Intelligent rescue system for elevator

Abstract

The embodiment of the invention relates to the technical field of emergency rescue, in particular to an elevator intelligent rescue system which comprises an Internet of Things help calling device, an artificial intelligence alarm receiving platform, an intelligent voice knowledge base, an intelligent rescue center control platform and an intelligent rescue APP. A one-key distress call button is arranged on the Internet of Things distress call device, and the Internet of Things distress call device is further connected with a self-checking device of the elevator and used for calling for help to the artificial intelligence alarm receiving platform; after receiving the call-for-help request, the artificial intelligence alarm receiving platform performs an artificial intelligence dialogue with the trapped passenger by using a voice recognition model, an intelligent voice knowledge base and an intelligent dialogue generation technology; the intelligent rescue center control platform is used for assigning the nearest idle rescue station to dispatch a rescue team to the scene for rescue according to the automatically matched optimal rescue path, and when the intelligent rescue center control platform breaks down, the remote backup machine carries out remote dispatching; and the intelligent rescue APP is used for the rescue team to check the optimal rescue path and to communicate with the intelligent rescue central control platform in real time.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of emergency rescue technology, and in particular to an elevator intelligent rescue system. Background Art

[0002] An elevator is a type of vertical transportation device used between floors of a building. Its car runs along rigid tracks and is primarily used to transport people or goods. As an indispensable means of transportation in modern society, elevators are closely integrated into people's daily lives and have become a special and important piece of equipment. In recent years, with the acceleration of urbanization, elevators have played a vital role in significantly improving the quality of life in modern society. The number of elevators has shown rapid growth, with the number of new elevators reaching new highs. This has posed an increasingly severe challenge to elevator safety supervision. For example, in Shaanxi Province, the number of elevators in the province is increasing by 7% annually, with both the number of elevators in operation and the growth rate being high. However, there is a serious shortage of certified special equipment inspectors, with a certification rate of only 0.6 per 10,000 units in Shaanxi Province, posing a serious safety hazard.

[0003] When an elevator malfunctions or accidents trap passengers, quickly and effectively resolving the problem and ensuring safe rescue is crucial to their lives. To improve rescue effectiveness, a research team has proposed building an IoT-based elevator rescue system that integrates IoT sensor data collection, video surveillance, big data statistical analysis, and mobile communications. This system enables timely rescue and provides reliable protection for travel safety.

[0004] However, the elevator rescue systems that have been built and put into use still have the following problems.

[0005] First, the traditional elevator rescue system is not applicable when the elevator communication signal coverage is incomplete, passengers do not carry mobile phones, and special groups such as the elderly, children, and the deaf and mute people actually need it. It is impossible to obtain the real-time situation of trapped passengers in time, and it is even impossible to detect elevator failures and accidents in time.

[0006] Second, in the event of force majeure, such as widespread power outages caused by high-temperature loads, or severe weather conditions like heavy rain and lightning damaging high-voltage power lines, which can lead to a large number of trapped passengers in a short period of time, the volume of incoming calls for help can increase dramatically. Traditional elevator rescue systems are unable to handle such a high volume of calls. Furthermore, the control center of the elevator rescue system could potentially be paralyzed due to force majeure, causing incoming calls to fail and leaving many trapped passengers without timely assistance. Summary of the Invention

[0007] In order to solve the above technical problems, the embodiments of the present application propose an elevator intelligent rescue system, which realizes automatic calling for help through the Internet of Things call for help device in the elevator car, realizes automatic alarm reception through the artificial intelligence alarm reception platform, uses intelligent dialogue generation technology to soothe the emotions of trapped passengers, and sets up an off-site backup machine and remote dispatch function in the intelligent rescue central control platform as instant emergency reinforcement, thereby ensuring that the elevator intelligent rescue system can still function in the event of force majeure.

[0008] In order to achieve the above-mentioned purpose, the embodiment of the present application proposes an elevator intelligent rescue system, which includes: an Internet of Things call for help device installed in the elevator car, an artificial intelligence alarm platform, an intelligent voice knowledge base, a smart rescue central control platform, and a smart rescue APP installed on a mobile terminal; the Internet of Things call for help device is provided with a one-button call for help button for passengers to trigger when the elevator fails, thereby sending a call for help to the artificial intelligence alarm platform, and the Internet of Things call for help device is also connected to the elevator's self-test device. When the elevator's self-test device confirms that the elevator has a trapped person failure and the one-button call for help button is not triggered within a preset reaction time, it automatically sends a call for help to the artificial intelligence alarm platform; after receiving the call for help, the artificial intelligence alarm platform , connect to the IoT distress device corresponding to the distress request and feedback the successful alarm information, use the voice recognition model, intelligent voice knowledge base and intelligent dialogue generation technology to conduct artificial intelligence dialogue with the trapped passengers to soothe the emotions of the trapped passengers; the smart rescue central control platform simultaneously receives the distress request, determines the location of the faulty elevator corresponding to the distress request, and assigns the nearest idle rescue station to send a rescue team to rush to the scene for rescue according to the automatically matched optimal rescue path. When the smart rescue central control platform is paralyzed, it will be remotely dispatched by the off-site backup machine; the smart rescue APP is equipped with a rescue page for the rescue team to view the location of the faulty elevator and the automatically matched optimal rescue path, as well as to communicate with the smart rescue central control platform in real time.

