Translation method and device, mobile translation equipment, server and storage medium

Abstract

The embodiment of the invention provides a translation method and device, mobile translation equipment, a server and a storage medium. The method comprises the following steps: acquiring first voice information collected by an earphone through a second communication unit, and determining a first voice packet based on the first voice information and position information of mobile translation equipment; sending the first voice packet to a target relay node through the first communication unit, and forwarding the first voice packet to a server through the target relay node; receiving a second voice packet and a translation instruction sent by the server through the first communication unit; and calling a translation model based on the translation instruction, determining translation voice corresponding to the second voice information, and sending the translation voice to the earphone through the second communication unit. According to the technical scheme provided by the embodiment of the invention, the scenarized translation service can be triggered according to positioning, the speech translation requirement in the mobile state is met, and the user experience is improved.

Description

Technical Field

[0001] This disclosure relates to communication technology, and more particularly to a translation method, apparatus, mobile translation device, server, and storage medium. Background Technology

[0002] With the rapid development of communication and internet technologies, an increasing number of products with translation functions have emerged. For example, in scenarios such as conferences, industrial visits, or tourist attractions, users can use devices with translation capabilities to obtain translated audio from other users. However, current translation devices can only generate translations based on speech, making it difficult to provide a contextualized translation experience, resulting in a poor user experience. Summary of the Invention

[0003] This disclosure provides a translation method, apparatus, mobile translation device, server, and storage medium, which can translate speech information in combination with the context to obtain contextualized translation content, thereby improving the user experience.

[0004] In a first aspect, embodiments of this disclosure provide a translation method applied to a processor of a mobile translation device. The mobile translation device further includes a first communication unit and a second communication unit. The frequency band of the first communication unit is higher than that of the second communication unit. The first communication unit communicates with a target relay node, and the second communication unit communicates with an earpiece. The method includes:

[0005] The first voice information collected by the earphone is obtained through the second communication unit, and a first voice packet is determined based on the first voice information and the location information of the mobile translation device. The first voice information is the voice information of the first user in the conversation, and the location information is determined by the positioning signal transmitted by the first communication unit.

[0006] The first voice packet is sent to the target relay node through the first communication unit, so that the first voice packet is forwarded to the server through the target relay node, wherein the target relay node is determined based on the signal strength of the positioning signal returned by multiple relay nodes;

[0007] The first communication unit receives a second voice packet and a translation instruction sent by the server, wherein the translation instruction includes contextualized translation resources corresponding to the location information, and the second voice packet includes the second voice information of the second user in the conversation;

[0008] Based on the translation instruction, the translation model is invoked to determine the translated speech corresponding to the second speech information, and the translated speech is sent to the headset through the second communication unit.

[0009] Secondly, this disclosure also provides a translation method applied to a server, the method comprising:

[0010] The system receives a first voice packet sent by a mobile translation device, wherein the first voice packet includes first voice information and location information of the mobile translation device, the first voice information is the voice information of a first user in the conversation, and the location information is determined by a positioning signal broadcast by the first communication unit of the mobile translation device.

[0011] The first voice packet is parsed to obtain the location information and the first voice information, and the first voice information is sent to the second user in the session.

[0012] The translation instruction is determined based on the location information, wherein the translation instruction includes the contextualized translation resources corresponding to the location information;

[0013] The second user's second voice packet is obtained, and the second voice packet and translation instructions are sent to the mobile translation device through the target relay node.

[0014] Thirdly, this disclosure also provides a translation device, applied to a processor of a mobile translation device, the mobile translation device further including a first communication unit and a second communication unit, the first communication unit having a higher frequency band than the second communication unit, the first communication unit communicating with a target relay node, and the second communication unit communicating with an earpiece, the device comprising:

[0015] The acquisition module is used to acquire first voice information collected by the earphone through the second communication unit, and determine a first voice packet based on the first voice information and the location information of the mobile translation device, wherein the first voice information is the voice information of the first user in the conversation, and the location information is determined by the positioning signal transmitted by the first communication unit;

[0016] A first sending module is configured to send the first voice packet to the target relay node through the first communication unit, so that the first voice packet can be forwarded to the server through the target relay node, wherein the target relay node is determined based on the signal strength of the positioning signal returned by multiple relay nodes;

[0017] The first receiving module is configured to receive a second voice packet and a translation instruction sent by the server through the first communication unit, wherein the translation instruction includes contextualized translation resources corresponding to the location information, and the second voice packet includes the second voice information of the second user in the conversation;

[0018] The translation module is used to invoke the translation model based on the translation instruction, determine the translated speech corresponding to the second speech information, and send the translated speech to the headset through the second communication unit.

[0019] Fourthly, embodiments of this disclosure also provide a translation apparatus applied to a server, the apparatus comprising:

[0020] The second receiving module is used to receive a first voice packet sent by the mobile translation device, wherein the first voice packet includes first voice information and location information of the mobile translation device, the first voice information is the voice information of the first user in the conversation, and the location information is determined by a positioning signal broadcast by the first communication unit of the mobile translation device;

[0021] The parsing module is used to parse the first voice packet, obtain the location information and the first voice information, and send the first voice information to the second user in the session;

[0022] A determining module is used to determine translation instructions based on the location information, wherein the translation instructions include contextualized translation resources corresponding to the location information;

[0023] The second sending module is used to acquire the second user's second voice packet and send the second voice packet and translation instructions to the mobile translation device through the target relay node.

