A method and system for internet of things alarm audio call dispatching

Abstract

The application discloses a kind of Internet of Things alarm audio call scheduling method and system, it is related to Internet of Things intelligent decision-making technical field, including, receiving the alarm request message from Internet of Things perception terminal, according to the equipment identification and area coding in alarm request message, multi-dimensional information report of real-time environmental noise data, audio playing equipment state information and user state information is collected and generated;According to multi-dimensional information report, generate the dynamic priority score of alarm request message by inquiring preset strategy library;The dynamic priority score of alarm request message to be processed is sorted, and the preliminary scheduling strategy of the recommended playing equipment and the broadcast parameter of the highest priority alarm request message is generated.The application generates intelligibility index report by high-fidelity simulation through acoustic digital twin model, generates execution instruction based on simulation result and is issued to target audio equipment, realizes the intelligent scheduling of whole process from multidimensional dynamic perception to acoustic effect optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Things intelligent decision-making, and particularly relates to a method and system for alarm audio call scheduling of Internet of Things. BACKGROUND

[0002] Under the background of rapid development of Internet of Things technology, various types of environment sensing terminals are widely deployed in the fields of intelligent security, industrial Internet of Things and smart home, etc., for real-time monitoring of abnormal events such as smoke, intrusion and leakage. After triggering an alarm, these terminals need to issue an alarm call to the target area through an audio playing device to prompt personnel to respond in time. In the prior art, after receiving an alarm, the system gives the alarm a fixed priority according to the inherent level of the alarm type, and distributes the audio broadcast task to the idle playing devices in the area in order of priority. Usually, only limited dimensions such as alarm type and device availability are considered, and the scheduling is completed through simple loop or preemption strategy, aiming to achieve fast broadcast of alarm information. To some extent, such a scheme meets the needs of orderly triggering of multiple alarms, and is easy to deploy and implement on resource-limited edge computing nodes due to its simple rules and low computational overhead.

[0003] However, with the complication of Internet of Things application scenarios and the improvement of users' requirements for alarm effectiveness, the above-mentioned scheduling method based on static rules and device states gradually shows its limitations. In terms of dynamic environment adaptability, the prior art is difficult to make prospective prediction and optimization of the actual propagation effect of alarm broadcasting. Since the real-time environmental noise level at the time of alarm occurrence, the actual performance state of the playing device, the current activity state of the user and other dynamic context information are not fully considered, and there is a lack of quantitative simulation of the propagation characteristics of audio in a specific physical space, the scheduling decision may deviate from the actual acoustic effect. SUMMARY

[0004] In view of the above-mentioned existing problems, the present application is proposed.

[0005] Therefore, the present application provides a method for alarm audio call scheduling of Internet of Things, which solves the problem of deviation between scheduling decision and actual broadcast effect caused by lack of multi-dimensional dynamic information fusion and acoustic propagation effect simulation in the prior art.

[0006] To solve the above-mentioned technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a method for alarm audio call scheduling of Internet of Things, which comprises receiving an alarm request message from an Internet of Things sensing terminal, collecting and generating a multi-dimensional information report of real-time environmental noise data, audio playing device state information and user state information according to the device identifier and region code in the alarm request message;

[0008] According to the multi-dimensional information report, a dynamic priority score of the alarm request message is generated by querying a preset strategy library;

[0009] The dynamic priority score of the alarm request message to be processed is sorted, and a preliminary scheduling strategy of a recommended playing device and a broadcast parameter is generated for the alarm request message with the highest priority;

[0010] The preliminary scheduling strategy is input into an acoustic digital twin model of an alarm occurrence area, and through digital twinning, the preliminary scheduling strategy is subjected to high-fidelity acoustic simulation and ambiguity analysis to generate a simulation report of intelligibility indicators;

[0011] According to the simulation report of the intelligibility indicators, the preliminary scheduling strategy is converted from the priority score into a quantifiable expected propagation effect comparison based on physical acoustic simulation, and the strategy parameters are fine-tuned and optimized according to an acoustic confusion risk assessment, and the preliminary scheduling strategy with the optimal intelligibility indicators and the lowest ambiguity risk is set as a final scheduling execution instruction, and the final scheduling execution instruction is sent to the target audio playing device.

[0012] As a preferred scheme of the method for scheduling an alarm audio call of the Internet of Things, wherein: receiving an alarm request message from an Internet of Things sensing terminal, collecting and generating a multi-dimensional information report of real-time environmental noise data, audio playing device state information and user state information according to a device identifier and a region code in the alarm request message, including the following steps:

[0013] Parsing the device unique identifier and the alarm occurrence region code in the alarm request message, querying an environment monitoring service according to the device unique identifier and the alarm occurrence region code to obtain real-time environmental noise data, and querying a device management device according to the device unique identifier and the alarm occurrence region code to obtain audio playing device state information;

[0014] Querying a user state service according to the device unique identifier and the alarm occurrence region code to obtain user state information;

[0015] Integrating the real-time environmental noise data, the audio playing device state information and the user state information to generate the multi-dimensional information report.

[0016] As a preferred scheme of the method for scheduling an alarm audio call of the Internet of Things, wherein: according to the multi-dimensional information report, a dynamic priority score of the alarm request message is generated by querying a preset strategy library, including the following steps:

[0017] Reading an environmental noise value in the multi-dimensional information report and directly converting the environmental noise value into an environmental noise coefficient;

[0018] Extract equipment state data, collect equipment state data through multi-dimensional equipment health indicators, generate dynamic health score by weighted fusion, establish equipment health score library, and directly obtain equipment reliability coefficient;

[0019] Parse user activity information into user state emergency coefficient, extract alarm type from alarm request message to generate basic priority coefficient, obtain timestamp in alarm request message and derive time difference from current time, derive time attenuation factor through exponential decay function;

[0020] Encode the alarm occurrence area into the query log to generate an associated event enhancement factor by counting the number of associated events;

[0021] Integrate the basic priority coefficient, the environmental noise coefficient, the user state emergency coefficient, the equipment reliability coefficient, the time attenuation factor and the associated event enhancement factor to generate a dynamic priority score.

