An elevator dispatching optimization method, device, storage medium and equipment

Abstract

Embodiments of the present application disclose an elevator dispatching optimization method, device, storage medium and equipment, the method comprising: obtaining a plurality of simulation boarding information of each time period of the day according to a plurality of historical boarding information of each time period through machine learning, thereby obtaining the simulation traffic flow of each time period of the day, and determining whether the simulation traffic flow of each time period is greater than a traffic flow threshold value; when the simulation traffic flow of each time period is greater than the traffic flow threshold value, it indicates that the corresponding time period may have passenger retention and long queue phenomenon; at this time, the push boarding information is generated through machine learning and pushed to passengers, thereby avoiding too many passengers arriving at the same time and optimizing the randomness of passenger arrival; the method can optimize the elevator dispatching, avoid passenger retention and long queue phenomenon, effectively reduce the waiting time of passengers boarding, solve the problem of insufficient elevator capacity, greatly improve the operation efficiency of the elevator, and the like.

Description

Technical Field

[0001] This invention relates to the field of elevator technology, and in particular to an optimized method, apparatus, storage medium, and device for elevator dispatching. Background Technology

[0002] With the development of electronics and intelligence, elevators with intelligent functions have gradually emerged in recent years. These elevators can be booked in advance through smart terminals or called upon arrival. This generates elevator data (elevator information), and the elevator control system can generate a dispatch plan based on the elevator information to dispatch the elevator to the passenger.

[0003] Currently, due to peak hours for passenger use and limitations in elevator capacity, elevator dispatching cannot be optimized, leading to passenger congestion and long queues. Specifically, too many passengers arrive at the same time (e.g., during rush hour), the number of elevators in the building is insufficient, and the randomness of passenger arrivals means that passengers may need to get off at every floor, requiring elevators to stop at every floor. Passengers follow a first-come, first-served principle, resulting in insufficient elevator capacity and low elevator operating efficiency. Summary of the Invention

[0004] Based on this, it is necessary to propose an optimized method, device, storage medium, and equipment for elevator dispatching to address the above problems. This optimizes elevator dispatching, prevents passenger congestion and long queues, effectively reduces passenger waiting time, solves the problem of insufficient elevator capacity, and greatly improves elevator operating efficiency.

[0005] To achieve the above objectives, the present invention provides, in a first aspect, an optimized method for elevator dispatching, the method comprising:

[0006] Based on machine learning, multiple simulated elevator ride information for each time period of the day is obtained from multiple historical elevator ride information for each time period.

[0007] Based on multiple simulated elevator usage data for different time periods of the day, determine multiple simulated elevator dispatch plans and simulated traffic flows for each time period of the day.

[0008] When the simulated traffic flow in the k-th time period is greater than the traffic flow threshold, a first difference between the simulated traffic flow in the k-th time period and the traffic flow threshold is determined.

[0009] Based on machine learning, multiple push elevator information is determined according to multiple simulated elevator riding information in the kth time period, the first difference, and the first preset optimization rule;

[0010] Multiple push elevator ride information messages are sent to the corresponding smart terminals, and the first push time is recorded;

[0011] When the time difference between the current time and the first push time is equal to a preset duration, the push elevator information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatching scheme is updated according to the push elevator information.

[0012] Here, k takes the values ​​of integers greater than 0, until k equals the total number of time periods in the simulated traffic flow.

[0013] Optionally, after determining the push-to-ride information corresponding to the smart terminal that issued the preset feedback signal when the time difference between the current time and the first push time is equal to a preset duration, and updating the corresponding simulated elevator dispatching scheme according to the push-to-ride information, the method further includes:

[0014] When the time difference between the current time and the first push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than a preset threshold, then multiple secondary simulated elevator information in the k-th time period is determined based on multiple pushed elevator information and multiple simulated elevator information in the k-th time period.

[0015] The secondary simulated traffic flow for the k-th time period is determined based on multiple secondary simulated elevator ride information and multiple simulated elevator ride information corresponding to multiple push elevator ride information that did not issue a preset feedback signal.

[0016] Determine the second difference between the secondary simulated traffic flow in the k-th time period and the traffic flow threshold;

[0017] Based on machine learning, multiple secondary push elevator information is determined according to multiple secondary simulated elevator riding information in the kth time period, the second difference, and the first preset optimization rule;

[0018] Multiple secondary push elevator ride information messages are sent to the corresponding smart terminals, and the time of the second push is recorded;

[0019] When the time difference between the current time and the second push time is equal to the preset duration, the secondary push elevator information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatching scheme is updated according to the secondary push elevator information.

[0020] Similarly, when the time difference between the current time and the p-th push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than the preset threshold, then multiple p+1 simulated elevator information in the k-th time period are determined based on multiple p-th push elevator information and multiple p-th simulated elevator information in the k-th time period.

[0021] The p+1 simulated elevator flow in the k-th time period is determined based on the multiple p+1 simulated elevator ride information in the k-th time period, the multiple simulated elevator ride information corresponding to the multiple push elevator ride information that did not issue a preset feedback signal, and the multiple p simulated elevator ride information corresponding to the multiple p push elevator ride information that did not issue a preset feedback signal.

[0022] Determine the (p+1)th difference between the simulated traffic flow in the kth time period and the traffic flow threshold;

[0023] Based on machine learning, multiple p+1 simulated elevator ride information are determined according to the multiple p+1 simulated elevator ride information in the kth time period, the p+1th difference, and the first preset optimization rule;

[0024] Multiple p+1 push elevator information messages are sent to the corresponding smart terminals, and the time of the p+1th push is recorded.

[0025] When the time difference between the current time and the p+1th push time is equal to the preset duration, determine the p+1th push of elevator information corresponding to the smart terminal that issued the preset feedback signal, and update the corresponding simulated elevator dispatch scheme according to the p+1th push of elevator information.

[0026] Where p takes integers greater than 1 in sequence, until the time difference between the current time and the (p+1)th push time is equal to the preset duration, there are no smart terminals that have not issued a preset feedback signal, or there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is less than or equal to the preset threshold.

[0027] Optionally, after determining the push-to-ride information corresponding to the smart terminal that issued the preset feedback signal when the time difference between the current time and the first push time is equal to a preset duration, and updating the corresponding simulated elevator dispatching scheme according to the push-to-ride information, the method further includes:

[0028] Obtain multiple elevator usage information for the current and next time period;

[0029] The traffic flow for the current and next time periods is determined based on multiple elevator usage information for the current and next time periods.

[0030] When the traffic flow in the current next time period is greater than the traffic flow threshold, a third difference between the traffic flow in the current next time period and the traffic flow threshold is determined.

[0031] Based on machine learning, multiple elevator ride information to be pushed in the current next time period are determined according to multiple elevator ride information in the current next time period, the third difference, and the second preset optimization rule;

[0032] Multiple current and next time period push elevator information to the corresponding smart terminals, and record the third push time;

[0033] When the time difference between the current time and the third push time is equal to the preset duration, the smart terminal that issued the preset feedback signal is determined to push elevator information for the next time period, and the elevator dispatching scheme for the next time period is updated according to the elevator information pushed for the next time period.

[0034] Optionally, after determining the next time period for pushing elevator information corresponding to the smart terminal that issued the preset feedback signal when the time difference between the current time and the third push time is equal to the preset duration, and updating the corresponding elevator dispatching scheme for the next time period based on the elevator information pushed in the next time period, the method further includes:

[0035] When the time difference between the current time and the third push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than a preset threshold, then multiple secondary elevator information for the current next time period is determined based on multiple elevator information pushed in the current next time period and multiple elevator information for the current next time period.

[0036] The secondary traffic flow for the current next time period is determined based on multiple secondary elevator ride information for the current next time period and multiple elevator ride information for the current next time period corresponding to multiple elevator ride information pushed for the current next time period without issuing a preset feedback signal.

[0037] Determine the fourth difference between the secondary traffic flow in the current next time period and the traffic flow threshold;

[0038] Based on machine learning, multiple secondary elevator ride information for the current next time period are determined according to the multiple secondary elevator ride information of the current next time period, the fourth difference, and the second preset optimization rule;

[0039] Multiple current and next time period elevator ride information are pushed to the corresponding smart terminals, and the fourth push time is recorded;

[0040] When the time difference between the current time and the fourth push time is equal to the preset duration, determine the second push of elevator information for the current next time period corresponding to the smart terminal that issued the preset feedback signal, and update the corresponding elevator dispatching scheme for the current next time period according to the second push of elevator information for the current next time period.

[0041] Similarly, when the time difference between the current time and the (q+2)th push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than the preset threshold, then multiple (q+1) elevator ride information in the current next time period are determined based on multiple (q) push elevator ride information in the current next time period and multiple (q) elevator ride information in the current next time period.

