Elevator Multi-device Volume Control System Based on Passenger Behavior

Abstract

This invention discloses an elevator multi-device volume adjustment system based on passenger behavior, comprising: a signal acquisition module, which acquires all sound signals inside the elevator car and at the landings and outputs digital signals; a voice signal pre-cancellation module, which receives the digital signals output by the signal acquisition module, removes sound signals from known devices inside the elevator car and at the landings, and then outputs the separated sound sources; a voice separation module, which receives the sound sources output by the voice signal pre-cancellation module, separates human voices from ambient sounds, and outputs the processed sound signals; and an intelligent volume adjustment module, which adjusts the volume of voice announcements and multimedia devices inside the car or at the landings, so that the ratio of passenger conversation voices to ambient volume reaches a preset range. This invention can detect and separate passenger conversation voices from numerous sound sources in the car and at the landings, obtaining feedback directly related to passenger conversation behavior. Based on this feedback, the volume adjustment strategy is more accurate and adaptable to different scenarios.

Description

Technical Field

[0001] This invention relates to the field of elevators, and in particular to a multi-device volume control system for elevators based on passenger behavior. Background Technology

[0002] Currently, the volume of voice announcements and multimedia equipment inside elevator cars and at floors is adjusted in two ways: manual and automatic. Manual adjustment results in a fixed volume that cannot be automatically adjusted online, and the fixed offline volume parameters are difficult to adapt to frequently changing and fluctuating ambient volumes. Automatic adjustment is mainly achieved through methods such as setting different volumes for different time periods and intelligent adjustment based on background sound detection.

[0003] However, in noisy elevator cars or landings, multiple different sound sources often exist simultaneously, such as passenger conversations, elevator operating noise, multimedia equipment playback, and sounds from passengers' electronic devices. Existing background noise detection methods fail to differentiate between these various sounds; volume adjustment is simply fixed: increase the volume when the background noise is loud, and decrease it when the background noise is low, resulting in a poor riding experience. For example, when passengers are chatting in the car, the background noise increases. If the volume of voice announcements and multimedia equipment is increased using current methods, passengers will have difficulty hearing each other's conversations.

[0004] The conditions in the car and at the landing are complex and varied. Passengers' voices, multimedia equipment, voice broadcast modules, and electronic devices carried by passengers all generate human voices. These human voices will also create echoes in the enclosed space of the car. If only human voices are used as feedback to adjust the volume without distinguishing between different human voices, the adjustment result will deviate from the passenger's expectations.

[0005] The environments of the elevator car and the landing differ; the elevator car is enclosed, while the landing is relatively open, and the impact of background noise on passenger conversations also differs. Furthermore, passenger behavior is diverse; for example, during normal conversation, passengers may want to raise their voices to ensure they are heard clearly, while on the phone, they may intentionally lower their voices to protect the content of their conversation. Existing volume adjustment methods are ill-suited to these complex situations. Summary of the Invention

[0006] The summary of this invention introduces a series of simplified concepts, all of which are simplifications of existing technologies in the field, and will be further explained in detail in the detailed description section. This summary is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0007] To solve the above-mentioned technical problems, the present invention provides an elevator multi-device volume control system based on passenger behavior, characterized in that it includes:

[0008] The system includes a signal acquisition module for acquiring all sound signals inside the elevator car and at the landings, and outputting digital signals; a voice signal pre-cancellation module for receiving the digital signals output by the signal acquisition module, removing sound signals from known devices inside the elevator car and at the landings, and then outputting the separated sound source; a voice separation module for receiving the sound source output by the voice signal pre-cancellation module, separating human voices from ambient sounds, and outputting the processed sound signal; and an intelligent volume adjustment module for receiving the processed sound signal from the voice separation module and adjusting the volume of voice announcements and multimedia devices inside the elevator car or at the landings according to the sound signal, so that the ratio of passenger conversation to ambient volume reaches a preset range.

[0009] Preferably, the sound of the known device is the sound of a multimedia device or the sound of a floor station voice playback.

[0010] Preferably, the voice signal pre-cancellation module uses an echo cancellation algorithm to remove the voice signal from the known device.

