Sound-based guidance evacuation method and system for building corridors

Abstract

The application is suitable for the technical field of personal safety guarantee, and provides a sound guiding evacuation method and system based on building corridors, which comprises the following steps: firstly, in response to a pre-warning signal, real-time personnel position information of target personnel and safety exit position information of a target safety exit are quickly acquired; then, according to the real-time personnel position information and the safety exit position information, a plurality of target loudspeakers are effectively determined; finally, based on the plurality of target loudspeakers, sound guiding instructions are accurately generated and executed. The application can realize effective escape of target personnel by using sound guidance, establish a continuous sound path with real-time direction for trapped personnel, avoid the functional blind area of the traditional visual guiding mode in the visibility zero or crowd congestion scene, significantly improve the success rate and reliability of personnel evacuation in extreme environment, and greatly improve the safety.

Description

Technical Field

[0001] This application relates to the technical field of personal safety protection, and more specifically, to a sound-guided evacuation method and system based on building corridors. Background Technology

[0002] In the event of an emergency in a building (such as a violent shaking caused by a natural disaster or a fire caused by a gas leak), orderly guiding people to evacuate safely is crucial to avoiding panic and even stampedes. It can maximize the chances of completing the evacuation of all personnel in the shortest possible time, thereby ensuring the safety of every individual.

[0003] Currently, the most common way to guide people is to stick evacuation signs on the wall. However, in an emergency, the evacuation signs may be damaged or disappear due to the wall falling or collapsing, or they may be blocked due to the density of people, making it impossible for some people to get the evacuation direction in time. This poses a safety problem and needs to be further improved. Summary of the Invention

[0004] Based on this, embodiments of this application provide a sound-guided evacuation method and system based on building corridors to solve the problem of low safety in the prior art.

[0005] In a first aspect, embodiments of this application provide a sound-guided evacuation method based on a building corridor, applicable to building corridors, wherein multiple candidate loudspeakers are pre-installed in the building corridor, and the method includes:

[0006] In response to the warning signal, obtain the real-time location information of the target personnel and the location information of the target safety exit; Based on the real-time personnel location information and safety exit location information, multiple target loudspeakers are identified; Based on the multiple target speakers, sound guidance instructions are generated and executed.

[0007] Compared with the prior art, the beneficial effects are as follows: The sound-guided evacuation method based on building corridors provided in this application embodiment allows the terminal device to respond to the warning signal first, quickly obtain the real-time personnel location information of the target personnel and the safety exit location information of the target safety exit, and then effectively determine multiple target loudspeakers based on the real-time personnel location information and safety exit location information. Finally, based on the multiple target loudspeakers, sound guidance instructions are accurately generated and executed, thereby realizing the effective escape of target personnel by using sound, which to a certain extent solves the problem of low safety at present.

[0008] Secondly, embodiments of this application provide a sound-guided evacuation system based on a building corridor, applicable to building corridors, wherein multiple selectable loudspeakers are pre-installed in the building corridor, and the system includes: Real-time personnel location information acquisition module: In response to the warning signal, it acquires the real-time personnel location information of the target personnel and the safety exit location information of the target safety exit; Target loudspeaker determination module: used to determine multiple target loudspeakers based on the real-time personnel location information and safety exit location information; Sound guidance instruction generation module: used to generate and execute sound guidance instructions based on multiple target speakers.

[0009] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0010] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0011] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0013] Figure 1 This is a schematic flowchart of a sound-guided evacuation method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating step S100 in a sound-guided evacuation method provided in an embodiment of this application; Figure 3 This is a flowchart illustrating step S200 in a sound-guided evacuation method provided in an embodiment of this application; Figure 4 This is a flowchart illustrating the process after step S291 in a sound-guided evacuation method provided in an embodiment of this application. Figure 5 This is a flowchart illustrating step S300 in a sound-guided evacuation method provided in an embodiment of this application; Figure 6 This is a flowchart illustrating the process before step S300 in a sound-guided evacuation method provided in an embodiment of this application; Figure 7 This is a schematic diagram of a building corridor provided in one embodiment of this application; Figure 8 This is a block diagram of a sound-guided evacuation system provided in one embodiment of this application; Figure 9 This is a schematic diagram of a terminal device provided in an embodiment of this application. Detailed Implementation

