An elevator task control method and system based on medical logistics robot scheduling

Abstract

The present invention relates to the field of elevator control technology, and discloses an elevator task control method and system based on medical logistics robot scheduling, the method comprising: identifying the robot position, power information, scheduling tasks to be executed, and the elevator floor, running direction, whether it is fully loaded, and the floor where the elevator needs to stop of the available medical logistics robot according to the scheduling task of the medical logistics robot, and constructing a distribution combination, constructing an evaluation function according to the robot path length of each scheduling task in the allocation combination and the time of taking the corresponding available elevator, and optimizing the scheduling based on the evaluation function to obtain the target medical logistics robot and the target available elevator; constructing a target control signal according to the target medical logistics robot and the target available elevator; generating a scheduling path for the target medical logistics robot, and performing elevator task control on the target available elevator according to the scheduling path and the target control signal. The present invention can improve the accuracy of elevator task control.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator control, and in particular to an elevator task control method and system based on medical logistics robot scheduling. Background Art

[0002] Medical logistics robots are automated devices used to transport various medical supplies (such as medicines, equipment, samples, etc.) and daily necessities (such as bedding, food, etc.) within hospitals. Medical logistics robots can move between various departments, wards, and warehouses in hospitals according to preset routes or received instructions. When medical supplies need to be transported, the dispatch center assigns transportation tasks to the logistics robots based on the robot's current location, task queue, and elevator operating status.

[0003] However, in large medical institutions, there may be multiple medical logistics robots that need to use multiple elevators at the same time. Existing control methods may have problems with uneven resource allocation and chaotic scheduling when dealing with the coordinated scheduling of multiple robots and multiple elevators. For example, multiple robots may be waiting for one elevator at the same time, while other elevators are idle, resulting in low overall transportation efficiency. At the same time, existing elevator task control methods focus more on the task execution of a single medical logistics robot and the local scheduling of elevators, but lack global optimization of the entire hospital logistics system, resulting in poor accuracy of elevator task control.

[0004] Therefore, how to improve the accuracy of elevator task control under medical logistics robot scheduling has become an urgent problem to be solved. Summary of the invention

[0005] The present invention provides an elevator task control method and system based on medical logistics robot scheduling, the main purpose of which is to solve the problem of poor accuracy of elevator task control under medical logistics robot scheduling.

[0006] To achieve the above purpose, the present invention provides an elevator task control method based on medical logistics robot scheduling, comprising:

[0007] Obtain the scheduling tasks of the medical logistics robot, and identify the robot position, power information, scheduling tasks to be executed, and the floor, running direction, full load, and floor at which the elevator needs to stop of the available medical logistics robot according to the scheduling tasks;

[0008] According to the robot position, power information, scheduling tasks to be performed, and the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop, a distribution combination of the available medical logistics robots and the available elevators for the scheduling task allocation is constructed, and the robot path length of each scheduling task in the distribution combination and the time to take the corresponding available elevator are calculated;

[0009] Performing a weighted summation on the robot path length and the time of taking the corresponding available elevator to obtain an evaluation function, and performing scheduling optimization on the allocation combination based on the evaluation function to obtain a target medical logistics robot and a target available elevator corresponding to the scheduling task;

[0010] Generate an elevator control signal according to the target medical logistics robot and the target available elevator, extract a signal weakness feature of the elevator control signal, and construct a target control signal according to the signal weakness feature;

[0011] Generate a scheduling path for the target medical logistics robot, and perform elevator task control on the target available elevator according to the scheduling path and the target control signal.

[0012] Optionally, the identifying, according to the scheduling task, the robot position, power information, the scheduling task to be executed, and the elevator floor, running direction, whether it is fully loaded, and the floor at which the elevator needs to stop of the available medical logistics robot, includes:

[0013] According to the scheduling task, robot status signals of a preset medical logistics robot set and elevator status signals and elevator car images of a preset elevator are collected;

[0014] Performing signal channel conversion on the robot state signal and the elevator state signal respectively to obtain signal characteristics of the robot state signal and the elevator state signal;

[0015] Identify whether the preset elevator is fully loaded according to the elevator car picture;

[0016] According to the signal characteristics, the signal status is identified to obtain the robot position, power information, scheduling tasks to be executed, the floor where the elevator is located, the running direction, and the floor where the elevator needs to stop of the available medical logistics robot;

[0017] According to whether the preset elevator is fully loaded, the floor where the elevator is located, the running direction, and the floor where the elevator needs to stop, the floor where the available elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop are identified.

[0018] Optionally, performing signal channel conversion on the robot state signal and the elevator state signal respectively to obtain signal characteristics of the robot state signal and the elevator state signal includes:

[0019] Performing wavelet transform, Hilbert-Huang transform and signal bispectral transform on the robot state signal and the elevator state signal respectively to obtain a transform coefficient matrix;

[0020] A three-dimensional coefficient image of the transformation coefficient matrix is ​​constructed, and two-dimensional mapping is performed on the three-dimensional coefficient image to obtain signal characteristics of the robot state signal and the elevator state signal.

[0021] Optionally, the allocation combination of the available medical logistics robots and the available elevators for the scheduling task allocation is constructed according to the robot position, power information, the scheduling task to be executed, the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop, including:

[0022] Determine the path execution node according to the robot position, power information, the scheduling task to be executed, the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop;

[0023] Allocate available medical logistics robots and available elevators to the scheduling task according to the path execution nodes to obtain an initial task allocation;

[0024] An allocation combination is constructed based on the initial assignment of tasks.

