CN211555461U

CN211555461U - Multi-language translator for gesture recognition and voice picking

Info

Publication number: CN211555461U
Application number: CN201921337563.4U
Authority: CN
Inventors: 陈清宇
Original assignee: Individual
Current assignee: Individual
Priority date: 2019-08-16
Filing date: 2019-08-16
Publication date: 2020-09-22
Anticipated expiration: 2029-08-16

Abstract

A multi-language translator for gesture recognition and voice pickup relates to the technical field of multi-language translation. The intelligent translator comprises a translator shell, a visual sensor, an earphone interface, a charging port, a touch display screen, a switch button, a finger module part, a processor, a voice recognition module, an energy storage device, an operation module, a display module, an analysis comparison module, a voice conversion module, a language database, a gesture database, a voice acquisition module, a voice playing module, a loudspeaker and a communication module, wherein the visual sensor is arranged in the middle of the front end face of the translator shell. After the technical scheme is adopted, the utility model discloses beneficial effect does: the translation device has the advantages of high use value, powerful functions, clear and accurate gesture collection, high voice collection and playing accuracy and real-time data updating, so that translation content accuracy is high, electricity consumption is environment-friendly, usability is high, carrying is convenient, long-time use is realized, operation is simple, humanization is strong, multiple selections are realized, use comfort is high, and the translation device is superior in performance and strong in popularization in the field of the same trip.

Description

Multi-language translator for gesture recognition and voice picking

Technical Field

The utility model relates to a multilingual translation technical field, the multilingual translator of concretely relates to gesture recognition and voice pickup.

Background

At present, in international business conversations, conferees often come from multiple countries under the scenes of meetings and the like, so that a plurality of special interpretation personnel are needed to carry out high-intensity interpretation work. However, this too depends on the professional literacy and energy of the interpreter, and the labor and financial resources are high. In addition, with frequent civil trips such as international travel, the phenomenon of communication anytime and anywhere becomes more obvious.

The multi-language translator for gesture recognition and voice pickup in the current market has the advantages of low use value, weaker functionality, low accuracy of gesture collection and voice collection and playing, difficulty in updating data in real time, great reduction of accuracy of translation contents, no environmental protection in power consumption, weaker usability, inconvenience in carrying, short use time, tedious operability, few humanized settings, low use comfort, lower performance in the field of the same trip and poor popularization.

SUMMERY OF THE UTILITY MODEL

An object of the utility model is to prior art's defect and not enough, provide a multilingual translator that gesture recognition and pronunciation picked up, use value is high, powerful, the gesture is gathered clearly accurately, the broadcast degree of accuracy is high to pronunciation collection, real-time update data for translation content degree of accuracy is high, the power consumption environmental protection, the usability is strong, can conveniently carry, long-time the use, easy operation, humanized strong, select many, use comfort is high, superior and the popularization nature is strong in the field of the same personals.

In order to achieve the above purpose, the utility model adopts the following technical scheme: the intelligent translator comprises a translator shell 1, wherein a vision sensor 2 is arranged in the middle of the front end face of the translator shell 1, an earphone interface 3 and a charging port 4 are respectively arranged on the left side and the right side of the rear end face of the translator shell 1, a touch display screen 5 is arranged in the middle of the upper surface of the translator shell 1, and a switch button 6 is arranged in the middle of the lower end of the upper surface of the translator shell 1; the front end of the upper surface of the translator shell 1 is provided with a solar panel 101, and the solar panel 101 is electrically connected with the energy storage device 10

The lower end of the translator shell 1 is provided with a finger part 7, and the surface of the finger part 7 is provided with a soft layer 71.

The front ends of the left surface and the right surface of the translator shell 1 are respectively provided with a plurality of through holes 011.

The inside voice acquisition module 17 and the speech recognition module 9 that are provided with of translator casing 1, voice acquisition module 17 and speech recognition module 9 are through gathering fidelity module 171 electric connection, and gather fidelity module 171 and set up inside translator casing 1.

The translator shell 1 is internally provided with a voice playing module 18 and a loudspeaker 19, the voice playing module 18, the loudspeaker 19 and the earphone interface 3 are electrically connected through a playing fidelity module 181, and the playing fidelity module 181 is arranged inside the translator shell 1.