[0009] In order to achieve the above-mentioned purpose, the embodiment of the present application also proposes an elevator intelligent rescue method, which is applied to an artificial intelligence alarm receiving platform and an intelligent rescue central control platform. The method includes the following steps: receiving a rescue request sent by an Internet of Things rescue device; wherein, the Internet of Things rescue device is provided with a one-touch rescue button, and is also connected to the elevator's self-test device. When the one-touch rescue button is triggered, or when the elevator's self-test device confirms that the elevator has a trapped person fault and the one-touch rescue button is not triggered within a preset response time, a rescue request is sent to the artificial intelligence alarm receiving platform; using a speech recognition model, an intelligent speech knowledge base and an intelligent dialogue generation technology, an artificial intelligence dialogue is conducted with the trapped passengers to soothe the trapped passengers' emotions; determining the location of the faulty elevator corresponding to the rescue information, assigning the nearest idle rescue station to send a rescue team to rush to the scene for rescue according to the automatically matched optimal rescue path; displaying the location of the faulty elevator and the automatically matched optimal rescue path to the rescue team through the smart rescue APP, and communicating with the rescue team in real time; wherein, when the smart rescue central control platform is paralyzed, remote dispatch is performed by an off-site backup machine.

[0010] In order to achieve the above-mentioned purpose, an embodiment of the present application also proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute an elevator intelligent rescue method as described above.

[0011] In order to achieve the above-mentioned purpose, an embodiment of the present application further proposes a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement an elevator intelligent rescue method as described above.

[0012] The embodiment of the present application proposes an elevator intelligent rescue system, which, through the collaborative operation of multiple modules including an IoT call for help device, an artificial intelligence alarm receiving platform, an intelligent voice knowledge base, an intelligent rescue central control platform, and an intelligent rescue APP, builds a complete closed-loop system from fault discovery to rescue completion, significantly improving the response efficiency and handling quality of elevator entrapment accidents. The core innovation of this application is reflected in four aspects: automatic call for help mechanism, intelligent soothing service, intelligent rescue central control command, and multiple disaster recovery guarantees, forming an intelligent solution covering the entire process of "call for help, handling, and rescue". At the level of fault perception and call for help, the elevator intelligent rescue system is designed with a dual-mode mechanism of active triggering and passive triggering. The IoT call for help device is not only equipped with a one-button call for help button for trapped passengers to trigger directly, but also realizes intelligent analysis and judgment by connecting to the elevator self-test device, realizing automatic call for help when the trapped passengers lose the ability to call for help, effectively improving the rescue success rate. The AI-powered alarm response platform utilizes speech recognition models, an intelligent speech knowledge base, and intelligent dialogue generation technology to analyze trapped passengers' emotions in real time during the alarm response phase. This allows for dynamic adjustments to comfort strategies through appropriate dialogue, significantly reducing the risk of secondary injuries. In the event of a large-scale elevator failure caused by force majeure, the AI-powered alarm response platform can handle alarms in parallel, maintaining high throughput and ensuring that all trapped passengers can successfully call for help. The Smart Rescue Central Control Platform, acting as a command center, can respond quickly, dispatching rescue teams from the nearest available rescue station along an automatically selected optimal rescue route. This effectively shortens the time it takes for rescue teams to reach the faulty elevator and further improves the success rate of rescue operations. The elevator smart rescue system utilizes an active-active architecture. The Smart Rescue Central Control Platform regularly synchronizes data with an offsite backup server, providing mutual backup. If the Smart Rescue Central Control Platform fails, the offsite backup server can remotely take over its tasks, ensuring uninterrupted rescue operations. The Smart Rescue app helps rescue teams stay updated on the latest situation and enables real-time communication with the Smart Rescue Central Control Platform, further improving the success rate of rescue operations.