[0042] The traffic flow for the current next time period is determined based on multiple q+1 elevator ride information in the current next time period, multiple elevator ride information pushed in the current next time period corresponding to multiple current next time period without issuing a preset feedback signal, and multiple q elevator ride information pushed in the current next time period q times corresponding to multiple current next time period without issuing a preset feedback signal.

[0043] Determine the (q+1)th difference between the traffic flow in the current next time period and the (q+3)th traffic flow threshold.

[0044] Based on machine learning, multiple elevator ride information pushes for the current next time period are determined according to multiple q+1 elevator ride information in the current next time period, the q+3rd difference, and the second preset optimization rule.

[0045] Push elevator information for the current next time period q+1 times to the corresponding smart terminal, and record the push time of the q+3th push.

[0046] When the time difference between the current time and the q+3th push time is equal to the preset duration, determine the current next time period q+1 push elevator information corresponding to the smart terminal that issued the preset feedback signal, and update the corresponding current next time period elevator dispatching scheme according to the current next time period q+1 push elevator information.

[0047] Wherein, q takes integers greater than 1 in sequence until the time difference between the current time and the (q+3)th push time is equal to the preset duration, at which point there is no smart terminal that has not issued a preset feedback signal, or there is a smart terminal that has not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is less than or equal to the preset threshold.

[0048] Optionally, the method further includes:

[0049] When the time difference between the current time and the first push time is equal to a preset duration, the smart terminal that has not issued a preset feedback signal is identified, and the corresponding push elevator information is eliminated by controlling the smart terminal.

[0050] Optionally, the method further includes:

[0051] In the event of an elevator malfunction, obtain elevator malfunction information;

[0052] Based on the elevator malfunction information, determine multiple elevator travel options for the malfunctioning elevator in the current time period, and based on the multiple elevator travel options for the malfunctioning elevator in the current time period, determine multiple elevator travel information for the malfunctioning elevator in the current time period.

[0053] Based on machine learning, multiple elevator notification messages are determined according to multiple elevator usage information of the faulty elevator in the current time period and a third preset optimization rule.

[0054] Based on multiple notifications of elevator usage information, determine multiple elevator usage plans for the faulty elevator in the current time period.

[0055] Optionally, before or after determining multiple elevator access plans for the faulty elevator in the current time period based on multiple notification elevator access information, the method further includes:

[0056] Multiple elevator access notifications are pushed to the corresponding smart terminals, prompting the smart terminals to issue audio and visual alerts.

[0057] To achieve the above objectives, the present invention provides, in a second aspect, an optimized elevator dispatching device, the device comprising:

[0058] The first simulation module is used to obtain multiple simulated elevator ride information for each time period of the day based on machine learning and multiple historical elevator ride information for each time period.

[0059] The second simulation module is used to determine multiple simulated elevator dispatching schemes and simulated traffic flow for each time period of the day based on multiple simulated elevator riding information for each time period of the day.

[0060] The first judgment module is used to determine the first difference between the simulated traffic flow in the k-th time period and the traffic flow threshold when the simulated traffic flow in the k-th time period is greater than the traffic flow threshold.

[0061] The elevator ride information determination module is used to determine multiple elevator ride information based on machine learning, according to multiple simulated elevator ride information in the k-th time period, the first difference, and the first preset optimization rule;

[0062] The push module is used to push multiple elevator ride information to the corresponding smart terminals and record the first push time;

[0063] The second judgment module is used to determine the push elevator information corresponding to the smart terminal that issued the preset feedback signal when the time difference between the current time and the first push time is equal to a preset duration, and update the corresponding simulated elevator dispatching scheme according to the push elevator information.

[0064] The sequential value selection module is used to sequentially select integers greater than 0 for k until k equals the total number of time periods of the simulated traffic flow.

[0065] To achieve the above objectives, the present invention provides, in a third aspect, a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method as described in any of the first aspects.

[0066] To achieve the above objectives, the present invention provides a computer device in a fourth aspect, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any of the first aspects.

[0067] The embodiments of the present invention have the following beneficial effects: Based on machine learning, multiple simulated elevator ride information for each time period of the day is obtained from multiple historical elevator ride information for each time period; multiple simulated elevator dispatch schemes and simulated traffic flows for each time period of the day are determined based on the multiple simulated elevator ride information for each time period of the day; when the simulated traffic flow in the k-th time period is greater than the traffic flow threshold, a first difference between the simulated traffic flow in the k-th time period and the traffic flow threshold is determined; based on machine learning, multiple push elevator ride information is determined based on the multiple simulated elevator ride information in the k-th time period, the first difference, and a first preset optimization rule; the multiple push elevator ride information is pushed to the corresponding smart terminal, and the first push time is recorded; when the time difference between the current time and the first push time is equal to a preset duration, the push elevator ride information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatch scheme is updated based on the push elevator ride information; wherein, k takes integers greater than 0 in sequence until k is equal to the total number of time periods of simulated traffic flow. The above method uses machine learning to obtain multiple simulated elevator travel data for each time period of the day based on historical elevator travel information from various time periods. This allows for the estimation of simulated traffic flow for each time period of the day. The method then determines whether the simulated traffic flow for each time period exceeds a traffic flow threshold. When the simulated traffic flow exceeds the threshold, it indicates that passenger congestion and long queues may occur during the corresponding time period. In this case, machine learning is used to generate and push elevator travel information to passengers, thereby preventing too many passengers from arriving at the same time and optimizing the randomness of passenger arrivals. This method optimizes elevator dispatching, prevents passenger congestion and long queues, effectively reduces passenger waiting time, solves the problem of insufficient elevator capacity, and greatly improves elevator operating efficiency. Attached Figure Description

[0068] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0069] in:

[0070] Figure 1 This is a schematic diagram of an elevator cloud control system according to an embodiment of this application;

[0071] Figure 2 This is a schematic diagram of an optimized elevator dispatching method according to an embodiment of this application;

[0072] Figure 3 This is a schematic diagram of an elevator dispatching optimization device according to an embodiment of this application;

[0073] Figure 4 Internal structural diagrams of computer devices in some embodiments are shown. Detailed Implementation

[0074] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0075] In this application embodiment, an elevator dispatch optimization method is mainly used for elevator dispatch optimization of elevators with intelligent functions (if the elevator does not have intelligent functions, it is equally applicable by manually collecting elevator information). That is, elevator information can be generated and pushed to passengers through machine learning of elevator information, thereby avoiding too many passengers arriving at the same time and optimizing the randomness of passenger arrival, so as to optimize elevator dispatch.

[0076] For example, please refer to an elevator cloud control system with intelligent functions. Figure 1 The diagram below is a schematic of an elevator cloud control system according to an embodiment of this application. The system includes: one or more smart terminals 110, a cloud platform 120, and one or more local speed control systems 130. The smart terminals 110 are communicatively connected to the cloud platform 120, and the cloud platform 120 is communicatively connected to the local speed control system 130.

[0077] Among them, the smart terminal 110 belongs to the user end, while the cloud platform 120 and the local speed control system 130 belong to the control end.

[0078] In some embodiments, the smart terminal 110 can be a smartphone, tablet, computer, etc., and the smart terminal 110 has a pre-installed system for calling elevators. Furthermore, the elevator calling system can be an APP, public account, mini program, webpage, PC software, etc. Therefore, the smart terminal 110 can transmit the elevator information input by the user (including the elevator time, starting floor and destination floor) to the cloud platform 120 through communication. The cloud platform can calculate the elevator dispatch plan based on the elevator information, and issue an operation command to the local elevator speed control system 130 through communication according to the elevator dispatch plan, so that the local elevator speed control system 130 executes the elevator dispatch plan to drive the elevator car to the destination floor. At this time, the cloud platform of the elevator cloud control system has the daily elevator information of the passengers.

[0079] In order to optimize elevator dispatching by utilizing passenger information, an elevator dispatching optimization method will be adopted in the following embodiments to optimize elevator dispatching.

[0080] Please see Figure 2 This is a schematic diagram of an optimized elevator dispatching method according to an embodiment of this application. The method includes:

[0081] Step 210: Based on machine learning, obtain multiple simulated elevator ride information for each time period of the day from multiple historical elevator ride information for each time period.

[0082] The length of each time period can be set by the operator according to actual needs, and there are no restrictions here.

[0083] It should be noted that the historical elevator riding information, simulated elevator riding information, and other elevator riding information in the embodiments of this application include, but are not limited to, elevator riding time, starting floor, and destination floor. It is understood that operators can also modify or equivalently replace the content in the elevator riding information.

[0084] In some embodiments, after obtaining all historical elevator usage information for each time period of each day, machine learning can be used to simulate possible elevator usage information for each time period of the day, thereby facilitating the subsequent push of elevator usage information.

