WO2020057040A1 - 蓝牙翻译机、蓝牙翻译的交互方法及其装置 - Google Patents

蓝牙翻译机、蓝牙翻译的交互方法及其装置 Download PDF

Info

Publication number
WO2020057040A1
WO2020057040A1 PCT/CN2019/073760 CN2019073760W WO2020057040A1 WO 2020057040 A1 WO2020057040 A1 WO 2020057040A1 CN 2019073760 W CN2019073760 W CN 2019073760W WO 2020057040 A1 WO2020057040 A1 WO 2020057040A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice information
bluetooth
voice
mobile terminal
deletion
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2019/073760
Other languages
English (en)
French (fr)
Inventor
陈良辉
王文祺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Water World Co Ltd
Original Assignee
Shenzhen Water World Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Water World Co Ltd filed Critical Shenzhen Water World Co Ltd
Publication of WO2020057040A1 publication Critical patent/WO2020057040A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/005—Language recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication

Definitions

  • the present application relates to the technical field of translators, and in particular, to a Bluetooth translator, an interaction method for a Bluetooth translator, and a device thereof.
  • the purpose of this application is to solve the technical problems that the user starts to speak before the translator is connected to the mobile terminal, causing some voices to be lost and the translation to be incomplete, and the translation voice buffer being too large to cause the translator to fail to translate, and to provide a Bluetooth Interactive method and device for translation.
  • This application provides an interactive method for Bluetooth translation, including:
  • the second voice information is voice information obtained by translating and converting the first voice information.
  • the method includes:
  • Deleting the first voice information and the second voice information according to the first delete instruction, and sending the first delete instruction to the mobile terminal to delete the first voice saved by the mobile terminal The information and the second voice information are deleted.
  • the step of outputting the second voice information according to a first preset rule includes:
  • Generate a delimiter Generate a delimiter, generate a delimiter based on a semantic analysis result of the second voice information, and insert the delimiter into the second voice text.
  • the method includes:
  • the method includes:
  • the deletion information including at least one of voice-activated deletion information, button-activated deletion information, or touch-activated deletion information.
  • the method includes:
  • Scan at least one first Bluetooth signal around, the first Bluetooth signal is sent by a mobile terminal, and one of the mobile terminals corresponds to one of the first Bluetooth signal;
  • the mobile terminal corresponding to the designated first Bluetooth signal establishes a wireless connection.
  • the method includes:
  • This application proposes an interactive device for Bluetooth translation, including:
  • a first receiving unit configured to receive first voice information input by a user, and analyze a buffer occupation amount of the first voice information
  • a cache judging unit configured to judge whether the cache occupation amount is greater than a preset cache value
  • a sending unit configured to send the first voice information to a pre-associated mobile terminal if it is greater than
  • a second receiving unit is configured to receive second voice information returned by the mobile terminal, where the second voice information is voice information obtained by translating and converting the first voice information.
  • the interactive device for Bluetooth translation further includes:
  • a first output unit configured to output second voice information according to a first preset rule
  • a first instruction deletion unit configured to generate a first deletion instruction
  • a first deleting unit configured to delete the first voice information and the second voice information according to the first delete instruction, and send the first delete instruction to the mobile terminal to delete the mobile terminal
  • the saved first voice information and the second voice information are deleted.
  • the first output unit of the interactive device for Bluetooth translation includes:
  • a text creation module configured to perform semantic analysis on the second voice information to obtain a second voice text
  • a delimiter module configured to generate a delimiter based on a semantic analysis result of the second voice information, and insert the delimiter into the second voice text.
  • the interactive device for Bluetooth translation further includes:
  • a server sending unit configured to send the first voice message to the server if it is less than
  • a server return unit configured to receive third voice information returned by the server output, where the third voice information is voice information obtained by translating and converting the first voice information;
  • a second output unit configured to output the third voice information according to a second preset rule
  • a second instruction deletion unit configured to generate a second deletion instruction
  • a second deleting unit is configured to delete the first voice information and the third voice information according to the second delete instruction.
  • the interactive device for Bluetooth translation further includes:
  • the deletion activation unit is configured to receive deletion information input by a user, where the deletion information includes at least one of a voice activation deletion information, a button activation deletion information, or a touch activation deletion information.
  • the interactive device for Bluetooth translation further includes:
  • a scanning unit configured to scan at least one first Bluetooth signal around the first Bluetooth signal sent by a mobile terminal, and one of the mobile terminals corresponds to one of the first Bluetooth signal;
  • An output unit for outputting a second Bluetooth signal, and filtering a designated first Bluetooth signal that is mutually recognized with the second Bluetooth signal from at least one of the first Bluetooth signals according to a handshake protocol;
  • the connection unit is configured to establish a wireless connection with the mobile terminal corresponding to the designated first Bluetooth signal.
  • the interactive device for Bluetooth translation further includes:
  • the reminder output unit is configured to output the reminder signal to remind the user to input the first voice information.
  • the application also provides a Bluetooth translator, including a memory, a processor, and at least one application program stored in the memory and configured to be executed by the processor, the application program being configured to execute the foregoing.
  • a Bluetooth translator including a memory, a processor, and at least one application program stored in the memory and configured to be executed by the processor, the application program being configured to execute the foregoing.
  • the Bluetooth translator receives the first voice information input by the user and analyzes the buffer occupancy of the first voice information; determines whether the buffer occupancy is greater than a preset buffer value; if it is greater than that, it sends the first voice information to the pre-associated mobile Terminal; receiving the second voice information returned by the mobile terminal, and the second voice information is the voice information obtained by translating and converting the first voice information; thereby solving the problem that the user starts to speak without the translator connected to the mobile terminal, resulting in partial
  • the technical problem is that the speech is lost and the translation is incomplete, and the translation voice buffer is too large, which makes the translator unable to translate.
  • FIG. 1 is a schematic flowchart of an interaction method for Bluetooth translation provided by this application
  • FIG. 2 is a structural block diagram of a Bluetooth translation interactive device provided by the present application.
  • FIG. 3 is a structural block diagram of a Bluetooth translator provided by the present application.
  • a schematic flowchart of an interaction method for Bluetooth translation includes:
  • Step S1 receiving first voice information input by a user, and analyzing a buffer occupation amount of the first voice information
  • Step S2 determine whether the cache occupancy is greater than a preset cache value
  • Step S3 if it is greater than, sending the first voice message to the pre-associated mobile terminal;
  • Step S4 Receive second voice information returned by the mobile terminal, where the second voice information is voice information obtained by translation and conversion of the first voice information;
  • the Bluetooth translator receives the first voice information input by the user.
  • the first voice information is the voice to be translated, which can be Chinese, English, French, and other countries.
  • Voice the Bluetooth translator obtains the recording duration used by the user to input the first voice information, and identifies the valid duration of the first voice information in the recording duration according to a preset decibel rule, and deletes the recording duration other than the valid duration to retain the recorded first
  • the effective duration of a voice message is to reduce the effect of buffering.
  • the user turns on a Bluetooth translator for translation.
  • the user inputs the first voice information to the Bluetooth translator, and the process of inputting the first voice information is the recording duration.
  • the first voice information is not recorded during a part of the recording duration, which results in the occupation of redundant buffers. Therefore, the first voice information is identified by a preset decibel rule, and the recording duration with the first voice information is recognized as a valid duration.
  • the recording duration without the first voice information is the duration to be deleted.
  • the time to be deleted is to reduce the input of each first voice message to the buffer of the Bluetooth translator.
  • the process of identifying the first voice message by a preset decibel rule is whether the volume value of the first voice message reaches or exceeds the decibel threshold. Or if it exceeds, the recording duration of the first voice information is retained, and the preferred decibel threshold is 40 decibels.
  • the buffer occupancy of the retained first voice information Analyzes the buffer occupancy of the retained first voice information to determine whether the buffer occupancy is greater than a preset cache value, where the cache occupancy is the amount of cache required to record the first voice information, and the preset cache value is in Bluetooth
  • the preset cache threshold in the translator the preferred cache threshold is 5Mbyte; it can be known from the above step S3 that if it is determined that the buffer occupation of the first voice information is greater than the cache threshold of the Bluetooth translator, the first voice information is sent to the pre-association Mobile terminal translates the voice information based on the server, the mobile terminal receives the first voice information sent by the Bluetooth translator, the mobile terminal sends the first voice information to the server for translation, and the server translates the first voice information into the second voice Information to achieve the translation effect, the server sends the second voice message to the mobile terminal, the mobile terminal receives the second voice message and sends it to the Bluetooth translator, and completes the translation process of the Bluetooth translator; from the perspective of solving technical problems, the user inputs Long-sentence speech, or
  • step S4 of receiving the second voice information returned by the mobile terminal the method includes:
  • S41 Output second voice information according to a first preset rule.
