Systems and methods for providing ai-assisted updates of operating status of a personnel mover

Abstract

A personnel mover system having: a personnel mover; one or more controllers executing an artificial intelligence module configured to: operate the personnel mover in a first operating state in accordance with operating parameters that can be individually adjusted by a mechanic via a mobile device; and after receiving input data from the mobile device of the mechanic of a first adjustment to one or more of the operating parameters, transmit to the mobile device of the mechanic a prediction of a second operating state, wherein the input data is indicative of a target operating state of the personnel mover identified in the input data.

Description

Technical Field

[0001] The embodiments relate to a distributed personnel mobility system, and more specifically, to a system and method for providing AI-assisted updates on the operational status of the personnel mobility system. Background Technology

[0002] A mechanic at the site of a personnel mover operating in its first operating state may seek to perform various updates to the personnel mover's operating parameters to bring it into operation in a target operating state. This can be time-consuming because changing the parameters could result in a second operating state that differs unacceptably from the target operating state. Summary of the Invention

[0003] A personnel mover system is disclosed, including a personnel mover; one or more controllers that execute an artificial intelligence module configured to: operate the personnel mover in a first operating state according to operating parameters that can be individually adjusted by a mechanic via the moving device; and, upon receiving input data from the mechanic's moving device regarding the first adjustment of one or more of the operating parameters, transmit a prediction of a second operating state to the mechanic's moving device, wherein the input data indicates a target operating state of the personnel mover identified in the input data.

[0004] One or more aspects of the personnel mover system, or alternatively, the one or more controllers are configured to: determine that the target operating state resolves a customer complaint; and, depending on whether a second operating state matches the target operating state, fails to match the target operating state and causes the system to operate outside acceptable parameters, or fails to match the target operating state and causes the system to operate within acceptable parameters, transmit an "in" or "not in" or "warning" response to the mechanic's movement device.

[0005] One or more aspects of the personnel mover system, or as an alternative, are configured to issue a warning when the difference between a second operating state and a target operating state is greater than a first threshold.

[0006] One or more aspects of the personnel mobility system, or alternatively, the one or more controllers are configured to implement a first adjustment to one or more operating parameters when the difference between the second operating state and the target operating state is less than a first threshold.

[0007] One or more aspects of the personnel mover system, or alternatively, the one or more controllers are configured to identify a third operating state based on a second adjustment of one or more operating parameters among the operating parameters; and the third operating state and the target operating state are predicted to differ from each other by less than a first threshold.

[0008] One or more aspects of the personnel movement system, or alternatively, the one or more controllers are configured to implement a third operating state upon receiving an instruction from the mechanic to accept input for a third operating state.

[0009] A method for controlling a personnel mover system is disclosed, comprising: one or more controllers executing an artificial intelligence module operating the personnel mover in a first operating state according to operating parameters that can be individually adjusted by a mechanic via a moving device; and the one or more controllers receiving input data indicating a first adjustment to one or more operating parameters to obtain a target operating state of the personnel mover; and, upon processing the input data, the one or more controllers transmitting a determination of a second operating state to the mechanic's moving device.

[0010] One or more aspects of a method attached to a system for controlling a human movement device, or alternatively, the method includes the one or more controllers determining that the target operating state resolves a customer complaint; and, depending on whether a second operating state matches the target operating state, fails to match the target operating state and causes the system to operate outside acceptable parameters, or fails to match the target operating state and causes the system to operate within acceptable parameters, transmitting an enable, disable, or warning response to the human movement device.

[0011] One or more aspects of a method for controlling a personnel movement system, or as an alternative, include the method of issuing a warning by the one or more controllers when a second operating state and a target operating state differ from each other by more than a first threshold.

[0012] One or more aspects of a method for controlling a personnel movement system, or as an alternative, include the method comprising, by the one or more controllers, implementing a first adjustment of one or more operating parameters among the operating parameters when the difference between a second operating state and a target operating state is less than a first threshold.

[0013] One or more aspects of a method for controlling a personnel movement system, or as an alternative, include identifying a third operating state by the one or more controllers based on a second adjustment of one or more operating parameters among the operating parameters; wherein the third operating state and a target operating state are predicted to differ from each other by less than a first threshold.

[0014] One or more aspects of a method for controlling a human movement system, or alternatively, the method includes implementing a third operating state by the one or more controllers upon receiving an instruction from the movement device of the mechanic to accept input of a third operating state.

[0015] One or more aspects of a method for controlling a personnel mover system, or as an alternative, include a personnel mover operated in a second operating state by a moving device utilized by a mechanic.

[0016] One or more aspects of a method for controlling a personnel mover system, or as an alternative, include a personnel mover operated by a mechanic in a first operating state and a second operating state based on data received from the one or more controllers.

[0017] One or more aspects of a method attached to a control personnel movement system, or as an alternative, the method includes a first parameter identified in first parameter data transmitted from the one or more controllers, plotted by the mobile device on a display of the mobile device based on data received from the one or more controllers, wherein the first parameter has a relatively greater influence on a second operating state compared to a first operating state.

[0018] One or more aspects of a method for controlling a personnel mobility device system, or alternatively, the method includes plotting on a display of the mobility device a comparison of operational characteristics of the personnel mobility device, operated in a first operational state and a second operational state, received as comparison data from the one or more controllers, based on data received by the one or more controllers, wherein the operational characteristics include one or more of door operation, energy consumption, and waiting time.