[0022] As a preferred scheme of the alarm audio call scheduling method of the Internet of Things, wherein: the dynamic priority score of the alarm request message to be processed is sorted, and a preliminary scheduling strategy of the recommended playing device and the broadcast parameter is generated for the alarm request message with the highest priority, including the following steps:

[0023] Sort the alarm request messages to be processed according to the dynamic priority score from high to low, generate an ordered sorted alarm request queue, select the alarm request message at the first position in the sorted alarm request queue, and obtain the highest priority alarm to be scheduled;

[0024] According to the alarm occurrence area coding in the alarm request message, query the online audio playing device registered in the device management platform, obtain the candidate audio playing device list and the candidate audio playing device list;

[0025] For each audio playing device in the candidate audio playing device list, filter out the device-environment matching degree score;

[0026] Combine the device-environment matching degree score, the dynamic priority score of the alarm request message and the environmental noise data in the multi-dimensional information report to generate the expected broadcast utility value of each audio playing device, and generate a preliminary scheduling strategy of the recommended volume, tone and repetition number for each device based on the expected broadcast utility value.

[0027] As a preferred scheme of the alarm audio call scheduling method of the Internet of Things, wherein: the preliminary scheduling strategy is input into the acoustic digital twin model of the alarm occurrence area, the digital twin is converted from static environment modeling to dynamic scheduling strategy prediction and optimization engine, high-fidelity acoustic simulation and ambiguity analysis are performed on the preliminary scheduling strategy, a simulation report of intelligibility index is generated, including the following steps:

[0028] Encode the corresponding physical space three-dimensional geometric data, interface material acoustic parameters and real-time environmental noise data based on the alarm occurrence area, and obtain an acoustic digital twin model through a finite element method;

[0029] Convert each strategy in the preliminary scheduling strategy into an acoustic simulation parameter, set a point sound source in the acoustic digital twin model according to the target audio playing device position in each strategy in the preliminary scheduling strategy, calculate the sound power level according to the broadcast volume parameter in the strategy, load the alarm audio segment to be broadcast, and obtain a sound source signal;

[0030] Deploy a virtual microphone array as a receiving point in the acoustic digital twin model in a user activity area, adopt a sound ray tracing method to calculate the sound wave propagation, reflection and absorption process in the acoustic digital twin model corresponding to each strategy in parallel, and obtain impulse response data at the receiving point;

[0031] Convolve the impulse response data and the alarm audio segment to simulate the actual audio signal at the receiving point, perform time-frequency analysis on the simulated actual audio signal, and extract the mel frequency cepstral coefficient (MFCC) feature thereof;

[0032] Based on the impulse response data and the alarm audio segment, calculate the speech transmission index value of the receiving point;

[0033] Integrate the speech transmission index value, semantic confusion probability and simulation parameter corresponding to each preliminary scheduling strategy to generate a simulation report of intelligibility indicators.

[0034] As a preferred scheme of the method for calling scheduling of the alarm audio of the Internet of Things, the preliminary scheduling strategy is converted from a priority score to a quantifiable expected propagation effect comparison based on physical acoustic simulation according to the simulation report of the intelligibility indicators, the strategy parameters are fine-tuned and optimized according to the acoustic confusion risk assessment, the preliminary scheduling strategy with the optimal intelligibility indicators and the lowest ambiguity risk is selected as the final scheduling execution instruction, and the method comprises the following steps:

[0035] Analyze the simulation report to extract the speech transmission index value corresponding to each preliminary scheduling strategy, and generate a mapping list;

[0036] Calculate the device resource consumption coefficient based on the preliminary scheduling strategy parameters in the mapping list;

[0037] Query the target audio playing device identifier specified in the strategy in the mapping list, obtain the device reliability coefficient and calculate the execution risk coefficient;

[0038] Substitute the speech transmission index value, the semantic confusion probability, the device resource consumption coefficient and the execution risk coefficient into a comprehensive performance score formula to calculate the comprehensive performance score of each strategy;

[0039] The preliminary scheduling strategy with the highest comprehensive performance score is selected as the final scheduling execution instruction.

[0040] As a preferred scheme of the method for scheduling an alarm audio call in the Internet of Things, the final scheduling execution instruction is sent to the target audio playback device, including the following steps:

[0041] The final scheduling execution instruction is packaged into a standard control protocol data packet recognizable by the device, and the control protocol data packet is sent to the target audio playback device through a secure transmission layer protocol encryption channel to identify the corresponding network endpoint;

[0042] The target audio playback device receives and analyzes the control protocol data packet to extract the broadcast parameters;

[0043] The target audio playback device performs a local audio broadcast operation according to the broadcast parameters, and the scheduling engine returns a status code to confirm the response.

[0044] In a second aspect, the present application provides a system for scheduling an alarm audio call in the Internet of Things, including a fusion module that receives alarm request messages from Internet of Things sensing terminals, collects and generates a multi-dimensional information report of real-time environmental noise data, audio playback device state information and user state information according to the device identifier and region code in the alarm request message;

[0045] A dynamic priority module generates a dynamic priority score for the alarm request message by querying a preset strategy library based on the multi-dimensional information report;

[0046] A preliminary scheduling strategy generation module sorts the dynamic priority scores of the alarm request messages to be processed, and generates a preliminary scheduling strategy for the alarm request message with the highest priority, including a recommended playback device and broadcast parameters;

[0047] An emulation report module inputs the preliminary scheduling strategy into an acoustic digital twin model of the alarm occurrence area, and through digital twinning, converts the static environment modeling into a dynamic scheduling strategy prediction and optimization engine for high-fidelity acoustic simulation and ambiguity analysis, and generates an emulation report of intelligibility indicators;

[0048] A decision module converts the preliminary scheduling strategy from a priority score to a quantifiable expected propagation effect comparison based on physical acoustic simulation according to the emulation report of intelligibility indicators, fine-tunes and optimizes the strategy parameters according to the acoustic confusion risk assessment, selects the preliminary scheduling strategy with the optimal intelligibility indicators and the lowest ambiguity risk, and sets it as the final scheduling execution instruction, which is sent to the target audio playback device.

[0049] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the computer program, when executed by the processor, implements any step of the method for scheduling an alarm audio call of an Internet of Things according to the first aspect of the present application.

[0050] In a fourth aspect, the present application provides a computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements any step of the method for scheduling an alarm audio call of an Internet of Things according to the first aspect of the present application.

[0051] The present application has the following beneficial effects: by receiving an alarm request message of an Internet of Things sensing terminal, generating a multi-dimensional information report based on device identification and area coding to collect environmental noise, device state and user state information, and generating a dynamic priority score by using weighted calculation; generating a preliminary scheduling strategy for the highest priority alarm after sorting the alarm request, generating an intelligibility index report by high-fidelity simulation through an acoustic digital twin model, selecting an optimal strategy based on the simulation result to generate an execution instruction and issuing it to the target audio device, and realizing intelligent scheduling of the whole process from multi-dimensional dynamic sensing to acoustic effect optimization. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0053] Fig. 1 Flowchart of the method for scheduling an alarm audio call of an Internet of Things.