[0014] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0015] In the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0016] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0017] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0018] Please see Figure 1 , Figure 1 This is a flowchart illustrating a sound-guided evacuation method based on a building corridor, as provided in this embodiment. In this embodiment, the executing entity of the sound-guided evacuation method is a terminal device. It is understood that the types of terminal devices include, but are not limited to, mobile phones, tablets, laptops, Ultra-Mobile Personal Computers (UMPCs), netbooks, Personal Digital Assistants (PDAs), etc. This embodiment does not impose any restrictions on the specific type of terminal device.

[0019] Please see Figure 1 The sound-guided evacuation method provided in this application includes, but is not limited to, the following steps: In S100, in response to the warning signal, the real-time location information of the target personnel and the location information of the target safety exit are obtained.

[0020] Without loss of generality, the sound-guided evacuation method of this application can be applied to building corridors, wherein multiple candidate speakers can be pre-installed in the building corridors, the candidate speakers being used to describe the speakers to be controlled, and the multiple candidate speakers are located in different positions with a specified spacing between them.

[0021] Specifically, the terminal device can first respond to the warning signal to obtain the real-time location information of the target personnel and the location information of the target safety exit. The warning signal can be triggered based on an emergency. The target personnel is used to describe the personnel who are still in the building corridor in the event of an emergency. The real-time personnel location information is used to describe the real-time location of the target personnel. The target safety exit is used to describe the safety exit of the building. The safety exit location information is used to describe the specific location of the safety exit of the building.

[0022] In some possible implementations, to obtain real-time personnel location information and safety exit location information, please refer to [link / reference]. Figure 2 Step S100 includes, but is not limited to, the following steps: In S110, in response to the warning signal, the location information of the target safety exit is obtained, and real-time corridor image information is obtained based on the preset monitoring camera.

[0023] Specifically, the terminal device can respond to the warning signal and obtain the location information of the target safety exit. At the same time, the terminal device can obtain real-time corridor image information based on the preset monitoring camera with depth perception capability. The safety exit location information can be stored in a specified database in advance; the monitoring camera can be installed in the building corridor in advance; the real-time corridor image information is used to describe the images obtained by using the monitoring camera to capture images of the building corridor.

[0024] In S120, based on a preset target detection algorithm, feature identification information and personnel category information of target personnel are determined according to real-time corridor image information.

[0025] Specifically, after the terminal device acquires real-time corridor image information, it can perform target detection processing on the real-time corridor image information based on a preset target detection algorithm to effectively determine the personnel category information of the target personnel, and effectively determine the feature identification information based on the text labels on the wall. The feature identification information is used to describe specific text labels in the real-time corridor image information, such as "301" representing room 301 on the third floor or "407" representing room 407 on the fourth floor. The target detection algorithm can be a target detection algorithm based on YOLO v11 or a target detection algorithm based on Mask R-CNN. The personnel category information is used to describe the category of the personnel.

[0026] In S130, based on feature identification information, a preset identification association database is searched to determine the real-time personnel location information.

[0027] Specifically, after the terminal device determines the feature identification information and personnel category information, it can quickly determine the real-time personnel location information by searching a pre-set identifier association database based on the feature identification information. This allows for the effective determination of the target personnel's specific location through specific identifiers in the surrounding environment. The identifier association database pre-stores multiple candidate identifier information and their corresponding associated location information. The multiple candidate identifier information can be "201", "202", ..., "406" and "407". Specifically, the candidate identifier information "201" corresponds to... The associated location information is the specific location of "Room 201 on the second floor" in the building corridor. Specifically, the associated location information corresponding to the candidate identifier information "202" is the specific location of "Room 202 on the second floor" in the building corridor. Specifically, the associated location information corresponding to the candidate identifier information "406" is the specific location of "Room 406 on the fourth floor" in the building corridor. Specifically, the associated location information corresponding to the candidate identifier information "407" is the specific location of "Room 407 on the fourth floor" in the building corridor. The real-time personnel location information is used to describe the associated location information corresponding to the candidate identifier information that is the same as the feature identifier information.

