A stand-alone voice AI wearable interaction method, application thereof, device and storage medium

Abstract

The application discloses an independent voice AI wearable interaction method and application thereof, a device and a storage medium. The method comprises the following steps: acquiring a triggering state of a physical key on a device; when the physical key is triggered, a master control circuit board controls a cellular communication module to switch from a low-power state to a working state, and a voice data channel with a remote AI server is established; a user voice signal is collected through an audio collection module, and after being processed by the master control circuit board, the voice signal is uploaded to the remote AI server through the cellular communication module; voice response data returned by the remote AI server is received through the cellular communication module, and after being processed by the master control circuit board, the voice response data is played through an audio output device. The application realizes the independent communication capability of the wearable device, and solves the voice interaction demand in a mobile phone disabled scene.

Description

Technical Field

[0001] This application relates to the field of wearable device technology, particularly to the field of artificial intelligence voice interaction technology, and especially to a stand-alone voice AI wearable interaction method, its application, device, and storage medium. Background Technology

[0002] With the rapid development of artificial intelligence technology, intelligent voice assistants based on large language models have been widely used in daily life and work. Currently, users interact with AI through voice in the following ways: First, smartphone + AI application scenario: users need to take out their phone, unlock it, and open the application before they can interact with it, which involves many steps and is extremely inconvenient in situations where it is not convenient to use a phone (such as driving, exercising, or working). Second, smart speaker scenario: relying on WiFi networks and fixed power sources, it cannot be carried around and its application is limited to indoor scenarios. Third, smart headphones + mobile phone relay scenario: such as Apple AirPods with Siri, Google Pixel Buds with Gemini, etc., but this type of solution highly relies on the smartphone as a relay device, users still need to carry their phones with them, and the voice interaction link is too long (headphones → phone → cloud → phone → headphones), resulting in a large response delay.

[0003] A Chinese patent with publication number CN 110086930 A discloses a voice interaction method, a wearable device, and a computer-readable storage medium. This solution triggers a voice assistant via a physical button, activating related functions upon receiving a voice signal. However, this solution requires the wearable device to maintain a Bluetooth connection with a paired terminal such as a smartphone, relying on the paired terminal for network communication capabilities. This makes voice interaction impossible in special scenarios where mobile phone use is prohibited, such as hospital operating rooms, gas stations, and military-controlled areas. Furthermore, existing AI wearable devices, such as the Limitless Pendant, Rabbit R1, and Humane AI Pin, are problematic. The Rabbit R1 and Humane AI Pin have been discontinued due to poor user experience, and all these devices share common issues: reliance on Bluetooth pairing with a smartphone, the need for activation via a wake word (awkward in public and posing privacy risks), and short battery life (typically 1-2 days).

[0004] In summary, the existing technology lacks an independent voice AI wearable interaction method, its application, device, and storage medium that does not require a mobile phone as a relay, does not require a wake word, has low power consumption and long battery life. Summary of the Invention

[0005] To address the shortcomings or deficiencies of the existing technologies, this application aims to provide an independent voice AI wearable interaction method, its application, device, and storage medium, thereby resolving the following technical problems in the prior art: existing wearable voice interaction devices rely on Bluetooth connections with paired terminals to achieve network communication, resulting in the inability to realize voice interaction functions in special scenarios where the use of mobile phones is prohibited, such as hospital operating rooms, gas stations, and military control zones; existing devices have crude power management strategies for cellular communication modules, resulting in high standby power consumption and affecting device battery life; and the single physical button interaction method has limited functionality, making it difficult to meet diverse operational needs and lacking an effective real-time feedback mechanism.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution: This application proposes a stand-alone voice AI wearable interaction method, including: Get the trigger status of physical buttons on the device; When the physical button is triggered, the main control circuit board controls the device to switch from a low-power state to a working state and establishes a voice data channel with the remote AI server. Based on the collected user voice signals, the data is processed by the main control circuit board and then uploaded to the remote AI server via the cellular communication module. The voice response data returned by the remote AI server is received through the cellular communication module, processed by the main control circuit board, and played through the device or an external audio output device.

