Elevator sound control method and system

Abstract

The method comprises the following steps that firstly, an elevator is activated, specifically, personnel face information is collected through an image collecting module arranged outside the elevator, the personnel face information is compared with database information, and the elevator is called to arrive; step 2, authority binding: a voice acquisition module acquires a voiceprint and a voice instruction of a person, compares the voiceprint with database information to obtain an elevator control right, and outputs an elevator control instruction; step 3, instruction confirmation and permission cancelling: after instruction issuing is completed, personnel are prompted to confirm through voice, single permission is ended if no voice is input within three seconds after confirmation, and instruction confusion caused by personnel communication is avoided; conflict resolution is carried out on multiple personnel instructions, elevator control instructions are output, and if the instructions need to be changed, permission binding is obtained through personnel output activation instructions. The invention relates to the technical field of elevator equipment, and particularly provides an elevator sound control method and system.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator equipment, and in particular to a voice-controlled elevator method and system. Background Art

[0002] Voice-controlled elevators replace physical buttons with voice commands, reducing the risk of contact transmission of viruses and bacteria. They also offer hands-free operation for those with limited mobility, such as the elderly, the disabled, children, or those carrying heavy objects. This form of operation enables contactless operation, improves public health and safety, enhances the barrier-free user experience, promotes intelligent elevator audits, reduces wear and tear on physical buttons, and reduces maintenance costs.

[0003] However, existing voice-controlled elevators have the problem of multiple command conflicts. When multiple people call at the same time, the response logic is chaotic. Traditional solutions rely on a single voice recognition chip + a fixed command library, which cannot meet the needs of complex scenarios. In addition, the authority control is weak and the usage permissions cannot be dynamically bound. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that multiple people calling at the same time causes confusion in the voice-controlled elevator response, and at the same time, it is impossible to dynamically bind the usage authority.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: This solution provides a voice-controlled elevator method, comprising the following steps:

[0006] Step 1: Elevator activation: The image acquisition module installed outside the elevator collects the facial information of the person, compares the facial information with the database information, and calls the elevator to arrive;

[0007] Step 2: Permission binding: The voice collection module collects the personnel's voiceprint and voice commands, compares the voiceprint with the database information, obtains the elevator control right, and outputs the elevator control command;

[0008] Step 3: Command confirmation and permission cancellation: After the command is issued, the person in charge will be prompted to confirm. If there is no voice input within three seconds after confirmation, the single permission will be terminated to avoid confusion caused by personnel communication; multiple personnel commands will be resolved for conflict and the elevator control command will be output. If the command needs to be changed, the person in charge will input the "activation command" to obtain permission binding;

[0009] Step 4: Elevator sleep: After reaching the floor, the elevator shuts down and goes into sleep.

[0010] Preferred technical solution 1: The method of obtaining permissions also includes dynamically binding permissions through the mobile NFC module. The dynamic binding step includes: the user's mobile terminal NFC module sends the identity code to the elevator control system and compares it with the database information to obtain dynamic permissions.

[0011] Preferred technical solution 2: The conflict resolution includes priority sorting: emergency medical instructions > fire instructions > high-authority user instructions > ordinary elevator instructions.

[0012] The present invention proposes a voice-controlled elevator system for implementing the above method, comprising: an image acquisition module, a voice acquisition module, a dynamic binding module, an elevator control system, an offline-cloud verification module, and an execution unit;

[0013] The image acquisition module uses a wide-angle infrared camera to assist in sound source localization: it verifies the direction of the sound source through face orientation and lip movement detection, and detects scenes such as falls and fires to trigger priority responses;

[0014] The voice acquisition module includes two groups of MEMS microphones spaced apart at the front and rear of the car top, covering the core frequency band of human voice, suppressing mechanical low-frequency noise, and digitizing voice signals. It cooperates with the image acquisition module to achieve dynamic binding and obtain elevator usage rights.

[0015] Furthermore, the dynamic binding module includes an NFC reading and writing module and a voiceprint feature extraction unit. The voiceprint feature extraction unit receives the pure audio of the voice module to generate a voiceprint feature vector. The NFC reading and writing module receives the user's NFC tag and outputs the authority level to the elevator control system.

[0016] Furthermore, the offline-cloud verification module includes an FPGA local database and a cloud blockchain verification platform. FPGA offline verification and sensitive operations such as "disable elevator" trigger cloud voiceprint secondary verification + blockchain evidence storage.

[0017] Furthermore, when the voiceprint / face matching confidence level is lower than the threshold, NFC or password-assisted verification is forcibly triggered, and the abnormal event is recorded in the blockchain evidence module to prevent identity fraud.

[0018] Furthermore, the voice acquisition module integrates an LMS adaptive filter to dynamically adjust the noise reduction parameters according to the mechanical noise spectrum in the car (such as motor frequency) to ensure that the signal-to-noise ratio of voiceprint feature extraction is ≥20dB.

