Intelligent voice action control equipment
Technical Field
The invention belongs to the field of intelligent control equipment, and particularly relates to intelligent voice action control equipment.
Background
The intelligent voice control is a generally accepted technical field by the public and gradually becomes a consumer product, and such consumer products generally appear in the form of an intelligent sound box, including a remote control unit and a sound box sounding unit, which are mostly integrated. Consumers are generally required to approach to command operations or to improve the speech recognition capabilities of the device, while feedback from the device is more often presented in the form of sound/light/electricity. Another type of intelligent voice control is often in the form of a software controlled system.
Patent No. 201410046639.3 discloses a method for increasing the operation speed of voice recognition in a voice interactive smart home system, which has a self-learning function and saves the programming workload of preset values of various voice use environments at the early stage; and a speech recognition module frequency spectrum analysis method is adopted, and the accuracy of speech recognition is improved. It can be seen that the improved emphasis is on the computing and recognition capabilities of the device.
Patent No. 201510246674.4 discloses a gesture speech recognition's intelligent bracelet, and the user must awaken the bracelet through the gesture, then unlocks the bracelet through speech recognition, could normally work after the unblock, and its interactive system still is the mode of a relatively traditional gesture and pronunciation.
Application No. 201710696616.0 discloses an intelligent sound box, which comprises a so-called split structure, wherein a housing of a first split body is provided with an arc-shaped surface structure; and the movement is arranged on the second component, namely the movement is on the cambered surface structure, and the two are not separated.
Disclosure of Invention
Based on above-mentioned current situation, this application provides an intelligence pronunciation action controlgear, richenes more lively human-computer interaction through dynamic fit sound formation.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows: an intelligent voice action control device comprising: the upper structure body and the lower structure body are arranged, an upper electromagnetic coil group is arranged at the bottom of the upper structure body, and the upper electromagnetic coil group is connected with an upper controller; the top of the lower structural body is provided with a lower electromagnetic coil group, the lower electromagnetic coil group is connected with a lower controller, the upper controller and the lower controller are both connected with a CPU microprocessor, the CPU microprocessor is also connected with a programmer, a memory and a driver, the programmer is also connected with the memory, and the upper structural body and the lower structural body are separably connected through an electromagnetic field repulsive force;
the upper structure body is also provided with: the voice receiving and processing module is used for receiving human voice and carrying out voice search and comprises a power supply control unit, a voice receiving and processing unit and an information output unit;
the lower structure still is equipped with: the intelligent feedback module is a sound box for receiving and processing signals, and comprises a code receiving module, an offset sensor and a sound playing unit.
Preferably, the power control unit comprises a touch key and a sensor;
the voice receiving and processing unit comprises a plurality of microphones and a far-field voice interaction processing chip.
The information output unit is a Wifi/Bluetooth module;
preferably, the code receiving module is used for receiving the instruction of the information output unit;
and the offset sensor is used for detecting the change of the electromagnetic field, correspondingly carrying out current compensation and adjusting the posture of the voice receiving and processing module.
Preferably, the upper electromagnetic coil group is composed of a plurality of electromagnetic coils which are arranged at the bottom of the upper structural body in a surrounding manner; the lower electromagnetic coil group is composed of a plurality of electromagnetic coils which are arranged on the top of the lower structural body in a surrounding manner.
Preferably, the CPU microprocessor controls the current intensity of the upper and lower electromagnetic coil groups through the upper and lower controllers.
Further preferably, the electromagnetic field of the present application is variable, and the switching of the current is controlled by a driver.
Further preferably, the driver controls the intensity conversion of the circuit current to form electromagnetic field variation and simultaneously control the corresponding sound effect.
It is further preferred that a plurality of offset sensors are provided, each offset sensor being connected to a drive.
This application owing to adopt above technical scheme, has following beneficial effect: the invention can convert the machine code into the voice to prompt the electromagnetic field of a plurality of points to change, thereby changing the angle and the posture of the equipment and finally forming a separated intelligent equipment with the action and the sound composite interaction.
Drawings
The invention has the following figures 7:
FIG. 1 is a schematic diagram of an intelligent voice action control device;
FIG. 2 is a partial schematic view of an intelligent voice motion control device;
FIG. 3 is a diagram of the overall control framework;
FIGS. 4-5 are schematic diagrams illustrating the position of the device based on the variation of the electromagnetic field intensity in the embodiment; fig. 6-7 are flow diagrams of methods from voice input to motion control in embodiments.
The sequence numbers in the figures illustrate: 11. the system comprises an upper electromagnetic coil group, 12 an upper controller, 21 a lower electromagnetic coil group, 22 a lower controller, 1 a voice receiving and processing module, 2 a power supply control unit, 3 a voice receiving and processing unit, 4 an information output unit, 5 an upper electromagnetic coil group, 6 an intelligent feedback module, 7 a lower electromagnetic coil group, 8 a code receiving module, 9 an offset sensor and 10 a sound external-playing unit.
Detailed Description
The embodiment provides an intelligent voice action control device which can perform corresponding actions in cooperation with random voice, and performs corresponding action control by grouping, determining meaning and classifying human languages through a database.
