Disclosure of Invention
The invention aims to provide a wireless interphone with artificial intelligence translation to solve the technical problem.
In order to achieve the above object, the present invention provides a wireless intercom with artificial intelligence translation, comprising:
an interphone body;
the interphone body is provided with a plurality of keys, a display screen and function keys, and the function keys are used for switching an intercom mode and a translation mode;
the display screen is a touch screen, and languages needing translation are set through the touch screen so as to finish translation of specific languages;
the interphone comprises a interphone body, a voice acquisition module and a main control board, wherein the interphone body is internally provided with the main control board which is internally provided with the language switching module and used for switching different foreign languages; the system also comprises a language matching module, a speech acquisition module and a speech processing module, wherein the language matching module acquires a specific certain language according to a certain language requirement, determines whether the specific certain language is matched with a standard language according to real-time output, and acquires corresponding matching degree information T through the speech acquisition module when acquiring real-time language information;
a language matching degree matrix H (Ai, T1, T2, T0) is set in the language matching module, wherein Ai represents a corresponding certain foreign language, T1 represents a first matching degree of a certain language, T2 represents a second matching degree of a certain language, and T0 represents the lowest matching degree of a certain language; and adopting different matching degrees for different languages, and performing translation and communication when the voice transmission meets the preset matching degree.
Further, after the language matching module obtains the matching degree result obtained by the voice module within the preset time T1, if the real-time matching degree T is greater than the first matching degree T1, the language matching module notifies the control module in the main control board to continuously translate and communicate.
Further, if the real-time matching degree T is greater than a second matching degree T2 and less than a first matching degree T1, the control module notifies the voice obtaining module to continue to obtain a matching degree result within a preset time T2, and after the real-time matching degree Ts is obtained, the real-time matching degree is compared with a standard matching degree, wherein the preset time T2 is greater than a preset time T1, and if the real-time matching degree is greater than the first matching degree T1, the language matching module notifies the control module in the main control board to continue translating and communicating; and if the real-time matching degree T is greater than the second matching degree T2 and less than the first matching degree T1, performing communication according to the current matching degree, switching to the talkback mode after continuing to translate for a preset time T0, switching back to the translation mode again, and performing translation matching again.
Further, if the real-time matching degree T is greater than the minimum matching degree T0 and is less than the second matching degree T2, the control module notifies the voice obtaining module to continue to obtain a matching degree result within a preset time T3, and compares the real-time matching degree result with the standard matching degree after obtaining the real-time matching degree Ts, where the preset time T3 is greater than the preset time T2.
Further, if the real-time matching degree is greater than a first matching degree T1, the language matching module informs a control module in the main control board of continuous translation and communication; and if the real-time matching degree T is greater than the second matching degree T2 and less than the first matching degree T1, performing communication according to the current matching degree, switching to the talkback mode after continuing to translate for a preset time T0, switching back to the translation mode again, and performing translation matching again. If the real-time matching degree T is greater than the minimum matching degree T0 and is less than the second matching degree T2, the control module notifies the voice obtaining module to continue obtaining the matching degree result within the preset time T4, and compares the real-time matching degree Ts with the standard matching degree after obtaining the real-time matching degree Ts, and then re-determines the process according to the determination, wherein the preset time T4 is greater than the preset time T3.
Further, if the real-time matching degree is greater than the first matching degree T1 in the re-determination process, the language matching module informs the control module in the main control board of continuous translation and communication; and if the real-time matching degree T is greater than the second matching degree T2 and less than the first matching degree T1, performing communication according to the current matching degree, switching to the talkback mode after continuing to translate for a preset time T0, switching back to the translation mode again, and performing translation matching again. If the real-time matching degree T is greater than the lowest matching degree T0 and less than the second matching degree T2, the translation and the communication are stopped, at the moment, the translation condition cannot meet the enough recognition degree, and the translation is invalid.
Further, if the real-time matching degree T is lower than the minimum matching degree T0, the translation and communication are stopped.
Further, the voice obtaining module obtains the matching degree within the preset time T1, and the process is that firstly, the voice translation information within the preset time T1 is obtained, the voice translation information is compared with the standard voice information to obtain the matching degree of the voice translation information, the real-time sound wave curve d1 is obtained through the voice translation information, the real-time sound wave curve d0 is compared with the standard voice sound wave curve d0, in the comparison process, the number n of overlapping peaks and troughs of the real-time sound wave curve d1 and the standard voice sound wave curve d0 is obtained, and the total number of the peaks and the troughs of the standard voice sound wave curve d0 is divided by the number to obtain the real-time matching degree value T.
