A cloud-based campus self-service laundry management system

Abstract

This invention relates to the field of self-service technology, and discloses a cloud-based campus self-service laundry management system. The system includes: acquiring the laundry tasks of all users who have made reservations for a future reservation time, and the available washing machines; acquiring fatigue level data for the available washing machines; matching the number of target washing machines equal to the number of users who made reservations from all available washing machines based on the fatigue level index, and forming multiple laundry matching strategies based on all target washing machines and users who made reservations; using a pre-configured genetic algorithm to obtain the optimal laundry matching strategy from the multiple matching strategies; and assigning each target washing machine to the corresponding user who made reservations based on the optimal laundry matching strategy. This invention helps optimize the usage frequency of low-frequency washing machines, reduce the difference in maintenance cycles between washing machines, and improve the return on investment for low-frequency washing machines.

Description

Technical Field

[0001] This invention relates to the field of self-service technology, and more specifically, to a cloud-based campus self-service laundry management system. Background Technology

[0002] With the advancement of intelligent campus construction, self-service laundry systems have become an important part of dormitory logistics management in universities. However, existing washing machine management models generally suffer from uneven equipment usage loads during long-term operation, affecting the uniformity of equipment lifespan and return on investment. Due to limitations imposed by user habits, equipment location, and allocation strategies, some washing machines operate at high frequency for extended periods, while others operate at low frequency, resulting in significant differences in wear and tear between the devices. In the long run, excessive wear and tear on high-frequency-use equipment leads to premature scrapping, increasing maintenance costs, while the resources of low-frequency-use equipment are not effectively utilized, resulting in a low return on investment and impacting the overall operational efficiency of the system.

[0003] Existing campus self-service laundry management systems typically allocate washing machines to users based on simple principles of "proximity priority" or "equipment availability." While this approach offers some convenience, improves user experience, and reduces waiting time, it lacks balanced management of the long-term usage frequency of washing machines. This results in a significant reduction in the lifespan of some equipment, while low-usage equipment suffers from substantial resource waste. Furthermore, the maintenance cycle of the equipment varies considerably depending on the intensity of use. The maintenance needs of high-frequency-use equipment are more concentrated, while the maintenance plans for low-usage equipment are relatively loose. This leads to difficulties in scheduling maintenance resources, fragmented maintenance plans, and increases management complexity and subsequent operating costs.

[0004] Therefore, there is an urgent need for a cloud-based intelligent washing machine management system to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a cloud-based campus self-service laundry management system.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A cloud-based campus self-service laundry management system, the system comprising:

[0008] The first data acquisition module is used to acquire the laundry tasks of all users who have made reservations at the future reservation time, as well as the available washing machines at the future reservation time.

[0009] The second data acquisition module is used to acquire fatigue level data about the optional washing machines, the fatigue level data including the short-term fatigue index of each optional washing machine at the future scheduled time;

[0010] The reservation matching module is used to match the same number of target washing machines as the reservation user from all available washing machines based on the fatigue level index, and to form multiple washing matching strategies based on all target washing machines and reservation users.

[0011] The decision optimization module is used to obtain the best laundry matching strategy from multiple laundry matching strategies using a pre-configured genetic algorithm;

[0012] The adaptive allocation module is used to assign each target washing machine to the corresponding scheduled user according to the optimal washing matching strategy, so that each target washing machine can perform the washing task of the corresponding scheduled user at the future scheduled time.

[0013] Preferably, the laundry task includes laundry task data, which includes the scheduled time, type of laundry, quantity of laundry, and planned washing duration.

[0014] The acquisition of fatigue level data regarding the selectable washing machine includes:

[0015] Obtain fatigue impact characteristic data of the selectable washing machine. The fatigue impact characteristic data includes the number of washing tasks in the past L hours, the motor temperature, motor power and planned washing duration for each washing task, where L is an integer greater than zero.

[0016] The fatigue impact feature data is input into the pre-trained first LSTM neural network model to predict the short-term fatigue index of the optional washing machine at the future reservation time.

[0017] Repeat the above steps until you obtain the short-term fatigue index of each selectable washing machine at the future scheduled time.

[0018] The short-term fatigue index of each selectable washing machine at the future scheduled time is used as data on the fatigue level of the selectable washing machines.