[0054] Fig. 2 Schematic diagram of the system for scheduling an alarm audio call of an Internet of Things. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned objects, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0056] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the scope of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0057] Second, the "one embodiment" or "an embodiment" referred to herein can include a particular feature, structure, or characteristic. The various embodiments appearing at different places in this specification can not all refer to the same embodiment or to the same implementations or alternatives of the present application.

[0058] Referring to Figs. 1-2 For one embodiment of the present application, the embodiment provides a method for alarm audio call scheduling of Internet of Things, comprising the following steps:

[0059] S1, receiving an alarm request message from an Internet of Things sensing terminal, collecting and generating a multi-dimensional information report of real-time environmental noise data, audio playback device state information and user state information according to the device identifier and the area code in the alarm request message.

[0060] S1.1, parsing the device unique identifier and the alarm occurrence area code in the alarm request message, querying the environmental monitoring service according to the device unique identifier and the alarm occurrence area code to obtain real-time environmental noise data, querying the device management device according to the device unique identifier and the alarm occurrence area code to obtain audio playback device state information.

[0061] Further, receiving an alarm request message sent by an Internet of Things sensing terminal through a message queue or an interface, parsing the protocol payload of the alarm request message, and extracting the device unique identifier and the alarm occurrence area code; calling the application program interface of the environmental monitoring service with the device unique identifier and the alarm occurrence area code as the joint query condition, the environmental monitoring service returns the current environmental noise decibel value collected by the audio sensor in the physical space corresponding to the alarm occurrence area code as the real-time environmental noise data, querying the application program interface of the device management platform with the device unique identifier and the alarm occurrence area code as the index, and the device management platform returns a detailed state set of all registered online audio playback devices in the alarm occurrence area code as the audio playback device state information, the detailed state set includes device network round-trip delay, central processor current load, battery remaining capacity percentage and current volume setting gear.

[0062] S1.2, querying the user state service according to the device unique identifier and the alarm occurrence area code to obtain user state information.

[0063] Further, calling the application program interface of the user state service with the device unique identifier and the alarm occurrence area code as parameters, the user state service returns the target user's current activity state inference result as the user state information based on the fusion of intelligent wearable device sensor data and calendar schedule information, and the user state information includes sleep, meeting and idle state classification.

[0064] S1.3, integrate real-time ambient noise data, audio playback device status information and user state information to generate a multi-dimensional information report.

[0065] Further, the real-time ambient noise data, audio playback device status information and user state information are standardized and converted into a format, the data fields are aligned and time-stamped, and a structured multi-dimensional information report containing all context information is generated. The multi-dimensional information report provides a complete data basis for subsequent scheduling decisions.

[0066] S2, according to the multi-dimensional information report, generate a dynamic priority division of the alarm request message by querying the preset strategy library.

[0067] S2.1, read the ambient noise value in the multi-dimensional information report and directly convert it into an ambient noise coefficient.

[0068] Further, reading the ambient noise value in the multi-dimensional information report and directly converting it into an ambient noise coefficient is achieved by a pre-defined noise level mapping table. The mapping table divides the continuous ambient noise value into discrete level intervals and assigns a standardized ambient noise coefficient to each interval. The ambient noise value is input immediately after matching and querying in the mapping table and the corresponding ambient noise coefficient is output to complete the direct conversion from physical quantity to coefficient.

[0069] S2.2, extract device status data, collect device status data through multi-dimensional device health indicators, generate dynamic health score using weighted fusion, establish device health score library, and directly obtain device reliability coefficient.

[0070] Further, the extraction of device status data is achieved by continuously collecting multi-dimensional device health indicators during device operation, including current remaining battery percentage, signal strength coefficient, historical online rate and recent failure record frequency. The dynamic health scores of all devices are persistently stored and maintained to form a device health score library. When the device reliability coefficient is needed, the latest score corresponding to the device identifier is directly retrieved from the device health score library as the device reliability coefficient.

[0071] S2.3, analyze user activity information to map to user state emergency coefficient, extract alarm type from alarm request message to generate basic priority coefficient, obtain time stamp in alarm request message and derive time difference from current time, derive time attenuation factor through exponential decay function.

[0072] Further, the user activity information is mapped to the user state emergency coefficient according to the user activity state classification rule, which classifies the user activity information into each of the predefined emergency state levels, each of which corresponds to a fixed user state emergency coefficient value. The base priority coefficient is generated by extracting the alarm type from the alarm request message, and a priority level table is queried, which sets a fixed base priority coefficient for each alarm type. The time difference between the timestamp in the alarm request message and the current time is obtained, and the difference between the time represented by the timestamp and the current time is calculated in seconds. The time decay factor is derived by substituting the time difference into an exponential decay function, which yields a time decay factor that asymptotically approaches zero as the time difference increases.

[0073] S2.4, an associated event enhancement factor is generated by encoding the alarm occurrence area into the query log to count the number of associated events.

[0074] Further, the associated event enhancement factor is generated by encoding the alarm occurrence area to count the number of associated events in the event log database using the alarm occurrence area code as a query key. The number of events is input into a linear normalization function, which maps the number to an associated event enhancement factor value within a predetermined range. The more events, the larger the associated event enhancement factor value.

[0075] S2.5, the base priority coefficient, the environmental noise coefficient, the user state emergency coefficient, the device reliability coefficient, the time decay factor, and the associated event enhancement factor are integrated to generate a dynamic priority score.

[0076] Further, the base priority coefficient, the environmental noise coefficient, the user state emergency coefficient, the device reliability coefficient, the time decay factor, and the associated event enhancement factor are integrated to generate a dynamic priority score.

[0077] S3, the dynamic priority scores of the alarm request messages to be processed are sorted, and a preliminary scheduling strategy for the suggested playing device and the broadcast parameters is generated for the alarm request message with the highest priority.

[0078] S3.1, the alarm request messages to be processed are sorted from high to low according to the dynamic priority scores, an ordered sorted alarm request queue is generated, and the alarm request message at the top of the sorted alarm request queue is selected to obtain the highest priority alarm to be scheduled.

[0079] Further, the dynamic priority scores of all alarm request messages to be processed are sorted in descending order, a sorted alarm request queue is generated according to the dynamic priority scores from high to low, and the alarm request message at the top of the sorted alarm request queue is selected to obtain the highest priority alarm to be scheduled.

