A method, apparatus, electronic device, and storage medium for target layer registration.

Abstract

This application discloses a method, apparatus, electronic device, and storage medium for destination floor registration. The method is applied to a destination floor registration system connected to an elevator control system. The destination floor registration system includes monitoring equipment installed in the elevator lobby. The method includes: determining registered passengers and passengers to be registered based on monitoring video collected by the monitoring equipment, wherein the registered passengers have associated destination floor information, and the monitoring video includes the registration behavior of each passenger; obtaining the associated destination floor information of the registered passengers to form a destination floor list; determining the credibility of each passenger to be registered with each destination floor information in the destination floor list; and using the destination floor information with the highest credibility as the predicted destination floor information of the passenger to be registered, which can match the number of registered passengers with the number of passengers waiting for the elevator, so that the elevator control system can more rationally schedule the elevator based on the number of registered passengers.

Description

Technical Field

[0001] This application relates to the field of elevator data analysis technology, and in particular to a method for destination floor registration, a device for destination floor registration, an electronic device, and a computer-readable storage medium. Background Technology

[0002] Currently, there are various elevator destination floor registration products on the market, most of which require passengers to actively register, such as through IC cards, ID cards, facial recognition, and other authentication information linked to the destination floor. However, some passengers may not register because their desired floor has already been registered by other passengers, leading to a discrepancy between the number of registered passengers and the actual number of passengers using the elevator. This affects the efficiency of elevator dispatching and passengers' waiting time. For example, if 12 passengers are waiting for the elevator in the waiting hall, with 6 passengers aiming for the 3rd floor and 6 passengers aiming for the 4th floor, but only 1 passenger registers for the 3rd floor and 1 passenger registers for the 4th floor, the elevator system will receive registration information indicating 2 people using the elevator, thus only calling one elevator and failing to meet the needs of all passengers.

[0003] Other related technologies can use video scanning to collect the facial features of everyone in the waiting hall and automatically register the destination floor by linking the facial features to the parent floor. However, this requires obtaining passengers' facial features, which raises privacy concerns and is not suitable for most environments. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for destination floor registration, in order to solve the problem of elevator scheduling being affected by discrepancies between registered data and actual number of passengers when registering elevators in related technologies.

[0005] According to a first aspect of this application, a method for destination floor registration is provided, the method being applied to a destination floor registration system connected to an elevator control system, the destination floor registration system including monitoring equipment installed in the elevator lobby, the method comprising:

[0006] Based on the surveillance video collected by the monitoring equipment, registered passengers and passengers to be registered are identified. The registered passengers have associated destination layer information, and the surveillance video includes the behavior of each passenger registering their destination layer.

[0007] Obtain the destination layer information associated with the registered passengers and form a destination layer list;

[0008] For each passenger to be registered, determine the credibility of the passenger to be registered with the destination layer information in the destination layer list;

[0009] The destination layer information with the highest credibility will be used as the predicted destination layer information for the passengers to be registered.

[0010] According to a second aspect of this application, a destination floor registration device is provided, the device being disposed in a destination floor registration system connected to an elevator control system, the destination floor registration system including monitoring equipment disposed in the elevator lobby, the device comprising:

[0011] The registration and identification module is used to determine registered passengers and passengers to be registered based on the monitoring video collected by the monitoring equipment. The registered passengers have associated destination layer information, and the monitoring video includes the behavior of each passenger at the registration destination layer.

[0012] The destination layer list acquisition module is used to acquire the destination layer information associated with the registered passengers and form a destination layer list.

[0013] The credibility determination module is used to determine the credibility of each passenger to be registered with each destination layer information in the destination layer list for each passenger to be registered;

[0014] The destination layer prediction module is used to select the destination layer information with the highest confidence level as the predicted destination layer information for the passenger to be registered.

[0015] According to a third aspect of this application, an electronic device is provided, the electronic device comprising a light curtain transmitter and a light curtain receiver, the light curtain receiver comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0019] According to a fourth aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method described in the first aspect above.

[0020] In this embodiment, by supplementing the registration of passengers who have not registered for their destination floor, the number of people registering for their destination floor can be matched with the number of people waiting for the elevator. This allows the elevator control system to schedule the elevator more rationally based on the number of registered passengers, thereby improving the efficiency of elevator scheduling and reducing passengers' waiting time.