[0007] More preferably, it further includes: playing the processed audio signal from the main control circuit board through a short-range communication module and an external audio output device, wherein the short-range communication module is connected to the external audio output device via short-range communication.

[0008] More preferably, when the physical button is triggered, the method further includes: the main control circuit board controlling the power management module to switch the cellular communication module from a low-power state to a working state, and establishing a voice data channel with the remote AI server.

[0009] More preferably, when the physical button is not triggered, the main control circuit board controls the power management module to put the cellular communication module into a deep sleep mode, in which the power consumption of the cellular communication module is less than 10μA.

[0010] More preferably, the power management module also supports the discontinuous reception (DRX) mode of the cellular communication module; When the physical button is not triggered and the device is in standby mode, the main control circuit board controls the cellular communication module to listen to the paging channel at a preset period in the DRX mode; The power consumption in the Discontinuous Receive (DRX) mode is 1-3mA, which is between the power consumption in the deep sleep mode and the power consumption in the operating mode.

[0011] More preferably, when the physical button is triggered, the cellular communication module switches from discontinuous reception (DRX) mode or deep sleep mode to the working mode and establishes a voice data channel within 800ms.

[0012] More preferably, it also includes: when the physical button is triggered, the main control circuit board controls the vibration motor installed in the device to generate a first vibration mode as operation confirmation feedback; More preferably, after the audio acquisition module completes voice acquisition, the main control circuit board controls the vibration motor to generate a second vibration mode as feedback that the voice reception is complete.

[0013] More preferably, it further includes: detecting the pressing pattern of the physical button, which includes: Single press: Press duration is less than the first threshold; Double press: Two single presses are detected within a first preset duration; Three presses: Three single presses are detected within the first preset duration; Long press: Press duration exceeds the second threshold; The main control circuit board executes the corresponding operation command based on the detected pressing mode.

[0014] More preferably, the operation instruction includes: the single press triggering a voice dialogue process with the remote AI server; The double press triggers a replay of the voice response data previously returned by the remote AI server; The three presses trigger a device status broadcast, and the device status includes the remaining power of the rechargeable battery, the information of the currently connected external Bluetooth audio output device, and the information of the currently activated AI service. The long press triggers the Bluetooth communication module to enter pairing mode; When a single press is detected during a voice conversation, the playback of the current voice response is interrupted and the voice data channel is closed.

[0015] This application also proposes an application based on a stand-alone voice AI wearable interaction method for scenarios such as hospital operating rooms, gas stations, conference rooms, military control zones / classified units, and some mines / tunnels.

[0016] This application also proposes a stand-alone voice AI wearable interactive device, wherein the device includes a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the method described thereon.

[0017] This application also proposes a computer-readable storage medium having computer program instructions stored thereon, which can be executed by a processor to implement the method.

[0018] Compared with the prior art, this application has the following technical effects: This application establishes a voice data channel directly with a remote AI server by using a cellular communication module, thus eliminating the dependence on a pairing terminal and enabling independent communication capabilities for wearable devices. It also solves the technical problem of not being able to realize voice interaction functions in special scenarios where the use of mobile phones is prohibited, such as hospital operating rooms, gas stations, and military control zones.

[0019] This application employs a three-level power management strategy to reduce standby power consumption to below 10μA in deep sleep mode, control power consumption to 1-3mA while maintaining network connectivity in DRX mode, and achieve 800ms fast wake-up in working mode. This balances the conflict between standby power consumption and fast response, significantly extending the device's battery life. With a 300mAh battery capacity, the theoretical standby time in deep sleep mode exceeds 1250 hours, and the standby time in DRX mode is approximately 100-300 hours, which is more than 100 times better than the traditional always-on connectivity mode.

[0020] This application utilizes a multi-mode press recognition mechanism with a single physical button to achieve various operation commands, such as triggering voice dialogue with a single press, replaying response with a double press, broadcasting device status with a triple press, triggering Bluetooth pairing with a long press, and interrupting playback with a single click during a conversation. This simplifies hardware design while improving interactive flexibility and meeting diverse operational needs.