[0080] S3.2, query the online audio playback devices registered in the device management platform according to the alarm occurrence area code in the alarm request message, obtain the candidate audio playback device list for alarm broadcasting and the candidate audio playback device list.

[0081] Further, according to the alarm occurrence area code contained in the alarm request message of the highest priority alarm, query the online audio playback device list registered in the device management platform, obtain the identification and detailed state parameters of all audio playback devices in the area code under the state of online, and form a candidate audio playback device list.

[0082] S3.3, for each audio playback device in the candidate audio playback device list, filter out the device-environment matching degree score.

[0083] Further, for each audio playback device in the candidate audio playback device list, the device-environment matching degree score is obtained by the following steps: first, obtain the real-time network delay coefficient and signal strength coefficient of the audio playback device, and extract the current environmental noise data from the multi-dimensional information report; then input the network delay coefficient, signal strength coefficient and environmental noise data into the pre-defined device-environment matching degree mapping table, and directly output the obtained device-environment matching degree score as the result.

[0084] S3.4, combine the device-environment matching degree score, the dynamic priority score of the alarm request message and the environmental noise data in the multi-dimensional information report to generate the expected broadcasting utility value of each audio playback device, and generate a preliminary scheduling strategy of the recommended volume, tone and repetition number for each device based on the expected broadcasting utility value.

[0085] Further, through multi-factor weighted fusion and acoustic utility optimization technology means, the independent evaluation one-sidedness of the device-environment matching degree score, the dynamic priority score and the environmental noise data is linearly weighted and nonlinearly normalized, and the discrete evaluation indexes are integrated into a unified expected broadcasting utility value; further through parameter mapping and rule reasoning technology means, the strategy generation ambiguity of the expected broadcasting utility value is segmented function mapping and experience rule matching, and a preliminary scheduling strategy containing quantitative recommended volume, adaptive tone adjustment and dynamic repetition number is generated.

[0086] S4, input the preliminary scheduling strategy into the acoustic digital twin model of the alarm occurrence area, and through digital twinning from static environment modeling to dynamic scheduling strategy prediction and optimization engine, perform high-fidelity acoustic simulation and ambiguity analysis on the preliminary scheduling strategy, and generate a simulation report of intelligibility index.

[0087] S4.1, encode the corresponding physical space three-dimensional geometric data, interface material acoustic parameters and real-time environmental noise data based on the alarm occurrence area code, and obtain the acoustic digital twin model by finite element method.

[0088] Further, through finite element mesh partitioning and wave equation discretization technical means, the complex boundary representation of the physical space three-dimensional geometric data existing in the alarm occurrence area code is divided into tetrahedral element mesh and the interface condition is loaded, and the continuous physical space is converted into a discrete node system; further through material parameter mapping and acoustic property assignment technical means, the frequency-dependent characteristic loss of interface material acoustic parameters is defined and the frequency-dependent sound absorption coefficient is fitted; finally, through environmental noise coupling and transient sound field calculation technical means, the dynamic interference unmodeled by the real-time environmental noise data is superimposed and the background sound field is integrated, and a high-fidelity acoustic digital twin model is constructed, which integrates static geometric characteristics, material acoustic characteristics and dynamic environmental interference.

[0089] S4.2, convert each strategy in the preliminary scheduling strategy into acoustic simulation parameters, set a point sound source in the acoustic digital twin model according to the target audio playback device position in each strategy in the preliminary scheduling strategy, calculate the sound power level according to the broadcast volume parameter in the strategy, load the alarm audio segment to be broadcast, and obtain the sound source signal.

[0090] Further, through acoustic parameter mapping and sound field modeling technical means, the spatial positioning deviation and energy quantization mismatch of discrete device positions and broadcast parameters in the preliminary scheduling strategy are converted into three-dimensional coordinates and standardized sound power levels, and the strategy configuration is converted into a point sound source with explicit spatial coordinates and acoustic energy; further through audio segment loading and signal generation technical means, the format heterogeneity and loudness inconsistency of the alarm audio segment are unified in sampling rate and amplitude, and the sound source signal with spatial, energy and waveform attributes conforming to the input specification of the acoustic digital twin model is generated.

[0091] S4.3, deploy a virtual microphone array as a receiving point in the user activity area in the acoustic digital twin model, and use ray tracing method to calculate the sound wave propagation, reflection and absorption process in the acoustic digital twin model corresponding to each strategy in parallel, and obtain the impulse response data at the receiving point.

[0092] The impulse response data expression is:

[0093] ;

[0094] Wherein, is the impulse response data, is the geometric amplitude attenuation coefficient of the first ray. For vocal syllable index, For the first The propagation delay of each sound ray For the first The reflection coefficient in the direction of sound wave propagation during a secondary reflection event. For the first Sound absorption coefficient along the secondary propagation path For the propagation path, For reflection index, For time variables, for Number of sound ray reflections The air absorption coefficient, For the sound wave at the 1st The distance propagated along the path segment, For the first The total propagation time of each sound ray for The angle between the direction of sound wave propagation and the normal direction of the reflecting interface during a secondary reflection event. The total number of vocal timbres For the first A sound ray passes through a medium region with different acoustic properties during its propagation.

[0095] Furthermore, the key activity areas of the user are located in the acoustic digital twin model, a virtual microphone array is deployed as an acoustic receiving point, and a sound ray tracing algorithm is used to calculate the sound wave propagation path of the sound source corresponding to each strategy in the model in parallel. The reflection, diffraction and material absorption effects of the sound wave during the propagation process are simulated, and the sound pressure response data of each receiving point over time is recorded to generate high-precision impulse response data.

[0096] It should be noted that the summation term of the linear superposition principle... The total sound pressure at any receiving point in the sound field is a linear superposition of the sound wave contributions from all propagation paths. Each sound ray represents an independent sound wave propagation path. The physical essence is the superposition characteristic of the solutions to the wave equation, which conforms to the Huygens-Fresnel principle.

[0097] Geometric divergence decay This describes the natural energy attenuation of a sound wave as it propagates in a free field, caused by the expansion of the wavefront. The calculation formula is... = ,in, For the first The path length of a sound ray is directly derived from the physical law that sound intensity is inversely proportional to the square of the distance, and is a fundamental characteristic of point source radiation.

[0098] Reflection cumulative loss multiplication term The energy loss in each reflection is determined by the reflection coefficient. The value depends on the interface material properties, the sound wave frequency and the incident angle The reflection coefficient modulus is less than or equal to 1, and the loss of multiple reflections is calculated by multiplication, which conforms to the physical fact that the energy decays successively.

