Campus self-service clothes washing management system based on cloud platform

Abstract

The invention relates to the technical field of self-service, and discloses a campus self-service clothes washing management system based on a cloud platform, and the system comprises the steps: obtaining clothes washing tasks of all appointment users in future appointment time, and selectable washing machines; obtaining fatigue degree data about the selectable washing machine; target washing machines with the same number as the reservation users are matched from all the selectable washing machines according to the fatigue degree index, and a plurality of washing matching strategies are formed according to all the target washing machines and the reservation users; acquiring an optimal washing matching strategy from the plurality of washing matching strategies by using a pre-configured genetic algorithm; distributing each target washing machine to the corresponding reservation user according to the optimal washing matching strategy; the use frequency of the low-frequency washing machine is optimized, the maintenance period difference between the washing machines is reduced, and the return on investment of the low-frequency washing machine is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of self-service, and more specifically, to a campus self-service laundry management system based on a cloud platform. Background Art

[0002] With the advancement of campus intelligent construction, the self-service laundry system has become an important part of the logistics management of university dormitories; however, in the long-term operation process of the existing washing machine management mode, there is generally a problem of uneven load in the use of equipment, which affects the life balance of the equipment and the return on investment; due to the limitations of user habits, equipment location, and the advantages and disadvantages of the allocation strategy, some washing machines are in a high-frequency operation state for a long time, while some equipment is in a low-frequency operation state, resulting in a significant difference in the wear degree between equipment; in the long run, the excessive wear of high-frequency used equipment will lead to its premature scrapping, increasing the maintenance cost, while the resources of low-frequency used equipment are not effectively utilized, resulting in a low return on investment and affecting the overall operation efficiency of the system.

[0003] The existing campus self-service laundry management system usually allocates washing machines to users based on simple principles such as "nearest first" or "equipment availability". Although this method can provide certain convenience, improve the user experience, and reduce waiting time, it lacks the balanced management of the long-term usage frequency of washing machines, resulting in a significant reduction in the service life of some equipment, while the resources of low-usage equipment are seriously wasted; in addition, the maintenance cycle of the equipment also varies greatly due to different usage intensities. The maintenance requirements of high-frequency used equipment are relatively concentrated, and the maintenance plan of low-usage equipment is relatively loose, resulting in difficult scheduling of operation and maintenance resources, and there is a problem of fragmented maintenance plans, increasing the management complexity and the later operation cost.

[0004] In view of this, there is an urgent need for an intelligent washing machine management system based on a cloud platform to solve the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a campus self-service laundry management system based on a cloud platform.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A campus self-service laundry management system based on a cloud platform, the system includes:

[0008] A first data acquisition module, configured to acquire the laundry tasks of all reserved users at a future reservation time, and acquire the optional washing machines at the future reservation time;

[0009] The second data acquisition module is used to acquire fatigue degree data regarding optional washing machines, and the fatigue degree data includes the short-term fatigue index of each optional washing machine at a future reserved time.

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

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

[0012] The adaptive allocation module is used to allocate each target washing machine to the corresponding reserved user according to the best laundry matching strategy, so that each target washing machine executes the laundry task of the corresponding reserved user at the future reserved time.

[0013] Preferably, the laundry task includes laundry task data, and the laundry task data includes the reserved time, the type of laundry to be washed, the quantity of laundry to be washed, and the planned washing duration.

[0014] Among them, the acquisition of the fatigue degree data regarding optional washing machines includes:

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

[0016] Input the fatigue impact characteristic data into a pre-trained first LSTM neural network model to predict the short-term fatigue index of the optional washing machine at the future reserved time.

[0017] Repeat the above steps until the short-term fatigue index of each optional washing machine at the future reserved time is obtained.

[0018] Take the short-term fatigue index of each optional washing machine at the future reserved time as the fatigue degree data regarding the optional washing machine.

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

[0020] Collect historical fatigue degree training data, and divide the historical fatigue degree training data into a fatigue degree training set and a fatigue degree test set. Among them, the historical fatigue degree training data includes the fatigue impact characteristic data and its corresponding short-term fatigue index.