[0021] During destination layer registration, surveillance video is captured by monitoring equipment installed in the elevator lobby to obtain passenger registration information, thus distinguishing passengers into registered passengers and those awaiting registration. Then, based on the list of registered destination layers, the credibility of each passenger awaiting registration with the information of each destination layer in the list is calculated. Finally, based on this credibility, the predicted destination layer information for each passenger awaiting registration is determined. The entire process does not specifically identify the physical features of each passenger, and the accuracy requirements for video recognition are not high, thereby reducing system costs. Furthermore, by not actively identifying and storing passengers' physical features, the risk of personal privacy leakage can be avoided, making it applicable to most environments.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for target layer registration provided in Embodiment 1 of this application;

[0025] Figure 2 This is a schematic diagram of the communication architecture between a registration system and a destination-level supplementary registration system provided in Embodiment 1 of this application;

[0026] Figure 3 This is a flowchart of a method for determining the credibility of passengers to be registered and information of each destination layer in the destination layer list, provided in Embodiment 1 of this application;

[0027] Figure 4 This is a schematic diagram of a passenger entering an elevator lobby provided in Embodiment 1 of this application;

[0028] Figure 5 This is a schematic diagram of a passenger stopping and waiting for the elevator in the elevator lobby, as provided in Embodiment 1 of this application;

[0029] Figure 6 This is a schematic diagram of another passenger entering the elevator lobby provided in Embodiment 1 of this application;

[0030] Figure 7 This is another schematic diagram of a passenger stopping and waiting for the elevator in the waiting hall, as provided in Embodiment 1 of this application;

[0031] Figure 8 This is a schematic diagram of the structure of a target layer registration device provided in Embodiment 2 of this application;

[0032] Figure 9 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of this application. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0035] Example 1

[0036] Figure 1 This is a flowchart illustrating a method for destination floor registration according to Embodiment 1 of this application. The method is applied to a destination floor registration system connected to the elevator control system. The destination floor registration system includes monitoring equipment installed in the elevator lobby, for example... Figure 2 As shown, the monitoring device may include a camera. This monitoring device can monitor the entire waiting hall and the scene of passengers entering the destination floor registration device to register for their destination floor. In addition, the destination floor registration system may also include a processing unit connected to the monitoring device, which is used to perform the various steps of the following embodiments.

[0037] like Figure 1 As shown, this embodiment may include the following steps:

[0038] Step 101: Based on the surveillance video collected by the monitoring equipment, identify registered passengers and passengers to be registered, wherein the registered passengers have associated destination layer information.

[0039] In elevator environments equipped with destination floor registration devices, some passengers will proactively register their destination floor, while others will not register because their destination floor is the same as their registered floor, and will instead follow the registered passengers onto the elevator. This step can identify registered passengers and passengers waiting to register by analyzing surveillance images.

[0040] Among them, registered passengers are those who actively register at the destination layer registration device, and therefore have associated destination layer information; while unregistered passengers are those who have not registered at the destination layer registration device, and therefore do not have associated destination layer information.

[0041] In this embodiment, the surveillance video includes the behavior of each passenger registration destination layer. This embodiment can determine the behavior of each passenger registration destination layer by performing image analysis on the surveillance video collected by the monitoring equipment, thereby identifying registered passengers and passengers to be registered. In one embodiment, step 101 may further include the following steps:

[0042] Step 101-1: Identify passenger objects from the surveillance video collected by the monitoring equipment and assign a unique identifier to each passenger object.

[0043] In one implementation, a pre-generated object detection algorithm can be used to detect objects in the surveillance video captured by the monitoring equipment, thereby identifying human objects from each video frame as passenger objects. Then, a unique identifier is assigned to each identified passenger object in real time to distinguish between them.

[0044] Step 101-2: When a passenger is detected performing a destination layer registration operation at the destination layer registration device, the destination layer information of the passenger is obtained from the destination layer registration device, and the destination layer information is associated with the unique identifier of the passenger, and the passenger is registered as a passenger.

[0045] In implementation, the destination floor registration device is also connected to the elevator's control system. This control system enables information exchange between the destination floor registration device and the destination floor supplementary registration system, for example... Figure 2 As shown, the destination floor registration device is located in the registration system and is connected to the server of the registration system. The destination floor registration device sends the registration data to the server, and then the server sends the registration data to the elevator control system. Then the processing unit of the destination floor registration system obtains the corresponding registration data from the control system.

[0046] In this step, when a passenger registers at the destination level registration device, the device sends the passenger's destination level information to the control system. Simultaneously, the destination level registration system, through monitoring equipment, detects a passenger approaching the registration device and registering. It then obtains real-time destination level information from the control system and binds this information to the passenger's unique identifier, marking the passenger as a registered passenger.

[0047] Step 101-3: Passenger objects that do not have associated destination layer information are designated as passengers to be registered.

[0048] If a passenger fails to complete the destination layer registration operation at the destination layer registration device, the passenger can be marked as a passenger awaiting registration.

[0049] Step 102: Obtain the destination layer information associated with the registered passengers and form a destination layer list.

