CN104778867A - Multifunctional child talkback early education machine - Google Patents

Abstract

The invention relates to a multi-functional children's intercom early education machine, which includes a voice recognition module, a face recognition module, a controller module, a display module and a voice playback module, and the controller module is respectively connected to the voice recognition module, the face recognition module, the display Module and voice playback module, to start different user modes corresponding to different users according to the user identified by the voice recognition module or face recognition module, wherein, the video played by the display module and the voice playback module respectively under different user modes Content and audio content are different. Through the present invention, the user who is currently using the early education machine can be identified to start different user modes and realize the playback of various styles of audio and video content.

Description

Multifunctional children's intercom early education machine

The present invention is a divisional application of a patent whose application number is 201310181325X, the application date is May 15, 2013, and the invention name is "Multifunctional Children's Intercom Early Education Machine".

technical field

The invention relates to the field of early education machines, in particular to a multifunctional intercom early education machine for children.

Background technique

With the development of science and technology and the improvement of human living standards, various novel and educational children's toys have appeared, and children's education time is getting earlier and earlier. Among them, the children's early education machine has won the love of children and parents with its rich and colorful content, entertaining and friendly style, and diverse appearance designs. It also caters to the parents' psychology of letting their children learn early. Early education machines of different brands and levels emerge in endlessly.

However, some existing early childhood education machines have uneven functions. Generally speaking, the interaction is not strong, the user mode is single, and the audio and video content played for different user groups is exactly the same, which cannot meet the different needs of girls and boys. At the same time, because of the frequent use and high power consumption of the early education machine, it needs to be charged continuously. However, the traditional charging method makes parents have to be busy monitoring the power situation of the early education machine. Moreover, the external audio and video interface of the current early education machine Relatively single, poor compatibility.

Therefore, there is a need for a multi-functional children's intercom early education machine, which transforms the original early education machine with poor interaction, single function, and inconvenient charging. Through the identification of different user groups, different modes of audio and video content playback are started, and clean and environmentally friendly solar energy is introduced. The charger automatically charges the early childhood education machine when taking children for a walk, and adds an external interface for unified audio and video signal connection in multiple formats, increases the functions of the children's early education machine, and enriches the user's experience.

Contents of the invention

In order to solve the above problems, the present invention provides a multi-functional children's intercom early education machine, which can identify the user group to which the current user belongs through the voice recognition device and face recognition mode, so as to control the operation mode of the early education machine, and play the voice playing device Play audio and video content on the display that caters to different user preferences, add a solar charger, and charge it in time when the power of the early education machine is lower than the predetermined threshold. In addition, use FPGA chips to design a unified signal compatible with DVI, HDMI and DisplayPort formats The interface enables the early education machine to receive and play audio and video signals in various formats, thus making the design of the early education machine more humanized.

According to one aspect of the present invention, a multifunctional children's intercom early education machine is provided, including a voice recognition module, a face recognition module, a controller module, a display module and a voice playback module, and the controller module is respectively connected to the voice recognition module, human Face recognition module, display module and voice playback module, to start different user modes corresponding to different users according to the user identified by the voice recognition module or face recognition module, wherein the display module and voice playback module are in different user modes The video content and audio content played separately are different.

