Emergency traffic evacuation path planning method and system

Abstract

The invention discloses an emergency traffic evacuation path planning method and system. The method comprises the following steps: acquiring multiple pieces of sound information of an emergency event area; according to a voice analysis algorithm, analyzing a voice text and a voice type corresponding to each piece of voice information; according to a sound text and a sound type corresponding to each piece of sound information, determining vehicle danger probabilities corresponding to a plurality of sub-regions of the emergency event region; and calculating an evacuation path corresponding to the emergency event area according to the vehicle danger probabilities corresponding to the plurality of sub-areas. Therefore, the sound information of the emergency event area can be effectively utilized for route planning, the safety and efficiency of route planning are improved, and further loss is reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an emergency traffic evacuation route planning method and system. Background Technology

[0002] Accurately determining vehicle evacuation routes during traffic emergencies is of significant technical importance for safe vehicle evacuation and traffic congestion relief. Efficiently determining accurate and safe evacuation routes is a major technical challenge. Current traffic evacuation route planning technologies do not adequately utilize on-site sound data to delineate hazardous areas and determine evacuation routes accordingly. Therefore, their planning efficiency is low, and the planned routes have poor reliability. Clearly, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an emergency traffic evacuation route planning method and system, which can effectively utilize sound information in emergency event areas for route planning, improve the safety and efficiency of route planning, and reduce further losses.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses an emergency traffic evacuation route planning method, the method comprising:

[0005] Acquire multiple audio information from the emergency area;

[0006] Based on the speech analysis algorithm, analyze the audio text and audio type corresponding to each piece of audio information;

[0007] Based on the audio text and audio type corresponding to each audio information, determine the vehicle danger probability corresponding to multiple sub-regions of the emergency event area;

[0008] Based on the vehicle hazard probability corresponding to the multiple sub-regions, the evacuation route corresponding to the emergency event area is calculated.

[0009] As an optional implementation, in the first aspect of the present invention, the step of analyzing the audio text and audio type corresponding to each audio information according to the speech analysis algorithm includes:

[0010] The multiple sound information are processed based on a denoising synthesis algorithm to obtain the regional sound information corresponding to each sub-region of the emergency event area;

[0011] The sound information of each region is input into the sound processing algorithm model to obtain the sound text and sound type corresponding to the sound information of each region.

[0012] As an optional implementation, in the first aspect of the present invention, the step of processing the plurality of sound information based on a denoising synthesis algorithm to obtain regional sound information corresponding to each sub-region of the emergency event region includes:

[0013] For each sub-region of the emergency event area, all sound information whose location information belongs to that sub-region among the multiple sound information are determined as the regional sound material corresponding to that sub-region;

[0014] The wavelet transform algorithm is used to denoise all the sound materials of the sub-region to obtain multiple denoised sound materials of the sub-region.

[0015] Calculate the sound similarity between any two sound data points from the same time period in any two of the denoised sound materials;

[0016] For any given time period, the audio data of at least two noise audio materials whose audio similarity is greater than a first similarity threshold within that time period are mixed and synthesized to obtain the synthesized audio material corresponding to that time period.

[0017] The synthesized sound materials corresponding to all the time periods are combined to obtain the regional sound information corresponding to the sub-region.

[0018] As an optional implementation, in the first aspect of the present invention, the step of inputting the sound information of each region into a sound processing algorithm model to obtain the sound text and sound type corresponding to the sound information of each region includes:

[0019] For each area of ​​sound information, the dialogue sound portion and the non-dialogue sound portion in the area of ​​sound information are determined based on the classifier model;

[0020] Based on the speech-to-text recognition algorithm model, the audio text corresponding to the dialogue audio portion is determined;

[0021] Based on the template matching algorithm, the sound type corresponding to the non-dialogue sound part is determined.

[0022] As an optional implementation, in the first aspect of the invention, determining the dialogue voice portion and the non-dialogue voice portion in the sound information of the region based on the classifier model includes:

[0023] Each part of the sound information in the region is input into a trained sound classifier neural network model to determine whether each part of the sound information in the region is a dialogue sound part or a non-dialogue sound part; the sound classifier neural network model is trained on a training dataset that includes multiple training sound information and corresponding sound type labels; the sound type labels are either dialogue labels or non-dialogue labels.

[0024] As an optional implementation, in the first aspect of the invention, determining the sound type corresponding to the non-dialogue sound portion based on the template matching algorithm includes:

[0025] Calculate the template similarity between each preset emergency event sound template and the non-dialogue sound portion;

[0026] The template sound type corresponding to the emergency event sound template with the highest template similarity is determined as the sound type corresponding to the non-dialogue sound part; the sound type includes at least one of groaning, vehicle collision sound, glass breaking sound, shouting sound and explosion sound.