[0099] Medium absorption attenuation When the sound wave propagates in the air, energy absorption is caused by viscosity, heat conduction and molecular relaxation effect, and the absorption coefficient significantly increases with the increase of frequency, and the exponential decay form is the sound wave absorption, which conforms to the Lambert-Beer law.

[0100] Time delay and phase Dirac function The energy of each sound ray reaches the receiving point at a certain time, and the Dirac function accurately describes the time delay effect of sound wave propagation. In frequency domain calculation, the time delay is reflected as a phase shift, which is the core cause of sound field interference and reverberation.

[0101] Specifically, the traditional algorithm: numerical solution of wave equation, direct solution of Helmholtz equation or sound wave equation, which needs to be discretized in the whole space, and the calculation complexity increases exponentially with the model size.

[0102] Limitations: huge consumption of computing resources, difficult to parallel process multiple strategy scenarios, and the results lack intuitive path-level physical decomposition.

[0103] The present algorithm improves: high frequency approximation and energy path decomposition, high frequency acoustic assumption, when the sound wave wavelength is much smaller than the environmental geometric size, the sound ray tracking method can approximate the wave propagation, and the physical meaning is clear.

[0104] Energy additivity: the total sound field is regarded as the superposition of multiple independent sound ray energies, and each sound ray represents a propagation path.

[0105] S4.4 Convolution is performed based on the impulse response data and the alarm audio segment to simulate the actual audio signal at the receiving point. Time-frequency analysis is performed on the simulated actual audio signal to extract its Mel frequency cepstral coefficient (MFCC) feature.

[0106] Further, through the convolution operation technical means, the time domain aliasing and energy distortion of the received point analog audio signal synthesized by the impulse response data and the alarm audio segment are processed by time domain convolution and frequency domain filtering, the non-stationary characteristics and the insufficient high frequency resolution of the analog audio signal are processed by windowing framing and critical band mapping through the short-time Fourier transform and the mel filter bank technical means, the dimension redundancy and the high correlation of the mel spectrum characteristics are processed by decorrelation and dimension reduction compression through the discrete cosine transform technical means, and the low-dimensional mel frequency cepstrum coefficient MFCC feature representing the sound channel characteristics and the excitation source separation is extracted.

[0107] S4.5, based on the impulse response data and the alarm audio segment, calculating the voice transmission index value of the receiving point.

[0108] The voice transmission index value expression is:

[0109] ;

[0110] Among them, is the voice transmission index value, is the number of octave band center frequencies, is the number of modulation frequencies, is the modulation frequency index, is the number of modulation frequencies, is the apparent signal-to-noise ratio under the condition of the th octave band center frequency and the th modulation frequency combination, is the reference signal-to-noise ratio, is the curve steepness factor, is the modulation frequency weight.

[0111] Further, through the modulation transmission ratio measurement and psychoacoustic mapping technical means, the physical acoustic parameters and subjective perception disconnection of the received point analog signal generated by the convolution of the impulse response data and the alarm audio segment are processed by multi-band modulation depth analysis and signal-to-noise ratio nonlinear conversion, and the linear time-invariant system characteristics of sound wave propagation are converted into voice transmission index values conforming to the human ear auditory perception characteristics.

[0112] It should be noted that the frequency band processing outer sum The basilar membrane of the human ear has selective response to different frequency sounds

[0113] The formula divides the audio spectrum into B octave bands, independently analyzes the contribution of each frequency band to intelligibility, and finally takes the average, which conforms to the human ear frequency domain analysis characteristics.

[0114] The modulation frequency perception inner sum Speech intelligibility is crucially dependent on the preservation of envelope modulation information, the formula analyzes the signal-to-noise ratio of M modulation frequencies in each frequency band, covering time scale changes such as syllables, words, etc., matching the sensitivity of the auditory nervous system to the timing structure.

[0115] Non-linear signal-to-noise ratio mapping The human ear has a non-linear threshold effect on the perception of signal-to-noise ratio, the intelligibility decreases sharply at low signal-to-noise ratio, and the improvement is limited at high signal-to-noise ratio, the Sigmoid function takes the reference signal-to-noise ratio SNR0 as the inflection point, and the steepness factor Control the transition slope to accurately simulate this psychoacoustic characteristic.

[0116] Modulation frequency weighting weight Different modulation frequencies have different contributions to intelligibility, the weight Based on the setting of hearing experiment data, it reflects the importance difference of modulation domain.

[0117] Specifically, the calculation of the traditional speech transmission index is based on the measurement of the modulation transfer function MTF, which evaluates the intelligibility by analyzing the influence of the acoustic channel on the envelope modulation depth of the test signal, and the standard method needs to measure the signal-to-noise ratio at multiple octave bands and modulation frequencies, and then get The value through a series of conversions and weightings, the calculation process is complex and the physical meaning is not intuitive enough.

[0118] S4.6, integrate the speech transmission index value corresponding to each preliminary scheduling strategy, semantic confusion probability and simulation parameters to generate a simulation report of intelligibility index.

[0119] Furthermore, the integration process first collects the speech transmission index value corresponding to each preliminary scheduling strategy and the semantic confusion probability, while associating and recording the simulation parameters including the target audio playback device identifier, the playback volume parameter, the playback tone parameter and the repetition number parameter; then the speech transmission index value, the semantic confusion probability and the simulation parameters are structured and organized according to the strategy number, to generate a data record containing the strategy number, the speech transmission index value, the semantic confusion probability and the complete simulation parameter list; finally, all the data records of the strategies are summarized into a table form of the simulation report of the intelligibility index.

[0120] S5, according to the simulation report of the intelligibility index, convert the preliminary scheduling strategy from the priority score to the quantifiable expected propagation effect comparison based on physical acoustic simulation, and fine-tune and optimize the strategy parameters according to the acoustic confusion risk assessment, and select the preliminary scheduling strategy with the optimal intelligibility index and the lowest ambiguity risk as the final scheduling execution instruction.

[0121] S5.1, analyze the simulation report to extract the speech transmission index value corresponding to each preliminary scheduling strategy, and generate a mapping list.

[0122] Further, through the structured data extraction and key-value mapping technology means, the correlation between the discrete distribution of voice transmission index values and policy identifiers in the simulation report is matched and aligned with the field processing, and the unstructured simulation result data is converted into a mapping list corresponding to the policy number and the voice transmission index value.