[0050] In one implementation, the destination layer information associated with all registered passengers can be organized to generate a destination layer list. In this way, the destination layer supplementary registration system can know which destination layers the current waiting crowd needs to reach, so as to facilitate the supplementary registration of destination layers for passengers waiting to be registered.

[0051] Step 103: For each passenger to be registered, determine the credibility of the passenger to be registered and the destination layer information in the destination layer list.

[0052] Step 104: Use the destination layer information with the highest credibility as the predicted destination layer information for the passenger to be registered.

[0053] In this step, for each passenger to be registered, the credibility of that passenger relative to each destination layer in the destination layer list can be calculated according to the set credibility calculation logic. This credibility indicates which destination layer the passenger is more likely to reach. Finally, the destination layer with the highest credibility can be used as the predicted destination layer for the passenger to be registered.

[0054] Once the predicted destination floor information of the passengers to be registered is obtained, the predicted destination floor information and the passenger's unique identifier can be sent to the control system so that the control system can obtain the number of registered passengers that matches the actual number of passengers waiting in the elevator lobby, thereby enabling better elevator scheduling.

[0055] In this embodiment, by supplementing the registration of passengers who have not registered for their destination floor, the elevator control system can be provided with more accurate passenger data, so that the number of people registered for their destination floor matches the number of people waiting for the elevator. This allows the elevator control system to schedule the elevator more rationally based on the number of registered passengers, thereby improving the efficiency of elevator scheduling and reducing passengers' waiting time.

[0056] During destination layer registration, surveillance video is captured by monitoring equipment installed in the elevator lobby to obtain passenger registration information, thus distinguishing passengers into registered passengers and those awaiting registration. Then, based on the list of registered destination layers, the credibility of each passenger awaiting registration with the information of each destination layer in the list is calculated. Finally, based on this credibility, the predicted destination layer information for each passenger awaiting registration is determined. The entire process does not specifically identify the physical features of each passenger, and the accuracy requirements for video recognition are not high, thereby reducing system costs. Furthermore, by not actively identifying and storing passengers' physical features, the risk of personal privacy leakage can be avoided, making it applicable to most environments.

[0057] In one embodiment, unregistered passengers can be registered based on passenger movement in the waiting area. (See reference) Figure 3 As shown, step 103 may further include the following steps:

[0058] Step 103-1: Determine the synchronization reliability, aggregation reliability, and time reliability of the current passenger to be registered and the destination layer information in the destination layer list.

[0059] In this embodiment, the reliability can include synchronization reliability, aggregation reliability, and temporal reliability. Synchronization reliability reflects the influence of the distance between the passenger to be registered and other registered passengers during the passenger's movement in the waiting hall on determining their destination floor information. Aggregation reliability reflects the influence of the distance between the passenger to be registered and other registered passengers when the passenger stops moving in the waiting hall on determining their destination floor information. Temporal reliability reflects the influence of time on the destination floor information of each registered passenger.

[0060] In one embodiment, from the moment a passenger enters the video surveillance range until they stop moving in the elevator lobby, the synchronization between their movement and that of other actively registered passengers will affect the synchronization reliability. The calculation logic for synchronization reliability may include the following steps:

[0061] Step S11: Obtain the list of registered passengers corresponding to each destination layer.

[0062] It should be noted that after entering the elevator lobby, users first pass through the destination floor registration device before proceeding to the waiting areas for each elevator. Therefore, when a passenger passes through the destination floor registration device, their registration behavior at the device can be used to identify in real time whether they are a registered passenger or a passenger awaiting registration. In other words, once a passenger passes through the destination floor registration device, it can be determined whether they are a registered passenger or a passenger awaiting registration.

[0063] For registered passengers, the destination information can be used to divide the passengers into different destinations to generate a list of registered passengers for each destination. For example, if there are two destinations: the 3rd floor and the 4th floor, and user A registered for the 3rd floor, user B registered for the 4th floor, user C registered for the 3rd floor, and user D registered for the 4th floor, then the list of registered passengers for the 3rd floor includes user A and user C, and the list of registered passengers for the 4th floor includes user B and user D.

[0064] Step S12: After the passengers to be registered enter the waiting hall, each passenger to be registered is tracked to obtain the first distance between the passenger to be registered and each registered passenger in the list of registered passengers on each destination floor.

[0065] In implementation, by analyzing surveillance video, each passenger awaiting registration can be tracked. Once a passenger enters the waiting hall, the image distance between them and each registered passenger can be continuously tracked. This image distance is then converted into physical distance, which serves as the first distance between the passenger awaiting registration and the registered passengers. Therefore, for a list of registered passengers on the same destination floor, the distance between the passenger awaiting registration and each registered passenger in that list can be obtained.

[0066] Step S13: Determine the first average distance between the passenger to be registered and each destination floor based on the first distance.

