Riding helmet voice instruction and background music intelligent management method and system

Abstract

The invention relates to the technical field of voice control, in particular to a riding helmet voice instruction and background music intelligent management method and system. The method comprises the steps of obtaining voice instruction input data and riding state data of a riding helmet, and performing first voice preprocessing on the voice instruction input data to obtain second voice instruction data, wherein the riding state data comprises speed data, illumination data, geographic position data and posture data; presetting a first voice instruction processing model and inputting the second voice instruction data into the model; and performing intelligent audio management according to the output of the voice instruction processing model and the riding state data. According to the embodiment of the invention, the riding helmet voice instruction and the background music are dynamically adjusted according to the voice instruction input data and the riding state, so that the user experience can be improved, and the potential safety hazard can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of voice control technology, and in particular to a method and system for intelligently managing voice commands and background music of a cycling helmet. Background Art

[0002] With the rapid development of smart wearable device technology, smart cycling helmets, as a new generation of sports technology products, have gradually attracted market attention. Modern smart cycling helmets usually integrate functions such as communication, audio playback and navigation, and mainly use voice interaction and touch operation to achieve function switching. At present, the industry generally uses neural network-based speech recognition algorithms for command processing, and uses Bluetooth modules to achieve data interaction with mobile devices. At the same time, with the help of built-in multi-source sensors, smart helmets can obtain riding status information and provide data support for safety assistance functions. However, in actual applications, due to the complexity of the riding environment, the accuracy of speech recognition is often significantly affected by factors such as wind noise and environmental noise. Especially in high-speed riding scenarios, traditional speech recognition systems are difficult to maintain stable performance.

[0003] Existing smart cycling helmets have the following main problems:

[0004] Existing systems generally use fixed audio parameter settings and lack the ability to dynamically adjust according to riding status, which not only affects the user experience but also may pose a safety hazard. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention is proposed.

[0006] The problem to be solved by the present invention is how to solve the problem that the existing systems generally adopt fixed audio parameter settings, which lack the ability to dynamically adjust according to the riding status, resulting in affecting the user experience and posing safety hazards.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a method for intelligently managing voice commands and background music of a cycling helmet, which comprises: acquiring voice command input data and riding status data of a cycling helmet, and performing a first voice preprocessing on the voice command input data to obtain second voice command data;

[0009] Preset a first voice command processing model, input the second voice command data into the first voice command processing model, and output a helmet voice command;

[0010] Intelligent audio management is performed on the helmet voice command and background music according to the helmet voice command and the riding status data.

[0011] As a preferred solution of the method for intelligently managing voice commands and background music for riding helmets of the present invention, the riding status data includes:

[0012] Speed ​​data, lighting data, geographic location data, and attitude data;

[0013] The voice command input data is all voice data acquired when voice recognition is performed using a preset first voice interaction optimization algorithm.

[0014] As a preferred solution of the method for intelligently managing voice commands and background music for riding helmets of the present invention, wherein: the first voice preprocessing includes at least a first noise elimination process and a first voice enhancement process;

[0015] The first noise cancellation process includes a first wind noise cancellation operation and a second environmental noise cancellation operation;

[0016] The first speech enhancement processing is used to improve the quality of the speech instruction input data after the first noise elimination processing.

[0017] As a preferred solution of the method for intelligently managing voice commands and background music for riding helmets of the present invention, the first voice interaction optimization algorithm includes:

[0018] Taking the voice command input data as a sequence to be processed and the response of the voice command processing model as an output sequence;

[0019] The sequence to be processed and the output sequence are optimized according to preset voice interaction rules.

[0020] As a preferred solution of the method for intelligently managing voice commands and background music of a riding helmet according to the present invention, the method for intelligently managing the voice commands and background music of a riding helmet according to the voice commands of the helmet and the riding status data includes:

[0021] When it is detected that the speed data in the riding status data exceeds a first preset threshold, the volume of the background music is automatically increased;

[0022] When it is detected that the illumination data in the riding status data is lower than a second preset threshold, the volume of the background music is automatically reduced;

[0023] When the geographical location data in the riding status data is detected as being in a preset complex road condition geographical location, the background music playback is automatically paused and the voice navigation prompt is turned on;

[0024] When it is detected that the posture data in the riding status data is abnormal, an emergency processing mechanism is triggered.

