Method and system for providing communication services to elevator passengers

Abstract

The subject matter of the invention is a method and system for providing communication services to elevator passengers. An elevator system has an elevator car, a controller operatively coupled to the elevator car, and a communication device in communication with the controller. The controller is configured to execute a program to communicate with a passenger or a technician using the communication device upon determining that an alarm condition associated with the elevator car occurs while the passenger or the technician is trapped within the elevator car.

Description

Technical Field

[0001] Embodiments described herein relate to elevator systems, and more particularly, to methods and systems for providing communication services to elevator passengers. Background Art

[0002] During a trapped passenger assistance (TPA) scenario, a passenger may seek support by using video and voice solutions provided by the elevator system (e.g., via a remote service center or a landline telephone line in the elevator car). The success of these solutions may depend on network traffic and may present challenges in quickly and efficiently establishing a connection between the elevator car and the service center. Furthermore, mechanics often work in elevator cars located in locations where Internet connections may be unstable, thus preventing them from quickly getting help from a remote service center. Summary of the invention

[0003] An elevator system is disclosed, which has an elevator car, a controller operatively coupled to the elevator car, and a communication device in communication with the controller. The controller is configured to execute a program to communicate with the passenger using the communication device when determining that an alarm condition associated with the elevator car occurs while a passenger is trapped in the elevator car.

[0004] In addition to one or more of the system aspects, or as an alternative, the controller includes a processor and a non-transitory memory, and the program is a compressed transformer model stored on the non-transitory memory, such that the processor is configured to execute the program via edge computing.

[0005] In addition to or as an alternative to one or more of the aspects of the system, the program is a natural language processing (NLP) model.

[0006] In addition to or as an alternative to one or more of the aspects of the system, the program is a chatbot.

[0007] Additionally or alternatively to one or more of the system aspects, the program is trained via one or more of periodically receiving training data and model updates from a remote server.

[0008] Additionally or alternatively to one or more of the system aspects, the program is configured to attempt to initiate two-way communication with a remote service center and to continue communicating with the occupant during the alarm condition until two-way communication with the remote service center is established.

[0009] Additionally or alternatively to one or more of the aspects of the system, the communication means is one or more of: a speaker and a visual display on board the elevator car; and a passenger's mobile phone.

[0010] In addition to one or more of the aspects of the system, or as an alternative, the alarm condition is that the elevator car is stopped at a landing with the car door closed for a time greater than a threshold, or the elevator car is stopped between floors for a time greater than another threshold, so that passengers are trapped in the elevator car, and the program is configured to transmit instructions for one or more of restarting the elevator car or leaving the elevator car.

[0011] Additionally or alternatively to one or more of the system aspects, the system includes a sensor operatively coupled to the elevator car, and the controller is configured to receive sensor data from the sensor, whereby the controller determines that an alarm condition has occurred.

[0012] In addition to or as an alternative to one or more of the aspects of the system, the sensor is one or more of: a smart wearable device on a passenger and a LIDAR.

[0013] A method of communicating with an elevator passenger on an elevator car during an alarm condition is also disclosed. The method includes executing a program by a controller of the elevator car upon determining that an alarm condition related to the operation of the elevator car occurs while a passenger is trapped in the elevator car, and initiating communication with a remote service center by the controller while executing the program, and continuing to communicate with the passenger using a communication device during the alarm condition until communication with the remote service center is established.

[0014] Additionally or alternatively to one or more of the method aspects, the method includes communicating instructions to the passenger including one or more of restarting the elevator car or exiting the elevator car.

[0015] In addition to one or more of the aspects of the method, or as an alternative, the method includes determining that an alarm condition occurs when the elevator car is stopped and the elevator car door is closed for a time greater than a threshold while a passenger is in the elevator car, or the elevator car is stopped between floors for a time period exceeding another threshold.

[0016] Additionally or alternatively to one or more of the method aspects, the method includes receiving, by a controller, sensor data transmitted by a sensor mounted to the elevator car or hoistway, whereby the controller determines that an alarm condition has occurred.

