System and method for controlling the movement of a group of elevators

Abstract

The present disclosure provides a system and method for controlling the movement of an elevator group. The method includes accepting a current request for service by the elevator group, accepting a partial travel path of a person's movement through an environment serviced by the elevator group, and obtaining future elevator request probabilities. The method further includes processing the partial travel path with a neural network trained to estimate a weighted combination of probability density functions indicative of the person's arrival time distribution, and generating a set of possible future requests that jointly represent the future elevator request probabilities and the arrival time distribution. The method further includes optimizing a schedule for the elevator group to correspond to the current request and the set of possible future requests, and controlling the elevator group according to the schedule.

Description

[Technical Field]

[0001] The present disclosure generally relates to elevators, and more specifically to systems and methods for controlling the movement of a group of elevators. [Background Art]

[0002] An elevator or a group of elevators is installed in a building including a plurality of floors. Users move from one floor to another in the building using the group of elevators. Elevator scheduling is an important aspect for guaranteeing efficient operation of the group of elevators, for example, to reduce users' waiting time. Generally, a current elevator request is received from a user, and a schedule for controlling the group of elevators is determined based on the current elevator request. However, in order to determine an optimal schedule for the group of elevators that minimizes the average waiting time of all users, it is necessary to consider future elevator requests. To account for future elevator requests, the arrival times of potential future passengers should be predicted. Arrival time refers to the amount of time a user may take to reach the group of elevators.

[0003] Some approaches predict arrival times using model-based methods. Model-based methods build a simulator of user movement using either queuing theory or agent-based modeling. The models used by model-based methods make assumptions about the flow, speed, and density of user movement. Since the models used by model-based methods are essentially generative models, it is relatively straightforward to sample user movement paths from the model. However, sampling movement paths is time-consuming and expensive. Furthermore, performance degrades as the simulation duration increases. Additionally, accurate calibration of physical models can be time-consuming and cumbersome.

[0004] Therefore, methods and systems for optimal scheduling and control of elevator groups are still needed. [Overview of the project]

[0005] The objective of some embodiments is to provide a system and method for predicting the arrival times of future passengers to elevators in a group of elevators. Specifically, the objective of some embodiments is to predict the probability distribution of future passenger arrival times. Another objective of some embodiments is to obtain the probability of future passenger elevator requests (i.e., future elevator requests) and determine the continuity of future passenger arrival streams based on the obtained future elevator request probabilities and the predicted probability distribution of future passenger arrival times. In addition, the objective of some embodiments is to determine the schedule of the group of elevators based on the continuity of future passenger arrival streams, and the schedule optimizes performance metrics by minimizing the average waiting time (AWT) for all passengers.

[0006] Generally, elevator schedulers receive current elevator requests from passengers for service from an elevator group, and the elevator group's schedule is determined based on these current requests. However, to determine the optimal schedule for the elevator group, it is desirable to consider future elevator requests in addition to current ones. For example, suppose a first passenger on the 6th floor of a building requests service to the elevator group to go to the 1st floor. Suppose the elevator car assigned to serve the first passenger is currently on the 15th floor. In the next 5 seconds, a second passenger on the 10th floor also requests service to go to the 1st floor. In this case, the elevator scheduler may determine in advance such arrival information associated with the future passenger, i.e., the second passenger, and determine the schedule so that the elevator car on the 15th floor can wait for 5 seconds until the future passenger, i.e., the second passenger, requests service to go to the 1st floor. Upon receiving the request from the second passenger, the elevator car may first pick up the second passenger on the 10th floor, and then the first passenger on the 6th floor, so that both passengers can arrive at the 1st floor together. Thus, it is desirable to further optimize the AWT (Autonomous Throttle Time) of passengers, taking into account future elevator requirements.

[0007] To consider future elevator demand, it is necessary to determine the probability that a passenger will reach the elevator for service and the probability of the amount of time it may take for the passenger to reach the elevator. The probability that a passenger will reach the elevator for service is sometimes called the future elevator demand probability. The amount of time it may take for the passenger to reach the elevator is called the arrival time.

[0008] The problem of determining the probability of future elevator requests is called the future service request problem. The problem of determining the probability of arrival time is called the arrival time prediction problem. Some embodiments are based on the understanding that the future service request problem and the arrival time prediction problem can be considered as separate and independent problems. For example, the probability of a passenger reaching the elevator can be determined independently, and the probability of arrival time can also be predicted independently, assuming that the passenger reaches the elevator. Since the future service request problem and the arrival time prediction problem can be considered as separate problems, each problem can be solved using a different approach.

[0009] For example, in some embodiments, given a passenger's current location and destination, a neural network can be used to predict the passenger's arrival time. However, given the current location and destination, a passenger may take multiple routes to reach their destination (for example, a passenger might first go to some intermediate point (e.g., a restroom) from their current location and then head to the elevator, which may take slightly longer than going directly to the elevator). To accurately predict arrival time, such multimodalities of arrival time must be taken into account. Some embodiments are based on the understanding that the probability distribution of arrival time can be predicted in a way that takes into account the multimodalities of arrival time.

[0010] To this end, some embodiments of the present disclosure disclose a Neural Travel-time Mixture Model (NTMM) for predicting the probability distribution of arrival times. The NTMM is trained to estimate a weighted combination of probability density functions such that the weighted combination of probability density functions represents the arrival time distribution of passengers arriving at an elevator via one of several paths. The weighted combination of probability density functions predicted by the NTMM is advantageous because, in addition to evaluating the probability density, the resulting distribution can be used to evaluate a conditional cumulative distribution function and generate samples.