[0025] As a preferred solution of the method for intelligently managing voice commands and background music for riding helmets of the present invention, when the posture data is detected to be abnormal, triggering the emergency processing mechanism includes:

[0026] Start the emergency contact notification program and automatically call the preset emergency contact;

[0027] Send the current geographic location information to the client corresponding to the preset emergency contact;

[0028] Save the riding status data when the emergency handling mechanism is triggered.

[0029] As a preferred solution of the method for intelligently managing voice commands and background music for riding helmets of the present invention, the first voice command processing model includes:

[0030] The input is the second voice command data, the output is the voice command recognition result, and it supports a multi-round dialogue mode.

[0031] In a second aspect, an embodiment of the present invention provides a riding helmet voice command and background music intelligent management system, which includes:

[0032] A voice data acquisition module acquires voice command input data and riding status data of the riding helmet, and performs a first voice preprocessing on the voice command input data to obtain second voice command data;

[0033] The model operation module presets a first voice command processing model, inputs the second voice command data into the first voice command processing model, and outputs a helmet voice command;

[0034] The audio management module performs intelligent audio management on the helmet voice command and background music according to the helmet voice command and the riding status data.

[0035] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the method for intelligent management of voice commands and background music of a cycling helmet as described in the first aspect of the present invention are implemented.

[0036] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the method for intelligent management of voice commands and background music of a cycling helmet as described in the first aspect of the present invention are implemented.

[0037] The beneficial effects of the present invention are as follows: the present invention dynamically adjusts the voice instructions and background music of the riding helmet according to the voice instruction input data and the riding status, which can not only improve the user experience but also reduce safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 A flow chart of a method for intelligently managing voice commands and background music for a cycling helmet;

[0040] Figure 2 A diagram of a computer device for an intelligent management method of voice commands and background music for a cycling helmet. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] Example 1

[0045] Reference Figure 1-2 , which is the first embodiment of the present invention, provides a method for intelligent management of voice commands and background music of a cycling helmet, comprising:

[0046] S100: Acquire voice command input data and riding status data of the riding helmet, and perform first voice preprocessing on the voice command input data to obtain second voice command data;

[0047] S101: Riding status data includes:

[0048] Speed ​​data, lighting data, geographic location data, and attitude data;

[0049] The voice command input data is all the voice data obtained when voice recognition is performed through the preset first voice interaction optimization algorithm.

[0050] In the embodiment of the present application, the riding status data includes: speed data, light data, geographic location data, and posture data;

[0051] The voice command input data is all the voice data obtained when voice recognition is performed through the preset first voice interaction optimization algorithm.

[0052] Specifically, speed data can be riding speed information obtained through accelerometer and gyroscope sensors, illumination data can be ambient brightness information collected through ambient light sensors, geographic location data can be real-time location information obtained through GPS (Global Positioning System) modules, and posture data can be helmet spatial posture information obtained through six-axis sensors. These data together constitute a complete picture of the riding status, providing a basis for subsequent intelligent processing.

[0053] In an optional embodiment, the collection frequency of riding status data can be dynamically adjusted according to different scenarios. For example, in complex road conditions, the system will increase the sampling rate of posture data and speed data to respond to emergencies more promptly; when riding at night, the sampling frequency of light data will be increased to ensure that subtle changes in ambient light can be accurately perceived.

[0054] In order to ensure accurate recognition of voice commands, this application uses a highly sensitive MEMS (Micro-Electro-Mechanical System) microphone array, combined with beamforming technology, to effectively capture the user's voice commands. The voice interaction optimization algorithm uses adaptive noise reduction technology to effectively filter out interference from wind noise and ambient noise.

[0055] S102: The first speech preprocessing includes at least a first noise elimination process and a first speech enhancement process;

[0056] The first noise cancellation process includes a first wind noise cancellation operation and a second environmental noise cancellation operation;

[0057] The first voice enhancement process is used to improve the quality of the voice command input data after the first noise elimination process.