[0025] Optionally, the calculating of the robot path length of each scheduling task in the allocation combination and the time to take a corresponding available elevator comprises:

[0026] Calculating the robot path length of each scheduling task in the allocation combination;

[0027] Calculate the elevator waiting time, elevator riding time and elevator energy consumption according to the elevator floor, running direction, whether it is fully loaded, and the floor where the elevator needs to stop of the available elevators in each of the scheduling tasks;

[0028] The following formula is used to calculate the elevator waiting time, elevator riding time and elevator energy consumption:

[0029] in, Indicates the elevator waiting time. Indicates the available elevators in floors, Indicates the current floor where the available elevator is located. Indicates the floor where the available medical logistics robots corresponding to the available elevators are located. Indicates the elevator speed of the preset available elevators, Indicates the number of times an available elevator needs to stop to let passengers off in the elevator status. Indicates the preset average time for each stop. Indicates the elevator ride time. Indicates the number of times the available elevator needs to stop to let passengers off when executing the scheduling task. represents the energy consumption of the elevator, Indicates the number of available elevator starts and stops, Indicates the preset average energy consumption of available elevators each time they start and stop;

[0030] The time for taking a corresponding available elevator is determined according to the elevator waiting time, the elevator riding time and the elevator energy consumption.

[0031] Optionally, the scheduling optimization of the allocation combination based on the evaluation function to obtain a target medical logistics robot and a target available elevator corresponding to the scheduling task includes:

[0032] Initializing a particle population, and calculating an evaluation function value of each particle in the particle population according to the evaluation function;

[0033] Performing population migration on the particle population according to the evaluation function value to obtain a migrated particle population;

[0034] Calculating the migration evaluation function value of each particle in the migrating particle population, iterating the migrating particle population according to the migration evaluation function value until the number of iterations of the migrating particle population is greater than a preset iteration number threshold, thereby obtaining a target particle population;

[0035] Target particles are selected according to the target particle population, and the allocation combination is scheduled and optimized according to the target particles to obtain a target medical logistics robot and a target available elevator corresponding to the scheduling task.

[0036] Optionally, performing population migration on the particle population according to the evaluation function value to obtain a migrated particle population includes:

[0037] Calculating the variable-scale black hole radius and displacement coefficient of the particle population;

[0038] The variable-scale black hole radius and displacement coefficient of the particle population are calculated using the following formula:

[0039] in, represents the radius of the variable-scale black hole, Represents the preset initial value of the black hole scale, Indicates the final value of the preset black hole scale, Indicates the current iteration number, Represents the preset iteration number threshold, represents the displacement coefficient, represents the preset initial displacement coefficient, represents the preset final displacement coefficient, express A random number, Indicates a preset first mapping relationship;

[0040] Calculating the update speed and update position of the particle population based on the variable-scale black hole radius and the displacement coefficient;

[0041] The update speed and update position of the particle population are calculated using the following formula:

[0042] in,

[0043] Indicates that the particle in the particle population is The update speed at the iteration, represents the preset inertia weight, is the particle in the particle population. The speed at the iteration, represents the preset first learning factor, represents the preset second learning factor, , , , express A random number, represents the individual optimal position of the particle, represents the global optimal position of the particle, Indicates that the particle The position at the iteration, Indicates that the particle The updated position at the iteration, represents the displacement coefficient, represents the radius of the variable-scale black hole, , , They represent the preset first black hole attraction probability, second black hole attraction probability, and third black hole attraction probability, respectively. , Represent the randomly generated Particles and The particle in The position at the iteration, They represent the sensory factor, fragrance stimulation intensity and power index preset in the butterfly optimization algorithm respectively;

[0044] The particle population is updated according to the update speed and the update position to obtain a migration particle population.

[0045] Optionally, extracting the signal weakness feature of the elevator control signal includes:

[0046] Performing wavelet transform on the elevator control signal to obtain transform coefficients;

[0047] Performing threshold processing on the transform coefficients to obtain target transform coefficients;

[0048] A signal weakness feature of the elevator control signal is identified according to the target transformation coefficient.

[0049] Optionally, generating a dispatch path for the target medical logistics robot includes:

[0050] Obtaining a dispatch map corresponding to the target medical logistics robot, and performing semantic segmentation on the dispatch map to obtain a segmented map;

[0051] Performing convolution erosion on the segmentation map to obtain an obstacle probability map;

[0052] Constructing a replacement point map corresponding to the target medical logistics robot according to the obstacle probability map;

[0053] The path of the target medical logistics robot is planned according to the replacement point map to obtain a scheduling path for the target medical logistics robot.

[0054] In order to solve the above problems, the present invention also provides an elevator task control system based on medical logistics robot scheduling, the system comprising:

[0055] A state recognition module is used to obtain the scheduling tasks of the medical logistics robot, and identify the robot position, power information, scheduling tasks to be executed, and the floor, running direction, full load, and floor at which the elevator needs to stop of the available medical logistics robot according to the scheduling tasks;

[0056] A task index calculation module is used to construct an allocation combination of the available medical logistics robots and the available elevators for the scheduling task allocation according to the robot position, power information, the scheduling task to be executed, and the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop, and calculate the robot path length of each scheduling task in the allocation combination and the time to take the corresponding available elevator;

[0057] A scheduling optimization module, used to perform a weighted summation of the robot path length and the time of taking the corresponding available elevator to obtain an evaluation function, and perform scheduling optimization on the allocation combination based on the evaluation function to obtain a target medical logistics robot and a target available elevator corresponding to the scheduling task;

[0058] A target control signal construction module, used to generate an elevator control signal according to the target medical logistics robot and the target available elevator, extract a signal weakness feature of the elevator control signal, and construct a target control signal according to the signal weakness feature;

[0059] The elevator task control module is used to generate a scheduling path for the target medical logistics robot and perform elevator task control on the target available elevator according to the scheduling path and the target control signal.

