Multi-scene intelligent desk type translation machine

Abstract

The invention relates to the technical field of machine translation and the like, and provides a multi-scene intelligent desktop translation machine which comprises a host and a detachable translation bar. The host receives and processes an instruction of the mobile intelligent terminal; the host shell is provided with a translation rod configuration groove and a charging head, and the translation rod can be charged and a pickup of the translation rod is turned off when the translation rod is assembled in the groove; in a noisy environment, a user can take down the translation rod for short-distance pickup and translation playing. The host is provided with a distributed pickup array, and when the translation bar pickup is turned off, sounds in different directions are positioned, and the voice of a main speaker is selected and extracted to translate and play. And the host monitors the connection state of the translation rod and the charging head, and closes the sound pickup array when the translation rod and the charging head are disconnected, so that automatic switching between a near-speaking mode of the translation rod and a far-speaking mode of the host is realized. The method can solve the problems that a desktop translation machine is poor in hardware expansibility, and a noisy scene pickup path is not adaptive, and realizes intelligent switching of pickup paths and multi-scene adaptation based on a hardware structure and state perception.

Description

Technical Field

[0001] The present invention relates to the technical fields of machine translation, semantic processing, and the like, and in particular to a multi-scenario intelligent desktop translation machine. Background Art

[0002] Currently, in the field of machine translation and semantic processing, there are two main types of translation machines: handheld translation machines (such as translation sticks) and desktop translation machines. Handheld translation machines are easy to carry and convenient for users to use on the go. Desktop translation machines have advantages in various scenarios, such as office communication, conference negotiations, international ports, and information desks. Currently, desktop translation machine technology developed for various scenarios has made significant progress, but the overall technical development direction is focused on software development. The hardware structure of desktop translation machines is relatively fixed, which cannot support the expansion and integration of the translation machine's hardware and software functions, and is not conducive to systematically solving specific problems that arise in different translation scenarios.

[0003] In summary, existing desktop translation machine technology has poor scalability, which is not conducive to systematically solving specific problems that occur in different translation scenarios. Summary of the Invention

[0004] In response to the above-mentioned deficiencies in the existing technology, the present invention provides a multi-scenario intelligent desktop translator to support the expansion of the translator's software and hardware functions and systematically solve specific problems occurring in different translation scenarios.

[0005] The present invention provides a multi-scenario intelligent desktop translation machine, comprising: A translation machine host, wherein a translation stick configuration slot is provided on the housing of the translation machine host, a charging head is provided inside the translation stick configuration slot, and the charging head is electrically connected to a power module inside the housing of the translation machine host; the translation machine host establishes a data connection with a mobile smart terminal running a translation control APP through a wireless communication module, receives and processes language pair and translation mode setting instructions, offline language package or local model download and activation instructions, and cloud or local translation engine call switching instructions issued by the mobile smart terminal; A translation stick is mounted in the translation stick configuration slot and is used for receiving voice signals within a close range near a sound source in a noisy environment by a user, and translating and playing the received voice signals. The translation stick is provided with a charging port. When the translation stick is mounted in the translation stick configuration slot, the charging port of the translation stick is electrically connected to a charging head provided in the translation stick configuration slot, and the power module charges the translation stick. The translation stick turns off its own pickup when charging. The microphone array is distributed on the shell of the translation machine host and is used to locate and select sounds from different directions when the microphone of the translation stick itself is turned off, pick up the sound from the direction of the speaker, separate the voice signal of the main speaking user, and give it to the translation machine host for translation and playback; the translation machine host monitors the connection status of the electrical connection between the translation stick and the charging head set in the translation stick configuration slot, and controls the microphone array to be turned off when the electrical connection between the translation stick and the charging head set in the translation stick configuration slot is disconnected.