[0021] Among them, the calculation logic of the short-term fatigue index in the historical fatigue degree training data is as follows:

[0022]

[0023] In the formula: is the short-term fatigue index, is the motor power of the optional washing machine during the kth laundry task, is the motor temperature of the optional washing machine during the kth laundry task, is the planned washing duration of the kth laundry task, R is the number of laundry tasks, is the reference set operating duration, is the natural constant;

[0024] Construct a regression network with an LSTM neural network as the architecture, use the fatigue impact feature data in the fatigue degree training set as the input of the regression network, and use the short-term fatigue index as the output, train the regression network to obtain an initial fatigue degree regression model;

[0025] Use the fatigue degree test set to verify the initial fatigue degree regression model, and output the initial fatigue degree regression model whose prediction test error threshold is less than or equal to as the trained first LSTM neural network model.

[0026] Preferably, the matching of the same number of target washing machines as the reserved users from all optional washing machines includes:

[0027] Obtain the number M of all reserved users, where M is an integer greater than zero;

[0028] Sort the fatigue degree indexes of all optional washing machines from small to large, and select the first N optional washing machines as the target washing machines to obtain the same number of target washing machines as the reserved users, where N = M.

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

[0030] a1: Initialize the population: Randomly select a certain laundry matching strategy as the original population. The original population contains X individuals, each individual represents a laundry matching strategy. There are multiple reserved users and their corresponding target washing machines in each laundry matching strategy. X is an integer greater than zero;

[0031] a2: Fitness evaluation: Under each individual, obtain the cumulative operating duration of all target washing machines; and input the cumulative operating duration into the pre-constructed fitness function to calculate the fitness of each individual;

[0032] a3: Selection: Use the roulette wheel method to select two individuals with high fitness in the original population as the father and mother;

[0033] a4: Crossover: Perform a crossover operation on the male and female parents to generate 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 the above steps a2 - a5 until the fitness of the individuals 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 iteration thresholds, and output the laundry matching strategy represented by the corresponding individual as the optimal laundry matching strategy.

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

[0037] Obtain the operation time characteristic data of the target washing machine, where the operation time characteristic data includes the past usage characteristic data in the past S hours and the future reservation characteristic data within the next W hours, and S and W are positive integers;

[0038] Input the operation time characteristic data into a pre-trained second LSTM neural network model to predict the cumulative operation duration of the target washing machine at the future reservation time;

[0039] Among them, the training method of the second LSTM neural network model is as follows:

[0040] Obtain the historical operation duration training data, and divide the historical operation duration training data into an operation duration prediction training set and an operation duration prediction test set. The historical operation duration training data includes the operation time characteristic data and its corresponding cumulative operation duration;

[0041] Construct a regression network with an LSTM neural network architecture, use the operation time characteristic data in the operation duration prediction training set as the input of the regression network, and use the cumulative operation duration as the output of the regression network, and train the regression network to obtain an initial operation duration regression network;

[0042] Use the operation duration prediction test set to verify the model of the initial operation duration regression network, and output the initial operation duration regression network with a prediction test error less than or equal to the threshold as the trained second LSTM neural network model.

[0043] Preferably, the calculation formula of the pre-constructed fitness function is: ; In the formula: is the fitness, is the cumulative operation duration of the i-th target washing machine, is the average operation duration of all target washing machines, is the total number of target washing machines.

[0044] A campus self-service laundry management method based on a cloud platform is implemented based on the above-mentioned campus self-service laundry management based on a cloud platform. The method includes:

[0045] Obtain the laundry tasks of all reserved users at the future reservation time, and obtain the optional washing machines at the future reservation time;

[0046] Obtain the fatigue degree data of the optional washing machines. The fatigue degree data includes the short-term fatigue index of each optional washing machine at the future reservation time;

[0047] Match the same number of target washing machines as the reserved users from all the optional washing machines according to the fatigue degree index, and form multiple laundry matching strategies based on all the target washing machines and the reserved users;

[0048] Use a pre-configured genetic algorithm to obtain the best laundry matching strategy from multiple laundry matching strategies;

[0049] Allocate each target washing machine to the corresponding reserved user according to the best laundry matching strategy, so that each target washing machine executes the laundry task of the corresponding reserved user at the future reservation time.