[0019] A method for operating a personnel mover system is further disclosed, comprising: operating the personnel mover in a first operating state by one or more controllers executing an artificial intelligence module, based on operating parameters that can be individually adjusted by a mechanic using a mobile device with a display; predicting a second operating state by the one or more controllers upon receiving input data from the mechanic's mobile device instructing a first adjustment of one or more operating parameters to obtain a target operating state of the personnel mover; transmitting the prediction of the second operating state to the mechanic's mobile device by the one or more controllers; and, after processing the input data, plotting the personnel mover operating in the second operating state on the display of the mobile device based on the data received by the one or more controllers.

[0020] Attached to one or more aspects of an operator mobility system, or alternatively, the method includes plotting on a display of the mobility device a person mobility device operating in a first operating state and a second operating state based on data received from the one or more controllers.

[0021] Attached to one or more aspects of an operator mobility system, or as an alternative, the method includes plotting on a display of the mobility device a first parameter identified in first parameter data transmitted from the one or more controllers, wherein the first parameter has a relatively greater influence on a second operating state compared to a first operating state.

[0022] As an adjunct to or alternative to an operator mobility system, the method includes plotting on a display of the mobility device a comparison of operational characteristics of the operator mobility device, operated in a first operational state and a second operational state, as comparative data received from the one or more controllers, based on data received from the one or more controllers, wherein the operational characteristics include one or more of door operation, energy consumption, and waiting time. Attached Figure Description

[0023] This disclosure is illustrated in the accompanying drawings by way of example and not by way of limitation, wherein the same reference numerals indicate similar elements.

[0024] Figure 1 These are schematic illustrations of elevator systems that may employ various embodiments of the present disclosure; Figure 2 A distributed system according to an embodiment is shown, configured to provide AI assistance to solve technical problems of mechanics performing maintenance on a personnel mobility system; Figure 3 This is a flowchart illustrating a method for moving a manager according to an embodiment; Figure 4 This is a flowchart illustrating a method for moving a manager according to an embodiment; Figure 5 It is a side-by-side visualization of the first and second operating states of an elevator car with changing parameters. Detailed Implementation

[0026] Figure 1 This is a perspective view of elevator system 101, which includes elevator car 103, counterweight 105, tensioning member 107, guide rails (or rail system) 109, machine (or machine system) 111, position reference system 113, and electronic elevator controller (controller) 115. Elevator car 103 and counterweight 105 are connected to each other via tensioning member 107. Tensioning member 107 may include or be configured as, for example, ropes, cables, and / or coated steel strips. Counterweight 105 is configured to balance the load of elevator car 103 and to facilitate simultaneous and opposite movement of elevator car 103 relative to counterweight 105 within elevator shaft (or hoistway) 117 and along guide rails 109.

[0027] Tensioning member 107 engages machine 111, which is part of the overhead structure of elevator system 101. Machine 111 is configured to control movement between elevator car 103 and counterweight 105. Position reference system 113 may be mounted on a fixed component at the top of elevator shaft 117, such as on a support or guide rail, and may be configured to provide a position signal related to the position of elevator car 103 within elevator shaft 117. In other embodiments, position reference system 113 may be directly mounted to a moving component of machine 111, or may be located in other locations and / or configurations known in the art. Position reference system 113 may be any device or mechanism for monitoring the position of elevator car and / or counterweight, as known in the art. For example, without limitation, position reference system 113 may be an encoder, sensor, or other system, and may include speed sensing, absolute position sensing, etc., as will be understood by those skilled in the art.

[0028] As shown, controller 115 may be located in controller room 121 of elevator shaft 117 and configured to control the operation of elevator system 101, and particularly the operation of elevator car 103. It should be understood that controller 115 does not need to be in controller room 121, but may be located in the shaft or at other locations within the elevator system. For example, controller 115 may provide drive signals to machine 111 to control the acceleration, deceleration, leveling, stopping, etc., of elevator car 103. Controller 115 may also be configured to receive position signals from position reference system 113 or any other desired position reference device. When moving up or down along guide rail 109 within elevator shaft 117, elevator car 103 may stop at one or more floors 125 as controlled by controller 115. Although shown in controller room 121, those skilled in the art will understand that controller 115 may be located and / or configured in other locations or positions within elevator system 101. In one embodiment, the controller may be located remotely or in the cloud.

[0029] Machine 111 may include a motor or similar drive mechanism. According to embodiments of this disclosure, machine 111 is configured to include an electrically driven motor. The power supply for the motor can be any power source, including the power grid, which, in conjunction with other components, is supplied to the motor. Machine 111 may include a traction pulley that applies a force to a tensioning member 107 to move the elevator car 103 within the elevator shaft 117.

[0030] Although a rope system including a tensioning member 107 is shown and described, elevator systems employing other methods and mechanisms for moving the elevator car within the elevator shaft can adopt embodiments of this disclosure. For example, embodiments can be employed in cordless elevator systems using a linear motor to apply motion to the elevator car. Embodiments can also be employed in cordless elevator systems using a hydraulic lift to apply motion to the elevator car. Embodiments can also be employed in cordless elevator systems using a self-propelled elevator car (e.g., an elevator car equipped with friction wheels, clamping wheels, or traction wheels). Figure 1 These are non-restrictive examples presented merely for illustrative and explanatory purposes.

[0031] In other embodiments, the system includes a conveying system that moves passengers between floors and / or along individual floors. Such a conveying system may include escalators, people movers, etc. Therefore, the embodiments described herein are not limited to elevator systems, such as… Figure 1 The elevator system shown herein. In one example, the embodiments disclosed herein may be applied to transport systems, such as elevator system 101 and transport equipment of the transport system, such as elevator car 103 of elevator system 101. In another example, the embodiments disclosed herein may be applied to transport systems, such as escalator systems and transport equipment of the transport system, such as moving steps and / or moving walkway systems of escalator systems.