[0006] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a multi-scenario intelligent desktop translation machine, which includes: a translation machine host, a translation stick configuration slot is provided on the shell of the translation machine host, a charging head is provided inside the translation stick configuration slot, and the charging head is electrically connected to a power module inside the shell of the translation machine host; the translation machine host establishes a data connection with a mobile smart terminal running a translation control APP through a wireless communication module, receives and processes language pair and translation mode setting instructions, offline language package or local model download and activation instructions, and cloud or local translation engine call switching instructions issued by the mobile smart terminal; a translation stick, which is assembled in the translation stick configuration slot and is used for receiving voice signals within a close range near a sound source for a user to remove and place near a sound source in a noisy noise scene, and translates and plays the received voice signals; the translation stick A charging port is provided. When the translation stick is installed in the translation stick configuration slot, the charging port of the translation stick is electrically connected to the charging head provided in the translation stick configuration slot, and the power module charges the translation stick. When the translation stick is in the charging state, its own microphone is turned off. A microphone array is distributed on the housing of the translation machine host. When the translation stick's own microphone is turned off, it is used to locate and select sounds from different directions, pick up sounds from the direction of the speaker, and separate the voice signal of the main speaker to the translation machine host for translation and playback. The translation machine host monitors the connection status of the translation stick and the charging head provided in the translation stick configuration slot. When the connection status of the translation stick and the charging head provided in the translation stick configuration slot is disconnected, the microphone array is controlled to be turned off. This multi-scenario intelligent desktop translation machine can solve systemic problems of desktop translation machines such as poor hardware scalability, non-adaptive pickup path in noisy and multi-speaker environments, and easy conflict of parallel channels. It achieves the overall technical effect of automatic pickup path switching based on hardware structure and state perception, main voice enhancement and multi-scenario adaptation. At the same time, the translation machine host establishes a data connection with the mobile smart terminal running the translation control APP through the wireless communication module, receives and processes the language pair and translation mode setting instructions, offline language package or local model download and activation instructions, and cloud or local translation engine call switching instructions issued by the mobile smart terminal, which can solve the problems of limited host-side interaction capabilities and cumbersome language pair and mode switching, and solve the problems of large pre-installed offline language packages and local models and difficult updates and maintenance, realize on-demand download and activation, incremental updates and storage savings, and solve the problems of decentralized strategies and slow switching in multiple scenarios (simultaneous, alternating, dialogue, etc.). The mobile smart terminal can uniformly issue a combination strategy of language pairs, modes and engines, quickly adapt to different usage environments, solve the problem of uncontrollable operation and maintenance caused by decentralized configuration and version management, and realize centralized strategy management, version consistency, and rapid rollback and upgrade. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their description are used to explain the present invention and do not constitute an undue limitation of the present invention. Some specific embodiments of the present invention will be described in detail in an illustrative and non-restrictive manner with reference to the drawings. The same reference numerals in the drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the drawings: Figure 1 This is a schematic diagram of the system architecture of a multi-scenario intelligent desktop translator according to an embodiment of the present invention; Figure 2 This is a structural diagram of a multi-scenario intelligent desktop translator according to an embodiment of the present invention; Figure 3 This is a structural diagram showing the position of the translation stick configuration slot and the concave curved surface of the peripheral expansion on the outer side of the housing of the translation machine host according to an embodiment of the present invention; Figure 4 This is another structural diagram showing the position of the translation stick configuration slot and the concave curved surface of the peripheral expansion on the outer side of the housing of the translation machine host according to an embodiment of the present invention; Figure 5 This is a structural diagram of a case where a charging head is incorporated into a slot of a translation stick according to an embodiment of the present invention; Figure 6 This is a structural diagram of a charging interface on a translation stick according to an embodiment of the present invention.

[0008] Description of reference numerals: 1. Translator host; 10. Translator stick slot; 101. First slot; 102. Second slot; 11. Charging head; 2. Translation stick; 20. Charging port; 21. First translation stick; 22. Second translation stick; 3. Pickup array; 4. External expansion concave surface; 40. First concave surface; 41. Second concave surface; 5. External bracket. DETAILED DESCRIPTION

[0009] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0010] See also Figures 1-6The embodiment of the present invention provides a multi-scenario intelligent desktop translation machine, including: A translation machine host 1, wherein a translation stick configuration slot 10 is provided on the shell of the translation machine host 1, and the translation stick configuration slot 10 is located on one side of the peripheral expansion concave surface 4. A charging head 11 is provided inside the translation stick configuration slot 10, and the charging head 11 is electrically connected to the power module inside the shell of the translation machine host 1; the translation machine host 1 establishes a data connection with a mobile smart terminal running a translation control APP through a wireless communication module, receives and processes language pair and translation mode setting instructions, offline language package or local model download and activation instructions, and cloud or local translation engine call switching instructions issued by the mobile smart terminal; A translation stick 2 is mounted in the translation stick configuration slot 10 and is used for receiving voice signals within a close range near a sound source in a noisy environment by the user, and for translating and playing the received voice signals. The translation stick 2 is provided with a charging port 20. When the translation stick 2 is mounted in the translation stick configuration slot 10, the charging port 20 of the translation stick 2 is electrically connected to a charging head 11 provided in the translation stick configuration slot 10. The power module charges the translation stick 2, and the translation stick 2 turns off its own pickup when charging. The microphone array 3 is distributed on the shell of the translation machine host 1 and is used to locate and select sounds from different directions when the microphone of the translation stick 2 itself is turned off, pick up the sound from the direction of the speaker, separate the voice signal of the main speaking user, and give it to the translation machine host 1 for translation and playback; the translation machine host 1 monitors the connection status of the electrical connection between the translation stick 2 and the charging head 11 set in the translation stick configuration slot 10, and controls the microphone array 3 to be turned off when the electrical connection between the translation stick 2 and the charging head 11 set in the translation stick configuration slot 10 is disconnected.