[0024] Fifthly, embodiments of this disclosure also provide a mobile translation device, the mobile translation device comprising:

[0025] The first communication unit is used to transmit a positioning signal and to send a first voice packet to the target relay node;

[0026] The second communication unit is used to acquire the first voice packet collected by the earpiece, and to send the translated voice of the second voice information in the second voice packet to the earpiece;

[0027] One or more processors;

[0028] Storage device for storing one or more programs.

[0029] When the one or more programs are executed by the one or more processors, the one or more processors implement the translation method as described in the first aspect example.

[0030] Sixthly, embodiments of this disclosure also provide a server, the server comprising:

[0031] One or more processors;

[0032] Storage device for storing one or more programs.

[0033] When the one or more programs are executed by the one or more processors, the one or more processors implement the translation method as described in the second aspect.

[0034] In a seventh aspect, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the translation method as described in any embodiment of this disclosure.

[0035] This disclosure provides a translation method. A first voice information collected by an earpiece is acquired through a second communication unit. A first voice packet is determined based on the first voice information and the location information of a mobile translation device. The first voice packet is sent to a target relay node through the first communication unit, which then forwards it to a server, achieving stable and efficient transmission of the voice packet and reducing latency errors. Since the location information is determined by a positioning signal emitted by the first communication unit, high-frequency bands are used for positioning, improving positioning accuracy and stability. The location information of the mobile translation device is attached to the first voice packet and sent to the server, facilitating the server to generate translation instructions based on the contextualized translation resources corresponding to the location information, thus enabling contextualized translation services triggered by location. Further, a second voice packet and translation instructions sent by the server are received through the first communication unit. The second voice packet includes the second voice information of a second user in the conversation. Based on the translation instructions, a translation model is invoked to determine the translated voice corresponding to the second voice information. The translated voice is then sent to the earpiece through the second communication unit to play the translated voice, achieving contextualized real-time mobile translation. The technical solution of this disclosure solves the problem that translation devices can only generate translation content based on speech, making it difficult to provide a contextualized translation experience, thus meeting the needs of speech translation in mobile situations and improving the user experience. Attached Figure Description

[0036] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0037] Figure 1 This is a schematic flowchart illustrating a translation method provided in an embodiment of the present disclosure;

[0038] Figure 2 This is a flowchart illustrating another translation method provided in an embodiment of this disclosure;

[0039] Figure 3 This is a schematic diagram of a translation device provided in an embodiment of the present disclosure;

[0040] Figure 4 This is a schematic diagram of another translation device structure provided in an embodiment of the present disclosure;

[0041] Figure 5 This is a schematic diagram of the structure of a mobile translation device provided in an embodiment of the present disclosure;

[0042] Figure 6 This is a schematic diagram of the structure of a server provided in an embodiment of the present disclosure. Detailed Implementation

[0043] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0044] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0045] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0046] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0047] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0048] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0049] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0050] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0051] Example 1

[0052] Figure 1 This is a flowchart illustrating a translation method provided in an embodiment of the present disclosure. This embodiment is applicable to voice translation in mobile scenarios such as online meetings, industrial visits, or tourism. The method can be executed by a translation device, which can be implemented in software and / or hardware. Optionally, it can be implemented by a mobile translation device, which may include a processor, a first communication unit, a second communication unit, and an earpiece. The frequency band of the first communication unit is higher than that of the second communication unit. The first communication unit communicates with the target relay node, and the second communication unit communicates with the earpiece.

[0053] like Figure 1 As shown, the method includes:

[0054] S110. Obtain the first voice information collected by the earphone through the second communication unit, and determine the first voice packet based on the first voice information and the location information of the mobile translation device, wherein the first voice information is the voice information of the first user in the conversation, and the location information is determined by the positioning signal transmitted by the first communication unit.

[0055] The second communication unit is used to communicate with the headset. For example, if the headset is a Bluetooth headset, the second communication unit includes a Bluetooth module. Alternatively, if it is a wired headset, the second communication unit includes a headset interface circuit. The headset is used to play second voice information and to acquire first voice information. The first voice information is the voice information emitted by the first user in the session. The second voice information is the voice information received by the first user. The session is audio communication between the first user and at least one second user. For example, the session includes online meetings, industrial reference tours, or tour guides. For example, if the first user needs to attend a meeting while driving, they can join the meeting using a mobile translation device. Or, during an industrial visit or tour, the first user can listen to the guide's audio explanation and communicate with the guide via voice using a mobile translation device.

[0056] Location information refers to the positioning results of the mobile translation device. Location information can be determined through the positioning signal transmitted by the first communication unit. The first communication unit is a wireless positioning module with a frequency band of 7.75-8.25 GHz. For example, the first communication unit is an Ultra High Frequency (UHF) positioning module. Because the 7.75-8.25 GHz band does not share frequency with other wireless transmission protocols, it is less susceptible to interference from superimposed signals from other devices, exhibiting strong anti-interference capabilities. Furthermore, the 7.75-8.25 GHz wireless positioning module has advantages such as good signal penetration and long communication distance, enabling stable and accurate positioning in complex scenarios and under mobile conditions.