[0032] Go to Figure 2 Distributed (e.g., cloud) systems 200 have been disclosed. Although in Figure 2 The diagram illustrates various modules used to perform discrete functions; however, it should be understood that two or more functions may be combined into a common module, or alternatively, functions may be further divided into additional modules that can be executed on one or more controllers, which may generally be referred to as processors.

[0033] System 200 includes network 210, which may be a wide area network such as the Internet. Devices 103A-103C (typically 103, which may also be referred to as personnel movers), as a non-limiting embodiment, may be elevator cars, escalators, moving walkways, etc., and may be IoT (Internet of Things) devices, i.e., devices operatively coupled to the Internet via a first communication channel 175A. The first communication channel 175 may utilize a wired channel, such as Ethernet, or a wireless channel, such as a wide area network or cellular network, as discussed in more detail below. Each device in device 103 may have device controllers 150A-150C (typically controller 150) and sensors 155A-155C (typically 155), which are configured to transmit sensor data 156A-156C (typically 156). Sensor 155 may include one or more of a speed sensor 1551, a vibration sensor 1552, a load sensor 1553, an accelerometer 1554, a door operation sensor 1555, and a health sensor 1556, configured, for example, to sense mechanical failure of device 103. The system may include additional sensors—the preceding list should not be considered limiting. Controller 150 may control operating parameters 160 of device 103, such as, as non-limiting examples, speeds 1561 between end points (e.g., floors), braking speeds 1562 when approaching an end point, accelerations from rest 1563 when moving away from an end point, door opening speeds 1564, door closing speeds 1565, door idling when open 1566, and air conditioning conditions 1567, which may further include the volume of internal speakers or the sensitivity of internal microphones, etc.

[0034] System 200 may have a controller module (or service) 220, an IoT hub module 230 or a similar platform, and an IoT application and data storage module 240 (for simplicity, application module or IoT application module 240). The IoT hub module 230 is a known IoT application platform as a service (aPaaS) with a user-callable dashboard that centralizes device data, allows data-driven workflows, and enables the creation of custom applications.

[0035] The IoT application module 240 is utilized for storage and other processes running in a cloud service. Messages originate from device 103 (e.g., in raw format or as processed data, as a non-limiting example) and are extracted, converted to a readable / storable format, and loaded onto a database for consumption and distribution by front-end applications. The system controller module 220 instructs the IoT hub module 230 to register device 103 with the IoT application module 240, enabling the IoT application module 240 to receive telemetry data 250A-250C (typically 250) from device 103, which includes sensor data 156, and to transmit codes 260, such as updates, to device 103. Devices 103 can also interact with each other and the cloud in other ways, such as requesting updates, voice communication, etc. It should be understood that telemetry data 250 can include different types of data, such as logs, metrics, events, and traces. Logs capture detailed events or actions within the system, metrics track performance over time, events highlight important occurrences, and traces map process flows across different systems. These blocks together form a comprehensive picture of system health and performance. There may be thousands of devices 103, each sending production (e.g., actual) telemetry data 250 to the IoT application module 240. Each message relates to different aspects of device 103, such as the operating status of brakes, doors, etc. throughout the day.

[0036] The IoT application module 240 can generate a daily log 245 indicating received telemetry data 250 and transmitted codes 260. A monitoring and capture measurement module (referred to as the monitoring module for simplicity) 280 can monitor the logs generated by the IoT application module 240. The log 245 can be forwarded to the measurement storage module 310, where telemetry measurement data 315 is derived from the log 245. The query module 450 can generate a report 320 from the telemetry measurement data 315, which can be viewed via an interactive performance dashboard 297, for example, accessible via a web interface module 290, for example, on a mobile device, i.e., a mobile phone 298 with a user-callable display 298A as an example of a non-limiting embodiment. With this configuration, errors in communication can be identified by a user 295 who is likely a technician. The user can invoke the API module (or gateway) 300 to invoke the system controller module 220. Mobile phone 298 can communicate with, for example, system controller module 220 via a second communication channel 175B (which may be a cellular network or a wide area network) by transmitting outgoing mobile device data 299A to controller module 220 and receiving incoming mobile device data 299B from controller module 220.

[0037] More specifically, the diagram illustrates user 295, who invokes web interface module 290 to communicate with system controller module 220 via API module 300 and, for example, views performance dashboard 297 on their mobile phone 298. IoT hub module 230 is shown, which registers device 103 with IoT application module 240. This registration establishes trust in device connectivity and allows messages to travel in both directions between the device and the cloud, i.e., device-to-cloud and cloud-to-device, based on predefined load scenarios. Monitoring module 280 can monitor telemetry logs 245 generated by IoT application module 240. Query module 450 generates telemetry measurement data 315 and reports 320 from the telemetry measurement data 315, which can be stored on measurement storage module 310 and visualized on performance dashboard 297 via web interface module 290 to identify errors logged at IoT application module 240 over the past day (as an example).

[0038] According to an embodiment, a machine learning model (MLM) 325 (typically referred to as a neural network model or generative AI model 324) may be within the AI ​​module 327 or located in one of the identified modules, such as the query module 450 for generating report 320. When a report is requested, for example, when seeking a solution to a technical operational problem related to the operation of device 103, the MLM 325 may be invoked by user 295 using natural language. In response, the MLM 325 may provide suggestions for remedying problems identified in telemetry log 245, for example, based on accumulated data used to train the MLM 325.

[0039] Understandably, the MLM 325 can operate in learning mode (training mode), where it is trained on a dataset, such as a dataset obtained from sensor data 156 or other data identified below. In this mode, the MLM 325 learns patterns and relationships within the data to make accurate predictions or decisions. In this mode, the parameters of the MLM 325 are tuned based on the input data and the desired output. In production mode (inference mode), once the MLM 325 has been trained, validated, and deployed, it uses the learned parameters to make predictions on new, unseen data and provides real-time or batch predictions to end users or other systems.