[0011] In this embodiment, a translation stick configuration slot 10 is provided on the housing of the translation machine host 1. A charging head 11 electrically connected to the power module is provided inside the translation stick configuration slot 10. This can solve the problem that desktop translation machines lack physical support and power supply interfaces for detachable peripherals and are not convenient for integrated management of peripherals. It can also achieve orderly storage, interface alignment and stable power supply of the translation stick 2 on the translation machine host 1. The translation stick 2 is assembled in the translation stick configuration slot 10. The charging interface 20 of the translation stick 2 is electrically connected to the charging head 11. This can solve the problem that the peripherals need to be charged separately and the charging and storage are separated, which leads to cumbersome use processes. It can also achieve the process optimization of charging, accessing, charging and using the peripherals in place. The power module charges the translation stick 2, which can solve the problem that the translation stick 2 has limited battery life and frequent power outages that affect on-the-spot translation. It can also achieve continuous energy replenishment and improved usability of the translation stick 2 at the desktop workstation. The translation stick 2 can be placed close to the sound source in noisy environments to receive voice signals. This addresses the problem of low signal-to-noise ratio (SNR) and reduced speech recognition and translation accuracy associated with far-field pickup in high-noise environments. Close-talk pickup improves the signal-to-noise ratio (SNR) and transcription and translation robustness. SNR refers to the ratio of speech signal strength to background noise intensity, typically expressed in decibels (dB). In this embodiment, when the translation stick 2 is held close to the sound source (the speaker's mouth) to pick up sound, the amplitude of the speech signal increases significantly (due to the close distance and minimal energy attenuation). Background noise remains relatively constant or decreases (due to the narrow pickup range of the close-talk microphone). This significantly improves the SNR, ensuring clear and discernible speech. Transcription robustness refers to the process of converting speech signals into text, ensuring that the transcription results remain accurate, stable, and error-free under varying noise conditions, accents, and speaking speeds. Translation robustness refers to the accuracy and consistency of translation results across different scenarios and noise backgrounds. For machine translation, the more accurate the input text and the fewer errors and omissions, the more reliable the translation.

[0012] In this embodiment, the translation stick 2 translates and plays received voice signals, resolving the lack of immediate feedback and playback at a distance from the host, enabling closed-loop instant translation and local broadcasting close to the sound source. When the translation stick 2 is installed in the configuration slot and charging, its own pickup is disabled, and the translation unit 1 provides translation. This resolves the issues of parallel channel conflict, crosstalk, and howling caused by simultaneous audio pickup from both the host and the stick. Automatic channel management based on charging / parking status is implemented, avoiding acoustic interference and conserving power at the stick end.

[0013] In this embodiment, the microphone array 3 is distributed on the housing of the translator host 1. This solves the problem that a single fixed-point microphone on a desktop translator cannot cover multiple people speaking from multiple directions. It achieves array-based multi-unit coverage and provides a physical basis for beamforming and spatial filtering. When the microphone of the translator stick 2 is turned off, the microphone array 3 locates and selects sounds from different directions, picking up the sound from the speaker and separating the voice signal of the main speaker. This can solve the problem of difficulty in extracting the main sound source in far-field environments such as conferences and reception desks with multiple speakers, strong reverberation, and ambient noise. It achieves array-based DOA positioning and beam pointing, suppresses interfering sound sources, and improves the intelligibility and recognition accuracy of the main speech.

[0014] In this embodiment, the translator host 1 monitors the electrical connection status between the translator wand 2 and the charging head 11. This addresses the system's lack of awareness of the peripheral's status and the inability to coordinate modes based on the peripheral's presence or absence. This implements a software and hardware state machine driven by electrical connection as a reliable trigger, providing a criterion for automatically switching pickup paths. When the translator wand 2 is disconnected from the charging head 11, the microphone array 3 is controlled to shut down. This addresses the channel competition and acoustic loop overlap caused by the host array still participating in pickup when the translator wand 2 is lifted for close-talk operation. This enables mutually exclusive switching between close-talk operation at the wand end and far-talk operation at the host, avoiding interference from the dual-path parallelism. When the translator wand 2 is charging in its slot and its own microphone is turned off, the microphone array 3 of the translator host 1 takes over the audio pickup and passes it on to the host for translation and playback. This addresses the conflict between the need for far-talk pickup at a fixed workstation and the need for peripherals to be parked and charged in a desktop scenario, enabling adaptive switching between the wand in place (charging) and the array for far-talk; and the wand out of place (close-talk) and the array off.