[0057] In some embodiments, the location information is confirmed using the following methods:

[0058] The positioning signal is broadcast through the first communication unit, and the signal strength of the positioning signal received by at least one relay node and the location coordinates of the relay node are obtained. A weight is determined based on the signal strength, and the location information is determined based on the weight and the location coordinates.

[0059] The relay node is an electronic device equipped with a UHF module. Voice packet transmission between the mobile translation device and the server is achieved through the relay node. Since the user is mobile, the mobile translation device may be located within the coverage area of ​​multiple relay nodes. In this case, the mobile translation device detects the signal strength of each relay node and connects to the target relay node corresponding to the strongest signal.

[0060] Specifically, the mobile translation device periodically broadcasts a location signal, including an identification code, through a first communication unit. The UHF module of a relay node receives the location signal, amplifies and filters it to remove interference. Then, based on the filtered location signal, the signal strength is determined. The relay node feeds back its location coordinates and signal strength to the corresponding mobile translation device based on the identification code in the location signal. Since multiple relay nodes can be set up in an area, the mobile translation device can receive signal strength and location coordinates returned by multiple relay nodes. The processor determines the weight of the location coordinates based on the signal strength. For example, the weight can be a normalized value of the signal strength, etc., but this embodiment does not specifically limit the weight. Based on the weight and the corresponding location coordinates, the location information of the mobile translation device is determined.

[0061] S120. The first voice packet is sent to the target relay node through the first communication unit, so that the first voice packet is forwarded to the server through the target relay node, wherein the target relay node is determined based on the signal strength of the positioning signal returned by multiple relay nodes.

[0062] For example, after determining the real-time location information, the first voice information and location information are encapsulated into a first voice packet and sent to the target relay node through the first communication unit, so that the target relay node can send the first voice packet to the server. The server is the backend server of the mobile translation application. The mobile translation application is pre-installed on the mobile translation device. The first user can join a session by entering session identifier information in the interactive interface.

[0063] S130. Receive a second voice packet and a translation instruction sent by the server through the first communication unit, wherein the translation instruction includes contextualized translation resources corresponding to the location information, and the second voice packet includes the second voice information of the second user in the session.

[0064] The contextualized translation resources include a terminology database and translation model parameters. The terminology database contains specialized terms for different scenarios. The translation model parameters determine the type of translation model to be invoked. The second speech packet is the speech packet corresponding to the second user's second speech information in the conversation.

[0065] For example, the second voice packet and translation instruction are received from the target relay node through the first communication unit, wherein the translation instruction is determined by querying a preset scene database based on the location information obtained by the server parsing the first voice packet.

[0066] Because the first communication unit transmits voice packets via the less-interference 7.75-8.25GHz ultra-high frequency band, interference from other signal sources or complex obstructions can be avoided, ensuring stable transmission of voice packets. The server, based on the location information of the mobile translation device, queries a pre-set scenario database to obtain scenario-based translation resources and generates translation instructions based on these resources. In some scenarios, while the user is driving, the system locates the corresponding region, determines the language of that region, and then, combined with the language corresponding to the first voice information, determines the translation model parameters. Furthermore, it combines this with information from cultural attractions or industrial fields to determine a specialized terminology database. Therefore, the mobile translation device can more accurately translate the speech of guides during industrial references or sightseeing.

[0067] Optionally, the server obtains the second voice packet corresponding to the second user in the conference, and parses the voice packet to obtain the second voice information and the location information of the second user. Optionally, the server verifies the identity of the second user based on the voiceprint features of the second voice information. If the verification passes, the second voice information is encapsulated into a new second voice packet, and the new second voice packet and translation instructions are sent to the mobile translation device through the target relay node.

[0068] S140. Based on the translation instruction, call the translation model to determine the translated speech corresponding to the second speech information, and send the translated speech to the headset through the second communication unit.

[0069] Translation models are natural language processing models that convert one natural language (source language) into another natural language (target language). While preserving the semantics of the original text, translation models generate translated text that conforms to the grammar and expression habits of the target language.

[0070] The mobile translation device stores translation models and other translation resources capable of converting different types of languages ​​in its storage device. The mobile translation device receives a second speech packet, parses it to obtain second speech information and translation instructions. Environmental Noise Cancellation (ENC) technology is used to reduce noise in the second speech information. The noise-reduced second speech is converted into text information. The translation model corresponding to the translation instructions, combined with a terminology database, is used to translate the text information, resulting in translated text. The translated text is then translated into translated speech. The translated speech is transmitted to the headset via a second communication unit for playback through the headset.

[0071] For example, if the translation model parameters for a translation instruction include translating from language A to language B, then a translation model capable of translating from language A to language B will be invoked. The translation model, combined with a terminology database corresponding to the current location information, will translate the text information to obtain the translated text.

[0072] Optionally, the mobile translation device further includes an auxiliary positioning unit, and the method further includes:

[0073] If the first communication unit fails to connect with any of the relay nodes, the auxiliary positioning unit determines the offline location of the mobile translation device and generates an offline voice packet based on the offline location and the first voice information. In response to a successful connection between the first communication unit and a target relay node, the offline voice packet is sent to the target relay node, which then sends the offline voice packet to the server for correction of the offline location in the offline voice packet.