  • the server translates the first voice information into second voice information, the server sends the second voice message to the mobile terminal, and then the mobile terminal sends the second voice message to the Bluetooth translator, so the purpose of step S41 is Bluetooth translation
  • the machine outputs the second voice information.
  • the first preset rule is a way to output the second voice information.
  • the method may be a, the second voice information is output through the text on the display screen, and b, the second voice is output through the broadcast.
  • Mode a analysis Semantics of the second speech information, arrange the second speech text corresponding to the second speech information to the display screen of the Bluetooth translator, generate a separator based on the semantics, and insert the separator into the second speech text.
  • Method b The Bluetooth translator plays the second voice message.
  • the Bluetooth translator displays the second voice text through the display screen and plays the second voice information.
  • step S41 of outputting the second voice information according to the first preset rule the method includes:
  • S43 Delete the first voice information and the second voice information according to the first delete instruction, and send a first delete instruction to the mobile terminal to delete the first voice information and the second voice information saved by the mobile terminal to clear the cache.
  • This step is a step after the above-mentioned Bluetooth translator outputs the second voice information according to the first preset rule.
  • the purpose of this step is to translate the first voice information, and the Bluetooth translator and the mobile terminal will record the first voice information and The effective duration is to delete the first voice message and the effective duration to reduce the buffer of the Bluetooth translator and the mobile terminal. Therefore, this step is proposed.
  • the Bluetooth translator After the preset time of the Bluetooth translator to output the second voice information, The Bluetooth translator generates a first delete instruction, and deletes the first voice information and the second voice information retained by the Bluetooth translator through the first delete instruction.
  • the Bluetooth translator sends the first delete instruction to the mobile terminal, and the mobile terminal passes the first delete instruction.
  • the retained first voice information and the second voice information are deleted to achieve the effect of clearing the buffer of the Bluetooth translator and the mobile terminal.
  • the preset time is preferably 5 minutes.
  • step S2 of determining whether the cache occupancy is greater than a preset cache value the method includes:
  • S22 Receive the third voice information returned by the server, and the third voice information is the voice information obtained by the first voice information through translation and conversion;
  • S23 Output third voice information according to a second preset rule.
  • the Bluetooth translator determines that the first voice information input by the user is a short sentence voice, the Bluetooth translator directly sends the first voice information to the server, and the server translates the first voice information into the third voice information
  • the third voice message and the second voice message are both translated and generated by the server.
  • the difference between the third voice message and the second voice message is because the starting point of the first voice message sent to the server is different.
  • the Bluetooth translator directly sends the first voice information to the server and translates the generated voice information
  • the second voice information is the Bluetooth translator to send the first voice information to the mobile terminal, and then the mobile terminal sends the translated voice information to the server.
  • the second preset rule is the way that the Bluetooth translator outputs the third voice information.
  • the second preset rule is the same as the first preset rule.
  • the first and second distinctions between the Bluetooth translator and the second voice information are output.
  • Third voice message is the way that the Bluetooth translator outputs the third voice information.
  • step S23 of outputting the third voice information according to the second preset rule the method includes:
  • This embodiment is a step performed after the Bluetooth translator outputs the third voice message in step S23.
  • the preset time is preferably 5 minutes to clear the cache of the Bluetooth translator; the Bluetooth translator according to the third preset
  • the rule generates a second delete instruction
  • the third preset rule is a method of generating a second delete instruction.
  • the method is as follows: a. Receive deletion information input by the user.
  • the deletion information includes voice-activated deletion, button-enabled deletion, and touch-enabled deletion.
  • the deletion information generates a second deletion instruction.
  • the voice-activated deletion is that the user inputs a preset deletion voice into the Bluetooth translator, and determines whether the deletion voice input by the user to the Bluetooth translator is similar to the preset deletion voice.
  • the second delete instruction is generated according to the deleted voice;
  • the button to initiate the deletion is that the user presses the designated button on the Bluetooth translator, thereby starting the function of clearing the cache, receiving the button deletion information input by the user, and generating the second deletion according to the button deletion information Instruction;
  • touch start to delete is a display set outside the Bluetooth translator, The display screen receives the touch delete information input by the user to generate a second delete instruction, and receives the touch delete instruction input by the user to verify whether the touch stripe matches the preset stripe. If it matches, a second delete instruction is generated, which needs to be explained.
  • the touch stripe can be the user's fingerprint or other parts of the body, such as the forehead. People have unique personal stripes. The user can set the stripe on the Bluetooth translator in advance.
  • the stripe can generate a second delete instruction. This process is used in the scene. When the user has dirty hands, hands with water, and hands with oil, the fingerprints entered by the user are not easy to be identified, so other body parts can be entered to achieve the identification function. , And a second delete instruction is generated to delete the first voice information and the third voice information to clear the cache of the Bluetooth translator.
  • step S1 of receiving the first voice information input by the user the method includes:
  • S101 scan at least one first Bluetooth signal around, the first Bluetooth signal is sent by a mobile terminal, and one of the mobile terminals corresponds to one first Bluetooth signal;
  • S102 output a second Bluetooth signal, and select a designated first Bluetooth signal that is mutually recognized by the second Bluetooth signal from at least one first Bluetooth signal according to a handshake protocol;
  • S103 The mobile terminal corresponding to the designated first Bluetooth signal establishes a wireless connection.
  • This embodiment is a connection process between a Bluetooth translator and a mobile terminal.
  • the Bluetooth translator outputs a second Bluetooth signal, and the second Bluetooth signal and the first Bluetooth signal output by the pre-associated mobile terminal perform handshake recognition.
  • the mobile terminal establishes a wireless connection. It can be understood that the wireless connection includes a Bluetooth connection and a WIFI connection.
  • step S103 of establishing a wireless connection according to the mobile terminal corresponding to the designated first Bluetooth signal the method includes:
  • S105 Output a reminder signal to remind the user to input the first voice information.
  • the reminder signal is a signal generated to remind the user that the Bluetooth translator and the mobile terminal have established a wireless connection.
  • the purpose is to prevent the user from starting to speak when the Bluetooth translator is not connected to the mobile terminal, resulting in some voice loss and incomplete translation.
  • the Bluetooth translator includes a display screen and a broadcasting device, so the reminder signal is output through the display screen and the broadcasting device.
  • the steps of outputting the reminder signal by the display screen include: a.
  • the full screen display is green, which is to remind the user to move The terminal has established a wireless connection with the Bluetooth translator.
  • the full-screen display is yellow, which reminds the user that the mobile terminal and the Bluetooth translator are establishing a wireless connection. C.
  • the full-screen display is red, which reminds the user that the mobile terminal and the Bluetooth translator.
  • the machine cannot establish a wireless connection.
  • the reason for the failure to establish a wireless connection is that the power of the Bluetooth translator is insufficient, the motherboard of the Bluetooth translator is damaged, etc .; the broadcasting device directly outputs a reminder signal.
  • a structural block diagram of a Bluetooth translation interactive device provided by this application includes:
  • a first receiving unit 4 configured to receive first voice information input by a user, and analyze a buffer occupation amount of the first voice information
  • the cache judging unit 5 is configured to judge whether the cache occupation amount is greater than a preset cache value
  • the sending unit 6 is configured to send the first voice information to the pre-associated mobile terminal if it is greater than;
  • the second receiving unit 7 is configured to receive second voice information returned by the mobile terminal, where the second voice information is voice information obtained by translation and conversion of the first voice information.
  • the Bluetooth translator receives the first voice information input by the user through the first receiving unit 4.
  • the first voice information is a voice to be translated, and can be a multi-national voice such as Chinese, English, French, and the like.
  • the recorded recording time is identified according to a preset decibel rule.
  • the effective time of the first voice information in the recording time is identified, and the recording time other than the effective time is deleted to retain the effective time of the recording of the first voice information, thereby reducing the cache effect.
  • the user turns on the Bluetooth translator for translation.
  • the user enters the first voice information into the Bluetooth translator, and the process time of inputting the first voice information is the recording duration. It can be seen that the first voice information is not recorded in part of the recording duration.
  • the first voice information is identified through a preset decibel rule, and the recording duration with the first voice information is recognized as the effective duration, while the recording duration without the first voice information is the duration to be deleted , Delete the length of time to be deleted, to reduce the input of each first voice message to the blue
  • the process of identifying the first voice information by a preset decibel rule is whether the volume value of the first voice information reaches or exceeds the decibel threshold, and if it reaches or exceeds, the recording time of the first voice information is retained, preferably The decibel threshold is 40 dB.
  • the buffering value is a preset buffering threshold in the Bluetooth translator.
  • the preferred buffering threshold is 5Mbyte. If it is determined that the buffer occupation of the first voice message is greater than the buffering threshold of the Bluetooth translator, the first voice message is sent by the sending unit 6.