[0013] Optionally, the IoT rescue device is provided with at least a one-touch rescue button, a display screen, a speaker, a sound receiving device and a camera; in the absence of a fault, the display screen and the speaker cooperate to play a pre-set elevator safety code video and an advertising video, and the camera is in an off state; in the event of a fault, whether a passenger triggers the one-touch rescue button, or the elevator's self-test device confirms that the elevator has a trapped person fault and the one-touch rescue button is not triggered within a preset response time, the IoT rescue device generates a rescue message based on the basic information of the elevator to which it belongs, and sends a rescue request to the artificial intelligence alarm receiving platform based on the rescue message; the basic information of the elevator includes location information, brand information, service life information, scale information and working scene information Upon receiving a distress call, the AI ​​alarm platform immediately sends a successful alarm response to the corresponding faulty elevator. Upon receiving this response from the AI ​​alarm platform, the IoT distress device activates its display, speaker, sound pickup, and camera. This allows trapped passengers to engage in an AI-powered conversation with the AI ​​alarm platform. The camera captures real-time video from the elevator cabin and transmits it to the smart rescue control platform. The smart rescue control platform then dispatches a rescue team from the nearest available rescue station, following the automatically selected optimal rescue route. The rescue team's configuration, real-time location, and automatically selected optimal rescue route are then displayed in real time to the trapped passengers via the display. The display, speaker, and sound pickup provide a communication channel between trapped passengers and the AI ​​alarm platform, relaying the intelligent dialogue generated by the AI ​​alarm platform to the trapped passengers, calming them. The display also provides a window for trapped passengers to understand the rescue situation, helping to reassure them. The camera transmits information from the elevator cabin to the smart rescue control platform, facilitating detailed control by command personnel.

[0014] Optionally, the artificial intelligence alarm receiving platform is specifically composed of a first communication module, a speech recognition module, an emotion recognition module, and an intelligent dialogue generation module. The speech recognition module is provided with a speech recognition model based on DFCNN; the first communication module is used to receive a call for help, and after receiving the call for help, connect the Internet of Things call for help device corresponding to the call for help and feedback the alarm success information, and receive the voice and audio data of the trapped passengers collected by the Internet of Things call for help device through the sound collecting device; the speech recognition model is used to use the speech recognition model based on DFCNN to perform speech recognition on the voice and audio data of the trapped passengers, and convert the voice and audio data of the trapped passengers into speech. The audio data is converted into text data. The emotion recognition module performs emotion recognition on the trapped passenger's audio and speech data and the converted text data to determine the trapped user's current emotion. The intelligent dialogue generation module mines latent relationships and conducts knowledge search and matching within the intelligent voice knowledge base based on the converted text data and the trapped user's current emotion, generating dialogue audio data corresponding to the converted text data. The first communication module is also used to transmit the generated dialogue audio data to the corresponding IoT distress call device, which plays it to the trapped passenger via a display and speaker. The DFCNN-based speech recognition model can effectively represent the long-term correlation of speech and processes it quickly, accurately recognizing the trapped passenger's audio and speech data and converting it into text data. The emotion recognition module accurately infers the trapped passenger's current emotion based on both tone and text, guiding the intelligent dialogue generation module to deliver intelligent responses based on the intelligent voice knowledge base, thereby effectively soothing the trapped passenger and preventing secondary harm.

[0015] In some optional embodiments, the DFCNN-based speech recognition model directly converts the voice audio data of the trapped passenger into a voice image, performs Fourier transform on each frame of the voice audio data of the trapped passenger, and then uses time and frequency as the two dimensions of the voice image. The entire sentence of speech is modeled through a combination of a large number of convolutional layers and pooling layers, and finally outputs text data corresponding to the voice audio data of the trapped passenger.

[0016] In some optional embodiments, the smart rescue central control platform is specifically composed of a second communication module, an emergency response module, a smart large screen and a regular backup module; the second communication module is used to synchronously receive a call for help, determine the location of the faulty elevator corresponding to the call for help, and receive the real-time video inside the car collected by the IoT call for help device through the camera; the emergency response module is used to search for the nearest idle rescue station based on the location of the faulty elevator, and automatically match the optimal rescue path based on the location of the faulty elevator, the location of the nearest idle rescue station and the real-time road conditions, and then assign the nearest idle rescue station to carry rescue materials and rescue tools corresponding to the call for help and rush to the scene for rescue according to the automatically matched optimal rescue path; the smart large screen is used to display the call for help, the basic information of the faulty elevator, the automatically matched optimal rescue path, the real-time location of the rescue team, and the real-time video inside the car of the faulty elevator in real time; the regular backup module is used to exchange information of all elevators within their respective jurisdictions with the corresponding off-site backup machine according to the preset backup cycle to complete mutual backup; in the absence of a fault, the smart large screen is also used to scroll and display the basic information of all elevators within the jurisdiction of the smart rescue central control platform in real time. The emergency response module can automatically plan the optimal rescue route based on the location of the faulty elevator, the location of the nearest vacant rescue station and real-time traffic information, ensuring that the rescue team can reach the location of the faulty elevator as quickly as possible and rescue trapped passengers.

[0017] Optionally, if the Smart Rescue Central Control Platform fails, an off-site backup machine can remotely log in to the Smart Rescue Platform and authenticate using a pre-configured key. Upon successful authentication, the machine assumes full authority over the Smart Rescue Central Control Platform, enabling remote dispatch. Identity authentication is essential to protect the rescue process from unauthorized actors and better safeguard the lives of trapped passengers.

[0018] Optionally, when the rescue team rushes to the scene for rescue according to the automatically matched optimal rescue path, they carry a mobile terminal installed with the Smart Rescue APP. The rescue team uses the Smart Rescue APP to check the location of the faulty elevator and the automatically matched optimal rescue path. After arriving at the location of the faulty elevator and completing the rescue, they confirm and report to the Smart Rescue Central Control Platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related technologies, the following is a brief introduction to the drawings required for use in the embodiments of the present application or the description of the related technologies. Obviously, the following drawings are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. The drawings described here are only used to explain the present application and are not used to limit the present application.