[0027] As an optional implementation, in the first aspect of the present invention, determining the vehicle danger probability corresponding to multiple sub-regions of the emergency event area based on the audio text and audio type corresponding to each audio information includes:

[0028] For each sub-region, determine the text set of all the sound texts corresponding to the sound information of the region corresponding to that sub-region;

[0029] Determine the set of sound types corresponding to all the sound information of the sub-region;

[0030] Based on preset keyword scoring rules, calculate the text danger score corresponding to the text set;

[0031] Based on the preset type score correspondence, calculate the type risk score corresponding to the type set;

[0032] Calculate the weighted average of the text hazard score and the type hazard score to obtain the vehicle hazard probability corresponding to the sub-region.

[0033] As an optional implementation, in the first aspect of the present invention, calculating the evacuation route corresponding to the emergency event area based on the vehicle hazard probability corresponding to the plurality of sub-regions includes:

[0034] The objective functions include minimizing the length of the evacuation routes and minimizing the average curvature of the evacuation routes.

[0035] The limiting conditions include that the vertical distance between the evacuation route and the regional center house of each sub-area is greater than a preset distance threshold, and that the vertical distance is proportional to the vehicle danger probability of the corresponding sub-area;

[0036] Based on the objective function and the constraints, the route calculation for the emergency event area is repeatedly iterated using spatial search and dynamic programming algorithms until the optimal evacuation route is obtained and determined as the evacuation path corresponding to the emergency event area.

[0037] A second aspect of this invention discloses an emergency traffic evacuation route planning system, the system comprising:

[0038] The acquisition module is used to acquire multiple sound information from the emergency area;

[0039] The analysis module is used to analyze the audio text and audio type corresponding to each audio information according to the speech analysis algorithm;

[0040] The determination module is used to determine the vehicle danger probability corresponding to multiple sub-regions of the emergency event area based on the sound text and sound type corresponding to each sound information.

[0041] The calculation module is used to calculate the evacuation route corresponding to the emergency event area based on the vehicle danger probability corresponding to the multiple sub-areas.

[0042] As an optional implementation, in a second aspect of the invention, the analysis module analyzes the specific method by which it analyzes the audio text and audio type corresponding to each audio information according to a speech analysis algorithm, including:

[0043] The multiple sound information are processed based on a denoising synthesis algorithm to obtain the regional sound information corresponding to each sub-region of the emergency event area;

[0044] The sound information of each region is input into the sound processing algorithm model to obtain the sound text and sound type corresponding to the sound information of each region.

[0045] As an optional implementation, in a second aspect of the invention, the specific method by which the analysis module processes the plurality of sound information based on a denoising synthesis algorithm to obtain the regional sound information corresponding to each sub-region of the emergency event region includes:

[0046] For each sub-region of the emergency event area, all sound information whose location information belongs to that sub-region among the multiple sound information are determined as the regional sound material corresponding to that sub-region;

[0047] The wavelet transform algorithm is used to denoise all the sound materials of the sub-region to obtain multiple denoised sound materials of the sub-region.

[0048] Calculate the sound similarity between any two sound data points from the same time period in any two of the denoised sound materials;

[0049] For any given time period, the audio data of at least two noise audio materials whose audio similarity is greater than a first similarity threshold within that time period are mixed and synthesized to obtain the synthesized audio material corresponding to that time period.

[0050] The synthesized sound materials corresponding to all the time periods are combined to obtain the regional sound information corresponding to the sub-region.

[0051] As an optional implementation, in a second aspect of the invention, the analysis module inputs the sound information of each region into a sound processing algorithm model to obtain the sound text and sound type corresponding to the sound information of each region in a specific manner, including:

[0052] For each area of ​​sound information, the dialogue sound portion and the non-dialogue sound portion in the area of ​​sound information are determined based on the classifier model;

[0053] Based on the speech-to-text recognition algorithm model, the audio text corresponding to the dialogue audio portion is determined;

[0054] Based on the template matching algorithm, the sound type corresponding to the non-dialogue sound part is determined.

[0055] As an optional implementation, in a second aspect of the invention, the analysis module determines the dialogue audio portion and the non-dialogue audio portion in the sound information of the region based on a classifier model, including:

[0056] Each part of the sound information in the region is input into a trained sound classifier neural network model to determine whether each part of the sound information in the region is a dialogue sound part or a non-dialogue sound part; the sound classifier neural network model is trained on a training dataset that includes multiple training sound information and corresponding sound type labels; the sound type labels are either dialogue labels or non-dialogue labels.