[0019] Preferably, the training method for the first LSTM neural network model is as follows:

[0020] Collect historical fatigue level training data and divide the historical fatigue level training data into fatigue level training set and fatigue level test set. The historical fatigue level training data includes fatigue impact characteristic data and its corresponding short-term fatigue index.

[0021] The calculation logic for the short-term fatigue index in the historical fatigue training data is as follows:

[0022]

[0023] In the formula: This is a short-term fatigue index. This represents the motor power of the optional washing machine during the k-th washing cycle. The selectable motor temperature of the washing machine during the k-th washing task. Let R be the planned washing time for the k-th laundry task, and R be the number of laundry tasks. To set the runtime for reference, It is a natural constant;

[0024] A regression network based on an LSTM neural network is constructed. The fatigue impact feature data in the fatigue training set is used as the input of the regression network, and the short-term fatigue index is used as the output. The regression network is trained to obtain an initial fatigue regression model.

[0025] The initial fatigue regression model is validated using a fatigue level test set. The initial fatigue regression model whose output is less than or equal to the prediction test error threshold is used as the first trained LSTM neural network model.

[0026] Preferably, matching the number of target washing machines from all available washing machines to the number of users making reservations includes:

[0027] Get the total number of registered users M, where M is a positive integer;

[0028] Sort all available washing machines by fatigue index from smallest to largest, select the top N available washing machines as target washing machines, and obtain the same number of target washing machines as the number of users who made reservations, N=M.

[0029] Preferably, obtaining the optimal laundry matching strategy from multiple laundry matching strategies includes:

[0030] a1: Initialize the population: Randomly select a laundry matching strategy as the original population. The original population contains X individuals, each individual representing a laundry matching strategy. Each laundry matching strategy has multiple reservation users and corresponding target washing machines, where X is a positive integer.

[0031] a2: Fitness assessment: For each individual, obtain the cumulative runtime of all target washing machines; and input the cumulative runtime into the pre-built fitness function to calculate the fitness of each individual;

[0032] a3: Selection: Two individuals with high fitness from the original population were selected as the father and mother using the roulette wheel method;

[0033] a4: Crossover: Perform a crossover operation on the parent and parent to produce new individuals;

[0034] a5: Mutation: Perform a mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2;

[0035] a6: Repeat steps a2 to a5 above until the fitness of an individual in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold. Then, output the laundry matching strategy represented by the corresponding individual as the best laundry matching strategy.

[0036] Preferably, the method for obtaining the cumulative running time of all target washing machines is as follows:

[0037] Obtain the running time characteristic data of the target washing machine, which includes past usage characteristic data of the past S hours and future reservation characteristic data of the next W hours, where S and W are integers greater than zero;

[0038] The runtime feature data is input into a pre-trained second LSTM neural network model to predict the cumulative runtime of the target washing machine at the future scheduled time.

[0039] The training method for the second LSTM neural network model is as follows:

[0040] Acquire historical runtime training data and divide the historical runtime training data into a runtime prediction training set and a runtime prediction test set. The historical runtime training data includes runtime feature data and its corresponding cumulative runtime.

[0041] A regression network based on an LSTM neural network is constructed. The runtime feature data in the runtime prediction training set is used as the input of the regression network, and the cumulative runtime is used as the output of the regression network. The regression network is trained to obtain the initial runtime regression network.

[0042] The initial runtime regression network is validated using a runtime prediction test set. The initial runtime regression network whose output is less than or equal to the prediction test error threshold is used as the trained second LSTM neural network model.

[0043] Preferably, the pre-constructed fitness function is calculated using the following formula: In the formula: For fitness, Let i be the cumulative running time of the i-th target washing machine. The average runtime of all target washing machines. The target is the total number of washing machines.

[0044] A cloud-based campus self-service laundry management method, implemented based on the aforementioned cloud-based campus self-service laundry management system, includes the following steps:

[0045] Get the laundry tasks of all users who have made reservations for the future reservation time, and get the available washing machines for the future reservation time;

[0046] Obtain fatigue data for the optional washing machines, including a short-term fatigue index for each optional washing machine at a future scheduled time;

[0047] Based on the fatigue level index, match the same number of target washing machines as the reservation user from all available washing machines, and form multiple washing matching strategies based on all target washing machines and reservation users;

[0048] The optimal laundry matching strategy is obtained from multiple laundry matching strategies using a pre-configured genetic algorithm.