[0021] This application utilizes a graded feedback mechanism with a vibration motor to generate a first vibration mode as operation confirmation feedback when a physical button is triggered, and a second vibration mode as reception completion feedback after voice acquisition is completed. This provides instant tactile confirmation on screenless wearable devices, making it suitable for scenarios where a screen cannot be viewed, and enhancing the user's sense of operation confirmation.

[0022] This application presents a solution for connecting external audio output devices via a near-field communication module, which supports the transmission of voice response data to Bluetooth headphones or Bluetooth speakers for playback, thereby improving sound quality and user experience and adapting to the needs of different usage scenarios. Attached Figure Description

[0023] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This application presents an embodiment of a stand-alone voice AI wearable interaction method flowchart, illustrating the complete interaction process of physical button triggering, cellular communication, voice acquisition and playback. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] In a typical configuration of this application, the terminal and the service network devices each include one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0026] Memory may include non-persistent storage in computer-readable storage media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable storage media.

[0027] Computer-readable storage media include permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. Information can be computer program instructions, data structures, program devices, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only optical disc (CD-ROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0028] This application provides a stand-alone voice AI wearable interaction method, application, device, and computer-readable storage medium. The method triggers the wearable device to switch from a low-power state to an active state via a physical button, and utilizes a cellular communication module to directly establish a voice data channel with a remote AI server, achieving voice interaction functionality independent of the paired terminal.

[0029] This application presents an independent voice data transmission solution based on a cellular communication module, eliminating reliance on paired devices such as mobile phones; a three-level power management strategy (deep sleep less than 10μA, DRX mode 1-3mA, and working mode) significantly reduces standby power consumption while maintaining network connectivity; the cellular communication module quickly establishes a voice data channel within 800ms, achieving low-latency response; multi-mode recognition of a single physical button (single, double, triple, and long press) and corresponding operation command mapping enable rich interactive functions through simple hardware; and a vibration motor graded feedback mechanism provides instant tactile confirmation.

[0030] This application addresses the voice interaction needs of wearable devices in scenarios where pairing terminals cannot be used, while balancing the conflict between standby power consumption and rapid response. It is particularly suitable for special scenarios such as hospital operating rooms, gas stations, conference rooms, and military control zones.

[0031] Specifically, such as Figure 1 As shown in one embodiment of this application, a stand-alone voice AI wearable interaction method includes: Get the trigger status of physical buttons on the device; When the physical button is triggered, the main control circuit board controls the device to switch from a low-power state to a working state and establishes a voice data channel with the remote AI server. Based on the collected user voice signals, the voice response data processed by the main control circuit board is uploaded to the remote AI server through the cellular communication module; The voice response data returned by the remote AI server is received through the cellular communication module, processed by the main control circuit board, and played through the device or an external audio output device.

[0032] The cellular communication module establishes a TCP / IP voice data channel directly with the remote AI server via a 4G or 5G network, eliminating the need for a Bluetooth-paired mobile phone as a relay device. The audio acquisition module uses a MEMS microphone to collect user voice signals, and the main control circuit board performs noise reduction and audio encoding on the collected voice signals before uploading them through the cellular communication module. By establishing a direct voice data channel with the remote AI server using a cellular communication module, the dependence on a paired terminal is eliminated, enabling independent communication capabilities for wearable devices and solving the technical problem of not being able to use voice interaction in scenarios where mobile phones are disabled.

[0033] The physical button triggering method avoids the inconvenience and privacy risks associated with wake-word activation in public places. The power management module, through multi-level power management, switches the cellular communication module to a low-power state during standby, significantly extending battery life. The audio acquisition module, with its multi-microphone array configuration, can effectively collect user voice signals in noisy environments, enhancing the AI ​​interaction experience.