[0057] As an optional implementation, in a second aspect of the invention, the specific method by which the analysis module determines the sound type corresponding to the non-dialogue voice portion based on a template matching algorithm includes:

[0058] Calculate the template similarity between each preset emergency event sound template and the non-dialogue sound portion;

[0059] The template sound type corresponding to the emergency event sound template with the highest template similarity is determined as the sound type corresponding to the non-dialogue sound part; the sound type includes at least one of groaning, vehicle collision sound, glass breaking sound, shouting sound and explosion sound.

[0060] As an optional implementation, in a second aspect of the invention, the determining module determines the vehicle danger probability corresponding to multiple sub-regions of the emergency event area based on the audio text and audio type corresponding to each audio information, including:

[0061] For each sub-region, determine the text set of all the sound texts corresponding to the sound information of the region corresponding to that sub-region;

[0062] Determine the set of sound types corresponding to all the sound information of the sub-region;

[0063] Based on preset keyword scoring rules, calculate the text danger score corresponding to the text set;

[0064] Based on the preset type score correspondence, calculate the type risk score corresponding to the type set;

[0065] Calculate the weighted average of the text hazard score and the type hazard score to obtain the vehicle hazard probability corresponding to the sub-region.

[0066] As an optional implementation, in a second aspect of the invention, the calculation module calculates the specific method of the evacuation route corresponding to the emergency event area based on the vehicle hazard probability corresponding to the plurality of sub-regions, including:

[0067] The objective functions include minimizing the length of the evacuation routes and minimizing the average curvature of the evacuation routes.

[0068] The limiting conditions include that the vertical distance between the evacuation route and the regional center house of each sub-area is greater than a preset distance threshold, and that the vertical distance is proportional to the vehicle danger probability of the corresponding sub-area;

[0069] Based on the objective function and the constraints, the route calculation for the emergency event area is repeatedly iterated using spatial search and dynamic programming algorithms until the optimal evacuation route is obtained and determined as the evacuation path corresponding to the emergency event area.

[0070] A third aspect of the present invention discloses another emergency traffic evacuation route planning system, the system comprising:

[0071] Memory containing executable program code;

[0072] A processor coupled to the memory;

[0073] The processor calls the executable program code stored in the memory to execute some or all of the steps in the emergency traffic evacuation route planning method disclosed in the first aspect of the present invention.

[0074] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the emergency traffic evacuation route planning method disclosed in the first aspect of the present invention.

[0075] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0076] This invention can analyze the text and type of multiple sound information in an emergency area, and then determine the vehicle danger probability corresponding to each sub-area to calculate a more accurate evacuation route. This allows for the effective use of sound information in emergency areas for route planning, improving the safety and efficiency of route planning and reducing further losses. Attached Figure Description

[0077] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0078] Figure 1 This is a flowchart illustrating an emergency traffic evacuation route planning method disclosed in an embodiment of the present invention.

[0079] Figure 2 This is a schematic diagram of the structure of an emergency traffic evacuation route planning system disclosed in an embodiment of the present invention.

[0080] Figure 3 This is a schematic diagram of another emergency traffic evacuation route planning system disclosed in an embodiment of the present invention. Detailed Implementation

[0081] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0082] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0083] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0084] This invention discloses an emergency traffic evacuation route planning method and system. It analyzes the text and type of multiple sound information sources in an emergency area to determine the vehicle hazard probability for each sub-area, thereby calculating a more accurate evacuation route. This effectively utilizes sound information from the emergency area for route planning, improving the safety and efficiency of route planning and reducing further losses. Detailed explanations follow.

[0085] Example 1

[0086] Please see Figure 1 , Figure 1 This is a flowchart illustrating an emergency traffic evacuation route planning method disclosed in an embodiment of the present invention. Figure 1 The described emergency traffic evacuation route planning method can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 1 As shown, this emergency traffic evacuation route planning method may include the following operations:

[0087] 101. Obtain multiple sound information from the emergency area.

[0088] 102. Based on the speech analysis algorithm, analyze the audio text and audio type corresponding to each audio information.

[0089] 103. Based on the audio text and audio type corresponding to each audio information, determine the vehicle danger probability corresponding to multiple sub-regions of the emergency event area.