[0058] Specifically, the first wind noise elimination operation uses an adaptive filtering algorithm to estimate wind noise characteristics in real time and dynamically eliminate them. The algorithm can automatically adjust the filtering parameters according to the current riding speed, providing a stronger noise reduction effect when riding at high speed. The second environmental noise elimination operation uses multi-channel noise suppression technology, which uses acoustic signals collected by multiple microphones for spatial filtering to effectively suppress environmental noise from different directions.

[0059] The first voice enhancement process includes amplitude normalization, spectrum enhancement, and clarity improvement of the voice signal. The system will dynamically adjust the enhancement parameters according to the current ambient noise level to ensure that the processed voice commands are clear and discernible.

[0060] S103: The first voice interaction optimization algorithm includes:

[0061] The voice command input data is used as a sequence to be processed, and the response of the voice command processing model is used as an output sequence;

[0062] The processing sequence and output sequence are optimized according to the preset voice interaction rules.

[0063] Furthermore, the specific structure of the voice command processing model is supplemented:

[0064] The voice command processing model adopts a dual-stream network architecture: acoustic feature processing stream: processes the acoustic features of speech signals; context feature processing stream: processes the semantic and contextual information of commands.

[0065] Specifically include:

[0066] (1) Acoustic feature extraction layer: Use MFCC (Mel-frequency cepstral coefficient) to extract acoustic features; feature parameters: frame length 25ms, frame shift 10ms; extract 13-dimensional MFCC features and first-order and second-order differential features.

[0067] (2) Time series modeling layer: Bi LSTM network is used to capture long time series dependencies; number of hidden units: 256; number of layers: 2 layers.

[0068] (3) Attention mechanism layer: using multi-head self-attention mechanism; number of heads: 8; dimension of each head: 32.

[0069] (4) Context fusion layer: Fusion of acoustic features and historical conversation information; context window size: 5 rounds of conversation.

[0070] The training method of the model, supplement the training details of the model;

[0071] Model training adopts a two-stage strategy:

[0072] (1) Pre-training stage: Use large-scale general speech data for pre-training; training data volume: >1000 hours of speech data; training goal: minimize the speech recognition error rate.

[0073] (2) Fine-tuning stage: Use real speech data from cycling scenarios for fine-tuning; Data enhancement: Add wind noise and environmental noise at different speeds; Fine-tuning data volume: >100 hours of speech data from cycling scenarios.

[0074] Optimization strategy for instruction recognition

[0075] Supplement specific optimization methods:

[0076] (1) Multi-task learning: Optimize both speech recognition and intent understanding tasks simultaneously; improve model performance by sharing underlying features.

[0077] (2) Dynamic adjustment of instruction priority: Establish statistics on instruction usage frequency; dynamically adjust the threshold for instruction recognition based on the current scenario; and increase the priority of security-related instructions in high-risk scenarios.

[0078] (3) Personalized adaptation: record the user’s pronunciation characteristics and usage habits; establish user profiles and dynamically adjust model parameters.

[0079] Error handling mechanism

[0080] Supplementary exception handling strategy:

[0081] (1) Command confirmation mechanism: Confidence threshold: Confirmation is triggered when it is <0.8; Second confirmation method: voice feedback or vibration prompt; Waiting confirmation timeout: 3 seconds.

[0082] (2) Error recovery strategy: supports "undo last instruction"; records the execution status of the last five instructions; provides the function of quickly restoring to default settings.

[0083] For example, when the user says the preset wake-up word "Hey He lmet", the system will immediately enter the active listening state. In this state, the user can issue multiple commands in succession without repeating the wake-up word. This continuous dialogue mode greatly improves the naturalness and efficiency of the interaction. At the same time, the system also supports contextual understanding and can accurately understand context-dependent commands such as "play the next song" and "turn up a little".

[0084] Furthermore, the voice interaction optimization algorithm also includes a command confirmation mechanism. For important operations (such as making a call, switching navigation, etc.), the system will confirm the user's intention through voice feedback to avoid misoperation. This confirmation mechanism uses short and clear voice prompts that will not disturb the user's riding experience too much.

[0085] It should be explained that the preset voice interaction rules are predefined and used to guide how to optimize the processing of input sequences and output sequences. These rules include grammatical rules, context rules, polite expressions, etc., which are not limited here.

