through the social interface shown in fig. 5C.

The social interface of the smart mirror is only an example, and the smart mirror provided in this embodiment may also display other similar social interfaces.

In some embodiments, the text message obtained in response to the preset key of the social interface being triggered may include one or more of the following types of text messages:

1) responding to the social interface with the praise key triggered to obtain the text information dynamically contained corresponding to the praise key;

2) responding to the fact that a comment key in the social interface is triggered to obtain text information of comments;

3) responding to the triggering of a search key in the social interface to obtain searched text information;

4) and responding to the triggering of the publishing key in the social interface to obtain the published text information.

The text information is only an example, and text information obtained by other methods is also applicable to the embodiment.

The text information obtained by triggering the preset key of the response object display interface may be implemented by, but not limited to, the following manners:

1) the object display interface can be a mall interface, the preset keys of the object display interface are object storage keys of the mall interface, an object corresponding to the object storage keys is obtained in response to the object storage keys in the mall interface being triggered, and the text information is determined according to the title and/or text introduction information of the object.

Fig. 6A is a schematic diagram illustrating an example of a mall interface of an intelligent mirror provided in an embodiment of the present application. In some implementations, the target user can add the corresponding item to the shopping cart by touching any of the "+" icons on the mall interface shown in FIG. 6A.

2) The object display interface can be an interface which is displayed on one side of a video and contains an object in the video playing process, a preset key of the object display interface is an object storage key of the interface containing the object, the object corresponding to the object storage key is obtained in response to the object storage key being triggered, and the text information is determined through the title and/or text introduction information of the object.

Fig. 6B is a schematic diagram schematically illustrating a video display interface of an intelligent mirror provided in an embodiment of the present application. In some implementations, the target user can add the corresponding item to the shopping cart by touching any of the "+" icons on the object presentation interface at the upper level of the video display interface shown in FIG. 6B.

Other ways of obtaining the target user storage object are also applicable to this embodiment, and are not described herein again.

Step 402, determining a recommended video according to the key information of a preset video and the target key information, and displaying the recommended video through the display screen.

The key information of the preset video is obtained based on the text information corresponding to the preset video and the preset key information.

In this embodiment, the target key information is information that a target user is interested in within a preset time, the key information of the preset video is related information of the preset video, and based on this, which videos the target user is interested in can be determined by integrating the information that the target user is interested in within the preset time and the related information of the preset video.

The above determining the recommended video according to the key information of the preset video and the target key information may be implemented by, but not limited to, the following manners:

1) and determining the contact ratio of the key information of each preset video and the target key information, and taking the preset video with the contact ratio reaching a preset contact ratio threshold value as the recommended video.

For example: the preset contact ratio threshold value is 70%, the target key information is preset key information 1, preset key information 2, preset key information 3, preset key information 4 and preset key information 5, the preset video A has no key information, and the contact ratio with the target key information is 0; the key information of the preset video B is preset key information 1 and preset key information 2, and the contact ratio of the preset key information to the target key information is 40%; the key information of the preset video C is preset key information 1, preset key information 2, preset key information 3 and preset key information 4, and the contact ratio of the preset key information to the target key information is 80%; the key information of the preset video D is preset key information 1, preset key information 2, preset key information 3, preset key information 4 and preset key information 5, the contact ratio of the preset video D and the target key information is 100%, and the preset video C and the preset video D are used as recommended videos.

2) And sequencing the preset videos according to the contact ratio from high to low, determining the ranking of the preset videos, and taking the preset video before the preset ranking as the recommended video.

The preset video A, B, C, D is taken as an example, the four videos are sorted from top to bottom according to the contact ratio with the target key information, the sorting results are a preset video D, a preset video C, a preset video B and a preset video a, and if the preset ranking is 3, the ranking of the preset video C and the preset video D is before the preset ranking, the two preset videos are taken as the recommended videos.