[0074] The auxiliary positioning unit is used for positioning. For example, the auxiliary positioning unit includes a UWB (Ultra-Wideband) positioning module, a GRS positioning module, or a Wi-Fi positioning module. Since the user is carrying the mobile translation device and is in a mobile state, the connection with the first communication unit may fail when moving to a certain area. In response to the failure to connect with the first communication unit, the offline location of the mobile translation device is determined by the auxiliary positioning unit. The offline location refers to the location of the mobile translation device determined by the auxiliary positioning unit. The location information is the location of the mobile translation device determined by the UHF positioning module.

[0075] During the process of the mobile translation device failing to connect with the first communication unit, the first user may speak in the conversation and obtain the first voice information. However, the first voice information cannot be sent through the first communication unit. The offline location and the first voice information can be encapsulated into an offline voice packet and stored in the storage device of the mobile translation device.

[0076] In response to a successful connection between the first communication unit and the target relay node, the offline voice packet is read from the storage device and sent to the target relay node via the first communication unit, so that the target relay node can then send the offline voice packet to the server. The target relay base point is the relay node with the strongest positioning signal among multiple relay nodes.

[0077] Optionally, the mobile translation device also includes a microphone and a speaker. The mobile translation device acquires first voice information from the microphone, sends the translated voice to the speaker, and plays the translated voice through the speaker, thereby achieving voice pickup and playback without wearing headphones.

[0078] Optionally, the mobile translation device also includes an earphone charging case for storing and charging the wireless earphones.

[0079] Optionally, the mobile translation device also includes a display module and an operation module. The display module is used to display at least one of the following: current location, translated text, language, or device status information. The operation module includes operation buttons such as volume buttons and language switching buttons. Optionally, the mobile translation device adopts a waterproof and dustproof design and has a built-in high-capacity lithium battery, providing a long battery life and making it suitable for complex mobile scenarios such as outdoor and industrial environments.

[0080] The technical solution of this disclosure embodiment acquires first voice information collected by the earphone through a second communication unit, and determines a first voice packet based on the first voice information and the location information of the mobile translation device. The first voice packet is then sent to a target relay node via the first communication unit, which forwards the first voice packet to the server, achieving stable and efficient transmission of the voice packet and reducing latency errors. Since the location information is determined by the positioning signal emitted by the first communication unit, high-frequency bands are used for positioning, improving positioning accuracy and stability. The location information of the mobile translation device is attached to the first voice packet and sent to the server, facilitating the server to generate translation instructions based on the contextualized translation resources corresponding to the location information, thus enabling contextualized translation services triggered by location. Furthermore, the first communication unit receives a second voice packet and translation instructions sent by the server. The second voice packet includes the second voice information of the second user in the conversation. Based on the translation instructions, a translation model is invoked to determine the translated voice corresponding to the second voice information. The translated voice is then sent to the earphone via the second communication unit to play the translated voice, achieving contextualized real-time mobile translation. The technical solution of this disclosure embodiment solves the problem that translation devices can only generate translation content based on voice, making it difficult to provide a contextualized translation experience, thus meeting the voice translation needs in mobile situations and improving the user experience.

[0081] Example 2

[0082] Figure 2 This is a flowchart illustrating another translation method provided by an embodiment of the present disclosure. This embodiment is applicable to speech translation in mobile scenarios such as online meetings, industrial visits, or tourism. The method can be executed by a translation device, which can be implemented in the form of software and / or hardware, or optionally, through a server.

[0083] like Figure 2 As shown, the method includes:

[0084] S210. Receive a first voice packet sent by a mobile translation device, wherein the first voice packet includes first voice information and location information of the mobile translation device, the first voice information is the voice information of a first user in the conversation, and the location information is determined by a positioning signal broadcast by the first communication unit of the mobile translation device.

[0085] The first voice information in the first voice packet is the speech of the first user. For example, the first voice information could be the first user's speech at a meeting, or an inquiry to a guide about scenic spots or industrial equipment. The first communication unit is a wireless positioning module operating in the 7.75-8.25GHz frequency band. The location information is obtained by the mobile translation device using the 7.75-8.25GHz frequency band. This frequency band has strong anti-interference capabilities, effectively reducing interference from devices such as mobile phones and Wi-Fi, and has good signal penetration, enabling stable positioning even in complex environments such as indoor offices and roads.

[0086] S220. Parse the first voice packet to obtain the location information and the first voice information, and send the first voice information to the second user in the session.

[0087] For example, the server parses the first voice packet to obtain the location information of the mobile translation device and the first voice information of the first user. The server then sends the first voice information to the second user in the session.

[0088] Optionally, for sessions with security requirements, such as company meetings, the server needs to obtain the voiceprint features of the participants as a voiceprint database for the company meeting. The voiceprint features of the first voice message are matched with the voiceprint features in the preset voiceprint database, and the identity of the first user is verified based on the matching result. If the verification passes, the first voice message is sent to the second user related to the meeting.

[0089] S230. Determine translation instructions based on the location information, wherein the translation instructions include contextualized translation resources corresponding to the location information.

[0090] Contextualized translation resources consist of translation knowledge corresponding to specific scenarios. Optionally, these resources include a terminology database and translation model parameters. The terminology database contains specialized terms for different scenarios. The translation model parameters determine the type of translation model to be invoked.