[0067] Specifically, each time the distance between the current passenger to be registered and each registered passenger in the current passenger list is obtained, it is recorded. When the current passenger to be registered stops moving, the first average distance between the current passenger to be registered and the current passenger list can be calculated according to the recorded distance and the number of records in the current passenger list, based on the average calculation formula. This first average distance between the current passenger to be registered and the destination layer corresponding to the current passenger list is used as the first average distance between the current passenger to be registered and the current passenger list.

[0068] Step S14: Compare the first average distance with a plurality of first distance thresholds preset by the target layer to determine the synchronization reliability corresponding to the first average distance.

[0069] In implementation, multiple first distance thresholds and corresponding synchronization reliability can be preset. For example, when d同步 >2m, then α 同步 =0; when 2m≥d 同步 ≥0.5m, then When d 同步 If α < 0.5m, then 同步 =1; where d 同步 Let α be the first average distance. 同步 To ensure synchronization reliability, d 同步 The smaller α 同步 The larger.

[0070] For example, such as Figure 4 As shown, passenger #1 appeared together with passengers #2, #3, and #4 within a short period of time and were close to each other. Passenger #1 voluntarily registered for the 3rd floor, so passengers #2, #3, and #4 then registered for the 3rd floor (α). 同步 high.

[0071] In one embodiment, the distance between the passenger to be registered and the already registered passengers after the passenger stops moving affects the aggregation credibility α. 聚集 The logic for calculating clustered credibility may include the following steps:

[0072] Step S21: Obtain the list of registered passengers corresponding to each destination layer.

[0073] Step S22: After the passenger to be registered stops moving in the waiting hall, obtain the second distance between the passenger to be registered and each registered passenger in the list of registered passengers on each destination floor.

[0074] In implementation, by analyzing surveillance video, each passenger awaiting registration can be tracked. Once a passenger stops moving in the waiting hall, the image distance between them and each registered passenger who has stopped moving can be calculated. This image distance is then converted into physical distance, serving as a second distance between the passenger awaiting registration and the registered passengers. Therefore, for a list of registered passengers on the same destination floor, the second distance between the passenger awaiting registration and each registered passenger in that list can be obtained.

[0075] Step S23: Based on the second distance, determine the second average distance between the passenger to be registered and each registered passenger in the list of registered passengers for each destination layer, and use it as the second average distance for that destination layer.

[0076] Specifically, the second distance between the current passenger to be registered and each registered passenger in the current registered passenger list can be recorded. Then, based on the recorded second distances and the number of records corresponding to the current registered passenger list, the second average distance between the current passenger to be registered and the current registered passenger list can be calculated according to the average calculation formula, which serves as the second average distance between the current passenger to be registered and the destination layer corresponding to the current registered passenger list.

[0077] Step S24: Compare the second average distance with a plurality of second distance thresholds preset by the target layer to determine the aggregation confidence corresponding to the second average distance.

[0078] In implementation, multiple second distance thresholds and corresponding synchronization reliability can be preset. For example, when d 聚集 >2m, then α 聚集 =0; when 2m≥d 聚集 ≥0.5m, then When d 聚集 If α < 0.5m, then 聚集 =1; where d 聚集 For the second average distance, α 聚集 To aggregate credibility, d 聚集 The smaller α 聚集 The larger.

[0079] For example, such as Figure 5 As shown, passenger #1 has already registered their destination floor as the 6th floor. Passengers #2, #3, and #4 approach passenger #1 and stop moving. Therefore, passengers #2, #3, and #4 will then register for floor 6, floor α. 聚集 high.

[0080] In one embodiment, the destination floor registration system pre-sets a defined time period and a corresponding high-confidence floor. When a passenger is registered on a high-confidence floor within the defined time period, the system determines the time confidence α. 时间 High. The calculation logic for time reliability may include the following steps:

[0081] Step S31: Obtain the set high confidence level floors for the set time period.

[0082] For example, assuming the 4th floor is the cafeteria and lunchtime is from 12:00 to 13:00, then the 4th floor is a high-confidence floor during the time period from 12:00 to 13:00.

[0083] Step S32: If the target layer is a high-confidence layer within the set time period, then set the time confidence level of the target layer to a first value.

[0084] Step S33: If the target layer is a high-confidence layer but not within the set time period, or if it is within the set time period but the target layer is not a high-confidence layer, or if the target layer is neither a high-confidence layer nor within the set time period, then the time confidence of the target layer is set to a second value, wherein the second value is less than the first value.

[0085] For example, the first value can be 0.8, and the second value can be 0. In the example above, when the time is between 12:00 and 13:00, the time confidence of the target floor (4th floor) is 0.8, and the time confidence of other floors is 0. Outside of 12:00 and 13:00, the time confidence of all floors is 0.