[0019] The present invention proposes a method and system for controlling an elevator with voice control, which has the following beneficial effects by adopting the above structure:

[0020] (1) Intelligent conflict resolution mechanism: Through voiceprint recognition and priority sorting algorithm (medical instructions > fire instructions > authorized user instructions), it effectively solves the command conflict problem caused by multiple people calling at the same time, and the response accuracy rate is improved by more than 90%.

[0021] (2) Voiceprint + NFC dual-factor binding is used to automatically release temporary permissions with a 3-second timeout and store abnormal operations on the blockchain, reducing the risk of permission abuse by 95%.

[0022] (3) Environmental adaptive interaction: LMS filter + infrared wide-angle camera collaborates to reduce noise, and can still maintain a voiceprint signal-to-noise ratio of ≥20dB in a 60dB mechanical noise environment, ensuring reliable recognition in complex scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0024] Figure 1 This is a flow chart of a voice-controlled elevator method and system proposed by the present invention. DETAILED DESCRIPTION

[0025] The technical invention in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] It should be noted that the words "front", "rear", "left", "right", "up" and "down" used in the following description refer to directions in the accompanying drawings, and the words "inside" and "outside" refer to directions toward or away from the geometric center of a specific component, respectively.

[0027] Example 1

[0028] This solution provides a voice-controlled elevator method, comprising the following steps:

[0029] Step 1: Elevator activation: The image acquisition module installed outside the elevator collects the facial information of the person, compares the facial information with the database information, and calls the elevator to arrive;

[0030] Step 2: Permission binding: The voice collection module collects the personnel's voiceprint and voice commands, compares the voiceprint with the database information, obtains the elevator control right, and outputs the elevator control command;

[0031] Step 3: Command confirmation and permission cancellation: After the command is issued, the person in charge will be prompted to confirm. If there is no voice input within three seconds after confirmation, the single permission will be terminated to avoid confusion caused by personnel communication; multiple personnel commands will be resolved for conflict and the elevator control command will be output. If the command needs to be changed, the person in charge will input the "activation command" to obtain permission binding;

[0032] Step 4: Elevator sleep: After reaching the floor, the elevator shuts down and goes into sleep.

[0033] The present invention proposes a voice-controlled elevator system for implementing the above method, comprising: an image acquisition module, a voice acquisition module, a dynamic binding module, and an elevator control system;

[0034] The image acquisition module uses a wide-angle infrared camera to assist in sound source localization: it verifies the direction of the sound source through face orientation and lip movement detection, and detects scenes such as falls and fires to trigger priority responses;

[0035] The voice acquisition module includes two groups of MEMS microphones spaced apart at the front and rear of the car top, covering the core frequency band of human voice, suppressing mechanical low-frequency noise, and digitizing voice signals. It cooperates with the image acquisition module to achieve dynamic binding and obtain elevator usage rights.

[0036] Example 2

[0037] Based on the first embodiment, Figure 1 As shown, the present invention provides a method for controlling an elevator by voice, comprising the following steps:

[0038] Step 1: Elevator activation: The image acquisition module installed outside the elevator collects the facial information of the person, compares the facial information with the database information, and calls the elevator to arrive;

[0039] Step 2: Permission binding: The voice collection module collects the personnel's voiceprint and voice commands, compares the voiceprint with the database information, obtains the elevator control right, and outputs the elevator control command;

[0040] Step 3: Command confirmation and permission cancellation: After the command is issued, the person in charge will be prompted to confirm. If there is no voice input within three seconds after confirmation, the single permission will be terminated to avoid confusion caused by personnel communication; multiple personnel commands will be resolved for conflict and the elevator control command will be output. If the command needs to be changed, the person in charge will input the "activation command" to obtain permission binding;

[0041] Step 4: Elevator sleep: After reaching the floor, the elevator shuts down and goes into sleep.

[0042] Another way to obtain permissions is through dynamic binding via the mobile NFC module. This involves sending an identity code from the user's mobile terminal's NFC module to the elevator control system, which then compares it with the database to obtain dynamic permissions. After voiceprint / NFC binding, a three-second command window opens, automatically releasing permissions upon timeout. During this period, other user commands enter the arbitration queue and do not trigger a response.

[0043] The conflict resolution includes priority sorting: emergency medical instructions > fire instructions > high-authority user instructions > ordinary elevator instructions.

[0044] The present invention proposes a voice-controlled elevator system for implementing the above method, comprising: an image acquisition module, a voice acquisition module, a dynamic binding module, an elevator control system, an offline-cloud verification module, and an execution unit; the image acquisition module uses a wide-angle infrared camera to assist in sound source localization: the sound source direction is verified by detecting facial orientation / lip movement, and priority responses are triggered by detecting scenes such as falls and fires; the voice acquisition module includes two groups of MEMS microphones spaced apart at the front and rear of the car top, covering the core frequency band of human voice, suppressing mechanical low-frequency noise, and realizing digitization of voice signals, and cooperating with the image acquisition module to achieve dynamic binding to obtain elevator use rights.