[0028] In S200, multiple target loudspeakers are identified based on real-time personnel location information and safety exit location information.

[0029] Specifically, after the terminal device obtains real-time personnel location information and safety exit location information, it can effectively identify multiple target loudspeakers based on the real-time personnel location information and safety exit location information.

[0030] In some possible implementations, for effectively identifying multiple target loudspeakers, please refer to [link / reference needed]. Figure 3 Step S200 includes, but is not limited to, the following steps: In S210, based on the preset building spatial layout information, and according to the real-time personnel location information and safety exit location information, the available route information is determined.

[0031] Specifically, after the terminal device determines the real-time personnel location information, the terminal device can determine the optional route information based on the preset building spatial layout information, the real-time personnel location information, and the safety exit location information. The building spatial layout information can be the internal floor plan of the building; the optional route information is used to describe the route from the real-time personnel location information to the safety exit location information.

[0032] In S220, it is determined whether the number of optional route information is equal to one.

[0033] Specifically, after the terminal device determines the available route information, it can determine whether the number of available route information is equal to one.

[0034] In S230, if the number of optional route information is equal to one, then the optional route information is determined to be the target route information.

[0035] Specifically, if the number of available route information is equal to one, the terminal device can determine that the available route information is the target route information.

[0036] In S240, if the number of optional route information is greater than one, then for each optional route information: based on the real-time corridor image information, determine the obstacle category information and the obstacle width information corresponding to the obstacle category information.

[0037] For example, if the number of optional route information is greater than one, the terminal device can perform the following processing for each optional route information: Based on the real-time corridor image information, using the aforementioned target detection algorithm, target detection processing is performed on the real-time corridor image information to determine obstacle category information, and further, the obstacle width information corresponding to the obstacle category information is determined. The obstacle category information describes the category of the obstacle, such as "brick," "wooden board," or "door panel"; the obstacle width information describes the size of the obstacle in the sectional direction perpendicular to the extension direction of the building corridor. It should be noted that existing techniques can be used to calculate the size of objects using the 3D data output by the depth camera, and therefore will not be elaborated upon.

[0038] In S250, obtain the corridor width information of the building corridor.

[0039] Specifically, after the terminal device determines the obstacle category information and obstacle width information, the terminal device can obtain the corridor width information of the building corridor. The corridor width information is used to describe the width value of the building corridor, that is, the size of the building corridor in the tangential direction perpendicular to the extension direction of the building corridor. The corridor width information can be a preset value.

[0040] In S260, obstacle percentage information is generated based on obstacle width information and corridor width information.

[0041] Specifically, after the terminal device obtains the corridor width information, it can generate obstacle ratio information based on the obstacle width information and the corridor width information. The obstacle ratio information describes the quotient obtained by dividing the obstacle width information by the corridor width information.

[0042] In S270, the obstacle percentage information is compared with the preset obstacle threshold information.

[0043] Specifically, after the terminal device generates the obstacle ratio information, the terminal device can compare the obstacle ratio information with the preset obstacle threshold information, where the obstacle threshold information can be a preset value, such as 0.6 or 0.8.

[0044] In S280, if the obstacle percentage information is greater than or equal to the preset obstacle threshold information, then high collapse probability information is generated.

[0045] Specifically, if the obstacle percentage information is greater than or equal to the preset obstacle threshold information, it indicates that there are already many obstacles in the optional route information that have fallen due to an emergency. Therefore, the terminal device can generate high collapse probability information, which is used to indicate that the optional route information has a high probability of collapse.

[0046] In S290, based on the high collapse probability information, the optional route information corresponding to the high collapse probability information is eliminated.

[0047] Specifically, after the terminal device generates high collapse probability information, it can eliminate the optional route information corresponding to the high collapse probability information, thereby helping to ensure the personal safety of the target personnel.

[0048] In S291, if the obstacle percentage information is less than the preset obstacle threshold information, low collapse probability information is generated.