[0017] Additionally or alternatively to one or more of the method aspects, the method includes training the program via periodically receiving one or more of training data and model updates from a remote server.

[0018] The method of claim 11, wherein the controller includes a processor and a non-transitory memory, and the program is a compressed transformer model stored on the non-transitory memory, such that the processor is configured to execute the program via edge computing.

[0019] Additionally or alternatively to one or more of the method aspects, the program is a natural language processing (NLP) model.

[0020] Additionally or alternatively to one or more of the method aspects, the program is a chatbot.

[0021] Additionally or alternatively to one or more of the method aspects, the communication means is one or more of: a speaker and a visual display on the elevator car, and a mobile phone of the passenger.

[0022] In addition to or as an alternative to one or more of the method aspects, the sensor is one or more of: a smart wearable device on a passenger and a LIDAR. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The present disclosure is illustrated by way of examples, and not limitation, in the accompanying figures, in which like references indicate similar elements.

[0024] Figure 1 is a schematic diagram of an elevator system in which various embodiments of the present disclosure may be employed;

[0025] Figure 2 Additional aspects of a system configured to provide communication services to elevator passengers according to an embodiment are shown;

[0026] Figure 3 Additional aspects of a system configured to provide communication services to elevator passengers according to an embodiment are shown; and

[0027] Figure 4 is a flow chart illustrating a method of providing communication services to elevator passengers according to an embodiment. DETAILED DESCRIPTION

[0028] A detailed description of one or more embodiments of the disclosed apparatus and methods is presented herein by way of illustration and not limitation with reference to the figures.

[0029] Figure 11 is a perspective view of an elevator system 101, which includes an elevator car 103, a counterweight 105, a tension member 107, a guide rail (or track system) 109, a machine (or machine system) 111, a position reference system 113, and an electronic elevator controller (controller) 115. The elevator car 103 and the counterweight 105 are interconnected by the tension member 107. The tension member 107 can include or be configured as, for example, a rope, a steel cable, and / or a coated steel belt. The counterweight 105 is configured to balance the load of the elevator car 103 and is configured to facilitate the movement of the elevator car 103 in the elevator shaft (or hoistway) 117 and along the guide rail 109 relative to the counterweight 105 simultaneously and in opposite directions.

[0030] The tension member 107 engages a machine 111 that is part of the overhead structure of the elevator system 101. The machine 111 is configured to control movement between the elevator car 103 and the counterweight 105. The position reference system 113 can be mounted on a fixed portion of the top of the elevator shaft 117, such as on a support or rail, and can be configured to provide a position signal related to the position of the elevator car 103 within the elevator shaft 117. In other embodiments, the position reference system 113 can be mounted directly to the moving components of the machine 111, or can be located in other locations and / or configurations known in the art. The position reference system 113 can be any device or mechanism for monitoring the position of the elevator car and / or counterweight as known in the art. For example, but not limited to, the position reference system 113 can be an encoder, a sensor, or other system, and can include speed sensing, absolute position sensing, etc., as will be appreciated by those skilled in the art.

[0031] The controller 115 can be located in a controller room 121 of the elevator shaft 117. It is to be appreciated that the controller 115 need not be in the controller room 121, but can be in the hoistway or other locations in the elevator system. According to one aspect, the controller 115 is configured to control the operation of the elevator system 101 and in particular the elevator car 103. For example, the controller 115 can provide drive signals to the machine 111 to control the acceleration, deceleration, leveling, stopping, etc. of the elevator car 103. The controller 115 can also be configured to receive position signals from the position reference system 113 or any other desired position reference device. When moving up or down in the elevator shaft 117 along the guide rails 109, the elevator car 103 can stop at one or more landings 125 as controlled by the controller 115. Although shown in the controller room 121, those skilled in the art will appreciate that the controller 115 can be located and / or configured at other locations or places within the elevator system 101. In one embodiment, the controller can be remotely located or located in the cloud.