[0086] S104: The processing of riding status data includes:

[0087] When it is detected that the speed data in the riding status data exceeds a first preset threshold, the volume of the background music is automatically increased;

[0088] When it is detected that the illumination data in the riding status data is lower than a second preset threshold, the volume of the background music is automatically reduced;

[0089] When the geographical location data in the riding status data is detected as being in a preset complex road condition geographical location, the background music playback is automatically paused and the voice navigation prompt is turned on;

[0090] When it is detected that the posture data in the riding status data is abnormal, an emergency processing mechanism is triggered.

[0091] In specific implementation, the system sets multiple preset thresholds to trigger different response operations:

[0092] Speed ​​threshold: When the speed exceeds 20km / h, the system will calculate the required volume compensation value based on the wind noise estimation model to ensure that the audio content is still clearly audible when riding at high speed.

[0093] Light threshold: When the ambient light is lower than 100 l ux, the system will automatically reduce the background music volume to 60% of the original to enhance the rider's perception of the surrounding environment.

[0094] Complex road condition determination: The system maintains a geographic information database of special locations such as intersections, school areas, construction sections, etc. When GPS positioning shows that the rider is about to enter these areas, the system will actively lower or pause the background music and inform the rider of the road conditions ahead through voice prompts.

[0095] S105: When abnormal posture data is detected, triggering an emergency processing mechanism includes:

[0096] Start the emergency contact notification program and automatically call the preset emergency contact;

[0097] Send the current geographic location information to the client corresponding to the preset emergency contact;

[0098] Save the riding status data when the emergency handling mechanism is triggered.

[0099] The system determines whether an accident has occurred by analyzing the acceleration and angular velocity data of the helmet. When a severe impact or abnormal posture change is detected, the emergency process will be immediately initiated:

[0100] 1. First, the system will issue a voice prompt to ask the rider if he needs help. If no cancellation command is received within 10 seconds, it will automatically enter the emergency processing process.

[0101] 2. The system will call up to 3 preset emergency contacts in sequence until someone answers.

[0102] 3. At the same time, the mobile phone connected via Bluetooth sends an emergency text message containing precise GPS location, accident time, riding speed and other information.

[0103] 4. The system will save all sensor data 30 seconds before and after the accident, which can be used for subsequent accident analysis and insurance claims.

[0104] S200: Preset a first voice command processing model, and input the second voice command data into the first voice command processing model;

[0105] S201: The first voice instruction processing model includes:

[0106] The input is the second voice command data, the output is the voice command recognition result, and it supports a multi-round dialogue mode.

[0107] The first voice command processing model uses a lightweight neural network architecture that can run in real time on the helmet's microprocessor. The model supports the output of the following core helmet voice commands:

[0108] Audio control commands: including play / pause music, previous / next song, volume adjustment, etc.; - Communication control commands: answer / reject calls, send voice messages, etc.; Navigation control commands: turn on / off navigation, query destination information, etc.; Status query commands: query battery, speed, weather, etc.;

[0109] Personalized setting commands: switch audio mode, adjust reminder volume, etc.

[0110] S300: Perform intelligent audio management according to the output of the first voice command processing model and the riding status data.

[0111] The system is also equipped with a learning module that can continuously optimize the accuracy of command recognition based on the user's usage habits. For example, if the user often uses certain commands in a specific scenario, the system will automatically increase the recognition priority of these commands.

[0112] From the perspective of hardware implementation, this system uses a low-power ARM (Advanced RICS Machi n) processor as the main control unit and integrates the following core components:

[0113] MEMS microphone array: uses 4 high-precision digital microphones to support 360-degree sound pickup; bone conduction speaker: provides clear audio output without affecting the perception of external sounds; nine-axis sensor: integrates accelerometer, gyroscope and magnetometer to provide accurate posture perception; GPS module: supports multi-mode satellite positioning and provides meter-level positioning accuracy; Bluetooth 5.0 module: supports low-latency audio transmission and stable data communication; ambient light sensor: has a high dynamic range and can accurately perceive various lighting conditions; all components are modularly designed for easy maintenance and upgrades. The system also reserves expansion interfaces to add additional sensors or functional modules as needed.

[0114] In terms of software architecture, the system adopts a layered design: the underlying driver layer is responsible for hardware control and raw data collection; the middleware layer handles sensor data fusion and audio signal processing; the application layer realizes user interaction and intelligent decision-making functions;

[0115] This layered architecture allows the system to be easily scalable and maintainable. Each module communicates with the other through a standard interface and can be updated and optimized independently.