More specifically, the multifunctional children's intercom early education machine further includes: a solar charging module having a photovoltaic panel to collect solar energy by using the photovoltaic panel, and when the power supply of the early education machine is below a predetermined threshold, the solar charging module is activated The charging operation of the early education machine; the voice collection module, when the user selects voice collection by operating the remote control or the function button, collects the user voice signal sent by the user, and records the different voice characteristics of each user in advance, so that each user The different voice features of the user are pre-stored in the memory module; the voice recognition module is connected to the voice acquisition module and the memory module, and the user voice signal collected by the voice acquisition module is compared with the different voice features of each user stored in the memory module in advance, To identify the user corresponding to the current user's voice signal; the camera module collects the user's facial image when the user selects the user's facial feature collection by operating the remote control or the function button, and records the different facial features of each user in advance, so as to The different facial features of each user are pre-stored in the memory module; the face recognition module is connected to the camera module and the memory module, and the face image collected by the camera module is compared with the different faces of each user pre-stored in the memory module. Features are compared to identify the user corresponding to the face image currently collected by the camera module; the memory module is connected to the voice collection module, voice recognition module, camera module, and face recognition module, and stores different voice features and individual voice features of each user in advance. The different facial features of the user are used for the voice recognition module and the face recognition module to call respectively, and the memory module has also stored audio files and video files for the display module and the voice playback module to call respectively; the display module is connected to the memory module , to display the video content corresponding to the video file stored in the memory module; the voice playback module is connected to the memory module to play the audio content corresponding to the audio file stored in the memory module; the unified signal interface module is connected to the display module and the voice playback module, Adopt FPGA chip to realize the connection of external audio and video signals compatible with DVI, HDMI and DisplayPort formats, and forward the received external audio and video signals to the display module and voice playback module to play the audio and video signals. The FPGA chip is Xilinx company The Virtex4LX25; the remote control controls the early childhood education machine under the operation of the user, including starting up, shutting down, selecting the video file to be displayed by the display module, selecting the audio file to be played by the voice playback module, and selecting to receive external signals from the unified signal interface module. Audio and video signals, setting the predetermined threshold, setting the volume played by the voice playback module; the function button controls the early childhood education machine under the operation of the user, including starting, shutting down, selecting the video file to be displayed by the display module, selecting The audio file that the voice player module will play, select to receive the external audio and video signal from the unified signal interface module, set the predetermined threshold, set the volume of the voice player module to play; USB interface, for connecting external charging The device is charged, and is used to connect an external storage device to download audio files and video files selected by the user, and store the downloaded audio files and video files in the memory module; the controller module is connected to the voice recognition module and face recognition Module, to receive the user identified by the voice recognition module or the face recognition module, start different user modes corresponding to different users; wherein, the user mode includes girl mode, boy mode, parent mode, and the voice playback module is in different user modes Send out the sound that communicates with the user with different characteristics, and the display module displays the image background of communicating with the user with different characteristics in different user modes; wherein, the voice playback module is a left and right speaker, and the display module is a liquid crystal display screen. The resolution of the LCD screen is one of 160×128, 384×320, 640×480 or 1024×600.

More specifically, the multifunctional children's intercom early education machine further includes: a wireless communication module, connected to the camera module, so as to wirelessly send the images collected by the camera module to the parent's mobile phone.

More specifically, the multifunctional children's intercom early education machine further includes: the wireless communication module is one of a 3G communication module and a 4G communication module.

More specifically, the multifunctional children's intercom early education machine further includes: the voice collection module uses one of the sampling rates of 22.05KHz, 44.1KHz and 48KHz when collecting user voice signals.

Description of drawings

Embodiments of the present invention will be described below in conjunction with the accompanying drawings, wherein:

Fig. 1 shows a structural block diagram of a multifunctional children's intercom early education machine according to an embodiment of the present invention.

Among them, 1. Voice recognition module; 2. Face recognition module; 3. Controller module; 4. Display module; 5. Voice playback module.

Detailed ways

The embodiments of the multifunctional children's intercom early education machine of the present invention will be described in detail below with reference to the accompanying drawings.