[0086] Step 103-2: Determine the weights corresponding to the synchronization credibility, the aggregation credibility, and the time credibility, respectively.

[0087] In this step, corresponding weights can be pre-set for synchronization credibility, aggregation credibility, and time credibility. To match the needs of building and floor characteristics, the weights of synchronization credibility, aggregation credibility, and time credibility can also have different emphases. For example, in an office building scenario, the weight k of synchronization credibility... 同步 The weight k of the cluster credibility 聚集 and the weight k of time credibility 时间 The size relationship can be k 同步 >k 聚集 >k 时间 In the context of residential buildings, the relationship between the three can be k. 聚集 >k 时间 >k 同步 .

[0088] For example, the weight k of synchronization reliability. 同步 The weight k of the cluster credibility 聚集 and the weight k of time credibility 时间 They can be configured as: k 同步 =0.9, k 聚集 =0.85, k 时间 =0.8.

[0089] Step 103-3: Based on the weights, perform a weighted summation of the synchronization credibility, the aggregation credibility, and the time credibility to obtain the credibility of the passenger to be registered for the destination layer information.

[0090] When a passenger waiting to register enters the monitored area of ​​the waiting hall, the destination floor registration system begins to record the movement. Once the passenger moves to the waiting hall and stops moving, a credibility calculation is performed. By weighted summing of synchronization credibility, aggregation credibility, and time credibility, the credibility of the current passenger waiting to register for the destination floor information can be obtained.

[0091] That is, the credibility of a passenger awaiting registration for a certain destination layer = α 同步 *k 同步 +α 聚集 *k 聚集 +α 时间 *k 时间

[0092] It should be noted that after obtaining the credibility of the current passenger to be registered and each destination layer, the destination layer with the highest credibility is selected as the supplementary registration destination layer for that passenger. If there is more than one maximum credibility value, then for the destination layer corresponding to the maximum credibility value, the floor with the higher weight can be selected as the destination layer based on building characteristics or floor characteristics.

[0093] In one embodiment, the following steps may also be included:

[0094] Obtain the actual destination layer information of each passenger to be registered; compare the actual destination layer information of the same passenger with the predicted destination layer information; and adjust the weights according to the comparison results using a set correction algorithm.

[0095] Specifically, cameras inside the elevator car can track the actual destination floor information of each passenger waiting to register. Then, based on the actual destination floor information and the corresponding predicted destination floor information, a set dynamic correction algorithm (such as the PID algorithm, where PID stands for "proportional, integral, and derivative," a common "stability-maintaining" control algorithm) is used to correct k. 同步 k 聚集 and k 时间 This is to improve the accuracy of the target layer prediction. This embodiment does not limit the dynamic correction algorithm.

[0096] To enable those skilled in the art to better understand the embodiments of this application, the following specific example is provided:

[0097] In an office building elevator dispatching application scenario, assume the 4th floor is a cafeteria, and lunchtime is from 12:00 to 13:00. Based on the site environment, let k... 同步 =0.9, k 聚集 =0.85, k 时间 =0.8, and the confidence parameters are set as follows:

[0098] A. The first average distance between passengers waiting to register and those already registered when entering the waiting hall is d. 同步 When d 同步 When >2m, α 同步 =0; when 2m≥d 同步 When ≥0.5m, When d 同步 When <0.5m, α 同步 =1.

[0099] B. After the passenger waiting to register stops moving in the waiting hall, the second average distance between the passenger waiting to register and the registered passenger when entering the waiting hall is d. 聚集 When d 聚集 When >2m, α 聚集 =0; when 2m≥d 聚集 When ≥0.5m, When d 聚集 When <0.5m, α 聚集 =1.

[0100] C. When the time is between 12:00 and 13:00, the credibility of the target floor being the 4th floor is α. 时间 =0.8, otherwise α 时间 =0.

[0101] At 1:10 PM, six passengers entered the elevator waiting area as follows: Figure 6 As shown, the six elevator stops moving after entering the waiting hall. Figure 7 As shown.

[0102] Through analysis of surveillance video and floor registration synchronization information, passenger #1 proactively registered their destination as floor 4, and passenger #5 proactively registered their destination as floor 3.

[0103] Credibility analysis is as follows:

[0104] For passenger #2, upon entering the elevator lobby, the first average distance between #2 and #1 was 0.5m, and the first average distance between #2 and #5 was greater than 2m; after stopping, the second average distance between #2 and #1 was 0.5m, and the second average distance between #2 and #5 was greater than 2m. Therefore... α 同步-3楼 =0; α 聚集-3楼 =0; α 时间-4楼 =0.8; therefore, the confidence level of passenger #2's destination floor being the 4th floor is: α 同步-4楼 ×k 同步 +α 聚集-4楼 ×k 聚集 +α 时间-4楼 ×k 时间=1×0.9+1×0.85+0.8×0.8=2.39, the confidence level of passenger #2's destination floor being the 3rd floor is 0, so the predicted destination floor for passenger #2 is the 4th floor.