[0020] Figure 1 This is a structural diagram of an elevator intelligent rescue system provided by an embodiment of the present application;

[0021] Figure 2 This is a schematic diagram of the appearance of an IoT distress call device provided by one embodiment of the present application;

[0022] Figure 3 This is a schematic diagram of the structure of an artificial intelligence alarm receiving platform provided by an embodiment of the present application;

[0023] Figure 4 This is a schematic diagram of the structure of a smart rescue central control platform provided by an embodiment of the present application;

[0024] Figure 5 This is an interface diagram of a smart rescue APP provided by an embodiment of the present application;

[0025] Figure 6 This is a flow chart of an elevator intelligent rescue method provided by another embodiment of the present application;

[0026] Figure 7 This is a structural diagram of an electronic device provided by another embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, each embodiment of the present application will be described in detail below with reference to the accompanying drawings. Those skilled in the art will appreciate that in each embodiment of the present application, many technical details are provided to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present application. The various embodiments can be combined with each other and referenced to each other under the premise of no contradiction.

[0028] An embodiment of the present application proposes an elevator intelligent rescue system. The implementation details of the elevator intelligent rescue system proposed in this embodiment are described in detail below. The following content is only the implementation details provided for easy understanding and is not necessary for implementing this solution.

[0029] The structure of an elevator intelligent rescue system proposed in this embodiment is as follows Figure 1 As shown, it includes: an Internet of Things call for help device 20 installed in the elevator car 10, an artificial intelligence alarm receiving platform 30, an intelligent voice knowledge base 31, a smart rescue central control platform 40, and a smart rescue APP 51 installed on a mobile terminal.

[0030] The IoT rescue device 20 is provided with a one-touch rescue button 21 for passengers to trigger when the elevator 10 malfunctions, thereby sending a rescue request to the artificial intelligence alarm platform 30. The IoT rescue device 20 is also connected to the elevator's self-test device 11. When the elevator's self-test device 11 confirms that the elevator 10 has a trapped person malfunction and the one-touch rescue button 21 is not triggered within the preset reaction time, a rescue request is automatically sent to the artificial intelligence alarm platform 30.

[0031] After receiving the distress call, the artificial intelligence alarm platform 30 connects to the Internet of Things distress call device 20 corresponding to the distress call and feeds back the alarm success information. It uses the speech recognition model, intelligent speech knowledge base 31 and intelligent dialogue generation technology to conduct artificial intelligence dialogue with the trapped passengers to soothe the emotions of the trapped passengers.

[0032] The smart rescue central control platform 40 receives the rescue request synchronously, determines the location of the faulty elevator corresponding to the rescue request, and assigns the nearest idle rescue station 50 to send a rescue team to the scene for rescue according to the automatically matched optimal rescue path. When the smart rescue central control platform 40 is paralyzed, it will be remotely dispatched by the off-site backup machine 60.

[0033] The smart rescue APP51 is provided with a rescue page for the rescue team to view the location of the faulty elevator and the automatically matched optimal rescue path, as well as to communicate with the smart rescue central control platform 40 in real time.

[0034] The following is a detailed introduction and description of the various components of the elevator intelligent rescue system.

[0035] The IoT call for help device 20 is installed on the side wall of the elevator car 10. The IoT call for help device 20 is provided with at least a one-touch call for help button 21, a display screen, a speaker, a sound receiving device and a camera. For example, Figure 2 As shown, the one-touch call button 21 is located in the center below the display screen, the speaker and the sound receiving device are located on the left and right sides of the one-touch call button 21, and the camera is located in the center above the display screen. It is understood that the location of the one-touch call button 21 can be set as long as it is convenient for passengers to trigger it.

[0036] When no faults occur, the display and speakers work together to play a pre-set elevator safety guide video and an advertisement video, and the camera is turned off. In other words, in daily use, the IoT emergency call device 20 can be used as a billboard inside the elevator, which can recoup the R&D and assembly costs of the IoT emergency call device 20.

[0037] In the event of a malfunction, whether a passenger triggers the one-touch emergency call button 21, or the elevator's self-test device 11 confirms that a passenger is trapped in the elevator and the one-touch emergency call button 21 is not triggered within a preset response time, the IoT emergency call device 20 generates a distress message based on the basic information of the elevator to which it belongs, and sends a distress request to the artificial intelligence alarm receiving platform based on the distress message. The basic information of the elevator includes location information, brand information, age information, size information, and working scenario information. This basic information can help the smart rescue central control platform 40 clearly determine how to rescue trapped passengers, greatly improving the scientific nature of elevator emergency rescue.