[0090] 104. Calculate the evacuation routes corresponding to the emergency event area based on the vehicle hazard probabilities corresponding to multiple sub-areas.

[0091] Optionally, the sound information can be acquired through a microphone device installed on the vehicle or through a microphone device on a user device of a user in the emergency area. When transmitting the sound information, it is generally set to carry the location information acquired at the time of acquisition by default, so as to facilitate subsequent calculation and classification.

[0092] As can be seen, the above-described embodiments of the invention can analyze the text and type of multiple sound information in an emergency area, and then determine the vehicle danger probability corresponding to each sub-area, so as to calculate a more accurate evacuation route. This allows for the effective use of sound information in the emergency area for route planning, improving the safety and efficiency of route planning and reducing further losses.

[0093] As an optional embodiment, the step above, analyzing the audio text and audio type corresponding to each audio piece of information according to the speech analysis algorithm, includes:

[0094] Multiple sound information are processed based on a denoising synthesis algorithm to obtain the regional sound information corresponding to each sub-region of the emergency event area;

[0095] The sound information of each region is input into the sound processing algorithm model to obtain the sound text and sound type corresponding to the sound information of each region.

[0096] As can be seen, through the above optional embodiments, multiple sound information can be processed by a denoising and synthesis algorithm to determine the regional sound information corresponding to each sub-region. Then, based on the sound processing algorithm model, the sound text and type can be determined, which facilitates the subsequent accurate determination of the vehicle danger probability corresponding to each sub-region, so as to calculate a more accurate evacuation route. This helps to realize route planning using the sound information of the emergency event area, improves the safety and efficiency of route planning, and reduces further losses.

[0097] As an optional embodiment, the above steps, processing multiple sound information based on a denoising synthesis algorithm to obtain regional sound information corresponding to each sub-region of the emergency event area, include:

[0098] For each sub-region of the emergency event area, all sound information whose location information belongs to that sub-region among multiple sound information are identified as the regional sound material corresponding to that sub-region;

[0099] The wavelet transform algorithm is used to denoise all the regional sound materials of the sub-region to obtain multiple denoised sound materials of the sub-region.

[0100] Calculate the audio similarity between audio data from any two denoised audio materials at any time segment;

[0101] For any given time period, the audio data of at least two noise audio materials with a similarity greater than the first similarity threshold within that time period are mixed and synthesized to obtain the synthesized audio material corresponding to that time period.

[0102] By combining the synthesized sound materials corresponding to all time periods, the regional sound information corresponding to that sub-region is obtained.

[0103] As can be seen, through the above optional embodiments, by combining all sound information belonging to the sub-region of the location information and then performing noise reduction and similarity calculation, the regional sound information corresponding to each sub-region can be determined. This allows for the subsequent determination of the sound text and type based on the sound processing algorithm model, facilitating the calculation of more accurate evacuation routes. This helps to realize route planning using sound information from emergency event areas, improving the safety and efficiency of route planning and reducing further losses.

[0104] As an optional embodiment, the step described above, inputting the sound information of each region into the sound processing algorithm model to obtain the sound text and sound type corresponding to the sound information of each region, includes:

[0105] For each region's sound information, based on the classifier model, the dialogue sound portion and the non-dialogue sound portion in the sound information of that region are determined;

[0106] Based on the speech-to-text recognition algorithm model, determine the audio text corresponding to the dialogue audio portion;

[0107] Based on template matching algorithm, determine the sound type corresponding to the part of the voice without dialogue.

[0108] Optionally, the speech-to-text recognition algorithm model can be implemented using existing open-source speech-to-text algorithm models.

[0109] As can be seen, through the above optional embodiments, the dialogue part and the non-dialogue part can be distinguished by the binary classifier model, and then the text and type can be determined respectively, so as to calculate a more accurate evacuation route in the future. This helps to realize route planning using sound information in emergency areas, improves the safety and efficiency of route planning, and reduces further losses.

[0110] As an optional embodiment, the step described above, determining the dialogue audio portion and the non-dialogue audio portion in the sound information of the region based on the classifier model, includes:

[0111] Each part of the sound information in the region is input into a trained sound classifier neural network model to determine whether each part of the sound information in the region is a dialogue sound part or a non-dialogue sound part; optionally, the sound classifier neural network model is trained using a training dataset that includes multiple training sound information and corresponding sound type labels; the sound type labels are either dialogue labels or non-dialogue labels.

[0112] Optionally, the sound classifier neural network model can be an SVM classifier or a convolutional neural network algorithm model, and it is trained using the corresponding training dataset. During training, the model parameters are optimized based on the L1 loss function and gradient descent algorithm until convergence.