[0011] Furthermore, in one embodiment, the probability of a future elevator request is determined by using an attention-based destination prediction unit having an encoder / decoder structure. The attention-based destination prediction unit may be implemented using a transformer architecture-based neural network. Alternatively, in some embodiments, the probability of a future elevator request is determined by using a recurrent neural network (RNN). In addition to or instead of this, in some embodiments, the future elevator request is obtained directly. For example, in an organization's office space, a user may be provided with a user interface for making elevator service requests at their seat location (or within their private room). The user may make elevator service requests through the user interface.

[0012] The optimal schedule for a group of elevators can be determined using the calculated future elevator request probabilities and the predicted arrival time probability distribution. However, directly incorporating the calculated future elevator request probabilities and predicted arrival time probability distribution into determining the optimal schedule is difficult. Some embodiments are based on the understanding that a sequence of future passenger arrival streams (also called "a set of possible future requests") can be generated based on the calculated future elevator request probabilities and predicted arrival time probability distribution. Furthermore, the optimal schedule may be determined based on this sequence of future passenger arrival streams. In addition, the group of elevators is controlled according to an optimized schedule to accommodate both current and future elevator requests.

[0013] Accordingly, one embodiment discloses a control system for controlling the movement of a group of elevators, comprising at least one processor and a memory storing instructions. Instructions cause at least one processor of the control system to receive one or more current elevator requests for service by the group of elevators, to receive partial movement paths of people moving within an environment served by the group of elevators, to obtain future elevator request probabilities, and to process the partial movement paths using a neural network trained to estimate weighted combinations of probability density functions. The weighted combinations of probability density functions represent the arrival time distribution of people arriving at the group of elevators via one of several paths within the environment. Instructions further cause at least one processor of the control system to generate a set of possible future requests congruently representing the future elevator request probabilities and arrival time distributions, to optimize the schedule of the group of elevators to correspond to one or more current elevator requests and the set of possible future requests, and to control the group of elevators according to the schedule.

[0014] Accordingly, another embodiment discloses a method for controlling the movement of a group of elevators. The method includes the steps of receiving one or more current elevator requests for service by the group of elevators; receiving partial travel paths of a person moving within an environment served by the group of elevators; obtaining future elevator request probabilities; and processing the partial travel paths using a neural network trained to estimate a weighted combination of probability density functions. The weighted combination of probability density functions represents the arrival time distribution of a person arriving at the group of elevators via one of several paths within the environment. The method further includes the steps of generating a set of possible future requests congruently representing the future elevator request probabilities and arrival time distributions; optimizing the schedule of the group of elevators to correspond to one or more current elevator requests and the set of possible future requests; and controlling the group of elevators according to the schedule.

[0015] Accordingly, yet another embodiment discloses a non-temporary computer-readable storage medium containing a processor-executable program for performing a method for controlling the movement of a group of elevators. The method includes the steps of receiving one or more current elevator requests for service by the group of elevators; receiving partial travel paths of a person moving within an environment served by the group of elevators; obtaining future elevator request probabilities; and processing the partial travel paths using a neural network trained to estimate a weighted combination of probability density functions. The weighted combination of probability density functions represents the arrival time distribution of a person arriving at the group of elevators via one of several paths within the environment. The method further includes the steps of generating a set of possible future requests congruently representing the future elevator request probabilities and arrival time distributions; optimizing a schedule for the group of elevators to correspond to one or more current elevator requests and a set of possible future requests; and controlling the group of elevators according to the schedule.

[0016] The embodiments disclosed herein will be further described with reference to the accompanying drawings. The drawings are not necessarily to exact scale and are instead exaggerated in general to illustrate the principles of the embodiments disclosed herein. [Brief explanation of the drawing]

[0017] [Figure 1A] This is a schematic diagram illustrating the control of the movement of a group of elevators according to an embodiment of this disclosure. [Figure 1B] This is a block diagram of a control system for controlling the movement of a group of elevators according to an embodiment of the present disclosure. [Figure 1C] This figure shows a graph illustrating the arrival time distribution and the empirical probability density function (PDF) of the samples derived from the arrival time distribution, according to an embodiment of this disclosure. [Figure 2] FIG. 1 is a diagram illustrating training of a Neural Travel Time Mixture Model (NTMM) according to some embodiments of the present disclosure. [Figure 3A] FIG. 2 is a diagram illustrating a layout of a floor in a building having travel routes used for training an NTMM according to some embodiments of the present disclosure. [Figure 3B] FIG. 3 is a diagram illustrating retraining of a trained NTMM according to some embodiments of the present disclosure. [Figure 4A] FIG. 4 is a block diagram of a transformer architecture-based neural network according to some embodiments of the present disclosure. [Figure 4B] FIG. 5 is a schematic diagram illustrating a Long Short-Term Memory (LSTM)-based neural network according to some embodiments of the present disclosure. [Figure 5] FIG. 6 is a schematic diagram of a building floor plan according to some embodiments of the present disclosure. [Figure 6] FIG. 7 is a flow diagram of a method for controlling movement of an elevator group according to an embodiment of the present disclosure. [Figure 7] FIG. 8 is a schematic diagram illustrating a computing device for implementing the method and control system of the present disclosure. DETAILED DESCRIPTION OF EMBODIMENTS

[0018] Description of Embodiments In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure may be practiced without these specific details. In other instances, apparatuses and methods are shown in block diagram form only in order to avoid obscuring the present disclosure.