[0116] For example, in the embodiment of this application, we tested the system for one month in an actual road environment, involving 100 test users, with a cumulative test mileage of more than 10,000 kilometers, and the test scenarios covered a variety of environments such as urban roads and suburban highways. The test focused on the following aspects:

[0117] 1. Voice recognition performance: Voice command recognition tests were conducted under different speeds and environmental conditions: Stationary state: recognition accuracy reached 98%; Low-speed riding (speed <15km / h): recognition accuracy reached 95%; Medium-speed riding (15-25km / h): recognition accuracy reached 92%; High-speed riding (25km / h): recognition accuracy reached 88%.

[0118] These data show that the system can maintain a high recognition accuracy even in a noisy riding environment. In particular, after wind noise elimination and voice enhancement processing, the system's voice recognition performance remains at a usable level when riding at high speeds.

[0119] 2. Environmental adaptability test: the system's automatic adjustment performance in different environments:

[0120] (1) Light adaptation test: In bright sunlight on a sunny day, the system correctly identifies the bright light environment and maintains normal volume. In dim light in the evening, the system detects a decrease in light intensity and automatically reduces the volume to 60% of the original volume. When riding at night, the system further reduces the volume to 40% of the original volume, while increasing the volume of the warning sound effect.

[0121] (2) Scene recognition test: Test at preset complex road conditions (such as school areas, intersections, etc.):

[0122] Identify special areas 100 meters in advance and issue reminders; automatically pause music playback after entering the area; automatically resume previous playback status after leaving the area; scene recognition accuracy reaches 96%.

[0123] 3. Emergency response test

[0124] The system response performance in various emergency situations was simulated:

[0125] When a violent impact is detected, the emergency handling mechanism is 100% triggered; the average response time for emergency contact notification is <15 seconds; the accuracy of location information sending is 100%; the false alarm rate is <0.1%.

[0126] In terms of system implementation, several key technical details are particularly noted:

[0127] 1. Voice processing flow:

[0128] When a voice signal is captured, the system processes it in the following steps:

[0129] (1) Front-end signal processing: sampling rate: 16kHz; quantization bit number: 16bit; frame length: 25ms; frame shift: 10ms.

[0130] (2) Noise elimination: The first wind noise elimination adopts an adaptive filtering algorithm; filter order: 64; step factor: 0.01; forgetting factor: 0.95.

[0131] (3) Speech enhancement: dual-channel Wiener filtering; smoothing factor: 0.8; noise estimation window: 200ms; speech detection threshold: -26dB.

[0132] 2. Sensor data acquisition and processing:

[0133] (1) Accelerometer: sampling rate: 100 Hz; measurement range: ±16 g; raw data processed by Kalman filter.

[0134] (2) Gyroscope: sampling rate: 200 Hz; measurement range: ±2000° / s; zero bias stability: 0.5° / s.

[0135] (3) Ambient light sensor; response time: <100ms; measurement range: 0.1-100000l ux; resolution: 0.01lux.

[0136] 3. Audio management strategy: The system automatically adjusts audio parameters according to different scenarios:

[0137] (1) Volume adjustment: Basic volume range: 0-30; Speed ​​compensation coefficient: 0.5dB / (km / h); Environmental noise compensation: 0.3dB / dB.

[0138] (2) Equalizer settings:

[0139] Low speed mode: low frequency +2dB, medium frequency 0dB, high frequency -1dB; high speed mode: low frequency 0dB, medium frequency +3dB, high frequency +4dB.

[0140] 4. Power management: To ensure the continuous working ability of the system:

[0141] Working voltage: 3.7V; Battery capacity: 1000mAh; Standby time: >72 hours; Continuous use time: >8 hours; Charging time: <2 hours.

[0142] In terms of human-computer interaction, the system supports the following main functions:

[0143] 1. Voice control:

[0144] (1) Basic instruction set:

[0145] Music control: "Play / Pause / Previous song / Next song / Volume up / Volume down"; Call control: "Answer / Hang up / Reject"; Navigation control: "Start navigation / End navigation / Check traffic conditions"; System control: "Battery query / Switch mode / System status".