[0085] Furthermore, in other embodiments, operators may also use other methods to simulate possible elevator travel information for each time period of the day based on all historical elevator travel information for each time period, such as deep learning-based methods.

[0086] Step 220: Determine multiple simulated elevator dispatch schemes and simulated traffic flows for each time period of the day based on multiple simulated elevator ride information for each time period of the day.

[0087] The simulated traffic flow can be used to reflect passenger elevator usage or the number of passengers using the elevator.

[0088] In some embodiments, after obtaining the possible simulated elevator ride information for each time period of the day, a simulated elevator dispatching scheme for each time period of the day can be determined based on the possible simulated elevator ride information for each time period of the day. Furthermore, the possible simulated traffic flow for each time period of the day can be directly calculated based on the possible simulated elevator ride information for each time period of the day. Further, the simulated traffic flow for each time point can be obtained first, and then each time point can be segmented into time segments to obtain the simulated traffic flow for each time period. That is, the simulated traffic flow for each time period can be the average of the simulated traffic flow for all time points in each time period.

[0089] In other embodiments, multiple historical traffic flows for each time period can be obtained based on multiple historical elevator ride information for each time period; based on machine learning, the simulated traffic flow for each time period of the day can be determined based on multiple historical traffic flows for each time period. It is understood that multiple historical traffic flows for each time period can be directly calculated based on multiple historical elevator ride information for each time period, thereby using machine learning to simulate the possible simulated traffic flow for each time period of the day based on multiple historical traffic flows for each time period.

[0090] Step 230: When the simulated traffic flow in the k-th time period is greater than the traffic flow threshold, determine the first difference between the simulated traffic flow in the k-th time period and the traffic flow threshold.

[0091] The determination of the traffic flow threshold is related to the elevator's transport capacity. It can be understood that the traffic flow threshold is the maximum capacity of the elevator. When the traffic flow exceeds the maximum capacity of the elevator, the elevator will not be able to transport the extra passengers.

[0092] In some embodiments, if the simulated traffic flow in the k-th time period is greater than the traffic flow threshold, it indicates that there are too many passengers taking the elevator in the k-th time period, that is, the number of passengers taking the elevator in the k-th time period has exceeded the maximum carrying capacity of the elevator, causing the elevator to be unable to transport the extra passengers. Therefore, it is necessary to push the elevator information to the extra passengers to optimize elevator dispatch.

[0093] It should be noted that when the simulated traffic flow in the k-th time period is greater than the traffic flow threshold, the first difference between the simulated traffic flow in the k-th time period and the traffic flow threshold can be determined first, thereby determining the number of extra passengers, so as to push elevator information to the extra passengers.

[0094] Step 240: Based on machine learning, determine multiple push elevator information according to multiple simulated elevator ride information in the k-th time period, the first difference and the first preset optimization rule.

[0095] The first preset optimization rule can be set by the operator according to actual needs. In some embodiments, the first preset optimization rule may include one or more of the following principles: zoning principle, principle of having the most passengers in a zoning zone, principle of having the most passengers on the target floor in one direction, principle of having the most passengers in one direction, principle of having the most passengers in one direction, principle of having the fewest stops in one direction, principle of having the shortest distance in one direction, and principle of grouping passengers in the nearest group. It is understood that when pushing elevator information to extra passengers, the most optimized result is usually selected to achieve a better elevator dispatch optimization effect. In other embodiments, the first preset optimization rule may also include a list of passengers who frequently refuse to push elevator information or do not respond to push elevator information, so as to avoid pushing elevator information to passengers who do not like to push elevator information, thereby causing inconvenience to passengers.

[0096] In some embodiments, after obtaining the information of extra passengers, machine learning can be used to simulate and obtain the most optimized list of passengers to be pushed, based on multiple simulated elevator ride information in the k-th time period, a first difference, and a first preset optimization rule. Each simulated elevator ride information corresponds to one passenger, i.e., the list of simulated elevator ride information to be pushed, thereby generating multiple push elevator ride information corresponding to the list of simulated elevator ride information to be pushed. It can be understood that after obtaining the list of extra simulated elevator ride information to be pushed, the elevator ride time in the simulated elevator ride information corresponding to the list of extra simulated elevator ride information to be pushed can be directly modified, and the modified simulated elevator ride information can be used as the push elevator ride information.

[0097] Step 250: Push multiple elevator ride information messages to the corresponding smart terminals and record the first push time.

[0098] In some embodiments, when pushing elevator information to the smart terminal corresponding to the passenger who needs the elevator information, the current push time, i.e. the first push time, can be recorded to avoid some passengers who neither accept nor refuse the push of elevator information affecting the elevator dispatch optimization process. That is, by recording the first push time, if the duration exceeds the first push time and the exceeded duration reaches a preset duration, it is assumed that the passenger refuses to push the elevator information.

[0099] Step 260: When the time difference between the current time and the first push time is equal to the preset duration, determine the push elevator information corresponding to the smart terminal that issued the preset feedback signal, and update the corresponding simulated elevator dispatching scheme according to the push elevator information.

[0100] The preset feedback signal can be set by the operator according to actual needs. In some embodiments, the preset feedback signal is usually set to a signal with "accept" data. It can be understood that when pushing elevator information to the corresponding passenger, there is an option to select "accept" and "reject". At this time, when the passenger selects the "accept" option, the preset feedback signal will be received. When the passenger selects the "reject" option or does not select an option, no feedback signal will be received. Alternatively, when the passenger selects the "reject" option, other preset feedback signals will be received. When the passenger does not select an option, no feedback signal will be received.

[0101] In some embodiments, the current time can be obtained and compared with the first push time. If the time difference between the current time and the first push time is equal to a preset duration, when a preset feedback signal is received from the smart terminal, the push elevator information corresponding to the smart terminal that sent the preset feedback signal can be determined, and the previously corresponding simulated elevator dispatching scheme can be updated according to the push elevator information. That is, by updating the corresponding simulated elevator dispatching scheme, the elevator dispatching can be optimized.

[0102] Step 270: k takes the integers greater than 0 in turn until k equals the total number of time periods of the simulated traffic flow.

[0103] In some embodiments, assuming the total number of time periods for simulating traffic flow is 3, when k is 1 (i.e., when the simulated traffic flow in the first time period is greater than the traffic flow threshold), a first difference between the simulated traffic flow in the first time period and the traffic flow threshold is determined. Based on machine learning, multiple simulated elevator access information, the first difference, and a first preset optimization rule are used to determine multiple push elevator access information. These multiple push elevator access information are then pushed to the corresponding smart terminals, and the first push time is recorded. When the time difference between the current time and the first push time is equal to a preset duration, the push elevator access information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatch scheme is updated based on the push elevator access information. When k is 2 (i.e., when the simulated traffic flow in the second time period is greater than the traffic flow threshold), a first difference between the simulated traffic flow in the second time period and the traffic flow threshold is determined. Based on machine learning, multiple simulated elevator access information, the first difference, and a first preset optimization rule are used to determine multiple push elevator access information. The optimization rules determine multiple push elevator information messages, which are then pushed to the corresponding smart terminals. The first push time is recorded. When the time difference between the current time and the first push time equals a preset duration, the push elevator information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatching scheme is updated based on the push elevator information. When k is 3, that is, when the simulated traffic flow in the third time period is greater than the traffic flow threshold, the first difference between the simulated traffic flow in the third time period and the traffic flow threshold is determined. Based on machine learning, multiple push elevator information messages are determined according to the multiple simulated elevator information messages in the third time period, the first difference, and the first preset optimization rules. These multiple push elevator information messages are then pushed to the corresponding smart terminals, and the first push time is recorded. When the time difference between the current time and the first push time equals a preset duration, the push elevator information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatching scheme is updated based on the push elevator information.

[0104] In this embodiment, machine learning is used to obtain multiple simulated elevator travel information for each time period of the day based on multiple historical elevator travel information for each time period. This results in simulated traffic flow for each time period of the day. The system then determines whether the simulated traffic flow for each time period exceeds a traffic flow threshold. When the simulated traffic flow for each time period exceeds the threshold, it indicates that passenger congestion and long queues may occur during the corresponding time period. In this case, machine learning is used to generate and push elevator travel information to passengers, thereby preventing too many passengers from arriving at the same time and optimizing the randomness of passenger arrival. This method can optimize elevator dispatching, prevent passenger congestion and long queues, effectively reduce passenger waiting time, solve the problem of insufficient elevator capacity, and greatly improve elevator operating efficiency.