[0045] The dynamic binding module includes an NFC reading and writing module and a voiceprint feature extraction unit. The voiceprint feature extraction unit receives the pure audio from the voice module to generate a voiceprint feature vector. The NFC reading and writing module receives the user's NFC tag and outputs the permission level to the elevator control system.

[0046] The offline-cloud verification module includes an FPGA local database and a cloud blockchain verification platform. FPGA offline verification and sensitive operations such as "disable elevator" trigger cloud voiceprint secondary verification + blockchain evidence storage.

[0047] When the voiceprint / face matching confidence level is lower than the threshold, NFC or password-assisted verification is triggered forcibly, and the abnormal event is recorded in the blockchain evidence module to prevent identity fraud.

[0048] The initial voiceprint / face matching threshold is set at 85% confidence. When it is lower than the threshold, NFC / password-assisted verification is triggered. Sensitive operations (such as disabling elevators) require a confidence level ≥ 95% and force cloud blockchain secondary verification. Low-confidence scenarios give priority to calling NFC dynamic binding permissions and synchronously update the voiceprint feature library. Fire / fall detection directly triggers emergency commands through the infrared camera, skipping regular verification.

[0049] Permission classification: ordinary user threshold 85%, high-privilege user threshold 80%, emergency command threshold 60%.

[0050] The voice acquisition module integrates an LMS adaptive filter, which dynamically adjusts the noise reduction parameters according to the mechanical noise spectrum in the car (such as motor frequency), ensuring that the signal-to-noise ratio of voiceprint feature extraction is ≥20dB. The device is locked after three consecutive verification failures, and abnormal events are recorded in the blockchain evidence module. When the voiceprint signal-to-noise ratio is less than 20dB, the LMS filter is automatically enabled to enhance the audio quality.

[0051] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, material, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, material, or apparatus.

[0052] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A voice-controlled elevator method, characterized in that: The following steps are involved: Step 1: Elevator activation: The image acquisition module installed outside the elevator collects the facial information of the person, compares the facial information with the database information, and calls the elevator to arrive; Step 2: Permission binding: The voice collection module collects the personnel's voiceprint and voice commands, compares the voiceprint with the database information, obtains the elevator control right, and outputs the elevator control command; Step 3: Command confirmation and permission cancellation: After the command is issued, the person in charge will be prompted to confirm. If there is no voice input within three seconds after confirmation, the single permission will be terminated to avoid confusion caused by communication between personnel. Conflicts between multiple personnel's commands will be resolved and the elevator control command will be output. If the command needs to be changed, the person in charge will input the "activate command" to obtain permission binding. Step 4: Elevator sleep: After reaching the floor, the elevator shuts down and goes into sleep.

2. A voice-controlled elevator method according to claim 1, characterized in that: The method of obtaining permissions also includes dynamically binding permissions through the mobile NFC module. The dynamic binding steps include: the user's mobile terminal NFC module sends the identity code to the elevator control system, and compares it with the database information to obtain dynamic permissions.

3. A voice-controlled elevator method according to claim 2, characterized in that: The conflict resolution includes priority sorting: emergency medical instructions > fire instructions > high-authority user instructions > ordinary elevator instructions.

4. A voice-controlled elevator system, used to implement the method according to any one of claims 1 to 3, characterized in that: include: Image acquisition module, voice acquisition module, dynamic binding module, elevator control system, offline-cloud verification module and execution unit; The image acquisition module uses a wide-angle infrared camera to assist in sound source location, verifies the direction of the sound source through face orientation and lip movement detection, and detects scenes such as falls and fires to trigger priority responses; The voice acquisition module includes two groups of MEMS microphones spaced apart at the front and rear of the car top, covering the core frequency band of human voice, suppressing mechanical low-frequency noise, and digitizing voice signals. It cooperates with the image acquisition module to achieve dynamic binding and obtain elevator usage rights.

5. A voice-controlled elevator system according to claim 4, characterized in that: The dynamic binding module includes an NFC reading and writing module and a voiceprint feature extraction unit. The voiceprint feature extraction unit receives the pure audio from the voice module to generate a voiceprint feature vector. The NFC reading and writing module receives the user's NFC tag and outputs the permission level to the elevator control system.

6. The voice-controlled elevator system according to claim 4, characterized in that: The offline-cloud verification module includes an FPGA local database and a cloud blockchain verification platform, FPGA offline verification, and sensitive operations triggering cloud voiceprint secondary verification + blockchain evidence storage.

7. The voice-controlled elevator system according to claim 4, characterized in that: When the voiceprint or face matching confidence level is lower than the threshold, NFC or password-assisted verification is forcibly triggered, and the abnormal event is recorded in the blockchain evidence module to prevent identity fraud.

8. The voice-controlled elevator system according to claim 4, characterized in that: The voice acquisition module integrates an LMS adaptive filter, which dynamically adjusts the noise reduction parameters according to the mechanical noise spectrum in the car.

Images