[0060] The embodiment of the present invention can reduce the problem of re-assigning tasks due to the inability to execute scheduling tasks when performing task scheduling by identifying the robot position, power information, scheduling tasks to be executed, and the floor where the available elevators are located, the running direction, whether they are fully loaded, and the floor where the elevators need to stop of the available medical logistics robots, thereby effectively improving the execution efficiency and accuracy; constructing a distribution combination according to the robot state and the elevator state, calculating the robot path length of each scheduling task in the distribution combination and the time to take the corresponding available elevator, which can reduce unnecessary time waste when performing scheduling task allocation and more accurately control the elevator system; scheduling optimization is performed on the distribution combination to obtain the corresponding target medical logistics robot and the target available elevator, and an elevator control signal is generated according to the target medical logistics robot and the target available elevator to construct a target control signal, which can retain useful information in the elevator control signal, remove noise interference on the propagation of the elevator control signal, and improve the accuracy of the control of the target available elevator; generating a scheduling path for the target medical logistics robot, and performing elevator task control on the target available elevator according to the scheduling path and the target control signal, which can ensure that the target medical logistics robot accurately executes the scheduling task, and effectively improve the accuracy of the elevator task control. Therefore, the elevator task control method and system based on medical logistics robot scheduling proposed in the present invention can solve the problem of poor accuracy of elevator task control. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A flow chart of an elevator task control method based on medical logistics robot scheduling provided by an embodiment of the present invention;

[0062] Figure 2 A schematic diagram of a process for constructing a distribution combination provided by an embodiment of the present invention;

[0063] Figure 3 A schematic diagram of a process for extracting signal weakness characteristics of an elevator control signal provided by an embodiment of the present invention;

[0064] Figure 4 A functional module diagram of an elevator task control system based on medical logistics robot scheduling provided by one embodiment of the present invention.

[0065] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0066] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0067] The embodiment of the present application provides an elevator task control method based on medical logistics robot scheduling. The execution subject of the elevator task control method based on medical logistics robot scheduling includes but is not limited to at least one of the electronic devices such as the server, terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the elevator task control method based on medical logistics robot scheduling can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0068] Reference Figure 1 FIG. 1 is a flow chart of an elevator task control method based on medical logistics robot scheduling provided by an embodiment of the present invention. In this embodiment, the elevator task control method based on medical logistics robot scheduling includes:

[0069] S1. Obtain the scheduling task of the medical logistics robot, and identify the robot position, power information, scheduling tasks to be executed, and the floor where the available elevators are located, the running direction, whether they are fully loaded, and the floor where the elevator needs to stop according to the scheduling task.

[0070] In the embodiment of the present invention, the dispatching task is a task that needs to be performed by a medical logistics robot in a medical institution, such as transporting various medical supplies and daily necessities, etc. The medical logistics robot is equipped with a positioning and navigation system, such as laser navigation, visual navigation, etc., which can accurately plan and move along a preset path. At the same time, the medical logistics robot is equipped with a communication module, which can communicate with the elevator control system and the hospital logistics management system in a two-way manner to realize the control of the elevator.

[0071] Among them, the available medical logistics robots are medical logistics robots that can perform scheduling tasks, including but not limited to robots that are performing tasks and robots that are dormant and waiting for tasks. The robot status includes the robot's location, power information, scheduling tasks to be executed, etc.; the elevator status is the status of the elevator that can be used in the medical institution. The elevator status includes the floor where the elevator is located, the direction of operation, whether it is fully loaded, the floor where the elevator needs to stop, etc.

[0072] In an embodiment of the present invention, the method of identifying the robot position, power information, to-be-executed scheduling tasks, and the elevator floor, running direction, full load, and the floor at which the elevator needs to stop of the available medical logistics robot according to the scheduling task includes:

[0073] According to the scheduling task, robot status signals of a preset medical logistics robot set and elevator status signals and elevator car images of a preset elevator are collected;

[0074] Performing signal channel conversion on the robot state signal and the elevator state signal respectively to obtain signal characteristics of the robot state signal and the elevator state signal;

[0075] Identify whether the preset elevator is fully loaded according to the elevator car picture;

[0076] According to the signal characteristics, the signal status is identified to obtain the robot position, power information, scheduling tasks to be executed, the floor where the elevator is located, the running direction, and the floor where the elevator needs to stop of the available medical logistics robot;

[0077] According to whether the preset elevator is fully loaded, the floor where the elevator is located, the running direction, and the floor where the elevator needs to stop, the floor where the available elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop are identified.

[0078] In an embodiment of the present invention, robot status signals of a set of available medical logistics robots and elevator status signals and elevator car images of preset elevators are collected according to scheduling tasks. They can be obtained based on sensors installed in each medical logistics robot and each elevator, and elevator car images can be collected based on monitoring equipment installed in each elevator, thereby determining the status of each medical logistics robot and each elevator when multiple scheduling tasks are released.

[0079] In detail, the signal channel conversion is to transform the three signal channels of the state signal, generate a three-dimensional image of the coefficient matrix, and then project the image onto an appropriate two-dimensional plane to obtain the projection image features of the three channels, that is, the signal features of the robot state signal and the elevator state signal. The signal features include the time-frequency information and nonlinear features of the robot state signal and the elevator state signal, which can more accurately reflect the characteristics of the robot state signal and the elevator state signal.