[0105] For passenger #3, upon entering the elevator lobby, the first average distance between #3 and #1 was 0.5m, and the first average distance between #3 and #5 was 1.5m; after stopping, the second average distance between #3 and #1 was 0.5m, and the second average distance between #3 and #5 was 1.5m. α 时间-4楼 =0.8; therefore, the confidence level of passenger #3's destination floor being the 4th floor is: α 同步-4楼 ×k 同步 +α 聚集-4楼 ×k 聚集 +α 时间-4楼 ×k 时间 =1×0.9+1×0.85+0.8×0.8=2.39, the confidence level of passenger #3's destination floor being the 3rd floor is: α 同步-3楼 ×k 同步 +α 聚集-3楼 ×k 聚集 +α 时间-3楼 ×k 时间 =0.33×0.9+0.33×0.85+0×0.8=0.5775, so the predicted destination floor for passenger #3 to board is the 4th floor.

[0106] For passenger #4, upon entering the elevator lobby, the first average distance between #4 and #1 was 1.5m, and the first average distance between #4 and #5 was 1.5m; after stopping, the second average distance between #4 and #1 was 2m, and the second average distance between #4 and #5 was 0.5m. α 时间-4楼 =0.8; therefore, the confidence level of predicting passenger #4's destination floor as the 4th floor is: α 同步-4楼 ×k 同步 +α 聚集-4楼 ×k 聚集 +α 时间-4楼 ×k 时间 =0.33×0.9+0×0.85+0.8×0.8=0.937, the confidence level of passenger #4 predicting the destination floor as the 3rd floor is: α 同步-3楼 ×k 同步 +α 聚集-3楼 ×k 聚集 +α 时间-3楼 ×k 时间 =0.33×0.9+1×0.85+0×0.8=1.147, so passenger #4 should board to the destination floor 3.

[0107] For passenger #6: Upon entering the elevator lobby, the defined average distance between #6 and #1 is greater than 2m, and the first average distance between #6 and #5 is greater than 2m; after stopping, the second average distance between #6 and #1 is greater than 2m, and the second average distance between #6 and #5 is greater than 2m. Therefore, α is obtained. 同步-4楼 =0, α 同步-3楼 =0; α 聚集-4楼 =0, α 聚集-3楼 =0; α 时间-4楼 =0.8; therefore, the confidence level of passenger #6's destination floor being the 4th floor is: α 同步-4楼 ×k 同步 +α 聚集-4楼 ×k 聚集 +α 时间-4楼 ×k 时间 =0×0.9+0×0.85+0.8×0.8=0.64, the confidence level of passenger #6 being the 3rd floor is: α 同步-3楼 ×k 同步 +α 聚集-3楼 ×k 聚集 +α 时间-3楼 ×k 时间 =0×0.9+0×0.85+0×0.8=0, so passenger #6 should board to the 4th floor.

[0108] Example 2

[0109] Figure 8 This is a schematic diagram of a destination floor registration device provided in Embodiment 2 of this application. The device can be installed in a destination floor registration system, which is connected to the elevator control system. The destination floor registration system includes monitoring equipment installed in the elevator lobby. The device may include the following modules:

[0110] The registration and identification module 201 is used to determine registered passengers and passengers to be registered based on the monitoring video collected by the monitoring equipment. The registered passengers have associated destination layer information, and the monitoring video includes the behavior of each passenger registering the destination layer.

[0111] The destination layer list acquisition module 202 is used to acquire the destination layer information associated with the registered passengers and form a destination layer list.

[0112] The credibility determination module 203 is used to determine the credibility of each passenger to be registered with each destination layer information in the destination layer list for each passenger to be registered;

[0113] The destination layer prediction module 204 is used to use the destination layer information with the highest confidence level as the predicted destination layer information of the passenger to be registered.

[0114] In one embodiment, the registration and identification module 201 is specifically used for:

[0115] The passenger is identified from the surveillance video collected by the monitoring equipment, and a unique identifier is assigned to the passenger.

[0116] When a passenger is detected performing a destination layer registration operation at the destination layer registration device, the destination layer information of the passenger is obtained from the destination layer registration device, the destination layer information is associated with the unique identifier of the passenger, and the passenger is registered as a passenger.

[0117] Passenger objects that do not have associated destination layer information are treated as passengers to be registered.