[0032] The machine 111 may include a motor or similar drive mechanism. According to an embodiment of the present disclosure, the machine 111 is configured to include an electric drive motor. The power source for the motor may be any power source, including an electrical grid, which, in combination with other components, is supplied to the motor. The machine 111 may include a traction sheave that applies force to the tension member 107 to move the elevator car 103 within the elevator shaft 117.

[0033] Although shown and described with a roping system including tension members 107, elevator systems that employ other methods and mechanisms for moving an elevator car within an elevator shaft may employ embodiments of the present disclosure. For example, embodiments may be used in a ropeless elevator system that uses a linear motor to impart motion to an elevator car. Embodiments may also be used in a ropeless elevator system that uses a hydraulic lift to impart motion to an elevator car. Embodiments may also be used in a ropeless elevator system that uses a self-propelled elevator car (e.g., an elevator car equipped with friction wheels, pinch wheels, or traction wheels). Figure 1 These are non-limiting examples presented for purposes of illustration and explanation only.

[0034] In other embodiments, the system includes a transportation system that moves passengers between floors and / or along a single floor. Such a transportation system may include escalators, people movers, etc. Therefore, the embodiments described herein are not limited to systems such as Figure 1 An elevator system such as the elevator system shown in .

[0035] Go to Figure 2 , an elevator system 101 includes an elevator car 103 and a controller 115A, which may be located on the elevator car 103, but may also be located elsewhere in the hoistway / building and is operatively coupled to the car 103. A communication device, generally referenced as 150, may communicate with the controller 115A. In one embodiment, the controller 115A is configured to execute a procedure 200 upon determining that an alarm condition associated with the elevator car 103 has occurred while a passenger 210 is within the elevator car 103. This results in the system 101 communicating with the passenger 210 by utilizing the communication device 150.

[0036] The communication device 150 may be a speaker and / or visual display onboard the elevator car 103, such as a visual and voice tool 150A. Alternatively, the communication device 150 may be a mobile phone 150B carried by the passenger 210. The alarm condition may be a stopped elevator car 103 with the elevator car door 220 in a closed configuration for a period of time exceeding a predetermined time period (e.g., a threshold), or when the elevator car 103 is stopped between floors for a period of time exceeding another predetermined time period (e.g., another threshold). In the case of these conditions, the controller 115A may determine that the passenger 210 is trapped in the elevator car 103.

[0037] A sensor, generally referenced as 230, may be operatively coupled to the elevator car 103, and the controller 115A is configured to receive sensor data 240 from the sensor 230. Based on this sensor data 240, the controller 115A may determine both the presence of the passenger 210 in the car 103 and the occurrence of an alarm condition while the passenger 210 is in the car 103. The sensor 230 may be a LIDAR 230A, a motion sensor 230B, a smart wearable device 230C on the passenger 210, or some other type of sensor 230. It is to be appreciated that the sensor 230 (if of the type of LIDAR 230A) may be mounted in the hoistway 117 or within the elevator car 103.

[0038] In one embodiment, the program 200 is stored on a non-transitory memory 250 on the controller 115A and executed by a processor 260 on the controller 115A. With this configuration, the controller 115A is configured for edge computing. The program 200 can be a machine learning model, such as a transformer model (transformermodel) compressed for storage on the memory 250. More specifically, the program 200 can be a natural language processing (NLP) model. Still more specifically, the program 200 is an augmented reality (AR) chatbot. The program 200 can be trained via one or more of periodically receiving training data and model updates from a remote server 270.

[0039] During an alarm condition, the system 101 will initiate two-way voice and video communications (e.g., a call) with the remote service center 280 using the communication device 150. To establish the call, the system 101 will transmit a data stream 300 over the network 290. The data stream 300 includes voice and video data exchanged during the call. While the call is being initiated (which may take time due to, for example, a weak transmission signal), the system 101 will continue to communicate with the passengers 210 in the elevator car 103, for example, to provide instructions, reassurance, and comfort.

[0040] The system 101 can be configured to use local customs and communication styles to convey assurances to the passenger 210. In the case where the passenger 210 is a maintenance person, the system 101 can be configured to convey instructions for one or more of restarting the elevator car 103 or leaving the elevator car 103.