[0015] In this embodiment, the modular hardware architecture of the host, translation stick, physical storage for the translation stick, charging interface 20, and microphone array 3 can solve the problems of the single hardware structure, poor scalability, and difficulty in coupling with software functions of desktop translation machines, and realize software and hardware collaboration and expandable hardware base for multiple scenarios. Through automatic power on and off and pickup path management based on connection status (i.e., charging turns off the stick end pickup, and disconnecting turns off the array, two control logics), it can solve the problems of cumbersome manual switching by users, high misoperation rate, and translation interruption or error caused by inconsistent status, and realize automatic scene adaptation with zero learning cost and stable and consistent user experience. The separation of the main speaking user's voice signal during the array pickup stage and then handing it over to the host for translation and playback can solve the problem of recognition crosstalk caused by the main speaker not being prominent in a multi-person environment, and realize the improvement of the purity of the main channel voice, thereby improving the translation accuracy and delay stability. In general, in this embodiment, through the linkage control of the host, the translation stick 2, the configuration slot (including the charging head 11), the electrical connection status monitoring and the pickup array 3, it is possible to solve the systemic problems of the desktop translation machine such as poor hardware scalability, the non-adaptability of the pickup path in a noisy, multi-speaker environment, and the easy conflict of parallel channels, and achieve the overall technical effect of automatic switching of the pickup path based on hardware structure and status perception, main voice enhancement and multi-scene adaptation.

[0016] In this embodiment, the translation machine host establishes a data connection with a mobile smart terminal running a translation control app via a wireless communication module, receiving and processing language pair and translation mode setting instructions, offline language package or local model download and activation instructions, and cloud or local translation engine call switching instructions issued by the mobile smart terminal. This solution can address the problems of limited host-side interactive capabilities and cumbersome language pair and mode switching, as well as the large footprint of pre-installed offline language packages and local models and the difficulty of updating and maintaining them, enabling on-demand downloading and activation, incremental updates, and storage savings. This solution can also address the issues of fragmented strategies and slow switching across multiple scenarios (simultaneous, alternating, conversational, etc.). The mobile smart terminal can uniformly issue combined strategies for language pairs, modes, and engines, quickly adapting to different usage environments. This solution can also address the uncontrollable operation and maintenance issues caused by decentralized configuration and version management, enabling centralized strategy management, version consistency, and rapid rollback and upgrades.

[0017] It should be noted that the translation machine host 1 may include a state judgment module and an environmental noise detection unit. The environmental noise detection unit is used to collect background noise energy and spectrum distribution when the translation stick 2's own pickup is turned off and the pickup array 3 is in a working candidate state. The state judgment module generates array working parameters based on the background noise energy and spectrum distribution and historical scene parameters and sends them to the pickup array 3 through a control interface to dynamically set the beam width, pointing angle, front-end gain and echo suppression threshold of the pickup array 3, thereby realizing adaptive optimization of the pickup array 3 parameters and ensuring that the pickup array 3 maintains clear pickup in a steady state under different noise conditions.

[0018] Preferably, the translation stick configuration slot 10 includes a first configuration slot 101 and a second configuration slot 102; the translation stick 2 includes a first translation stick 21 and a second translation stick 22 for correspondingly configuring into the first configuration slot 101 and the second configuration slot 102; when the first translation stick 21 and the second translation stick 22 are correspondingly assembled into the first configuration slot 101 and the second configuration slot 102, the charging interface 20 of the first translation stick 21 and the second translation stick 22 are electrically connected to the charging head 11 provided in the first configuration slot 101 and the second configuration slot 102 respectively, and the power module charges the first translation stick 21 and the second translation stick 22, and the first translation stick 21 and the second translation stick 22 turn off their own pickups in the charging state.