The method comprises the steps of determining the contact ratio of key information of each preset video and target key information, selecting all preset videos with contact ratios reaching a preset contact ratio threshold value as recommended videos, or selecting a certain number of preset videos with larger contact ratios as recommended videos, and accordingly selecting a proper mode to determine the recommended videos according to actual application scenes.

The relevant information of the preset video is obtained based on the corresponding text information and the preset key information, and compared with the method that the preset video is input into a model constructed by a deep learning algorithm to determine the relevant information, the calculation amount is reduced, and the processing pressure of the intelligent mirror processor is further reduced, so that the processing can be finished by using a processor with general processing performance, and the method is more suitable for an intelligent mirror.

In this embodiment, it may be referred to the above embodiments as to which information is specifically included in the preset key information, and details are not described here.

For videos, particularly makeup videos, subtitles of the makeup bloggers can be presented basically, and/or product text presentation appears on one side of a picture when makeup products are presented every time, so that the subtitle texts can reflect the whole content of the videos;

the title is a brief summary of the whole video content and can also reflect the whole content of the video;

the comments and the barrage can reflect the whole content of the video to a certain extent.

The embodiment does not limit the specific manner of obtaining the subtitle text, the title, the author, the comment and the bullet screen corresponding to the preset video, for example:

crawling to obtain a title, an author, a comment and a barrage corresponding to the preset video by adopting crawler software;

the subtitle text corresponding to the preset video can be obtained in the following way:

Illustratively, each preset video is segmented according to a preset time interval to obtain a target image; and filtering the target images containing the characteristic values of the same subtitle text, namely only retaining one frame of target images containing the characteristic values of the same subtitle text, and taking the subtitle text contained in the target images after each preset video is filtered as the corresponding subtitle text.

The method for determining the preset time interval is not limited in this embodiment, for example, the time interval may be determined according to the interval and frequency of switching subtitles of some makeup teaching videos under the condition that it is ensured that more than 90% of subtitles are not ignored, so as to ensure content integrity and segmentation efficiency.

According to the method, the target image is selected from each preset video based on the preset time interval, so that the calculation amount for subsequently acquiring the caption text can be reduced while the content is ensured to be complete; images containing feature values of the same subtitle text are selected from the target images of the preset videos and are filtered, so that the same target images are removed, and the calculation amount of the subtitle text obtained subsequently is further reduced; the caption text contained in the filtered target image can comprehensively and accurately reflect the corresponding preset video related information.

The key information of the preset video can be obtained by, but not limited to, the following ways:

For example: the text information corresponding to the preset video A does not contain any preset key information, so that the preset video A has no key information;

the text information corresponding to the preset video B includes preset key information 1 and preset key information 2, and then the key information of the preset video B is the preset key information 1 and the preset key information 2.

The above is merely an example of possible implementation manners of the key information of the preset video, and is not limited to the embodiment.

In the embodiment, one or more items of subtitle texts, titles, authors, comments and barracks corresponding to the preset video are selected as text information according to the actual application scene, so that the requirements of different scenes are met; one or more pieces of preset key information contained in the text information corresponding to the preset video are used as the key information corresponding to the preset video, so that the key information of the preset video can be accurately obtained through a small calculation amount, the processing pressure of the processor is reduced, and the accuracy of obtaining the key information of the preset video is ensured.

Fig. 7 is a flowchart illustrating another video recommendation method for a scene with multiple target users. As shown in fig. 7, the process includes:

step 701, one or more pieces of preset key information included in the target information of each target user are used as key information of the corresponding target user.

In this embodiment, for a scenario with multiple target users, key information of each target user needs to be determined first. For example:

the target information of the target user A comprises preset key information 1, preset key information 2, preset key information 3 and preset key information 4, and then the key information of the target user A is the preset key information 1, the preset key information 2, the preset key information 3 and the preset key information 4;

the target information of the target user B includes preset key information 1, preset key information 2, preset key information 5 and preset key information 6, and then the key information of the target user B is the preset key information 1, the preset key information 2, the preset key information 5 and the preset key information 6.

The number of target users and the number of key information of each target user are not limited in this embodiment, and the number of key information of each target user may be the same or different, and is not described herein again.