[0091] For example, a scene identifier is determined based on the location information. A preset scene database is queried based on the scene identifier to obtain scene-specific translation resources, wherein the scene-specific translation resources are translation knowledge corresponding to the scene. Translation instructions are determined based on the scene-specific translation resources.

[0092] Scene identifiers are used to represent scenes. For example, the server combines location information and a map to determine the scene corresponding to the location information, obtaining a scene identifier. Scenes may include roads, tourist attractions, or industrial parks. The server then queries a pre-defined scene database based on the scene identifier to obtain scene-specific translation resources. These resources may include a terminology database and translation model parameters. Finally, translation instructions are determined based on the terminology database and translation model parameters.

[0093] Optionally, the type and version information of the terminology database in the mobile translation device can be obtained. If the mobile translation device already contains a terminology database to be distributed, the translation model parameters are encapsulated into translation instructions to avoid duplicate distribution of the terminology database.

[0094] S240: Obtain the second voice packet of the second user, and send the second voice packet and translation instructions to the mobile translation device through the target relay node.

[0095] For example, the server obtains the second voice packet of the second user in the session, and parses the second voice packet to obtain the second voice and location information.

[0096] In a company meeting scenario, the voiceprint features of the second voice message are matched with the voiceprint features in a preset voiceprint database, and the identity of the second user is verified based on the matching result. If the verification is successful, the second voice message is sent to the first user's mobile translation device.

[0097] For scenarios involving sightseeing or industrial visits, the location information in the second voice packet is matched with the location information in the first voice packet, and the identity of the second user is verified based on the matching result. If the verification is successful, the second voice information is sent to the first user's mobile translation device.

[0098] The technical solution of this disclosure improves session security by matching voiceprint features or location information to verify user identity.

[0099] For example, if the second user passes the identity verification, the second voice information is encapsulated into a second voice packet, and the second voice packet and translation instructions are sent to the mobile translation device.

[0100] Optionally, if the session includes an online meeting scenario, it further includes:

[0101] The system receives offline voice packets sent by the mobile translation device. These offline voice packets include first voice information generated during the process where the first communication unit fails to connect with any of the relay nodes, and an offline location determined by the auxiliary positioning unit in the mobile translation device. The system parses the offline voice packets to obtain the offline location and the first voice information. Based on the timestamp of the first voice information, the system adds the first voice information to the online meeting record.

[0102] Since the first user is mobile with the translation device, there may be instances where they cannot connect to any relay node during this movement. In this case, the first user is offline, and the server cannot obtain the first user's initial voice information during this period, resulting in an incomplete meeting transcript after the meeting ends. Therefore, after the mobile translation device connects to the target relay node, it will resend an offline voice packet to the server. Because the offline voice packet includes the first user's initial voice information and offline location, the server can add the initial voice information to the online meeting transcript based on the timestamp of the initial voice information to obtain a complete meeting record.

[0103] In some special meetings, the first user needs to receive instructions from the second user to move within a designated area, and the first user's movement trajectory needs to be recorded. If the first user is offline, their location information cannot be obtained, resulting in interruptions in the movement trajectory. The offline location data from the offline voice packet can be used to complete the movement trajectory.

[0104] Optionally, an offline voice packet sent by the mobile translation device is received. The offline voice packet includes first voice information and an offline location generated during the process where the first communication unit fails to connect with any of the relay nodes. The offline location is determined by the auxiliary positioning unit in the mobile translation device. Based on the location information and a map, the offline location is corrected. Based on the location information and the corrected offline location, trajectory information is determined.

[0105] Since the server stores the location information of the first user before going offline, each location and its timestamp can be marked on the map. The map with location markers and timestamps is input into the route prediction model to obtain the predicted route output by the model. The predicted route is an extension of the trajectory composed of each location. The predicted route includes the predicted location and its timestamp. The route prediction model can be a large language model, etc. The offline location is corrected based on the predicted route to obtain the corrected offline location. For example, the predicted location corresponding to the predicted route is determined based on the timestamp of the offline location, and the deviation between the offline location and the predicted location is calculated. The offline location is corrected based on the deviation. Optionally, if the deviation is less than or equal to a set threshold, no correction is performed on the offline location. If the deviation is greater than the set threshold, the corresponding predicted location is used as the corrected offline location.

[0106] The technical solution of this disclosure embodiment involves receiving a first voice packet sent by a mobile translation device. The first voice packet includes first voice information and location information of the mobile translation device. The first voice information is the voice information of a first user in the conversation, and the location information is determined by a positioning signal broadcast by the first communication unit of the mobile translation device. The first voice packet is parsed to obtain the location information and the first voice information, and the first voice information is sent to a second user in the conversation. A translation instruction is determined based on the location information, and the translation instruction includes contextualized translation resources corresponding to the location information. A second voice packet of the second user is obtained, and the second voice packet and the translation instruction are sent to the mobile translation device through a target relay node to realize a location-based contextualized translation service. By issuing translation instructions to the mobile translation device, the mobile translation device can call the translation model and professional terminology library corresponding to the scene based on the translation instructions to generate translation content that is closer to the needs of the scene.