[0034] The aforementioned device includes: physical buttons, a main control circuit board, a cellular communication module, an audio acquisition module, an audio output module, and a power management module. The physical buttons are mechanical microswitches mounted on the device's casing and can be activated by the user pressing them with their fingers. The main control circuit board uses a microcontroller based on the ARM Cortex-M4 architecture.

[0035] More preferably, the solution further includes: transmitting the processed audio from the main control circuit board to an external audio output device via a near-field communication module, wherein the near-field communication module is connected to the external audio output device via near-field communication. The near-field communication module uses a Bluetooth communication module, supporting Bluetooth 5.0 and above, and establishes a connection with the external audio output device via the Bluetooth A2DP protocol. The external audio output device includes Bluetooth headphones or Bluetooth speakers. This solution supports multiple audio output methods, adapts to different usage scenarios, and improves sound quality and user experience.

[0036] More preferably, when the physical button is triggered, the method further includes: the main control circuit board controlling the power management module to switch the cellular communication module from a low-power state to a working state, and establishing a voice data channel with the remote AI server. The power management module achieves refined power consumption management by controlling the power supply and working mode of the cellular communication module.

[0037] More preferably, when the physical button is not triggered, the main control circuit board controls the power management module to put the cellular communication module into a deep sleep mode. In this deep sleep mode, the power consumption of the cellular communication module is less than 10μA. In this deep sleep mode, the cellular communication module shuts down the radio frequency circuit and the baseband processing unit, keeping only the minimum clock circuit running, thereby reducing power consumption to below 10μA and significantly extending the device's battery life.

[0038] More preferably, the power management module also supports the discontinuous reception (DRX) mode of the cellular communication module; When the physical button is not triggered and the device is in standby mode, the main control circuit board controls the cellular communication module to listen to the paging channel at a preset period in the DRX mode; The power consumption in the Discontinuous Receive (DRX) mode is 1-3mA, which is between the power consumption in the deep sleep mode and the power consumption in the operating mode.

[0039] In the Discontinuous Reception (DRX) mode, the cellular communication module maintains an RRC connection with the base station and listens to the paging channel at a preset period of 1.28 seconds. While maintaining network connectivity, the power consumption is controlled at 1-3mA, balancing response speed and energy consumption.

[0040] That is, in this embodiment, the power management module supports three working modes, which are uniformly managed by the main control circuit board.

[0041] Mode 1 is the deep sleep mode.

[0042] Its power consumption is less than 10μA, and its theoretical standby time exceeds 6 years. Its trigger condition is that the device is in an inactive state for more than a preset timeout period, which is 15 seconds by default. Its state is that the cellular communication module is powered off, the near-field communication module is powered off, the main control circuit board enters STOP mode, and only the interrupt signal from the physical button can wake up the system.

[0043] Mode 2 is the DRX discontinuous reception mode.

[0044] Its power consumption is 1-3mA, and its standby time is 4-12 days. The trigger condition is that the physical button is pressed, the voice conversation is completed, and the preset timeout period has not yet elapsed. Its state is as follows: the cellular communication module listens to the paging channel at a preset period, such as 1.28 seconds; the near-field communication module is in a low-power connection state; and the main control circuit board is in a low-power operating mode. Its wake-up latency is less than 500ms from DRX mode to the completion of voice data channel establishment. The aforementioned discontinuous reception mode is an intermediate power consumption state between deep sleep mode and working mode. The cellular communication module listens to the paging channel at a preset period, maintaining network connectivity while reducing power consumption. The short wake-up latency when switching from discontinuous reception mode to working mode enables rapid establishment of the voice data channel, improving the user interaction experience.

[0045] Mode 3 is the working mode.

[0046] Its power consumption is approximately 200mA peak. It is triggered when a physical button is pressed or a voice conversation is in progress. When the physical button is pressed, the cellular communication module switches from the discontinuous reception mode or the deep sleep mode to the operating mode and establishes a voice data channel within 800ms. Its state is that the 4G cellular communication module is running at full speed, the audio acquisition module is working, the near-field communication module is transmitting audio data, and the LED indicator shows the current status. Its corresponding battery life is approximately 1.5 hours of continuous talk time. The above three-level management modes are automatically switched through the power management firmware of the main control circuit board, achieving a real-world battery life of 5-7 days with approximately 10 interactions per day, each lasting about 30 seconds, in daily use scenarios. This is far superior to the 1-2 day battery life of existing AI wearable devices, meeting the user's need for all-day wear.