[0105] In one feasible implementation, in step 260, when the time difference between the current time and the first push time is equal to a preset duration, the push elevator information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatch scheme is updated according to the push elevator information, the method in the above embodiment further includes: when the time difference between the current time and the first push time is equal to a preset duration, there are smart terminals that have not issued the preset feedback signal, and the number of smart terminals that have not issued the preset feedback signal is greater than a preset threshold, then multiple secondary simulated elevator information for the k-th time period is determined based on multiple push elevator information and multiple simulated elevator information for the k-th time period; based on the k-th time period... Multiple simulated elevator ride information and multiple simulated elevator ride information corresponding to multiple push elevator ride information without a preset feedback signal are used to determine the secondary simulated traffic flow in the k-th time period; the second difference between the secondary simulated traffic flow in the k-th time period and the traffic flow threshold is determined; based on machine learning, multiple secondary push elevator ride information are determined according to the multiple simulated elevator ride information in the k-th time period, the second difference, and the first preset optimization rule; the multiple secondary push elevator ride information are pushed to the corresponding smart terminals, and the second push time is recorded; when the time difference between the current time and the second push time is equal to the preset duration, the secondary push elevator ride information corresponding to the smart terminal that issued the preset feedback signal is determined, and the secondary push elevator ride information is determined according to the secondary... The simulated elevator dispatch scheme corresponding to the push elevator information update is implemented. Similarly, when the time difference between the current time and the p-th push time equals a preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than a preset threshold. Then, based on multiple p-th push elevator information and multiple p-th simulated elevator information in the k-th time period, multiple p+1 simulated elevator information in the k-th time period are determined. Based on the multiple p+1 simulated elevator information in the k-th time period, the multiple simulated elevator information corresponding to the multiple push elevator information that has not issued a preset feedback signal, and the multiple p-th simulated elevator information corresponding to the multiple p-th push elevator information that has not issued a preset feedback signal... Determine the p+1 simulated traffic flow in the k-th time period; determine the p+1-th difference between the p+1 simulated traffic flow in the k-th time period and the traffic flow threshold; based on machine learning, determine multiple p+1 push elevator information according to the multiple p+1 simulated elevator ride information in the k-th time period, the p+1-th difference, and the first preset optimization rule; push the multiple p+1 push elevator information to the corresponding smart terminals and record the p+1-th push time; when the time difference between the current time and the p+1-th push time is equal to the preset duration, determine the p+1 push elevator information corresponding to the smart terminal that issued the preset feedback signal, and update the corresponding simulated elevator dispatch scheme according to the p+1 push elevator information;Where p takes integer values ​​greater than 1, until the time difference between the current time and the (p+1)th push time equals a preset duration, at which point there are no smart terminals that have not issued a preset feedback signal, or there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is less than or equal to a preset threshold.

[0106] The preset threshold is set by the operator according to actual needs. Understandably, more elevator information will be pushed out in general. For example, if the difference between the simulated traffic flow and the traffic flow threshold is 100, then only 100 elevator information should be pushed out, but in reality, 110 elevator information will be pushed out, which means 10 more elevator information will be pushed out in the end. In this case, the preset threshold can be set to 10. Of course, in reality, only 100 elevator information can be pushed out. In this case, the preset threshold can be not set or can be set to 0.

[0107] Furthermore, pushing more elevator information is done to account for the possibility that some smart terminals may not send a preset feedback signal, meaning the passenger has selected the "decline" option or the passenger has not selected any option. Therefore, more elevator information is pushed out at once. Also, because more elevator information is pushed out, even if the number of smart terminals that have not sent a preset feedback signal is less than or equal to a preset threshold, the required optimization effect for elevator dispatch can still be achieved. In this case, no further optimization is needed, i.e., no more elevator information pushes are required.

[0108] It should be noted that when determining multiple secondary simulated elevator ride information for the k-th time period based on multiple push elevator ride information and multiple simulated elevator ride information for the k-th time period, it can be understood that the multiple push elevator ride information is equivalent to the push elevator ride information determined in the first optimization. If a second optimization is needed, the simulated elevator ride information corresponding to the push elevator ride information determined in the first optimization needs to be excluded. That is, the second optimization will not repeatedly optimize the simulated elevator ride information corresponding to the push elevator ride information determined in the first optimization. Therefore, it is necessary to determine multiple secondary simulated elevator ride information for the k-th time period based on multiple push elevator ride information and multiple simulated elevator ride information for the k-th time period. Furthermore, when determining the secondary simulated traffic flow for the k-th time period based on multiple secondary simulated elevator ride information and multiple push elevator ride information corresponding to multiple push elevator ride information that did not issue a preset feedback signal, i.e., when obtaining the multiple secondary simulated elevator ride information to be optimized in the second round, it is necessary to calculate the degree of optimization required for the second optimization. Therefore, it is necessary to first obtain... The secondary simulated traffic flow for the k-th time period should include simulated elevator information corresponding to those without pushed elevator information and simulated elevator information corresponding to those pushed elevator information but without issuing a preset feedback signal. That is, the secondary simulated traffic flow for the k-th time period is determined based on multiple secondary simulated elevator information and multiple simulated elevator information corresponding to multiple pushed elevator information without issuing a preset feedback signal (i.e., multiple simulated elevator information corresponding to multiple pushed elevator information without issuing a preset feedback signal). Furthermore, since the number of smart terminals that have not issued a preset feedback signal is greater than a preset threshold, a second optimization is definitely required. At this time, there is no need to compare the secondary simulated traffic flow for the k-th time period with the traffic flow threshold, that is, the secondary simulated traffic flow for the k-th time period is definitely greater than the traffic flow threshold. Therefore, the second difference between the secondary simulated traffic flow for the k-th time period and the traffic flow threshold can be directly calculated to determine the degree of optimization required for the second optimization.

[0109] It should be further explained that no matter how many optimizations are performed, as long as there are smart terminals that do not send a preset feedback signal, and the number of smart terminals that do not send a preset feedback signal is greater than a preset threshold, it means that the optimization effect at this time still does not achieve the desired optimization effect. Therefore, the optimization will be repeated. That is, in some embodiments, if the desired optimization effect can be achieved in the fourth optimization; p is 2. When the time difference between the current time and the second push time (Note: Arabic numerals below are equivalent to Chinese numerals, i.e., the second push time) is equal to a preset duration, there are smart terminals that do not send a preset feedback signal, and the number of smart terminals that do not send a preset feedback signal is greater than a preset threshold. At this time, a third optimization is performed. The kth time period is determined based on multiple second-pull elevator information (i.e., secondary push elevator information) and multiple second-simulated elevator information (i.e., secondary simulated elevator information) in the kth time period. Based on multiple simulated elevator ride information from three times, the simulated elevator ride information from multiple push elevator ride information corresponding to multiple times push elevator ride information corresponding to multiple times push elevator ride information corresponding to multiple times push elevator ride information corresponding to multiple times push elevator ride information without issuing a preset feedback signal is determined. The third difference between the simulated traffic flow from three times and the traffic flow threshold in the k-th time period is determined. Based on machine learning, multiple push elevator ride information is determined based on the multiple simulated elevator ride information from three times, the third difference, and the first preset optimization rule. The multiple push elevator ride information is pushed to the corresponding smart terminal, and the third push time is recorded. When the time difference between the current time and the third push time is equal to the preset duration, the push elevator ride information corresponding to the smart terminal that issues the preset feedback signal is determined, and the corresponding simulated elevator dispatching scheme is updated based on the push elevator ride information.When p is set to 3, if the time difference between the current time and the third push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than the preset threshold. In this case, a fourth optimization is performed. Based on multiple 3-push elevator ride information and multiple 3-simulated elevator ride information in the k-th time period, multiple 4-simulated elevator ride information in the k-th time period are determined. Based on the multiple 4-simulated elevator ride information in the k-th time period, the multiple simulated elevator ride information corresponding to multiple push elevator ride information that has not issued a preset feedback signal, the multiple 2-simulated elevator ride information corresponding to multiple push elevator ride information that has not issued a preset feedback signal, and the multiple 3-push elevator ride information corresponding to multiple push elevator ride information that has not issued a preset feedback signal, the four-simulated traffic flow in the k-th time period is determined. The four-simulated traffic flow in the k-th time period and the traffic flow are then determined. The fourth difference of the threshold is determined based on machine learning. Multiple four-times simulated elevator ride information is determined according to the fourth difference and the first preset optimization rule in the k-th time period. This information is then pushed to the corresponding smart terminals, and the fourth push time is recorded. When the time difference between the current time and the fourth push time equals a preset duration, the four-times pushed elevator ride information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatch scheme is updated based on this information. When p is 4, if the time difference between the current time and the fourth push time equals the preset duration, either there are no smart terminals that did not issue the preset feedback signal, or there are smart terminals that did not issue the preset feedback signal, and the number of smart terminals that did not issue the preset feedback signal is less than or equal to the preset threshold. Therefore, no further optimization is needed.