Further, when the first matching degree, the second matching degree and the lowest matching degree are set, Z is determined according to the circulation coefficient of each language, the higher the circulation coefficient is, the lower the three standard matching degree standards are set, when the matching degree of the low standard is, a matching degree standard matrix (Ai, T1i, T2i, T0i, Zi) is set, wherein Ai represents a corresponding certain foreign language, T1i represents the first matching degree of the corresponding i-th language, T2i represents the second matching degree of the corresponding i-th language, T0i represents the lowest matching degree of the corresponding i-th language, and Zi represents the circulation coefficient Z of the corresponding i-th language.
Further, the circulation coefficient Z is determined according to the statistics of the number of people using the language, a reference circulation coefficient Z0 is set, a reference number R0 is set, and the circulation coefficient Zi of the ith language is (R0/Ri) x Z0.
Compared with the prior art, the wireless interphone with the artificial intelligent translation has the technical effects that the public network talkback and the artificial intelligent translation are perfectly combined, the requirement of industrial users on the artificial intelligent translation and the talkback such as cross-border logistics, foreign infrastructure projects, visiting and touring companies and the like is met, the artificial intelligent translation software and the public network talkback are combined on a product terminal through the development of the interphone software bottom layer technology, and related keys and product appearances for realizing software requirements are formulated on the terminal development in combination with software.
Particularly, the product disclosed by the invention is beneficial to meeting the requirement of users on the translator in the aspects of cross-border logistics/foreign infrastructure projects/travel industries and the like, wherein the requirement of the cross-border logistics and foreign infrastructure projects on the interphone is just needed.
In particular, the invention sets a language matching degree matrix H (Ai, T1, T2, T0) in a language matching module, wherein Ai represents a corresponding certain foreign language, T1 represents a first matching degree of a certain language, T2 represents a second matching degree of a certain language, and T0 represents the lowest matching degree of a certain language; and adopting different matching degrees for different languages, and performing translation and communication when the voice transmission meets the preset matching degree. After the language matching module obtains the matching degree result obtained by the voice module within the preset time T1, if the real-time matching degree T is greater than the first matching degree T1, the language matching module informs the control module in the main control board to continuously translate and communicate. If the real-time matching degree T is greater than a second matching degree T2 and is less than a first matching degree T1, the control module informs the voice acquisition module to continuously acquire a matching degree result within a preset time T2, and after the real-time matching degree Ts is acquired, the real-time matching degree result is compared with a standard matching degree, wherein the preset time T2 is greater than a preset time T1, and if the real-time matching degree is greater than the first matching degree T1, the language matching module informs the control module in the main control board to continuously translate and communicate; and if the real-time matching degree T is greater than the second matching degree T2 and less than the first matching degree T1, performing communication according to the current matching degree, switching to the talkback mode after continuing to translate for a preset time T0, switching back to the translation mode again, and performing translation matching again. Different translation effects are determined by comparing different matching degree modes of the voice, so that reasonable translation can be realized in various occasions.
Particularly, the invention adopts the circulation coefficient Z to determine the high and low conditions of the matching degree, the higher the circulation coefficient is, the lower the three standard matching degree standards are set, and the matching degree of the low standard is set, so that the interphone meets the use of most people.
Detailed Description
Preferred embodiments of the invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the invention, and do not limit the scope of the invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are only for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Please refer to fig. 1-3, which are schematic front side views of a wireless intercom with artificial intelligence translation according to an embodiment of the present invention; the back structure schematic diagram of the wireless interphone with artificial intelligence translation of the embodiment of the invention; the side structure schematic diagram of the wireless interphone with artificial intelligence translation of the embodiment of the invention; the intercom of this embodiment includes the body the upper end side of body 1 sets up group switch button 2, SOS key 1 and pilot lamp 11, sets up function key 16, PTT key 18 in one side of body 1, volume rising key 31, volume reduction key 32, sets up earphone mouth 12, data transmission/mouthful 13 that charges at the opposite side of body, sets up display screen 17 on the positive upper portion of body 1, and the centre sets up first MIC key 14, and the lower part sets up loudspeaker 15.
Wherein, the second MIC key 41, the camera 42 and the flash 43 are arranged on the upper part of the back of the interphone, which are all designed in a conventional structure.
Specifically, in the embodiment of the present invention, when the function is switched, the function key 16 is used to switch the translation function and the intercom function, when the function needs to be switched, the function key is pressed to switch, in the intercom mode, the intercom is completed through the PTT key, the volume is adjusted through the volume up key 31 and the volume down key 32, after the function key is pressed, the translation mode is switched, the Chinese and foreign language translation is completed through the volume up key 31, the foreign and middle language translation is realized through the volume down key 32, and the voice is played.