[0019] As used herein and in the claims, the terms “for example,” “as an example,” and “like,” as well as the verbs “equip,” “have,” and “include,” and each of their other verbal forms, should be interpreted as open-ended when used with an enumeration of one or more components or other items, meaning that the enumeration should not be considered as excluding other further components or items. The term “based on” means based on at least partially. Furthermore, it should be understood that the style and terminology used herein are for illustrative purposes only and should not be considered restrictive. Any headings used herein are for convenience only and have no legal or restrictive effect.

[0020] Figure 1A shows a schematic diagram illustrating the control of the movement of an elevator group 115 according to an embodiment of the present disclosure. The elevator group 115 may include one or more elevator cars, such as car 117a and car 117b. The elevator group 115 may be installed in an environment such as a building that includes multiple floors, such as floor 119a, floor 119b, floor 119c, floor 119d, floor 119e, and floor 119f. The objective of some embodiments is to provide a control system for determining an optimal schedule for the elevator group 115, which optimizes performance metrics by minimizing the average waiting time (AWT) for all passengers. The objective of some embodiments is also to provide a control system for controlling the elevator group 115 based on the optimal schedule. Such control systems are described below in Figure 1B.

[0021] FIG. 1B shows a block diagram of a control system 121 for scheduling and controlling an elevator group 115 according to an embodiment of the present disclosure. The control system 121 includes a processor 123 and a memory 125. The processor 123 may be a single-core processor, a multi-core processor, a computing cluster, or any number of other configurations. The memory 125 may include random access memory (RAM), read-only memory (ROM), flash memory, or any other suitable memory system. In addition, in some embodiments, the memory 125 may be implemented using a hard drive, an optical drive, a thumb drive, an array of drives, or any combination thereof.

[0022] The processor 123 receives a partial movement route 101 of movement of a person (who may be a potential passenger) moving within an environment serviced by the elevator group 115. The partial movement route 101 of the person's movement may correspond to a part of a route that the person covers while traveling from a starting point to a destination. The partial movement route 101 may be determined depending on the route taken by the person. For example, the partial movement route 101 may be a straight line, a curved line, or a zigzag depending on the route taken by the person. The environment serviced by the elevator group 115 may be an area on a floor among a plurality of floors (119a to 119f). In an embodiment, the processor 123 may capture the movement of the person using a sensor (such as a camera) associated with the environment to obtain the partial movement route 101.

[0023] Furthermore, the processor 123 receives current elevator requests 111 from passengers for service by the elevator group 115 and determines the schedule for the elevator group 115 based on the current elevator requests. However, in order to determine the optimal schedule for the elevator group 115, it is desirable to consider future elevator requests in addition to the current elevator requests 111. For example, suppose a first passenger on the 6th floor of the building requests service to the elevator group to go to the 1st floor of the building. Suppose the elevator car assigned to serve the first passenger is currently on the 15th floor. Suppose that in the next 5 seconds, a second passenger on the 10th floor also requests service to go to the 1st floor. In this case, the elevator scheduler may determine in advance such arrival information associated with the future passenger, i.e., the second passenger, and determine the schedule so that the elevator car on the 15th floor can wait for 5 seconds until the future passenger, i.e., the second passenger, requests service to go to the 1st floor. If a request is received from a second passenger, the elevator car may first pick up the second passenger from the 10th floor, and then the first passenger from the 6th floor, so that both passengers can arrive at the 1st floor together. Thus, it is desirable to further optimize the passenger AWT by taking future elevator requests into consideration.

[0024] To consider future elevator requests, it is necessary to determine the probability that a passenger will reach elevator group 115 for elevator service, and the probability of the amount of time it may take for a passenger to reach elevator group 115. The probability that a passenger will reach elevator group 115 for elevator service is sometimes called the future elevator request probability. The amount of time it may take for a passenger to reach elevator group 115 is called the arrival time.

[0025] The problem of determining the probability of future elevator requests is called the future service request problem. The problem of determining the probability of arrival time is called the arrival time prediction problem. Some embodiments are based on the understanding that the future service request problem and the arrival time prediction problem can be considered as separate and independent problems. For example, the probability of a passenger reaching elevator group 115 can be determined independently, and the probability of arrival time can also be predicted independently, assuming that the passenger reaches elevator group 115. Since the future service request problem and the arrival time prediction problem can be considered as separate problems, each problem can be solved using a different approach.

[0026] For example, in some embodiments, given a passenger's current location and destination, a neural network can be used to predict the passenger's arrival time. However, given the current location and destination, a passenger may take multiple routes to reach their destination (for example, a passenger might first go to some intermediate point (e.g., a restroom) from their current location and then head to the elevator, which may take slightly longer than going directly to the elevator). To accurately predict arrival time, such multimodalities of arrival time must be taken into account. Some embodiments are based on the understanding that the probability distribution of arrival time can be predicted in a way that takes into account the multimodalities of arrival time.

[0027] To this end, some embodiments of the present disclosure disclose a neural network 103 trained to estimate a weighted combination of probability density functions, which represent the arrival time distribution of passengers arriving at an elevator via one of several paths. A processor 123 processes a partial travel path 101 using the neural network 103 to estimate a weighted combination of probability density functions that represent the arrival time distribution 105 of persons arriving at a group of elevators 115 via one of several paths. The weighted combination of probability density functions predicted by the neural network 103 is advantageous because, in addition to evaluating the probability density, the resulting distribution can be used to evaluate a conditional cumulative distribution function and generate samples.

