Vehicle real-time voice call processing method and system based on intranet browser

Abstract

The invention relates to a vehicle real-time voice call processing method and system based on an intranet browser, and the method comprises the steps: Q1, enabling an automatic driving vehicle to run on a preset road, collecting the data information of the historical sound intensity level and frequency value of the environment noise inside and outside the vehicle, and obtaining the data information of the voice inside and outside the vehicle in real time under the call condition; and Q2, on the basis of the data information of the historical sound intensity level and the frequency value of the environmental noise inside and outside the vehicle, constructing a removal model of the environmental noise inside and outside the vehicle, and performing training and learning to obtain the trained removal model of the environmental noise inside and outside the vehicle. The problems of high voice call delay, poor quality, excessive bandwidth occupation and the like in the prior art are solved, the data security in the call process can be ensured, the voice call quality is optimized, a user can clearly hear the voice of the other party even in the vehicle driving process, and the voice quality in the call process is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle voice processing, and in particular to a vehicle real-time voice call processing method and system based on an intranet browser. Background Art

[0002] With the rapid development of autonomous driving technology, L4 autonomous driving vehicles are already able to achieve fully automated driving under certain conditions. However, in an autonomous driving environment, real-time communication between the vehicle and the driver, passengers, or remote monitoring center has become a technical problem that needs to be solved urgently. Especially when the vehicle is operating autonomously, traditional communication methods (such as mobile phones, public networks, etc.) may have disadvantages such as large delays, insufficient bandwidth, and poor security. At the same time, during a call, the vehicle will be affected by the ambient noise inside and outside the vehicle, thereby reducing the passenger experience. Summary of the invention

[0003] In view of the above problems, the present invention provides a vehicle real-time voice call processing method and system based on an intranet browser, which not only solves the problems of high voice call delay, poor quality, excessive bandwidth occupancy, etc. in the prior art, and ensures data security during the call, but also optimizes the voice call quality. Even during the driving of the vehicle, the user can clearly hear the other party's voice, ensuring the voice quality during the call.

[0004] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0005] A vehicle real-time voice call processing method based on an intranet browser, the method comprising:

[0006] Q1. The autonomous driving vehicle is driving on a preset road, collecting data information on the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, and obtaining data information on the voice inside and outside the vehicle in real time during a call;

[0007] Q2. Based on the data information of the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, a model for removing the ambient noise inside and outside the vehicle is constructed, and training and learning are performed to obtain a trained model for removing the ambient noise inside and outside the vehicle;

[0008] Q3. Input the data information of the voice inside and outside the car into the trained model for removing the environmental noise inside and outside the car, remove the environmental noise in the voice inside and outside the car, and obtain the data information of the voice inside and outside the car after removal;

[0009] Q4. Based on the removed voice data information inside and outside the car, the voice data inside and outside the car are optimized by using a multi-objective sparrow optimization algorithm based on chaotic mapping to obtain the optimized voice data information inside and outside the car;

[0010] Q5. Based on the optimized voice data information inside and outside the vehicle, construct a vehicle voice call quality evaluation function W, evaluate the quality of the voice inside and outside the vehicle, and obtain evaluation data information of the voice quality inside and outside the vehicle.

[0011] Furthermore, in step Q2, the construction of a model for removing ambient noise inside and outside the vehicle, and the training and learning include:

[0012] Q21. Based on the data information of the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, a filter value function R of the ambient noise inside and outside the vehicle is established,

[0013]

[0014] Among them, x1 is the data information of the historical sound intensity level of the environmental noise inside and outside the car, x2 is the data information of the historical frequency value of the environmental noise inside and outside the car, α1, α2 and α3 are the weight coefficients of the environmental noise inside and outside the car, and the filter value of the environmental noise inside and outside the car is characterized to obtain the data information of the filter value of the environmental noise inside and outside the car;

[0015] Q22. Input the data information of the filter value of the vehicle interior and exterior environmental noise into the vehicle interior and exterior environmental noise removal model for training and learning, and determine the vehicle interior and exterior environmental noise removal function U,

[0016]

[0017] Among them, y is the data information of the filter value of the environmental noise inside and outside the car, β1, β2 and β3 are the penalty factors for removing the environmental noise inside and outside the car;

[0018] Q23. Based on the function U for removing the ambient noise inside and outside the vehicle, the trained voice data information inside and outside the vehicle is obtained.

[0019] Furthermore, the penalty factors β1, β2 and β3 for removing the ambient noise inside and outside the vehicle are:

[0020]

[0021] Among them, y is the data information of the filtered value of the environmental noise inside and outside the car.