[0011] Preferably, the voice signal pre-cancellation module converts the acquired analog audio signal into a digital signal after sampling, quantization, and encoding. It uses an adaptive filter to identify the parameters of the unknown echo channel, establishes a far-end signal model based on the correlation between the speaker signal and the generated multi-echoes, simulates the echo path, and adjusts it through an adaptive algorithm to make its impulse response approximate the real echo path. Then, the estimated value is subtracted from the signal received by the microphone to achieve echo cancellation.

[0012] Preferably, the speech separation module uses a single-channel speech separation method based on computational auditory scene analysis to separate human voices and environmental sounds.

[0013] Preferably, the speech separation module models the perception mechanism of the human ear on the target sound signal by simulating the computer. First, it separates the human voice from other environmental sounds, then it detects and separates the passenger chat voice from various human voices. After data processing, it outputs the decibel values ​​of the passenger chat voice and other environmental sounds.

[0014] Preferably, the intelligent volume adjustment module is further configured to: set different optimal volume ratio ranges according to the degree of enclosure of the car interior and the floor space; when the volume adjustment is completed, further determine whether the passenger chat is affected by comparing the current value with the historical value of the passenger chat sound, and dynamically adjust the optimal volume ratio range accordingly.

[0015] This invention can eliminate a known sound source from a mixture of multiple sound signals in an audio system, thereby removing known sound signals from multimedia equipment and voice playback in elevator cars and at landings in advance.

[0016] Furthermore, this invention can detect and separate passenger conversation voices from numerous sound sources in the car and at the landing, obtaining feedback quantities directly related to passenger conversation behavior. Based on this feedback, the volume adjustment strategy is more accurate and can adapt to different scenarios.

[0017] This invention can also ensure that the sound environment inside the elevator car and at each landing does not affect passengers' normal conversation by using optimal volume ratio range parameters. Furthermore, by analyzing the changes in passengers' conversational voices before and after the conversation, the volume adjustment values ​​of each device are further optimized, thus avoiding situations where the actual volume adjustment result contradicts the passenger's intention. By comparing the changes in passengers' conversational voices before and after the conversation, the volume is adjusted according to the passenger's true intention, making it more user-friendly. Simultaneously, for elevators equipped with video recognition capabilities, the presence or absence of passengers in the car can be used to determine whether the elevator playback equipment should be turned on, saving energy. Attached Figure Description

[0018] The accompanying drawings are intended to illustrate the general characteristics of the methods, structures, and / or materials used in specific exemplary embodiments of the invention, supplementing the description in the specification. However, the drawings are schematic diagrams not drawn to scale and may not accurately reflect the precise structural or performance characteristics of any of the given embodiments. The drawings should not be construed as limiting or restricting the range of numerical values ​​or properties covered by exemplary embodiments of the invention. The invention will now be described in further detail with reference to the accompanying drawings and specific embodiments:

[0019] Figure 1 This is a block diagram of the elevator multi-device volume control system based on passenger behavior according to the present invention.

[0020] Figure 2 This is a flowchart illustrating the process of the elevator multi-device volume control system based on passenger behavior according to the present invention. Detailed Implementation

[0021] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can fully understand other advantages and technical effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through different specific embodiments, and the details in this specification can also be applied based on different viewpoints, with various modifications or changes made without departing from the overall design concept of the invention. It should be noted that, unless otherwise specified, the following embodiments and features can be combined with each other. The following exemplary embodiments of the present invention can be implemented in many different forms and should not be construed as being limited to the specific embodiments set forth herein. It should be understood that these embodiments are provided to make the disclosure of the present invention thorough and complete, and to fully convey the technical solutions of these exemplary embodiments to those skilled in the art.

[0022] The present invention provides an elevator multi-device volume adjustment system based on passenger behavior, comprising: a signal acquisition module, a voice signal pre-cancellation module, a voice separation module, and an intelligent volume adjustment module.

[0023] The signal acquisition module is used to collect all sound signals inside the elevator car and at each floor and output digital signals.