[0028] Furthermore, the processor 123 obtains a future elevator request probability 107. In one embodiment, to obtain the future elevator request probability 107, the processor 123 processes a partial travel path 101 using an attention-based destination prediction unit having an encoder / decoder structure. The attention-based destination prediction unit may be implemented using a transformer architecture-based neural network. Alternatively, in some embodiments, to obtain the future elevator request probability 107, the processor 123 processes a partial travel path 101 using a recurrent neural network (RNN).

[0029] The optimal schedule for the elevator group 115 can be determined using the future elevator request probabilities 107 and the arrival time distribution 105. However, it is difficult to directly incorporate the future elevator request probabilities 107 and the arrival time distribution 105 when determining the optimal schedule. Some embodiments are based on the understanding that a set of possible future requests can be generated based on the future elevator request probabilities 107 and the arrival time distribution 105. To this end, the processor 123 generates a set of possible future requests 109 that congruently represent the future elevator request probabilities 107 and the arrival time distribution 105. An example of the generation of a set of possible future requests 109 is described below.

[0030]

number

[0031] Furthermore, the processor 123 optimizes the elevator group schedule 113 to correspond to the current elevator request 111 and a set of possible future requests 109. The processor 123 controls the elevator group 115 according to the optimized schedule 113.

[0032] Figure 1C shows the arrival time distribution 105 estimated by the neural network 103 and the empirical probability density function (PDF) of the samples derived from the arrival time distribution 105.

[0033] Figure 1C shows a graph 127 illustrating the arrival time distribution 105 according to some embodiments of this disclosure, and an empirical PDF 129 of a sample derived from the arrival time distribution 105.

[0034] In one embodiment, a neural network 103 trained to estimate a weighted combination of probability density functions representing the arrival time distribution 105 is a neural travel time mixture model (NTMM). The NTMM is trained on a dataset, as described below in Figure 2. (NTMM training)

[0035] Figure 2 shows the training of NTMM207 according to some embodiments of the present disclosure. NTMM207 is trained with a dataset 201 that includes the origin and destination coordinates 203 of different individuals and the durations 205 of travel paths corresponding to different individuals. In addition to or instead of this, dataset 201 includes the durations of travel paths corresponding to the same person at different times. The travel paths used to train NTMM207 are described below in Figure 3A.

[0036] Figure 3A shows a layout 300 of a floor 301 in a building having travel paths used to train an NTMM207, according to some embodiments of the present disclosure. In some embodiments, each travel path, such as travel path 305 and travel path 311, may be represented by a sequence of tessellation indices. Each travel path may have its own origin and destination. For example, travel path 305 includes origin 303 and destination 307, and travel path 311 includes origin 309 and destination 313. The tessellation index may be obtained by discretizing a range of position coordinates, where the range of position coordinates may represent longitude and latitude associated with the tessellation index corresponding to floor 301. In another embodiment, a travel path may include a travel path that includes both position information and timing information. Furthermore, each travel path may be represented by a sequence of tuples of tessellation indices, where each tuple may include a tessellation index obtained by discretizing a range of position coordinates and a prediction period.

[0037] As shown in Figure 3A, the representation of movement paths is simplified by discretizing the coordinates of positions on floor 301 into tessellation indices 1 to 2500. Tessellation indices 1 to 2500 are collectively represented by 315. The space of floor 301 is discretized into 50x50 tessellations, and each movement path is transformed into a sequence of tessellation locations. Such movement paths can serve to simulate the movement of a single person across the entire floor at a certain time of day, and the destinations visited by this person may represent actual indoor destinations primarily accessed, such as restrooms, stairs, elevators, and break rooms. Mathematically, the movement paths are given as described below.

[0038]

number

[0039]

number

[0040]

number

[0041]

number

[0042]

number

[0043]

number

[0044]

number

[0045]

number

[0046]

number

[0047]

number

[0048] For this purpose, the hyperparameters in the objective function are (a) the number of components (K), (b) the regularization penalty (λ), (c) the number of nodes in the two dense layers, and (d) the learning rate.

[0049] Some embodiments are based on the understanding that the movement paths of different individuals can change over time. In other words, the movement of individuals in an environment changes over time. Therefore, a trained NTMM207 needs to be retrained on new datasets, for example, for movement patterns where the hyperparameters are no longer optimal.

[0050] Figure 3B shows the retraining of a trained NTMM207 according to some embodiments of the present disclosure. An updated NTMM is obtained by further retraining an NTMM207 trained on dataset 201 with a new dataset 317. The new dataset 317 contains updated movement path durations corresponding to different individuals. Since the NTMM207 is retrained using the previous hyperparameters, an expensive hyperparameter search is not performed each time the NTMM207 is retrained. Thus, the NTMM207 is trained in a computationally inexpensive way.

[0051] NTMM207 estimates a weighted combination of probability density functions that represent the arrival time distribution 105. Based on the arrival time distribution and the future elevator request probabilities 107, the processor 123 generates a set of possible future requests 109, as described below. (Generating a set of possible future requirements)

[0052]

number

[0053]

number

[0054]

number

[0055] Furthermore, the assignment is determined by minimizing the AWT for candidate partitions of a contiguous set. To achieve this, either an exact or approximate algorithm can be applied.

[0056]

number

[0057]

number

[0058]

number

[0059] Furthermore, in one embodiment, in order to obtain a future elevator request probability 107, the processor 123 processes a partial travel path 101 using a transformer architecture-based neural network. The transformer architecture-based neural network is described below in Figure 4A.