[0047] More preferably, when the physical button is triggered, the cellular communication module switches from Discontinuous Receive (DRX) mode or deep sleep mode to the operating mode and establishes a voice data channel within 800ms. The cellular communication module utilizes pre-cached network parameters and a fast attach mechanism to complete RRC connection establishment and data channel activation within 800ms, achieving low-latency response and ensuring immediate use for the user.

[0048] More preferably, it also includes: when the physical button is triggered, the main control circuit board controls the vibration motor installed in the device to generate a first vibration mode as operation confirmation feedback; More preferably, after the audio acquisition module completes voice acquisition, the main control circuit board controls the vibration motor to generate a second vibration mode as feedback for voice reception completion. The first vibration mode is a single short vibration with a duration of 100ms and a medium amplitude; the second vibration mode is a double short vibration, each lasting 50ms with an interval of 100ms and a weak amplitude. This vibration feedback mechanism provides instant tactile confirmation on screenless wearable devices and is suitable for scenarios where a screen cannot be viewed.

[0049] Furthermore, in this embodiment, the audio acquisition module includes several MEMS microphones. MEMS microphones are characterized by their small size, low power consumption, and high sensitivity, making them suitable for integration into small wearable devices. By configuring multiple MEMS microphones, a microphone array can be implemented, improving voice acquisition quality and noise suppression capabilities.

[0050] The MEMS microphone includes at least a first MEMS microphone, a second MEMS microphone, and a third MEMS microphone. The first and second MEMS microphones form a forward array, mounted on the side of the housing facing the user and pointing towards the user's mouth. The third MEMS microphone serves as a rearward reference microphone, mounted on the side of the housing away from the user, and is used to collect ambient noise signals. The two microphones in the forward array point towards the user's mouth, primarily collecting the user's speech signals; the rearward reference microphone collects ambient noise signals, and noise suppression is achieved through signal processing algorithms, improving the quality of speech acquisition in noisy environments.

[0051] More preferably, the first, second, and third MEMS microphones are arranged in a triangular layout. This triangular layout allows the three microphones to form a stable geometric relationship in space, facilitating the formation of a gain main lobe in the pointing direction of the forward array and a zero-attenuation point in the direction of ambient noise using beamforming algorithms, thus achieving dynamic noise suppression and significantly improving the speech recognition rate. Specifically, the first and second MEMS microphones are mounted on the front of the housing, facing the user, with a spacing of 10mm, forming a forward array pointing towards the user's mouth. The third MEMS microphone is mounted on the back of the housing, away from the user, serving as a rearward reference microphone for acquiring ambient noise signals. The three microphones are arranged in a triangular layout; more specifically, the three MEMS microphones are arranged in an isosceles triangle.

[0052] Furthermore, a vibration motor is also installed inside the device housing, and the vibration motor is electrically connected to the main control circuit board. When the physical button is triggered, the main control circuit board controls the vibration motor to generate a first vibration mode as operation confirmation feedback. After the audio acquisition module completes voice acquisition, the main control circuit board controls the vibration motor to generate a second vibration mode as voice reception completion feedback. By providing tactile feedback through the vibration motor, users can perceive the operation status without looking at the device, thus improving the interactive experience.

[0053] In this embodiment, an LED indicator light is also provided on the outer surface of the device housing. The LED indicator light is electrically connected to the main control circuit board and is used to display the operating status of the device. The LED indicator light indicates the operating status of the device through different colors and flashing patterns, including: the LED indicator light is off in standby mode; the LED indicator light is continuously lit in a first color during voice acquisition mode; the LED indicator light flashes in a breathing pattern in a second color during voice processing mode; the LED indicator light flashes in a breathing pattern in a third color during voice playback mode; and the LED indicator light flashes in the first color a preset number of times in fault mode. Through visual feedback, the user can intuitively understand the current status of the device, facilitating operation and fault diagnosis.