[0118] In one embodiment, the confidence determination module 203 is specifically used for:

[0119] Determine the synchronization reliability, aggregation reliability, and temporal reliability of the current passengers to be registered and the destination layer information in the destination layer list;

[0120] Determine the weights corresponding to the synchronization credibility, the aggregation credibility, and the time credibility, respectively.

[0121] Based on the weights, the synchronization credibility, the aggregation credibility, and the time credibility are weighted and summed to obtain the credibility of the passenger to be registered for the destination layer information.

[0122] In one embodiment, the credibility determination module 203 may include a synchronous credibility determination module, used for:

[0123] Retrieve the list of registered passengers for each destination level;

[0124] After the passengers to be registered enter the waiting hall, each passenger to be registered is tracked to obtain the first distance between the passenger to be registered and each registered passenger in the list of registered passengers on each destination floor;

[0125] Based on the first distance, determine the first average distance between the passenger to be registered and each destination floor;

[0126] The synchronization reliability corresponding to the first average distance is determined by comparing the first average distance with a plurality of first distance thresholds preset by the target layer.

[0127] In one embodiment, the credibility determination module 203 may include an aggregation credibility determination module, used for:

[0128] Retrieve the list of registered passengers for each destination level;

[0129] After the passenger to be registered stops moving in the waiting hall, obtain the second distance between the passenger to be registered and each registered passenger in the list of registered passengers on each destination floor;

[0130] Based on the second distance, determine the second average distance between the passenger to be registered and each registered passenger in the list of registered passengers for each destination layer, and use it as the second average distance for that destination layer;

[0131] The aggregation confidence level corresponding to the second average distance is determined by comparing the second average distance with a plurality of second distance thresholds preset by the target layer.

[0132] In one embodiment, the credibility determination module 203 may include a time credibility determination module, used for:

[0133] Retrieve a set high-confidence floor within a specified time period;

[0134] If the target layer is a high-confidence layer within the set time period, then the time confidence level of the target layer is set to the first value.

[0135] If the target layer is a high-confidence layer but is not within the set time period, or if it is within the set time period but the target layer is not a high-confidence layer, or if the target layer is neither a high-confidence layer nor within the set time period, then the time confidence of the target layer is set to a second value, wherein the second value is less than the first value.

[0136] In one embodiment, the device may further include the following modules:

[0137] The actual destination layer acquisition module is used to acquire the actual destination layer information of each passenger to be registered;

[0138] The comparison module is used to compare the actual destination layer information of the same passenger with the predicted destination layer information;

[0139] The weight correction module is used to correct the weights according to the comparison results using a set correction algorithm.

[0140] The target layer registration apparatus provided in this application embodiment can execute the target layer registration method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of executing the method.

[0141] Example 3

[0142] Figure 9A schematic diagram of the structure of an electronic device 10 that can be used to implement embodiments of the methods of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.

[0143] like Figure 9 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0144] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0145] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method described in Embodiment 1.

[0146] In some embodiments, the method described in Embodiment 1 may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method described in Embodiment 1 above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method described in Embodiment 1 by any other suitable means (e.g., by means of firmware).

[0147] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0148] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0149] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0150] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0151] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0152] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0153] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0154] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method of destination layer registration, characterized by, The method is applied to a destination layer supplement system connected with a control system of an elevator, the destination layer supplement system comprises a monitoring device arranged in a waiting hall, and the method comprises: According to the monitoring video collected by the monitoring device, determining registered passengers and passengers to be registered, the registered passengers have associated destination layer information, and the monitoring video comprises the behavior of each passenger registering a destination layer; Obtaining the destination layer information associated with the registered passengers to form a destination layer list; For each passenger to be registered, determining the credibility of the passenger to be registered and each destination layer information in the destination layer list; The destination layer information with the highest credibility is taken as the predicted destination layer information of the passenger to be registered, so that the number of passengers registered for the destination layer is matched with the number of passengers in the waiting hall, and then the control system of the elevator is dispatched according to the number of registered passengers; According to the monitoring video collected by the monitoring device, the registered passengers and the passengers to be registered are determined, which comprises: Through a target detection algorithm generated in advance, the monitoring video collected by the monitoring device is subjected to target detection, so as to identify a human object from each video frame, take the human object as a passenger object, and assign a unique identifier to the passenger object in real time to distinguish each passenger object; When it is detected that a passenger object performs a destination layer registration operation at a destination layer registration device, the registered destination layer information of the passenger object is obtained from the destination layer registration device, the destination layer information is associated with the unique identifier of the passenger object, and the passenger object is taken as a registered passenger; The passenger object without associated destination layer information is taken as a passenger to be registered; The credibility of the passenger to be registered and each destination layer information in the destination layer list is determined, which comprises: The synchronous credibility, the aggregation credibility and the time credibility of the current passenger to be registered and each destination layer information in the destination layer list are determined; The weights corresponding to the synchronous credibility, the aggregation credibility and the time credibility are respectively determined; Based on the weights, the synchronous credibility, the aggregation credibility and the time credibility are weighted and summed to obtain the credibility of the passenger to be registered to the destination layer information; The method further comprises: Obtaining the actual destination layer information of each passenger to be registered; Comparing the actual destination layer information of the same passenger with the predicted destination layer information; According to the comparison result, a set correction algorithm is used to correct the weights.