[0060] Figure 4A shows a block diagram 400 illustrating the components of a transformer architecture-based neural network 435 according to some embodiments of the present disclosure. The transformer architecture-based neural network 435 may include an encoder 413 comprising a stack of N encoder blocks and a decoder 431 comprising a stack of N decoder blocks. These may further include stacks of components for self-attention and fully connected feedforward layers, in a manner that enables parallelization of the transformer architecture-based neural network 435 using position coding and attention mechanisms.

[0061] Some embodiments are based on the recognition that the attention mechanism of the transformer architecture-based neural network 435 allows for modeling the dependencies between elements in a sequence without considering their distances, and that such advantages of the transformer architecture-based neural network 435 are not limited to speech-related applications but also apply to augmented destination prediction tasks.

[0062] As shown in Figure 4A, first the input travel path 401 (partial travel path 101, etc.) passes through the embedding and position coding block 403, where the input token is d modelThe input tokens can be converted into a dimensional vector and may be discrete elements. Furthermore, the order information of the elements of the input movement path 401 is obtained using position coding and then combined with the embedding vector to obtain a new vector by additive operation. The new vector can then be sent to the multi-head attention block 407. Attention in the encoder 413 can be used as a means to refer to other tokens in the input movement path 401 when attempting to encode a particular token.

[0063] The multi-head attention block 407 may contain an array of scaled dot product attention components, and the attention function may be computed based on the data matrix X. The data matrix may be projected using three different matrices learned during training, yielding projection matrices Q, K, and V representing the query, key, and value, respectively.

[0064]

number

[0065] In some embodiments, the multi-head attention mechanism includes computing multiple attention functions using different learned projections to achieve improved representational performance.

[0066] Furthermore, the addition and normalization block 409 within encoder 413 may include residual coupling along with layer normalization (RLN), which may couple the input to multi-head attention block 407 to the output of multi-head attention block 407, add them together, and then normalize them. The resulting elements may then pass through a feedforward sub-layer 411 and subsequently another addition and normalization block 415, which includes RLN coupling, as it exits encoder 413. The addition and normalization block 415 may couple the input to feedforward layer 411 to the output of feedforward layer 411, add them together, and then normalize them.

[0067] Furthermore, the target output movement path 405 may pass through an embedding and position coding block 417, which may be similar to the embedding and position coding block 403, before entering the masked multi-head attention block 419. The elements of the masked multi-head attention block 419 may be similar to the multi-head attention block 407 of the encoder 413, except that the target output movement path 405 is masked so that the masked multi-head attention block 419 can refer only to the preceding output movement path positions. In addition, an addition and normalization block 421, which includes residual coupling with RLN, may combine the input to the masked multi-head attention block 419 with the output of the masked multi-head attention block 419, add them together, and normalize them.

[0068] Following the addition and normalization block 421, there may be another multi-head attention block 423. The multi-head attention block 423 may be similar to the multi-head attention block 407 of encoder 413, except that the multi-head attention block 423 uses information from the encoder output as an additional input in the attention calculation.

[0069] Furthermore, another addition and normalization block 425 may connect the input to the multi-head attention block 423 to the output of the multi-head attention block 423, add them together, and normalize them. The resulting elements may then pass through a feedforward sublayer 427 and subsequently through another addition and normalization block 429 as they exit the decoder 431. The addition and normalization block 429 may connect the input to the feedforward layer 427 to the output of the feedforward layer 427, add them together, and normalize them.

[0070] Outside of decoder 431, there may be a linear layer and a softmax block 433 that can take the output of decoder 431 and create a logic vector for all possible output elements. Furthermore, the linear layer and softmax block 433 may output the future elevator request probability 107 by performing a softmax operation to transform the values ​​in the logic vector.

[0071] Alternatively, processor 123 uses an RNN to process a partial travel path 101 and obtain the future elevator request probability 107. Examples of RNNs include, but are not limited to, long-short-term memory (LSTM) based neural networks and bidirectional long-short-term memory (BiLSTM) based neural networks.

[0072] Figure 4B shows an LSTM-based neural network 437 according to an embodiment of the present disclosure. The LSTM-based neural network unit 437 includes an input gate, a forget gate, and an output gate. Each of these gates corresponds to a “standard” neuron in a feedforward (or multilayer) neural network, i.e., each gate computes a weighted sum of activations (using an activation function). Furthermore, it, ot, and ft represent the activations of the input gate, output gate, and forget gate at time step t, respectively. Exit arrows from memory cell c to gates i, o, and f represent peephole connections. Peephole connections indicate the contribution of activation of memory cell c at time step t-1, i.e., the contribution of ct-1. In other words, gates i, o, and f compute their activations at time step t (i.e., it, ot, and ft, respectively) taking into account the activation of memory cell c at time step t-1, i.e., ct-1. A single left-to-right arrow emerging from memory cell c indicates ct rather than peephole coupling, and the symbol "×" represents element-wise multiplication between inputs. Furthermore, the LSTM-based neural network 437 includes the application of differentiable functions (such as the sigmoid function) to weighted sums.

[0073] During operation, the first LSTM unit receives a partial travel path 439, sends the hidden state vector ht to the next LSTM unit, and finally to the softmax layer, thereby outputting the future elevator request probability 107.

[0074] Alternatively, in one embodiment, the processor 123 receives an elevator service request from a person via a user device and generates a set of possible future requests that congruently represent the elevator service request and the arrival time distribution. Such an embodiment is described below in Figure 5.