[0040] Information sources for the learning mode of MLM 325 may include data 326, which includes device maintenance data 326A, for example, obtained from an application that transmits relevant data to system controller module 220, invoked by a mechanic on their phone 298. Data 326 may include code download (e.g., update) data 326B, for example, obtained from IoT application module 240. Data 326 may include heartbeat data 326C from telemetry data 250, including performance, alarm, and event data. Data 326 may also include initial debugging data 326D, for example, obtained from IoT central module 230 when registering device 103.

[0041] Similarly, according to embodiments, AI module 327 or, for example, query module 450, may be equipped with a large language model (LLM) 455 as another machine learning model 325 or generative AI model 324. LLM 455 can be trained using typical techniques, such as collecting and processing datasets related to the operation of device 103, applying model architectures such as transformers capable of handling long-range dependencies in text, applying hyperparameter tuning to batches of training data to adjust the size and configuration of the training data, applying optimization techniques to improve accuracy, and subsequently iteratively tuning LLM 455. LLM 455 can be trained to respond to queries submitted by technician 295 (e.g., submitted to system controller module 220) for reports 320 regarding the current, historical, and predictable (e.g., statistically) future operational status of system 200. That is, while MLM 325 can be used to identify technical operational problems in system 200 and recommend solutions, LLM 455 can be used to enable communication exchange with technician 295 using natural language.

[0042] It should be understood that an MLM 325 can be trained to respond to natural language input without requiring a separate MLM 455, for example, using Natural Language Processing (NLP). NLP is a subfield of machine learning that focuses on the interaction between computers and human language.

[0043] In the case where device 103 is an elevator car, the trained generative AI model 324 might be able to respond to queries such as: “How do we fix the door movement problem of elevator car number (xxx) located at (yyyy), where the problem is presented as (zzz)?” It is understood that, using the disclosed embodiments, a technician 295 can type their query in natural language into their phone 298 (or other mobile device), and system 200 will provide an answer based on accumulated data processed by the generative AI model 324. System 200 is able to save time and effort and provide technician 295 with a more accurate and reliable solution.

[0044] As pointed out, although in Figure 2 The diagram illustrates various modules used to perform discrete functions; however, it should be understood that two or more functions may be combined into a common module, or alternatively, functions may be further subdivided into additional modules. Therefore, references to system controller module 220 herein may imply a description of functions applicable to system controller module 220 or other modules, including one or more dedicated controllers (or processors) 330. Several individual controllers 330A-330C are shown, dedicated to AI module 327, IoT application module 240, and query module 450, but the system may have more or fewer dedicated processors 330. Additionally, or alternatively, system controller module 220 may facilitate… Figure 2 The communication and operation between the various modules are shown. General references to controller 340 herein include references to device controller 150 and module controller 330.

[0045] It should be further understood that the use of a distributed cloud system is not intended to limit the scope of the embodiments. That is, the mobile phone 298 of the technician 295 can be configured to perform procedures identified herein as being performed on a distributed system. This would be useful, for example, when the mobile phone 298 held by the technician 295 is in a location where no signal is available to communicate with other components of the distributed system 200. Equipping the mobile phone 298 to perform operations identified as being performed on a distributed system would also avoid the latency problems associated with communication exchanges over the network.

[0046] System 200 is configured to provide AI-assisted maintenance and control of personnel mobility device 103. Personnel mobility device 103 may be an elevator car, a moving platform, or an escalator. For example, attached to personnel mobility device 103, system 200 may include a device controller 150 operatively coupled to personnel mobility device 103. Device controller 150 is configured to transmit telemetry data 250 via a first communication channel 175A. System controller module 220 is configured to receive telemetry data 250. Mobile phone 298 may be configured to transmit mobile device data 299 to system controller module 220 via a second communication channel 175B.

[0047] Go to Figure 3 The flowchart illustrates a method for using a personnel mover 103 according to one embodiment. The personnel mover 103 may be an elevator car, a moving platform, or an escalator. That is, Figure 3 The discussion should relate to elevator car 103, but this reference is not intended to limit the scope of the embodiments. Figure 3 In the flowchart, the dashed boxes indicate further explanations, including one or more alternative embodiments of the preceding steps, and are not intended to limit the scope of the embodiments.

[0048] As shown in box 1010, the method includes operating the elevator car 103 in a first operating state by one or more controllers 340 according to operating parameters 1560 that can be individually adjusted by the mechanic 295 via a mobile phone 298.

[0049] As shown in block 1020, the method includes receiving input data 299 from a mobile phone 298 via communication channel 175 by one or more controllers 340 to obtain a target operating state of the elevator car 103 identified in the input data 299, which represents a first adjustment to one or more operating parameters 1560. For example, the adjustment of parameter 1560 may involve the elevator brake, and the target operating state may be a reduction in inter-floor travel time between five and ten seconds. This could be in response to customer complaints related to inter-floor travel time.

[0050] As shown in block 1030, the method includes: once the input data 299 has been processed, one or more controllers 340 executing the artificial intelligence module 325 transmit a prediction of a second operating state to a mobile phone 298 of the mechanic 295 via communication channel 175. For example, the second operating state determined by the one or more controllers 340 would indicate a reduction in travel time calculated by the one or more controllers 340 based on a first adjustment. As noted, the AI ​​module 325 can utilize training data to perform this analysis, which pertains to the effects of changes in parameter 1560 on the elevator car 103.