Fig. 1 shows a structural block diagram of a multifunctional children's intercom early education machine according to an embodiment of the present invention. Wherein said multifunctional children's intercom early education machine comprises, voice recognition module 1, face recognition module 2, controller module 3, display module 4 and voice playback module 5, and controller module 3 is respectively connected voice recognition module 1, people's face Recognition module 2, display module 4 and voice playback module 5, to start different user modes corresponding to different users according to the user identified by described voice recognition module 1 or face recognition module 2, wherein, display module 4, voice playback The video content and audio content played by the module 5 in different user modes are different. Further, the multi-functional children's intercom early education machine also includes a solar charging module, which has a photovoltaic panel to use the photovoltaic panel to collect solar energy, and when the power supply of the early education machine is below a predetermined threshold, the solar charging module is activated. The charging operation of the early education machine; the voice collection module, when the user selects voice collection by operating a remote controller or a function button, collects user voice signals sent by the user, and pre-records the different voice characteristics of each user, so that each user's Different voice features are pre-stored in the memory module; the voice recognition module 1 is connected to the voice acquisition module and the memory module, and the user voice signal collected by the voice acquisition module is compared with the different voice features of each user pre-stored in the memory module, To identify the user corresponding to the current user's voice signal; the camera module collects the user's facial image when the user selects the user's facial feature collection by operating the remote control or the function button, and records the different facial features of each user in advance, so as to The different facial features of each user are pre-stored in the memory module; the face recognition module 2 is connected to the camera module and the memory module, and the face image collected by the camera module is compared with the different faces of each user pre-stored in the memory module. Compare facial features to identify the user corresponding to the face image currently collected by the camera module; the memory module is connected to the voice collection module, voice recognition module 1, camera module, and face recognition module 2, and stores different voices of each user in advance feature and the different facial features of each user, to call respectively for the voice recognition module 1 and the face recognition module 2, and the memory module also stores audio files and video files, for the display module 4 and the voice playback module 5 to call respectively Display module 4, connect memory module, display the corresponding video content of the video file stored in the memory module; Voice playback module 5, connect memory module, play the audio content corresponding to the audio file stored in the memory module; unified signal interface module , connect the display module 4 and the voice playback module 5, adopt the FPGA chip to realize the connection of the external audio and video signals compatible with DVI, HDMI and DisplayPort formats, and forward the received external audio and video signals to the display module 4 and the voice playback module 5 to perform The broadcast of audio-video signal, described FPGA chip is the Virtex4LX25 of Xilinx company; Remote controller controls early childhood education machine under the user's operation, comprises start-up, shut-down, selects the video file that display module 4 will show, selects voice play module 5 Audio files to be played, select to receive external audio and video signals from the unified signal interface module, set the predetermined threshold, set the volume of the voice playback module 5 to play; the function button controls the early childhood education machine under the user's operation , including starting up, shutting down, selecting the video file to be displayed by the display module 4, selecting the audio file to be played by the voice playback module 5, selecting to receive the external audio and video signal from the unified signal interface module, setting the predetermined threshold, setting the voice The volume played by the playback module Size; USB interface, used to connect an external charging device for charging, and for connecting an external storage device to download audio files and video files selected by the user, and store the downloaded audio files and video files in the memory module; controller Module 3, connecting the voice recognition module 1 and the face recognition module 2, to receive the user identified by the voice recognition module 1 or the face recognition module 2, and start different user modes corresponding to different users; wherein, the user mode includes a girl mode , boy mode, parent mode, the voice playing module 5 sends the sound of communicating with the user with different characteristics under different user modes, and the display module 4 displays the image background of communicating with the user with different characteristics under different user modes; wherein, the voice The playback module 5 is left and right speakers, and the display module 4 is a liquid crystal display, and the resolution of the liquid crystal display is one of 160×128, 384×320, 640×480 or 1024×600.

Among them, face recognition specifically refers to computer technology that uses the analysis and comparison of visual feature information of faces for identity identification. Face recognition is a popular computer technology research field, face tracking detection, automatic adjustment of image magnification, night infrared detection, automatic adjustment of exposure intensity; ) to distinguish individual organisms by their own biological characteristics. Face recognition technology is based on human facial features. For the input face image or video stream, it first judges whether there is a face, and if there is a face, it further gives the position, size and each face of each face. Location information of major facial organs. Based on this information, the identity features contained in each face are further extracted, and compared with known faces, so as to identify the identity of each face.