[0110] It should also be noted that during the fourth optimization, the four simulated traffic flows in the k-th time period should also include multiple simulated elevator ride information corresponding to multiple two-time push elevator ride information that did not issue a preset feedback signal. That is, the simulated elevator ride information corresponding to multiple two-time push elevator ride information that did not issue a preset feedback signal is not optimized. Therefore, the simulated traffic flow at this time should also include the simulated elevator ride information corresponding to multiple two-time push elevator ride information that did not issue a preset feedback signal. In some embodiments, if there is a fifth optimization, the five simulated traffic flows in the k-th time period determined during the fifth optimization should also include multiple simulated elevator ride information corresponding to multiple two-time push elevator ride information that did not issue a preset feedback signal and multiple simulated elevator ride information corresponding to multiple three-time push elevator ride information that did not issue a preset feedback signal.

[0111] In this embodiment, by having smart terminals that do not send preset feedback signals and the number of such smart terminals exceeds a preset threshold, optimization push is performed again. This repeated optimization push avoids the optimization failing to achieve the desired effect, thereby optimizing elevator dispatch, preventing passenger congestion and long queues, effectively reducing passenger waiting time, solving the problem of insufficient elevator capacity, and greatly improving elevator operating efficiency.

[0112] In one feasible implementation, in step 260, when the time difference between the current time and the first push time is equal to a preset duration, the push elevator information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatching scheme is updated according to the push elevator information, the method in the above embodiment further includes: obtaining multiple elevator information for the current next time period; determining the traffic flow for the current next time period based on the multiple elevator information for the current next time period; when the traffic flow for the current next time period is greater than the traffic flow threshold, determining a third difference between the traffic flow for the current next time period and the traffic flow threshold; based on machine learning, determining multiple push elevator information for the current next time period according to the multiple elevator information for the current next time period, the third difference, and a second preset optimization rule; pushing the multiple push elevator information for the current next time period to the corresponding smart terminal and recording the third push time; when the time difference between the current time and the third push time is equal to a preset duration, determining the push elevator information for the current next time period corresponding to the smart terminal that issued the preset feedback signal, and updating the corresponding elevator dispatching scheme for the current next time period according to the push elevator information for the current next time period.

[0113] The second preset optimization rule can be set by the operator according to actual needs. In some embodiments, the second preset optimization rule may include one or more of the following principles: zoning principle, principle of maximizing the number of passengers within a zoning zone, principle of maximizing the number of passengers on the target floor in one direction, principle of maximizing the number of passengers carried in one direction, principle of minimizing the number of stops in one direction, principle of minimizing the distance traveled in one direction, and principle of grouping passengers in nearby locations. It also includes a push-based determination principle. Regarding the push-based determination principle, it is understood that in the above embodiments, the push of elevator information to extra passengers is simulated; in this case, the extra passengers are actual passengers. However, in the above embodiments… For additional passengers, elevator information is pushed to them. If a passenger has already accepted the push during the simulation, then in the actual case of additional passengers, those passengers who have already accepted the push during the simulation will generally not be optimized. That is, according to the push determination principle, passengers who have already accepted the push during the simulation will generally not be pushed elevator information again. In addition, the second preset optimization rule is similar to the first preset optimization rule, and usually selects the most optimized result to achieve a better elevator dispatch optimization effect. In some other embodiments, the second preset optimization rule may also include a list of passengers who frequently refuse to push elevator information or do not respond to push elevator information, so as to avoid pushing elevator information to passengers who do not like to push elevator information, thereby causing inconvenience to passengers.

[0114] In some embodiments, firstly, multiple elevator passenger information for the next time period can be obtained. This multiple elevator passenger information can be a current time period or a future time period. The multiple elevator passenger information includes actual reservations or calls, as well as successfully pushed elevator passenger information during simulation in the above embodiments. Then, the traffic flow for the next time period is determined based on the multiple elevator passenger information, i.e., the traffic flow for the next time period is directly calculated using the multiple elevator passenger information. Next, if the traffic flow for the next time period is greater than a traffic flow threshold, it indicates that there are too many elevator passengers in the next time period, meaning the number of passengers has exceeded the elevator's maximum carrying capacity, causing the elevator to be unable to transport the extra passengers. Therefore, it is necessary to push elevator passenger information to the extra passengers to optimize elevator dispatch. This is achieved by determining a third difference between the traffic flow for the next time period and the traffic flow threshold to determine the degree of optimization required. Finally, based on machine learning, multiple elevator passenger information to be pushed for the next time period are determined according to the multiple elevator passenger information for the next time period, the third difference, and a second preset optimization rule. After obtaining information on the extra passengers, machine learning can be used to generate an optimized list of passengers to be pushed to, based on multiple elevator ride information for the next time period, a third difference, and a second preset optimization rule. Each elevator ride information corresponds to one passenger, forming the list of elevator ride information to be pushed. This generates multiple elevator ride information for the next time period corresponding to the list of elevator ride information to be pushed. In essence, after obtaining the list of extra elevator ride information to be pushed, the elevator ride time in the elevator ride information for the next time period corresponding to the extra list can be directly modified, and the modified elevator ride information for the next time period is used as the elevator ride information for the next time period. Then, the multiple elevator ride information for the next time period are pushed to the corresponding smart terminals, and the third push time is recorded. Then, when the time difference between the current time and the third push time equals a preset duration, the elevator ride information for the next time period corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding elevator dispatch plan for the next time period is updated based on the elevator ride information for the next time period. Here, the elevator dispatch plan can be determined by the multiple elevator ride information for the next time period.

[0115] In this embodiment, elevator dispatching is optimized by acquiring multiple elevator ride information for the current time period or the next time period, i.e., multiple elevator ride information for the current time period or multiple elevator ride information for the future time period. It is understood that there may be some discrepancies between the simulated elevator ride information for each time period of the day and the actual elevator ride times for each time period. Therefore, if the traffic flow for the current time period is still too high, further optimization can be performed to optimize the current elevator dispatching, prevent passenger congestion and long queues, effectively reduce passenger waiting time, solve the problem of insufficient elevator capacity, and greatly improve elevator operating efficiency.

[0116] In one feasible implementation, when the time difference between the current time and the third push time is equal to a preset duration, the method further includes: when the smart terminal that issued the preset feedback signal is determined to have pushed elevator information for the next time period, and the corresponding elevator dispatching scheme for the next time period is updated based on the elevator information pushed for the next time period, the method in the above embodiment further includes: when the time difference between the current time and the third push time is equal to a preset duration, there are smart terminals that have not issued the preset feedback signal, and the number of smart terminals that have not issued the preset feedback signal is greater than a preset threshold, then the current elevator dispatching scheme is determined based on the multiple elevator information pushed for the next time period and the multiple elevator information of the multiple elevator information of the next time period. The system retrieves multiple secondary elevator ride information for the next time period; determines the secondary traffic flow for the current next time period based on these multiple secondary elevator ride information and multiple elevator ride information pushed for the current next time period that did not issue a preset feedback signal; determines the fourth difference between the secondary traffic flow for the current next time period and the traffic flow threshold; based on machine learning, determines multiple secondary elevator ride information pushed for the current next time period according to the multiple secondary elevator ride information, the fourth difference, and the second preset optimization rule; pushes the multiple secondary elevator ride information pushed for the current next time period to the corresponding smart terminals and records the fourth push time; when the time difference between the current time and the fourth push time is equal to the preset duration... The system determines the next time period for which a smart terminal that has issued a preset feedback signal will receive a second push of elevator information. Based on this second push, the system updates the corresponding elevator dispatch plan for the next time period. Similarly, if the time difference between the current time and the (q+2)th push time equals a preset duration, and there are smart terminals that have not issued a preset feedback signal, and the number of such terminals exceeds a preset threshold, then the system determines multiple (q+1)th pushes of elevator information for the next time period based on the multiple (q)th pushes of elevator information for the next time period and the multiple (q)th pushes of elevator information for the next time period. Based on the multiple (q+1)th pushes of elevator information for the next time period and the number of smart terminals that have not issued a preset feedback signal, the system determines multiple (q+1)th pushes of elevator information for the next time period. Let multiple elevator ride information corresponding to multiple current next time periods push elevator ride information and multiple q elevator ride information corresponding to multiple current next time periods push elevator ride information without issuing preset feedback signals be used to determine the q+1th traffic flow in the current next time period; determine the q+3rd difference between the q+1th traffic flow in the current next time period and the traffic flow threshold; based on machine learning, determine multiple q+1th elevator ride information pushes in the current next time period according to the multiple q+1th elevator ride information in the current next time period, the q+3rd difference, and the second preset optimization rule; push the multiple q+1th elevator ride information pushes in the current next time period to the corresponding smart terminals and record the q+3rd push time;When the time difference between the current time and the (q+3)th push time equals a preset duration, determine the elevator information pushed in the next time period (q+1)th push for the smart terminal that issued the preset feedback signal, and update the corresponding elevator dispatch plan for the next time period based on the elevator information pushed in the next time period (q+1). Here, q takes integer values ​​greater than 1, until the time difference between the current time and the (q+3)th push time equals the preset duration, indicating that there are no smart terminals that have not issued the preset feedback signal, or that there are smart terminals that have not issued the preset feedback signal, and the number of smart terminals that have not issued the preset feedback signal is less than or equal to a preset threshold.