Specifically, in the embodiment of the present invention, when the display screen 17 is a touch screen, the language to be translated can be set through the touch screen, so as to complete the translation of the specific language.
Specifically, the hardware structure of the interphone according to the embodiment of the present invention may be a conventional design, or may be a structure as in this embodiment, or other deformed structures, and only needs to be able to switch between the interphone and the translation model.
Fig. 4 is a schematic diagram of an explosion structure of the wireless intercom with artificial intelligence translation according to the embodiment of the present invention; the interphone of the embodiment comprises a lower cover 30 and an upper cover 40 buckled with the lower cover, wherein the display screen 17 which is a touch screen is arranged on the upper part of the upper cover 40; a key button is arranged at the lower part, and an induction board Y1 is arranged at the lower side of the key button and used for inducing key information and sending the information to the main control board; the inner side of the lower cover 30 is provided with a power supply component M1 for supplying power to the circuit board; still be provided with rotary switch subassembly, it includes two step motor M, and step motor M's output is connected with a carousel 21 respectively, step motor, carousel set up respectively at the upper and lower both ends of a backup pad, two the backup pad sets up the inboard at lower cover 30, and is corresponding, and step motor passes through screw P fixed connection with the backup pad. When the rotary table is used, the rotary table is driven to rotate by controlling the stepping motor, so that buttons arranged on the rotary table are switched, the main control panel is communicated with different relays, and then different working modes are switched. A main control board Y2 is arranged on the inner side of the lower cover 30, relays are arranged on the main control board Y2 and used for switching different working modes, and the relays are respectively communicated with control circuits on different main control boards; and a wireless transmission module 10 is also arranged in the lower cover, communicates with a public network in a wireless transmission mode and is fixedly connected with the lower cover through a clamping block Y3.
Referring to fig. 5, it is a logic control block diagram of the wireless intercom with artificial intelligence translation according to the embodiment of the present invention, wherein the control board is connected to a power control board, and the power control board is connected to a driver of the stepping motor, so as to control the start, stop and rotation of the stepping motor; the compiling board is connected with the power control board. The display screen is connected with the main control board through the language selection module, the display screen obtains language library information in the main control board through the language selection module, and the main control board outputs languages through the language selection module; the main control board is respectively connected with the talkback control circuit and the translation control circuit, the two circuits are respectively connected with the relay set, and the relay set is connected with the stepping motor so as to realize the control of software on hardware.
Specifically, the embodiment of the invention can switch and translate multiple languages, the main control board is internally provided with a language switching module for switching different foreign languages, and the main control board further comprises a voice acquisition module for acquiring translated voice within preset time after switching, comparing the voice with pre-stored standard voice data and determining whether the voice accords with a certain selected language; the system also comprises a language matching module which acquires a specific certain language according to a certain language requirement, determines whether the specific certain language is matched with a standard language according to the specific certain language output in real time, and acquires corresponding matching degree information T through the voice acquisition module when acquiring real-time language information.
Specifically, a language matching degree matrix H (Ai, T1, T2, T0) is set in the language matching module, where Ai represents a corresponding certain foreign language, for example, a1 represents english, a2 represents french, A3 represents german, a4 represents japanese, and so on, and the language type of the embodiment stores a corresponding breeding language database according to real-time requirements; t1 denotes a first degree of matching in a certain language, T2 denotes a second degree of matching in a certain language, and T0 denotes a minimum degree of matching in a certain language. For example, the first matching degree is 90%, the second matching degree is 80% and the lowest matching degree is 70% in English; for French, the first matching degree is 95%, the second matching degree is 85%, and the lowest matching degree is 75%. Different matching degrees are set for different languages, so that a user can clearly acquire language information, and can finish conversion of different languages and accurately acquire information on the premise of reducing equipment and program requirements as much as possible.
Specifically, after the language matching module obtains a matching degree result obtained by the voice module within a preset time T1, if the real-time matching degree T is greater than a first matching degree T1, the language matching module notifies the control module in the main control board to continuously translate and communicate; if the real-time matching degree T is greater than the second matching degree T2 and less than the first matching degree T1, the control module informs the voice acquisition module to continuously acquire a matching degree result within a preset time T2, and compares the real-time matching degree Ts with a standard matching degree after acquiring the real-time matching degree, wherein the preset time T2 is greater than a preset time T1, and if the real-time matching degree is greater than the first matching degree T1, the language matching module informs the control module in the main control board to continuously translate and communicate; and if the real-time matching degree T is greater than the second matching degree T2 and less than the first matching degree T1, performing communication according to the current matching degree, switching to the talkback mode after continuing to translate for a preset time T0, switching back to the translation mode again, and performing translation matching again.