The utility model discloses a theory of operation: the processor 8 is used for the operation driving equipment of the multi-language translator, and plays a role of integral operation, the operation module 11 and the display module 12 are matched, so that a user can conveniently select a language to be translated through the touch display screen 5, the humanized setting is strong, the analysis and comparison module 13 analyzes and compares the finger type, the action and the direction of a finger transmitted by the vision sensor 2 with gesture data in the gesture database 16, the voice conversion module 14 carries out language conversion, the voice playing module 18 carries out playing, and finally the voice acquisition module 17 is connected with an earphone through the loudspeaker 19 or the earphone interface 3 for playing and translation, the voice recognition module 9 recognizes the acquired voice, which language is the language, the analysis and comparison module 13 is matched with the language database 15, and the voice conversion module 14 carries out language conversion, and then the voice playing module 18 is used for playing, and finally the voice playing module is connected with the earphone through the loudspeaker 19 or the earphone interface 3 for playing and translating, the energy storage device 10 stores the running electric quantity of the multilingual translator, so that the multilingual translator is convenient to carry and long in service time, and after the multilingual translator is opened through the switch button 6, the communication module 20 is connected with the internet of things in real time to store latest language words and gesture words.

After the technical scheme is adopted, the utility model discloses beneficial effect does: the translation device has the advantages of high use value, powerful functions, clear and accurate gesture collection, high voice collection and playing accuracy and real-time data updating, so that translation content accuracy is high, electricity consumption is environment-friendly, usability is high, carrying is convenient, long-time use is realized, operation is simple, humanization is strong, multiple selections are realized, use comfort is high, and the translation device is superior in performance and strong in popularization in the field of the same trip.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.

Fig. 1 is a schematic structural diagram of the present invention;

FIG. 2 is a front view corresponding to FIG. 1;

FIG. 3 is a rear view corresponding to FIG. 1;

FIG. 4 is a left side view corresponding to FIG. 1;

fig. 5 is a schematic block diagram of the circuit principle of the present invention.

Description of reference numerals: the device comprises a translator shell 1, a visual sensor 2, an earphone interface 3, a charging port 4, a touch display screen 5, a switch button 6, a finger module part 7, a processor 8, a voice recognition module 9, an energy storage device 10, an operation module 11, a display module 12, an analysis comparison module 13, a voice conversion module 14, a language database 15, a gesture database 16, a voice acquisition module 17, a voice playing module 18, a loudspeaker 19, a communication module 20, a soft layer 71, a solar panel 101, a through hole 011, an acquisition fidelity module 171 and a playing fidelity module 181.

Detailed Description

Referring to fig. 1 to 5, the technical solution adopted by the present embodiment is: the intelligent mobile phone translation device comprises a translator shell 1, a vision sensor 2, an earphone interface 3, a charging port 4, a touch display screen 5, a switch button 6, a finger module part 7, a processor 8, a voice recognition module 9, an energy storage device 10, an operation module 11, a display module 12, an analysis comparison module 13, a voice conversion module 14, a language database 15, a gesture database 16, a voice acquisition module 17, a voice playing module 18, a loudspeaker 19 and a communication module 20, wherein the vision sensor 2 is arranged in the middle of the front end face of the translator shell 1, the shape, the size and the material of the translator shell 1 can be selected and set through market research to meet different user requirements, the vision sensor 2 can receive the finger type, the action and the orientation of a finger, the acquisition and the cleaning are accurate, the earphone interface 3 and the charging port 4 are respectively arranged on the left side and the right side of the rear end face of the translator shell 1, the earphone interface 3 is used for being connected with an earphone, when gesture communication is carried out and noise at the side is large, communication can be convenient and fast, the charging port 4 is used for being connected with a household circuit and charging the multi-language translator, the touch display screen 5 is arranged in the middle of the upper surface of the translator shell 1, a user can conveniently operate the multi-language translator by the touch display screen 5, different translation languages can be selected and displayed, the multi-language translator is an LED screen, the switch button 6 is arranged in the middle of the lower end of the upper surface of the translator shell 1 and used for opening or closing the multi-language translator, the multi-language translator is started when being pressed down for the first time and is closed when being pressed down again, the finger module part 7 is arranged at the lower end of the translator shell 1, friction between the user when the user holds the user, the degree of grip is improved, the degree of hand feeling is improved, the processor 8 is arranged inside the translator shell 1, The voice recognition module 9, the energy storage device 10, the operation module 11, the display module 12, the analysis and comparison module 13, the voice conversion module 14, the language database 15, the gesture database 16, the voice acquisition module 17, the voice playing module 18, the loudspeaker 19, the communication module 20, the processor 8 is used for the operation driving equipment of the multi-language translator, and has the function of integral operation, the operation module 11 and the display module 12 are matched, so that a user can select a language to be translated through the touch display screen 5, the humanization setting is strong, the analysis and comparison module 13 analyzes and compares the finger type, the action and the orientation of the finger transmitted by the vision sensor 2 with the gesture data in the gesture database 16, performs language conversion through the voice conversion module 14, performs playing through the voice playing module 18, and finally performs playing and translation through the loudspeaker 19 or the earphone interface 3, the voice collection module 17 is responsible for collecting voice, the voice recognition module 9 recognizes which language is the collected voice, the analysis comparison module 13 is matched with the language database 15, the voice conversion module 14 performs the language conversion, the voice playing module 18 plays the voice, and the voice is finally connected with the earphone through the loudspeaker 19 or the earphone interface 3 for playing and translating, the energy storage device 10 stores the running electric quantity of the multi-language translator, so that the multi-language translator is convenient to carry and has long service time, during the starting period of the multi-language translator, the communication module 20 is connected with the internet of things in real time to store latest words and gesture words for the language, the visual sensor 2, the voice recognition module 9, the switch button 6, the energy storage device 10, the operation module 11, the display module 12, the analysis comparison module 13, the voice conversion module 14 and the language database 15, Gesture database 16 all with treater 8 electric connection, pronunciation collection module 17 and speech recognition module 9 electric connection, mouth 4 and energy memory 10 electric connection charge, operation module 11, display module 12 all with touch display screen 5 electric connection, speaker 19, earphone interface 3, speech conversion module 14 all with pronunciation play module 18 electric connection, language database 15, gesture database 16 all with communication module 20 electric connection, communication module 20 and thing networking communication connection. The position setting of internal part can be based on rationally arranging the overall arrangement for space rational utilization.