[0019] In this embodiment, the translation stick configuration slot 10 includes a first configuration slot 101 and a second configuration slot 102, and the translation stick 2 includes a first translation stick 21 and a second translation stick 22 for correspondingly configuring the first configuration slot 101 and the second configuration slot 102. When the two are assembled in the corresponding slots, their charging interfaces 20 are electrically connected to the charging heads 11 in the configuration slots, and are charged by the power modules respectively. When the charging state is turned off, the microphone of the translation stick is turned off, which can solve the problem of frequent switching and low efficiency of a single translation stick under the requirements of multiple scenes, multiple languages ​​or multiple people simultaneously translating. In this way, two translation sticks can be configured at the same time in a desktop translator, which can support multiple people to speak close together and translate, reducing waiting time. At the same time, automatically turning off the microphone of the translation stick 2 itself in the charging state can avoid channel interference and acoustic crosstalk caused by the two translation sticks picking up sound at the same time, thereby realizing collaborative management of multiple translation sticks, automated pickup path control, and higher equipment utilization and scene coverage capabilities.

[0020] It should be noted that the translation machine host 1 can include a multi-stick management module and an identification unit. The identification unit uses RFID or NFC to identify the first and second translation sticks 21, 22 and bind them to corresponding configuration slots. The multi-stick management module assigns close-talk priority and working language pair to the first and second translation sticks 21, 22 based on the conversation role, target language pair, and the battery level of the translation stick 2. When either translation stick is removed from its corresponding configuration slot, the multi-stick management module issues a pickup shutdown and continuous charging command to the remaining translation stick 2, enabling conflict-free relaying and efficient scheduling in multi-user, multi-language scenarios. The conversation role refers to the functional label assigned by the system to a participant or device, such as Chinese speaking terminal or English speaking terminal, which determines language direction and routing permissions. The target language pair refers to the translation direction configuration, such as translating zh to en, en to zh, or bidirectional. The target language pair influences the selection of models, dictionaries, or vocoders for ASR, MT, or TTS. The close-talk priority defines the order in which the close-talk channel becomes active when both translation sticks are potentially picked up, to avoid preemption.

[0021] Preferably, when the microphones of the first translation stick 21 and the second translation stick 22 are turned off, the microphone array 3 locates and selects sounds from different directions, picks up the sound from the speaker's direction, separates the voice signal of the main speaking user, and gives it to the translation machine host 1 for translation and playback.

[0022] In this embodiment, when the microphones of the first translation stick 21 and the second translation stick 22 are turned off, the microphone array 3 locates and selects sounds from different directions, picks up the sound from the direction of the speaker, and separates the voice signal of the main speaker to the translation machine host 1 for translation and playback. This can solve the problem that in a multi-translation stick system, when all the microphones near the speaking stick end are not working, the desktop translation machine lacks effective far-field sound pickup capability and cannot cope with multi-directional sound scenarios such as meetings or information desks. The system can intelligently switch to the array pickup mode of the host end, selectively collect the voice of the main speaker through spatial positioning (DOA) and beamforming technology, and suppress environmental noise and other directional interference, thereby achieving main voice enhancement in a multi-speaker environment, improving the accuracy and stability of speech recognition and translation, and ensuring that the device still has high-quality voice collection capabilities when there is no stick-end pickup.

[0023] It should be noted that the microphone array 3 may include an adaptive beamforming unit, a direction tracking unit and a sidelobe suppression unit. The direction tracking unit obtains the direction of arrival (DOA) of the sound source based on multi-channel correlation-delay estimation and performs Kalman filtering on the speaker's movement. The adaptive beamforming unit dynamically generates the main and sub-beams according to the direction of arrival (DOA) of the sound source and the Kalman filtering prediction results, and sets a null in the interference direction. The sidelobe suppression unit combines with the reference microphone to achieve frequency band weighting and residual noise suppression. When the microphones of the first translation stick 21 and the second translation stick 22 are both turned off, the adaptive beamforming unit, the direction tracking unit and the sidelobe suppression unit are linked under the scheduling of the host controller to implement narrow beam pointing and time-varying gain control for the located direction of the main speaker, and output the main voice signal to the translation machine host 1 for translation and playback, thereby meeting the requirements of maintaining stable main sound source lock and high SNR in multi-speaker and mobile speaking scenarios.

[0024] Preferably, the translation machine host 1 monitors the connection status of the first translation stick 21, the second translation stick 22 and the charging head 11 set in the first configuration slot 101, the second configuration slot 102. When the connection status is disconnected, the pickup array 3 is controlled to be turned off.