Among them, speech recognition is an interdisciplinary subject, which is to recognize the content of the speech and the user who makes the speech according to the characteristics of the speech. In the past two decades, speech recognition technology has made remarkable progress and has begun to move from the laboratory to the market. It is expected that in the next 10 years, speech recognition technology will enter various fields such as industry, home appliances, communications, automotive electronics, medical care, home services, and consumer electronics. The application of speech recognition and dictation machines in some fields was rated as one of the ten major events in computer development in 1997 by the American press. Many experts believe that speech recognition technology is one of the ten most important technological developments in the field of information technology between 2000 and 2010. The fields involved in speech recognition technology include: signal processing, pattern recognition, probability theory and information theory, vocal mechanism and auditory mechanism, artificial intelligence, etc.

Among them, DVI, HDMI, DisplayPort, and DiiVA are common digital audio and video interface standards in the market. DVI (Digital Visual Interface), that is, digital video interface, is composed of Silicon Image, Intel (Intel), Compaq (Compaq), IBM, HP (Hewlett-Packard), NEC, Fujitsu (Fujitsu) and other companies to form DDWG (Digital Display Working Group) , Digital Display Working Group) interface standard introduced in 1999, DVI is based on the PanalLink interface technology, based on the TMDS (transmission minimized differential signal) electronic protocol as the basic electrical connection, the highest signal transmission rate is 1.65Gbps, compared with the previous The advanced analog video interface has the characteristics of fast speed, clear picture and support for HDCP protocol. HDMI (High Definition Multimedia Interface), that is, high-definition multimedia interface, was jointly organized by seven companies including Hitachi, Panasonic, Philips, Silicon Image, Sony, Thomson, and Toshiba on December 9, 2002. Officially released, HDMI is based on DVI and adopts TMDS coding mechanism to perform time-division control on video signals, audio signals and control signals. Copyright protection lacks support, digital audio signals are not supported, and the interface is bulky. DisplayPort, referred to as DP interface, was released by VESA (Video Electronics Standards Organization) in May 2006. It is an open standard for all display devices (including internal and external interfaces), adopts 8B/10B encoding, embedded clock signal and micro-packet architecture, video content is transmitted in packets, supports HDCP digital content protection protocol, and can simultaneously Transmission of audio and video, the maximum transmission bandwidth is 10.8Gb/S, it directly transmits low-bandwidth data such as voice and video through an external channel that can realize two-way communication. Compared with HDMI, DisplayPort has a larger transmission bandwidth and stronger compatibility. DiiVA, the digital high-definition interactive interface, was launched in April 2009 by 9 companies including TCL, Hisense, Skyworth, Konka, Changhong, Haier, SVA, Panda Electronics, and Lingxu. It adopts the same 8B/10B encoding as the DisplayPort interface technology, supports video bandwidth up to 13.5Gbps, supports mixed channel bandwidth totaling more than 2Gbps, can do two-way data and audio transmission, and also supports HDCP 2.0 and DTCP-IP, which adopts the daisy chain connection method, so that any one in the DiiVA network The devices in can all access each other. Different consumer electronics manufacturers, semiconductor companies, test equipment manufacturers and commercial electronics manufacturers choose different digital audio and video interfaces in their products according to their own interests. These products include digital TV, DVD, VCR, computer , set-top boxes, video cameras.

In addition, the multifunctional children's intercom early education machine further includes: a wireless communication module, connected to the camera module, so as to wirelessly send the images collected by the camera module to the parent's mobile phone. The addition of the wireless communication module enables parents to use the early education machine to conduct dynamic wireless monitoring of children.

In addition, the multifunctional children's intercom early education machine further includes: the wireless communication module is one of a 3G communication module and a 4G communication module. Users can choose early education machines customized by early education machine manufacturers according to the type of communication network implemented locally and their own economic conditions.