[0022] Furthermore, the constraints of the weight coefficients α1, α2 and α3 of the ambient noise inside and outside the vehicle are:

[0023]

[0024] Furthermore, in step Q4, the optimization of the voice data inside and outside the vehicle by using a multi-objective sparrow optimization algorithm based on chaotic mapping includes:

[0025] Q41. Based on the data information of the voice inside and outside the car after the removal, establish the chaotic mapping function P of the voice inside and outside the car,

[0026]

[0027] Wherein, z is the data information of the voice inside and outside the car after removal, δ1, δ2 and δ3 are the chaotic mapping parameters of the voice inside and outside the car, and the chaotic mapping sequence of the voice inside and outside the car is characterized to obtain the data information of the chaotic mapping sequence of the voice inside and outside the car;

[0028] Q42. Based on the data information of the chaotic mapping sequence of the voice inside and outside the car, the sparrow population is initialized, the population parameters and the maximum number of iterations are determined, and the data information of the initialized sparrow population is obtained;

[0029] Q43. Based on the data information of the initialized sparrow population, establish the fitness function S of the individual sparrow population,

[0030]

[0031] Among them, r is the data information of the initialized sparrow population, γ1, γ2 and γ3 are the fitness determining factors of the sparrow population individuals, and the fitness values ​​of the sparrow population individuals are calculated to obtain the data information of the fitness values ​​of the sparrow population individuals;

[0032] Q44. Based on the data information of the fitness values ​​of the sparrow population individuals, establish a target optimization function G,

[0033]

[0034] Among them, h is the data information of the fitness value of the individual sparrow population, η1, η2 and η3 are the optimization factors of the individual sparrow population, and the voice data inside and outside the car are optimized to obtain the optimized voice data information inside and outside the car.

[0035] Furthermore, the constraint function f of the optimization factors η1, η2 and η3 of the individual sparrow population is,

[0036]

[0037] The value range of the constraint function f is (1,2).

[0038] Furthermore, the vehicle's voice call quality evaluation function W is:

[0039]

[0040] Among them, g is the optimized data information of the voice inside and outside the car, and λ1, λ2 and λ3 are evaluation factors of the voice inside and outside the car.

[0041] Furthermore, the method further comprises:

[0042] Q6. Based on the evaluation data information of the voice quality inside and outside the car, a preset threshold is set. If the evaluation data information of the voice quality inside and outside the car is less than the preset threshold, the requirement is not met, and return to step Q3. If the evaluation data information of the voice quality inside and outside the car is greater than the preset threshold, the requirement is met and a real-time voice call is conducted.

[0043] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a vehicle real-time voice call processing system based on an intranet browser, including a computer device, which is programmed or configured to execute any one of the steps of the vehicle real-time voice call processing method based on an intranet browser.

[0044] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the intranet browser-based vehicle real-time voice call processing methods.

[0045] The present invention has the following positive effects:

[0046] 1. The present invention removes the environmental noise in the voice inside and outside the car by constructing a model for removing the environmental noise inside and outside the car, obtains the data information of the voice inside and outside the car after removal, and optimizes the voice data inside and outside the car by combining a multi-objective sparrow optimization algorithm based on chaotic mapping. It can not only optimize the voice call quality, even during the driving of the vehicle, the user can clearly hear the other party's voice, ensuring the voice quality during the call, but also ensure the stability during the call, avoiding the delay fluctuation and bandwidth limitation caused by the public network, and is particularly suitable for use in an autonomous driving environment.

[0047] 2. The present invention constructs a voice call quality evaluation function W for the vehicle to evaluate the quality of voice inside and outside the vehicle. It not only solves the problems of high voice call delay, poor quality, excessive bandwidth occupancy, etc. in the prior art, and ensures data security during the call, but also ensures that the real-time voice call between the vehicle and the browser has high quality and low latency, and adapts to the communication needs under different network environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0049] Figure 2A schematic diagram of the process of constructing a model for removing ambient noise inside and outside a vehicle according to the present invention;

[0050] Figure 3 The figure is a flow chart of the multi-objective sparrow optimization algorithm based on chaotic mapping of the present invention. DETAILED DESCRIPTION

[0051] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0052] Example 1: Figure 1 As shown, a vehicle real-time voice call processing method based on an intranet browser comprises:

[0053] Q1. The autonomous driving vehicle is driving on a preset road, collecting data information on the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, and obtaining data information on the voice inside and outside the vehicle in real time during a call;