[0038] After receiving a distress call, the AI ​​alarm platform 30 immediately sends a successful alarm response message to the corresponding faulty elevator. Upon receiving this response, the IoT rescue device 20 activates its display, speaker, sound pickup, and camera. The speaker and sound pickup enable an AI-powered conversation between the trapped passenger and the AI ​​alarm platform 30. The camera captures real-time video from the elevator car and transmits it to the intelligent rescue control platform 40. The display, speaker, and sound pickup provide a communication channel between the trapped passenger and the AI ​​alarm platform, relaying the intelligent conversation generated by the AI ​​alarm platform to the trapped passenger, calming them. The camera transmits information about the elevator car to the intelligent rescue control platform, facilitating detailed control by the commanding personnel.

[0039] After assigning the nearest unoccupied rescue station 50 to dispatch a rescue team to the scene along the automatically matched optimal rescue route, the intelligent rescue control platform 40 can display the rescue team's configuration, real-time location, and automatically matched optimal rescue route to the trapped passengers in real time via a display screen. In other words, the display screen provides a window for trapped passengers to understand the real-time rescue situation, which helps to further restore their confidence.

[0040] like Figure 3 As shown, the artificial intelligence alarm receiving platform 30 is specifically composed of a first communication module 301, a speech recognition module 302, an emotion recognition module 303, and an intelligent dialogue generation module 304. The speech recognition module 302 is provided with a DFCNN-based speech recognition model.

[0041] The first communication module 301 is used to receive a distress request. After receiving the distress request, it connects to the IoT distress device 20 corresponding to the distress request and feeds back a successful alarm information, as well as receives the voice audio data of the trapped passenger collected by the IoT distress device 20 through the sound collecting device.

[0042] Speech recognition model 302 is used to perform speech recognition on the voice and audio data of the trapped passengers using a DFCNN-based speech recognition model, and convert the voice and audio data of the trapped passengers into text data. The DFCNN-based speech recognition model can excellently express the long-term correlation of speech, has a high processing speed, and can accurately recognize the voice and audio data of the trapped passengers and convert it into text data.

[0043] The emotion recognition module 303 is used to perform emotion recognition on the trapped passenger's voice audio data and the converted text data to obtain the trapped user's current emotion. The emotion recognition module 303 can accurately infer the trapped passenger's current emotion based on both tone of voice and text.

[0044] Based on the converted text data and the trapped user's current emotions, the intelligent dialogue generation module 304 mines potential relationships and conducts knowledge search and matching within the intelligent voice knowledge base 31, generating audio data corresponding to the converted text data. Under the guidance of the emotion recognition module 303, the intelligent dialogue generation module 304 is able to provide scientific and reasonable intelligent responses based on the intelligent voice knowledge base 31, thereby effectively comforting the trapped passenger and preventing them from suffering secondary harm.

[0045] The first communication module 301 is further configured to send the generated conversation audio data to the corresponding IoT emergency call device 20 , so that the corresponding IoT emergency call device 20 can play the data to the trapped passengers through a display screen and a speaker.

[0046] It is worth mentioning that the artificial intelligence alarm receiving platform 30 is well able to cope with force majeure, such as high temperature power load causing large-scale power outages in various areas, heavy rain and lightning weather damaging high-voltage lines and other extreme weather conditions that lead to a large number of trapped people in a short period of time, and abnormal increase in incoming calls, ensuring that all trapped passengers in the jurisdiction can successfully call for help.

[0047] The DFCNN-based speech recognition model directly converts the trapped passenger's voice and audio data into speech images. It then performs a Fourier transform on each frame of the trapped passenger's voice and audio data, using time and frequency as the two dimensions of the speech image. It then models the entire speech sentence through a combination of numerous convolutional and pooling layers, ultimately outputting text data corresponding to the trapped passenger's voice and audio data. Compared to traditional speech recognition models, the DFCNN-based speech recognition model improves performance by over 15% and offers improved stability.

[0048] like Figure 4 As shown, the smart rescue central control platform 40 is specifically composed of a second communication module 401 , an emergency response module 402 , a smart large screen 403 and a regular backup module 404 .

[0049] The second communication module 401 is used to synchronously receive the rescue request, determine the location of the faulty elevator corresponding to the rescue request, and receive the real-time video inside the elevator car collected by the IoT rescue device 20 through the camera.

[0050] Based on the location of the faulty elevator, the emergency response module 402 searches for the nearest available rescue station 50. Based on the location of the faulty elevator, the location of the nearest available rescue station, and real-time traffic information, it automatically matches the optimal rescue route. It then assigns the nearest available rescue station 50, equipped with rescue supplies and tools corresponding to the rescue request, to the scene along the automatically matched optimal rescue route. This ensures that the rescue team can reach the location of the faulty elevator as quickly as possible and rescue trapped passengers.

[0051] The smart large screen 403 is used to display in real time the call for help, basic information of the faulty elevator, the automatically matched optimal rescue path, the real-time location of the rescue team, and the real-time video inside the car of the faulty elevator.