Specifically, if the real-time matching degree T is greater than the minimum matching degree T0 and is less than the second matching degree T2, the control module notifies the voice obtaining module to continue to obtain a matching degree result within a preset time T3, and after the real-time matching degree Ts is obtained, the real-time matching degree result is compared with a standard matching degree, wherein the preset time T3 is greater than a preset time T2, and if the real-time matching degree is greater than the first matching degree T1, the language matching module notifies the control module in the main control board to continue to translate and communicate; and if the real-time matching degree T is greater than the second matching degree T2 and less than the first matching degree T1, performing communication according to the current matching degree, switching to the talkback mode after continuing to translate for a preset time T0, switching back to the translation mode again, and performing translation matching again. If the real-time matching degree T is greater than the lowest matching degree T0 and is less than the second matching degree T2, the control module informs the voice acquisition module to continuously acquire a matching degree result within preset time T4, compares the real-time matching degree Ts with the standard matching degree after the real-time matching degree is acquired, and continues the judging process, wherein the preset time T4 is greater than the preset time T3, and if the real-time matching degree is greater than the first matching degree T1, the language matching module informs the control module in the main control board to continuously translate and communicate; and if the real-time matching degree T is greater than the second matching degree T2 and less than the first matching degree T1, performing communication according to the current matching degree, switching to the talkback mode after continuing to translate for a preset time T0, switching back to the translation mode again, and performing translation matching again. If the real-time matching degree T is greater than the lowest matching degree T0 and less than the second matching degree T2, the translation and the communication are stopped, at the moment, the translation condition cannot meet the enough recognition degree, and the translation is invalid.
Specifically, if the real-time matching degree T is lower than the minimum matching degree T0, the translation and communication are stopped, at this time, the translation condition cannot meet the sufficient identification degree, the translation fails, the interphone is switched to the talkback mode for the preset time T5, then the interphone is switched to the translation mode, and the language matching is continued.
Specifically, the voice obtaining module of the embodiment of the present invention obtains the matching degree within the preset time T1, and the process is to first obtain the voice translation information within the preset time T1, and compare the voice translation information with the standard voice information to obtain the matching degree thereof, in this embodiment, the voice translation information obtains the real-time acoustic wave curve d1, and compares the real-time acoustic wave curve d1 with the standard voice acoustic wave curve d0, and in the comparison process, the number n of overlapping peaks and troughs of the real-time acoustic wave curve d1 and the standard voice acoustic wave curve d0 is obtained, and is divided by the total number of peaks and troughs of the standard voice acoustic wave curve d0 to obtain the real-time matching degree value T. Certainly, the sound information is compared with the sound wave curve, or the sound information can be converted into a digital format, a real-time two-dimensional code sequence E1 and a standard voice information two-dimensional code sequence E0 are obtained, the real-time two-dimensional code sequence is compared with the standard voice information two-dimensional code sequence, the number m of repeated digits is determined, and the total number m0 of the digits of the standard voice information two-dimensional code sequence is divided by the real-time matching value T.
Specifically, when the first matching degree, the second matching degree, and the minimum matching degree are set, Z is determined according to the circulation coefficient of each language, the higher the circulation coefficient is, the lower the three standard matching degree standards are set, and at a low standard matching degree, the user can easily and accurately receive the speech translation information, and at a high standard matching degree, the user can receive the speech information according to a smooth standard. In the present embodiment, a matching degree criterion matrix (Ai, T1i, T2i, T0i, Zi) is set, where Ai represents a corresponding certain foreign language, for example, a1 represents english, a2 represents french, A3 represents german, a4 represents japanese, and so on, T1i represents a first matching degree of a corresponding i-th language, T2i represents a second matching degree of a corresponding i-th language, T0i represents a lowest matching degree of a corresponding i-th language, and Zi represents a flow coefficient Z of the corresponding i-th language.
Specifically, the circulation coefficient Z of the language in the present embodiment is determined by counting the number of persons using the language, a reference circulation coefficient Z0 is set, a reference number of persons R0 is set, for example, 5 hundred million, and the number of persons using a certain language Ri, the circulation coefficient Zi of the ith language is (R0/Ri) x Z0, and the circulation coefficient Z0 is set to 0.5.
Then set T1i ═ Ti x Zi
Ti represents a preset matching degree of a certain preset language, such as setting to 0.96;
T2i=T1i x 0.92
T0i=T2i x 0.92
t1i represents a first degree of matching of the corresponding i-th language, T2i represents a second degree of matching of the corresponding i-th language, and T0i represents a lowest degree of matching of the corresponding i-th language.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.