[0024] The voice signal pre-cancellation module is used to receive the digital signal output by the signal acquisition module, remove the sound signals from the elevator car and known devices in the landing, and then output the separated sound source; in this invention, the sound of the known devices is the sound of multimedia devices or the sound played by the landing voice system.

[0025] The voice signal pre-cancellation module employs an echo cancellation algorithm to remove the sound signal from known devices. The module converts the acquired analog audio signal into a digital signal through sampling, quantization, and encoding. It then uses an adaptive filter to identify the parameters of the unknown echo channel. Based on the correlation between the speaker signal and the generated multi-echo paths, a far-end signal model is established to simulate the echo path. This model is adjusted using an adaptive algorithm to make its impulse response approximate the actual echo path. Finally, the estimated value is subtracted from the signal received by the microphone to achieve echo cancellation.

[0026] This module can eliminate a known sound source from a mixture of multiple sound signals, thus removing known sound signals from multimedia equipment and voice playback in the elevator car and at the landings in advance.

[0027] The speech separation module is used to receive the sound source output by the speech signal pre-cancellation module, then separate human voice and ambient sound and output the processed sound signal.

[0028] In this invention, the speech separation module employs a single-channel speech separation method based on computational auditory scene analysis to separate human voices from environmental sounds. The speech separation module models the human ear's perception mechanism of target sound signals using computer simulation. First, it separates human voices from other environmental sounds, then detects and separates passenger chatter from various human voices. After data processing, it outputs the decibel values ​​of the passenger chatter and other environmental sounds.

[0029] The function of this module is to detect and separate the voices of passengers chatting from numerous sound sources in the car and at the landing, obtain feedback directly related to the passengers' chatting behavior, and formulate a more accurate volume adjustment strategy based on this feedback, which can adapt to different scenarios.

[0030] The intelligent volume adjustment module is used to receive the sound signal processed by the voice separation module and adjust the volume of the voice broadcast and multimedia equipment in the car or at the landing according to the sound signal, so that the ratio of passenger chat voice to ambient volume reaches a preset range.

[0031] Furthermore, the intelligent volume adjustment module can set different optimal volume ratio ranges based on the degree of enclosure of the car interior and the floor space; after adjusting the volume, it further compares the current value of the passenger's conversation with the historical value to determine whether the passenger's conversation is affected, and dynamically adjusts the optimal volume ratio range accordingly.

[0032] First, by using optimal volume ratio parameters, it is ensured that the sound environment inside the elevator car and at each landing will not affect passengers' normal conversation. Based on this, feedback from changes in passengers' talking volume is used to further optimize the volume adjustment values ​​of each device, thus avoiding situations where the actual volume adjustment results contradict the passengers' intentions. By comparing changes in passengers' talking volume before and after, volume adjustments are made according to the passengers' true intentions, making it more user-friendly. Simultaneously, for elevators equipped with video recognition capabilities, the presence or absence of passengers in the car can be used to determine whether the elevator playback devices should be turned on, saving energy.

[0033] like Figures 1-2 As shown, firstly, the signal acquisition module collects ambient sound, processes the collected analog audio signal into a digital signal, and inputs it into the voice signal pre-cancellation module to remove the sound source of the elevator equipment; secondly, the voice separation module separates the passengers' chat voice separately.

[0034] When no passenger conversation is detected, a one-way adjustment strategy is implemented: if the background noise is loud, the volume of the voice announcements and multimedia equipment inside the car or at the landing is increased accordingly. If passenger conversation is detected, the intelligent volume adjustment module calculates the ratio of the passenger conversation volume in decibels to the ambient sound volume in decibels and compares this ratio with a preset optimal volume ratio range. If it is within this range, it means the current announcement volume does not affect passenger conversation, and no adjustment is made; otherwise, intelligent adjustment is implemented, applying different adjustment strategies to different elevator equipment to ensure the actual volume ratio reaches the optimal range. Research shows that the normal speaking volume is 40-60 dB. When the ambient sound exceeds 70 dB, people find it noisy and it interferes with conversation. Based on this data, and taking into account sufficient margin and the degree of space enclosure, the optimal volume ratio range applicable to both inside the car and at the landing is obtained.