[0052] The periodic backup module 404 is used to exchange information about all elevators within its respective jurisdiction with the corresponding remote backup machine 60 according to the preset backup cycle, thereby completing mutual backup. Generally, the two closest cities of similar size serve as backups for each other. This design takes into account both processing power and signal transmission delay.

[0053] In the absence of a fault, the smart large screen 401 is also used to scroll and display the basic information of all elevators within the jurisdiction of the smart rescue central control platform 40 in real time, which is convenient for operation and maintenance personnel to monitor.

[0054] If the intelligent rescue control platform 40 fails, the remote backup machine 60 remotely logs in to the intelligent rescue platform 40 and uses a pre-configured key for identity authentication. Upon successful authentication, the remote backup machine 60 assumes full authority from the intelligent rescue control platform 40, enabling remote dispatch. Identity authentication is essential to protect the rescue process from unauthorized actors and better safeguard the lives of trapped passengers.

[0055] When the rescue team rushes to the scene for rescue according to the automatically matched optimal rescue path, they carry with them a mobile terminal installed with the smart rescue APP51. The rescue team uses the smart rescue APP51 to check the location of the faulty elevator and the automatically matched optimal rescue path. After arriving at the location of the faulty elevator and completing the rescue, they use the smart rescue APP51 to confirm and report to the smart rescue central control platform 40, thereby completing a complete elevator emergency rescue. The page of the smart rescue APP51 can be as follows Figure 5 shown.

[0056] The present embodiment proposes an intelligent elevator rescue system, which, through the collaborative operation of multiple modules including an IoT call for help device, an artificial intelligence alarm receiving platform, an intelligent voice knowledge base, an intelligent rescue central control platform, and an intelligent rescue APP, builds a complete closed-loop system from fault discovery to rescue completion, significantly improving the response efficiency and handling quality of elevator entrapment accidents. The core innovation of this application is reflected in four aspects: automatic call for help mechanism, intelligent soothing service, intelligent rescue central control command, and multiple disaster recovery guarantees, forming an intelligent solution covering the entire process of "call for help, handling, and rescue". At the level of fault perception and call for help, the elevator intelligent rescue system is designed with a dual-mode mechanism of active triggering and passive triggering. The IoT call for help device is not only equipped with a one-button call for help button for trapped passengers to trigger directly, but also realizes intelligent analysis and judgment by connecting to the elevator self-test device, realizing automatic call for help when the trapped passengers lose the ability to call for help or lose consciousness, effectively improving the rescue success rate. The AI-powered alarm response platform utilizes speech recognition models, an intelligent speech knowledge base, and intelligent dialogue generation technology to analyze trapped passengers' emotions in real time during the alarm response phase. This allows for dynamic adjustments to comfort strategies through appropriate dialogue, significantly reducing the risk of secondary injuries. In the event of a large-scale elevator failure caused by force majeure, the AI-powered alarm response platform can handle alarms in parallel, maintaining high throughput and ensuring that all trapped passengers can successfully call for help. The Smart Rescue Central Control Platform, acting as a command center, can respond quickly, dispatching rescue teams from the nearest available rescue station along an automatically selected optimal rescue route. This effectively shortens the time it takes for rescue teams to reach the faulty elevator and further improves the success rate of rescue operations. The elevator smart rescue system utilizes an active-active architecture. The Smart Rescue Central Control Platform regularly synchronizes data with an offsite backup server, providing mutual backup. If the Smart Rescue Central Control Platform fails, the offsite backup server can remotely take over its tasks, ensuring uninterrupted rescue operations. The Smart Rescue app helps rescue teams stay updated on the latest situation and enables real-time communication with the Smart Rescue Central Control Platform, further improving the success rate of rescue operations.

[0057] It is worth mentioning that all modules and modules involved in this embodiment are logical modules. In actual applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, to highlight the innovation of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application. However, this does not mean that other units do not exist in this embodiment.

[0058] An embodiment of the present application proposes an elevator intelligent rescue method, which is applied to an artificial intelligence alarm receiving platform and an intelligent rescue central control platform. The implementation details of the elevator intelligent rescue method proposed in this embodiment are specifically described below. The following content is only the implementation details provided for easy understanding and is not necessary for the implementation of this solution.

[0059] The specific process of the elevator intelligent rescue method proposed in this embodiment is as follows: Figure 6 Shown, including:

[0060] Step 71: Receive a distress request sent by the IoT distress call device, wherein the IoT distress call device is provided with a one-touch distress button and is also connected to the elevator's self-test device. When the one-touch distress button is triggered, or when the elevator's self-test device confirms that the elevator has a trapped person fault and the one-touch distress button is not triggered within a preset reaction time, a distress request is sent to the artificial intelligence alarm receiving platform.

[0061] Step 72: Use the speech recognition model, intelligent speech knowledge base and intelligent dialogue generation technology to conduct an artificial intelligence dialogue with the trapped passengers to soothe the trapped passengers.

[0062] Step 73: Determine the location of the faulty elevator corresponding to the distress message, assign the nearest idle rescue station to send a rescue team to the scene along the automatically matched optimal rescue path for rescue.