[0049] Specifically, if the obstacle percentage information is less than the preset obstacle threshold information, it indicates that there are not many obstacles that have fallen due to emergency situations in the optional route information, so the terminal device can generate low collapse probability information.

[0050] In S292, based on the low collapse probability information, the optional route information corresponding to the low collapse probability information is determined as the target route information.

[0051] Specifically, after the terminal device generates low collapse probability information, it can determine the optional route information corresponding to the low collapse probability information as the target route information based on the low collapse probability information.

[0052] In S293, the candidate loudspeaker in the target route information is determined as the target loudspeaker.

[0053] Specifically, after the terminal device determines the target route information, the terminal device can identify all the candidate speakers within the target route information as the target speaker.

[0054] In some possible implementation methods, to further ensure the personal safety of the target personnel, please refer to [link / reference needed]. Figure 4 After step S291, the method further includes, but is not limited to, the following steps: In S2911, it is determined whether the number of target route information is greater than one.

[0055] Specifically, after the terminal device generates low collapse probability information, the terminal device can determine whether the number of target route information is greater than one.

[0056] In S2912, if the number of target route information is greater than one, the target route information corresponding to the smallest obstacle percentage information is determined as the final selected target route information.

[0057] Specifically, if the number of target route information is greater than one, the terminal device can determine the target route information corresponding to the smallest obstacle percentage information as the final selected target route information.

[0058] In the S300, sound guidance instructions are generated and executed based on multiple target speakers.

[0059] Specifically, after the terminal device identifies multiple target speakers, it can accurately generate and execute sound guidance commands based on these speakers, thereby enabling the effective escape of target personnel using sound and significantly improving safety.

[0060] For improved security in some possible implementations, please refer to [link / reference]. Figure 5 Step S300 includes, but is not limited to, the following steps: In S310, multiple target loudspeakers are sorted in order from the location information closest to the real-time personnel to the location information closest to the safety exit, and start-up sequence information is generated.

[0061] Specifically, after the terminal device identifies multiple target speakers, it can sort the multiple target speakers in order from the location information closest to the real-time personnel to the location information closest to the safety exit, and generate start sequence information. The start sequence information is used to describe the multiple target speakers after sorting.

[0062] In S320, a sound guidance command is generated and executed based on the start sequence information, the preset sound interval information, and the preset sound intensity difference information.

[0063] Specifically, after the terminal device generates the activation sequence information, it can effectively generate and execute sound guidance instructions based on the activation sequence information, preset sound interval information, and preset sound intensity difference information. This enables the construction of a continuous, dynamic, and directional escape path through sound, significantly improving the accuracy and efficiency of personnel evacuation in complex building structures. The sound guidance instructions are used to instruct multiple target speakers to be activated sequentially, with the activation sequence information as the sound sequence, the sound interval information as the sound interval between two adjacent target speakers, and the sound intensity difference information as the sound intensity difference between two adjacent target speakers.

[0064] For further security enhancements in some possible implementations, please refer to [link / reference]. Figure 6 Before step S300, the method further includes, but is not limited to, the following steps: In S301, based on a preset sound sensor, ambient audio information of the target route is continuously acquired according to a preset sampling time period.

[0065] Specifically, the terminal device can continuously acquire environmental audio information of the target route based on a preset sound sensor and a preset sampling time period. The sound sensor can be pre-installed in the corridor of the building. The specific duration of the sampling time period can be customized, such as two minutes. The environmental audio information is used to describe the environmental audio during the sampling time period. The environmental audio information includes multiple sampling time information and the environmental sound intensity information corresponding to each sampling time information.

[0066] In S302, the maximum sound intensity information and the minimum sound intensity information are determined based on the ambient audio information.

[0067] Specifically, after the terminal device acquires the ambient audio information, it can determine the maximum sound intensity information and the minimum sound intensity information based on the ambient audio information. The maximum sound intensity information describes the maximum ambient sound intensity information, and the minimum sound intensity information describes the minimum ambient sound intensity information. The sampling time of the minimum sound intensity information is after the sampling time of the maximum sound intensity information.

[0068] In S303, waiting interval information is generated based on the sampling time information corresponding to the maximum sound intensity information and the sampling time information corresponding to the minimum sound intensity information.