  • the voice information is translated based on the server, the mobile terminal receives the first voice information sent by the Bluetooth translator, the mobile terminal sends the first voice information to the server for translation, and the server translates the first voice information into The second voice information to achieve the translation effect, the server sends the second voice information to the mobile terminal, the mobile terminal receives the second voice information and sends it to the Bluetooth translator, and the Bluetooth translator receives the second voice information through the second receiving unit 7, And complete the translation process of the Bluetooth translator; in terms of solving technical problems
  • the user enters long-sentence speech, or difficult speech that is too long and interrupts the input process to the Bluetooth translator.
  • the Bluetooth translator deletes the excess to-be-deleted duration to reduce the cache of difficult speech. The subsequent steps are the same as above, so I will not repeat them.
  • the translator translates difficult speech, which significantly improves the translation performance of the Bluetooth translator.
  • the interactive device for Bluetooth translation further includes:
  • the scanning unit 1 is configured to scan at least one first Bluetooth signal around the first Bluetooth signal sent by a mobile terminal, where one mobile terminal corresponds to one first Bluetooth signal;
  • An output unit 2 for outputting a second Bluetooth signal, and filtering a designated first Bluetooth signal that is mutually recognized by the second Bluetooth signal from at least one first Bluetooth signal according to a handshake protocol;
  • the connection unit 3 is configured to establish a wireless connection with a mobile terminal corresponding to a designated first Bluetooth signal.
  • the Bluetooth translator outputs a second Bluetooth signal through the output unit 2.
  • the second Bluetooth signal performs handshake identification with the first Bluetooth signal output by the pre-associated mobile terminal. If the identification is confirmed, a wireless connection is established between the Bluetooth translator and the mobile terminal through the connection unit 3. It can be understood that the wireless connection includes a Bluetooth connection and a WIFI connection.
  • the interactive device for Bluetooth translation further includes:
  • the first output unit 8 is configured to output second voice information according to a first preset rule.
  • the server translates the first voice information into second voice information, the server sends the second voice information to the mobile terminal, and then the mobile terminal sends the second voice information to the Bluetooth translator; the purpose is that the Bluetooth translator outputs the second Voice information.
  • the first output unit 8 outputs second voice information according to a first preset rule.
  • the output mode is a, the second voice information is output through the text on the display screen, and the b and the second voice are output through the broadcast.
  • a. Analyze the semantics of the second speech information, arrange the second speech text corresponding to the second speech information to the display screen of the Bluetooth translator, generate a separator based on the semantics, and insert the separator into the second speech text.
  • Method b The Bluetooth translator plays the second voice message.
  • the Bluetooth translator displays the second voice text through the display screen and plays the second voice information.
  • the interactive device for Bluetooth translation further includes:
  • a first instruction deletion unit 9 configured to generate a first deletion instruction
  • the first deleting unit 10 is configured to delete the first voice information and the second voice information according to the first delete instruction, and send a first delete instruction to the mobile terminal to delete the first voice information and the second voice information stored in the mobile terminal. To clear the cache.
  • the Bluetooth translator and the mobile terminal will record the first voice information and its effective duration, in order to delete the first voice information and its effective duration to reduce the Bluetooth translator.
  • the Bluetooth translator With the mobile terminal's cache, after a preset time when the Bluetooth translator outputs the second voice message, the Bluetooth translator generates a first deletion instruction through the first instruction deletion unit 9, and deletes the Bluetooth according to the first deletion instruction through the first deletion unit 10.
  • the first voice information and the second voice information retained by the translator the Bluetooth translator sends a first delete instruction to the mobile terminal, and the mobile terminal deletes the retained first voice information and second voice information through the first delete instruction, and reaches
  • the above preset time is preferably 5 minutes.
  • the interactive device for Bluetooth translation further includes:
  • the server sending unit 11 is configured to send the first voice information to the server if it is less than, and the third voice information is voice information obtained by translation and conversion of the first voice information;
  • the server return unit 12 is configured to receive the third voice information returned by the server output
  • the second output unit 13 is configured to output third voice information according to a second preset rule.
  • the Bluetooth translator determines that the first voice information input by the user is a short sentence voice, the Bluetooth translator sends the first voice information to the server through the server sending unit 11, and the server translates the first voice information into The third voice message needs to be explained.
  • the third voice message and the second voice message are both translated voice messages generated by the server. The difference between the third voice message and the second voice message is because the starting point of the first voice message sent to the server is different.
  • the voice message is translated by the Bluetooth translator directly sending the first voice message to the server, and the second voice message is sent by the Bluetooth translator to the mobile terminal, which is then translated by the mobile terminal to the server.
  • the generated voice information; the above-mentioned second preset rule is the way in which the Bluetooth translator outputs the third voice information.
  • the second preset rule is the same as the above-mentioned first preset rule.
  • the Bluetooth translator is distinguished by the first and second output.
  • the second voice information and the third voice information are the same as the above-mentioned first preset rule.
  • the interactive device for Bluetooth translation further includes:
  • a second instruction deletion unit 14 configured to generate a second deletion instruction
  • the second deleting unit 15 is configured to delete the first voice information and the third voice information according to the second delete instruction to clear the cache.
  • the Bluetooth translator generates a second deletion instruction according to a third preset rule through the second instruction deletion unit 14.
  • the third preset rule is a method for generating the second deletion instruction.
  • the method is as follows: a. Receive the deletion information input by the user, and delete The information includes voice-activated delete, button-activated delete, and touch-activated delete; a second delete instruction is generated according to the delete information; wherein the voice-activated delete is a user inputting a preset delete voice into the Bluetooth translator, and judging whether the user enters the Bluetooth translator Whether the voice is similar to the preset delete voice. If the similarity is high, a second delete instruction is generated according to the deleted voice.
  • the button to start the delete is that the user presses the designated button to the Bluetooth translator to start the function of clearing the cache and receiving.
  • the button delete information entered by the user generates a second delete instruction according to the button delete information;
  • a touch start delete is a display screen provided outside the Bluetooth translator, and the display screen receives the touch delete information entered by the user to generate a second delete instruction and receive user input Touch delete command to verify that the touch stripe is If the stripes match, a second delete command is generated.
  • the touch stripes can be user fingerprints or other parts of the body, such as foreheads. People have unique personal stripes. Users can use the Bluetooth translator in advance. Set the stripe. When the cache of the Bluetooth translator needs to be cleared, the user enters the preset stripe to generate a second delete instruction.
  • This process is used in scenarios where the user has dirty hands, hands with water, and hands with oil.
  • the input fingerprint is not easy to be identified, so other body parts can be input to achieve recognition, and a second deletion instruction is generated to delete the first voice information and the third voice information through the second deletion unit 15 to clean up the Bluetooth translator. Cache.
  • the interactive device for Bluetooth translation further includes:
  • the reminder unit 17 is configured to output a reminder signal to remind the user to input the first voice information.
  • the reminder signal is a signal generated to remind the user that the Bluetooth translator and the mobile terminal have established a wireless connection.
  • the purpose is to prevent the user from starting to speak when the Bluetooth translator is not connected to the mobile terminal, resulting in some voice loss and incomplete translation.
  • the Bluetooth translator includes a display screen and a broadcasting device, so the reminder signal is output through the display screen and the broadcasting device.
  • the steps of outputting the reminder signal by the display screen include: a.
  • the full screen display is green, which is to remind the user to move The terminal has established a wireless connection with the Bluetooth translator.
  • the full-screen display is yellow, which reminds the user that the mobile terminal and the Bluetooth translator are establishing a wireless connection. C.
  • the full-screen display is red, which reminds the user that the mobile terminal and the Bluetooth translator.
  • the machine cannot establish a wireless connection.
  • the reason for the failure to establish a wireless connection is that the power of the Bluetooth translator is insufficient, the motherboard of the Bluetooth translator is damaged, etc .; the broadcasting device directly outputs a reminder signal.
  • the Bluetooth translator 100 includes a memory 200, a processor 400, and at least one stored in the memory 200 and configured to be processed by the processor 400
  • An executed application program 300 configured to perform an interactive method of Bluetooth translation in any one of the above embodiments.
  • Bluetooth translator 100 described in this application and the above-mentioned devices used to perform one or more of the methods described in this application. These devices may be specially designed and manufactured for the required purpose, or they may include known devices in general-purpose computers. These devices have application programs 300 stored therein, which computer programs are selectively activated or reconfigured.
  • Such a computer program may be stored in a device (eg, a computer) readable medium or in any type of medium suitable for storing electronic instructions and coupled to a bus, respectively, including but not limited to any Types of disks (including floppy disks, hard disks, CD-ROMs, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory, read-only memory), and RAM (Random Access Memory (random memory), EPROM (Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or optical card. That is, a readable medium includes any medium that stores or transfers information in a readable form by a device (eg, a computer).
  • a readable medium includes any medium that stores or transfers information in a readable form by a device (eg, a computer).