[0075] Figure 5 shows a schematic diagram of a building floor 500 according to some embodiments of the present disclosure. The floor 500 may include an elevator group 115, one or more conference rooms 501, one or more cubicles 505, and a toilet 507. In one embodiment, a user device may be provided in each conference room and each cubicle. For example, a user device 503 may be provided in conference room 501. The user device 503 may include a user interface for presenting elevator service requests for services provided by the elevator group 115. A person in conference room 501 may present an elevator service request via the user interface of the user device 503. Alternatively, the person may present an elevator service request via a user device such as a smartphone or laptop.

[0076] Furthermore, the processor 123 generates a set of possible future requests that congruently represent the elevator service requests received via the user device 503 and the arrival time distribution 105. The processor 123 optimizes the schedule of the elevator group 115 to correspond to the current elevator request 111 and the generated set of possible future requests. Based on the optimized schedule, the processor 123 controls the elevator group 115.

[0077] The overall method for controlling the movement of the elevator group 115 is described below in Figure 6.

[0078] Figure 6 shows a block diagram of a method 600 for controlling the movement of an elevator group 115 according to an embodiment of the present disclosure.

[0079] In block 601, method 600 includes receiving one or more current elevator requests 111 from one or more passengers. For example, one or more passengers may make a request for an elevator car (car 117a or car 117b, etc.) by pressing or touching an up button or down button associated with the elevator group 115.

[0080] In block 603, method 600 includes receiving a partial travel path (e.g., partial travel path 101) of a person moving within an environment served by the elevator group 115. In block 605, method 600 includes obtaining a future elevator request probability, for example, a future elevator request probability 107.

[0081] In block 607, method 600 includes processing partial travel paths using a neural network trained to estimate weighted combinations of probability density functions. The weighted combinations of probability density functions represent the arrival time distribution of a person arriving at the elevator via one of several paths in the environment. In one embodiment, the neural network corresponds to the NTMM207 described above in Figure 2.

[0082] In block 609, method 600 includes generating a set of possible future requests that congruently represent future elevator request probabilities and arrival time distributions. In block 611, method 600 includes optimizing the schedule of elevator group 115 to correspond to the current requests and the generated set of possible future requests.

[0083] In block 613, method 600 includes controlling the elevator group 115 according to an optimized schedule.

[0084] Figure 7 is a schematic diagram showing a computing device 700 for implementing the method 600 and control system 121 of the present disclosure. The computing device 700 includes a power supply 701, a processor 703, a memory 705, and a storage device 707, all connected to a bus 709. Furthermore, a high-speed interface 711, a low-speed interface 713, a high-speed expansion port 715, and a low-speed expansion port 717 can be connected to the bus 709. In addition, a low-speed connection port 719 is connected to the bus 709. Furthermore, an input interface 721 can be connected to an external receiver 723 and an output interface 725 via the bus 709. The receiver 727 can be connected to an external transmitter 729 and a transmitter 731 via the bus 709. An external memory 733, an external sensor 735, a machine 737, and an environment 739 can also be connected to the bus 709. Furthermore, one or more external input / output devices 741 can be connected to the bus 709. The network interface controller (NIC) 743 can be adapted to connect to network 745 via bus 709. In particular, data or other data can be rendered on third-party display devices, third-party imaging devices, and / or third-party printing devices located outside the computing device 700.

[0085] Memory 705 can store instructions that the computing device 700 can execute, as well as any data available to the methods and systems of this disclosure. Memory 705 may include random access memory (RAM), read-only memory (ROM), flash memory, or any other suitable memory system. Memory 705 may consist of one or more volatile memory units and / or one or more non-volatile memory units. Memory 705 may also be another form of computer-readable medium, such as a magnetic disk or an optical disk.

[0086] The storage device 707 can be adapted to store supplemental data and / or software modules used by the computer device 700. The storage device 707 may include a hard drive, optical drive, thumb drive, array of drives, or any combination thereof. Furthermore, the storage device 707 may include computer-readable media such as floppy disk devices, hard disk devices, optical disk devices, or tape devices, flash memory or other similar solid-state memory devices, or arrays of devices including a storage area network or other configuration. Instructions can be stored on the information carrier. When an instruction is executed by one or more processing devices (e.g., processor 703), it performs one or more of the methods described above.

[0087] The computing device 700 may optionally be linked via bus 709 to a display interface or user interface (HMI) 747 adapted to connect the computing device 700 to a display device 749 and a keyboard 751. The display device 749 may include, among other things, a computer monitor, a camera, a television, a projector, or a mobile device. In some implementations, the computer device 700 may include a printer interface for connecting to a printing device. The printing device may include, among other things, a liquid inkjet printer, a solid ink printer, a large-scale commercial printer, a thermal printer, a UV printer, or a dye-sublimation printer.

[0088] The high-speed interface 711 manages the bandwidth-intensive operation of the computing device 700, and the low-speed interface 713 manages the low-bandwidth-intensive operation. Such function assignments are merely examples. In some implementations, the high-speed interface 711 can be coupled to memory 705, user interface (HMI) 747, keyboard 751, and display 749 (e.g., through a graphics processor or accelerator), and can also be coupled to a high-speed expansion port 715 that can accept various expansion cards via bus 709. In one implementation, the low-speed interface 713 is coupled to storage device 707 and low-speed expansion port 717 via bus 709. The low-speed expansion port 717, which may include various communication ports (e.g., USB, Bluetooth®, Ethernet®, Wireless Ethernet®), may be coupled to one or more input / output devices 741. The computing device 700 may be connected to server 753 and rack server 755. The computing device 700 may be implemented in several different forms. For example, the computing device 700 may be implemented as part of a rack server 755.