[0113] As can be seen, through the above optional embodiments, a trained sound classifier neural network model can determine whether each part of the regional sound information is a dialogue sound or a non-dialogue sound, so as to subsequently determine the text and type, thereby assisting in the use of sound information in emergency event areas for route planning, improving the safety and efficiency of route planning, and reducing further losses.

[0114] As an optional embodiment, the step above, determining the sound type corresponding to the non-dialogue sound portion based on the template matching algorithm, includes:

[0115] Calculate the template similarity between each preset emergency event sound template and the non-dialogue sound portion;

[0116] The template sound type corresponding to the emergency event sound template with the highest template similarity is determined as the sound type corresponding to the non-dialogue sound part; the sound type includes at least one of groaning, vehicle collision sound, glass breaking sound, shouting sound and explosion sound.

[0117] Optionally, template similarity can be calculated based on a vector distance algorithm.

[0118] As can be seen, through the above optional embodiments, the similarity between the emergency event sound template and the non-dialogue sound part can be calculated, and then the sound type corresponding to the non-dialogue sound part can be accurately determined, so as to calculate a more accurate evacuation route in the future. This helps to realize route planning using the sound information of the emergency event area, improves the safety and efficiency of route planning, and reduces further losses.

[0119] As an optional embodiment, the step above, determining the vehicle danger probability corresponding to multiple sub-regions of the emergency event area based on the audio text and audio type corresponding to each audio information, includes:

[0120] For each sub-region, determine the set of audio texts corresponding to all regional audio information in that sub-region;

[0121] Determine the set of sound types corresponding to all regional sound information of the sub-region;

[0122] Based on preset keyword scoring rules, calculate the text danger score corresponding to the text set;

[0123] Based on the preset type score correspondence, calculate the type risk score corresponding to the type set;

[0124] Calculate the weighted average of the text hazard score and the type hazard score to obtain the vehicle hazard probability corresponding to the sub-region.

[0125] Optionally, the preset keyword scoring rule can be to match and identify specific hazardous keywords in the text set, and then sum a specific score for each identified hazardous keyword. The specific score setting can be preset by the operator based on experiments or experience. Similarly, the type score correspondence can also be preset by the operator based on experiments or experience, or the above-mentioned hazard scoring work can be implemented through a convolutional neural network.

[0126] As can be seen, through the above optional embodiments, the risk score of the sound text and type in each sub-region can be separately calculated to comprehensively calculate the vehicle risk probability of the sub-region, so as to calculate a more accurate evacuation route in the future. This helps to realize route planning using sound information in emergency event areas, improves the safety and efficiency of route planning, and reduces further losses.

[0127] As an optional embodiment, the step above, calculating the evacuation route corresponding to the emergency event area based on the vehicle hazard probability corresponding to multiple sub-areas, includes:

[0128] The objective functions include minimizing the length of the evacuation routes and minimizing the average curvature of the evacuation routes.

[0129] The restrictions include that the vertical distance between the evacuation route and the central house of each sub-area is greater than a preset distance threshold, and that the vertical distance is proportional to the vehicle hazard probability of the corresponding sub-area.

[0130] Based on the objective function and constraints, the route calculation for the emergency event area is iteratively performed using spatial search and dynamic programming algorithms until the optimal evacuation route is obtained and determined as the evacuation path corresponding to the emergency event area.

[0131] As can be seen, through the above optional embodiments, route calculations can be iteratively performed on the emergency event area based on the set objective function and constraints until the optimal evacuation route is obtained, so as to calculate a more accurate and safer evacuation path. This allows the use of sound information from the emergency event area for route planning, thereby improving the safety and efficiency of route planning and reducing further losses.

[0132] Example 2

[0133] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an emergency traffic evacuation route planning system disclosed in an embodiment of the present invention. Figure 2 The described emergency traffic evacuation route planning system can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 2 As shown, the emergency traffic evacuation route planning system may include:

[0134] The acquisition module 201 is used to acquire multiple sound information from the emergency event area.

[0135] The analysis module 202 is used to analyze the audio text and audio type corresponding to each audio information according to the speech analysis algorithm.

[0136] The determination module 203 is used to determine the vehicle danger probability corresponding to multiple sub-regions of the emergency event area based on the sound text and sound type corresponding to each sound information.

[0137] The calculation module 204 is used to calculate the evacuation route corresponding to the emergency event area based on the vehicle danger probability corresponding to multiple sub-areas.