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Telephonic Communication Services (AREA)
  • Machine Translation (AREA)

Abstract

本申请提供一种蓝牙翻译机、蓝牙翻译的交互方法及其装置，包括接收用户输入的第一语音信息，分析第一语音信息的缓存占用量；判断缓存占用量是否大于缓存值；若大于，则发送第一语音信息至移动终端；接收移动终端输出的第二语音信息，从而翻译语音缓存占用过大而导致翻译机无法翻译的技术问题。

Description

蓝牙翻译机、蓝牙翻译的交互方法及其装置 技术领域
本申请涉及翻译机技术领域，特别涉及为一种蓝牙翻译机、蓝牙翻译的交互方法及其装置。
 背景技术
随着世界经济的快速发展，国际间的交流在不断增多，不同国家之间人与人的交往国外旅游、探亲等也很频繁，对于一般群体而言，出国外旅游、探亲的最大障碍是与外国人的语言交流。所以社会上就出现了很多的翻译器，支持多种语言和方言的翻译，包括英语、中文、西班牙语、德语、俄语、法语等，并能够完成语言的交互翻译。但现有的翻译器因为内存小，所录语音需发送至手机，通过手机转发服务器进行翻译，这就需要翻译器提前与手机扫描连接，而翻译器与手机的连接需要时间，多数用户在翻译器与手机未连接上便开始说话，这样就导致部分语音丢失，翻译不完整。
 技术问题
本申请的目的旨在解决用户在翻译器未与移动终端连接便开始说话，导致部分语音丢失而翻译不完整，以及翻译语音缓存占用过大而导致翻译机无法翻译的技术问题，提供一种蓝牙翻译的交互方法及其装置。
 技术解决方案
为实现上述目的，本申请提供如下技术方案：
本申请提供一种蓝牙翻译的交互方法，包括：
接收用户输入的第一语音信息，并分析所述第一语音信息的缓存占用量；
判断所述缓存占用量是否大于预设的缓存值；
若大于，则发送所述第一语音信息至预关联的移动终端；
接收由所述移动终端输出返回的第二语音信息，所述第二语音信息为所述第一语音信息经过翻译转换得到的语音信息。
进一步地，所述接收由所述移动终端输出返回的第二语音信息的步骤之后，包括：
根据第一预设规则输出所述第二语音信息；
生成第一删除指令；
根据所述第一删除指令将所述第一语音信息和所述第二语音信息删除，并发送所述第一删除指令至所述移动终端，以将所述移动终端保存的所述第一语音信息和所述第二语音信息删除。
进一步地，所述根据第一预设规则输出所述第二语音信息的步骤，包括：
对所述第二语音信息进行语义分析，以得到第二语音文本；
生成分割符，根据对所述第二语音信息的语义分析结果，生成分割符，并将所述分割符插入至所述第二语音文本。
进一步地，所述判断所述缓存占用量是否大于预设的缓存值的步骤之后，包括：
若小于，则发送所述第一语音信息至服务器；
接收由所述服务器输出返回的第三语音信息，所述第三语音信息为所述第一语音信息经过翻译转换得到的语音信息；
根据第二预设规则输出所述第三语音信息；
生成第二删除指令；
根据所述第二删除指令将所述第一语音信息和所述第三语音信息删除。
进一步地，所述生成第二删除指令的步骤之前，包括：
接收用户输入的删除信息，所述删除信息包括语音启动删除信息、按钮启动删除信息或触摸启动删除信息的至少一项。
进一步地，所述接收用户输入的第一语音信息的步骤之前，包括：
扫描周围至少一个第一蓝牙信号，所述第一蓝牙信号由移动终端发出，其中一个所述移动终端对应一个所述第一蓝牙信号；
输出第二蓝牙信号，根据握手协议从至少一个所述第一蓝牙信号中筛选与所述第二蓝牙信号相互识别的指定第一蓝牙信号；
与所述指定第一蓝牙信号对应的所述移动终端建立无线连接。
进一步地，所述与指定第一蓝牙信号对应的所述移动终端建立无线连接的步骤之后，包括：
生成提醒信号；
输出所述提醒信号以提醒用户输入所述第一语音信息。
本申请提出一种蓝牙翻译的交互装置，包括：
第一接收单元，用于接收用户输入的第一语音信息，并分析所述第一语音信息的缓存占用量；
缓存判断单元，用于判断所述缓存占用量是否大于预设的缓存值；
发送单元，用于若大于，则发送所述第一语音信息至预关联的移动终端；
第二接收单元，用于接收由所述移动终端输出返回的第二语音信息，所述第二语音信息为所述第一语音信息经过翻译转换得到的语音信息。
进一步地，蓝牙翻译的交互装置还包括：
第一输出单元，用于根据第一预设规则输出第二语音信息；
第一指令删除单元，用于生成第一删除指令；
第一删除单元，用于根据所述第一删除指令将所述第一语音信息和所述第二语音信息删除，并发送所述第一删除指令至所述移动终端，以将所述移动终端保存的所述第一语音信息和所述第二语音信息删除。
进一步地，蓝牙翻译的交互装置所述第一输出单元包括：
文本建立模块，用于对所述第二语音信息进行语义分析，以得到第二语音文本；
分隔符模块，用于根据对所述第二语音信息的语义分析结果，生成分割符，并将所述分割符插入至所述第二语音文本。
进一步地，蓝牙翻译的交互装置还包括：
服务器发送单元，用于若小于，则发送所述第一语音信息至服务器；
服务器返回单元，用于接收由所述服务器输出返回的第三语音信息，所述第三语音信息为所述第一语音信息经过翻译转换得到的语音信息；
第二输出单元，用于根据第二预设规则输出所述第三语音信息；
第二指令删除单元，用于生成第二删除指令；
第二删除单元，用于根据所述第二删除指令将所述第一语音信息和所述第三语音信息删除。
进一步地，蓝牙翻译的交互装置还包括：
删除启动单元，用于接收用户输入的删除信息，所述删除信息包括语音启动删除信息、按钮启动删除信息或触摸启动删除信息的至少一项。
进一步地，蓝牙翻译的交互装置还包括：
扫描单元，用于扫描周围至少一个第一蓝牙信号，所述第一蓝牙信号由移动终端发出，其中一个移动终端对应一个所述第一蓝牙信号；
输出单元，用于输出第二蓝牙信号，根据握手协议从至少一个所述第一蓝牙信号中筛选与所述第二蓝牙信号相互识别的指定第一蓝牙信号；
连接单元，用于与所述指定第一蓝牙信号对应的所述移动终端建立无线连接。
进一步地，蓝牙翻译的交互装置还包括：
提醒单元，用于生成提醒信号；
提醒输出单元，用于输出所述提醒信号以提醒用户输入所述第一语音信息。
本申请还提供一种蓝牙翻译机，包括存储器、处理器和至少一个被存储在所述存储器中并被配置为由所述处理器执行的应用程序，所述应用程序被配置为用于执行上述的蓝牙翻译的交互方法。
 有益效果
蓝牙翻译机通过接收用户输入的第一语音信息，并分析第一语音信息的缓存占用量；判断缓存占用量是否大于预设的缓存值；若大于，则发送第一语音信息至预关联的移动终端；接收由移动终端输出返回的第二语音信息，第二语音信息为所述第一语音信息经过翻译转换得到的语音信息；从而解决用户在翻译器未与移动终端连接便开始说话，导致部分语音丢失而翻译不完整，以及翻译语音缓存占用过大而导致翻译机无法翻译的技术问题。
 附图说明
图1为本申请提供的蓝牙翻译的交互方法的流程示意图；
图2为本申请提供的蓝牙翻译的交互装置的结构框图；
图3为本申请提供的蓝牙翻译机的结构框图。
本申请为目的的实现、功能特点及优点将结合实施例，参照附图做出说明。
 本发明的最佳实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请的一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
参考附图1，为本申请提供的蓝牙翻译的交互方法的流程示意图，包括：
步骤S1：接收用户输入的第一语音信息，并分析第一语音信息的缓存占用量；
步骤S2：判断缓存占用量是否大于预设的缓存值；
步骤S3：若大于，则发送第一语音信息至预关联的移动终端；
步骤S4：接收由移动终端输出返回的第二语音信息，第二语音信息为第一语音信息经过翻译转换得到的语音信息；