Step 702, using key information, the frequency of which is greater than a preset frequency threshold, in the target information of all target users as the target key information; or determining the selection proportion of the key information of each target user according to the level of each target user, and selecting the target key information from the key information of each target user based on the selection proportion.

In this embodiment, for a scenario with multiple target users, final target key information needs to be determined according to the key information of each target user, and the target key information may be determined in, but not limited to, the following two ways:

1) and taking key information of which the occurrence frequency is greater than a preset frequency threshold value in the target information of all target users as the target key information.

For example: the preset time threshold value is 3 times, the target user comprises a target user A and a target user B, the preset key information 1 appears 5 times in the target information of the target user A, and 1 time appears in the target information of the target user B, and the preset key information appears 6 times in total; presetting key information 2, wherein the key information 2 appears 3 times in target information of a target user A, and the key information 2 appears 5 times in target information of a target user B, and the preset key information appears 8 times in total; presetting key information 3 for 4 times in target information of a target user A; presetting key information 4 appears 2 times in target information of a target user A; presetting key information 5 appears 6 times in target information of a target user B; the preset key information 6 appears 4 times in the target user B target information. The occurrence frequency of the preset key information 1, the preset key information 2, the preset key information 3, the preset key information 5 and the preset key information 6 is greater than a preset frequency threshold value, and the five preset key information are used as target key information.

In the embodiment, the key information of which the occurrence frequency is greater than the preset frequency threshold value in the target information of all the target users is used as the target key information, so that the preference of all the target users can be considered in a balanced manner, and further, videos in which all the target users are interested are recommended subsequently.

2) And determining the selection proportion of the key information of each target user according to the grade of each target user, and selecting the target key information from the key information of each target user based on the selection proportion.

Also, by taking the above embodiment as an example, if the level of the target user a is the first level, the corresponding selection ratio is 75%, and the level of the target user B is the second level, the corresponding selection ratio is 50%. Sorting the key information of the target user A according to the occurrence times, selecting the key information of the first 75%, and selecting preset key information 1, preset key information 2 and preset key information 3; and sorting the key information of the target user B according to the occurrence times, selecting the top 50% of the key information, selecting the preset key information 1 and the preset key information 5, and finally taking the preset key information 1, the preset key information 2, the preset key information 3 and the preset key information 5 as the target key information.

Or the same key information of each target user is selected first, then the information is selected from different key information of each target user based on the selection proportion, and the same key information and the selected information are jointly used as the target key information.

According to the method and the device for recommending the video, the target key information is selected from the key information of the target users according to the selection proportion corresponding to the level of each target user, so that the target users with high priority can be considered in a high priority, and the video which is more interested by the target users with high priority is recommended subsequently.

Step 703, determining a recommended video according to the key information of a preset video and the target key information, and displaying the recommended video.

Step 703 is the same as step 402, and is not described herein again.

In this embodiment, for a scene with multiple target users, one or more pieces of preset key information included in target information of each target user are used as key information of a corresponding target user, and by using key information, the times of occurrence of which are greater than a preset time threshold, in the target information of all the target users as the target key information, the preference of all the target users can be considered in a balanced manner; target key information is selected from the key information of each target user according to the selection proportion corresponding to the grade of each target user, and the target users with high grade can be considered in a focused mode.

Fig. 8 is a flow chart illustrating another video recommendation method. As shown in fig. 8, the process includes:

step 801, determining preset face information of which the similarity with the user face information contained in the reference image reaches a preset similarity threshold, and taking a preset user corresponding to the preset face information as the target user.

The reference image is obtained by collecting face information of a user through an image collector.

In some embodiments of the application, the image collector can collect face information of a user before an intelligent mirror to obtain a reference image, the reference image can be a static image or a dynamic image, the processor obtains the reference image and determines the face information of the user contained in the reference image, the face information of the user is compared with preset face information, if the similarity between the face information of the user and certain preset face information reaches a preset similarity threshold, a preset user corresponding to the preset face information is determined according to the corresponding relation between the preset face information and the user, and the preset user is used as a target user.