[0117] It should be noted that after the first optimization of multiple elevator ride information in the current next time period, if the optimization effect does not reach the required level, further optimization (second optimization, third optimization, etc.) is required. That is, regardless of the number of optimizations, if there are smart terminals that do not send a preset feedback signal, and the number of such smart terminals exceeds a preset threshold, the optimization effect is still insufficient. Therefore, optimization will be repeated. In some embodiments, if the required optimization effect is achieved in the fifth optimization, and q is 2, when the time difference between the current time and the fourth push time (note: Arabic numerals below are equivalent to Chinese numerals, i.e., the fourth push time) equals a preset duration, and there are smart terminals that do not send a preset feedback signal, and the number of such smart terminals exceeds a preset threshold, a third optimization is performed. This is based on multiple elevator ride information pushed twice in the current next time period and multiple elevator ride information from the current next time period. The system determines multiple 3-time elevator ride information for the current and next time periods. Based on these multiple 3-time elevator ride information, multiple elevator ride information pushed for the current and next time periods without a preset feedback signal, and multiple 2-time elevator ride information pushed for the current and next time periods without a preset feedback signal, it determines the 3-time traffic flow for the current and next time periods. It then determines the 5th difference between the 3-time traffic flow for the current and next time periods and the traffic flow threshold. Based on machine learning, it determines multiple 3-time elevator ride information pushed for the current and next time periods based on the multiple 3-time elevator ride information, the 5th difference, and the second preset optimization rule. It then pushes the multiple 3-time elevator ride information pushed for the current and next time periods to the corresponding smart terminals and records the 5th push time. When the time difference between the current time and the 5th push time is equal to the preset duration, it determines the 3-time elevator ride information pushed for the current and next time periods corresponding to the smart terminal that issued the preset feedback signal, and updates the corresponding elevator dispatching scheme for the current and next time periods based on the 3-time elevator ride information pushed for the current and next time periods.When q is set to 3, if the time difference between the current time and the 5th push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than the preset threshold, then a fourth optimization is performed. This involves determining multiple 4-times of elevator ride information for the current next time period based on multiple 3-times of elevator ride information and multiple 3-times of elevator ride information for the current next time period. Then, based on the multiple 4-times of elevator ride information for the current next time period, the multiple elevator ride information corresponding to multiple current next time period pushes that have not issued a preset feedback signal, the multiple 2-times of elevator ride information corresponding to multiple current next time period pushes that have not issued a preset feedback signal, and the multiple current next time period pushes that have not issued a preset feedback signal... Multiple elevator ride information pushes for three consecutive times determine the four traffic flows in the next time period. The sixth difference between the four traffic flows in the next time period and the traffic flow threshold is determined. Based on machine learning, multiple elevator ride information pushes for the next time period are determined according to the multiple elevator ride information pushes for the next time period, the sixth difference, and the second preset optimization rule. These multiple elevator ride information pushes for the next time period to the corresponding smart terminals, and the sixth push time is recorded. When the time difference between the current time and the sixth push time is equal to the preset duration, the elevator ride information pushes for the next time period corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding elevator dispatching scheme for the next time period is updated according to the elevator ride information pushes for the next time period.When q is set to 4, and the time difference between the current time and the 6th push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than the preset threshold. At this time, the fourth optimization is performed. Based on the multiple 4-push elevator information in the current next time period and the multiple 4-push elevator information in the current next time period, multiple 5-push elevator information in the current next time period are determined. Based on the multiple 5-push elevator information in the current next time period, the multiple elevator information corresponding to the multiple elevator information in the current next time period that has not issued a preset feedback signal, the multiple 2-push elevator information corresponding to the multiple 2-push elevator information in the current next time period that has not issued a preset feedback signal, the multiple 3-push elevator information corresponding to the multiple 3-push elevator information in the current next time period that has not issued a preset feedback signal, and the multiple 4-push elevator information corresponding to the multiple 4-push elevator information in the current next time period that has not issued a preset feedback signal, the 5-push traffic flow in the current next time period is determined. The 7th difference between the 5 traffic flows in a given time period and the traffic flow threshold is determined using machine learning. Based on multiple 5 elevator ride information in the next time period, the 7th difference, and a second preset optimization rule, multiple 5-time push elevator ride information for the next time period are determined. These multiple 5-time push elevator ride information are pushed to the corresponding smart terminals, and the 7th push time is recorded. When the time difference between the current time and the 7th push time is equal to a preset duration, the 5-time push elevator ride information for the next time period corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding elevator dispatching scheme for the next time period is updated based on the 5-time push elevator ride information for the next time period. q is set to 5. When the time difference between the current time and the 7th push time is equal to the preset duration, either there are no smart terminals that have not issued the preset feedback signal, or there are smart terminals that have not issued the preset feedback signal, and the number of smart terminals that have not issued the preset feedback signal is less than or equal to the preset threshold. Therefore, no further optimization is needed.

[0118] In this embodiment, by having smart terminals that do not send preset feedback signals and the number of such smart terminals exceeds a preset threshold, optimization push is performed again. This repeated optimization push avoids the optimization failing to achieve the desired effect, thereby optimizing elevator dispatch, preventing passenger congestion and long queues, effectively reducing passenger waiting time, solving the problem of insufficient elevator capacity, and greatly improving elevator operating efficiency.

[0119] In one feasible implementation, the method in the above embodiments further includes: when the time difference between the current time and the first push time is equal to a preset duration, identifying the smart terminal that has not issued a preset feedback signal, and controlling the smart terminal to eliminate the corresponding push elevator information.

[0120] It should be noted that when passengers select the "decline" option or do not select an option, they do not receive a preset feedback signal. Therefore, it is necessary to eliminate the elevator push information corresponding to these smart terminals that have not sent preset feedback signals. This is understandable, as it is to prevent passengers from suddenly selecting the "accept" option when the time difference between the current time and the first push time is greater than the preset duration, thus disrupting the optimization effect and failing to achieve a perfect optimization result.

[0121] In this embodiment, when the time difference between the current time and the first push time is equal to a preset duration, it is determined that the smart terminal has not issued a preset feedback signal. The corresponding push elevator information is then eliminated by controlling the smart terminal to prevent passengers from selecting the "accept" option when the time difference between the current time and the first push time is greater than the preset duration, thereby disrupting the optimization effect and failing to achieve a more perfect optimization effect.

[0122] In one feasible implementation, the method in the above embodiments further includes: when an elevator malfunctions, obtaining elevator malfunction information; determining multiple elevator travel plans for the malfunctioning elevator in the current time period based on the elevator malfunction information, and determining multiple elevator travel information for the malfunctioning elevator in the current time period based on the multiple elevator travel plans for the malfunctioning elevator in the current time period; determining multiple notification elevator travel information based on machine learning, according to the multiple elevator travel information for the malfunctioning elevator in the current time period and a third preset optimization rule; and determining multiple elevator travel plans to update the malfunctioning elevator in the current time period based on the multiple notification elevator travel information.

[0123] The elevator malfunction information includes, but is not limited to, the elevator number, the start time of the malfunction, and the estimated time for resolution of the malfunction, etc. There are no restrictions here.

[0124] It should be noted that when an elevator malfunctions, it will affect the boarding of passengers in multiple boarding plans associated with the malfunctioning elevator, preventing passengers who need to use the malfunctioning elevator from doing so. Therefore, it is necessary to reassign passengers from these plans to other elevators. This can be achieved by using a third preset optimization rule. This third preset optimization rule can be set by the operator according to actual needs. In some embodiments, this third preset optimization rule may include one or more of the following principles: zoning principle, principle of maximizing the number of passengers in a zone, principle of maximizing the number of passengers on the target floor in one direction, principle of maximizing the number of passengers carried in one direction, principle of minimizing the number of stops in one direction, principle of minimizing the distance in one direction, and principle of grouping passengers in nearby clusters. It may also include an on-demand insertion principle. The on-demand insertion principle means that as long as it does not affect the optimization effect, passengers from the malfunctioning elevator can be inserted into other elevators. Of course, through machine learning, the most optimized result will usually be selected to achieve a better elevator dispatch optimization effect.