[0050] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. The characteristic is that when the processor executes the computer program, it implements the above-mentioned campus self-service laundry management method based on a cloud platform.

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

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

[0053] The present application discloses a campus self-service laundry management system based on a cloud platform, including: obtaining the laundry tasks of all reserved users at a future reservation time, and optional washing machines; obtaining fatigue degree data about the optional washing machines; matching the same number of target washing machines as the reserved users from all the optional washing machines according to the fatigue degree index, and forming multiple laundry matching strategies based on all the target washing machines and the reserved users; using a pre-configured genetic algorithm to obtain the best laundry matching strategy from the multiple laundry matching strategies; allocating each target washing machine to the corresponding reserved user according to the best laundry matching strategy; based on the above features, the present invention can reduce the high-load use of certain single washing machines, make the loss states of all washing machines tend to be consistent, so as to equalize the overall service life of the washing machines. Furthermore, it is beneficial to narrow the difference in maintenance cycles between washing machines, improve the return on investment of some washing machines, improve the overall operation efficiency, and reduce the later maintenance cost of campus self-service laundry equipment. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0055] Figure 2 FIG. is a flowchart of a campus self-service laundry management method based on a cloud platform provided by the present invention;

[0056] Figure 3 FIG. is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] Embodiment 1

[0059] Please refer to Figure 1 As shown, this embodiment discloses and provides a campus self-service laundry management system based on a cloud platform, including:

[0060] A first data acquisition module 101, configured to acquire the laundry tasks of all reserved users at a future reservation time, and acquire the optional washing machines at a future reservation time;

[0061] Among them, the laundry task contains laundry task data, and the laundry task data includes, but is not limited to, reservation time, types of laundry to be washed, quantity of laundry to be washed, planned washing duration, etc.; among them, the planned washing duration can be obtained by manual input of the reservation user, which specifically refers to the set washing duration of the clothes, and it can also be analyzed by the background server of the cloud platform according to the types of laundry to be washed and the quantity of laundry to be washed. This is not the focus of the present invention and will not be elaborated too much here. Any method that can obtain the planned washing duration can be used as the implementation basis of the present invention. For example, the existing method of determining the planned washing duration through fuzzy control algorithm;

[0062] It should be understood that: the laundry tasks of all reservation users at the future reservation time are obtained based on the established cloud platform, and the cloud platform is used to receive the reservation laundry requests of users and automatically allocate corresponding washing machines to each reservation user;

[0063] It should be noted that: the optional washing machines at the future reservation time are obtained by the cloud platform through analysis based on historical reservation conditions and the adaptive laundry allocation method;

[0064] Exemplarily, assume that the current time is 10:00, and the cloud platform receives two laundry reservation requests at the future reservation time (12:00). Assume that there are 5 washing machines, namely Z1, Z2, Z3, Z4, and Z5. And the cloud platform, according to the adaptive laundry allocation method, allocates Z1 and Z2 to the two users who sent the laundry reservation requests. Therefore, Z3, Z4, and Z5 are in an idle state at the future reservation time (12:00), and thus the optional washing machines at the future reservation time (12:00) are obtained as Z3, Z4, and Z5 respectively; among them, the specific content of the adaptive laundry allocation method is specifically referred to the following relevant content, and for this, no additional elaboration will be made here;

[0065] It is worth noting that: the optional washing machines at the future reservation time only indicate that the corresponding washing machines are in an idle state at the future reservation time, and it does not mean that the corresponding washing machines have not been used before the future reservation time;

[0066] Exemplarily, continuing with the above assumption, Z3, Z4, and Z5 are in an idle state at the future reservation time (12:00). Among them, the laundry task of Z3 ended at 11:55, so Z3 will also be used as an optional washing machine.