[0107] Example 3

[0108] Figure 3 This is a schematic diagram of a translation device structure provided in an embodiment of the present disclosure. The translation device can be implemented in the form of software and / or hardware. The device is applied to the processor of a mobile translation device. The mobile translation device also includes a first communication unit and a second communication unit. The frequency band of the first communication unit is higher than that of the second communication unit. The first communication unit communicates with a target relay node, and the second communication unit communicates with an earphone.

[0109] like Figure 3 As shown, the device includes: an acquisition module 310, a first sending module 320, a first receiving module 330, and a translation module 340.

[0110] The acquisition module 310 is used to acquire the first voice information collected by the earphone through the second communication unit, and determine the first voice packet based on the first voice information and the location information of the mobile translation device, wherein the first voice information is the voice information of the first user in the conversation, and the location information is determined by the positioning signal transmitted by the first communication unit;

[0111] The first sending module 320 is used to send the first voice packet to the target relay node through the first communication unit, so that the first voice packet can be forwarded to the server through the target relay node, wherein the target relay node is determined based on the signal strength of the positioning signal returned by multiple relay nodes;

[0112] The first receiving module 330 is configured to receive a second voice packet and a translation instruction sent by the server through the first communication unit, wherein the translation instruction includes contextualized translation resources corresponding to the location information, and the second voice packet includes the second voice information of the second user in the conversation;

[0113] The translation module 340 is used to call the translation model based on the translation instruction, determine the translated speech corresponding to the second speech information, and send the translated speech to the headset through the second communication unit.

[0114] Optionally, the first communication unit is a wireless positioning module with a frequency band range of 7.75-8.25 GHz, and the location information confirmation method includes:

[0115] The positioning signal is broadcast through the first communication unit to obtain the signal strength of the positioning signal received by at least one relay node and the location coordinates of the relay node;

[0116] The weights of the location coordinates are determined based on the signal strength, and the location information is determined based on the weights and the location coordinates.

[0117] Optionally, the first receiving module 330 is specifically used for:

[0118] The second voice packet and translation instruction are received from the target relay node through the first communication unit, wherein the translation instruction is determined by querying a preset scene database based on the location information obtained by the server parsing the first voice packet.

[0119] Optionally, the mobile translation device further includes an auxiliary positioning unit, and the method further includes:

[0120] If the first communication unit fails to connect with each of the relay nodes, the offline location of the mobile translation device is determined by the auxiliary positioning unit, and an offline voice packet is generated based on the offline location and the first voice information.

[0121] In response to the successful connection between the first communication unit and the target relay node, the offline voice packet is sent to the target relay node, and then the target relay node sends the offline voice packet to the server, so that the server can perform offline position correction processing on the offline voice packet.

[0122] The translation device provided in this embodiment can execute the translation method provided by the mobile translation device of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0123] Example 4

[0124] Figure 4This is a schematic diagram of another translation device structure provided in an embodiment of the present disclosure. The translation device can be implemented in the form of software and / or hardware, and the device is applied to a server.

[0125] like Figure 4 As shown, the device includes: a second receiving module 410, a parsing module 420, a determining module 430, and a second sending module 440.

[0126] The second receiving module 410 is used to receive a first voice packet sent by the mobile translation device, wherein the first voice packet includes first voice information and location information of the mobile translation device, the first voice information is the voice information of the first user in the conversation, and the location information is determined by a positioning signal broadcast by the first communication unit of the mobile translation device;

[0127] The parsing module 420 is used to parse the first voice packet, obtain the location information and the first voice information, and send the first voice information to the second user in the session;

[0128] The determining module 430 is used to determine a translation instruction based on the location information, wherein the translation instruction includes a contextualized translation resource corresponding to the location information;

[0129] The second sending module 440 is used to acquire the second voice packet of the second user and send the second voice packet and translation instructions to the mobile translation device through the target relay node.

[0130] Optionally, module 430 is specifically used for:

[0131] Determine the scene identifier based on the location information;

[0132] Based on the scene identifier, a preset scene database is queried to obtain scene-specific translation resources, wherein the scene-specific translation resources are translation knowledge corresponding to the scene;

[0133] Translation instructions are determined based on the aforementioned contextualized translation resources.

[0134] Optionally, if the session includes an online meeting scenario, it further includes:

[0135] The mobile translation device receives an offline voice packet, wherein the offline voice packet includes first voice information and an offline location generated during the process when the first communication unit fails to connect with each of the relay nodes, and the offline location is determined by the auxiliary positioning unit in the mobile translation device.

[0136] The offline voice packet is parsed to obtain the offline location and the first voice information. Based on the timestamp of the first voice information, the first voice information is added to the online meeting record.

[0137] Optionally, it also includes:

[0138] The mobile translation device receives an offline voice packet, wherein the offline voice packet includes first voice information and an offline location generated during the process when the first communication unit fails to connect with each of the relay nodes, and the offline location is determined by the auxiliary positioning unit in the mobile translation device.

[0139] Based on the location information and the map, the offline location is corrected, and the trajectory information is determined based on the location information and the corrected offline location.