[0041] Therefore, an embodiment provides a chatbot that is deployed to communicate with a passenger 210 during an alarm condition. The chatbot can be trained with possible queries and responses. Once the chatbot is trained, it can be run offline on an edge processing device such as a processor 260. That is, the chatbot can act as a chatbot running locally. Once a trapped passenger scenario is detected, the chatbot can automatically activate and initiate communication with the passenger 210 in the elevator car 103. During this period of time, the chatbot can initiate a call to the service center 280 to alert the service center 280 about the trapped passenger. Until the service center 280 takes over, the chatbot can provide basic assurance to the trapped passenger 210. The chatbot can be trained based on the geographical (global) region of the installation to handle communications using local customs and communication styles.

[0042] In addition, an embodiment is configured to provide assistance to a trapped mechanic. In such a scenario, the chatbot can be trained based on the mechanic assistance data. There are different ways to train the chatbot, including using machine learning algorithms such as supervised learning and natural language processing (NLP). As a non-limiting example, data can be collected from various sources such as conversations between maintenance personnel. Once the use case is defined, the AI ​​chatbot can be trained to understand the way passengers will ask their questions. The chatbot can be operated on a handheld device such as a mobile phone 150B. The chatbot can be triggered when a dangerous condition is detected via a sensor 230 installed in the shaft 117, such as a LIDAR 230A, a motion sensor 230B, a smart wearable device 230C on a mechanic 210A, etc.

[0043] like Figure 3 As shown in , in one embodiment, the communication device 150 is an AR display or an AR projector. The AR chatbot 200 works by using a text-to-text chatbot at its core. The response from the chatbot 200 is converted into an AR avatar and projected by the AR projector 150 into the available space 103A in the elevator car 103, which may be against a wall or other free space. This can be performed by a static image that is not dynamically generated. The chatbot 200 receives the voice from the AI ​​speech recognition system 200A (e.g., using a microphone as a sensor 230 ( Figure 2 )) and video processing of the AI ​​gesture recognition system 200B (e.g., using a camera as a sensor 230 ( Figure 2)) to receive the response of passenger 210. A subset of conversational AI, AI speech recognition includes automatic speech recognition (ASR) and text-to-speech (TTS) to convert human speech into text and generate human-like speech from written text. AI gesture recognition uses body movements to handle human-computer interaction, usually without the help of voice. AI gesture recognition systems typically use visual input, wearable sensors, or both. Based on the response of passenger 210, chatbot 200 prepares its next response, for example using edge computing. The response of chatbot 200 is again translated into an AR avatar-based response and projected onto the available space, as indicated. It is to be appreciated that using the AI ​​recognition process, the system may be able to confirm that the passenger is in the car during an alarm condition.

[0044] Steering Figure 4 , a flow chart shows a method for providing communication services to an elevator passenger 210 on an elevator car 103. As shown in block 310, the method includes executing the process 200 by the controller 115A upon determining that an alarm condition associated with the elevator car 103 occurs while the passenger 210 is trapped in the elevator car 103. Thus, the system 101 communicates with the passenger 210 using the communication device 150.

[0045] With respect to the alarm condition as mentioned in block 310, as shown in block 310A1, in one embodiment, the method includes the controller 115A receiving sensor data 240 transmitted by the sensor 230. As a non-limiting example, the sensor data 240 can be one or more of the following: voice, movement, and gesture. From this data, the controller 115A determines that an alarm condition has occurred. As shown in block 310A2, in one embodiment, the method includes when the elevator car 103 stops and the elevator car door 220 is closed for a time greater than a threshold while the passenger 210 is in the elevator car 103, the controller 115A determines that an alarm condition has occurred.

[0046] With respect to communicating with a passenger as mentioned in block 310 , as shown in block 310B, the method includes the controller 115A communicating instructions to a passenger 210 within the elevator car 103 including one or more of restarting the elevator car 103 or exiting the elevator car 103 .

[0047] As shown in block 320 , the method includes the controller 115A initiating two-way communication with the remote service center 280 and continuing to communicate with the occupant 210 during the alarm condition until two-way communication with the remote service center 280 is established.