[0069] Specifically, after the terminal device determines the maximum sound intensity information and the minimum sound intensity information, the terminal device can generate waiting interval information based on the sampling time information corresponding to the maximum sound intensity information and the sampling time information corresponding to the minimum sound intensity information, thereby enabling timely knowledge of the pattern of environmental noise. The waiting interval information is used to describe the time interval between the sampling time information corresponding to the maximum sound intensity information and the sampling time information corresponding to the minimum sound intensity information.

[0070] In S304, the sounding interval information is determined based on the waiting interval information.

[0071] Specifically, after the terminal device generates the waiting interval information, the terminal device can effectively determine the sound emission interval information based on the waiting interval information. This is beneficial for making the sound emission time of the target loudspeaker staggered from the moment of maximum environmental noise. This is applicable to scenarios where electrical wires are disconnected in a building corridor due to an emergency, and the current generates arcs or sparks through the air gap at the break point, resulting in intermittent noise.

[0072] In one possible implementation, please refer to Figure 7 To further verify the feasibility of sound guidance, the inventors modeled and experimented with a building corridor. The model was a closed, narrow space 20 meters long and 3.5 meters wide, perfectly simulating the environment of an everyday corridor. Two ordinary ceiling-mounted speakers, designated L1 and L2, were installed at each end of the space, spaced 18 meters apart with a 1-meter buffer at each end. The height of the space was 2.8 meters, the same as a typical indoor ceiling height, to closely resemble real-world usage. Test points were evenly spaced along a straight line down the center of the space, with five test locations distributed throughout. Figure 7 Positions P1 to P5 in the diagram are spaced 4.5 meters apart, covering the key areas of the entire corridor. Simultaneously, subsequent "reverberation" experiments were conducted by attaching foam mattresses to the walls, testing how quickly the reflected echoes disappeared after sound was emitted. Specifically, attaching 24 mattresses represented "short reverberation," attaching 12 mattresses represented "medium reverberation," and no mattresses represented "long reverberation." The final test results are shown in Table 1 below. Table 1 shows the reverberation time under the three different mattress arrangements. Because the narrow corridor is a symmetrical space, the reverberation times at points P1 and P5, and P2 and P4, are consistent.

[0073] Table 1 Reverberation Test Results

[0074] Specifically, in the inventor's experiment on the corridor of a building, the effect of reverberation time on the judgment of direction is shown in Table 2 below. As can be seen from Table 2, the shorter the reverberation time, the more accurate the tester's judgment of direction. The optimal reverberation time is 0.73 seconds to 1.0 seconds. After exceeding 1.0 seconds, the judgment ability will decrease significantly. If the number of speakers at the sound source point on each side is increased to two, the judgment time can be reduced by about 1.0 seconds.

[0075] Table 2 Experimental data for a single horn on each side

[0076] Specifically, in the experiment conducted by the inventors on the corridor of the building, the influence of the sound pressure level difference on the direction positioning perception is shown in Table 3 below. As can be seen from Table 3, the more obvious the difference in sound volume between the two speakers, the more accurate the judgment. If the reverberation is not well controlled (more than 1.0 second), as long as the loudness difference is adjusted to more than 3dB, the basic judgment accuracy can be maintained.

[0077] Table 3. Accuracy table related to sound pressure level difference

[0078] Specifically, in the inventor's experiment on building corridors, the effect of sound delay time on directional positioning perception was obtained, as shown in Table 4 below. As can be seen from Table 4, having one speaker sound before another (for example, with a delay of 30-50 milliseconds) can significantly improve the accuracy and speed of judgment. However, the greater the reverberation, the weaker this "delay advantage" becomes. Under short reverberation conditions, a 30ms delay can achieve 95% accuracy in the direction of the sound source.

[0079] Table 4. Accuracy Table Related to Sound Delay

[0080] In summary, the optimal acoustic conditions in a narrow space (such as a corridor) are: (1) prioritize controlling the reverberation time to 0.73 seconds to 1.0 seconds; (2) if the reverberation cannot be controlled (such as exceeding 1.0 seconds), adjust the loudness difference between the two sound sources to more than 3dB, or make one sound source sound 40-50 milliseconds earlier than the other.