[0080] Furthermore, the performing signal channel conversion on the robot state signal and the elevator state signal respectively to obtain signal characteristics of the robot state signal and the elevator state signal includes:

[0081] Performing wavelet transform, Hilbert-Huang transform and signal bispectral transform on the robot state signal and the elevator state signal respectively to obtain a transform coefficient matrix;

[0082] A three-dimensional coefficient image of the transformation coefficient matrix is ​​constructed, and two-dimensional mapping is performed on the three-dimensional coefficient image to obtain signal characteristics of the robot state signal and the elevator state signal.

[0083] In the embodiment of the present invention, the wavelet transform can highlight the subtle regional characteristics of the signal by performing localized analysis on the time (space) frequency. The Hilbert-Huang transform first performs empirical mode decomposition (EMD) on the signal to obtain a series of intrinsic mode functions, and then performs Hilbert transform on the intrinsic mode functions to obtain the Hilbert coefficient matrix. The signal bispectral transform can effectively suppress a certain amount of Gaussian noise, so that the leakage source noise is fully reflected in the bispectral information. These transform coefficient matrices can be visualized in three dimensions using tools such as Matlab to obtain three-dimensional coefficient images, and then two-dimensional mapping is performed according to different channel transformations to obtain signal characteristics.

[0084] Furthermore, the time domain of the three-dimensional coefficient image after wavelet transform and Hilbert-Huang transform can be projected to the frequency domain (YZ plane); the three-dimensional coefficient image of the signal bispectral transform can be mapped to the bispectral feature represented by the projection viewing angle (−45, ​​0, 0) to obtain the final signal characteristics after the three signal channels are transformed.

[0085] In the embodiment of the present invention, the signal features can be fused and then input into the pre-built convolutional neural network to classify and identify the medical logistics robot set and the elevator status of the preset elevator, and obtain the robot status and elevator operation status. At the same time, the elevator car image can be spatially identified to determine whether there is enough space in the elevator car to accommodate the medical logistics robot and determine the transportation status of the preset elevator. The pre-trained neural network can be used to classify the elevator car image to determine the transportation status.

[0086] In detail, the available medical logistics robots and available elevators are determined according to the signal characteristics, and then the robot status of the available medical logistics robots and the elevator status of the available elevators are obtained. This can reduce the problem of re-assigning tasks due to the inability to execute scheduling tasks during task scheduling, and effectively improve the execution efficiency and accuracy of scheduling tasks.

[0087] S2. Construct an allocation combination of the available medical logistics robots and the available elevators for the scheduling task allocation according to the robot position, power information, scheduling tasks to be executed, the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop, and calculate the robot path length of each scheduling task in the allocation combination and the time to take the corresponding available elevator.

[0088] In an embodiment of the present invention, the allocation combination is to allocate the corresponding available medical logistics robots and available elevators to each scheduling task based on the robot status and the elevator status to ensure the execution of the scheduling task, wherein one available medical logistics robot can execute multiple scheduling tasks, one scheduling task can be executed by multiple available medical logistics robots, and one available elevator can carry more than one available medical logistics robot.

[0089] For details, see Figure 2 As shown, the allocation combination of the available medical logistics robots and the available elevators for the scheduling task allocation is constructed according to the robot position, power information, the scheduling task to be executed, the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop, including:

[0090] S21, determining a path execution node according to the robot position, power information, the scheduling task to be executed, the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop;

[0091] S22, allocating available medical logistics robots and available elevators to the scheduling task according to the path execution nodes to obtain initial task allocation;

[0092] S23: constructing an allocation combination according to the initial task allocation.

[0093] In an embodiment of the present invention, the path execution node is the position of each available medical logistics robot and the position and current floor of an available elevator. An available medical logistics robot and an available elevator are allocated to each scheduling task through the path execution node, wherein a preset allocation rule may be used, for example, the proximity principle, selecting the available medical logistics robot or available elevator closest to the starting point or end point of the scheduling task; the priority principle, allocating medical logistics robots or available elevators according to the emergency situation of the scheduling task, determining the available medical logistics robots and available elevators corresponding to each scheduling task according to the initial task allocation, and obtaining the allocation combination of the entire scheduling task.

[0094] In detail, the allocation combination is a combination of available medical logistics robots and available elevators assigned to each scheduling task. The allocation combination can be used to clarify the allocation of scheduling tasks and ensure the execution of scheduling tasks.

[0095] In an embodiment of the present invention, the robot task indicator is the path length of the medical logistics robot in each scheduling task, including the path length to the starting point of the scheduling task execution and the path length to the corresponding available elevator. The elevator task indicator represents the time to take the corresponding available elevator, wherein the time to take the corresponding available elevator may include the waiting time and the time to take the elevator.

[0096] Specifically, the calculating of the robot path length of each scheduling task in the allocation combination and the time to take the corresponding available elevator includes:

[0097] Calculating the robot path length of each scheduling task in the allocation combination;

[0098] Calculate the elevator waiting time, elevator riding time and elevator energy consumption according to the elevator floor, running direction, whether it is fully loaded, and the floor where the elevator needs to stop of the available elevators in each of the scheduling tasks;

[0099] The time for taking a corresponding available elevator is determined according to the elevator waiting time, the elevator riding time and the elevator energy consumption.

[0100] In an embodiment of the present invention, the distance between the available medical logistics robot corresponding to each scheduling task and the corresponding available elevator is used as the robot path length. A map of the medical institution can be constructed for path planning to obtain the robot path length.