[0146] (2) Contextual instructions: Supports understanding simple instructions based on context; supports fuzzy matching and synonym recognition; supports multiple rounds of dialogue to maintain contextual consistency.

[0147] 2. Touch operation:

[0148] The helmet shell integrates a touch area as an alternative input method: single click: play / pause; double click: next song; long press: activate voice assistant; slide: volume adjustment.

[0149] System workflow example:

[0150] 1. The user puts on the helmet to start the system: system self-check; sensor calibration; Bluetooth automatic connection.

[0151] 2. Daily use scenarios: The system continuously monitors environmental data; automatically adjusts the volume according to speed; receives and processes voice commands; and adjusts the working mode according to geographic location.

[0152] 3. Special situation handling: Start emergency procedures when an abnormality is detected; record abnormal data; send a message for help; wait for manual confirmation or lift the alarm.

[0153] The technical solution of the present invention realizes an intelligent, safe and easy-to-use riding assistance system through deep integration of software and hardware. The system can not only provide a good user experience, but more importantly, it can provide timely help in emergency situations and improve riding safety. Through a large number of field tests and user feedback, it is proved that the system has good practical value and market prospects.

[0154] It should be noted that the various parameters and configurations given in the above implementations are preferred implementations, and those skilled in the art can make appropriate adjustments according to actual needs and hardware conditions, and these adjustments should fall within the protection scope of the present invention. At the same time, with the development of technology, the various performance indicators of the system can be further improved, and the technical solution of the present invention can also be upgraded and optimized accordingly.

[0155] Furthermore, this embodiment also provides a riding helmet voice command and background music intelligent management system, including:

[0156] A voice data acquisition module acquires voice command input data and riding status data of the riding helmet, and performs a first voice preprocessing on the voice command input data to obtain second voice command data;

[0157] The model operation module presets a first voice command processing model and inputs the second voice command data into the first voice command processing model;

[0158] The audio management module performs intelligent audio management according to the output of the first voice command processing model and the riding status data.

[0159] In summary, by acquiring the voice command input data and riding status data of the riding helmet and performing the first voice preprocessing technical solution, the collaborative collection and processing of multi-dimensional data is realized. This solution uses a four-channel MEMS microphone array with beamforming technology to effectively solve the problem of low voice recognition rate of traditional helmets in high-noise environments, allowing the system to maintain a recognition accuracy of more than 88% when riding at high speed (25km / h), which is significantly higher than the 60% accuracy level in the existing technology.

[0160] By integrating the first wind noise elimination operation and the second environmental noise elimination operation in the first voice preprocessing, and combining its own adaptive filtering algorithm, it realizes accurate identification and elimination of different types of noise. This solution dynamically adjusts the filtering parameters according to the real-time riding speed, allowing the system to suppress environmental noise by more than 20dB in complex road environments, far exceeding the 8-10dB effect of traditional fixed parameter noise reduction solutions.

[0161] By designing a voice interaction optimization algorithm based on scene perception, a correlation model between voice commands and riding status was established. The system can automatically adjust the interaction strategy according to different scenarios, while maintaining a high recognition accuracy rate, and control the command response time within 200ms, which is 60% higher than the 500ms response time of the traditional solution, greatly improving the user experience.

[0162] By building a multi-dimensional riding status data collection and processing mechanism, real-time monitoring of speed, light, geographic location, posture and other data is achieved. The system can automatically adjust audio parameters based on these data, such as reducing the music volume to 60% of the original when the light is insufficient, and issuing warnings 100 meters in advance at complex intersections. This active safety protection mechanism effectively reduces the risk of riding accidents, and actual measurements show that it can reduce more than 30% of dangerous conditions.

[0163] By establishing a complete emergency handling mechanism, including automatic alarm, location sharing and data storage, a rapid response to unexpected situations is achieved. When an abnormality is detected, the system can complete the notification of emergency contacts within 15 seconds, the accuracy of location information transmission reaches 100%, and the false alarm rate is less than 0.1%, providing reliable safety protection for riders.

[0164] By adopting modular hardware design and layered software architecture, the system is highly integrated and easily expandable. The solution uses a low-power ARM processor as the main control unit. While ensuring continuous working capacity of more than 8 hours, it reserves a standardized expansion interface, which can flexibly add new functional modules according to needs, significantly improving the adaptability and maintainability of the system.