In some embodiments of the present application, the image collector has both an image collecting function and an image processing function, for example, an Artificial Intelligence (AI) camera, and the step of determining the target user may also be performed by the AI camera.

Step 802, determining target key information based on target information corresponding to a target user received within a preset time and preset key information.

And 803, determining a recommended video according to the key information of the preset video and the target key information, and displaying the recommended video.

The steps 802 and 803 are the same as the implementation of the steps 401 and 402, and are not described herein again.

In this embodiment, the target user in front of the intelligent mirror can be accurately determined through the reference image collected by the image collector.

As shown in fig. 9, based on the same inventive concept, an embodiment of the present invention provides a video recommendation apparatus 900, including: a determination module 901 and a video recommendation module 902.

A determining module 901, configured to determine target key information based on target information and preset key information corresponding to a target user received within a preset time, where the target information includes text information obtained by triggering a preset key on a response social interface and/or text information obtained by triggering a preset key on a response object display interface;

the video recommending module 902 is configured to determine a recommended video according to key information of a preset video and the target key information, and display the recommended video, where the key information of the preset video is obtained by the determining module 901 based on text information corresponding to the preset video and the preset key information.

Optionally, the number of the target users is multiple, and the determining module 901 determines the target key information based on the target information corresponding to the target user and the preset key information received within the preset time, where the determining includes:

Optionally, the determining module 901 is further configured to, before determining the target key information, determine preset face information that a similarity with user face information included in a reference image reaches a preset similarity threshold, and use a preset user corresponding to the preset face information as the target user, where the reference image is obtained by collecting the face information of the user through an image collector.

Optionally, if the text information corresponding to the preset video includes a subtitle text corresponding to the preset video, the determining module 901 obtains the subtitle text corresponding to the preset video in the following manner:

Optionally, the text information corresponding to the preset video includes at least one of a subtitle text, a title, an author, a comment, and a barrage corresponding to the preset video, and the determining module 901 obtains the key information of the preset video in the following manner:

Optionally, the video recommendation module 902 determines, according to the key information of the preset video and the target key information, a recommended video, which includes:

Since the apparatus is the apparatus in the method in the embodiment of the present invention, and the principle of the apparatus for solving the problem is similar to that of the method, the implementation of the apparatus may refer to the implementation of the method, and repeated details are not repeated.

An embodiment of the present invention further provides a computer-readable non-volatile storage medium, which includes a program code, and when the program code runs on a computing terminal, the program code is configured to enable the computing terminal to execute the steps of the video recommendation method according to the embodiment of the present invention.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A smart mirror, comprising:

a processor configured to:

2. The intelligent mirror according to claim 1, wherein the number of the target users is plural,

the processor is configured to:

3. The smart mirror of claim 1, further comprising: the image collector is used for collecting the face information of the user to obtain a reference image and transmitting the reference image to the processor;

4. The smart mirror of claim 1, wherein the processor is configured to:

if the text information corresponding to the preset video comprises the subtitle text corresponding to the preset video,

5. The smart mirror of claim 1, wherein the text information corresponding to the preset video includes at least one of a subtitle text, a title, an author, a comment, and a bullet screen corresponding to the preset video,

the processor is configured to:

6. The smart mirror of any of claims 1-5, wherein the processor is configured to:

7. The smart mirror of any one of claims 1 to 5, wherein the preset key information includes at least one type of makeup information.

8. A method for video recommendation, the method comprising:

9. The method of claim 8, wherein the number of target users is plural,

the determining of the target key information based on the target information corresponding to the target user received within the preset time and the preset key information includes:

10. The method of claim 8, prior to determining target key information, further comprising:

the method comprises the steps of determining preset face information of which the similarity with user face information contained in a reference image reaches a preset similarity threshold value, and taking a preset user corresponding to the preset face information as a target user, wherein the reference image is obtained by collecting the face information of the user through an image collector.