Among them, the third-generation mobile communication technology (3rd-generation, 3G) refers to a cellular mobile communication technology that supports high-speed data transmission. 3G services can transmit voice and data information at the same time, and the rate is generally above several hundred kbps. 3G refers to a new generation of mobile communication system that combines wireless communication with multimedia communication such as the Internet. Currently, there are four standards for 3G: CDMA2000, WCDMA, TD-SCDMA, and WiMAX. The main difference between 3G and 2G is the increase in the speed of transmitting voice and data. It can better realize wireless roaming around the world, and process images, music, video streams and other media forms, providing services including web browsing, Teleconferencing, e-commerce and other information services, but also consider the good compatibility with the existing second-generation system. In order to provide this service, the wireless network must be able to support different data transmission speeds, that is to say, it can support at least 2Mbps (megabits per second) and 384kbps (kilobits per second) in indoor, outdoor and driving environments, respectively. And a transmission speed of 144kbps (this value will change according to the network environment).

Among them, 4G is the abbreviation of the fourth generation mobile communication and its technology. It is a technical product that integrates 3G and WLAN and can transmit high-quality video images, and the image transmission quality is comparable to that of high-definition television. The 4G system can download at a speed of 100Mbps, which is 2000 times faster than dial-up Internet access, and the upload speed can also reach 20Mbps, and can meet the requirements of almost all users for wireless services. In addition, 4G can be deployed where DSL and cable modems do not have coverage, and then spread throughout the region.

In addition, the multifunctional children's intercom early education machine further includes: the voice collection module uses one of the sampling rates of 22.05KHz, 44.1KHz and 48KHz when collecting user voice signals. The sampling rate of the voice collection module used can be determined according to the voice quality required by the voice recognition module 5 .

Among them, the audio sampling rate refers to the number of times the recording device samples the sound signal within one second. The higher the sampling frequency, the more realistic and natural the sound reproduction will be. On today's mainstream acquisition cards, the sampling frequency is generally divided into three levels: 22.05KHz, 44.1KHz, and 48KHz. 22.05KHz can only reach the sound quality of FM broadcasting, 44.1KHz is the theoretical limit of CD sound quality, and 48KHz is even higher. Be more precise. For the sampling frequency higher than 48KHz, the human ear can no longer distinguish it, so it has little use value on the computer. Sound is actually a kind of energy wave, so it also has the characteristics of frequency and amplitude. The frequency corresponds to the time axis, and the amplitude corresponds to the level axis. The wave is infinitely smooth, and the string can be regarded as composed of countless points. Since the storage space is relatively limited, the points of the string must be sampled during the digital encoding process. The process of sampling is to extract the frequency value of a certain point. Obviously, the more points are extracted in one second, the more abundant the frequency information can be obtained. In order to restore the waveform, there must be two sampling points in one vibration. The highest frequency that can be felt is 20kHz, so to meet the auditory requirements of the human ear, at least 40k samples per second are required, expressed in 40kHz, this 40kHz is the sampling rate.

Using the multifunctional children's intercom early education machine of the present invention, aiming at the technical problem that the existing children's intercom early education machine is not humanized enough, a variety of user identification devices are used to identify the current user, and according to the user group to which the identified user belongs Start playing the audio and video content of the early education machine in different user modes. The early education machine also uses the solar automatic charging function and the unified reception function of multiple audio and video signals to meet the various needs of users.

It can be understood that although the present invention has been disclosed above with preferred embodiments, the above embodiments are not intended to limit the present invention. For any person skilled in the art, without departing from the scope of the technical solution of the present invention, the technical content disclosed above can be used to make many possible changes and modifications to the technical solution of the present invention, or be modified to be equivalent to equivalent changes. Example. Therefore, any simple modifications, equivalent changes and modifications made to the above embodiments according to the technical essence of the present invention, which do not deviate from the technical solution of the present invention, still fall within the protection scope of the technical solution of the present invention.