[0049] Each target washing machine is assigned to a corresponding user based on the optimal laundry matching strategy, so that each target washing machine can perform the laundry task for the corresponding user at the scheduled time in the future.

[0050] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the aforementioned cloud-based campus self-service laundry management method.

[0051] A computer-readable storage medium is characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the above-described cloud-based campus self-service laundry management method.

[0052] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0053] This application discloses a cloud-based campus self-service laundry management system, comprising: acquiring the laundry tasks of all users who have made reservations for a future reservation time, and the available washing machines; acquiring fatigue level data of the available washing machines; matching the same number of target washing machines as the number of users who made reservations from all available washing machines based on the fatigue level index, and forming multiple laundry matching strategies based on all target washing machines and users who made reservations; using a pre-configured genetic algorithm to obtain the optimal laundry matching strategy from the multiple laundry matching strategies; and assigning each target washing machine to the corresponding user who made reservations according to the optimal laundry matching strategy. Based on the above features, this invention can reduce the high-load use of certain individual washing machines, make the wear and tear of all washing machines more consistent, thereby balancing the overall lifespan of the washing machines. This, in turn, helps to reduce the differences in maintenance cycles between washing machines, improve the return on investment of some washing machines, improve overall operating efficiency, and reduce the later maintenance costs of campus self-service laundry equipment. Attached Figure Description

[0054] Figure 1 A module diagram of a cloud-based campus self-service laundry management system provided by the present invention;

[0055] Figure 2 A flowchart illustrating a cloud-based campus self-service laundry management method provided by the present invention;

[0056] Figure 3 This is a schematic diagram of the structure of an electronic device provided by the present invention. Detailed Implementation

[0057] 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.

[0058] Example 1

[0059] Please see Figure 1 As shown in the figure, this embodiment discloses a campus self-service laundry management system based on a cloud platform, including:

[0060] The first data acquisition module 101 is used to acquire the laundry tasks of all users who have made reservations at a future reservation time, and to acquire the available washing machines at the future reservation time.

[0061] The laundry task includes laundry task data, which includes, but is not limited to, appointment time, type of laundry, quantity of laundry, and planned washing duration. The planned washing duration can be manually input by the user making the appointment, specifically referring to the set washing duration for the clothes. Alternatively, it can be obtained by the cloud platform's backend server based on the type and quantity of laundry. This is not the focus of this invention and will not be described in detail. Any method that can obtain the planned washing duration can be used as the basis for implementing this invention. For example, there are existing methods that determine the planned washing duration using fuzzy control algorithms.

[0062] It should be understood that: the laundry tasks of all users who make reservations at the future reservation time are obtained based on the established cloud platform, which is used to receive users' laundry reservation requests and automatically assign a corresponding washing machine to each user.

[0063] It should be noted that the available washing machines for future reservation times are determined by the cloud platform based on historical reservation data and an adaptive washing allocation method.

[0064] For example, assuming the current time is 10:00 AM, and the cloud platform receives a laundry reservation request from two people at a future reservation time (12:00 PM), and assuming there are five washing machines, Z1, Z2, Z3, Z4, and Z5, and the cloud platform assigns Z1 and Z2 to the two people who made the laundry reservation requests according to the adaptive laundry allocation method, Z3, Z4, and Z5 will be idle at the future reservation time (12:00 PM). Therefore, the available washing machines at the future reservation time (12:00 PM) are Z3, Z4, and Z5. The adaptive laundry allocation method is detailed in the following content and will not be elaborated further here.

[0065] It is important to note that the availability of a washing machine at a future scheduled time only indicates that the corresponding washing machine will be available at that time, and does not mean that the washing machine will not be used before the future scheduled time.

[0066] For example, following the above assumptions, Z3, Z4 and Z5 will be idle at the future scheduled time (12:00), where Z3's laundry task ends at 11:55, so Z3 will also be selected as an optional washing machine.