[0025] In this embodiment, the translation machine host 1 monitors the electrical connection status of the first translation stick 21, the second translation stick 22 and the charging head 11 in the first configuration slot 101 and the second configuration slot 102, and controls the microphone array 3 to shut down when the connection status is disconnected. This can solve the problem that the multi-translation stick system lacks an automated sound pickup control mechanism based on the hardware connection status and cannot prevent the array and the stick end from picking up sounds at the same time, causing resource conflicts and acoustic feedback. In this embodiment, the connection status of the charging interface 20 is used as a reliable hardware trigger signal to achieve automatic start and stop control of the array pickup: when a translation stick 2 is removed for use, the array is shut down to avoid dual-channel interference; when the stick end is put back for charging, the array can be restarted for far-field pickup. This can improve the adaptability and stability of the system in multiple scenarios, reduce manual switching steps, and reduce the risk of misoperation.

[0026] It should be noted that the translation machine host 1 may include a delay control module and a disconnection confirmation module. When it is detected that the electrical connection between the first translation stick 21 or the second translation stick 22 and the charging head 11 in the corresponding configuration slot is disconnected, the delay control module starts a configurable hysteresis timer. During the hysteresis period, the disconnection confirmation module integrates the detection data of the in-position sensor (any one of the Hall sensor, optical sensor, and micro switch) and the accelerometer for off-position verification; if it is confirmed to be reconnected or judged to be instantaneous looseness within the hysteresis period, the array closing instruction is canceled; if it is still determined to be a real disconnection at the end of the hysteresis period, a closing instruction is sent to the pickup array 3 and the channel status is updated synchronously, thereby suppressing frequent switching caused by false touches and ensuring channel stability.

[0027] Preferably, the disconnection in the connection state includes: the electrical connection between the first translation stick 21 and the charging head 11 set in the first configuration slot 101 is disconnected, or the electrical connection between the second translation stick 22 and the charging head 11 set in the second configuration slot 102 is disconnected, or the electrical connection between the first translation stick 21, the second translation stick 22 and the charging heads 11 set in the first configuration slot 101, and the second configuration slot 102 are all disconnected.

[0028] In this embodiment, the disconnection state includes: the first translation stick 21 is disconnected from the charging head 11 of the first configuration slot 101, or the second translation stick 22 is disconnected from the charging head 11 of the second configuration slot 102, or both are disconnected. This can solve the defect that the single connection state detection logic cannot cover the use scenario of multiple translation sticks, and avoid the pickup conflict caused by the inability to turn off the array in time due to the removal of a translation stick. In this embodiment, multiple judgment conditions are provided to ensure that as long as any translation stick is in the removed working state, the host can respond and turn off the array pickup, preventing the sound source aliasing and echo problems caused by the simultaneous operation of the array and the close-talking pickup. This more refined connection and disconnection judgment mechanism can improve the pickup path switching accuracy and scene adaptability of the multi-translation stick system, making hardware collaboration more intelligent and reliable.

[0029] It should be noted that when only one of the first translation stick 21 or the second translation stick 22 is electrically disconnected from its corresponding charging head 11, the translation machine host 1 keeps the microphone array 3 closed and designates the disconnected translation stick 2 as the main voice channel, and puts the undisconnected translation stick 2 into the charging and microphone-off state; when the first translation stick 21 and the second translation stick 22 are both electrically disconnected from their respective charging heads 11, the microphone array 3 is kept closed and the status indicator light is turned on, prompting the user that the translation stick 2 has been selected as the close-talking device to enter the conversation process, thereby refining the channel strategy in the disconnection situation and improving operability.

[0030] Preferably, a peripheral expansion concave curved surface 4 is formed on the outer side of the shell of the translation machine host 1, and the concave direction of the peripheral expansion concave curved surface 4 is toward the inside of the shell of the translation machine host 1, so as to form a peripheral accommodating and supporting space on the outer side of the shell of the translation machine host 1, which is used to accommodate and support peripherals used with the translation machine; the translation stick configuration slot 10 is located next to the peripheral expansion concave curved surface 4, and is located at different positions on the outer side of the shell of the translation machine host 1 from the peripheral accommodating and supporting space.

[0031] In this embodiment, a peripheral expansion concave surface 4 is formed on the outer side of the housing of the translation machine host 1, and the concave direction of the curved surface is toward the inside of the host, so as to form a peripheral accommodating support space for accommodating and supporting peripherals used with the translation machine. The translation stick configuration slot 10 is located next to the concave curved surface, and is located in a different part of the housing from the peripheral accommodating support space. This can solve the problems of fixed placement of peripherals of desktop translation machines, low space utilization, and the unsightly and easy loss of peripherals and the host when they are placed separately. In this embodiment, by forming a dedicated concave space in the body of the translation machine host 1, a stable and integrated storage and support position is provided for the peripherals supporting the translation machine (such as headphones, expansion microphones, cameras, barcode scanners, mobile phones, etc.). At the same time, it is arranged in a partition with the translation stick configuration slot 10 to avoid mutual interference, thereby improving the overall appearance integration of the whole machine, the convenience of peripheral management, and optimizing the operation and management in the desktop scenario.