[0081] The implementation principle of the sound-guided evacuation method based on building corridors in this application embodiment is as follows: The terminal device can first respond to the warning signal, quickly obtain the real-time personnel location information and the safety exit location information of the target personnel, and then effectively determine multiple target loudspeakers based on the real-time personnel location information and safety exit location information. Finally, based on the multiple target loudspeakers, it accurately generates and executes sound guidance instructions, thereby realizing the effective escape of target personnel by using sound, avoiding the possibility that some personnel cannot obtain the evacuation direction in time due to the damage of evacuation signs or the obstruction of evacuation signs due to the density of people, thus greatly improving safety.

[0082] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0083] Embodiments of this application also provide a sound-guided evacuation system based on building corridors, suitable for building corridors where multiple selectable loudspeakers are pre-installed. For ease of explanation, only the parts relevant to this application are shown, such as... Figure 8 As shown, the system 80 includes: Real-time personnel location information acquisition module 81: In response to the warning signal, it acquires the real-time personnel location information of the target personnel and the safety exit location information of the target safety exit; Target loudspeaker determination module 82: used to determine multiple target loudspeakers based on real-time personnel location information and safety exit location information; Sound guidance instruction generation module 83: Used to generate and execute sound guidance instructions based on multiple target speakers.

[0084] Optionally, the above-mentioned real-time personnel location information acquisition module 81 includes: Real-time corridor image information acquisition submodule: In response to the warning signal, it acquires the location information of the target safety exit and acquires real-time corridor image information based on the preset monitoring camera, wherein the monitoring camera is pre-installed in the building corridor; Feature identification information determination submodule: Based on a preset target detection algorithm and real-time corridor image information, determine feature identification information and personnel category information of target personnel; The real-time personnel location information determination submodule is used to retrieve real-time personnel location information from a preset identifier association database based on feature identifier information. The identifier association database stores multiple candidate identifier information and the associated location information corresponding to each candidate identifier information. The real-time personnel location information is used to describe the associated location information corresponding to the candidate identifier information that is the same as the feature identifier information.

[0085] Optionally, the target loudspeaker determination module 82 mentioned above includes: Optional route information determination submodule: This module is used to determine optional route information based on preset building spatial layout information, real-time personnel location information, and safety exit location information; Optional route information determination submodule: Used to determine whether the number of optional route information is equal to one; The first submodule for determining target route information is used to determine the target route information if the number of available route information is equal to one. Obstacle Category Information Determination Submodule: If the number of optional route information is greater than one, then for each optional route information, based on real-time corridor image information, determine the obstacle category information and the obstacle width information corresponding to the obstacle category information; Corridor Width Information Acquisition Submodule: Used to acquire corridor width information of building corridors; Obstacle percentage information generation submodule: used to generate obstacle percentage information based on obstacle width information and corridor width information; Obstacle percentage information comparison submodule: used to compare obstacle percentage information with preset obstacle threshold information; High collapse probability information generation submodule: used to generate high collapse probability information if the obstacle ratio information is greater than or equal to the preset obstacle threshold information; Elimination processing submodule: Used to eliminate optional route information corresponding to high collapse probability information based on high collapse probability information; Low collapse probability information generation submodule: used to generate low collapse probability information if the obstacle ratio information is less than the preset obstacle threshold information; The second target route information determination submodule is used to determine the optional route information corresponding to the low collapse probability information as the target route information based on the low collapse probability information. Target Speaker Determination Submodule: Used to determine the candidate speakers in the target route information as the target speakers.

[0086] Optionally, the system 80 also includes: Target route information determination module: Used to determine whether the number of target route information is greater than one; Final Target Route Information Determination Module: If the number of target route information is greater than one, the target route information corresponding to the smallest obstacle percentage information is determined as the final selected target route information.