[0051] In other words, as shown in block 1030A, the method includes one or more controllers 340 determining that the target operating state has resolved the customer complaint. As shown in block 1030B, the method includes one or more controllers 340 transmitting a response (perform, do not perform, or warn) via communication channel 175 to a mobile phone 298 of the mechanic 295, depending on whether a second operating state matches the target operating state, fails to match the target operating state and causes the system to operate outside acceptable parameters, or fails to match the target operating state and causes the system to operate within acceptable parameters.

[0052] As shown in box 1040, the method includes issuing a warning via communication channel 175 by one or more controllers 340 when the difference between the second operating state and the target operating state is greater than a first threshold. For example, if one or more controllers 340 determine that the reduction in travel time based on the first adjustment is outside the range of five to ten seconds, or less than or greater than that range, an alarm can be issued, which the mechanic 295 can view on its phone 298. For example, the reduction may be less than expected, such as one second. Alternatively, the reduction may be greater than expected, which could result in an uncomfortable ride. That is, one or more controllers 340 executing AI module 325 can issue a "do not proceed" or "warning" response to the mechanic. For example, if the resulting travel time is far outside the target time reduction and therefore does not resolve the customer complaint, or if it is determined that a major system error may have occurred (i.e., the system is operating outside acceptable operating parameters), one or more processors 340 may issue a "do not proceed" recommendation. If the resulting travel time is exactly outside the target time reduction, such as by one second, or if the travel time is outside the target time reduction and therefore does not resolve the customer complaint but does not lead to a major system error (i.e., the system is operating within acceptable operating parameters), one or more controllers 340 may issue a "warning" recommendation, that is, instruct the mechanic to proceed with caution. This allows the mechanic to make an informed decision about whether to continue with the change.

[0053] As shown in block 1050, the method includes one or more controllers 340 implementing a first adjustment to one or more operating parameters of operating parameters 1560 when the difference between a second operating state and a target operating state is less than a first threshold. For example, controller 340 may implement the first adjustment if the travel time between floors of elevator car 103 falls within a target time range. One or more controllers 340 executing AI module 325 may issue a "go" response, indicating that a customer complaint will be resolved, instructing the mechanic to operate elevator car 103 using the adjusted parameters.

[0054] As shown in block 1060, the method includes identifying a third operating state by one or more controllers 340 based on a second adjustment of one or more operating parameters 1560. The third operating state and the target are predicted to differ from each other by less than a first threshold. For example, if the second operating state differs from the target operating state, the one or more controllers 340 can determine which of the one or more parameters 1560 should be adjusted to achieve the target operating state. Such parameters 1560 may include adjusting motion-related parameters of the elevator car 103, including acceleration, deceleration, and velocity. The one or more controllers 340 executing the AI ​​module 325 may suggest parameter changes to address complaints raised by customers.

[0055] As shown in block 1070, the method includes implementing the third operating state by one or more controllers 340 upon receiving an input indicating acceptance of the third operating state from a mechanic 295 via a mobile phone 298 communicating through communication channel 175.

[0056] Using the above embodiments, mechanics can visit the site based on customer complaints. When a mechanic executes a proposed parameter change, the AI ​​engine analyzes the change within the context of the customer complaint. The analysis aims to determine whether the change will resolve the customer complaint. If the AI ​​engine finds that the proposed parameter change does not resolve the customer complaint, it will alert the mechanic with a "Do Not" or "Warning" response. If the proposed change does not resolve the customer complaint and may cause system failure, the response is "Do Not." If the proposed change does not resolve the customer complaint but does not cause system problems, the response is "Warning." When the proposed change resolves the customer complaint, a "Do" response is provided. This system enables an improved problem-solving experience with less training and minimal experience.

[0057] Go to Figure 4 The flowchart illustrates a method for using a personnel mover 103 according to another embodiment. The personnel mover 103 can be an elevator car, a moving platform, or an escalator. That is, Figure 4 The discussion will involve elevator car 103, but this reference is not intended to limit the scope of the embodiments. Figure 4 In the flowchart, the dashed boxes indicate further explanations, including one or more alternative embodiments of the preceding steps, and are not intended to limit the scope of the embodiments.

[0058] As shown in block 1210, the method includes operating the elevator car 103 in a first operating state by one or more controllers 340 according to operating parameters 1560 that can be individually adjusted by a mechanic 295 using a mobile phone 298 having a display 298A.

[0059] As shown in block 1220, the method includes receiving input data 299 via communication channel 175 from a mobile phone 298 of a mechanic 295 indicating a first adjustment to one or more operating parameters 1560, and then having a second operating state determined by one or more controllers 340 executing the AI ​​module 325. For example, the adjustment of parameter 1560 could involve the elevator brake, and the target operating state could be a reduction in travel time between floors of five to ten seconds. The second operating state determined by the one or more controllers 340 executing the AI ​​module 325 would indicate a reduction in travel time based on the first adjustment. As noted, the AI ​​module 325 could be used to perform this analysis based on training data relating to the effect of changes in parameter 1560 on the elevator car 103.

[0060] As shown in box 1230, and in Figure 5 As illustrated in the diagram, the method includes plotting an elevator car 103 operating in a second operating state on a display 298A of a mobile phone 298 belonging to a mechanic 295, based on data 299B received from one or more controllers 340. For example, the mobile phone 298 will graphically display an image 500A on the display 298A showing the elevator car 103 moving between a first floor 125A and a second floor 125B in the hoistway 117, and display a timer 501A to indicate how long the elevator car 103 takes to travel between floors 125A and 125B. The image 500A will graphically illustrate whether the elevator car 103 operating in the second operating state meets the purpose of the target operating state. The mechanic 295 may know the travel time between floors 125A and 125B in the first operating state, which can also be displayed on the display as a reference timer 501B. Using this information, the mechanic 295 can determine, based on a diagram of the elevator car 103 traveling between floors 125A and 125B, whether the travel time of the elevator car 103 reduces the expected amount of the indication for the target operating state.