本申请提出一种蓝牙翻译机结合运行蓝牙翻译的交互方法做出说明，蓝牙翻译机接收用户输入的第一语音信息，第一语音信息为待翻译语音，可以为汉语、英语、法语等多国家语音，蓝牙翻译机获取用户输入第一语音信息所用到的记录时长，根据预设的分贝规则识别记录时长中第一语音信息的有效时长，删减有效时长以外的记录时长，以保留记录有第一语音信息的有效时长，达到减少缓存的效果，以举例示意：用户开启蓝牙翻译机进行翻译工作，用户向蓝牙翻译机输入第一语音信息，而输入第一语音信息的过程时间为记录时长，可知，记录时长的部分时长没有记录第一语音信息，而导致多余缓存的占用，故通过预设的分贝规则识别第一语音信息，而识别出具有第一语音信息的记录时长为有效时长，而不具有第一语音信息的记录时长为待删时长，删除待删时长，达到减少每条第一语音信息输入至蓝牙翻译机的缓存，预设的分贝规则识别第一语音信息的过程为，第一语音信息的音量值是否到达或超过分贝阈值，若达到或超过，则保留第一语音信息的记录时长，优选的分贝阈值采用40分贝。分析保留的第一语音信息的缓存占用量，判断缓存占用量是否大于预设的缓存值，其中，缓存占用量为记录第一语音信息所需要占用的缓存量，预设的缓存值为在蓝牙翻译机中预设的缓存阈值，优选的缓存阈值采用5Mbyte；由上述步骤S3可知，若判断第一语音信息的缓存占用量大于蓝牙翻译机的缓存阈值，则将第一语音信息发送至预关联的移动终端，基于服务器对语音信息进行翻译，由移动终端接收到蓝牙翻译机发出的第一语音信息，移动终端发送第一语音信息至服务器进行翻译，服务器将第一语音信息翻译为第二语音信息，从而达到翻译的效果，服务器发送第二语音信息至移动终端，移动终端接收第二语音信息并发送至蓝牙翻译机，而完成蓝牙翻译机的翻译过程；从解决技术问题而言，用户输入长句语音、或者超长且输入过程中断句的困难语音至蓝牙翻译机，由蓝牙翻译机删除多余的待删时长而降低困难语音的缓存，以后步骤如上述相同故不赘述，实现蓝牙翻译机对困难语音的翻译，显著提升蓝牙翻译机的翻译性能。
在一实施例，根据接收由移动终端输出返回的第二语音信息的步骤S4之后，包括：
S41：根据第一预设规则输出第二语音信息。
由上述可知，服务器翻译第一语音信息而转换为第二语音信息，服务器发送第二语音信息至移动终端，再由移动终端发送第二语音信息至蓝牙翻译机，故此步骤S41的目的为蓝牙翻译机输出第二语音信息，第一预设规则为输出第二语音信息的方式，方式可为a、第二语音信息通过显示屏的文字输出，b、第二语音通过播音输出；方式a，分析第二语音信息的语义，排列第二语音信息所对应的第二语音文本至蓝牙翻译机的显示屏，根据语义生成分割符并将分割符插入至第二语音文本中。方式b、蓝牙翻译机播放第二语音信息。另外，接合方式a与方式b，蓝牙翻译机即通过显示屏显示第二语音文本，并播放第二语音信息。
在一实施例，根据第一预设规则输出第二语音信息的步骤S41之后，包括：
S42：生成第一删除指令；
S43：根据第一删除指令将第一语音信息和第二语音信息删除，并发送第一删除指令至移动终端，将移动终端保存的第一语音信息和第二语音信息删除，以清理缓存。
本步骤为上述蓝牙翻译机根据第一预设规则输出第二语音信息之后的步骤，本步骤的目的为，因为翻译第一语音信息，蓝牙翻译机与移动终端上会记录有第一语音信息及其带有的有效时长，为删除第一语音信息及其带有的有效时长以减少蓝牙翻译机与移动终端的缓存，故提出本步骤，蓝牙翻译机输出第二语音信息的预设时间之后，蓝牙翻译机生成第一删除指令，通过第一删除指令删除蓝牙翻译机所保留的第一语音信息和第二语音信息，蓝牙翻译机发送第一删除指令至移动终端，移动终端通过第一删除指令将保留的第一语音信息和第二语音信息删除，而达到清理蓝牙翻译机和移动终端缓存的效果，上述预设时间优选采用5分钟。
在一实施例，根据判断缓存占用量是否大于预设的缓存值的步骤S2之后，包括：
S21：若小于，则发送第一语音信息至服务器；
S22：接收由服务器输出返回的第三语音信息，第三语音信息为第一语音信息经过翻译转换得到的语音信息；
S23：根据第二预设规则输出第三语音信息。
若判断缓存占用量小于缓存阈值，则蓝牙翻译机认定用户输入的第一语音信息为短句语音，蓝牙翻译机直接发送第一语音信息至服务器，服务器将第一语音信息翻译为第三语音信息，需要说明，第三语音信息与第二语音信息同为服务器所翻译生成的语音信息，其区分第三、第二是因为第一语音信息发送至服务器的起点不同，即第三语音信息是由蓝牙翻译机直接发送第一语音信息至服务器而翻译生成的语音信息，而第二语音信息是由蓝牙翻译机发送第一语音信息至移动终端，再由移动终端发送至服务器而翻译生成的语音信息；上述第二预设规则为蓝牙翻译机输出第三语音信息的方式，第二预设规则与上述的第一预设规则相同，此处以第一、第二区分蓝牙翻译机输出第二语音信息、第三语音信息。
在一实施例，根据第二预设规则输出第三语音信息的步骤S23之后，包括：
S23：生成第二删除指令；
S24：根据第二删除指令将第一语音信息和第三语音信息删除，以清理缓存。
本实施例为蓝牙翻译机输出第三语音信息的步骤S23经过预设时间之后所执行的步骤过程，预设时间优选为5分钟，以清理蓝牙翻译机的缓存；蓝牙翻译机根据第三预设规则生成第二删除指令，第三预设规则为生成第二删除指令的方式，其方式为，a、接收用户输入的删除信息，删除信息包括语音启动删除、按钮启动删除以及触摸启动删除；根据删除信息生成第二删除指令；其中，语音启动删除为用户向蓝牙翻译机输入预设的删除语音，判断用户向蓝牙翻译机输入的删除语音是否与预设的删除语音相类似，若相似度较高，则根据删除语音生成第二删除指令；按钮启动删除为用户向蓝牙翻译机按下指定的按钮，从而启动清理缓存的功能，接收用户输入的按钮删除信息，根据按钮删除信息生成第二删除指令；触摸启动删除为蓝牙翻译机外部设置有显示屏，显示屏接收用户输入的触摸删除信息，以生成第二删除指令，接收用户输入的触摸删除指令，验证触摸条纹是否与预设的条纹相匹配，若匹配则生成第二删除指令，需要说明，上述触摸条纹可以为用户指纹，或为身体其它部位，例如额头等，人们都有独一无二的个人条纹，用户可事先在蓝牙翻译机上设置条纹，当需要清理蓝牙翻译机的缓存时，用户输入预设的条纹即可生成第二删除指令，该过程运用与场景中，用户出现手很脏、手有水以及手有油时，用户输入的指纹则不易被识别，故可以输入其他身体部位以达到识别作用，而生成第二删除指令，以将第一语音信息和第三语音信息删除，以清理蓝牙翻译机的缓存。
在一实施例，根据接收用户输入的第一语音信息的步骤S1之前，包括：
S101：扫描周围至少一个第一蓝牙信号，第一蓝牙信号由移动终端发出，其中一个移动终端对应一个第一蓝牙信号；
S102：输出第二蓝牙信号，根据握手协议从至少一个第一蓝牙信号中筛选与第二蓝牙信号相互识别的指定第一蓝牙信号；
S103：与指定第一蓝牙信号对应的移动终端建立无线连接。
本实施例为蓝牙翻译机和移动终端的连接过程，蓝牙翻译机输出第二蓝牙信号，第二蓝牙信号与预关联移动终端输出的第一蓝牙信号进行握手识别，若确认识别则蓝牙翻译机与移动终端建立无线连接，可以理解，无线连接包括蓝牙连接与WIFI连接。
在另一实施例，根据与指定第一蓝牙信号对应的移动终端建立无线连接的步骤S103之后，包括：
S104：生成提醒信号；
S105：输出提醒信号以提醒用户输入第一语音信息。
提醒信号为提醒用户蓝牙翻译机与移动终端已建立无线连接而生成的信号，目的是防止用户在蓝牙翻译器与移动终端未连接上便开始说话，导致部分语音丢失，翻译不完整的问题，有上述可知，蓝牙翻译机包含显示屏和播音设备，故提醒信号通过显示屏和播音设备进行输出，由显示屏进行输出提醒信号的步骤包括，a、显示屏全屏显示为绿色，则为提醒用户移动终端与蓝牙翻译机已建立无线连接，b、显示屏全屏显示为黄色，则提醒用户移动终端与蓝牙翻译机正在建立无线连接，c、显示屏全屏显示为红色，则提醒用户移动终端与蓝牙翻译机无法建立无线连接，无法建立的原因可以是蓝牙翻译机电量不足、蓝牙翻译机内主板受到损坏等；播音设备则直接输出提醒信号。
参考附图2，为本申请提供的蓝牙翻译的交互装置的结构框图，包括：
第一接收单元4，用于接收用户输入的第一语音信息，并分析第一语音信息的缓存占用量；
缓存判断单元5，用于判断缓存占用量是否大于预设的缓存值；
发送单元6，用于若大于，则发送第一语音信息至预关联的移动终端；
第二接收单元7，用于接收由移动终端输出返回的第二语音信息，第二语音信息为第一语音信息经过翻译转换得到的语音信息。