[0067] The second data acquisition module 102 is used to acquire fatigue level data about the optional washing machines, the fatigue level data including the short-term fatigue index of each optional washing machine at a future scheduled time;

[0068] In implementation, obtaining fatigue level data regarding the optional washing machine includes:

[0069] Obtain fatigue impact characteristic data of the selectable washing machine. The fatigue impact characteristic data includes the number of washing tasks in the past L hours, the motor temperature, motor power and planned washing duration for each washing task, where L is an integer greater than zero.

[0070] The fatigue impact feature data is input into the pre-trained first LSTM neural network model to predict the short-term fatigue index of the optional washing machine at the future reservation time.

[0071] Specifically, the training method for the first LSTM neural network model is as follows:

[0072] Collect historical fatigue level training data and divide the historical fatigue level training data into fatigue level training set and fatigue level test set. The historical fatigue level training data includes fatigue impact characteristic data and its corresponding short-term fatigue index.

[0073] It should be noted that the fatigue impact characteristics and short-term fatigue index in the historical fatigue level training data were obtained by technicians based on the specific experimental data.

[0074] The calculation logic for the short-term fatigue index in the historical fatigue training data is as follows:

[0075]

[0076] In the formula: This is a short-term fatigue index. This represents the motor power of the optional washing machine during the k-th washing cycle. The selectable motor temperature of the washing machine during the k-th washing task. R represents the planned washing time for the k-th laundry task, and R is the number of laundry tasks (equivalent to the number of users who made reservations). The runtime is set for reference (obtained by fitting historical data). It is a natural constant;

[0077] A regression network based on an LSTM neural network is constructed. The fatigue impact feature data in the fatigue training set is used as the input of the regression network, and the short-term fatigue index is used as the output. The regression network is trained to obtain an initial fatigue regression model.

[0078] The initial fatigue regression model is validated using a fatigue test set. The initial fatigue regression model whose output is less than or equal to the prediction test error threshold is used as the first trained LSTM neural network model.

[0079] Repeat the above steps until you obtain the short-term fatigue index of each selectable washing machine at the future scheduled time.

[0080] The short-term fatigue index of each selectable washing machine at the future scheduled time is used as data on the fatigue level of the selectable washing machines;

[0081] The reservation matching module 103 is used to match the same number of target washing machines as the reservation user from all available washing machines based on the fatigue level index, and to form multiple washing matching strategies based on all target washing machines and the reservation user.

[0082] In implementation, matching the same number of target washing machines as the number of users making reservations from all available washing machines includes:

[0083] Get the total number of registered users M, where M is a positive integer;

[0084] Sort all available washing machines by fatigue index from smallest to largest, select the top N available washing machines as target washing machines, and obtain the same number of target washing machines as the number of users who made reservations, N=M;

[0085] It should be understood that a higher fatigue index indicates that the corresponding optional washing machine may have been in a washing operation state for a long time, and / or that the corresponding optional washing machine may have just finished a washing task and the motor operating temperature is too high. Therefore, even if the cumulative running time of this optional washing machine differs significantly from the cumulative running time of other optional washing machines from a global perspective, it will not be considered in the target washing machine. This is to avoid the optional washing machine from malfunctioning due to short-term overload operation, which would affect its service life. To further explain, it is to eliminate the local impact caused when performing washing load balancing from a global perspective in the future, thereby truly achieving load balancing in the usage frequency of all washing machines, ensuring the consistency of the service life of all washing machines, and further solving the problem of fragmented subsequent washing machine maintenance plans, reducing the excessive operation and maintenance costs caused by multi-stage maintenance of washing machines.

[0086] It should be noted that: multiple laundry matching strategies are formed by combining all target washing machines with reservation users in a unique way. Each laundry matching strategy includes all reservation users, and each reservation user is randomly matched with a corresponding target washing machine.

[0087] For example, suppose there are two users who make reservations, C1 and C2, and two target washing machines, D1 and D2. Therefore, all the washing machine matching strategies include C1D1, C1D2, C2D1 and C2D2.

[0088] The decision optimization module 104 is used to obtain the best laundry matching strategy from multiple laundry matching strategies using a pre-configured genetic algorithm.