[0138] As can be seen, the above-described embodiments of the invention can analyze the text and type of multiple sound information in an emergency area, and then determine the vehicle danger probability corresponding to each sub-area, so as to calculate a more accurate evacuation route. This allows for the effective use of sound information in the emergency area for route planning, improving the safety and efficiency of route planning and reducing further losses.

[0139] As an optional embodiment, the analysis module analyzes the specific method by which it analyzes the audio text and audio type corresponding to each audio piece of information according to the speech analysis algorithm, including:

[0140] Multiple sound information are processed based on a denoising synthesis algorithm to obtain the regional sound information corresponding to each sub-region of the emergency event area;

[0141] The sound information of each region is input into the sound processing algorithm model to obtain the sound text and sound type corresponding to the sound information of each region.

[0142] As can be seen, through the above optional embodiments, multiple sound information can be processed by a denoising and synthesis algorithm to determine the regional sound information corresponding to each sub-region. Then, based on the sound processing algorithm model, the sound text and type can be determined, which facilitates the subsequent accurate determination of the vehicle danger probability corresponding to each sub-region, so as to calculate a more accurate evacuation route. This helps to realize route planning using the sound information of the emergency event area, improves the safety and efficiency of route planning, and reduces further losses.

[0143] As an optional embodiment, the analysis module processes multiple sound information based on a denoising and synthesis algorithm to obtain the specific method of regional sound information corresponding to each sub-region of the emergency event area, including:

[0144] For each sub-region of the emergency event area, all sound information whose location information belongs to that sub-region among multiple sound information are identified as the regional sound material corresponding to that sub-region;

[0145] The wavelet transform algorithm is used to denoise all the regional sound materials of the sub-region to obtain multiple denoised sound materials of the sub-region.

[0146] Calculate the audio similarity between audio data from any two denoised audio materials at any time segment;

[0147] For any given time period, the audio data of at least two noise audio materials with a similarity greater than the first similarity threshold within that time period are mixed and synthesized to obtain the synthesized audio material corresponding to that time period.

[0148] By combining the synthesized sound materials corresponding to all time periods, the regional sound information corresponding to that sub-region is obtained.

[0149] As can be seen, through the above optional embodiments, by combining all sound information belonging to the sub-region of the location information and then performing noise reduction and similarity calculation, the regional sound information corresponding to each sub-region can be determined. This allows for the subsequent determination of the sound text and type based on the sound processing algorithm model, facilitating the calculation of more accurate evacuation routes. This helps to realize route planning using sound information from emergency event areas, improving the safety and efficiency of route planning and reducing further losses.

[0150] As an optional embodiment, the analysis module inputs the sound information of each region into the sound processing algorithm model to obtain the specific method of the sound text and sound type corresponding to the sound information of each region, including:

[0151] For each region's sound information, based on the classifier model, the dialogue sound portion and the non-dialogue sound portion in the sound information of that region are determined;

[0152] Based on the speech-to-text recognition algorithm model, determine the audio text corresponding to the dialogue audio portion;

[0153] Based on template matching algorithm, determine the sound type corresponding to the part of the voice without dialogue.

[0154] As can be seen, through the above optional embodiments, the dialogue part and the non-dialogue part can be distinguished by the binary classifier model, and then the text and type can be determined respectively, so as to calculate a more accurate evacuation route in the future. This helps to realize route planning using sound information in emergency areas, improves the safety and efficiency of route planning, and reduces further losses.

[0155] As an optional embodiment, the analysis module determines the specific method by which it identifies the dialogue and non-dialogue components in the sound information of the region based on a classifier model, including:

[0156] Each part of the sound information in the region is input into a trained sound classifier neural network model to determine whether each part of the sound information in the region is a dialogue sound part or a non-dialogue sound part; optionally, the sound classifier neural network model is trained using a training dataset that includes multiple training sound information and corresponding sound type labels; the sound type labels are either dialogue labels or non-dialogue labels.

[0157] As can be seen, through the above optional embodiments, a trained sound classifier neural network model can determine whether each part of the regional sound information is a dialogue sound or a non-dialogue sound, so as to subsequently determine the text and type, thereby assisting in the use of sound information in emergency event areas for route planning, improving the safety and efficiency of route planning, and reducing further losses.

[0158] As an optional embodiment, the analysis module determines the specific method by which it determines the sound type corresponding to the non-dialogue sound portion based on a template matching algorithm, including:

[0159] Calculate the template similarity between each preset emergency event sound template and the non-dialogue sound portion;

[0160] The template sound type corresponding to the emergency event sound template with the highest template similarity is determined as the sound type corresponding to the non-dialogue sound part; the sound type includes at least one of groaning, vehicle collision sound, glass breaking sound, shouting sound and explosion sound.