[0125] It should be further explained that the method of determining multiple elevator notification information based on machine learning, multiple elevator information of the malfunctioning elevator in the current time period and the third preset optimization rule, and determining multiple elevator access plans for updating the malfunctioning elevator in the current time period based on the multiple elevator notification information, is different from pushing elevator information. This method only informs passengers that due to the elevator malfunction, they can only take the elevator in the notification information, and cannot select "accept" or "reject" options. Therefore, multiple elevator access plans for the malfunctioning elevator in the current time period can be directly updated based on the multiple elevator notification information.

[0126] In this embodiment, when an elevator malfunctions, multiple passenger routes corresponding to the malfunctioning elevator are assigned to other elevators to obtain multiple passenger route notifications. Based on these notifications, multiple passenger routes for the malfunctioning elevator in the current time period are updated to avoid the problem that passengers of the multiple passenger routes corresponding to the malfunctioning elevator cannot ride the elevator when it malfunctions, thus further optimizing elevator dispatching.

[0127] In one feasible implementation, before or after determining multiple elevator access plans for the faulty elevator in the current time period based on multiple elevator access notifications, the method in the above embodiment further includes: pushing multiple elevator access notifications to the corresponding smart terminals, so that the smart terminals issue sound and light reminders.

[0128] It should be noted that, since only passengers using the multiple elevator plans associated with the malfunctioning elevator are notified when an elevator malfunctions, permission can be granted to the smart terminal to issue an audio-visual alert, thus ensuring that the notification is delivered to the passengers and preventing them from being unaware in a timely manner.

[0129] In this embodiment, when an elevator malfunctions, multiple elevator access plans corresponding to the malfunctioning elevator are arranged to other elevators to obtain multiple elevator access notifications. These notifications are then pushed to the corresponding smart terminals, which issue audible and visual alerts to ensure that the notifications are delivered to passengers and prevent them from being unaware of the information in a timely manner.

[0130] Please see Figure 3 This is a schematic diagram of an elevator dispatching optimization device according to an embodiment of this application. The device 310 includes:

[0131] The first simulation module 311 is used to obtain multiple simulated elevator ride information for each time period of the day based on machine learning and multiple historical elevator ride information for each time period.

[0132] The second simulation module 312 is used to determine multiple simulated elevator dispatch schemes and simulated traffic flow for each time period of the day based on multiple simulated elevator riding information for each time period of the day.

[0133] The first judgment module 313 is used to determine the first difference between the simulated traffic flow and the traffic flow threshold in the k-th time period when the simulated traffic flow in the k-th time period is greater than the traffic flow threshold.

[0134] The elevator information push determination module 314 is used to determine multiple elevator information pushes based on machine learning, according to multiple simulated elevator information in the k-th time period, a first difference, and a first preset optimization rule.

[0135] The push module 315 is used to push multiple elevator ride information to the corresponding smart terminal and record the first push time;

[0136] The second judgment module 316 is used to determine the push elevator information corresponding to the smart terminal that issued the preset feedback signal when the time difference between the current time and the first push time is equal to the preset duration, and update the corresponding simulated elevator dispatching scheme according to the push elevator information.

[0137] The sequential value selection module 317 is used to sequentially select integers greater than 0 for k until k equals the total number of time periods of the simulated traffic flow.

[0138] In this embodiment, the relevant contents of the first simulation module 311, the second simulation module 312, the first judgment module 313, the push elevator information determination module 314, the push module 315, the second judgment module 316, and the sequential value retrieval module 317 can be found in the following references. Figure 2 The contents of the illustrated embodiments will not be repeated here.

[0139] In this embodiment, machine learning is used to obtain multiple simulated elevator travel information for each time period of the day based on multiple historical elevator travel information for each time period. This results in simulated traffic flow for each time period of the day. The system then determines whether the simulated traffic flow for each time period exceeds a traffic flow threshold. When the simulated traffic flow for each time period exceeds the threshold, it indicates that passenger congestion and long queues may occur during the corresponding time period. In this case, machine learning is used to generate and push elevator travel information to passengers, thereby preventing too many passengers from arriving at the same time and optimizing the randomness of passenger arrival. This method can optimize elevator dispatching, prevent passenger congestion and long queues, effectively reduce passenger waiting time, solve the problem of insufficient elevator capacity, and greatly improve elevator operating efficiency.

[0140] In some embodiments, a computer-readable storage medium is provided storing a computer program, which, when executed by a processor, causes the processor to perform an optimized elevator dispatching method according to the above method embodiments.

[0141] In some embodiments, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs an optimized elevator dispatching method according to the above method embodiments.

[0142] Figure 4 The diagram illustrates the internal structure of a computer device in some embodiments. This computer device may specifically be a terminal, a server, or a gateway. Figure 4 As shown, the computer device includes a processor, memory, and network interface connected via a system bus.

[0143] The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When executed by a processor, this computer program causes the processor to perform the steps in the above method embodiments. The internal memory may also store a computer program, which, when executed by a processor, causes the processor to perform the steps in the above method embodiments. Those skilled in the art will understand that... Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0144] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods.

[0145] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0146] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0147] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for optimizing elevator dispatching, characterized in that The method includes: Based on machine learning, multiple simulated elevator ride information for each time period of the day is obtained from multiple historical elevator ride information for each time period. Based on multiple simulated elevator usage data for different time periods of the day, determine multiple simulated elevator dispatch plans and simulated traffic flows for each time period of the day. When the simulated traffic flow in the k-th time period is greater than the traffic flow threshold, a first difference between the simulated traffic flow in the k-th time period and the traffic flow threshold is determined. Based on machine learning, multiple push elevator information is determined according to multiple simulated elevator riding information in the kth time period, the first difference, and the first preset optimization rule; Multiple push elevator ride information messages are sent to the corresponding smart terminals, and the first push time is recorded; When the time difference between the current time and the first push time is equal to a preset duration, the push elevator information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatching scheme is updated according to the push elevator information. Here, k takes the values ​​of integers greater than 0, until k equals the total number of time periods in the simulated traffic flow; Wherein, after determining the push elevator information corresponding to the smart terminal that issued the preset feedback signal when the time difference between the current time and the first push time is equal to a preset duration, and updating the corresponding simulated elevator dispatch scheme according to the push elevator information, the method further includes: When the time difference between the current time and the first push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than a preset threshold, then multiple secondary simulated elevator information in the k-th time period is determined based on multiple pushed elevator information and multiple simulated elevator information in the k-th time period. The secondary simulated traffic flow for the k-th time period is determined based on multiple secondary simulated elevator ride information and multiple simulated elevator ride information corresponding to multiple push elevator ride information that did not issue a preset feedback signal. Determine the second difference between the secondary simulated traffic flow in the k-th time period and the traffic flow threshold; Based on machine learning, multiple secondary push elevator information is determined according to multiple secondary simulated elevator riding information in the kth time period, the second difference, and the first preset optimization rule; Multiple secondary push elevator ride information messages are sent to the corresponding smart terminals, and the time of the second push is recorded; When the time difference between the current time and the second push time is equal to the preset duration, the secondary push elevator information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatching scheme is updated according to the secondary push elevator information. Similarly, when the time difference between the current time and the p-th push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than the preset threshold, then multiple p+1 simulated elevator information in the k-th time period are determined based on multiple p-th push elevator information and multiple p-th simulated elevator information in the k-th time period. The p+1 simulated elevator flow in the k-th time period is determined based on the multiple p+1 simulated elevator ride information in the k-th time period, the multiple simulated elevator ride information corresponding to the multiple push elevator ride information that did not issue a preset feedback signal, and the multiple p simulated elevator ride information corresponding to the multiple p push elevator ride information that did not issue a preset feedback signal. Determine the (p+1)th difference between the simulated traffic flow in the kth time period and the traffic flow threshold; Based on machine learning, multiple p+1 simulated elevator ride information are determined according to the multiple p+1 simulated elevator ride information in the kth time period, the p+1th difference, and the first preset optimization rule; Multiple p+1 push elevator information messages are sent to the corresponding smart terminals, and the time of the p+1th push is recorded. When the time difference between the current time and the p+1th push time is equal to the preset duration, determine the p+1th push of elevator information corresponding to the smart terminal that issued the preset feedback signal, and update the corresponding simulated elevator dispatch scheme according to the p+1th push of elevator information. Where p takes integers greater than 1 in sequence, until the time difference between the current time and the (p+1)th push time is equal to the preset duration, there are no smart terminals that have not issued a preset feedback signal, or there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is less than or equal to the preset threshold.