[0089] In implementation, obtaining the optimal laundry matching strategy from multiple laundry matching strategies includes:

[0090] a1: Initialize the population: Randomly select a laundry matching strategy as the original population. The original population contains X individuals, each individual representing a laundry matching strategy. Each laundry matching strategy has multiple reservation users and corresponding target washing machines, where X is a positive integer.

[0091] a2: Fitness assessment: For each individual (i.e., each washing matching strategy in the original population), obtain the cumulative runtime of all target washing machines; and input the cumulative runtime into the pre-constructed fitness function to calculate the fitness of each individual;

[0092] Specifically, the method for obtaining the cumulative runtime of all target washing machines is as follows:

[0093] Obtain the running time characteristic data of the target washing machine. The running time characteristic data includes past usage characteristic data of the past S hours and future reservation characteristic data of the next W hours. The past usage characteristic data includes idle time ratio, average daily usage duration, and weekly usage frequency. The future reservation characteristic data includes the number of reserved laundry requests and the laundry task data in each reserved laundry request, including but not limited to reservation time, type of laundry to be washed, quantity of laundry to be washed, and planned washing duration. S and W are integers greater than zero.

[0094] The runtime feature data is input into a pre-trained second LSTM neural network model to predict the cumulative runtime of the target washing machine at the future scheduled time.

[0095] The training method for the second LSTM neural network model is as follows:

[0096] Acquire historical runtime training data and divide the historical runtime training data into a runtime prediction training set and a runtime prediction test set. The historical runtime training data includes runtime feature data and its corresponding cumulative runtime.

[0097] It should be noted that the runtime feature data and cumulative runtime in the historical runtime training data were collected and recorded by technicians based on specific experimental data.

[0098] A regression network based on an LSTM neural network is constructed. The runtime feature data in the runtime prediction training set is used as the input of the regression network, and the cumulative runtime is used as the output of the regression network. The regression network is trained to obtain the initial runtime regression network.

[0099] The initial runtime regression network is validated using a runtime prediction test set. The initial runtime regression network whose output is less than or equal to the prediction test error threshold is used as the trained second LSTM neural network model.

[0100] The formula for calculating the pre-constructed fitness function is as follows: In the formula: For fitness, Let i be the cumulative running time of the i-th target washing machine. The average runtime of all target washing machines. The total number of target washing machines;

[0101] a3: Selection: Two individuals with high fitness from the original population were selected as the father and mother using the roulette wheel method;

[0102] Roulette wheel selection is a commonly used selection method in genetic algorithms to select individuals with higher fitness to enter the next generation. It simulates the process of roulette, where each individual receives a corresponding "roulette" area based on its fitness. The higher the fitness of an individual, the larger its corresponding area and the higher its probability of being selected.

[0103] a4: Crossover: Perform a crossover operation on the parent and parent to produce new individuals;

[0104] It should be noted that the crossover operation between the parent and mother lines is based on the crossover operation, which includes, but is not limited to, one of the following: single-point crossover, uniform crossover, or sequential crossover.

[0105] In genetic algorithms, crossover is an important genetic operation used to generate a new generation of candidate solutions. The basic idea of ​​crossover is to simulate the sexual reproduction process in biological genetics, where two parents produce offspring by combining their genetic information. This process helps to introduce diversity into the solution space and may produce new individuals that are more adapted to the environment.

[0106] a5: Mutation: Perform a mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2;

[0107] In genetic algorithms, mutation is used to introduce genetic diversity and prevent the algorithm from getting stuck in local optima; the mutation operation on new individuals is achieved through methods such as uniform mutation or Gaussian mutation.

[0108] a6: Repeat steps a2 to a5 above until the fitness of an individual in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold. Then, output the laundry matching strategy represented by the corresponding individual as the best laundry matching strategy.

[0109] For example: Assuming the maximum number of iterations is 100, after each iteration, record the individual with the highest fitness in the current population and its fitness value; if the fitness value does not change significantly in a certain generation, it is considered that the convergence condition has been met, the iteration stops, and the laundry matching strategy represented by the corresponding individual is output as the best laundry matching strategy.

[0110] The adaptive allocation module 105 is used to allocate each target washing machine to the corresponding reservation user according to the best washing matching strategy, so that each target washing machine can perform the washing task of the corresponding reservation user at the future reservation time.