Claims (2)

1. A multifunctional children's intercom early education machine, is characterized in that, said early education machine can include: Voice recognition module, face recognition module, controller module, display module and voice playback module, the controller module is connected with voice recognition module, face recognition module, display module and voice playback module respectively, to The user identified by the face recognition module activates different user modes corresponding to different users, Wherein, the video content and audio content played by the display module and the voice playback module in different user modes are different, Also includes: The solar charging module has a photovoltaic panel to use the photovoltaic panel to collect solar energy, and when the power supply of the early education machine is below a predetermined threshold, the solar charging module is started to charge the early education machine; The voice collection module, when the user selects voice collection by operating the remote control or the function button, collects the user voice signal sent by the user, and pre-records the different voice characteristics of each user, so as to pre-store the different voice characteristics of each user in the memory module middle; The voice recognition module is connected to the voice acquisition module and the memory module, and the user voice signal collected by the voice acquisition module is compared with the different voice characteristics of each user pre-stored in the memory module, so as to identify the user corresponding to the current user voice signal; The camera module, when the user chooses to collect the user's facial features by operating the remote control or the function button, collects the user's facial image, and pre-records the different facial features of each user, so as to pre-store the different facial features of each user in the memory module; The face recognition module is connected to the camera module and the memory module, and compares the facial images collected by the camera module with the different facial features of each user pre-stored in the memory module, so as to identify the face currently collected by the camera module the user to whom the image corresponds; The memory module is connected to the voice acquisition module, the voice recognition module, the camera module, and the face recognition module, and stores different voice features of each user and different facial features of each user in advance, so as to be called by the voice recognition module and the face recognition module respectively, The memory module also stores audio files and video files for calling by the display module and the voice playback module respectively; The display module is connected to the memory module to display the video content corresponding to the video file stored in the memory module; The voice playing module is connected to the memory module, and plays the audio content corresponding to the audio file stored in the memory module; The unified signal interface module connects the display module and the voice playback module, uses FPGA chips to realize the connection of external audio and video signals compatible with DVI, HDMI and DisplayPort formats, and forwards the received external audio and video signals to the display module and voice playback module for further processing. The broadcast of audio-video signal, described FPGA chip is the Virtex4 LX25 of Xilinx company; The remote control controls the early childhood education machine under the operation of the user, including turning on and off, selecting the video file to be displayed by the display module, selecting the audio file to be played by the voice playback module, and selecting to receive external audio and video signals from the unified signal interface module , setting the predetermined threshold, setting the volume played by the voice playback module; The function button is used to control the early childhood education machine under the operation of the user, including starting up, shutting down, selecting the video file to be displayed by the display module, selecting the audio file to be played by the voice playback module, and selecting to receive external audio and video signals from the unified signal interface module , setting the predetermined threshold, setting the volume played by the voice playback module; The USB interface is used to connect an external charging device for charging, and is used to connect an external storage device to download audio files and video files selected by the user, and store the downloaded audio files and video files in the memory module; The controller module is connected to the voice recognition module and the face recognition module, to receive the user identified by the voice recognition module or the face recognition module, and start different user modes corresponding to different users; Wherein, the user mode includes a girl mode, a boy mode, and a parent mode, and the voice playback module emits sounds of different characteristics to communicate with the user under different user modes, and the display module displays image backgrounds of different characteristics to communicate with the user under different user modes; Wherein, the voice playback module is left and right speakers, the display module is a liquid crystal display, and the resolution of the liquid crystal display is one of 160×128, 384×320, 640×480 or 1024×600; The wireless communication module is connected with the camera module, so as to wirelessly send the images collected by the camera module to the parent's mobile phone. 2. The multifunctional children's intercom early education machine as claimed in claim 1, characterized in that: The wireless communication module is one of a 3G communication module and a 4G communication module.