[0101] Furthermore, the following formula is used to calculate the elevator waiting time, elevator riding time and elevator energy consumption:

[0102] in, Indicates the elevator waiting time. Indicates the available elevators in floors, Indicates the current floor where the available elevator is located. Indicates the floor where the available medical logistics robots corresponding to the available elevators are located. Indicates the elevator speed of the preset available elevators, Indicates the number of times an available elevator needs to stop to let passengers off in the elevator status. Indicates the preset average time for each stop. Indicates the elevator ride time. Indicates the number of times the available elevator needs to stop to let passengers off when executing the scheduling task. represents the energy consumption of the elevator, Indicates the number of available elevator starts and stops, Indicates the preset average energy consumption of available elevators each time they start and stop.

[0103] In an embodiment of the present invention, the elevator waiting time, the elevator riding time and the elevator energy consumption are added together to obtain the time for taking the corresponding available elevator. The time for taking the corresponding available elevator and the robot path can reduce unnecessary time waste when allocating scheduling tasks, improve the efficiency of scheduling task execution, and control the elevator system more accurately.

[0104] S3. Take a weighted sum of the robot path length and the time of taking the corresponding available elevator to obtain an evaluation function, and optimize the allocation combination based on the evaluation function to obtain the target medical logistics robot and target available elevator corresponding to the scheduling task.

[0105] In an embodiment of the present invention, the evaluation function is an objective function that comprehensively evaluates the efficiency and accuracy of the scheduling task. The robot task indicators and the elevator task indicators can be weighted and summed to obtain the evaluation function. The scheduling tasks in the allocation combination are optimized by taking the minimum value of the evaluation function as the objective function to obtain a more accurate target medical logistics robot and a target available elevator corresponding to each scheduling task.

[0106] Furthermore, the scheduling optimization of the allocation combination based on the evaluation function to obtain the target medical logistics robot and the target available elevator corresponding to the scheduling task includes:

[0107] Initializing a particle population, and calculating an evaluation function value of each particle in the particle population according to the evaluation function;

[0108] Performing population migration on the particle population according to the evaluation function value to obtain a migrated particle population;

[0109] Calculating the migration evaluation function value of each particle in the migrating particle population, iterating the migrating particle population according to the migration evaluation function value until the number of iterations of the migrating particle population is greater than a preset iteration number threshold, thereby obtaining a target particle population;

[0110] Target particles are selected according to the target particle population, and the allocation combination is scheduled and optimized according to the target particles to obtain a target medical logistics robot and a target available elevator corresponding to the scheduling task.

[0111] In detail, each particle in the particle population is based on each scheduling task in the allocation combination and the available medical logistics robots and available elevators that perform the scheduling tasks. That is, each particle represents a possibility of scheduling task allocation in the allocation combination. By calculating the evaluation function value of each particle, the particle population is iterated to find the target particle with the smallest evaluation function value, and the target medical logistics robot and target available elevator corresponding to each scheduling task in the allocation combination are obtained.

[0112] In the embodiment of the present invention, the step of performing population migration on the particle population according to the evaluation function value to obtain a migrated particle population includes:

[0113] Calculating the variable-scale black hole radius and displacement coefficient of the particle population;

[0114] Calculating the update speed and update position of the particle population based on the variable-scale black hole radius and the displacement coefficient;

[0115] The particle population is updated according to the update speed and the update position to obtain a migration particle population.

[0116] In detail, the variable-scale black hole radius and displacement coefficient of the particle population are calculated using the following formula:

[0117] in, represents the radius of the variable-scale black hole, Represents the preset initial value of the black hole scale, Indicates the final value of the preset black hole scale, Indicates the current iteration number, Represents the preset iteration number threshold, represents the displacement coefficient, represents the preset initial displacement coefficient, represents the preset final displacement coefficient, express A random number, Indicates a preset first mapping relationship.

[0118] In the embodiment of the present invention, the variable-scale black hole radius of the variable black hole mechanism can make the particles move quickly to the vicinity of the global optimum, thereby achieving rapid optimization. The displacement coefficient can make the particles carefully optimize in a local range with a smaller displacement, thereby improving the convergence accuracy of the algorithm.

[0119] Furthermore, the update speed and update position of the particle population are calculated using the following formula:

[0120] in,

[0121] Indicates that the particle in the particle population is The update speed at the iteration, represents the preset inertia weight, is the particle in the particle population. The speed at the iteration, represents the preset first learning factor, represents the preset second learning factor, , , , express A random number, represents the individual optimal position of the particle, represents the global optimal position of the particle, Indicates that the particle The position at the iteration, Indicates that the particle The updated position at the iteration, represents the displacement coefficient, represents the radius of the variable-scale black hole, , , They represent the preset first black hole attraction probability, second black hole attraction probability, and third black hole attraction probability, respectively. , Represent the randomly generated Particles and The particle in The position at the iteration, They respectively represent the sensory factor, fragrance stimulation intensity and power exponent preset in the butterfly optimization algorithm.

[0122] In the embodiment of the present invention, the speed and position of each particle in the particle population can be migrated based on the butterfly optimization algorithm, thereby realizing population update of the particle population, which can reduce the convergence speed and optimization accuracy.

[0123] Furthermore, the particle population is updated using the following formula:

[0124] in, Particles in the The updated position of the population at the iteration, represents the global optimal position of the particle, Indicates that the particle The updated position at the iteration, Indicates a preset second mapping relationship.

[0125] In the embodiment of the present invention, the individual optimal and global optimal particles are selected by migrating the evaluation function value until the number of iterations is greater than the preset iteration number threshold, and the particle with the smallest evaluation function value in the target particle population is selected as the target particle. The allocation combination is scheduled and optimized according to the allocation of scheduling tasks in the target particle to obtain the target medical logistics robot and the target available elevator corresponding to each scheduling task.

[0126] In the embodiment of the present invention, the allocation combination is scheduled and optimized through the evaluation function, so as to improve the efficiency of the execution of the scheduling task, and at the same time, the corresponding available medical logistics robots and available elevators are allocated to each scheduling task, so as to improve the accuracy of the execution of the scheduling task.