[0054] Q2. Based on the data information of the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, a model for removing the ambient noise inside and outside the vehicle is constructed, and training and learning are performed to obtain a trained model for removing the ambient noise inside and outside the vehicle;

[0055] Q3. Input the data information of the voice inside and outside the car into the trained model for removing the environmental noise inside and outside the car, remove the environmental noise in the voice inside and outside the car, and obtain the data information of the voice inside and outside the car after removal;

[0056] Q4. Based on the removed voice data information inside and outside the car, the voice data inside and outside the car are optimized by using a multi-objective sparrow optimization algorithm based on chaotic mapping to obtain the optimized voice data information inside and outside the car;

[0057] Q5. Based on the optimized voice data information inside and outside the vehicle, construct a vehicle voice call quality evaluation function W, evaluate the quality of the voice inside and outside the vehicle, and obtain evaluation data information of the voice quality inside and outside the vehicle.

[0058] In this embodiment, if Figure 2 As shown, in step Q2, the construction of a model for removing ambient noise inside and outside the vehicle, and the training and learning include:

[0059] Q21. Based on the data information of the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, a filter value function R of the ambient noise inside and outside the vehicle is established,

[0060]

[0061] Among them, x1 is the data information of the historical sound intensity level of the environmental noise inside and outside the car, x2 is the data information of the historical frequency value of the environmental noise inside and outside the car, α1, α2 and α3 are the weight coefficients of the environmental noise inside and outside the car, and the filter value of the environmental noise inside and outside the car is characterized to obtain the data information of the filter value of the environmental noise inside and outside the car;

[0062] Q22. Input the data information of the filter value of the vehicle interior and exterior environmental noise into the vehicle interior and exterior environmental noise removal model for training and learning, and determine the vehicle interior and exterior environmental noise removal function U,

[0063]

[0064] Among them, y is the data information of the filter value of the environmental noise inside and outside the car, β1, β2 and β3 are the penalty factors for removing the environmental noise inside and outside the car;

[0065] Q23. Based on the function U for removing the ambient noise inside and outside the vehicle, the trained voice data information inside and outside the vehicle is obtained.

[0066] In this embodiment, the penalty factors β1, β2 and β3 for removing the ambient noise inside and outside the vehicle are:

[0067]

[0068] Among them, y is the data information of the filtered value of the environmental noise inside and outside the car.

[0069] In this embodiment, the constraints of the weight coefficients α1, α2 and α3 of the ambient noise inside and outside the vehicle are:

[0070]

[0071] In this embodiment, the browser-side device includes a browser that supports the WebRTC protocol, an audio acquisition device (such as a microphone), an audio playback device (such as a speaker) and an intranet communication module (such as a Wi-Fi module), which are used to initiate voice call requests, receive voice data, and play voice.

[0072] Vehicle-side equipment: including the on-board audio processing unit, microphone array, speaker, audio encoding and decoding module, intranet communication module and automatic driving control system. The system is used to collect voice inside and outside the vehicle, encode and compress data, transmit voice data and play voice.

[0073] Intranet communication equipment: including high-bandwidth and low-latency routers, switches and bandwidth management equipment to ensure that real-time voice calls between the browser and the vehicle have efficient and stable communication quality.

[0074] Data storage device: used to store voice call data, call logs, communication protocols and system status information. Data storage uses encrypted storage to ensure the security of communication data.

[0075] Real-time Example 2: Based on the vehicle real-time voice call processing method based on an intranet browser in Example 1, the present invention is further illustrated and described below.

[0076] like Figure 1 As shown, a vehicle real-time voice call processing method based on an intranet browser comprises:

[0077] Q1. The autonomous driving vehicle is driving on a preset road, collecting data information on the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, and obtaining data information on the voice inside and outside the vehicle in real time during a call;

[0078] Q2. Based on the data information of the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, a model for removing the ambient noise inside and outside the vehicle is constructed, and training and learning are performed to obtain a trained model for removing the ambient noise inside and outside the vehicle;

[0079] Q3. Input the data information of the voice inside and outside the car into the trained model for removing the environmental noise inside and outside the car, remove the environmental noise in the voice inside and outside the car, and obtain the data information of the voice inside and outside the car after removal;

[0080] Q4. Based on the removed voice data information inside and outside the car, the voice data inside and outside the car are optimized by using a multi-objective sparrow optimization algorithm based on chaotic mapping to obtain the optimized voice data information inside and outside the car;

[0081] Q5. Based on the optimized voice data information inside and outside the vehicle, construct a vehicle voice call quality evaluation function W, evaluate the quality of the voice inside and outside the vehicle, and obtain evaluation data information of the voice quality inside and outside the vehicle.