[0123] S5.2, based on the preliminary scheduling strategy parameter in the mapping list, calculate the device resource consumption coefficient;

[0124] The device resource consumption coefficient expression is:

[0125] ;

[0126] Wherein, is the device resource consumption coefficient, is the policy recommended volume, is the maximum available volume of the device, is the alarm audio file, is the device cache upper limit, is the policy recommended repeat broadcast times, is the maximum allowed number of repetitions, is the policy recommended volume weight, is the audio file weight, is the policy recommended repeat broadcast times weight.

[0127] Further, the policy recommended volume, alarm audio file size, and policy recommended repeat broadcast times are extracted from the mapping list, and the maximum available volume of the device, the device cache upper limit, and the maximum allowed number of repetitions are obtained. Then, the policy recommended volume is divided by the maximum available volume of the device to obtain the volume ratio, the alarm audio file size is divided by the device cache upper limit to obtain the file size ratio, and the policy recommended repeat broadcast times is divided by the maximum allowed number of repetitions to obtain the repeat number ratio. Finally, the volume ratio is multiplied by the policy recommended volume weight, the file size ratio is multiplied by the alarm audio file weight, and the repeat number ratio is multiplied by the policy recommended repeat broadcast times weight. The three weighted results are added to obtain the device resource consumption coefficient.

[0128] It should be noted that the power operation simulates the non-linear loss , the volume power consumption : the sound power is proportional to the square of the voltage, and the power consumption increases super-linearly with the increase of the volume, which accurately reflects the physical constraints of the electro-acoustic conversion efficiency.

[0129] File processing overhead Large file transmission involves protocol overhead, cache fragmentation, and other non-linear costs, reflecting the diminishing marginal utility of storage and bandwidth resources.

[0130] Time resource occupation , repeated broadcast occupation device time window, may block other tasks and increase the risk of user disturbance, reflect the cumulative negative effects of repeated behavior.

[0131] Specifically, the traditional device resource evaluation usually adopts a linear weighting model, that is, the volume, file size, repetition times and other parameters are linearly superimposed into a comprehensive score by fixed weights. This method ignores the nonlinear characteristics of resource consumption and the coupling effect between dimensions, resulting in deviation between the evaluation results and the real device load.

[0132] S5.3, query the target audio playback device identifier specified by the policy in the mapping list, obtain the device reliability coefficient and calculate the execution risk coefficient.

[0133] The expression of the execution risk coefficient is:

[0134] ;

[0135] Among them, is the execution risk coefficient, is the basic execution risk coefficient, is the device reliability threshold, is the ambient noise value, is the ambient noise threshold, is the volume redundancy, is the minimum required signal-to-noise ratio, is the basic execution risk coefficient weight, is the ambient noise value weight, is the volume redundancy weight.

[0136] Further, query the target audio playback device identifier specified by the policy in the mapping list corresponding to the device reliability coefficient, and obtain the current ambient noise value and the policy recommended volume parameter; calculate the volume redundancy as the policy recommended volume minus the ambient noise value; compare the device reliability coefficient with the device reliability threshold and the ambient noise value with the ambient noise threshold to obtain the basic execution risk coefficient; compare the volume redundancy with the minimum required signal-to-noise ratio to obtain the volume redundancy risk term; finally, multiply the basic execution risk coefficient by the basic execution risk coefficient weight, multiply the ambient noise value by the ambient noise value weight, and multiply the volume redundancy risk term by the volume redundancy weight to obtain the execution risk coefficient.

[0137] It should be noted that the nonlinear amplification power operation of the risk factor , the device reliability risk The device reliability coefficient is lower, the higher the risk of failure, when < , the ratio 1- 1- >1, index >1 significantly amplifies the risk, reflecting the accelerated rise in failure probability caused by the deterioration of device status.

[0138] environmental interference risk environmental noise value exceeds the environmental noise threshold >1, ratio greater than 1, index >1 amplifies the negative impact of noise on audio masking, consistent with the Weber-Fechner law in acoustics.

[0139] task failure risk , volume redundancy less than the minimum required signal-to-noise ratio ratio <1, but index <0 will make the value greater than 1, inversely amplify the risk, directly simulate the physical law of sound propagation that the failure probability rises sharply when the signal-to-noise ratio is insufficient.

[0140] Specifically, traditional risk assessment usually adopts a linear weighted scorecard model, i.e. by setting fixed weights through expert experience, linearly stacking risk indicators such as device status and environmental parameters into a risk score. This method assumes that risk factors are independent and linearly affect, ignoring the nonlinear threshold effect and multi-factor coupling relationship of actual risk transmission, resulting in a deviation between risk assessment and real failure probability.

[0141] S5.4, substitute the voice transmission index value, semantic confusion probability, device resource consumption coefficient and execution risk coefficient into the comprehensive performance score formula to calculate the comprehensive performance score of each strategy.

[0142] The comprehensive performance score expression is:

[0143] ;

[0144] Among them, is the comprehensive performance score, is the, is the intelligibility utility saturation threshold, is the intelligibility benefit amplification index, is the maximum tolerable confusion threshold, is the semantic confusion probability, is the execution risk realization probability.

[0145] Further, through the multi-factor nonlinear coupling and psychoacoustic utility mapping technology means, the Sigmoid function thresholding processing is performed on the perceptual saturation characteristic loss of the speech transmission index value, the linear intelligibility index is converted into the utility value conforming to the human ear hearing marginal effect; the logistic function conversion is performed on the risk mutation characteristic loss of the semantic confusion probability, the maximum tolerable confusion threshold is taken as the critical point to realize the nonlinear penalty of semantic fidelity; the exponential decay modeling is performed on the rigidity constraint neglecting drawback of the device resource consumption coefficient, the ratio of the resource usage rate to the maximum tolerable value is converted into the performance reduction factor; the Weber distribution function fitting is performed on the probabilistic expression deficiency of the execution risk coefficient, the risk level is mapped into the task failure probability and converted into the success probability complement; through the multiplication coupling mechanism, the four types of parameters are integrated into the unified comprehensive performance score, and the problem that the traditional linear weighting model cannot reflect the nonlinear interaction and coupling amplification between dimensions is solved.

[0146] It should be noted that the nonlinear saturation of intelligibility benefit power operation , simulating the initial high benefit of intelligibility improvement, when is low, the intelligibility improvement is significant, reflecting the sensitivity of the auditory system to the improvement of intelligibility, and the Sigmoid saturation function : defines the intelligibility utility saturation point, when exceeds the threshold , the intelligibility utility saturation threshold, the perceived utility decreases further, which conforms to the Weber-Fechner law of psychoacoustics.