[0054] In this embodiment, it further includes: a button detection unit, which is used to detect the pressing mode of the physical button, and includes: Single press: Press duration is less than the first threshold; Double press: Two single presses are detected within a first preset duration; Three presses: Three single presses are detected within the first preset duration; Long press: Press duration exceeds the second threshold; The main control circuit board executes the corresponding operation command based on the detected pressing mode.

[0055] The main control circuit board detects the press and release events of the physical button via GPIO interrupts, records the press duration and the time interval between adjacent presses, with a first threshold of 200ms, a first preset duration of 500ms, and a second threshold of 2 seconds. This multi-mode press recognition mechanism enables multiple operation commands through a single physical button, simplifying hardware design while improving interaction flexibility.

[0056] More preferably, the operation instruction includes: the single press triggering a voice dialogue process with the remote AI server; The double press triggers a replay of the voice response data previously returned by the remote AI server; The three presses trigger a device status broadcast, and the device status includes the remaining power of the rechargeable battery, the information of the currently connected external Bluetooth audio output device, and the information of the currently activated AI service. The long press triggers the Bluetooth communication module to enter pairing mode; When a single press is detected during a voice conversation, the playback of the current voice response is interrupted and the voice data channel is closed. A double press triggers the reading and replay of the previous voice response data from the local cache. The device status announcement outputs the remaining battery percentage, the name of the currently connected Bluetooth device, and the name of the currently activated AI service via voice.

[0057] In practical applications, the tactile feedback in this embodiment is achieved through the aforementioned vibration motor: When the operation is confirmed, the physical button mentioned above is triggered, and the vibration motor generates a single vibration of 50ms.

[0058] When voice reception is complete, the vibration motor generates two short 10ms vibrations as the audio acquisition module completes voice acquisition.

[0059] When a fault alarm occurs, and the cellular communication module cannot connect to the network, the vibration motor generates three 200ms long vibrations.

[0060] Visual feedback is provided via LED indicators.

[0061] The LED indicator light is off when in standby mode.

[0062] When voice recording is in progress, the LED indicator light will remain solid blue.

[0063] When processing is in progress, the LED indicator light will flash blue in a breathing pattern for 1 second.

[0064] When the voice playback is active, the LED indicator light will flash green in a breathing pattern for 1 second.

[0065] When the battery is low, the LED indicator flashes red three times.

[0066] When charging, the LED indicator light remains solid orange.

[0067] When charging is complete, the LED indicator light will remain solid green.

[0068] Auditory feedback is provided via an external Bluetooth headset.

[0069] The startup prompt is a short "ding" sound with a frequency of 250Hz and a duration of 100ms.

[0070] The processing prompt is a short "beep" sound with a frequency of 500Hz and a duration of 50ms.

[0071] The fault message is a three-tone falling tone "dududu".

[0072] The AI ​​voice response played normally through Bluetooth headphones.

[0073] This application also proposes an application based on a stand-alone voice AI wearable interaction method for scenarios such as hospital operating rooms, gas stations, conference rooms, military-controlled areas / classified units, and some mines / tunnels. In the hospital operating room scenario, medical staff wear the device of this invention to query drug information and surgical procedures through voice interaction, without needing to carry a mobile phone; in the gas station scenario, staff wear the device of this invention to query vehicle information and fuel inventory through voice interaction, ensuring safety; in the military-controlled area or classified unit scenario, personnel wear the device of this invention to access an internal dedicated AI server through a cellular communication module, realizing voice queries and command issuance, meeting confidentiality requirements.

[0074] Specifically, in a hospital operating room setting, medical staff need to access information such as medication details, surgical procedures, and patient medical records during surgery. However, mobile phones are strictly prohibited in the operating room to prevent bacterial infection and electromagnetic interference with medical equipment. Medical staff wear the stand-alone voice AI device of this invention (such as a smart bracelet or pendant) and trigger voice interaction via a physical button.