[0161] As can be seen, through the above optional embodiments, the similarity between the emergency event sound template and the non-dialogue sound part can be calculated, and then the sound type corresponding to the non-dialogue sound part can be accurately determined, so as to calculate a more accurate evacuation route in the future. This helps to realize route planning using the sound information of the emergency event area, improves the safety and efficiency of route planning, and reduces further losses.

[0162] As an optional embodiment, the determining module determines the specific method by which it determines the vehicle danger probability corresponding to multiple sub-regions of the emergency event area based on the audio text and audio type corresponding to each audio information, including:

[0163] For each sub-region, determine the set of audio texts corresponding to all regional audio information in that sub-region;

[0164] Determine the set of sound types corresponding to all regional sound information of the sub-region;

[0165] Based on preset keyword scoring rules, calculate the text danger score corresponding to the text set;

[0166] Based on the preset type score correspondence, calculate the type risk score corresponding to the type set;

[0167] Calculate the weighted average of the text hazard score and the type hazard score to obtain the vehicle hazard probability corresponding to the sub-region.

[0168] As can be seen, through the above optional embodiments, the risk score of the sound text and type in each sub-region can be separately calculated to comprehensively calculate the vehicle risk probability of the sub-region, so as to calculate a more accurate evacuation route in the future. This helps to realize route planning using sound information in emergency event areas, improves the safety and efficiency of route planning, and reduces further losses.

[0169] As an optional embodiment, the calculation module calculates the specific method of the evacuation route corresponding to the emergency event area based on the vehicle hazard probability corresponding to multiple sub-regions, including:

[0170] The objective functions include minimizing the length of the evacuation routes and minimizing the average curvature of the evacuation routes.

[0171] The restrictions include that the vertical distance between the evacuation route and the central house of each sub-area is greater than a preset distance threshold, and that the vertical distance is proportional to the vehicle hazard probability of the corresponding sub-area.

[0172] Based on the objective function and constraints, the route calculation for the emergency event area is iteratively performed using spatial search and dynamic programming algorithms until the optimal evacuation route is obtained and determined as the evacuation path corresponding to the emergency event area.

[0173] As can be seen, through the above optional embodiments, route calculations can be iteratively performed on the emergency event area based on the set objective function and constraints until the optimal evacuation route is obtained, so as to calculate a more accurate and safer evacuation path. This allows the use of sound information from the emergency event area for route planning, thereby improving the safety and efficiency of route planning and reducing further losses.

[0174] Example 3

[0175] Please see Figure 3 , Figure 3 This is another emergency traffic evacuation route planning system disclosed in the embodiments of the present invention. Figure 3 The described emergency traffic evacuation route planning system is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server).

[0176] like Figure 3 As shown, the emergency traffic evacuation route planning system may include:

[0177] Memory 301 storing executable program code;

[0178] Processor 302 coupled to memory 301;

[0179] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the emergency traffic evacuation route planning method described in Embodiment 1.

[0180] Example 4

[0181] This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the emergency traffic evacuation route planning method described in Embodiment 1.

[0182] Example 5

[0183] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the emergency traffic evacuation route planning method described in Embodiment 1.

[0184] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0185] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0186] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0187] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0189] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0190] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0191] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0192] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory. Memory is an example of computer-readable media.

[0193] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transient computer-readable media, such as modulated data signals and carrier waves.

[0194] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0195] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0196] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0197] Finally, it should be noted that the emergency traffic evacuation route planning method and system disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for planning an emergency traffic evacuation path, characterized in that: The method comprises: Obtain multiple sound information of emergency area; Analyze the voice text and voice type corresponding to each of the voice information according to the voice analysis algorithm; Determining vehicle danger probabilities corresponding to a plurality of sub-areas of the emergency area according to the sound text and the sound type corresponding to each of the sound information; An evacuation path corresponding to the emergency area is calculated according to the vehicle danger probabilities corresponding to the multiple sub-areas.

2. The method for emergency traffic evacuation route planning according to claim 1, characterized in that: The step of analyzing the voice text and voice type corresponding to each voice information according to the voice analysis algorithm includes: Processing the plurality of sound information based on a denoising synthesis algorithm to obtain regional sound information corresponding to each sub-region of the emergency area; Each of the regional sound information is input into a sound processing algorithm model to obtain a sound text and a sound type corresponding to each of the regional sound information.