[0048] As shown in block 330, the method includes training procedure 200. Training includes periodically receiving one or more of training data and model updates from remote server 270.

[0049] As used herein, a transformer model is a neural network that learns context and meaning by tracking relationships in sequential data such as words in a sentence. It is used in the fields of natural language processing (NLP) and computer vision (CV). The transformer architecture implements an encoder-decoder structure. A chatbot is a computer program that uses artificial intelligence (AI) and natural language processing (NLP) to simulate a conversation with a human user. Chatbots use AI and NLP to help users interact with network (web) services or applications through text, graphics or voice. Chatbots can understand natural human language, simulate human conversations, and run automated tasks. The training of a model means feeding a data set to the model so that the model can make predictions or decisions. The training process involves feeding data to the model and adjusting the parameters of the model (such as bias and weights) until it can relatively accurately predict the output of new data.

[0050] In the above embodiments, sensor data may be obtained and processed individually, or simultaneously and stitched together, or a combination thereof, and may be processed in raw or compiled form. Sensor data may be processed on the sensor (e.g., via edge computing), by a controller identified or implied herein, on a cloud service, or by a combination of one or more of these computing systems. Sensors may transmit data via wired or wireless transmission lines, applying one or more protocols as indicated below.

[0051] Wireless connection can apply the protocol including local area network (LAN, or WLAN for wireless LAN) protocol. LAN protocol includes WiFi technology based on the 802.11 standard from the Institute of Electrical and Electronics Engineers (IEEE). Other applicable protocols include low power WAN (LPWAN), which is a wireless wide area network (WAN) designed to allow remote communication at low bit rates, so that terminal devices can operate for extended periods of time (several years) using battery power. Long-range WAN (LoRaWAN) is a type of LPWAN maintained by the LoRa Alliance, and is a media access control (MAC) layer protocol for transmitting management and application messages between network servers and application servers, respectively. LAN and WAN protocols can generally be considered to be TCP / IP protocols (Transmission Control Protocol / Internet Protocol) for managing the connection of computer systems to the Internet. Wireless connection can also apply the protocol including private area network (PAN) protocol. PAN protocol includes, for example, Bluetooth Low Energy (BTLE), which is a wireless technology standard designed and sold by the Bluetooth Special Interest Group (SIG) for exchanging data over short distances using short wavelength radio waves. PAN protocols also include Zigbee (a technology based on the Section 802.15.4 protocol from the IEEE), which represents a set of advanced communication protocols for creating personal area networks with small, low-power digital radios for low-power, low-bandwidth requirements. Such protocols also include Z-Wave, which is a wireless communication protocol supported by the Z-Wave Alliance that uses mesh networking, applies low-energy radio waves to communicate between devices such as appliances, allowing wireless control thereof.

[0052] The wireless connection may also include radio frequency identification (RFID) technology for communicating with, for example, an integrated chip (IC) on an RFID smart card. In addition, sub-1Ghz RF devices operate in the ISM (Industrial, Scientific and Medical) band below sub-1Ghz (usually in the frequency range of 769–935MHz, 315Mhz and 468Mhz). This frequency band below 1Ghz is particularly useful for RFIOT (Internet of Things) applications. The Internet of Things (IoT) describes a network of physical objects ("things") embedded with sensors, software and other technologies for the purpose of connecting and exchanging data with other devices and systems via the Internet. Other LPWAN-IOT technologies include narrowband Internet of Things (NB-IOT) and M1 category Internet of Things (M1-IOT). Wireless communications for the disclosed system may include cellular, such as 2G / 3G / 4G (etc.). Other wireless platforms based on RFID technology include near field communication (NFC), which is a set of communication protocols for low-speed communication, for example, to exchange data between electronic devices within a short distance. NFC standards are defined by the ISO / IEC, NFC Forum and GSMA (Global System for Mobile Communications) groups (defined below).The above is not intended to limit the scope of applicable wireless technologies.