[0075] After pressing the physical button, medical staff say to the device, "Check the dosage and administration of amoxicillin." The device uploads the voice message via a cellular communication module to a dedicated AI server deployed within the hospital. The AI ​​server retrieves information from the drug database and generates a voice response: "The adult oral dosage of amoxicillin is 0.5 grams per dose, every 8 hours." The device then plays the voice response, allowing medical staff to obtain the necessary information without leaving the operating table or touching any equipment.

[0076] In a gas station setting, the use of mobile phones is prohibited to prevent static electricity from causing fires or explosions. However, staff need to check vehicle information, fuel inventory, refueling records, etc. Staff wearing the device of this invention can complete information queries and recording via voice interaction.

[0077] After pressing the physical button, the staff member says to the device, "Check the inventory of 92-octane gasoline." The device uploads the voice message to the AI ​​server of the gas station management system via a cellular communication module. The AI ​​server retrieves information from the inventory database and generates a voice response: "Current inventory of 92-octane gasoline: 15,000 liters." Once the staff member receives the inventory information, they can promptly arrange replenishment to ensure uninterrupted supply.

[0078] In military-controlled areas or classified units, carrying smartphones with camera and audio recording functions is strictly prohibited to prevent the leakage of classified information. However, personnel may need to access information such as operational orders, equipment parameters, and personnel organization. Personnel wearing the device of this invention (with the camera module and external storage interface removed from the hardware) access a dedicated internal AI server via a cellular communication module.

[0079] The dedicated internal AI server is deployed within a secure network, physically isolated from the internet. The cellular communication module accesses the secure network via a dedicated APN; all voice data is transmitted only within this secure network and never through the public internet. After pressing a physical button, personnel speak to the device, saying, "Query the technical parameters of a certain type of equipment." The AI ​​server retrieves information from the equipment database, generates a voice response, and sends it to the device for playback.

[0080] In complex environments such as mines or tunnels, where flammable and explosive gases may be present, the use of ordinary mobile phones is prohibited. However, workers need to maintain voice communication with the ground command center to report on operational progress and safety conditions. Workers wear the device of this invention (which features an explosion-proof casing and is explosion-proof certified) and communicate with the AI ​​dispatch system of the ground command center via a cellular communication module.

[0081] After pressing the physical button, the worker speaks to the device, "Report your current location and work progress." The device uploads the voice message to the AI ​​dispatch system via its cellular communication module. The AI ​​dispatch system recognizes the voice content, records the work log, and generates a voice response, "Received, please continue work and pay attention to safety." The device plays the voice response, confirming that the instruction has been received.

[0082] This application also proposes a stand-alone voice AI wearable interactive device, wherein the device includes a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the method described thereon.

[0083] This application also proposes a computer-readable storage medium having computer program instructions stored thereon, which can be executed by a processor to implement the method.

[0084] Based on another aspect of this application, embodiments of this application also provide a stand-alone voice AI wearable interaction device, which includes a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the aforementioned stand-alone voice AI wearable interaction method.

[0085] In particular, the methods and / or embodiments in this application 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 computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. When the computer program is executed by a processing unit, it performs the functions defined in the methods of this application.

[0086] It should be noted that the computer-readable storage medium described in this application 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 application, 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.

[0087] In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium, which can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.

[0088] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and 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).

[0089] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. 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-specific system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0090] In another aspect, this application also provides a computer-readable storage medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The aforementioned computer-readable storage medium carries one or more computer program instructions, which may be executed by a processor to implement the methods and / or technical solutions of the various embodiments of this application.

[0091] It should be noted that this application can be implemented in software and / or a combination of software and hardware, for example, using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In some embodiments, the software program of this application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, a magnetic or optical drive, a floppy disk, or similar devices. Furthermore, some steps or functions of this application can be implemented in hardware, for example, as circuitry that cooperates with a processor to perform the various steps or functions.