[0082] In this embodiment, if Figure 3 As shown, in step Q4, the optimization of the voice data inside and outside the vehicle by using the multi-objective sparrow optimization algorithm based on chaotic mapping includes:

[0083] Q41. Based on the data information of the voice inside and outside the car after the removal, establish the chaotic mapping function P of the voice inside and outside the car,

[0084]

[0085] Wherein, z is the data information of the voice inside and outside the car after removal, δ1, δ2 and δ3 are the chaotic mapping parameters of the voice inside and outside the car, and the chaotic mapping sequence of the voice inside and outside the car is characterized to obtain the data information of the chaotic mapping sequence of the voice inside and outside the car;

[0086] Q42. Based on the data information of the chaotic mapping sequence of the voice inside and outside the car, the sparrow population is initialized, the population parameters and the maximum number of iterations are determined, and the data information of the initialized sparrow population is obtained;

[0087] Q43. Based on the data information of the initialized sparrow population, establish the fitness function S of the individual sparrow population,

[0088]

[0089] Among them, r is the data information of the initialized sparrow population, γ1, γ2 and γ3 are the fitness determining factors of the sparrow population individuals, and the fitness values ​​of the sparrow population individuals are calculated to obtain the data information of the fitness values ​​of the sparrow population individuals;

[0090] Q44. Based on the data information of the fitness values ​​of the sparrow population individuals, establish a target optimization function G,

[0091]

[0092] Among them, h is the data information of the fitness value of the individual sparrow population, η1, η2 and η3 are the optimization factors of the individual sparrow population, and the voice data inside and outside the car are optimized to obtain the optimized voice data information inside and outside the car.

[0093] In this embodiment, the constraint function f of the optimization factors η1, η2 and η3 of the sparrow population individuals is,

[0094]

[0095] The value range of the constraint function f is (1,2).

[0096] In this embodiment, the vehicle's voice call quality evaluation function W is:

[0097]

[0098] Among them, g is the optimized data information of the voice inside and outside the car, and λ1, λ2 and λ3 are evaluation factors of the voice inside and outside the car.

[0099] In this embodiment, the method further includes:

[0100] Q6. Based on the evaluation data information of the voice quality inside and outside the car, a preset threshold is set. If the evaluation data information of the voice quality inside and outside the car is less than the preset threshold, the requirement is not met, and return to step Q3. If the evaluation data information of the voice quality inside and outside the car is greater than the preset threshold, the requirement is met and a real-time voice call is conducted.

[0101] In this embodiment, the present invention also provides a vehicle real-time voice call processing system based on an intranet browser, including a computer device, which is programmed or configured to execute any one of the steps of the vehicle real-time voice call processing method based on an intranet browser.

[0102] In this embodiment, the present invention further provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the intranet browser-based vehicle real-time voice call processing methods.

[0103] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0104] To sum up, the present invention not only solves the problems of high voice call delay, poor quality, excessive bandwidth occupancy, etc. in the prior art, and ensures data security during the call, but also optimizes the voice call quality. Even when the vehicle is driving, the user can clearly hear the other party's voice, ensuring the voice quality during the call.

[0105] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A vehicle real-time voice call processing method based on an intranet browser, characterized in that: The method comprises: Q1. The autonomous driving vehicle is driving on a preset road, collecting data information on the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, and obtaining data information on the voice inside and outside the vehicle in real time during a call; Q2. Based on the data information of the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, a model for removing the ambient noise inside and outside the vehicle is constructed, and training and learning are performed to obtain a trained model for removing the ambient noise inside and outside the vehicle; Q3. Input the data information of the voice inside and outside the car into the trained model for removing the environmental noise inside and outside the car, remove the environmental noise in the voice inside and outside the car, and obtain the data information of the voice inside and outside the car after removal; Q4. Based on the removed voice data information inside and outside the car, the voice data inside and outside the car are optimized by using a multi-objective sparrow optimization algorithm based on chaotic mapping to obtain the optimized voice data information inside and outside the car; Q5. Based on the optimized voice data information inside and outside the vehicle, construct a vehicle voice call quality evaluation function W, evaluate the quality of the voice inside and outside the vehicle, and obtain evaluation data information of the voice quality inside and outside the vehicle.