[0061] As shown in box 1240, the method includes plotting, on the display 298A of the mechanic 295's mobile phone 298, elevator cars 103 operating in a first operating state and a second operating state based on data 299B received by one or more controllers 340, i.e., a second image 500B next to a first image 500A. For example, the display 298A may display two elevator cars 103 side-by-side, traveling between a first floor 125A and a second floor 125B in corresponding shafts 117, with one image 500A showing the car 103 operating according to the first operating state and the other image 500B showing the car 103 operating according to the second operating state. Using this illustration, the mechanic 295 can graphically see whether the second operating state is an improvement over the first operating state and to what extent. Operational statuses that can resolve customer complaints may include, but are not limited to, the speed at which the elevator car responds to a call, the speed at which the elevator car travels between floors while transporting customers, the duration for which the elevator car remains at a floor with the doors open or closed while passengers are entering or leaving the elevator car, the speed at which the doors open or close while passengers are entering or leaving the elevator car, the acceleration of the elevator car from rest or the deceleration from a steady running speed between floors, vibrations associated with elevator movement and door operation, internal ventilation, lighting, speaker volume from onboard speakers, communication problems with onboard microphones, video clarity of onboard displays, and other aspects of the elevator car's interior environment.

[0062] As shown in box 1250, the method includes illustrating on the display 298A of the mechanic's mobile phone 298 a first parameter identified in first parameter data 299B transmitted from one or more controllers 340 via communication channel 175. The first parameter data 299B identifies a parameter among one or more parameters 1560 that has a relatively greater impact on a second operating state compared to a first operating state, as determined by the AI ​​module 325. For example, it can be determined that a parameter controlling acceleration from a standstill has a greater impact than braking in reducing travel time between floors. This can help inform the mechanic 295 about which parameters to adjust to achieve the target operating state.

[0063] As shown in box 1260, the method includes plotting a comparison of operating characteristics of an elevator car 103 operating in a first operating state and a second operating state on a display 298A of a mobile phone 298 of a mechanic 295, based on data 299B received by one or more controllers 340. The comparison may be illustrated as information 502A, 502B on corresponding images 500A, 500B of the elevator car 103 operating in the first and second operating states. The comparison is obtained from comparison data received from one or more controllers 340 executing the AI ​​module 325. Operating characteristics may include one or more of door operation, energy consumption, and waiting time.

[0064] use Figure 4 and Figure 5 In the above embodiment, AI model 325 is a video generation AI model trained on various elevator operation scenarios based on elevator components and standards. Given a set of parameters 1560, the AI ​​model generates a realistic simulation of elevator operation. This helps mechanic 295 assess and view the impact of changes to parameter 1560. Mechanic 295 can invoke the model by providing the changes being performed. For example, if mechanic 295 expects to change the parameter value from "X" to "Y", AI model 325 predicts the impact of the change and summarizes the possible areas of impact and dependent parameters, for example, via graphical representation. The response from AI model 325 is rendered as video and displayed on display 298A of mobile phone 298 utilized by mechanic 295. This helps mechanic 295 perform the service in a comprehensive manner. Furthermore, AI model 325 also summarizes service instances where parameter 1560 has been changed and illustrates the impact of the changes, as they relate to the performance of elevator car 103. In one embodiment, AI model 325 can generate video using the mechanic's preferred language. In one embodiment, the video can be visualized as an augmented reality (AR) object, for example, using AR projection. AR projection can assist the mechanic 295 in displaying performance updates to colleagues (including customers).

[0065] Furthermore, the Mechanic 295 allows customization of the video being generated, for example, by displaying a side-by-side visualization of the current (first operation) state and a future (second operation) state with parameter changes, such as... Figure 5 As shown in the image. Different views included in the video can include door operation, drive energy consumption, passenger waiting, etc. The video can be updated based on building configuration, product model, etc. It should be understood that the number of adjustable parameters may vary depending on the type of personnel mobility device utilized. For example, the number of adjustable parameters may differ between an elevator system and an escalator system. However, the claimed embodiment remains applicable to all forms of controlled personnel mobility devices.

[0066] Regarding the implementations of artificial intelligence (AI) explicitly or implicitly identified herein, machine learning models, such as part of an AI system, may be utilized in the embodiments. AI systems use digital computers or machines controlled by digital computers to simulate human intelligence, sense the environment (e.g., using available sensors, including speed, acceleration, vibration, sound, video, etc.), acquire knowledge, and use that knowledge to achieve optimal results. AI infrastructure includes technologies such as sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technologies, operating / interaction systems, mechatronics, etc. Some implementations of AI according to the embodiments utilize computer vision, speech processing, natural language processing, machine learning / deep learning, etc.

[0067] Some implementations of the AI ​​according to the examples utilize pre-trained (PT) machine translation models that employ a neural network-based sequence-to-sequence (SS) framework. The SS framework is a framework that includes an encoder-decoder structure. The encoder-decoder structure transforms an input sequence into another sequence output. In this framework, the encoder converts the input sequence into a vector, and the decoder takes the vector and generates the output sequence in chronological order. The encoder and decoder can utilize the same type of neural network (NN) model, or they can utilize different types of neural network models. The neural network model can be a CNN (Convolutional Neural Network) model, an RNN (Redundant Neural Network) model, a Long Short-Term Memory (LSTM) model, a Delayed Network model, a Gated CNN model, etc.