[0147] Threshold penalty of semantic fidelity , Sigmoid decay function, with the maximum tolerable confusion threshold as the critical point, when > , the function value decreases sharply, realizing the one-vote veto effect, and the semantic confusion probability exceeding the limit directly leads to the collapse of the performance score, reflecting the physical constraint that accuracy is prior to intelligibility in information transmission.

[0148] Exponential decay of resource consumption Exponential decay model: when the resource consumption coefficient approaches the maximum tolerable value , the performance decreases exponentially with the resource consumption, reflecting the rigidity constraint of the device resource bottleneck.

[0149] Complement compensation of risk implementation probability , risk implementation probability , the execution risk coefficient is mapped into the task failure probability, and the complement The success probability of the direct characterization task is directly represented, the performance score is physically associated with the risk, and the probability risk analysis principle in reliability engineering is met.

[0150] S5.5, select the preliminary scheduling strategy with the highest comprehensive performance score as the final scheduling execution instruction.

[0151] Further, compare the comprehensive performance score values of all preliminary scheduling strategies, and select the preliminary scheduling strategy with the highest comprehensive performance score value as the final scheduling execution instruction. The scheduling execution instruction includes complete device identification and broadcast parameter set.

[0152] S6, the final scheduling execution instruction is issued to the target audio playback device specified in the instruction.

[0153] S6.1, encapsulate the final scheduling execution instruction into a device-identifiable standard control protocol data packet, and send the control protocol data packet to the network endpoint corresponding to the target audio playback device identification through a secure transmission layer protocol encrypted channel.

[0154] Further, the device identification, broadcast audio file uniform resource identifier, volume parameter value, tone parameter value, and repetition number parameter value included in the final scheduling execution instruction are structured and encapsulated in JSON format to generate a device-identifiable standard control protocol data packet. The encapsulated control protocol data packet is sent to the network endpoint address registered in the device management platform through a secure transmission layer protocol encrypted channel.

[0155] S6.2, the target audio playback device receives and parses the control protocol data packet to extract the broadcast parameters.

[0156] Further, the target audio playback device receives the control protocol data packet through the network interface, decrypts and parses the data packet, and extracts the broadcast audio file uniform resource identifier, volume parameter value, tone parameter value, and repetition number parameter value.

[0157] S6.3, the target audio playback device performs local audio broadcast operation according to the broadcast parameters, and the scheduling engine returns a status code execution confirmation response.

[0158] Further, the target audio playback device performs local audio broadcast operation according to the broadcast parameters obtained by parsing, which includes downloading the audio data file corresponding to the broadcast audio file uniform resource identifier from the storage service, processing the audio data to the specified tone parameter value, outputting through the physical loudspeaker with the specified volume parameter value and repeating the specified repetition number parameter value, and returning an execution confirmation response containing a success or failure status code to the scheduling engine after the operation is completed.

[0159] The embodiment also provides a system for alarm audio call scheduling of an Internet of Things, comprising: a fusion module configured to receive an alarm request message from an Internet of Things sensing terminal, and collect and generate a multi-dimensional information report of real-time environmental noise data, audio playing device state information and user state information according to a device identifier and a region code in the alarm request message;

[0160] a dynamic priority module configured to generate a dynamic priority score of the alarm request message by querying a preset strategy library according to the multi-dimensional information report;

[0161] a preliminary scheduling strategy generation module configured to sort the dynamic priority scores of the alarm request messages to be processed, and generate a preliminary scheduling strategy of a recommended playing device and a broadcast parameter for an alarm request message with the highest priority;

[0162] a simulation report module configured to input the preliminary scheduling strategy into an acoustic digital twin model of an alarm occurrence region, and perform high-fidelity acoustic simulation and ambiguity analysis on the preliminary scheduling strategy by a digital twin from static environment modeling to a dynamic scheduling strategy prediction and optimization engine to generate a simulation report of intelligibility indexes;

[0163] a decision module configured to convert the preliminary scheduling strategy from a priority score to a quantifiable expected propagation effect comparison based on physical acoustic simulation according to the simulation report of intelligibility indexes, fine-tune and optimize the strategy parameters according to an acoustic confusion risk assessment, select a preliminary scheduling strategy with optimal intelligibility indexes and lowest ambiguity risk as a final scheduling execution instruction, and send the final scheduling execution instruction to a target audio playing device.

[0164] The embodiment also provides a computer device suitable for the method for alarm audio call scheduling of an Internet of Things, comprising: a memory and a processor; the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the method for alarm audio call scheduling of an Internet of Things proposed in the above embodiment.

[0165] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. The processor of the computer device is configured 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 running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved by WIFI, an operator network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0166] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the method for scheduling an alarm audio call of an Internet of Things as described above. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk or an optical disk.

[0167] To sum up, the application receives an alarm request message of an Internet of Things sensing terminal, generates a multi-dimensional information report based on device identification and regional coding to collect environmental noise, device status and user status information, and generates a dynamic priority score by using weighted calculation. After sorting the alarm request, a preliminary scheduling strategy is generated for the highest priority alarm, an intelligibility index report is generated by high-fidelity simulation through an acoustic digital twin model, an optimal strategy is selected based on the simulation result to generate an execution instruction and is delivered to a target audio device, and the whole-process intelligent scheduling from multi-dimensional dynamic sensing to acoustic effect optimization is realized.