[0111] This invention can reduce the high load usage of certain individual washing machines, making the wear and tear of all washing machines more consistent, thereby balancing the overall lifespan of the washing machines. This, in turn, helps to reduce the differences in maintenance cycles between washing machines, improve the return on investment of some washing machines, improve overall operational efficiency, and reduce the later maintenance costs of campus self-service laundry equipment.

[0112] Example 2

[0113] Please see Figure 2 As shown in the figure, this embodiment discloses a campus self-service laundry management method based on a cloud platform, the method including:

[0114] S201: Obtain the laundry tasks of all users who have made reservations for the future reservation time, and obtain the available washing machines for the future reservation time;

[0115] S202: Obtain fatigue data for the optional washing machines, the fatigue data including a short-term fatigue index for each optional washing machine at a future scheduled time;

[0116] S203: Based on the fatigue level index, match the same number of target washing machines as the reservation user from all available washing machines, and form multiple washing matching strategies based on all target washing machines and reservation users;

[0117] S204: Use a pre-configured genetic algorithm to obtain the best laundry matching strategy from multiple laundry matching strategies;

[0118] S205: Assign each target washing machine to the corresponding scheduled user according to the optimal laundry matching strategy, so that each target washing machine can perform the laundry task of the corresponding scheduled user at the future scheduled time.

[0119] Example 3

[0120] Please see Figure 3 As shown, this embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the cloud-based campus self-service laundry management method provided by the above methods.

[0121] Since the electronic device described in this embodiment is the electronic device used to implement the cloud-based campus self-service laundry management method described in this application embodiment, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the cloud-based campus self-service laundry management method described in this application embodiment. Therefore, how the electronic device implements the method in this application embodiment will not be described in detail here. Any electronic device used by those skilled in the art to implement the cloud-based campus self-service laundry management method described in this application embodiment falls within the scope of protection of this application.

[0122] Example 4

[0123] A computer-readable storage medium storing a computer program, which, when executed, implements the aforementioned cloud-based campus self-service laundry management method.

[0124] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters, weights, and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0125] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0126] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0127] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0128] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0129] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0131] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0132] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A cloud-based campus self-service laundry management system, characterized in that, The system includes: The first data acquisition module is used to acquire the laundry tasks of all users who have made reservations at the future reservation time, as well as the available washing machines at the future reservation time. The second data acquisition module is used to acquire fatigue level data about the optional washing machines, the fatigue level data including the short-term fatigue index of each optional washing machine at the future scheduled time; The laundry task includes laundry task data, which includes the scheduled time, type of laundry, quantity of laundry, and planned washing duration. The acquisition of fatigue level data regarding the selectable washing machine includes: Obtain fatigue impact characteristic data of the selectable washing machine. The fatigue impact characteristic data includes the number of washing tasks in the past L hours, the motor temperature, motor power and planned washing duration for each washing task, where L is an integer greater than zero. The fatigue impact feature data is input into the pre-trained first LSTM neural network model to predict the short-term fatigue index of the optional washing machine at the future reservation time. The training method for the first LSTM neural network model is as follows: Collect historical fatigue level training data and divide the historical fatigue level training data into fatigue level training set and fatigue level test set. The historical fatigue level training data includes fatigue impact characteristic data and its corresponding short-term fatigue index. The calculation logic for the short-term fatigue index in the historical fatigue training data is as follows: ； In the formula: This is a short-term fatigue index. This represents the motor power of the optional washing machine during the k-th washing cycle. The selectable motor temperature of the washing machine during the k-th washing task. Let R be the planned washing time for the k-th laundry task, and R be the number of laundry tasks. To set the runtime for reference, It is a natural constant; A regression network based on an LSTM neural network is constructed. The fatigue impact feature data in the fatigue training set is used as the input of the regression network, and the short-term fatigue index is used as the output. The regression network is trained to obtain an initial fatigue regression model. The initial fatigue regression model is validated using a fatigue level test set. The initial fatigue regression model whose output is less than or equal to the prediction test error threshold is used as the first trained LSTM neural network model. Repeat the above steps until you obtain the short-term fatigue index of each selectable washing machine at the future scheduled time. The short-term fatigue index of each selectable washing machine at the future scheduled time is used as data on the fatigue level of the selectable washing machines; The reservation matching module is used to match the same number of target washing machines as the reservation user from all available washing machines based on the fatigue level index, and to form multiple washing matching strategies based on all target washing machines and reservation users. The decision optimization module is used to obtain the best laundry matching strategy from multiple laundry matching strategies using a pre-configured genetic algorithm; The step of obtaining the optimal laundry matching strategy from multiple laundry matching strategies includes: a1: Initialize the population: Randomly select a laundry matching strategy as the original population. The original population contains X individuals, each individual representing a laundry matching strategy. Each laundry matching strategy has multiple reservation users and corresponding target washing machines, where X is a positive integer. a2: Fitness assessment: For each individual, obtain the cumulative runtime of all target washing machines; and input the cumulative runtime into the pre-built fitness function to calculate the fitness of each individual; The formula for calculating the pre-constructed fitness function is as follows: In the formula: For fitness, Let i be the cumulative running time of the i-th target washing machine. The average runtime of all target washing machines. The target is the total number of washing machines; a3: Selection: Two individuals with high fitness from the original population were selected as the father and mother using the roulette wheel method; a4: Crossover: Perform a crossover operation on the parent and parent to produce new individuals; a5: Mutation: Perform a mutation operation on the new individuals to obtain Y new individuals, combine the Y new individuals into a new population, replace the original population with the new population, and return to step a2; a6: Repeat steps a2 to a5 above until the fitness of an individual in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold. Then, output the laundry matching strategy represented by the corresponding individual as the best laundry matching strategy. The adaptive allocation module is used to assign each target washing machine to the corresponding scheduled user according to the optimal washing matching strategy, so that each target washing machine can perform the washing task of the corresponding scheduled user at the future scheduled time.