2. The method of claim 1, wherein, When the time difference between the current time and the first push time is equal to a preset duration, the method further includes determining the push elevator information corresponding to the smart terminal that issued the preset feedback signal, and updating the corresponding simulated elevator dispatch scheme according to the push elevator information. Obtain multiple elevator usage information for the current and next time period; The traffic flow for the current and next time periods is determined based on multiple elevator usage information for the current and next time periods. When the traffic flow in the current next time period is greater than the traffic flow threshold, a third difference between the traffic flow in the current next time period and the traffic flow threshold is determined. Based on machine learning, multiple elevator ride information to be pushed in the current next time period are determined according to multiple elevator ride information in the current next time period, the third difference, and the second preset optimization rule; Multiple current and next time period push elevator information to the corresponding smart terminals, and record the third push time; When the time difference between the current time and the third push time is equal to the preset duration, the elevator information for the next time period corresponding to the smart terminal that issued the preset feedback signal is determined, and the elevator dispatching scheme for the next time period is updated according to the elevator information for the next time period.

3. The method of claim 2, wherein, When the time difference between the current time and the third push time is equal to the preset duration, the method further includes determining the next time period for pushing elevator information corresponding to the smart terminal that issued the preset feedback signal, and updating the corresponding elevator dispatching plan for the next time period based on the elevator information pushed in the next time period. When the time difference between the current time and the third push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than a preset threshold, then multiple secondary elevator information for the current next time period is determined based on multiple elevator information pushed in the current next time period and multiple elevator information for the current next time period. The secondary traffic flow for the current next time period is determined based on multiple secondary elevator ride information for the current next time period and multiple elevator ride information for the current next time period corresponding to multiple elevator ride information pushed for the current next time period without issuing a preset feedback signal. Determine the fourth difference between the secondary traffic flow in the current next time period and the traffic flow threshold; Based on machine learning, multiple secondary elevator ride information for the current next time period are determined according to the multiple secondary elevator ride information of the current next time period, the fourth difference, and the second preset optimization rule; Multiple current and next time period elevator ride information are pushed to the corresponding smart terminals, and the fourth push time is recorded; When the time difference between the current time and the fourth push time is equal to the preset duration, determine the second push of elevator information for the current next time period corresponding to the smart terminal that issued the preset feedback signal, and update the corresponding elevator dispatching scheme for the current next time period according to the second push of elevator information for the current next time period. Similarly, when the time difference between the current time and the (q+2)th push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than the preset threshold, then multiple (q+1) elevator ride information in the current next time period are determined based on multiple (q) push elevator ride information in the current next time period and multiple (q) elevator ride information in the current next time period. The traffic flow for the current next time period is determined based on multiple q+1 elevator ride information in the current next time period, multiple elevator ride information pushed in the current next time period corresponding to multiple current next time period without issuing a preset feedback signal, and multiple q elevator ride information pushed in the current next time period q times corresponding to multiple current next time period without issuing a preset feedback signal. Determine the (q+1)th difference between the traffic flow in the current next time period and the (q+3)th traffic flow threshold. Based on machine learning, multiple elevator ride information pushes for the current next time period are determined according to multiple q+1 elevator ride information in the current next time period, the q+3rd difference, and the second preset optimization rule. Push elevator information for the current next time period q+1 times to the corresponding smart terminal, and record the push time of the q+3th push. When the time difference between the current time and the q+3th push time is equal to the preset duration, determine the current next time period q+1 push elevator information corresponding to the smart terminal that issued the preset feedback signal, and update the corresponding current next time period elevator dispatching scheme according to the current next time period q+1 push elevator information. Wherein, q takes integers greater than 1 in sequence until the time difference between the current time and the (q+3)th push time is equal to the preset duration, at which point there is no smart terminal that has not issued a preset feedback signal, or there is a smart terminal that has not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is less than or equal to the preset threshold.

4. The method of claim 1, wherein, The method further includes: When the time difference between the current time and the first push time is equal to a preset duration, the smart terminal that has not issued a preset feedback signal is identified, and the corresponding push elevator information is eliminated by controlling the smart terminal.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: In the event of an elevator malfunction, obtain elevator malfunction information; Based on the elevator malfunction information, determine multiple elevator travel options for the malfunctioning elevator in the current time period, and based on the multiple elevator travel options for the malfunctioning elevator in the current time period, determine multiple elevator travel information for the malfunctioning elevator in the current time period. Based on machine learning, multiple elevator notification messages are determined according to multiple elevator usage information of the faulty elevator in the current time period and a third preset optimization rule. Based on multiple notifications of elevator usage information, determine multiple elevator usage plans for the faulty elevator in the current time period.

6. The method of claim 5, wherein, Before or after determining multiple elevator access plans for the faulty elevator in the current time period based on multiple elevator access notifications, the method further includes: Multiple elevator access notifications are pushed to the corresponding smart terminals, prompting the smart terminals to issue audio and visual alerts.

7. An elevator dispatching optimization device, characterized by The device includes: The first simulation module is used to obtain multiple simulated elevator ride information for each time period of the day based on machine learning and multiple historical elevator ride information for each time period. The second simulation module is used to determine multiple simulated elevator dispatching schemes and simulated traffic flow for each time period of the day based on multiple simulated elevator riding information for each time period of the day. The first judgment module is used to determine the first difference between the simulated traffic flow in the k-th time period and the traffic flow threshold when the simulated traffic flow in the k-th time period is greater than the traffic flow threshold. The elevator ride information determination module is used to determine multiple elevator ride information based on machine learning, according to multiple simulated elevator ride information in the kth time period, the first difference, and the first preset optimization rule; The push module is used to push multiple elevator ride information to the corresponding smart terminals and record the first push time; The second judgment module is used to determine the push elevator information corresponding to the smart terminal that issued the preset feedback signal when the time difference between the current time and the first push time is equal to a preset duration, and update the corresponding simulated elevator dispatching scheme according to the push elevator information. The sequential value selection module is used to sequentially select integers greater than 0 for k until k equals the total number of time periods of the simulated traffic flow; Wherein, after determining the push elevator information corresponding to the smart terminal that issued the preset feedback signal when the time difference between the current time and the first push time is equal to a preset duration, and updating the corresponding simulated elevator dispatch scheme according to the push elevator information, the method further includes: When the time difference between the current time and the first push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than a preset threshold, then multiple secondary simulated elevator information in the k-th time period is determined based on multiple pushed elevator information and multiple simulated elevator information in the k-th time period. The secondary simulated traffic flow for the k-th time period is determined based on multiple secondary simulated elevator ride information and multiple simulated elevator ride information corresponding to multiple push elevator ride information that did not issue a preset feedback signal. Determine the second difference between the secondary simulated traffic flow in the k-th time period and the traffic flow threshold; Based on machine learning, multiple secondary push elevator information is determined according to multiple secondary simulated elevator riding information in the kth time period, the second difference, and the first preset optimization rule; Multiple secondary push elevator ride information messages are sent to the corresponding smart terminals, and the time of the second push is recorded; When the time difference between the current time and the second push time is equal to the preset duration, the secondary push elevator information corresponding to the smart terminal that issued the preset feedback signal is determined, and the corresponding simulated elevator dispatching scheme is updated according to the secondary push elevator information. Similarly, when the time difference between the current time and the p-th push time is equal to the preset duration, there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is greater than the preset threshold, then multiple p+1 simulated elevator information in the k-th time period are determined based on multiple p-th push elevator information and multiple p-th simulated elevator information in the k-th time period. The p+1 simulated elevator flow in the k-th time period is determined based on the multiple p+1 simulated elevator ride information in the k-th time period, the multiple simulated elevator ride information corresponding to the multiple push elevator ride information that did not issue a preset feedback signal, and the multiple p simulated elevator ride information corresponding to the multiple p push elevator ride information that did not issue a preset feedback signal. Determine the (p+1)th difference between the simulated traffic flow in the kth time period and the traffic flow threshold. Based on machine learning, multiple p+1 simulated elevator ride information are determined according to the multiple p+1 simulated elevator ride information in the kth time period, the p+1th difference, and the first preset optimization rule; Multiple p+1 push elevator information messages are sent to the corresponding smart terminals, and the time of the p+1th push is recorded. When the time difference between the current time and the p+1th push time is equal to the preset duration, determine the p+1th push of elevator information corresponding to the smart terminal that issued the preset feedback signal, and update the corresponding simulated elevator dispatch scheme according to the p+1th push of elevator information. Where p takes integers greater than 1 in sequence, until the time difference between the current time and the (p+1)th push time is equal to the preset duration, there are no smart terminals that have not issued a preset feedback signal, or there are smart terminals that have not issued a preset feedback signal, and the number of smart terminals that have not issued a preset feedback signal is less than or equal to the preset threshold.

8. A computer-readable storage medium, characterized in that, The system stores a computer program that, when executed by a processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 6.

9. A computer device, comprising: It includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 6.

Images