According to fig. 1, an intelligent voice action control device comprises: the upper structure body and the lower structure body are arranged, an upper electromagnetic coil group is arranged at the bottom of the upper structure body, and the upper electromagnetic coil group is connected with an upper controller; the top of the lower structural body is provided with a lower electromagnetic coil group, the lower electromagnetic coil group is connected with a lower controller, the upper controller and the lower controller are both connected with a CPU microprocessor, the CPU microprocessor is also connected with a programmer, a memory and a driver, the programmer is also connected with the memory, and the upper structural body and the lower structural body are separably connected through an electromagnetic field repulsive force; the upper structure body is also provided with: the voice receiving and processing module is used for receiving human voice and carrying out voice search and comprises a power supply control unit, a voice receiving and processing unit and an information output unit; the lower structure still is equipped with: the intelligent feedback module is a sound box for receiving and processing signals, and comprises a code receiving module, an offset sensor and a sound playing unit.
According to the illustration of fig. 2, in order to realize the magnetic levitation technology, a plurality of electromagnetic coils are arranged on the bottom surface of the upper structure body and the top surface of the lower structure body in a surrounding manner, and the current with different strengths is controlled by the upper controller and the lower controller, and the strength of the electromagnetic field is controlled by the current with different strengths, so that the corresponding change and adjustment of the posture of the equipment are finally achieved.
According to the structure diagram of the whole control frame shown in fig. 3, different digital controller switches are connected with a programmer, the programmer outputs control instructions after forming machine coding language, the control instructions enter an instant memory or directly enter a CPU microprocessor, and the programmer calculates and outputs the instructions to an upper controller and a lower controller so as to control the current of each electromagnetic coil group and finally form the magnetic field strength change of a local electromagnetic coil group.
However, the simultaneous operation of a plurality of electromagnetic fields inevitably has the problem of electromagnetic superposition, so that the magnetic suspension of the upper structure body is unstable and the upper structure body is easy to fall off in the magnetic field conversion process, a plurality of offset sensors are arranged in the equipment and can detect the change of the electromagnetic fields, when the upper structure body is suspended and deviates from the balance position, the compensation current can be generated immediately, the intensity of the electromagnetic current can be increased after the compensation current flows into the electromagnetic suspension system, and the suspended object can be pulled back to the balance position, so that the purpose of permanent suspension is achieved.
According to the illustrations of fig. 4-5, local variations occur due to the intensity of the electromagnetic field, and such variations are controllable, eventually resulting in corresponding changes and adjustments of the attitude of the upper half of the device as shown. The device has the advantages that the device dynamically cooperates with the sound to form rich and more vivid man-machine interaction and forms a plurality of anthropomorphic expression modes, and the rich expression is achieved through the cooperation of the action and the sound.
For example, fig. 4 shows that the current of the right-side electromagnet assembly increases and the electromagnetic field repulsive force increases, and at the same time, the current of the left-side electromagnet assembly decreases and the electromagnetic field repulsive force decreases and the distance decreases. The superposed value of the magnetic fields is the vector sum of all the magnetic fields in the magnetic fields, and the structural body on the equipment at the moment inclines towards the left side and forms preset interaction.
According to fig. 6, the flow of the speech-to-sound interaction of the present invention is as follows:
(1) the user makes a sound, and the sound is received and processed by the voice receiving and processing unit;
(2) importing the voice into a database and an acoustic library to screen key words and key information;
(3) the screened keywords are led into a CPU (central processing unit) microprocessor, converted into machine codes and output to an intelligent feedback module of the equipment through Wifi/Bluetooth;
(4) the code receiving module receives the machine code, retrieves the related sound file in the network server through the code, and plays the sound file out through the sound playing unit (loudspeaker unit).
Eventually a closed loop of sound-to-sound interaction is formed between the user and the device.
According to FIG. 7, the flow of the speech to action interaction of the present invention is as follows:
(1) the user makes a sound, and the sound is received and processed by the voice receiving and processing unit;
(2) and importing the voice into a database and an acoustic library to screen key words and key information.
(3) The screened keywords are led into a CPU (central processing unit) microprocessor, converted into machine codes and output to an intelligent feedback module of the equipment through Wifi/Bluetooth;
(4) the code receiving module receives machine codes, the drivers generate currents with different strengths, the strengths of electromagnetic fields are controlled through the currents with different strengths, and the integration of electromagnetic field forces of a plurality of points prompts the equipment to form a certain posture.
Eventually a closed loop is formed between the user and the device, where the sound and the action interact.
From the above description, it can be seen that: the invention can convert the machine code into the voice to prompt the electromagnetic field of a plurality of points to change, thereby changing the angle and the posture of the equipment and finally forming a separated intelligent equipment with the action and the sound composite interaction. Those skilled in the art will recognize that: many modifications may be made to the above-described embodiments of the invention within the scope of the inventive concept. It should be understood that: the invention is not intended to be limited to the specific embodiments described, but the scope thereof encompasses all modifications that fall within the scope of the invention as defined by the claims appended hereto.