[0127] S4. Generate an elevator control signal according to the target medical logistics robot and the target available elevator, extract the signal weakness feature of the elevator control signal, and construct a target control signal according to the signal weakness feature.

[0128] In the embodiment of the present invention, the elevator control signal is a control signal for the target medical logistics robot assigned by the scheduling task to control the corresponding target available elevator. The start and stop of the target available elevator can be controlled by the elevator control signal to achieve control of the target available elevator.

[0129] In detail, the elevator control signal can be an executable syntax command used to control the operation of the target available elevator. For example, a preset script can be used to generate an elevator control signal that can be executed by the target available elevator, such as an elevator control signal compiled by a Python script, an elevator control signal compiled by a Java script, etc., and then the signal is transmitted through the sensor on the target medical logistics robot to achieve control of the target elevator.

[0130] In another embodiment of the present invention, the signal weakness feature refers to a signal in the elevator control signal that is weak but has important information, and these features are difficult to be directly detected and extracted under a strong noise background.

[0131] In the embodiment of the present invention, refer to Figure 3 As shown, the step of extracting the signal weakness feature of the elevator control signal includes:

[0132] S31, performing wavelet transform on the elevator control signal to obtain transform coefficients;

[0133] S32, performing threshold processing on the transform coefficient to obtain a target transform coefficient;

[0134] S33. Identify a signal weakness feature of the elevator control signal according to the target transformation coefficient.

[0135] In detail, discrete wavelet transform (DWT) decomposes the elevator control signal to obtain approximate coefficients and detail coefficients, where the approximate coefficients represent the low-frequency characteristics of the signal, while the detail coefficients contain the high-frequency characteristics of the signal (such as mutations or weak signals). Therefore, the weak characteristics of the signal can be extracted by analyzing the detail coefficients.

[0136] In the embodiment of the present invention, the target signal is constructed by restoring the signal to a state close to the original state through wavelet reconstruction, while retaining the extracted weak features of the signal. The noise information in the transform coefficient can be removed through threshold processing. The useful information in the elevator control signal can be retained through signal reconstruction, and the interference of noise on the propagation of the elevator control signal can be removed, thereby improving the accuracy of the target available elevator control.

[0137] S5. Generate a dispatch path for the target medical logistics robot, and perform elevator task control on the target available elevator according to the dispatch path and the target control signal.

[0138] In an embodiment of the present invention, the scheduling path is a planned path for the target medical logistics robot to move from the starting point to the end point of the scheduling task. The movement of the target medical logistics robot is controlled by the scheduling path, and the start and stop of the target available elevator is controlled by the target control signal, thereby more accurately controlling the elevator task.

[0139] In the embodiment of the present invention, the step of generating the dispatch path of the target medical logistics robot includes:

[0140] Obtaining a dispatch map corresponding to the target medical logistics robot, and performing semantic segmentation on the dispatch map to obtain a segmented map;

[0141] Performing convolution erosion on the segmentation map to obtain an obstacle probability map;

[0142] Constructing a replacement point map corresponding to the target medical logistics robot according to the obstacle probability map;

[0143] The path of the target medical logistics robot is planned according to the replacement point map to obtain a scheduling path for the target medical logistics robot.

[0144] In one embodiment, the dispatch map can be a two-dimensional real-time map of the medical institution where the target medical logistics robot is located, including obstacles, walls, floors, etc. on the ground. Semantic segmentation is to semantically annotate objects in the dispatch map, such as walls, tables, chairs, beds, etc. However, semantic segmentation may cause semantic segmentation errors due to the adjacency of pixel points during semantic segmentation. Therefore, a 5*5 all-1 convolution kernel can be used to perform convolution erosion on the segmentation map. The pixel value on the segmentation map represents the semantic probability. For example, if a pixel point is a specific semantic point with a probability of 1 and is located inside a semantic object, the value of the point after the convolution operation is 25. Considering the position and probability of the semantic point at the same time, the points with a value greater than 23.5 after convolution are retained as specific semantic areas in the final segmentation map. The probability of semantic segmentation errors at the edge of the object can be reduced through convolution erosion, but it will not affect the quasi-grouping of path planning.

[0145] Furthermore, the alternative point map sets alternative points for some obstacles in the obstacle probability map. For example, when the end point of the scheduling task performed by the target medical logistics robot is an obstacle in the obstacle probability map, the end point of the scheduling task is replaced by the alternative point. For example, when the end point of the scheduling task is a target such as a hospital bed or a transfer station marked as an obstacle in the obstacle probability map, the path of the target medical logistics robot is planned through the alternative point map, which can avoid the problem that the end point is surrounded by obstacles and the path cannot be planned.

[0146] In another optional embodiment of the present invention, path planning can be performed on the target medical logistics robot with the shortest path of the target medical logistics robot as the goal to obtain a scheduling path.

[0147] In an embodiment of the present invention, the target medical logistics robot is navigated through a scheduling path, and the available elevators are controlled through a target control signal, thereby ensuring that the target medical logistics robot can accurately perform scheduling tasks and effectively improving the accuracy of elevator task control.

[0148] like Figure 4 , which is a functional module diagram of an elevator task control system based on medical logistics robot scheduling provided by one embodiment of the present invention.