[0053] Wired connections may include connections (cables / interfaces) under RS ​​(Recommended Standard)-422, also known as TIA / EIA-422, which is a technical standard supported by the Telecommunications Industry Association (TIA) and initiated by the Electronic Industries Alliance (EIA) that specifies the electrical characteristics of digital signal circuits. Wired connections may also include (cables / interfaces) under the RS-232 standard for data serial communication transmission, which formally defines the signal connection between DTE (data terminal equipment) such as a computer terminal and DCE (data circuit terminating equipment or data communication equipment) such as a modem. Wired connections may also include connections (cables / interfaces) under the Modbus serial communication protocol managed by the Modbus organization. Modbus is a server / client protocol designed for use by its programmable logic controller (PLC) and is a common means of connecting industrial electronic devices. Wireless connections may also include connectors (cables / interfaces) under the PROFibus (process field bus) standard managed by PROFIBUS and PROFINET International (PI). PROFibus is a standard for fieldbus communication in automation technology, published as part of IEC (International Electrotechnical Commission) 61158. Wired communication is also possible via the Controller Area Network (CAN) bus. CAN is a vehicle bus standard that allows microcontrollers and devices to communicate with each other in applications without a host computer. CAN is a message-based protocol published by the International Standards Organization (ISO). The above is not intended to limit the scope of applicable wired technologies.

[0054] When data is transmitted over a network between terminal processors as identified herein, the data may be transmitted in raw form, or may be processed in whole or in part at any of the terminal processors or intermediate processors, such as at a cloud service (e.g., where at least a portion of the transmission path is wireless) or other processors. The data may be parsed, partially or completely processed or compiled at any of the processors, and may then be spliced ​​together or maintained as separate information packets. Each processor or controller identified herein may be, but is not limited to, a single processor or multi-processor system of any of a variety of possible architectures, including field programmable gate arrays (FPGAs), central processing units (CPUs), application specific integrated circuits (ASICs), digital signal processors (DSPs), or graphics processing units (GPUs) hardware arranged homogeneously or heterogeneously. The memory identified herein may be, but is not limited to, random access memory (RAM), read-only memory (ROM), or other electronic, optical, magnetic, or any other computer-readable medium.

[0055] In addition to the processor and non-volatile memory, the controller may further include one or more input and / or output (I / O) device interfaces, which are coupled to the onboard (onboard) (local) interface communication so as to communicate between other devices. The onboard interface may include, for example, but not limited to, an onboard system bus, including a control bus (for inter-device communication), an address bus (for physical addressing), and a data bus (for transmitting data). In other words, the system bus may be able to realize electronic communication between the processor, the memory, and the I / O connection. The I / O connection may also include a wired connection and / or a wireless connection identified in this article. The onboard interface may have additional elements omitted for simplicity, such as a controller, a buffer (cache), a driver, a repeater, and a receiver, so as to realize electronic communication. The memory may execute a program, access data or a lookup table, or a combination of each to facilitate its processing, all of which may be pre-stored or received by other computing devices during the execution of its process (e.g., via a cloud service or identified in this article as other network connections with other processors).

[0056] Embodiments may take the form of processor-implemented processes and means for practicing those processes (such as a processor). Embodiments may also take the form of computer code-based modules, such as computer program code (e.g., a computer program product) containing instructions embodied in a tangible medium (e.g., a non-transitory computer-readable medium), such as a floppy disk, a CD ROM, a hard drive, on processor registers as firmware, or any other non-transitory computer-readable medium, wherein when the computer program code is loaded into and executed by a computer, the computer becomes a means for practicing the embodiments. Embodiments may also take the form of, for example, computer program code, whether stored in a storage medium, loaded into and / or executed by a computer, or transmitted over some transmission medium, such as transmitted over wires or cables, over optical fibers, or via electromagnetic radiation, wherein when the computer program code is loaded into and executed by a computer, the computer becomes a means for practicing the exemplary embodiments. When implemented on a general-purpose microprocessor, the computer program code segments configure the microprocessor to create specific logic circuits.

[0057] The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the terms "comprises and / or comprising" when used in this specification specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, element components, and / or groups thereof.