[0035] Finally, the system will continue to monitor the current volume of passengers' conversations and compare it with historical values. Based on this, the volume will be adjusted accordingly. For example, if it is found that passengers' conversations have become louder, it means that background noise is still affecting their conversations. In this case, the volume of voice announcements and multimedia equipment in the car and on each floor will be adjusted until the volume of passengers' conversations no longer increases.

[0036] The following description uses specific scenarios as examples:

[0037] Scenario 1: If no real passenger conversation is detected, but the noise level inside the car or on the floor is increased due to passengers' electronic devices or external noise, the volume of the voice broadcast should be increased accordingly to ensure that passengers can hear the announcement clearly. At the same time, the volume of the multimedia devices should be reduced to avoid affecting passengers' access to information from their electronic devices.

[0038] Scenario 2: If passenger chatting is detected, first detect and determine the largest sound interference source affecting passenger chatting in the current car or floor. Determine the largest sound interference source by judging the decibel value of each sound:

[0039] (1) If the largest source of noise interference is the elevator's own equipment, reduce the volume of the multimedia equipment. At the same time, adjust the volume of the floor announcements according to the content: if the content is the arrival information, increase the volume to prevent passengers from missing the information; if it is an advertisement or other content, decrease the volume. Continue until the ratio of passenger conversation volume to ambient volume reaches the optimal range.

[0040] (2) If the largest source of sound interference is other passengers, external environmental noise, etc., and the volume of the elevator’s own equipment is within the preset reasonable range (40-60db), then no adjustment is made.

[0041] Scenario 3: If the current volume ratio is within the optimal range, compare the current value of the passenger's chat voice with the historical value.

[0042] (1) If the current passengers’ conversations become louder, it means that the elevator’s own equipment is playing too loudly. At this time, the optimal volume ratio range will be adjusted to reduce the volume of the equipment.

[0043] (2) If the current passenger's chat volume decreases, it means that the elevator's own equipment volume will not affect the passenger's chat, and no adjustment should be made. If it continues to decrease and falls below the preset value, it means that the passenger is intentionally reducing the chat volume, such as when the passenger is making a phone call or replying to a voice message, and wants to protect the content of the conversation. In this case, the elevator equipment's announcement volume should be increased appropriately.

[0044] Scenario 4: For elevators equipped with video recognition, if no passenger conversation is detected again after a period of time, the camera on the top of the car will determine whether there are passengers in the car. If there are passengers, the volume of the elevator equipment will be restored to its initial state. If there are no passengers, the multimedia equipment in the car will be turned off to save energy. The multimedia equipment will be turned on again when the elevator doors open next time and the camera determines that a passenger has entered.

[0045] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It will also be understood that, unless expressly defined herein, terms such as those defined in a general dictionary shall be interpreted as having the meaning consistent with their meaning in the relevant field context, and not as having an idealized or overly formal meaning.

[0046] The present invention has been described in detail above through specific embodiments and examples, but these are not intended to limit the invention. Many modifications and improvements can be made by those skilled in the art without departing from the principles of the invention, and these should also be considered within the scope of protection of the present invention.

Claims

1. A multi-device volume control system for elevators based on passenger behavior, characterized in that, include: The signal acquisition module is used to collect all sound signals inside the elevator car and at the landings and output digital signals. The voice signal pre-cancellation module is used to receive the digital signal output by the signal acquisition module, remove the sound signals from the elevator car and known equipment at the landing, and then output the separated sound source. The speech separation module is used to receive the sound source output by the speech signal pre-cancellation module, then separate human voice and ambient sound and output the processed sound signal; The intelligent volume adjustment module is used to receive the sound signal processed by the voice separation module and adjust the volume of the voice broadcast and multimedia equipment in the car or at the floor according to the sound signal, so that the ratio of passenger chat voice to ambient volume reaches a preset range. The intelligent volume adjustment module is also used to: set different optimal volume ratio ranges according to the degree of enclosure of the car interior and the floor space; when the volume adjustment is completed, further determine whether the passenger's conversation is affected by comparing the current value with the historical value, and dynamically adjust the optimal volume ratio range accordingly.