[0149] The elevator task control system 400 based on medical logistics robot scheduling of the present invention can be installed in an electronic device. According to the functions implemented, the elevator task control system 400 based on medical logistics robot scheduling can include a state recognition module 401, a task index calculation module 402, a scheduling optimization module 403, a target control signal construction module 404 and an elevator task control module 405. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0150] In this embodiment, the functions of each module / unit are as follows:

[0151] The state recognition module 401 is used to obtain the scheduling task of the medical logistics robot, and identify the robot position, power information, scheduling tasks to be executed, and the floor, running direction, full load, and floor where the elevator needs to stop of the available medical logistics robot according to the scheduling task;

[0152] The task index calculation module 402 is used to construct the allocation combination of the available medical logistics robots and the available elevators for the scheduling task allocation according to the robot position, power information, the scheduling task to be executed, and the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop, and calculate the robot path length of each scheduling task in the allocation combination and the time to take the corresponding available elevator;

[0153] The scheduling optimization module 403 is used to perform a weighted summation of the robot path length and the time of taking the corresponding available elevator to obtain an evaluation function, and perform scheduling optimization on the allocation combination based on the evaluation function to obtain a target medical logistics robot and a target available elevator corresponding to the scheduling task;

[0154] The target control signal construction module 404 is used to generate an elevator control signal according to the target medical logistics robot and the target available elevator, extract the signal weakness feature of the elevator control signal, and construct a target control signal according to the signal weakness feature;

[0155] The elevator task control module 405 is used to generate a scheduling path for the target medical logistics robot, and perform elevator task control on the target available elevator according to the scheduling path and the target control signal.

[0156] In detail, each module described in the elevator task control system 400 based on medical logistics robot scheduling in the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The elevator task control method based on medical logistics robot scheduling described in the text is the same as the technical means and can produce the same technical effects, so I will not go into details here.

[0157] The present invention also provides an electronic device, which may include a processor, a memory, a communication bus and a communication interface, and may also include a computer program stored in the memory and executable on the processor, such as an elevator task control method program based on medical logistics robot scheduling.

[0158] In some embodiments, the processor may be composed of an integrated circuit, for example, it may be composed of a single packaged integrated circuit, or it may be composed of multiple packaged integrated circuits with the same or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors and a combination of various control chips.

[0159] The memory includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device.

[0160] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0161] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface.

[0162] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0163] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0164] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0165] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0166] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0167] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0168] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0169] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0170] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An elevator task control method based on medical logistics robot scheduling, characterized in that: The method comprises: Obtain the scheduling tasks of the medical logistics robot, and identify the robot position, power information, scheduling tasks to be executed, and the floor, running direction, full load, and floor at which the elevator needs to stop of the available medical logistics robot according to the scheduling tasks; According to the robot position, power information, scheduling tasks to be performed, and the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop, a distribution combination of the available medical logistics robots and the available elevators for the scheduling task allocation is constructed, and the robot path length of each scheduling task in the distribution combination and the time to take the corresponding available elevator are calculated; Performing a weighted summation on the robot path length and the time of taking the corresponding available elevator to obtain an evaluation function, and performing scheduling optimization on the allocation combination based on the evaluation function to obtain a target medical logistics robot and a target available elevator corresponding to the scheduling task; Generate an elevator control signal according to the target medical logistics robot and the target available elevator, extract a signal weakness feature of the elevator control signal, and construct a target control signal according to the signal weakness feature; Generate a scheduling path for the target medical logistics robot, and perform elevator task control on the target available elevator according to the scheduling path and the target control signal.

2. The elevator task control method based on medical logistics robot scheduling according to claim 1 is characterized in that: The method of identifying the robot position, power information, to-be-executed scheduling tasks, and the elevator floor, running direction, full load, and the floor at which the elevator needs to stop of the available medical logistics robot according to the scheduling task includes: According to the scheduling task, robot status signals of a preset medical logistics robot set and elevator status signals and elevator car images of a preset elevator are collected; Performing signal channel conversion on the robot state signal and the elevator state signal respectively to obtain signal characteristics of the robot state signal and the elevator state signal; Identify whether the preset elevator is fully loaded according to the elevator car picture; According to the signal characteristics, the signal status is identified to obtain the robot position, power information, scheduling tasks to be executed, the floor where the elevator is located, the running direction, and the floor where the elevator needs to stop of the available medical logistics robot; According to whether the preset elevator is fully loaded, the floor where the elevator is located, the running direction, and the floor where the elevator needs to stop, the floor where the available elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop are identified.

3. The elevator task control method based on medical logistics robot scheduling as claimed in claim 2 is characterized in that: The performing signal channel conversion on the robot state signal and the elevator state signal respectively to obtain signal characteristics of the robot state signal and the elevator state signal comprises: Performing wavelet transform, Hilbert-Huang transform and signal bispectral transform on the robot state signal and the elevator state signal respectively to obtain a transform coefficient matrix; A three-dimensional coefficient image of the transformation coefficient matrix is ​​constructed, and two-dimensional mapping is performed on the three-dimensional coefficient image to obtain signal characteristics of the robot state signal and the elevator state signal.

4. The elevator task control method based on medical logistics robot scheduling according to claim 1 is characterized in that: The allocation combination of the available medical logistics robots and the available elevators for the scheduling task allocation is constructed according to the robot position, power information, the scheduling task to be executed, the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop, including: Determine the path execution node according to the robot position, power information, the scheduling task to be executed, the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop; Allocate available medical logistics robots and available elevators to the scheduling task according to the path execution nodes to obtain an initial task allocation; An allocation combination is constructed based on the initial assignment of tasks.