[0058] Those skilled in the art will appreciate that various example embodiments are shown and described herein, each of which has certain features in a particular embodiment, but the disclosure is not limited thereto. On the contrary, the disclosure may be modified to incorporate any number of variations, alterations, substitutions, combinations, sub-combinations, or equivalent arrangements not previously described but commensurate with the scope of the disclosure. In addition, although various embodiments of the disclosure have been described, it is to be understood that aspects of the disclosure may include only some of the described embodiments. Therefore, the disclosure is not to be considered limited by the foregoing description, but only by the scope of the appended claims.

Claims

1. An elevator system, comprising: Elevator car; a controller operatively coupled to the elevator car; as well as a communication device for communicating with the controller, Wherein, the controller is configured to execute a program upon determining that an alarm condition associated with the elevator car occurs while a passenger or a mechanic is trapped in the elevator car, thereby communicating with the passenger or the mechanic using the communication device.

2. The system of claim 1, wherein: The controller includes a processor and a non-transitory memory, and the program is a compressed transformer model stored on the non-transitory memory, such that the processor is configured to execute the program via edge computing.

3. The system of claim 2, wherein: The program is a natural language processing (NLP) model.

4. The system of claim 3, wherein: The program in question is a chatbot.

5. The system of claim 3, wherein: The program is trained via periodic receipt of one or more of training data and model updates from a remote server.

6. The system of claim 3, wherein: The program is configured to attempt to initiate two-way communication with a remote service center and to continue communicating with the passenger or mechanic during the alarm condition until the two-way communication with the remote service center is established.

7. The system of claim 3, wherein: The communication means is one or more of: a speaker and a visual display on the elevator car; and a mobile phone of the passenger or mechanic.

8. The system of claim 7, wherein: The alarm condition is the elevator car being stopped at a landing with the car door closed for a time greater than a threshold, or the elevator car being stopped between floors for a time greater than another threshold, such that the passenger or mechanic is trapped in the elevator car; and The program is configured to communicate instructions for one or more of restarting the elevator car or exiting the elevator car.

9. The system of claim 3, comprising a sensor operatively coupled to the elevator car, and the controller is configured to receive sensor data from the sensor, whereby the controller determines that the alarm condition has occurred.

10. The system of claim 9, wherein: The sensor is one or more of: a smart wearable device and LIDAR on the craft.

11. A method of communicating with an elevator passenger or mechanic on an elevator car during an alarm condition, comprising: executing a program by a controller of the elevator car upon determining that the alarm condition related to operation of the elevator car occurs while the passenger or mechanic is trapped in the elevator car; as well as The controller initiates communication with a remote service center while executing the program, and continues to communicate with the passenger or mechanic using a communication device during the alarm condition until the communication with the remote service center is established.

12. The method of claim 11, comprising: Instructions including one or more of restarting the elevator car or exiting the elevator car are communicated to the passenger or mechanic.

13. The method of claim 11, comprising: The alarm condition is determined to occur when the elevator car is stopped and the elevator car doors are closed for a time greater than a threshold while the passenger or mechanic is in the elevator car, or the elevator car is stopped between floors for a time period exceeding another threshold.

14. The method of claim 11, comprising: Sensor data transmitted by sensors mounted to the elevator car or hoistway is received by the controller, whereby the controller determines that the alarm condition has occurred.

15. The method of claim 11, comprising training the program via periodically receiving one or more of training data and model updates from a remote server.

16. The method of claim 11, wherein: The controller includes a processor and a non-transitory memory, and the program is a compressed transformer model stored on the non-transitory memory, such that the processor is configured to execute the program via edge computing.

17. The method of claim 13, wherein: The program is a natural language processing (NLP) model.

18. The method of claim 13, wherein: The program in question is a chatbot.

19. The method of claim 13, wherein: The communication means is one or more of: a speaker and a visual display on the elevator car; and a mobile phone of the passenger or mechanic.

20. The method of claim 14, wherein: The sensor is one or more of: a smart wearable device and LIDAR on the craft.

Images