蓝牙翻译机通过第一接收单元4接收用户输入的第一语音信息，第一语音信息为待翻译语音，可以为汉语、英语、法语等多国家语音，蓝牙翻译机获取用户输入第一语音信息所用到的记录时长，根据预设的分贝规则识别记录时长中第一语音信息的有效时长，删减有效时长以外的记录时长，以保留记录有第一语音信息的有效时长，达到减少缓存的效果，以举例示意：用户开启蓝牙翻译机进行翻译工作，用户向蓝牙翻译机输入第一语音信息，而输入第一语音信息的过程时间为记录时长，可知，记录时长的部分时长没有记录第一语音信息，而导致多余缓存的占用，故通过预设的分贝规则识别第一语音信息，而识别出具有第一语音信息的记录时长为有效时长，而不具有第一语音信息的记录时长为待删时长，删除待删时长，达到减少每条第一语音信息输入至蓝牙翻译机的缓存，预设的分贝规则识别第一语音信息的过程为，第一语音信息的音量值是否到达或超过分贝阈值，若达到或超过，则保留第一语音信息的记录时长，优选的分贝阈值采用40分贝。分析保留的第一语音信息的缓存占用量，通过缓存判断单元5判断缓存占用量是否大于预设的缓存值，其中，缓存占用量为记录第一语音信息所需要占用的缓存量，预设的缓存值为在蓝牙翻译机中预设的缓存阈值，优选的缓存阈值采用5Mbyte；若判断第一语音信息的缓存占用量大于蓝牙翻译机的缓存阈值，则通过发送单元6将第一语音信息发送至预关联的移动终端，基于服务器对语音信息进行翻译，由移动终端接收到蓝牙翻译机发出的第一语音信息，移动终端发送第一语音信息至服务器进行翻译，服务器将第一语音信息翻译为第二语音信息，从而达到翻译的效果，服务器发送第二语音信息至移动终端，移动终端接收第二语音信息并发送至蓝牙翻译机，蓝牙翻译机通过第二接收单元7接收第二语音信息，而完成蓝牙翻译机的翻译过程；从解决技术问题而言，用户输入长句语音、或者超长且输入过程中断句的困难语音至蓝牙翻译机，由蓝牙翻译机删除多余的待删时长而降低困难语音的缓存，以后步骤如上述相同故不赘述，实现蓝牙翻译机对困难语音的翻译，显著提升蓝牙翻译机的翻译性能。
在一实施例，蓝牙翻译的交互装置还包括：
扫描单元1，用于扫描周围至少一个第一蓝牙信号，第一蓝牙信号由移动终端发出，其中一个移动终端对应一个第一蓝牙信号；
输出单元2，用于输出第二蓝牙信号，根据握手协议从至少一个第一蓝牙信号中筛选与第二蓝牙信号相互识别的指定第一蓝牙信号；
连接单元3，用于与指定第一蓝牙信号对应的移动终端建立无线连接。
蓝牙翻译机通过输出单元2输出第二蓝牙信号，第二蓝牙信号与预关联移动终端输出的第一蓝牙信号进行握手识别，若确认识别则通过连接单元3蓝牙翻译机与移动终端建立无线连接，可以理解，无线连接包括蓝牙连接与WIFI连接。
在一实施例，蓝牙翻译的交互装置，还包括：
第一输出单元8，用于根据第一预设规则输出第二语音信息。
由上述可知，服务器翻译第一语音信息而转换为第二语音信息，服务器发送第二语音信息至移动终端，再由移动终端发送第二语音信息至蓝牙翻译机；目的为蓝牙翻译机输出第二语音信息，第一输出单元8根据第一预设规则为输出第二语音信息，其输出的的方式为a、第二语音信息通过显示屏的文字输出，b、第二语音通过播音输出；方式a，分析第二语音信息的语义，排列第二语音信息所对应的第二语音文本至蓝牙翻译机的显示屏，根据语义生成分割符并将分割符插入至第二语音文本中。方式b、蓝牙翻译机播放第二语音信息。另外，接合方式a与方式b，蓝牙翻译机即通过显示屏显示第二语音文本，并播放第二语音信息。
在一实施例，蓝牙翻译的交互装置，还包括：
第一指令删除单元9，用于生成第一删除指令；
第一删除单元10，用于根据第一删除指令将第一语音信息和第二语音信息删除，并发送第一删除指令至移动终端，将移动终端保存的第一语音信息和第二语音信息删除，以清理缓存。
目的为，因为翻译第一语音信息，蓝牙翻译机与移动终端上会记录有第一语音信息及其带有的有效时长，为删除第一语音信息及其带有的有效时长以减少蓝牙翻译机与移动终端的缓存，蓝牙翻译机输出第二语音信息的预设时间之后，蓝牙翻译机通过第一指令删除单元9生成第一删除指令，并通过第一删除单元10根据第一删除指令删除蓝牙翻译机所保留的第一语音信息和第二语音信息，蓝牙翻译机发送第一删除指令至移动终端，移动终端通过第一删除指令将保留的第一语音信息和第二语音信息删除，而达到清理蓝牙翻译机和移动终端缓存的效果，上述预设时间优选采用5分钟。
在一实施例，蓝牙翻译的交互装置，还包括：
服务器发送单元11，用于若小于，则发送第一语音信息至服务器，第三语音信息为第一语音信息经过翻译转换得到的语音信息；
服务器返回单元12，用于接收由服务器输出返回的第三语音信息；
第二输出单元13，用于根据第二预设规则输出第三语音信息。
若判断缓存占用量小于缓存阈值，则蓝牙翻译机认定用户输入的第一语音信息为短句语音，蓝牙翻译机通过服务器发送单元11发送第一语音信息至服务器，服务器将第一语音信息翻译为第三语音信息，需要说明，第三语音信息与第二语音信息同为服务器所翻译生成的语音信息，其区分第三、第二是因为第一语音信息发送至服务器的起点不同，即第三语音信息是由蓝牙翻译机直接发送第一语音信息至服务器而翻译生成的语音信息，而第二语音信息是由蓝牙翻译机发送第一语音信息至移动终端，再由移动终端发送至服务器而翻译生成的语音信息；上述第二预设规则为蓝牙翻译机输出第三语音信息的方式，第二预设规则与上述的第一预设规则相同，此处以第一、第二区分蓝牙翻译机输出第二语音信息、第三语音信息。
在一实施例，蓝牙翻译的交互装置，还包括：
第二指令删除单元14，用于生成第二删除指令；
第二删除单元15，用于根据第二删除指令将第一语音信息和第三语音信息删除，以清理缓存。
蓝牙翻译机通过第二指令删除单元14根据第三预设规则生成第二删除指令，第三预设规则为生成第二删除指令的方式，其方式为，a、接收用户输入的删除信息，删除信息包括语音启动删除、按钮启动删除以及触摸启动删除；根据删除信息生成第二删除指令；其中，语音启动删除为用户向蓝牙翻译机输入预设的删除语音，判断用户向蓝牙翻译机输入的删除语音是否与预设的删除语音相类似，若相似度较高，则根据删除语音生成第二删除指令；按钮启动删除为用户向蓝牙翻译机按下指定的按钮，从而启动清理缓存的功能，接收用户输入的按钮删除信息，根据按钮删除信息生成第二删除指令；触摸启动删除为蓝牙翻译机外部设置有显示屏，显示屏接收用户输入的触摸删除信息，以生成第二删除指令，接收用户输入的触摸删除指令，验证触摸条纹是否与预设的条纹相匹配，若匹配则生成第二删除指令，需要说明，上述触摸条纹可以为用户指纹，或为身体其它部位，例如额头等，人们都有独一无二的个人条纹，用户可事先在蓝牙翻译机上设置条纹，当需要清理蓝牙翻译机的缓存时，用户输入预设的条纹即可生成第二删除指令，该过程运用与场景中，用户出现手很脏、手有水以及手有油时，用户输入的指纹则不易被识别，故可以输入其他身体部位以达到识别作用，而生成第二删除指令，以通过第二删除单元15将第一语音信息和第三语音信息删除，以清理蓝牙翻译机的缓存。
在一实施例，蓝牙翻译的交互装置，还包括：
生成单元16，用于生成提醒信号；
提醒单元17，用于输出提醒信号以提醒用户输入第一语音信息。
提醒信号为提醒用户蓝牙翻译机与移动终端已建立无线连接而生成的信号，目的是防止用户在蓝牙翻译器与移动终端未连接上便开始说话，导致部分语音丢失，翻译不完整的问题，有上述可知，蓝牙翻译机包含显示屏和播音设备，故提醒信号通过显示屏和播音设备进行输出，由显示屏进行输出提醒信号的步骤包括，a、显示屏全屏显示为绿色，则为提醒用户移动终端与蓝牙翻译机已建立无线连接，b、显示屏全屏显示为黄色，则提醒用户移动终端与蓝牙翻译机正在建立无线连接，c、显示屏全屏显示为红色，则提醒用户移动终端与蓝牙翻译机无法建立无线连接，无法建立的原因可以是蓝牙翻译机电量不足、蓝牙翻译机内主板受到损坏等；播音设备则直接输出提醒信号。
参考附图3，为本申请同时提出的蓝牙翻译机100的结构框图，该蓝牙翻译机100包括存储器200、处理器400和至少一个被存储在存储器200中并被配置为由所述处理器400执行的应用程序300，所述应用程序300被配置为用于执行上述任一实施例中的蓝牙翻译的交互方法。
本领域技术人员可以理解，本申请所述的蓝牙翻译机100和上述所涉及用于执行本申请中所述方法中的一项或多项的设备。这些设备可以为所需的目的而专门设计和制造，或者也可以包括通用计算机中的已知设备。这些设备具有存储在其内的应用程序300，这些计算机程序选择性地激活或重构。这样的计算机程序可以被存储在设备（例如，计算机）可读介质中或者存储在适于存储电子指令并分别耦联到总线的任何类型的介质中，所述计算机可读介质包括但不限于任何类型的盘（包括软盘、硬盘、光盘、CD-ROM、和磁光盘）、ROM（Read-Only Memory，只读存储器）、RAM（Random Access Memory，随机存储器）、EPROM（Erasable Programmable Read-Only Memory，可擦写可编程只读存储器）、EEPROM（Electrically Erasable Programmable Read-Only Memory，电可擦可编程只读存储器）、闪存、磁性卡片或光线卡片。也就是，可读介质包括由设备（例如，计算机）以能够读的形式存储或传输信息的任何介质。
尽管已经示出和描述了本申请的实施例，对于本领域的普通技术人员而言，可以理解在不脱离本申请的原理和精神的情况下可以对这些实施例进行多种变化、修改、替换和变型，本申请的范围由所附权利要求及其等同物限定。