5. The elevator task control method based on medical logistics robot scheduling according to claim 1 is characterized in that: The calculating of the robot path length of each scheduling task in the allocation combination and the time to take the corresponding available elevator comprises: Calculating the robot path length of each scheduling task in the allocation combination; Calculate the elevator waiting time, elevator riding time and elevator energy consumption according to the elevator floor, running direction, whether it is fully loaded, and the floor where the elevator needs to stop of the available elevators in each of the scheduling tasks; The following formula is used to calculate the elevator waiting time, elevator riding time and elevator energy consumption: in, Indicates the elevator waiting time. Indicates the available elevators in floors, Indicates the current floor where the available elevator is located. Indicates the floor where the available medical logistics robots corresponding to the available elevators are located. Indicates the elevator speed of the preset available elevators, Indicates the number of times an available elevator needs to stop to let passengers off in the elevator status. Indicates the preset average time for each stop. Indicates the elevator ride time. Indicates the number of times the available elevator needs to stop to let passengers off when executing the scheduling task. represents the energy consumption of the elevator, Indicates the number of available elevator starts and stops. Indicates the preset average energy consumption of available elevators each time they start and stop; The time for taking a corresponding available elevator is determined according to the elevator waiting time, the elevator riding time and the elevator energy consumption.

6. The elevator task control method based on medical logistics robot scheduling according to claim 1 is characterized in that: The scheduling optimization of the allocation combination based on the evaluation function to obtain the target medical logistics robot and the target available elevator corresponding to the scheduling task includes: Initializing a particle population, and calculating an evaluation function value of each particle in the particle population according to the evaluation function; Performing population migration on the particle population according to the evaluation function value to obtain a migrated particle population; Calculating the migration evaluation function value of each particle in the migrating particle population, iterating the migrating particle population according to the migration evaluation function value until the number of iterations of the migrating particle population is greater than a preset iteration number threshold, thereby obtaining a target particle population; Target particles are selected according to the target particle population, and the allocation combination is scheduled and optimized according to the target particles to obtain a target medical logistics robot and a target available elevator corresponding to the scheduling task.

7. The elevator task control method based on medical logistics robot scheduling according to claim 6 is characterized in that: The step of performing population migration on the particle population according to the evaluation function value to obtain a migrated particle population includes: Calculating the variable-scale black hole radius and displacement coefficient of the particle population; The variable-scale black hole radius and displacement coefficient of the particle population are calculated using the following formula: in, represents the radius of the variable-scale black hole, Represents the preset initial value of the black hole scale, Indicates the final value of the preset black hole scale, Indicates the current iteration number, Represents the preset iteration number threshold, represents the displacement coefficient, represents the preset initial displacement coefficient, represents the preset final displacement coefficient, express A random number, Indicates a preset first mapping relationship; Calculating the update speed and update position of the particle population based on the variable-scale black hole radius and the displacement coefficient; The update speed and update position of the particle population are calculated using the following formula: in, Indicates that the particle in the particle population is The update speed at the iteration, represents the preset inertia weight, is the particle in the particle population. The speed at the iteration, represents the preset first learning factor, represents the preset second learning factor, , , , express A random number, represents the individual optimal position of the particle, represents the global optimal position of the particle, Indicates that the particle The position at the iteration, Indicates that the particle The updated position at the iteration, represents the displacement coefficient, represents the radius of the variable-scale black hole, , , They represent the preset first black hole attraction probability, second black hole attraction probability, and third black hole attraction probability, respectively. , Represent the randomly generated Particles and The particle in The position at the iteration, They represent the sensory factor, fragrance stimulation intensity and power index preset in the butterfly optimization algorithm respectively; The particle population is updated according to the update speed and the update position to obtain a migration particle population.

8. The elevator task control method based on medical logistics robot scheduling according to claim 1 is characterized in that: The step of extracting the signal weakness feature of the elevator control signal comprises: Performing wavelet transform on the elevator control signal to obtain transform coefficients; Performing threshold processing on the transform coefficients to obtain target transform coefficients; A signal weakness feature of the elevator control signal is identified according to the target transformation coefficient.

9. The elevator task control method based on medical logistics robot scheduling according to claim 1 is characterized in that: The generating of the dispatch path of the target medical logistics robot comprises: Obtaining a dispatch map corresponding to the target medical logistics robot, and performing semantic segmentation on the dispatch map to obtain a segmented map; Performing convolution erosion on the segmentation map to obtain an obstacle probability map; Constructing a replacement point map corresponding to the target medical logistics robot according to the obstacle probability map; The path of the target medical logistics robot is planned according to the replacement point map to obtain a scheduling path for the target medical logistics robot.

10. An elevator task control system based on medical logistics robot scheduling, characterized in that: The system comprises: A state recognition module is used to obtain the scheduling tasks of the medical logistics robot, and identify the robot position, power information, scheduling tasks to be executed, and the floor, running direction, full load, and floor at which the elevator needs to stop of the available medical logistics robot according to the scheduling tasks; A task index calculation module is used to construct an allocation combination of the available medical logistics robots and the available elevators for the scheduling task allocation according to the robot position, power information, the scheduling task to be executed, and the floor where the elevator is located, the running direction, whether it is fully loaded, and the floor where the elevator needs to stop, and calculate the robot path length of each scheduling task in the allocation combination and the time to take the corresponding available elevator; A scheduling optimization module, used to perform a weighted summation of the robot path length and the time of taking the corresponding available elevator to obtain an evaluation function, and perform scheduling optimization on the allocation combination based on the evaluation function to obtain a target medical logistics robot and a target available elevator corresponding to the scheduling task; A target control signal construction module, used to generate an elevator control signal according to the target medical logistics robot and the target available elevator, extract a signal weakness feature of the elevator control signal, and construct a target control signal according to the signal weakness feature; The elevator task control module is used to generate a scheduling path for the target medical logistics robot and perform elevator task control on the target available elevator according to the scheduling path and the target control signal.

Images