[0063] Step 74: Display the location of the faulty elevator and the automatically matched optimal rescue path to the rescue team through the smart rescue APP, and communicate with the rescue team in real time.

[0064] The steps of the various methods above are divided only for clear description. They can be combined into one step during implementation, or some steps can be decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application. Adding insignificant modifications or introducing insignificant designs to the algorithm or process without changing the core design of the algorithm and process are all within the scope of protection of this application.

[0065] It is not difficult to find that this embodiment is a method embodiment corresponding to the above-mentioned system embodiment. This embodiment can be implemented in conjunction with the above-mentioned system embodiment. The relevant technical details and technical effects mentioned in the above-mentioned system embodiment are still valid in this embodiment. In order to reduce repetition, they will not be repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the above-mentioned system embodiment.

[0066] Another embodiment of the present application provides an electronic device, such as Figure 7 As shown, it includes: at least one processor 81; and a memory 82 that is communicatively connected to the at least one processor 81; wherein the memory 82 stores instructions that can be executed by the at least one processor 81, and the instructions are executed by the at least one processor 81 so that the at least one processor 81 can execute an elevator intelligent rescue method as described in the above method embodiment.

[0067] The memory and processor are connected using a bus, which includes any number of interconnected buses and bridges. The bus connects various circuits of one or more processors and memories. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. These are all well known in the art and therefore will not be described further in this article. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. Data processed by the processor is transmitted on a wireless medium via an antenna. Furthermore, the antenna also receives data and transmits it to the processor.

[0068] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0069] Another embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it can implement an elevator intelligent rescue method as described in the above method embodiment.

[0070] That is, those skilled in the art will understand that all or part of the steps in the above-described embodiments can be implemented by instructing the relevant hardware through a program, which is stored in a storage medium and includes a number of instructions for causing a device (such as a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the methods described in the various embodiments of the present application. Storage media include: U disk, mobile hard disk, read-only memory, random access memory, magnetic disk or optical disk, etc., various media that can store program code.

[0071] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the technical solutions of this application. In actual applications, various changes in form and details may be made without departing from the spirit and scope of this application. Those skilled in the art will appreciate that improvements and modifications may be made without departing from the principles of this application, and such improvements and modifications are also considered to be within the scope of protection of this application.

Claims

1. An elevator intelligent rescue system, characterized in that: include: An IoT emergency call device installed in the elevator car, an AI alarm receiving platform, an intelligent voice knowledge base, a smart rescue central control platform, and a smart rescue app installed on mobile terminals; The IoT emergency call device is equipped with a one-touch emergency call button for passengers to trigger when an elevator malfunctions, thereby sending a emergency call request to the artificial intelligence alarm receiving platform. The IoT emergency call device is also connected to the elevator's self-test device. When the elevator's self-test device confirms that the elevator has trapped people and the one-touch emergency call button is not triggered within the preset response time, a emergency call request is automatically sent to the artificial intelligence alarm receiving platform. After receiving a distress call, the AI-powered alarm platform connects to the corresponding IoT distress device and provides feedback on successful alarm reception. It then uses speech recognition models, an intelligent speech knowledge base, and intelligent dialogue generation technology to conduct AI-powered dialogues with trapped passengers to calm them down. The smart rescue control platform receives the emergency call, determines the location of the faulty elevator, and dispatches a rescue team from the nearest available rescue station to the scene along the automatically matched optimal rescue route. If the smart rescue control platform fails, remote dispatch is performed by a remote backup machine. The Smart Rescue APP has a rescue page for the rescue team to view the location of the faulty elevator and the automatically matched optimal rescue path, as well as to communicate with the Smart Rescue Central Control Platform in real time.

2. An elevator intelligent rescue system according to claim 1, characterized in that: The IoT emergency call device is installed on the side wall of the elevator car and is provided with at least a one-touch emergency call button, a display screen, a speaker, a sound receiving device and a camera; In the absence of any faults, the display screen and speakers will play pre-set elevator safety rules and advertising videos, and the camera will be turned off; In the event of a malfunction, whether a passenger triggers the one-touch emergency call button, or the elevator's self-diagnosis device confirms a passenger-trapped elevator malfunction and the one-touch emergency call button is not triggered within a preset response time, the IoT emergency call device generates a distress message based on the basic information of the elevator and sends a distress request to the artificial intelligence alarm receiving platform based on the distress message. The basic information of the elevator includes location information, brand information, age information, size information, and working scenario information. After receiving the call for help, the AI ​​alarm platform immediately sends a successful alarm response message to the corresponding faulty elevator. After receiving the successful alarm response message from the AI ​​alarm platform, the IoT emergency device turns on the display, speaker, sound receiver, and camera. The speaker and sound receiver enable an AI conversation between the trapped passenger and the AI ​​alarm platform. The camera collects real-time video from the elevator car and sends it to the smart rescue central control platform. After assigning the nearest unoccupied rescue station to send a rescue team to the scene according to the automatically matched optimal rescue route, the smart rescue central control platform will display the rescue team's configuration, real-time location and automatically matched optimal rescue route to the trapped passengers in real time through the display screen.