Claims (15)

  1. 一种蓝牙翻译的交互方法，其特征在于，包括：
    接收用户输入的第一语音信息，并分析所述第一语音信息的缓存占用量；
    判断所述缓存占用量是否大于预设的缓存值；
    若大于，则发送所述第一语音信息至预关联的移动终端；
    接收由所述移动终端输出返回的第二语音信息，所述第二语音信息为所述第一语音信息经过翻译转换得到的语音信息。
  2. 根据权利要求1所述的蓝牙翻译的交互方法，其特征在于，所述接收由所述移动终端输出返回的第二语音信息的步骤之后，包括：
    根据第一预设规则输出所述第二语音信息；
    生成第一删除指令；
    根据所述第一删除指令将所述第一语音信息和所述第二语音信息删除，并发送所述第一删除指令至所述移动终端，以将所述移动终端保存的所述第一语音信息和所述第二语音信息删除。
  3. 根据权利要求2所述的蓝牙翻译的交互方法，其特征在于，所述根据第一预设规则输出所述第二语音信息的步骤，包括：
    对所述第二语音信息进行语义分析，以得到第二语音文本；
    生成分割符，根据对所述第二语音信息的语义分析结果，生成分割符，并将所述分割符插入至所述第二语音文本。
  4. 根据权利要求1所述的蓝牙翻译的交互方法，其特征在于，所述判断所述缓存占用量是否大于预设的缓存值的步骤之后，包括：
    若小于，则发送所述第一语音信息至服务器；
    接收由所述服务器输出返回的第三语音信息，所述第三语音信息为所述第一语音信息经过翻译转换得到的语音信息；
    根据第二预设规则输出所述第三语音信息；
    生成第二删除指令；
    根据所述第二删除指令将所述第一语音信息和所述第三语音信息删除。
  5. 根据权利要求4所述的蓝牙翻译的交互方法，其特征在于，所述生成第二删除指令的步骤之前，包括：
    接收用户输入的删除信息，所述删除信息包括语音启动删除信息、按钮启动删除信息或触摸启动删除信息的至少一项。
  6. 根据权利要求1所述的蓝牙翻译的交互方法，其特征在于，所述接收用户输入的第一语音信息的步骤之前，包括：
    扫描周围至少一个第一蓝牙信号，所述第一蓝牙信号由移动终端发出，其中一个所述移动终端对应一个所述第一蓝牙信号；
    输出第二蓝牙信号，根据握手协议从至少一个所述第一蓝牙信号中筛选与所述第二蓝牙信号相互识别的指定第一蓝牙信号；
    与所述指定第一蓝牙信号对应的所述移动终端建立无线连接。
  7. 根据权利要求6所述的蓝牙翻译的交互方法，其特征在于，所述与指定第一蓝牙信号对应的所述移动终端建立无线连接的步骤之后，包括：
    生成提醒信号；
    输出所述提醒信号以提醒用户输入所述第一语音信息。
  8. 一种蓝牙翻译的交互装置，其特征在于，包括：
    第一接收单元，用于接收用户输入的第一语音信息，并分析所述第一语音信息的缓存占用量；
    缓存判断单元，用于判断所述缓存占用量是否大于预设的缓存值；
    发送单元，用于若大于，则发送所述第一语音信息至预关联的移动终端；
    第二接收单元，用于接收由所述移动终端输出返回的第二语音信息，所述第二语音信息为所述第一语音信息经过翻译转换得到的语音信息。
  9. 根据权利要求8所述的蓝牙翻译的交互装置，其特征在于，还包括：
    第一输出单元，用于根据第一预设规则输出第二语音信息；
    第一指令删除单元，用于生成第一删除指令；
    第一删除单元，用于根据所述第一删除指令将所述第一语音信息和所述第二语音信息删除，并发送所述第一删除指令至所述移动终端，以将所述移动终端保存的所述第一语音信息和所述第二语音信息删除。
  10. 根据权利要求9所述的蓝牙翻译的交互装置，其特征在于，所述第一输出单元包括：
    文本建立模块，用于对所述第二语音信息进行语义分析，以得到第二语音文本；
    分隔符模块，用于根据对所述第二语音信息的语义分析结果，生成分割符，并将所述分割符插入至所述第二语音文本。
  11. 根据权利要求8所述的蓝牙翻译的交互装置，其特征在于，还包括：
    服务器发送单元，用于若小于，则发送所述第一语音信息至服务器；
    服务器返回单元，用于接收由所述服务器输出返回的第三语音信息，所述第三语音信息为所述第一语音信息经过翻译转换得到的语音信息；
    第二输出单元，用于根据第二预设规则输出所述第三语音信息；
    第二指令删除单元，用于生成第二删除指令；
    第二删除单元，用于根据所述第二删除指令将所述第一语音信息和所述第三语音信息删除。
  12. 根据权利要求11所述的蓝牙翻译的交互装置，其特征在于，还包括：
    删除启动单元，用于接收用户输入的删除信息，所述删除信息包括语音启动删除信息、按钮启动删除信息或触摸启动删除信息的至少一项。
  13. 根据权利要求8所述的蓝牙翻译的交互装置，其特征在于，还包括：
    扫描单元，用于扫描周围至少一个第一蓝牙信号，所述第一蓝牙信号由移动终端发出，其中一个移动终端对应一个所述第一蓝牙信号；
    输出单元，用于输出第二蓝牙信号，根据握手协议从至少一个所述第一蓝牙信号中筛选与所述第二蓝牙信号相互识别的指定第一蓝牙信号；
    连接单元，用于与所述指定第一蓝牙信号对应的所述移动终端建立无线连接。
  14. 根据权利要求13所述的蓝牙翻译的交互装置，其特征在于，还包括：
    提醒单元，用于生成提醒信号；
    提醒输出单元，用于输出所述提醒信号以提醒用户输入所述第一语音信息。
  15. 一种蓝牙翻译机，其特征在于，包括存储器、处理器和至少一个被存储在所述存储器中并被配置为由所述处理器执行的应用程序，所述应用程序被配置为用于执行权利要求1至7任一项所述的蓝牙翻译的交互方法。
PCT/CN2019/073760 2018-09-17 2019-01-29 蓝牙翻译机、蓝牙翻译的交互方法及其装置 Ceased WO2020057040A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811083882.7 2018-09-17
CN201811083882.7A CN109446533B (zh) 2018-09-17 2018-09-17 蓝牙翻译机、蓝牙翻译的交互方式及其装置