2. The method for processing vehicle real-time voice calls based on an intranet browser according to claim 1, characterized in that: In step Q2, the construction of a model for removing ambient noise inside and outside the vehicle, and the training and learning include: Q21. Based on the data information of the historical sound intensity level and frequency value of the ambient noise inside and outside the vehicle, a filter value function R of the ambient noise inside and outside the vehicle is established, Among them, x1 is the data information of the historical sound intensity level of the environmental noise inside and outside the car, x2 is the data information of the historical frequency value of the environmental noise inside and outside the car, α1, α2 and α3 are the weight coefficients of the environmental noise inside and outside the car, and the filter value of the environmental noise inside and outside the car is characterized to obtain the data information of the filter value of the environmental noise inside and outside the car; Q22. Input the data information of the filter value of the vehicle interior and exterior environmental noise into the vehicle interior and exterior environmental noise removal model for training and learning, and determine the vehicle interior and exterior environmental noise removal function U, Among them, y is the data information of the filter value of the environmental noise inside and outside the car, β1, β2 and β3 are the penalty factors for removing the environmental noise inside and outside the car; Q23. Based on the function U for removing the ambient noise inside and outside the vehicle, the trained voice data information inside and outside the vehicle is obtained.

3. The method for processing vehicle real-time voice calls based on an intranet browser according to claim 2, characterized in that: The penalty factors β1, β2 and β3 for removing the ambient noise inside and outside the vehicle are: Among them, y is the data information of the filtered value of the environmental noise inside and outside the car.

4. The method for processing vehicle real-time voice calls based on an intranet browser according to claim 2, characterized in that: The constraints of the weight coefficients α1, α2 and α3 of the ambient noise inside and outside the vehicle are:

5. The method for processing vehicle real-time voice calls based on an intranet browser according to claim 1, characterized in that: In step Q4, the optimization of the voice data inside and outside the vehicle by using a multi-objective sparrow optimization algorithm based on chaotic mapping includes: Q41. Based on the data information of the voice inside and outside the car after the removal, establish the chaotic mapping function P of the voice inside and outside the car, Wherein, z is the data information of the voice inside and outside the car after removal, δ1, δ2 and δ3 are the chaotic mapping parameters of the voice inside and outside the car, and the chaotic mapping sequence of the voice inside and outside the car is characterized to obtain the data information of the chaotic mapping sequence of the voice inside and outside the car; Q42. Based on the data information of the chaotic mapping sequence of the voice inside and outside the car, the sparrow population is initialized, the population parameters and the maximum number of iterations are determined, and the data information of the initialized sparrow population is obtained; Q43. Based on the data information of the initialized sparrow population, establish the fitness function S of the individual sparrow population, Among them, r is the data information of the initialized sparrow population, γ1, γ2 and γ3 are the fitness determining factors of the sparrow population individuals, and the fitness values ​​of the sparrow population individuals are calculated to obtain the data information of the fitness values ​​of the sparrow population individuals; Q44. Based on the data information of the fitness values ​​of the sparrow population individuals, establish a target optimization function G, Among them, h is the data information of the fitness value of the individual sparrow population, η1, η2 and η3 are the optimization factors of the individual sparrow population, and the voice data inside and outside the car are optimized to obtain the optimized voice data information inside and outside the car.

6. The method for processing vehicle real-time voice calls based on an intranet browser according to claim 5, characterized in that: The constraint function f of the optimization factors η1, η2 and η3 of the sparrow population individuals is, The value range of the constraint function f is (1,2).

7. The method for processing vehicle real-time voice calls based on an intranet browser according to claim 1, characterized in that: The vehicle's voice call quality evaluation function W is: Among them, g is the optimized data information of the voice inside and outside the car, and λ1, λ2 and λ3 are evaluation factors of the voice inside and outside the car.

8. The method for processing vehicle real-time voice calls based on an intranet browser according to claim 1, characterized in that: The method further comprises: Q6. Based on the evaluation data information of the voice quality inside and outside the car, a preset threshold is set. If the evaluation data information of the voice quality inside and outside the car is less than the preset threshold, the requirement is not met, and return to step Q3. If the evaluation data information of the voice quality inside and outside the car is greater than the preset threshold, the requirement is met and a real-time voice call is conducted.

9. A vehicle real-time voice call processing system based on an intranet browser, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the vehicle real-time voice call processing method based on an intranet browser as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program programmed or configured to execute the vehicle real-time voice call processing method based on an intranet browser as described in any one of claims 1 to 8.

Images