[0032] Preferably, the peripheral expansion concave surface 4 includes a first concave surface 40 and a second concave surface 41; the first concave surface 40 and the second concave surface 41 are respectively formed at different positions on the outside of the shell of the translation machine host 1 to form peripheral accommodating support spaces at different positions on the outside of the shell of the translation machine host 1; the peripheral accommodating support spaces at different positions are used to accommodate the same type of peripherals used with the translation machine, or to accommodate different types of peripherals used with the translation machine.

[0033] In this embodiment, the peripheral expansion concave surface 4 includes a first concave surface 40 and a second concave surface 41, which are formed in different parts of the host housing to form peripheral storage support spaces at different locations. These spaces can accommodate the same or different types of peripherals, which can solve the problem that a single peripheral storage location cannot simultaneously meet the storage needs of multiple types and quantities of peripherals, while also improving the device's peripheral adaptability in different working scenarios. In this embodiment, multi-point storage is supported. Users can place the same type of peripherals separately as needed (such as two pairs of headphones) to support multiple people, or accommodate different types of peripherals to expand functions (such as headphones and video modules), thereby enhancing the multi-functional expandability of the host and improving the spatial organization and on-site deployment flexibility of the entire machine.

[0034] Preferably, an external device bracket 5 is provided in the external device expansion concave surface 4, and the external device bracket 5 is used to fix the external device used with the translation machine, so that the external device used with the translation machine is located in the external device accommodating support space.

[0035] In this embodiment, an external device holder 5 is positioned within the concave curved surface 4 of the peripheral extension. This holder is used to secure the external device used with the translator, positioning it within the external device storage and support space. This solves the problem of securing the external device in its storage position. The external device holder 5 provides stable support and fixation for the external device, maintaining its stable position. Furthermore, the combination of the concave curved surface and the holder not only provides storage space for the external device but also secures it, enhancing its safety, durability, and ease of use.

[0036] Preferably, the peripheral bracket 5 fixes the peripheral used with the translation machine through a fixed connection method or a detachable connection method; the detachable connection method includes a snap-on method, a suction cup method or a magnetic method.

[0037] In this embodiment, the peripheral bracket 5 can be fixed or detachable. The detachable connection method includes snap connection, suction cup or magnetic connection, which is convenient for users to quickly disassemble and replace peripherals. Magnetic connection, snap connection and other methods can improve the efficiency of assembly and disassembly.

[0038] Preferably, when the peripheral device used with the translator is used with the translator, it is connected to the translator host for communication, provides a control signal to the translator host to control the translator host and / or receives a control signal provided by the translator host and is controlled by the translator host, so as to cooperate with the translator host to realize the preset function; or, when the peripheral device used with the translator is used with the translator, it is not connected to the translator host for communication, and independently realizes its own preset function.

[0039] In this embodiment, the peripherals used with the translator can connect and communicate with the host computer to achieve collaborative control and functional expansion; or they can independently complete their own functions without connecting to the communication. This can solve the problem that the peripherals of desktop translators have single functions and must rely on the host computer to work. In this embodiment, active collaborative peripherals (such as control panels that can control the host computer's operating mode and cameras that share data with the host) and independent peripherals (such as wireless headphones with built-in storage and processing capabilities) are compatible, thereby significantly expanding the functional boundaries and application scenarios of the translator. This not only improves the scalability and adaptability of the system, but also supports users to combine hardware on demand to achieve diverse operating modes and business functions.