[0140] The translation apparatus provided in this embodiment can execute the translation method provided by the server of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0141] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0142] Example 5

[0143] Figure 5 This is a schematic diagram of the structure of a mobile translation device provided in an embodiment of this disclosure. Figure 5 As shown, the mobile translation device 510 includes a processor 520, a first communication unit 530, a second communication unit 540, an auxiliary positioning unit 550, an input device 560, an output device 570, an earphone 580, and a storage device 590. The input device 560 includes at least one of a microphone, an operation module, and a touchscreen. The output device 570 includes at least one of a speaker and a display module. The processor 520 can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 5100 or a program loaded from the storage device 590 into a random access memory (RAM) 5110. The processing device 510, ROM 5100, and RAM 5110 are interconnected via a bus 5120. An edit / output (I / O) interface 5130 is also connected to the bus 5120. Typically, the following devices can be connected to the I / O interface 5130: the first communication unit 530, the second communication unit 540, the auxiliary positioning unit 560, the input device 560, the output device 570, and the storage device 590. The earphone 580 is connected to the second communication unit 540. Although Figure 5A mobile translation device 510 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0144] In some embodiments, a first communication unit 520 is configured to transmit a positioning signal and send a first voice packet to a target relay node. A second communication unit 540 is configured to acquire the first voice packet collected by the earpiece and send translated voice of the second voice information in the second voice packet to the earpiece 580; one or more processors 520; and a storage device 590 for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement a translation method as described in any of the embodiments applied to a mobile translation device.

[0145] The mobile translation device provided in this embodiment and any of the translation methods applied to the mobile translation device provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0146] Example 6

[0147] Figure 6 This is a schematic diagram of the structure of a server provided in an embodiment of this disclosure. Refer to the following... Figure 6 It shows a schematic diagram of the structure of a server 600 suitable for implementing embodiments of the present disclosure. Figure 6 The server shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0148] like Figure 6 As shown, server 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from storage device 606 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of server 600. Processing device 601, ROM 602, and RAM 603 are interconnected via bus 604. Edit / output (I / O) interface 605 is also connected to bus 604.

[0149] Typically, the following devices can be connected to I / O interface 605: storage devices 606, such as magnetic tape and hard disk; and communication devices 607. Communication device 607 allows server 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6A server 600 with various devices is shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0150] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 607, or installed from storage device 606, or installed from ROM 602. When the computer program is executed by processing device 601, it performs the functions defined in the methods of embodiments of this disclosure.

[0151] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0152] The server provided in this embodiment belongs to the same inventive concept as the translation method applied to the server provided in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0153] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the translation method provided in the above embodiments.

[0154] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0155] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0156] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. For example, the electronic device includes a mobile translation device or a server.

[0157] The aforementioned computer-readable medium carries one or more programs, which, when executed by the mobile translation device, cause the mobile translation device to:

[0158] The first voice information collected by the earphone is obtained through the second communication unit, and the first voice packet is determined based on the first voice information and the location information of the mobile translation device. The first voice information is the voice information of the first user in the conversation, and the location information is determined by the positioning signal transmitted by the first communication unit.

[0159] The first voice packet is sent to the target relay node through the first communication unit, so that the first voice packet is forwarded to the server through the target relay node. The target relay node is determined based on the signal strength of the positioning signals returned by multiple relay nodes.

[0160] The first communication unit receives a second voice packet and a translation instruction sent by the server. The translation instruction includes contextualized translation resources corresponding to the location information, and the second voice packet includes the second voice information of the second user in the conversation.

[0161] The translation model is invoked based on the translation command to determine the translated speech corresponding to the second speech information, and the translated speech is sent to the headset through the second communication unit.

[0162] Alternatively, the aforementioned computer-readable medium carries one or more programs that, when executed by the server, cause the server to:

[0163] The system receives a first voice packet sent by a mobile translation device, wherein the first voice packet includes first voice information and location information of the mobile translation device, the first voice information is the voice information of the first user in the conversation, and the location information is determined by a positioning signal broadcast by the first communication unit of the mobile translation device.

[0164] Parse the first voice packet to obtain location information and the first voice information, and send the first voice information to the second user in the conversation;

[0165] Translation instructions are determined based on location information, wherein the translation instructions include contextualized translation resources corresponding to the location information;

[0166] Obtain the second user's second voice packet, and send the second voice packet and translation instructions to the mobile translation device through the target relay node.

[0167] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0168] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0169] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0170] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0171] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0172] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0173] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0174] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method of translation, characterized by, A processor for use in a mobile translation device, the mobile translation device further comprising a first communication unit and a second communication unit, the first communication unit operating at a higher frequency than the second communication unit, the first communication unit communicating with a target relay node, and the second communication unit communicating with an earpiece, the method comprising: The first voice information collected by the earphone is obtained through the second communication unit, and a first voice packet is determined based on the first voice information and the location information of the mobile translation device. The first voice information is the voice information of the first user in the conversation, and the location information is determined by the positioning signal transmitted by the first communication unit. The first voice packet is sent to the target relay node through the first communication unit, so that the first voice packet is forwarded to the server through the target relay node, wherein the target relay node is determined based on the signal strength of the positioning signal returned by multiple relay nodes; The first communication unit receives a second voice packet and a translation instruction sent by the server, wherein the translation instruction includes contextualized translation resources corresponding to the location information, and the second voice packet includes the second voice information of the second user in the conversation; Based on the translation instruction, the translation model is invoked to determine the translated speech corresponding to the second speech information, and the translated speech is sent to the headset through the second communication unit.