[0087] Optionally, the aforementioned voice guidance instruction generation module 83 includes: Startup sequence information generation submodule: This module sorts multiple target loudspeakers in order from the location closest to the real-time personnel location to the location closest to the safety exit location, and generates startup sequence information. The sound guidance instruction generation submodule is used to generate and execute sound guidance instructions based on the start sequence information, the preset sound interval information, and the preset sound intensity difference information. The sound guidance instructions are used to instruct multiple target speakers to be started sequentially, with the start sequence information as the sound sequence, the sound interval information as the sound interval between two adjacent target speakers, and the sound intensity difference information as the sound intensity difference between two adjacent target speakers.

[0088] Optionally, the system 80 also includes: Environmental audio information acquisition module: It is used to continuously acquire environmental audio information of the target route based on a preset sound sensor and a preset sampling time period. The environmental audio information includes multiple sampling time information and the environmental sound intensity information corresponding to each sampling time information. Sound intensity information determination module: used to determine the maximum sound intensity information and the minimum sound intensity information based on the ambient audio information. The maximum sound intensity information is used to describe the maximum ambient sound intensity information, and the minimum sound intensity information is used to describe the minimum ambient sound intensity information. The sampling time of the minimum sound intensity information is after the sampling time of the maximum sound intensity information. Waiting interval information generation module: used to generate waiting interval information based on the sampling time information corresponding to the maximum sound intensity information and the sampling time information corresponding to the minimum sound intensity information; Voice interval information determination module: used to determine the voice interval information based on the waiting interval information.

[0089] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0090] This application also provides a terminal device, such as... Figure 9 As shown, the terminal device 90 in this embodiment includes a processor 91, a memory 92, and a computer program 93 stored in the memory 92 and executable on the processor 91. When the processor 91 executes the computer program 93, it implements the steps described in the above-described sound-guided evacuation method embodiment, for example... Figure 1 Steps S100 to S300 are shown; or, when processor 91 executes computer program 93, it implements the functions of each module in the above-described device, for example... Figure 8 The functions of modules 81 to 83 are shown.

[0091] The terminal device 90 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The terminal device 90 includes, but is not limited to, a processor 91 and a memory 92. Those skilled in the art will understand that... Figure 9 This is merely an example of terminal device 90 and does not constitute a limitation on terminal device 90. It may include more or fewer components than shown, or combine certain components, or different components. For example, terminal device 90 may also include input / output devices, network access devices, buses, etc.

[0092] The processor 91 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0093] The memory 92 can be an internal storage unit of the terminal device 90, such as the hard disk or memory of the terminal device 90. The memory 92 can also be an external storage device of the terminal device 90, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device 90. Furthermore, the memory 92 can include both internal storage units and external storage devices of the terminal device 90. The memory 92 can also store computer program 93 and other programs and data required by the terminal device 90. The memory 92 can also be used to temporarily store data that has been output or will be output.

[0094] One embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0095] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the methods, principles and structures of this application should be covered within the scope of protection of this application.

Claims

1. A sound-guided evacuation method based on a building corridor, applicable to building corridors, wherein multiple candidate loudspeakers are pre-installed in the building corridor, characterized in that, The method includes: In response to the warning signal, obtain the real-time location information of the target personnel and the location information of the target safety exit; Based on the real-time personnel location information and safety exit location information, multiple target loudspeakers are identified; Based on the multiple target speakers, sound guidance instructions are generated and executed.

2. The method according to claim 1, characterized in that, The process of responding to an early warning signal by acquiring the real-time location information of the target personnel and the location information of the target safety exit includes: In response to an early warning signal, the system acquires the location information of the target safety exit and, based on a pre-installed surveillance camera, acquires real-time corridor image information, wherein the surveillance camera is pre-installed in the building corridor. Based on a preset target detection algorithm, feature identification information and personnel category information of the target personnel are determined according to the real-time corridor image information; Based on the feature identification information, a preset identifier association database is searched to determine the real-time personnel location information. The identifier association database pre-stores multiple candidate identifier information and the associated location information corresponding to each candidate identifier information. The real-time personnel location information is used to describe the associated location information corresponding to the candidate identifier information that is the same as the feature identification information.