[0089] The description provides only specific embodiments and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the following description of specific embodiments will provide a description that enables the realization of one or more specific embodiments for those skilled in the art. Various modifications are intended to be made to the function and configuration of the elements without departing from the spirit and scope of the subject matter disclosed in the appended claims.

[0090] Specific details are provided in the following description to ensure a full understanding of the embodiments. However, those skilled in the art will understand that the embodiments can be carried out even without these specific details. For example, systems, processes, and other elements in the disclosed subject matter may be shown as components in the form of block diagrams to avoid obscuring the embodiments with unnecessary details. In other examples, well-known processes, structures, and techniques may be shown without unnecessary details to avoid obscuring the embodiments. Furthermore, similar reference numbers and names in different drawings refer to similar elements.

[0091] Furthermore, individual embodiments may be described as processes shown as flowcharts, flow diagrams, data flow diagrams, structural diagrams, or block diagrams. While flowcharts may describe operations as sequential processes, many operations can be performed in parallel or simultaneously. In addition, the order of operations may be reordered. A process may terminate when its operations are complete, but it may have additional steps that are not discussed or included in the diagrams. Moreover, not all operations in any specifically described process can occur in all embodiments. A process may correspond to a method, function, procedure, subroutine, subprogram, etc. If a process corresponds to a function, the termination of the function may correspond to returning the function to the calling function or the main function.

[0092] Furthermore, embodiments of the disclosed subject matter may be implemented either manually or automatically, at least in part. Manual or automatic implementation may be performed, or at least assisted, through the use of a machine, hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof. If implemented with software, firmware, middleware, or microcode, the program code or code segments for performing the required tasks may be stored in a machine-readable medium. A processor(s) may perform the required tasks.

[0093] The various methods or processes outlined herein may be encoded as software executable on one or more processors employing any one of a variety of operating systems or platforms. In addition, such software may be written using any of several suitable programming languages ​​and / or programming or scripting tools, and may be compiled as executable machine language code or intermediate code that runs on a framework or virtual machine. Typically, the functions of program modules may be combined or distributed as desired in various embodiments.

[0094] Embodiments of the present disclosure may also be embodied as methods, and one example is provided. The order of operations performed as part of this method may be determined in any suitable manner. Thus, embodiments may be configured such that operations are performed in an order different from the order illustrated, which may include performing some operations simultaneously, although they are shown as a series of operations in the exemplary embodiments.

[0095] Furthermore, embodiments of the present disclosure and the functional operations described herein can be implemented in digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including structures disclosed herein and their structural equivalents, or one or more combinations thereof. Furthermore, some embodiments of the present disclosure can be implemented as one or more computer programs, i.e., as one or more modules of computer program instructions encoded on a tangible, non-temporary program carrier for execution by a data processing device or for controlling the operation of a data processing device. Furthermore, program instructions can be encoded on artificially generated propagating signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information to be transmitted to a suitable receiving device for execution by a data processing device. Computer storage media may be machine-readable storage devices, machine-readable storage boards, random or serial access memory devices, or one or more combinations thereof.

[0096] In accordance with embodiments of this disclosure, the term “data processing device” may encompass all types of devices, machines, and apparatus that process data, including, for example, a programmable processor, a computer, or multiple processors or computers. The device may include dedicated logic circuits, such as FPGAs (field-programmable gate arrays) or ASICs (application-specific integrated circuits). In addition to hardware, the device may also include code that generates the execution environment for the computer program, such as processor firmware, a protocol stack, a database management system, an operating system, or code that constitutes one or more of these.

[0097] Computer programs (sometimes called or described as programs, software, software applications, modules, software modules, scripts, or code) can be written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and can be deployed in any form, as standalone programs or as modules, components, subroutines, or other units suitable for use in a computing environment. Computer programs may or may not correspond to files in a file system. A program may be stored in part of a file that holds other programs or data, for example, one or more scripts stored in a markup language document, a single file dedicated to the program, or a coordinated set of files, for example, one or more modules, subprograms, or parts of code.

[0098] Computer programs can be deployed to run on a single computer, or on multiple computers located in one location or distributed across multiple locations and interconnected by a communication network. A computer suitable for running a computer program may, for example, be based on a general-purpose microprocessor, a dedicated microprocessor, or both, or any other type of central processing unit. Generally, the central processing unit receives instructions and data from read-only memory, random-access memory, or both. Essential elements of a computer are a central processing unit for executing or running instructions, and one or more memory devices for storing instructions and data.

[0099] Generally, a computer also includes one or more mass storage devices for storing data, such as magnetic, magneto-optical disks, or optical disks, or is operationally coupled to such disks to receive data from them, transfer data to them, or both. However, a computer does not have to have such devices. Furthermore, a computer can be embedded in another device, for example, a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device, such as a Universal Serial Bus (USB) flash drive.

[0100] To provide user interaction, embodiments of the subject matter described herein may be implemented on a computer having a display device for displaying information to the user, such as a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, and a keyboard and pointing device, such as a mouse or trackball, that allows the user to provide input to the computer. User interaction may be provided using other types of devices. For example, the feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback, and input from the user may be received in any form, including acoustic input, voice input, or tactile input. In addition, the computer may implement user interaction by sending documents to and receiving documents from a device used by the user, for example, by sending web pages to a web browser on the user's client device in response to a request received from the web browser.

[0101] Embodiments of the subject matter described herein can be implemented in a computing system including, for example, a backend component as a data server, or a computing system including a middleware component such as an application server, or a computing system including a frontend component such as a client computer having a graphical user interface or a web browser that allows a user to interact with an implementation of the subject matter described herein, or a computing system including any combination of one or more such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication, such as a communication network. Examples of communication networks include local area networks ("LANs") and wide area networks ("WANs"), such as the Internet.