[0067] The second data acquisition module 102 is used to acquire fatigue degree data of the optional washing machines, and the fatigue degree data includes the short-term fatigue index of each optional washing machine at the future reservation time;

[0068] In implementation, the acquisition of the fatigue degree data of the optional washing machines includes:

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

[0070] Input the fatigue impact characteristic data 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 of the first LSTM neural network model is as follows:

[0072] Collect historical fatigue degree training data, and divide the historical fatigue degree training data into a fatigue degree training set and a fatigue degree test set. Among them, the historical fatigue degree training data includes the fatigue impact characteristic data and its corresponding short-term fatigue index;

[0073] It should be noted that: the fatigue impact characteristic data and short-term fatigue index in the historical fatigue degree training data are specifically collected and calculated by technical personnel according to experimental data;

[0074] Among them, the calculation logic of the short-term fatigue index in the historical fatigue degree training data is as follows:

[0075]

[0076] In the formula: is the short-term fatigue index, is the motor power of the optional washing machine during the kth laundry task, is the motor temperature of the optional washing machine during the kth laundry task, is the planned washing duration of the kth laundry task, R is the number of laundry tasks (equivalent to the number of reserved users), is the reference set running duration (obtained by fitting historical data), is the natural constant;

[0077] Construct a regression network with an LSTM neural network as the architecture. Use the fatigue impact characteristic data in the fatigue degree training set as the input of the regression network and the short-term fatigue index as the output, and train the regression network to obtain an initial fatigue degree regression model;

[0078] Use the fatigue degree test set to verify the initial fatigue degree regression model, and output the initial fatigue degree regression model with a prediction test error threshold less than or equal to it as the trained first LSTM neural network model;

[0079] Repeat the above steps until the short-term fatigue index of each optional washing machine at the future reservation time is obtained;

[0080] Take the short-term fatigue index of each optional washing machine at the future reservation time as the fatigue degree data regarding the optional washing machine;

[0081] The reservation matching module 103 is used to match the same number of target washing machines as the reservation users from all optional washing machines according to the fatigue degree index, and form multiple laundry matching strategies based on all the target washing machines and the reservation users;

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

[0083] Obtain the number M of all reservation users, where M is an integer greater than zero;

[0084] Sort the fatigue degree indexes of all optional washing machines from small to large, and select the first N optional washing machines as target washing machines to obtain the same number of target washing machines as the reservation users, where N = M;

[0085] It should be understood that: the larger the fatigue degree index, the more it reflects that the corresponding optional washing machine may be in the laundry working state for a long time, and / or it indicates that the corresponding optional washing machine may have just finished the laundry task not long ago, and the motor working temperature is too high. Therefore, even if the cumulative operation duration of this optional washing machine is quite different from that of other optional washing machines from a global perspective, it will not be considered within the target washing machines. This is to avoid the optional washing machine from malfunctioning due to short-term overload operation and affecting its service life. Further explanation is that to eliminate the local influence generated when performing laundry load balancing from a global perspective, and further, to truly achieve load balancing in the usage frequency of all washing machines and ensure the life consistency of all washing machines. Further, to solve the problem of fragmentation in the subsequent washing machine maintenance plan and reduce the excessive operation and maintenance costs caused by multi-stage maintenance of the washing machines;

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

[0087] Exemplarily, assume there are 2 reservation users, namely C1 and C2, and there are also 2 target washing machines, namely D1 and D2. Therefore, all the laundry matching strategies include C1D1, C1D2, C2D1, and C2D2.

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

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

[0090] a1: Initialize the population: Randomly select a certain laundry matching strategy as the original population. The original population contains X individuals, and each individual represents a laundry matching strategy. There are multiple reserved users and corresponding target washing machines for each laundry matching strategy. X is an integer greater than zero;

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

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

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

[0094] Input the running time feature data into a pre-trained second LSTM neural network model to predict the cumulative running duration of the target washing machine at the future reservation time;

[0095] Among them, the training method of the second LSTM neural network model is as follows:

[0096] Obtain historical running duration training data, and divide the historical running duration training data into a running duration prediction training set and a running duration prediction test set. The historical running duration training data includes running time feature data and its corresponding cumulative running duration;

[0097] It should be noted that: The running time feature data and the cumulative running duration in the historical running duration training data are collected and recorded by technical personnel according to specific experimental data;