3. An elevator intelligent rescue system according to claim 2, characterized in that: The artificial intelligence alarm receiving platform consists of a first communication module, a speech recognition module, an emotion recognition module, and an intelligent dialogue generation module. The speech recognition module is equipped with a DFCNN-based speech recognition model. The first communication module is used to receive a distress call, and after receiving the distress call, connect to the IoT distress call device corresponding to the distress call and feedback a successful alarm response message, and receive voice and audio data of the trapped passenger collected by the IoT distress call device through the sound collecting device; The speech recognition model is used to perform speech recognition on the voice and audio data of the trapped passengers using a DFCNN-based speech recognition model, and convert the voice and audio data of the trapped passengers into text data; The emotion recognition module is used to perform emotion recognition on the voice audio data and converted text data of the trapped passenger to obtain the current emotion of the trapped user; The intelligent dialogue generation module is used to mine potential relationships and conduct knowledge search and matching in the intelligent voice knowledge base based on the converted text data and the current emotions of the trapped user, and generate dialogue audio data corresponding to the converted text data; The first communication module is also used to send the generated conversation audio data to the corresponding Internet of Things distress call device, so that the corresponding Internet of Things distress call device can play it to the trapped passengers through the display screen and the speaker.

4. An elevator intelligent rescue system according to claim 3, characterized in that: The DFCNN-based speech recognition model directly converts the voice audio data of the trapped passengers into voice images, performs Fourier transform on each frame of the voice audio data of the trapped passengers, and then uses time and frequency as the two dimensions of the voice image. The entire sentence of speech is modeled through a combination of a large number of convolutional layers and pooling layers, and finally outputs text data corresponding to the voice audio data of the trapped passengers.

5. The intelligent elevator rescue system according to claim 2, characterized in that: The smart rescue central control platform consists of a second communication module, an emergency response module, a smart large screen, and a regular backup module; The second communication module is used to synchronously receive the distress request, determine the location of the faulty elevator corresponding to the distress request, and receive the real-time video inside the elevator car collected by the IoT distress device through the camera; The emergency response module searches for the nearest available rescue station based on the location of the faulty elevator. Based on the location of the faulty elevator, the location of the nearest available rescue station, and real-time traffic information, it automatically matches the optimal rescue route. It then assigns the nearest available rescue station to rush to the scene, carrying rescue supplies and tools corresponding to the rescue request, along the automatically matched optimal rescue route. The smart large screen is used to display in real time the rescue request, basic information of the faulty elevator, the automatically matched optimal rescue route, the real-time location of the rescue team, and the real-time video inside the faulty elevator car; The regular backup module is used to exchange information of all elevators in their respective areas with the corresponding remote backup machine according to the preset backup cycle to complete mutual backup; In the absence of a fault, the smart large screen is also used to display the basic information of all elevators within the jurisdiction of the smart rescue central control platform in real time.

6. An elevator intelligent rescue system according to claim 5, characterized in that: When the smart rescue central control platform is paralyzed, the off-site backup machine remotely logs in to the smart rescue platform and uses the pre-configured key for identity authentication during the remote login. If the identity authentication is passed, it takes over all the permissions of the smart rescue central control platform and realizes remote dispatch.

7. The intelligent elevator rescue system according to claim 5, characterized in that: When the rescue team rushes to the scene for rescue according to the automatically matched optimal rescue path, they carry a mobile terminal with the Smart Rescue APP installed. The rescue team uses the Smart Rescue APP to check the location of the faulty elevator and the automatically matched optimal rescue path. After arriving at the location of the faulty elevator and completing the rescue, they confirm and report to the Smart Rescue Central Control Platform.

8. An intelligent elevator rescue method, characterized in that: Applied to an artificial intelligence alarm receiving platform and a smart rescue central control platform, the method includes: Receive a distress request from an IoT distress call device; the IoT distress call device is provided with a one-touch distress button and is also connected to the elevator's self-test device. When the one-touch distress button is triggered, or when the elevator's self-test device confirms that a person is trapped in the elevator and the one-touch distress button is not triggered within a preset response time, a distress request is sent to the artificial intelligence alarm receiving platform; Using speech recognition models, intelligent speech knowledge bases, and intelligent dialogue generation technologies, AI-powered conversations were conducted with trapped passengers to soothe their emotions. Determine the location of the faulty elevator corresponding to the distress call, assign the nearest available rescue station to send a rescue team to the scene along the automatically matched optimal rescue path; The Smart Rescue App shows the rescue team the location of the faulty elevator and the automatically matched optimal rescue route, and enables real-time communication with the rescue team; Among them, when the smart rescue central control platform is paralyzed, it will be remotely dispatched by an off-site backup machine.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the elevator intelligent rescue method according to claim 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it can implement the elevator intelligent rescue method as claimed in claim 8.

Images