[0165] In summary, the present invention not only solves the problems of inaccurate voice control and unintelligent audio management of traditional cycling helmets in complex environments by integrating innovative technical solutions such as multi-source data collection, intelligent voice interaction, and adaptive audio management, but also significantly improves cycling safety through active safety protection mechanisms. The system has shown excellent performance and reliability in practical applications and has important practical value.

[0166] Example 2

[0167] This embodiment also provides a computer device, which is suitable for a method for intelligent management of voice commands and background music of a cycling helmet, and includes a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement a forced oscillation detection and positioning method for a distribution network as proposed in the above embodiment.

[0168] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, a forced oscillation detection and positioning method for a distribution network is implemented as proposed in the above embodiment.

[0169] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WI FI (mobile hotspot), operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0170] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0171] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0172] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0173] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0174] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for intelligent management of voice commands and background music for a cycling helmet, characterized in that: include: Acquire voice command input data and riding status data of the riding helmet, and perform first voice preprocessing on the voice command input data to obtain second voice command data; Preset a first voice command processing model, input the second voice command data into the first voice command processing model, and output a helmet voice command; Intelligent audio management is performed on the helmet voice command and background music according to the helmet voice command and the riding status data.

2. The method for intelligent management of voice commands and background music for a cycling helmet according to claim 1, characterized in that: The riding status data includes: speed data, light data, geographic location data and posture data; The voice command input data is all voice data acquired when voice recognition is performed using a preset first voice interaction optimization algorithm.

3. The method for intelligent management of voice commands and background music for a cycling helmet as claimed in claim 2, characterized in that: The first speech preprocessing includes at least a first noise elimination process and a first speech enhancement process; The first noise cancellation process includes a first wind noise cancellation operation and a second environmental noise cancellation operation; The first speech enhancement processing is used to improve the quality of the speech instruction input data after the first noise elimination processing.

4. The method for intelligent management of voice commands and background music for a cycling helmet as claimed in claim 3, characterized in that: The first voice interaction optimization algorithm includes: The voice command input data is used as a sequence to be processed, and the response of the voice command processing model is used as an output sequence; The sequence to be processed and the output sequence are optimized according to preset voice interaction rules.

5. The method for intelligent management of voice commands and background music for a cycling helmet as claimed in claim 2, characterized in that: The intelligent audio management of the helmet voice command and the background music according to the helmet voice command and the riding status data includes: When it is detected that the speed data in the riding status data exceeds a first preset threshold, the volume of the background music is automatically increased; When it is detected that the illumination data in the riding status data is lower than a second preset threshold, the volume of the background music is automatically reduced; When the geographical location data in the riding status data is detected as being in a preset complex road condition geographical location, the background music playback is automatically paused and the voice navigation prompt is turned on; When it is detected that the posture data in the riding status data is abnormal, an emergency processing mechanism is triggered.

6. The method for intelligent management of voice commands and background music for a cycling helmet as claimed in claim 5, characterized in that: When the posture data is detected to be abnormal, triggering the emergency processing mechanism includes: Start the emergency contact notification program and automatically call the preset emergency contact; Send the current geographic location information to the client corresponding to the preset emergency contact; Save the riding status data when the emergency handling mechanism is triggered.

7. The method for intelligent management of voice commands and background music for a cycling helmet according to claim 1, characterized in that: The first voice instruction processing model includes: The input is the second voice command data, the output is the voice command recognition result, and it supports a multi-round dialogue mode.

8. An intelligent management system for voice commands and background music of a cycling helmet, characterized in that: The system comprises: A voice data acquisition module, which acquires voice command input data and riding status data of the riding helmet, and performs a first voice preprocessing on the voice command input data to obtain second voice command data; The model operation module presets a first voice command processing model, inputs the second voice command data into the first voice command processing model, and outputs a helmet voice command; The audio management module performs intelligent audio management on the helmet voice command and background music according to the helmet voice command and the riding status data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for intelligent management of voice instructions and background music for a cycling helmet as described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the method for intelligently managing voice instructions and background music for a cycling helmet as described in any one of claims 1 to 7 are implemented.

Images