2. The method of claim 1, wherein, The synchronous credibility of the passenger to be registered and each destination layer in the destination layer list is obtained in the following way: Obtaining the registered passenger list corresponding to each destination layer; When the passenger to be registered enters the waiting hall, each passenger to be registered is tracked to obtain the first distance between the passenger to be registered and each registered passenger in the registered passenger list of each destination layer; According to the first distance, the first average distance between the passenger to be registered and each destination layer is determined; The first average distance is compared with a plurality of first distance threshold values preset for the destination floors to determine a synchronization credibility corresponding to the first average distance.

3. The method of claim 1, wherein, The aggregation credibility of the passenger to be registered with each destination floor in the destination floor list is obtained in the following manner: A list of registered passengers corresponding to each destination floor is obtained; After the passenger to be registered stops moving in the waiting hall, a second distance between the passenger to be registered and each registered passenger in the list of registered passengers corresponding to each destination floor is obtained; According to the second distance, a second average distance between the passenger to be registered and each registered passenger in the list of registered passengers corresponding to each destination floor is determined as a second average distance of the destination floor; The second average distance is compared with a plurality of second distance threshold values preset for the destination floor to determine an aggregation credibility corresponding to the second average distance.

4. The method of claim 1, wherein, The time credibility of the passenger to be registered with each destination floor in the destination floor list is obtained in the following manner: A set high-credibility floor in a set time period is obtained; If the destination floor is a high-credibility floor within the set time period, the time credibility of the destination floor is set to a first value; If the destination floor is a high-credibility floor but not within the set time period, or within the set time period but not a high-credibility floor, or neither a high-credibility floor nor within the set time period, the time credibility of the destination floor is set to a second value, wherein the second value is less than the first value.

5. An apparatus for destination layer registration, the apparatus comprising: The device is arranged in a destination floor registration system, the destination floor registration system is connected with a control system of an elevator, the destination floor registration system comprises a monitoring device arranged in a waiting hall, and the device comprises: A registration identification module is configured to determine registered passengers and passengers to be registered according to monitoring videos collected by the monitoring device, the registered passengers have associated destination floor information, and the monitoring videos include behaviors of passengers registering destination floors; A destination floor list acquisition module is configured to obtain the destination floor information associated with the registered passengers to form a destination floor list; A credibility determination module is configured to determine, for each passenger to be registered, a credibility of the passenger to be registered with each destination floor information in the destination floor list; A destination floor prediction module is configured to take the destination floor information with the highest credibility as predicted destination floor information of the passenger to be registered, so as to perform destination floor registration for passengers to be registered who have not performed destination floor registration, match the number of passengers registered with the number of passengers in the waiting hall, and then make the control system of the elevator dispatch the elevator according to the number of passengers registered; The registration identification module is specifically configured to: perform target detection on the monitoring videos collected by the monitoring device through a target detection algorithm generated in advance, so as to identify a human object from each video frame, take the human object as a passenger object, and assign a unique identifier to the passenger object in real time to distinguish each passenger object; When it is detected that a passenger object performs a destination registration operation at a destination registration device, the registered destination information of the passenger object is obtained from the destination registration device, and the destination information is associated with the unique identification of the passenger object, and the passenger object is regarded as a registered passenger; a passenger object without associated destination information is regarded as a passenger to be registered; The trustworthiness determination module is specifically configured to: determine the synchronization trustworthiness, the aggregation trustworthiness and the time trustworthiness of each destination information in the destination layer list with respect to the passenger to be registered; determine the weight corresponding to the synchronization trustworthiness, the aggregation trustworthiness and the time trustworthiness, respectively; based on the weight, perform weighted summation on the synchronization trustworthiness, the aggregation trustworthiness and the time trustworthiness to obtain the trustworthiness of the passenger to be registered with respect to the destination information; The device further comprises: an actual destination layer acquisition module configured to acquire the actual destination information of each passenger to be registered; a comparison module configured to compare the actual destination information with the predicted destination information of the same passenger; a weight correction module configured to correct the weight according to the comparison result by using a set correction algorithm.

6. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the method of any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the method of any one of claims 1-4 when executed. The computer readable storage medium stores computer instructions for enabling the processor to execute the method of any one of claims 1-4 when executed.

Images