[0168] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A method for Internet of Things alert audio call dispatching, the method comprising: The method comprises the following steps: The device unique identifier and the alarm occurrence area code in the alarm request message are parsed, the environment monitoring service is queried according to the device unique identifier and the alarm occurrence area code, real-time environment noise data are acquired, the device management device is queried according to the device unique identifier and the alarm occurrence area code, and audio playback device state information is acquired; The user state service is queried according to the device unique identifier and the alarm occurrence area code, and user state information is acquired; The real-time environment noise data, the audio playback device state information and the user state information are integrated, and a multi-dimensional information report is generated; The environment noise value in the multi-dimensional information report is directly converted into an environment noise coefficient; The device state data are extracted, the device state data are collected through multi-dimensional device health indicators, a dynamic health degree score is generated by using weighted fusion, a device health degree score library is established, and a device reliability coefficient is directly acquired; The user activity information is mapped into a user state emergency coefficient, a basic priority coefficient is generated by extracting the alarm type from the alarm request message, a timestamp in the alarm request message is acquired and a time difference from the current time is derived, and a time attenuation factor is derived through an exponential decay function; An associated event enhancement factor is generated by querying the log to count the number of associated events according to the alarm occurrence area code; The basic priority coefficient, the environment noise coefficient, the user state emergency coefficient, the device reliability coefficient, the time attenuation factor and the associated event enhancement factor are integrated to generate a dynamic priority score; The dynamic priority scores of the alarm request messages to be processed are sorted, and a preliminary scheduling strategy of the recommended playback device and the broadcast parameter is generated for the alarm request message with the highest priority; The preliminary scheduling strategy is input into the acoustic digital twin model of the alarm occurrence area, the digital twin is used to convert the static environment modeling into a dynamic scheduling strategy prediction and optimization engine, high-fidelity acoustic simulation and ambiguity analysis are performed on the preliminary scheduling strategy, and a simulation report of the intelligibility indicator is generated, including the following steps: Based on the physical space three-dimensional geometric data corresponding to the alarm occurrence area code, the interface material acoustic parameters and the real-time environment noise data, the acoustic digital twin model is obtained by the finite element method; Each strategy in the preliminary scheduling strategy is converted into an acoustic simulation parameter, the target audio playback device position in each strategy in the preliminary scheduling strategy is set as a point sound source in the acoustic digital twin model, the sound power level is calculated according to the broadcast volume parameter in the strategy, the alarm audio segment to be broadcast is loaded, and a sound source signal is obtained; A virtual microphone array is deployed as a receiving point in the user activity area in the acoustic digital twin model, the sound wave propagation, reflection and absorption process in the acoustic digital twin model corresponding to each strategy is calculated in parallel by using the ray tracing method, and impulse response data at the receiving point are obtained; ​ Convolution is performed between the impulse response data and the alarm audio segment to simulate the actual audio signal at the receiving point, time-frequency analysis is performed on the simulated actual audio signal, and the mel frequency cepstral coefficient (MFCC) feature is extracted; Based on the impulse response data and the alarm audio segment, the speech transmission index value of the receiving point is calculated; Integrate the speech transmission index value, semantic confusion probability and simulation parameters corresponding to each preliminary scheduling strategy to generate a simulation report of intelligibility index; According to the simulation report of intelligibility index, the preliminary scheduling strategy is converted from priority score to quantifiable expected propagation effect comparison based on physical acoustics simulation, and the strategy parameters are fine-tuned and optimized according to the acoustic confusion risk assessment, and the preliminary scheduling strategy with the optimal intelligibility index and the lowest ambiguity risk is set as the final scheduling execution instruction, including the following steps: Analyze the simulation report to extract the speech transmission index value corresponding to each preliminary scheduling strategy, and generate a mapping list; Based on the preliminary scheduling strategy parameters in the mapping list, calculate the device resource consumption coefficient; Query the target audio playback device identifier specified in the strategy in the mapping list, obtain the device reliability coefficient and calculate the execution risk coefficient; Substitute the speech transmission index value, semantic confusion probability, device resource consumption coefficient and execution risk coefficient into the comprehensive performance score formula to calculate the comprehensive performance score of each strategy; Select the preliminary scheduling strategy with the highest comprehensive performance score and set it as the final scheduling execution instruction; Issue the final scheduling execution instruction to the target audio playback device.

2. The method of IoT alert audio call dispatching of claim 1, wherein: Sort the dynamic priority scores of the alarm request messages to be processed, and generate a preliminary scheduling strategy for the recommended playback device and broadcast parameters for the alarm request message with the highest priority, including the following steps: Sort the alarm request messages to be processed according to the dynamic priority scores from high to low to generate an ordered sorted alarm request queue, select the alarm request message at the top of the sorted alarm request queue, and obtain the highest priority alarm to be scheduled; According to the alarm occurrence area code in the alarm request message, query the online audio playback devices registered in the device management platform to obtain the candidate audio playback device list and the candidate audio playback device list; For each audio playback device in the candidate audio playback device list, filter out the device-environment matching degree score; Combine the device-environment matching degree score, the dynamic priority score of the alarm request message and the environmental noise data in the multi-dimensional information report to generate the expected broadcast utility value of each audio playback device, and generate a preliminary scheduling strategy for the recommended volume, tone and repetition number based on the expected broadcast utility value of each device.

3. The method of IoT alert audio call dispatching of claim 1, wherein: Issue the final scheduling execution instruction to the target audio playback device, including the following steps: Package the final scheduling execution instruction into a standard control protocol data packet recognizable by the device, and send the control protocol data packet to the network endpoint corresponding to the target audio playback device identifier through a secure transmission layer protocol encryption channel; The target audio playback device receives and analyzes the control protocol data packet to extract the broadcast parameters; The target audio playback device performs local audio broadcast operation according to the broadcast parameters, and the scheduling engine returns a status code to confirm the response.

4. A system for dispatching an alarm audio call for an Internet of Things based on the method for dispatching an alarm audio call for an Internet of Things according to any one of claims 1 to 3, characterized in that: The method comprises the following steps: a fusion module receives an alarm request message from an Internet of Things sensing terminal, collects and generates a multi-dimensional information report of real-time environmental noise data, audio playback device state information and user state information according to the device identifier and the area code in the alarm request message; a dynamic priority module generates a dynamic priority score of the alarm request message by querying a preset strategy library according to the multi-dimensional information report; a preliminary scheduling strategy generation module sorts the dynamic priority scores of the alarm request messages to be processed, and generates a preliminary scheduling strategy of a recommended playback device and a broadcast parameter for the alarm request message with the highest priority; a simulation report module inputs the preliminary scheduling strategy into an acoustic digital twin model of an alarm occurrence area, converts the preliminary scheduling strategy into a dynamic scheduling strategy prediction and optimization engine through digital twinning from static environment modeling, performs high-fidelity acoustic simulation and ambiguity analysis on the preliminary scheduling strategy, and generates a simulation report of intelligibility indicators; a decision module converts the preliminary scheduling strategy from a priority score into a quantifiable expected propagation effect comparison based on physical acoustic simulation according to the simulation report of intelligibility indicators, fine-tunes and optimizes the strategy parameters according to an acoustic confusion risk assessment, selects a preliminary scheduling strategy with optimal intelligibility indicators and the lowest ambiguity risk as a final scheduling execution instruction, and sends the final scheduling execution instruction to a target audio playback device.

5. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that: The processor executes the computer program to realize the steps of the method for scheduling an alarm audio call of the Internet of Things according to any one of claims 1-3.

6. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the method for scheduling an alarm audio call of the Internet of Things according to any one of claims 1-3.

Images