2. The elevator multi-device volume control system based on passenger behavior as described in claim 1, characterized in that, The sound from the known device is the sound played by a multimedia device or a station voice system.

3. The elevator multi-device volume control system based on passenger behavior as described in claim 1, characterized in that, The voice signal pre-cancellation module uses an echo cancellation algorithm to remove the voice signal from known devices.

4. The elevator multi-device volume control system based on passenger behavior as described in claim 3, characterized in that, The voice signal pre-cancellation module converts the acquired analog audio signal into a digital signal after sampling, quantization, and encoding. It uses an adaptive filter to identify the parameters of the unknown echo channel, establishes a far-end signal model based on the correlation between the speaker signal and the generated multi-echo, simulates the echo path, and adjusts it through an adaptive algorithm to make its impulse response approximate the real echo path. Then, it subtracts the estimated value from the signal received by the microphone to achieve echo cancellation.

5. The elevator multi-device volume control system based on passenger behavior as described in claim 1, characterized in that, The speech separation module uses a single-channel speech separation method based on computational auditory scene analysis to separate human voices from environmental sounds.

6. The elevator multi-device volume control system based on passenger behavior as described in claim 5, characterized in that, The speech separation module models the human ear's perception mechanism of target sound signals by simulating the computer. First, it separates human voices from other environmental sounds, and then detects and separates passenger chat voices from various human voices. After data processing, it outputs the decibel values ​​of passenger chat voices and other environmental sounds.

7. The elevator multi-device volume control system based on passenger behavior as described in claim 1, characterized in that, When the elevator multi-device volume adjustment system based on passenger behavior does not detect real passenger conversations, but rather the ambient sound inside the car or at the landing is increased due to electronic devices carried by passengers or external noise, the intelligent volume adjustment module increases the voice playback volume and simultaneously decreases the multimedia device volume.

8. The elevator multi-device volume control system based on passenger behavior as described in claim 1, characterized in that, When the elevator multi-device volume adjustment system based on passenger behavior detects passengers chatting, if the largest source of sound interference comes from the elevator's own equipment, the intelligent volume adjustment module reduces the playback volume of the multimedia device. At the same time, adjust the volume of the voice broadcast at each floor according to the content of the voice broadcast. If the content being played is arrival information for a floor, the intelligent volume adjustment module increases the volume to prevent passengers from missing the arrival information; if it is other content, the intelligent volume adjustment module decreases the volume until the ratio of the passenger's conversation volume to the ambient volume reaches the optimal range.

9. The elevator multi-device volume control system based on passenger behavior as described in claim 1, characterized in that, When the elevator multi-device volume adjustment system based on passenger behavior detects passengers chatting, if the largest source of sound interference comes from other passengers or external environmental noise, and the volume of the elevator's own devices is within a preset range, the intelligent volume adjustment module will not make any adjustments.

10. The elevator multi-device volume control system based on passenger behavior as described in claim 9, characterized in that, The preset range is 40-60dB.

11. The elevator multi-device volume control system based on passenger behavior as described in claim 1, characterized in that, When the elevator multi-device volume adjustment system based on passenger behavior detects that the current volume ratio is within the optimal range, it compares the current value of the passenger's conversation with the historical value.

12. The elevator multi-device volume control system based on passenger behavior as described in claim 11, characterized in that, If the current passengers' conversation becomes louder, the intelligent volume adjustment module will reduce the device's playback volume.

13. The elevator multi-device volume control system based on passenger behavior as described in claim 11, characterized in that, If the current passenger's chat volume decreases below a preset value, the intelligent volume adjustment module will increase the device's playback volume.

14. The elevator multi-device volume control system based on passenger behavior as described in claim 1, characterized in that, When the elevator is equipped with video recognition, if the elevator multi-device volume adjustment system based on passenger behavior does not detect passengers chatting again within a preset time, the elevator uses a camera on the top of the car to determine whether there are passengers in the car. If there are passengers, the intelligent volume adjustment module restores the elevator equipment playback volume to its initial state; if there are no passengers, the intelligent volume adjustment module turns off the multimedia equipment playback in the car.

Images