[0040] It should be pointed out that the above embodiments are only preferred specific implementation methods of the present invention, and the protection scope of the present invention is not limited thereto. Any changes or replacements that can be easily thought of by any technician familiar with this technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A multi-scenario intelligent desktop translator, characterized in that: include: A translation machine host, wherein a translation stick configuration slot is provided on the housing of the translation machine host, a charging head is provided inside the translation stick configuration slot, and the charging head is electrically connected to a power module inside the housing of the translation machine host; the translation machine host establishes a data connection with a mobile smart terminal running a translation control APP through a wireless communication module, receives and processes language pair and translation mode setting instructions, offline language package or local model download and activation instructions, and cloud or local translation engine call switching instructions issued by the mobile smart terminal; A translation stick is mounted in the translation stick configuration slot and is used for receiving voice signals within a close range near a sound source in a noisy environment by a user, and translating and playing the received voice signals. The translation stick is provided with a charging port. When the translation stick is mounted in the translation stick configuration slot, the charging port of the translation stick is electrically connected to a charging head provided in the translation stick configuration slot, and the power module charges the translation stick. The translation stick turns off its own pickup when charging. The microphone array is distributed on the shell of the translation machine host and is used to locate and select sounds from different directions when the microphone of the translation stick itself is turned off, pick up the sound from the direction of the speaker, separate the voice signal of the main speaking user, and give it to the translation machine host for translation and playback; the translation machine host monitors the connection status of the electrical connection between the translation stick and the charging head set in the translation stick configuration slot, and controls the microphone array to be turned off when the electrical connection between the translation stick and the charging head set in the translation stick configuration slot is disconnected.

2. The multi-scenario intelligent desktop translator according to claim 1 is characterized in that: The translation stick configuration slot includes a first configuration slot and a second configuration slot; the translation stick includes a first translation stick and a second translation stick for correspondingly configuring into the first configuration slot and the second configuration slot; when the first translation stick and the second translation stick are correspondingly assembled into the first configuration slot and the second configuration slot, the charging interfaces of the first translation stick and the second translation stick are electrically connected to the charging heads provided in the first configuration slot and the second configuration slot respectively, the power module charges the first translation stick and the second translation stick, and the first translation stick and the second translation stick turn off their own pickups when in the charging state.

3. The multi-scenario intelligent desktop translator according to claim 2, characterized in that: When the microphones of the first and second translation sticks are turned off, the microphone array locates and selects sounds from different directions, picks up the sound from the speaker's direction, separates the voice signal of the main speaker, and gives it to the translation machine host for translation and playback.

4. The multi-scenario intelligent desktop translator according to claim 2, characterized in that: The translation machine host monitors the connection status of the first translation stick, the second translation stick and the charging heads set in the first configuration slot and the second configuration slot. When the connection status is disconnected, the pickup array is controlled to be turned off.

5. The multi-scenario intelligent desktop translator according to claim 4 is characterized in that: The disconnection in the connection state includes: the electrical connection between the first translation stick and the charging head set in the first configuration slot is disconnected, or the electrical connection between the second translation stick and the charging head set in the second configuration slot is disconnected, or the electrical connections between the first translation stick, the second translation stick and the charging heads set in the first configuration slot and the second configuration slot are all disconnected.

6. The multi-scenario intelligent desktop translator according to any one of claims 1 to 5, characterized in that: The outer side of the housing of the translation machine host is formed with an external device expansion concave curved surface, and the concave direction of the external device expansion concave curved surface is toward the interior of the housing of the translation machine host, so as to form an external device accommodating and supporting space on the outer side of the housing of the translation machine host for accommodating and supporting external devices used with the translation machine; The translation stick configuration slot is located beside the peripheral extended concave surface, and is located at different positions on the outside of the translation machine host housing than the peripheral accommodating support space.

7. The multi-scenario intelligent desktop translator according to claim 6, characterized in that: The peripheral expansion concave surface includes a first concave surface and a second concave surface; the first concave surface and the second concave surface are respectively formed at different positions on the outside of the shell of the translation machine host to form peripheral accommodating support spaces at different positions on the outside of the shell of the translation machine host; the peripheral accommodating support spaces at different positions are used to accommodate the same type of peripherals used with the translation machine, or to accommodate different types of peripherals used with the translation machine.

8. The multi-scenario intelligent desktop translator according to claim 6, characterized in that: An external device bracket is provided in the inner concave curved surface of the external device extension, and the external device bracket is used to fix the external device used with the translation machine, so that the external device used with the translation machine is located in the external device accommodating support space.

9. The multi-scenario intelligent desktop translator according to claim 8, characterized in that: The peripheral bracket fixes the peripheral used with the translation machine through a fixed connection method or a detachable connection method; the detachable connection method includes a snap connection method, a suction cup method or a magnetic method.

10. The multi-scenario intelligent desktop translator according to claim 6, characterized in that: When the peripheral device used with the translation machine is used with the translation machine, it is connected to the translation machine host for communication, provides a control signal to the translation machine host to control the translation machine host and / or receives a control signal provided by the translation machine host and is controlled by the translation machine host, so as to cooperate with the translation machine host to realize the preset function; or, when the peripheral device used with the translation machine is used with the translation machine, it is not connected to the translation machine host for communication, and independently realizes its own preset function.

Images