2. The campus self-service laundry management system based on a cloud platform according to claim 1, characterized in that, The process of matching the same number of target washing machines as the number of users making reservations from all available washing machines includes: Get the total number of registered users M, where M is a positive integer; Sort all available washing machines by fatigue index from smallest to largest, select the top N available washing machines as target washing machines, and obtain the same number of target washing machines as the number of users who made reservations, N=M.

3. The campus self-service laundry management system based on a cloud platform according to claim 2, characterized in that, The method for obtaining the cumulative runtime of all target washing machines is as follows: Obtain the running time characteristic data of the target washing machine, which includes past usage characteristic data of the past S hours and future reservation characteristic data of the next W hours, where S and W are integers greater than zero; The runtime feature data is input into a pre-trained second LSTM neural network model to predict the cumulative runtime of the target washing machine at the future scheduled time. The training method for the second LSTM neural network model is as follows: Acquire historical runtime training data and divide the historical runtime training data into a runtime prediction training set and a runtime prediction test set. The historical runtime training data includes runtime feature data and its corresponding cumulative runtime. A regression network based on an LSTM neural network is constructed. The runtime feature data in the runtime prediction training set is used as the input of the regression network, and the cumulative runtime is used as the output of the regression network. The regression network is trained to obtain the initial runtime regression network. The initial runtime regression network is validated using a runtime prediction test set. The initial runtime regression network whose output is less than or equal to the prediction test error threshold is used as the trained second LSTM neural network model.

4. A cloud-based campus self-service laundry management method, implemented based on any one of claims 1-3, characterized in that, The method includes: Get the laundry tasks of all users who have made reservations for the future reservation time, and get the available washing machines for the future reservation time; Obtain fatigue data for the optional washing machines, including a short-term fatigue index for each optional washing machine at a future scheduled time; Based on the fatigue level index, match the same number of target washing machines as the reservation user from all available washing machines, and form multiple washing matching strategies based on all target washing machines and reservation users; The optimal laundry matching strategy is obtained from multiple laundry matching strategies using a pre-configured genetic algorithm. Each target washing machine is assigned to a corresponding user based on the optimal laundry matching strategy, so that each target washing machine can perform the laundry task for the corresponding user at the scheduled time in the future.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the campus self-service laundry management method based on a cloud platform as described in claim 4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed, implements the campus self-service laundry management method based on a cloud platform as described in claim 4.

Images