Publications (1)

Publication Number Publication Date
WO2020057040A1 true WO2020057040A1 (zh) 2020-03-26

Family

ID=65532853

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/073760 Ceased WO2020057040A1 (zh) 2018-09-17 2019-01-29 蓝牙翻译机、蓝牙翻译的交互方法及其装置

Country Status (2)

Country Link
CN (1) CN109446533B (zh)
WO (1) WO2020057040A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111027330A (zh) * 2019-11-22 2020-04-17 深圳情景智能有限公司 翻译系统、翻译方法、翻译机及存储介质
CN113706977A (zh) * 2020-08-13 2021-11-26 苏州韵果莘莘影视科技有限公司 基于译语智能手语翻译软件的播放方法及系统
CN113035165B (zh) * 2021-03-04 2023-01-03 北京雷石天地电子技术有限公司 音频数据处理方法、音频数据处理装置及可读存储介质
CN113903341B (zh) * 2021-09-30 2025-05-20 安克创新科技股份有限公司 音频数据的转录方法和电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102647718A (zh) * 2012-04-16 2012-08-22 北京大学 一种对VoIP业务进行混合资源分配的方法
CN106131349A (zh) * 2016-09-08 2016-11-16 刘云 一种具有自动翻译功能的手机、蓝牙耳机组件
CN206921088U (zh) * 2017-06-02 2018-01-23 苏州龙诺法智能科技有限公司 集移动电源与翻译功能于一体的智能系统
CN107862060A (zh) * 2017-11-15 2018-03-30 吉林大学 一种追踪目标人的语义识别装置及识别方法

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102368258B (zh) * 2011-09-30 2014-11-26 广州市动景计算机科技有限公司 一种网页页面缓存管理方法及其系统
AU2015390534B2 (en) * 2015-04-10 2019-08-22 Honor Device Co., Ltd. Speech recognition method, speech wakeup apparatus, speech recognition apparatus, and terminal
CN205942689U (zh) * 2016-07-02 2017-02-08 苏州龙诺法智能科技有限公司 智能随身翻译器
CN107123418B (zh) * 2017-05-09 2020-12-25 广东小天才科技有限公司 一种语音消息的处理方法及移动终端
CN107343113A (zh) * 2017-06-26 2017-11-10 深圳市沃特沃德股份有限公司 语音通话方法和装置
CN109451027A (zh) * 2017-07-07 2019-03-08 西安万像电子科技有限公司 数据传输方法及系统
CN107885731A (zh) * 2017-11-06 2018-04-06 深圳市沃特沃德股份有限公司 语音翻译方法和装置
CN108090052A (zh) * 2018-01-05 2018-05-29 深圳市沃特沃德股份有限公司 语音翻译方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102647718A (zh) * 2012-04-16 2012-08-22 北京大学 一种对VoIP业务进行混合资源分配的方法
CN106131349A (zh) * 2016-09-08 2016-11-16 刘云 一种具有自动翻译功能的手机、蓝牙耳机组件
CN206921088U (zh) * 2017-06-02 2018-01-23 苏州龙诺法智能科技有限公司 集移动电源与翻译功能于一体的智能系统
CN107862060A (zh) * 2017-11-15 2018-03-30 吉林大学 一种追踪目标人的语义识别装置及识别方法

Also Published As

Publication number Publication date
CN109446533A (zh) 2019-03-08
CN109446533B (zh) 2020-12-22

Similar Documents

Publication Publication Date Title
KR101768509B1 (ko) 온라인 음성 번역 방법 및 장치
KR102437944B1 (ko) 음성 웨이크업 방법 및 장치
CN113327609B (zh) 用于语音识别的方法和装置
CN111177338B (zh) 一种基于上下文的多轮对话方法
CN109326289A (zh) 免唤醒语音交互方法、装置、设备及存储介质
CN109658579A (zh) 一种门禁控制方法、系统、设备及存储介质
CN111128166B (zh) 连续唤醒识别功能的优化方法和装置
CN110853638A (zh) 语音交互过程中实时打断语音机器人的方法及设备
CN109256133A (zh) 一种语音交互方法、装置、设备及存储介质
CN103514882B (zh) 一种语音识别方法及系统
CN113643684A (zh) 语音合成方法、装置、电子设备及存储介质
CN114724561A (zh) 一种语音打断方法、装置、计算机设备及存储介质
CN109446533B (zh) 蓝牙翻译机、蓝牙翻译的交互方式及其装置
CN112929501B (zh) 语音通话服务方法、装置、设备、介质及计算机程序产品
CN116052664A (zh) 用于口语对话的实时语义理解方法、系统和电子设备
WO2015188454A1 (zh) 一种快速进入ivr菜单的方法及装置
CN112002325A (zh) 多语种语音交互方法和装置
US20200051556A1 (en) Speech control for complex commands
CN115440220A (zh) 一种话语权切换方法、装置、设备和存储介质
WO2021134237A1 (zh) 一种视频录制方法、装置及计算机可读存储介质
CN111951832B (zh) 一种语音分析用户对话情绪的方法及装置
CN105551504B (zh) 一种基于哭声触发智能移动终端功能应用的方法及装置
CN116013306B (zh) 会议记录生成方法、装置、服务器以及存储介质
CN111866883A (zh) 基于语音模块的路由器wifi设置方法及系统
CN115273912A (zh) 语音状态判定方法、装置、终端及存储介质

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19861492

Country of ref document: EP

Kind code of ref document: A1