3. The method according to claim 2, characterized in that, The step of determining multiple target loudspeakers based on the real-time personnel location information and safety exit location information includes: Based on the preset building spatial layout information, and according to the real-time personnel location information and safety exit location information, the available route information is determined; Determine whether the number of available route information is equal to one; If the number of optional route information is equal to one, then the optional route information is determined to be the target route information; If the number of optional route information is greater than one, then for each optional route information: based on the real-time corridor image information, determine the obstacle category information and the obstacle width information corresponding to the obstacle category information; Obtain the corridor width information of the building corridor; Based on the obstacle width information and corridor width information, obstacle percentage information is generated; Compare the obstacle percentage information with the preset obstacle threshold information; If the obstacle percentage information is greater than or equal to the preset obstacle threshold information, then high collapse probability information is generated; Based on the high collapse probability information, the optional route information corresponding to the high collapse probability information is eliminated. If the obstacle percentage information is less than the preset obstacle threshold information, then low collapse probability information is generated; Based on the low collapse probability information, the optional route information corresponding to the low collapse probability information is determined as the target route information; The candidate loudspeaker in the target route information is determined as the target loudspeaker.

4. The method according to claim 3, characterized in that, After determining the selectable route information corresponding to the low collapse probability information as the target route information based on the low collapse probability information, the method further includes: Determine whether the number of target route information items is greater than one; If the number of target route information is greater than one, then the target route information corresponding to the smallest obstacle percentage information is determined as the final selected target route information.

5. The method according to claim 3, characterized in that, The step of generating and executing sound guidance instructions based on multiple target speakers includes: The target loudspeakers are sorted in order from the location closest to the real-time personnel location information to the location closest to the safety exit location information to generate activation sequence information. Based on the activation sequence information, the preset sound interval information, and the preset sound intensity difference information, a sound guidance instruction is generated and executed. The sound guidance instruction is used to instruct multiple target speakers to be activated sequentially, with the activation sequence information as the sound sequence, the sound interval information as the sound interval between two adjacent target speakers, and the sound intensity difference information as the sound intensity difference between two adjacent target speakers.

6. The method according to claim 5, characterized in that, Before generating and executing sound guidance instructions based on the plurality of target speakers, the method further includes: Based on a preset sound sensor, the ambient audio information of the target route information is continuously acquired according to a preset sampling time period. The ambient audio information includes multiple sampling time information and ambient sound intensity information corresponding to each sampling time information. Based on the environmental audio information, maximum sound intensity information and minimum sound intensity information are determined, wherein the maximum sound intensity information is used to describe the maximum environmental sound intensity information, the minimum sound intensity information is used to describe the minimum environmental sound intensity information, and the sampling time of the minimum sound intensity information is after the sampling time of the maximum sound intensity information. Based on the sampling time information corresponding to the maximum sound intensity information and the sampling time information corresponding to the minimum sound intensity information, waiting interval information is generated; Based on the waiting interval information, the vocalization interval information is determined.

7. A sound-guided evacuation system based on a building corridor, suitable for building corridors, wherein multiple selectable loudspeakers are pre-installed in the building corridor, characterized in that, The system includes: Real-time personnel location information acquisition module: In response to the warning signal, it acquires the real-time personnel location information of the target personnel and the safety exit location information of the target safety exit; Target loudspeaker determination module: used to determine multiple target loudspeakers based on the real-time personnel location information and safety exit location information; Sound guidance instruction generation module: used to generate and execute sound guidance instructions based on multiple target speakers.

8. The system according to claim 7, characterized in that, The real-time personnel location information acquisition module includes: Real-time corridor image information acquisition submodule: In response to the warning signal, it acquires the location information of the target safety exit and acquires real-time corridor image information based on a preset monitoring camera, wherein the monitoring camera is pre-installed in the building corridor; Feature identification information determination submodule: used to determine feature identification information and personnel category information of the target personnel based on the real-time corridor image information and a preset target detection algorithm; The real-time personnel location information determination submodule is used to retrieve real-time personnel location information from a preset identifier association database based on the feature identifier information. The identifier association database stores multiple candidate identifier information and the associated location information corresponding to each candidate identifier information. The real-time personnel location information is used to describe the associated location information corresponding to the candidate identifier information that is the same as the feature identifier information.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images