2. The method according to claim 1, characterized in that, The first communication unit is a wireless positioning module with a frequency band range of 7.75-8.25GHz, and the location information confirmation method includes: The positioning signal is broadcast through the first communication unit to obtain the signal strength of the positioning signal received by at least one relay node and the location coordinates of the relay node; The weights of the location coordinates are determined based on the signal strength, and the location information is determined based on the weights and the location coordinates.

3. The method according to claim 1, characterized in that, The step of receiving the second voice packet and translation instruction sent by the server through the first communication unit includes: The second voice packet and translation instruction are received from the target relay node through the first communication unit, wherein the translation instruction is determined by querying a preset scene database based on the location information obtained by the server parsing the first voice packet.

4. The method according to claim 1, characterized in that, The mobile translation device further includes an auxiliary positioning unit, and the method further includes: If the first communication unit fails to connect with each of the relay nodes, the offline location of the mobile translation device is determined by the auxiliary positioning unit, and an offline voice packet is generated based on the offline location and the first voice information. In response to the successful connection between the first communication unit and the target relay node, the offline voice packet is sent to the target relay node, and then the target relay node sends the offline voice packet to the server, so that the server can perform offline position correction processing on the offline voice packet.

5. A translation method, characterized in that, Applied to a server, the method includes: The system receives a first voice packet sent by a mobile translation device, wherein the first voice packet includes first voice information and location information of the mobile translation device, the first voice information is the voice information of a first user in the conversation, and the location information is determined by a positioning signal broadcast by the first communication unit of the mobile translation device. The first voice packet is parsed to obtain the location information and the first voice information, and the first voice information is sent to the second user in the session. The translation instruction is determined based on the location information, wherein the translation instruction includes the contextualized translation resources corresponding to the location information; The second user's second voice packet is obtained, and the second voice packet and translation instructions are sent to the mobile translation device through the target relay node.

6. The method according to claim 5, characterized in that, The step of determining the translation instruction based on the location information includes: Determine the scene identifier based on the location information; Based on the scene identifier, a preset scene database is queried to obtain scene-specific translation resources, wherein the scene-specific translation resources are translation knowledge corresponding to the scene; Translation instructions are determined based on the aforementioned contextualized translation resources.

7. The method according to claim 5, characterized in that, If the session includes an online meeting scenario, it also includes: The mobile translation device receives an offline voice packet, wherein the offline voice packet includes first voice information and an offline location generated during the process when the first communication unit fails to connect with each of the relay nodes, and the offline location is determined by the auxiliary positioning unit in the mobile translation device. The offline voice packet is parsed to obtain the offline location and the first voice information. Based on the timestamp of the first voice information, the first voice information is added to the online meeting record.

8. The method according to claim 5, characterized in that, Also includes: The mobile translation device receives an offline voice packet, wherein the offline voice packet includes first voice information and an offline location generated during the process when the first communication unit fails to connect with each of the relay nodes, and the offline location is determined by the auxiliary positioning unit in the mobile translation device. Based on the location information and the map, the offline location is corrected, and the trajectory information is determined based on the location information and the corrected offline location.

9. A translation device, characterized in that, A processor for use in a mobile translation device, the mobile translation device further comprising a first communication unit and a second communication unit, the first communication unit operating at a higher frequency than the second communication unit, the first communication unit communicating with a target relay node, and the second communication unit communicating with an earpiece, the device comprising: The acquisition module is used to acquire first voice information collected by the earphone through the second communication unit, and determine a first voice packet based on the first voice information and the location information of the mobile translation device, wherein the first voice information is the voice information of the first user in the conversation, and the location information is determined by the positioning signal transmitted by the first communication unit; A first sending module is configured to send the first voice packet to the target relay node through the first communication unit, so that the first voice packet can be forwarded to the server through the target relay node, wherein the target relay node is determined based on the signal strength of the positioning signal returned by multiple relay nodes; The first receiving module is configured to receive a second voice packet and a translation instruction sent by the server through the first communication unit, wherein the translation instruction includes contextualized translation resources corresponding to the location information, and the second voice packet includes the second voice information of the second user in the conversation; The translation module is used to invoke the translation model based on the translation instruction, determine the translated speech corresponding to the second speech information, and send the translated speech to the headset through the second communication unit.

10. A translation device, characterized in that, Applied to a server, the device includes: The second receiving module is used to receive a first voice packet sent by the mobile translation device, wherein the first voice packet includes first voice information and location information of the mobile translation device, the first voice information is the voice information of the first user in the conversation, and the location information is determined by a positioning signal broadcast by the first communication unit of the mobile translation device; The parsing module is used to parse the first voice packet, obtain the location information and the first voice information, and send the first voice information to the second user in the session; A determining module is used to determine translation instructions based on the location information, wherein the translation instructions include contextualized translation resources corresponding to the location information; The second sending module is used to acquire the second user's second voice packet and send the second voice packet and translation instructions to the mobile translation device through the target relay node.

11. A mobile translation device, characterized in that, The mobile translation device includes: The first communication unit is used to transmit a positioning signal and to send a first voice packet to the target relay node; The second communication unit is used to acquire the first voice packet collected by the earpiece, and to send the translated voice of the second voice information in the second voice packet to the earpiece; One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the translation method as described in any one of claims 1-4.

12. A server, characterized in that, The server includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the translation method as described in any one of claims 5-8.

13. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the translation method as described in any one of claims 1-8.

Images