3. The method for emergency traffic evacuation route planning according to claim 2, characterized in that: The processing of the plurality of sound information based on the denoising synthesis algorithm to obtain regional sound information corresponding to each sub-region of the emergency area includes: For each sub-region of the emergency area, all the sound information whose positioning information belongs to the sub-region among the plurality of sound information are determined as the regional sound material corresponding to the sub-region; Performing denoising processing on all the regional sound materials of the sub-region by using a wavelet transform algorithm to obtain a plurality of denoised sound materials of the sub-region; Calculating the sound similarity between any two sound data of the same time period in the denoised sound materials; For any time period, mixing and synthesizing the sound data of at least two noise sound materials whose sound similarity in the time period is greater than a first similarity threshold, to obtain a synthesized sound material corresponding to the time period; The synthesized sound materials corresponding to all the time periods are combined to obtain the regional sound information corresponding to the sub-region.

4. The method for planning an emergency traffic evacuation path according to claim 2, characterized in that: The step of inputting each of the regional sound information into a sound processing algorithm model to obtain a sound text and a sound type corresponding to each of the regional sound information includes: For each of the regional sound information, based on the classifier model, determining a dialogue sound portion and a non-dialogue sound portion in the regional sound information; Determining the voice text corresponding to the voice part of the conversation based on the voice-to-text recognition algorithm model; Based on the template matching algorithm, the sound type corresponding to the non-dialogue sound portion is determined.

5. The method for planning an emergency traffic evacuation path according to claim 4, characterized in that: The step of determining the conversation sound part and the non-conversation sound part in the sound information of the region based on the classifier model includes: Each part of the regional sound information is input into a trained sound classifier neural network model to determine whether each part of the regional sound information is a dialogue sound part or a non-dialogue sound part; the sound classifier neural network model is trained by a training data set including a plurality of training sound information and corresponding sound type labels; the sound type label is a dialogue label or a non-dialogue label.

6. The method for planning an emergency traffic evacuation path according to claim 4, characterized in that: The determining the sound type corresponding to the non-dialogue sound portion based on the template matching algorithm includes: Calculating the template similarity between each preset emergency event sound template and the non-dialogue sound portion; The template sound type corresponding to the emergency sound template with the highest template similarity is determined as the sound type corresponding to the non-dialogue sound part; the sound type includes at least one of groaning, vehicle collision, glass breaking, shouting and explosion.

7. The method for planning an emergency traffic evacuation path according to claim 2, characterized in that: The determining, according to the sound text and the sound type corresponding to each of the sound information, the vehicle danger probabilities corresponding to the plurality of sub-areas of the emergency area includes: For each sub-region, determining a text set of sound texts corresponding to all the regional sound information corresponding to the sub-region; Determine a type set of sound types corresponding to all the regional sound information corresponding to the sub-region; Calculating a text risk score corresponding to the text set based on a preset keyword scoring rule; Based on a preset type-score correspondence, calculating a type risk score corresponding to the type set; The weighted average of the text risk score and the type risk score is calculated to obtain the vehicle risk probability corresponding to the sub-area.

8. The method for planning an emergency traffic evacuation route according to claim 1, characterized in that: The calculating, according to the vehicle danger probabilities corresponding to the plurality of sub-areas, an evacuation path corresponding to the emergency area comprises: The objective function is set to include the shortest length of the evacuation route and the minimum average curvature of the evacuation route; The setting restriction conditions include that the vertical distance between the evacuation route and the regional center house of each sub-area is greater than a preset distance threshold and the vertical distance is proportional to the vehicle danger probability of the corresponding sub-area; According to the objective function and the restriction conditions, the route calculation of the emergency area is repeatedly iterated based on the spatial search algorithm and the dynamic programming algorithm until the optimal evacuation route is obtained, which is determined as the evacuation path corresponding to the emergency area.

9. An emergency traffic evacuation route planning system, characterized in that: The system comprises: An acquisition module, used for acquiring multiple sound information of an emergency area; An analysis module, used for analyzing the voice text and voice type corresponding to each of the voice information according to a voice analysis algorithm; A determination module, configured to determine the vehicle danger probability corresponding to the plurality of sub-areas of the emergency area according to the sound text and the sound type corresponding to each of the sound information; The calculation module is used to calculate the evacuation path corresponding to the emergency area according to the vehicle danger probabilities corresponding to the multiple sub-areas.

10. An emergency traffic evacuation route planning system, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the emergency traffic evacuation path planning method as described in any one of claims 1-8.

Images