[0068] Once trained, a machine learning model can analyze input data and predict and / or characterize features contained in the sensed data in one or more aspects. In the case of video, in a non-limiting example, the sensed data may include sequence images and / or encoded video data (e.g., using digital video file / stream formats and / or codecs such as MP4, MOV, AVI, WEBM, AVCHD, OGG, and / or similar formats, including combinations and / or magnifications thereof). Feature prediction and / or characterization may include segmenting the video data. In some cases, the one or more trained machine learning models include or are associated with preprocessing or enhancement (e.g., intensity normalization, resizing, cropping, and / or similar operations, including combinations and / or magnifications thereof), which is performed before segmenting the video data. The output of the one or more trained machine learning models may include predictions of aspects of the video data, the location and / or position of the aspects within the video data, and / or the state of the aspects. The location may be a set of coordinates in an image / frame in the video data. In one or more examples, the trained machine learning model is trained to perform higher-level prediction and tracking.

[0069] Similar predictions about the operational state of a device can be made by analyzing sensor data captured during device utilization and applying that data to a trained machine learning model. For example, using service learning techniques, the model is trained on known inputs and outputs from legacy events to predict future outputs from future inputs. The model can be evaluated so that variables can be weighted or reweighted to more accurately correlate inputs and outputs, and the model can be retrained as more inputs and outputs are collected. For example, a trained model can be used to obtain predictions about the state of multiple devices in an operationally integrated device system. For one (or fewer) devices in the system, data, including operational sounds, vibrations, etc., can be captured, and the captured data can be run through a trained model that is trained to recognize the (constructive and destructive) effects that the devices have on each other in their respective operational states, including when they are operating within and outside acceptable tolerances.

[0070] Regarding the telecommunications implementations explicitly or implicitly identified herein, the wireless connections identified above may apply protocols including Local Area Network (LAN, or WLAN for wireless LAN) protocols and / or Private Area Network (PAN) protocols. LAN protocols include WiFi technology, based on the 802.11 section standard from the Institute of Electrical and Electronics Engineers (IEEE). PAN protocols include, for example, Bluetooth Low Energy (BTLE), a wireless technology standard designed and marketed 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 802.15.4 section protocol from IEEE, representing 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, a wireless communication protocol supported by the Z-Wave Alliance that uses mesh networking and low-energy radio waves to communicate between devices such as electrical appliances, allowing for wireless control of them.

[0071] Other applicable protocols include Low-Power WAN (LPWAN), a type of wireless wide-area network (WAN) designed to allow long-distance communication at low bit rates, enabling terminal devices to operate on battery power for extended periods (years). Long-Range WAN (LoRaWAN) is a type of LPWAN maintained by the LoRa Alliance and is a Media Access Control (MAC) layer protocol used to transmit management and application messages between network servers and application servers, respectively. This wireless connectivity can also include Radio Frequency Identification (RFID) technology for communication with integrated circuits (ICs), such as on RFID smart cards. Furthermore, Sub-1GHz RF devices operate in the ISM (Industrial, Scientific, and Medical) spectrum band below Sub-1GHz—typically in the 769-935 MHz, 315 MHz, and 468 MHz frequency ranges. This sub-1GHz spectrum band is particularly useful for RF IoT (Internet of Things) applications. Other LPWAN-IoT technologies include Narrowband IoT (NB-IoT) and Category M1 IoT (Cat M1-IoT). Wireless communication used in the disclosed system may include cellular technologies, such as 2G / 3G / 4G (etc.). The above is not intended to limit the scope of applicable wireless technologies.

[0072] The wired connections identified above can include connections (cables / interfaces) under RS-422 (Recommended Standard), also known as TIA / EIA-422, a technical standard supported by the Telecommunications Industry Association (TIA) and initiated by the Electronic Industries Alliance (EIA), which specifies the electrical characteristics of digital signaling circuits. Wired connections can also include connections (cables / interfaces) under the RS-232 standard for serial data communication transmission, which formally defines the signaling between a DTE (Data Terminal Equipment) such as a computer terminal and a DCE (Data Circuit Terminal Equipment or Data Communication Equipment) such as a modem. Wired connections can 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 with programmable logic controllers (PLCs) and is a common means of connecting industrial electronic devices. Wireless connections can also include connectors (cables / interfaces) under the PROFibus (Process Fieldbus) standard managed by PROFIBUS & PROFINET International (PI). PROFibus is a standard for fieldbus communication in automation technology, publicly released as part of IEC (International Electrotechnical Commission) 61158. Wired communication can also be achieved via 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 Organization for Standardization (ISO). The above is not intended to limit the scope of applicable wired technologies.

[0073] As noted, when data is transmitted between terminal processors over a network, the data can be transmitted in its raw form, or it can be processed, in whole or in part, at any terminal processor or intermediate processor (e.g., at a cloud service or other processor). The data can be parsed, partially or completely processed or compiled at any processor, and then stitched together or kept as separate packets.

[0074] Regarding the computing technologies explicitly or implicitly identified herein, each processor identified herein can be, but is not limited to, any single-processor or multi-processor system of a wide range 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 can 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. Embodiments can take the form of processor implementations of processes and apparatuses for practicing those processes, such as processors. Embodiments can also take the form of modules based on computer code, 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 floppy disks, CD-ROMs, hard disk drives, processor-on-a-registers as firmware, or any other non-transitory computer-readable medium, wherein when the computer program code is loaded into a computer and executed by the computer, the computer becomes an apparatus for practicing the embodiment. The embodiments can also be in the form of computer program code, for example, whether stored in a storage medium, loaded into and / or executed by a computer, or transmitted via some transmission medium, such as by wires or cables, by optical fibers, or via electromagnetic radiation, wherein when the computer program code is loaded into and executed by the computer, the computer becomes an apparatus 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.