The front end of the upper surface of the translator shell 1 is provided with a solar panel 101, and the solar panel 101 is electrically connected with the energy storage device 10. The solar panel 101 can receive the illumination of the sun, so that the multilingual translator has a source of redundant electric quantity, the environment is protected, the energy is saved, and a corresponding conversion device is also arranged between the solar panel 101 and the energy storage device 10, which are the prior art.

The surface of the finger mould part 7 is provided with a soft layer 71. The soft layer 71 is arranged so that the finger mould part 7 is softer in contact with the hand, and the soft layer 71 is made of a breathable material and a warm-keeping material and is selectively arranged according to different requirements.

The front ends of the left surface and the right surface of the translator shell 1 are respectively provided with a plurality of through holes 011. The arrangement of the through holes 011 can improve heat dissipation inside the multilingual translator, prevent the inside of the multilingual translator from operating excessively, and can improve the transmission quality of voice.

Voice acquisition module 17 and voice recognition module 9 are through gathering fidelity module 171 electric connection, and gather fidelity module 171 and set up inside translator casing 1. The quality of voice collection is greatly improved by the collection fidelity module 171, so that translation is more accurate.

The voice playing module 18, the loudspeaker 19 and the earphone interface 3 are electrically connected through the playing fidelity module 181, and the playing fidelity module 181 is arranged inside the translator shell 1. The play fidelity module 181 greatly improves the quality of voice play, improves the answering effect, and makes translation more accurate.

The above description is only for the purpose of illustrating the technical solutions of the present invention and not for the purpose of limiting the same, and other modifications or equivalent replacements made by those of ordinary skill in the art to the technical solutions of the present invention should be covered within the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solutions of the present invention.

Claims

1. A multilingual translator for gesture recognition and voice picking, comprising: the intelligent translator comprises a translator shell (1), wherein a vision sensor (2) is arranged in the middle of the front end face of the translator shell (1), an earphone interface (3) and a charging port (4) are respectively arranged on the left side and the right side of the rear end face of the translator shell (1), a touch display screen (5) is arranged in the middle of the upper surface of the translator shell (1), and a switch button (6) is arranged in the middle of the lower end of the upper surface of the translator shell (1); the solar energy translation device is characterized in that a solar panel (101) is arranged at the front end of the upper surface of the translator shell (1), and the solar panel (101) is electrically connected with the energy storage device (10).

2. The gesture recognition and speech picking multilingual translator of claim 1, wherein: the translator shell is characterized in that a finger mold part (7) is arranged at the lower end of the translator shell (1), and a soft layer (71) is arranged on the surface of the finger mold part (7).

3. The gesture recognition and speech picking multilingual translator of claim 1, wherein: the front ends of the left surface and the right surface of the translator shell (1) are respectively provided with a plurality of through holes (011).

4. The gesture recognition and speech picking multilingual translator of claim 1, wherein: the translator shell is characterized in that a voice acquisition module (17) and a voice recognition module (9) are arranged inside the translator shell (1), the voice acquisition module (17) is electrically connected with the voice recognition module (9) through an acquisition fidelity module (171), and the acquisition fidelity module (171) is arranged inside the translator shell (1).

5. The gesture recognition and speech picking multilingual translator of claim 1, wherein: the translator shell is characterized in that a voice playing module (18) and a loudspeaker (19) are arranged inside the translator shell (1), the voice playing module (18), the loudspeaker (19) and the earphone interface (3) are all electrically connected through a playing fidelity module (181), and the playing fidelity module (181) is arranged inside the translator shell (1).