[0102] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically communicate through a communication network. The client-server relationship arises from computer programs running on each computer that have a client-server relationship.

[0103] While this disclosure has been described using several preferred embodiments, it should be understood that various other adaptations and modifications can be carried out within the spirit and scope of this disclosure. Therefore, it is the aspect of the following claims to cover all such variations and modifications that fall within the true spirit and scope of this disclosure.

Claims

1. A control system for controlling the movement of a group of elevators, At least one processor, It comprises memory in which instructions are stored, The instruction is given to at least one processor of the control system, The elevator group receives one or more current elevator requests for its services. The elevators allow the system to receive partial movement paths of people moving within the environment provided by the aforementioned group of elevators. Obtain the future elevator request probability, The partial travel paths are processed using a neural network trained to estimate weighted combinations of probability density functions. The weighted combination of the aforementioned probability density functions represents the arrival time distribution of the person arriving at the elevator group via one of several paths within the environment. The instruction further causes the at least one processor of the control system to: A set of possible future requests is generated that congruently represents the aforementioned future elevator request probability and the aforementioned arrival time distribution. The schedule of the group of elevators is optimized to correspond to one or more current elevator requests and a set of possible future requests. A control system that controls the group of elevators according to the aforementioned schedule.

2. The control system according to claim 1, wherein the neural network is a Neural Travel-time Mixture Model (NTMM).

3. The control system according to claim 2, wherein the NTMM is trained on a dataset including the coordinates of a starting point and a destination, and the duration of travel paths corresponding to different people.

4. The control system according to claim 3, wherein the duration of the aforementioned travel path corresponds to the same person at different times.

5. The control system according to claim 3, wherein the processor is further configured to retrain the NTMM based on a new dataset including updated movement path durations corresponding to different individuals.

6. The control system according to claim 1, wherein the processor is further configured to process the partial travel path using a transformer architecture-based neural network in order to obtain the future elevator request probability.

7. The control system according to claim 1, wherein the processor is further configured to process the partial travel path using a recurrent neural network (RNN) in order to obtain the future elevator request probability.

8. The aforementioned processor further, The elevator service request is received from the person via the user device. The control system according to claim 1, configured to generate a set of possible future requests that congruently represent the elevator service requests and the arrival time distribution.

9. A method for controlling the movement of a group of elevators, wherein the method is The steps include receiving one or more current elevator requests for services provided by the group of elevators, A step of receiving a partial movement path of a person moving within the environment served by the aforementioned group of elevators, Steps to obtain future elevator request probabilities, The process includes the step of processing the partial travel path using a neural network trained to estimate weighted combinations of probability density functions, The weighted combination of the aforementioned probability density functions represents the arrival time distribution of the person arriving at the elevator group via one of several paths within the environment. The above method further, A step of generating a set of possible future requests that congruently represent the aforementioned future elevator request probabilities and the aforementioned arrival time distribution, The steps include optimizing the schedule of the group of elevators to correspond to one or more current elevator requests and a set of possible future requests, A method comprising the step of controlling the group of elevators in accordance with the schedule.

10. The method according to claim 9, wherein the neural network is a neural transit time mixed model (NTMM).

11. The method according to claim 10, wherein the NTMM is trained on a dataset including the coordinates of a starting point and a destination, and the duration of travel paths corresponding to different people.

12. The method according to claim 11, wherein the duration of the travel path corresponds to the same person at different times.

13. The method according to claim 11, further comprising the step of retraining the NTMM based on a new dataset including updated travel path durations corresponding to different individuals.

14. The method according to claim 9, wherein the method further includes the step of processing the partial travel path using a transformer architecture-based neural network in order to obtain the future elevator request probability.

15. The method according to claim 9, wherein the method further includes the step of processing the partial travel path using a recurrent neural network (RNN) in order to obtain the future elevator request probability.

16. The above method further, The steps include receiving an elevator service request from the person via a user device, The method according to claim 9, comprising the step of generating a set of possible future requests that congruently represent the elevator service requests and the arrival time distribution.

17. A non-temporary computer-readable storage medium containing a processor-executable program for performing a method for controlling the movement of a group of elevators, wherein the method is The steps include receiving one or more current elevator requests from one or more passengers for the service provided by the group of elevators, A step of receiving a partial movement path of a person moving within the environment served by the aforementioned group of elevators, Steps to obtain future elevator request probabilities, The process includes the step of processing the partial travel path using a neural network trained to estimate weighted combinations of probability density functions, The weighted combination of the aforementioned probability density functions represents the arrival time distribution of the person arriving at the elevator group via one of several paths within the environment. The above method further, A step of generating a set of possible future requests that congruently represent the aforementioned future elevator request probabilities and the aforementioned arrival time distribution, The steps include optimizing the schedule of the group of elevators to correspond to one or more current elevator requests and a set of possible future requests, A non-temporary computer-readable storage medium, comprising the step of controlling the group of elevators according to the schedule described above.

18. The non-temporary computer-readable storage medium according to claim 17, wherein the neural network is a neural transit time mixed model (NTMM).

19. The non-temporary computer-readable storage medium according to claim 17, wherein the NTMM is trained on a dataset including the coordinates of a starting point and a destination, and the duration of travel paths corresponding to different people.

20. The method further comprises the step of retraining the NTMM based on a new dataset including the duration of updated travel paths corresponding to different persons, for a non-temporary computer-readable storage medium according to claim 19.

Images