[0075] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The term “about” is intended to include the degree of error and / or manufacturing tolerances associated with a measurement of a particular quantity based on equipment available at the time of filing. As used herein, the singular forms “a,” “an,” and “described” are also intended to include the plural forms unless the context clearly indicates otherwise. It should be further understood that the terms “comprising” and / or “including” as used in this specification specify the presence of the 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, elements, components, and / or groups thereof.

Claims

1. A personnel mobility system, comprising: Personnel movement device; One or more controllers, which execute an artificial intelligence module, are configured as follows: The personnel mover is operated in a first operating state according to operating parameters that can be individually adjusted by the mechanic via the moving device; and After receiving input data from the mechanic's mobile device for a first adjustment of one or more of the operating parameters, a prediction of a second operating state is transmitted to the mechanic's mobile device, wherein the input data indicates the target operating state of the personnel mobile device identified in the input data.

2. The personnel mobility system according to claim 1, wherein, The one or more controllers are configured as follows: The target operational status was determined to have resolved the customer complaint. as well as Depending on whether the second operating state matches the target operating state, fails to match the target operating state and causes the system to operate outside the acceptable parameters, or fails to match the target operating state and causes the system to operate within the acceptable parameters, a "go," "do not go," or "warning" response is transmitted to the mechanic's moving device.

3. The personnel mobility system according to claim 2, wherein, The one or more controllers are configured to issue a warning when the difference between the second operating state and the target operating state is greater than a first threshold.

4. The personnel mobility system according to claim 3, wherein, The one or more controllers are configured to perform a first adjustment to one or more of the operating parameters when the difference between the second operating state and the target operating state is less than the first threshold.

5. The personnel mobility system according to claim 4, wherein: The one or more controllers are configured to identify a third operating state based on a second adjustment of one or more of the operating parameters; and The third operating state and the target operating state are predicted to differ from each other by less than the first threshold.

6. The personnel mobility system according to claim 5, wherein, The one or more controllers are configured to implement the third operating state upon receiving an instruction from the mechanic to accept input for the third operating state.

7. A method for controlling a personnel movement system, comprising: One or more controllers executing the artificial intelligence module operate the operator's mobile device in a first operating state according to operating parameters that can be individually adjusted by the mechanic via the mobile device; The one or more controllers receive input data indicating a first adjustment to one or more of the operating parameters to obtain a target operating state of the personnel mover; and Once the input data is processed, the one or more controllers transmit the determination of the second operating state to the moving device of the mechanic.

8. The method of claim 7, comprising the one or more controllers: It was determined that the target operational status resolved the customer complaint; and Depending on whether the second operating state matches the target operating state, fails to match the target operating state and causes the system to operate outside the acceptable parameters, or fails to match the target operating state and causes the system to operate within the acceptable parameters, a "go," "do not go," or "warning" response is transmitted to the mechanic's moving device.

9. The method of claim 8, comprising: The one or more controllers issue a warning when the difference between the second operating state and the target operating state is greater than a first threshold.

10. The method of claim 9, comprising: When the difference between the second operating state and the target operating state is less than the first threshold, the one or more controllers implement a first adjustment to one or more operating parameters among the operating parameters.

11. The method of claim 10, comprising: The third operating state is identified by the one or more controllers based on a second adjustment of one or more of the operating parameters; The third operating state and the target operating state are predicted to differ from each other by less than the first threshold.

12. The method of claim 11, comprising: Once the input of the third operating state is received from the moving device of the mechanic, the third operating state is implemented by the one or more controllers.

13. The method of claim 11, further comprising displaying the personnel mover in the second operating state via a mobile device used by a mechanic.

14. The method of claim 13, comprising the personnel mover operated by a mechanic's movement device in a first operating state and a second operating state based on data received from the one or more controllers.

15. The method of claim 14, comprising: The mobile device displays a first parameter identified in first parameter data transmitted from the one or more controllers on the display of the mobile device, based on data received from the one or more controllers, wherein the first parameter has a relatively greater influence on the second operating state compared to the first operating state.

16. The method of claim 15, comprising: The display of the mobile device plots a comparison of the operational characteristics of the human mobility device, which are operated in the first operating state and the second operating state, as compared data received from the one or more controllers, based on data received from the one or more controllers. The operational characteristics include one or more of door operation, energy consumption, and waiting time.

17. A method for an operator movement system, comprising: The operator moves the machine in a first operating state, based on operating parameters that can be individually adjusted by a mechanic using a moving device with a display, according to one or more controllers that execute the artificial intelligence module. Once the machine operator receives input data from the moving device instructing a first adjustment to one or more of the operating parameters to obtain a target operating state of the personnel mover, the one or more controllers predict a second operating state. The prediction of the second operating state is transmitted from the one or more controllers to the moving device of the mechanic. and After processing the input data, the mobile device displays the human mobility device operating in the second operating state based on the data received by the one or more controllers.

18. The method of claim 17, comprising: The mobile device displays a diagram on its screen showing the human mobility device operating in the first operating state and the second operating state, based on data received from the one or more controllers.

19. The method of claim 18, comprising: The display of the mobile device illustrates a first parameter identified from first parameter data transmitted from the one or more controllers, wherein the first parameter has a relatively greater influence on the second operating state compared to the first operating state.

20. The method of claim 19, comprising: The display of the mobile device plots a comparison of the operational characteristics of the human mobility device, which are operated in the first operating state and the second operating state, as compared data received from the one or more controllers, based on data received from the one or more controllers. The operational characteristics include one or more of door operation, energy consumption, and waiting time.

Images