[0092] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in the apparatus claims may also be implemented by a single unit or device in software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

Claims

1. A stand-alone voice AI wearable interaction method, characterized in that, include: Get the trigger status of physical buttons on the device; When the physical button is triggered, the main control circuit board controls the device to switch from a low-power state to a working state and establishes a voice data channel with the remote AI server. Based on the collected user voice signals, the data is processed by the main control circuit board and then uploaded to the remote AI server via the cellular communication module. The voice response data returned by the remote AI server is received through the cellular communication module, and the voice response data processed by the main control circuit board is played through the device or an external audio output device.

2. The stand-alone voice AI wearable interaction method according to claim 1, characterized in that, Also includes: The voice response data processed by the main control circuit board is played through an external audio output device via a short-range communication module, wherein the short-range communication module is connected to the external audio output device via short-range communication.

3. The stand-alone voice AI wearable interaction method according to claim 1, characterized in that, When the physical button is triggered, the main control circuit board controls the power management module to switch the cellular communication module from a low-power state to a working state and establish a voice data channel with the remote AI server.

4. The stand-alone voice AI wearable interaction method according to claim 1, characterized in that, When the physical button is not triggered, the main control circuit board controls the power management module to put the cellular communication module into a deep sleep mode, in which the power consumption of the cellular communication module is less than 10μA.

5. The stand-alone voice AI wearable interaction method according to claim 3, characterized in that, The power management module also supports the discontinuous reception (DRX) mode of the cellular communication module; When the physical button is not triggered and the device is in standby mode, the main control circuit board controls the cellular communication module to listen to the paging channel at a preset period in the discontinuous reception (DRX) mode. The power consumption in the Discontinuous Receive (DRX) mode is 1-3mA, which is between the power consumption in the deep sleep mode and the power consumption in the operating mode.

6. The stand-alone voice AI wearable interaction method according to claim 5, characterized in that, When the physical button is triggered, the cellular communication module switches from discontinuous reception (DRX) mode or deep sleep mode to the working mode and establishes a voice data channel within 800ms.

7. The stand-alone voice AI wearable interaction method according to claim 1, characterized in that, Also includes: When the physical button is triggered, the main control circuit board controls the vibration motor installed in the device to generate a first vibration mode as operation confirmation feedback. After the audio acquisition module completes voice acquisition, the main control circuit board controls the vibration motor to generate a second vibration mode as feedback that the voice reception is complete.

8. The stand-alone voice AI wearable interaction method according to any one of claims 1 to 7, characterized in that, Also includes: The method for detecting the pressing pattern of the physical button includes: Single press: Press duration is less than the first threshold; Double press: Two single presses are detected within a first preset time period; Three presses: Three single presses are detected within the first preset duration; Long press: The press duration is greater than the second threshold; The main control circuit board executes the corresponding operation command based on the detected pressing mode.

9. The stand-alone voice AI wearable interaction method according to claim 8, characterized in that, The operation instructions include: triggering a voice dialogue process with the remote AI server with a single press; The double press triggers a replay of the voice response data previously returned by the remote AI server; The three presses trigger a device status broadcast, and the device status includes the remaining power of the rechargeable battery, the information of the currently connected external Bluetooth audio output device, and the information of the currently activated AI service. The long press triggers the Bluetooth communication module to enter pairing mode; When a single press is detected during a voice conversation, the playback of the current voice response is interrupted and the voice data channel is closed.

10. An application of the stand-alone voice AI wearable interaction method based on any one of claims 1 to 9, characterized in that, This is intended for locations where the use of mobile terminals is prohibited, including: hospital operating rooms, gas stations, conference rooms, military-controlled areas / classified units, and any of the following scenarios: a cellular communication module can be triggered by a physical button to directly establish a voice data channel with a remote AI server for voice interaction.

11. A stand-alone voice AI wearable interactive device, wherein, The device includes a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to perform the method of any one of claims 1 to 9.

12. A computer-readable storage medium having stored thereon computer program instructions that can be executed by a processor to implement the method as described in any one of claims 1 to 9.

Images