[0098] Construct a regression network with an LSTM neural network architecture, use the running time feature data in the running time estimation training set as the input of the regression network, and use the cumulative running time as the output of the regression network, and train the regression network to obtain an initial running time regression network;

[0099] Use the running time estimation test set to verify the model of the initial running time regression network, and output the initial running time regression network with a prediction test error threshold less than or equal to it as the trained second LSTM neural network model;

[0100] Among them, the calculation formula of the pre-constructed fitness function is: ; In the formula: is the fitness, is the cumulative running time of the i-th target washing machine, is the average running time of all target washing machines, is the total number of target washing machines;

[0101] a3: Selection: Use the roulette wheel method to select two individuals with high fitness in the original population as the father and mother;

[0102] The roulette wheel method is a commonly used selection method, which is used in genetic algorithms to select individuals with higher fitness to enter the next generation; it simulates the process of roulette, and each individual obtains the corresponding "roulette" area according to the level of its fitness; the higher the fitness of an individual, the larger its corresponding area and the higher the probability of being selected;

[0103] a4: Crossover: Perform a crossover operation on the father and mother to generate new individuals;

[0104] It should be noted that: the crossover operation on the father and mother is realized based on the crossover operation, and the crossover operation includes but is not limited to one of single-point crossover, uniform crossover or order crossover, etc.;

[0105] In genetic algorithms, crossover is an important genetic operation used to generate candidate solutions for the new generation; the basic idea of crossover is to simulate the sexual reproduction process in biological genetics, where two parents combine their genetic information to produce offspring; this process helps to introduce diversity in the solution space and may produce new individuals that are more adaptable 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 a genetic algorithm, the mutation operation is to introduce gene diversity and prevent the algorithm from falling into a local optimum; the mutation operation on the new individuals is achieved by means such as uniform mutation or Gaussian mutation;

[0108] a6: Repeat the above steps a2 - a5 until the fitness of the individuals 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 iteration threshold, and then output the laundry matching strategy represented by the corresponding individual as the optimal laundry matching strategy;

[0109] Exemplarily: Assume that the maximum number of iterations is 100 times, and record the individual with the highest fitness and its fitness value in the current population after each iteration; if it is found that the fitness value does not change significantly in a certain generation, it is considered that the convergence condition is reached, stop the iteration, and output the laundry matching strategy represented by the corresponding individual as the optimal laundry matching strategy.

[0110] The adaptive allocation module 105 is used to allocate each target washing machine to the corresponding reserved user according to the optimal laundry matching strategy, so that each target washing machine executes the laundry task of the corresponding reserved user at the future reserved time;

[0111] The present invention can reduce the high - load use of some single washing machines, make the loss states of all washing machines tend to be consistent, thereby equalize the overall washing machine life. Furthermore, it is beneficial to narrow the difference in maintenance cycles between washing machines, improve the return on investment of some washing machines, improve the overall operation efficiency, and reduce the later - stage maintenance cost of campus self - service laundry equipment.

[0112] Embodiment 2

[0113] Please refer to Figure 2 As shown, this embodiment publicly provides a campus self - service laundry management method based on a cloud platform. The method includes:

[0114] S201: Obtain the laundry tasks of all reserved users at the future reserved time, and obtain the optional washing machines at the future reserved time;

[0115] S202: Obtain the fatigue degree data of the optional washing machines, where the fatigue degree data includes the short - term fatigue index of each optional washing machine at the future reserved time;

[0116] S203: Match the same number of target washing machines as the reserved users from all the optional washing machines according to the fatigue degree index, and form multiple laundry matching strategies based on all the target washing machines and the reserved users;

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

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

[0119] Embodiment 3

[0120] Please refer to Figure 3 As shown, this embodiment publicly provides an electronic device, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, it implements the above-mentioned method for a campus self-service laundry management method based on a cloud platform.

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

[0122] Embodiment 4

[0123] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed, it implements the above-mentioned campus self-service laundry management method based on a cloud platform.

[0124] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters, weights, and threshold selections 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 combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of 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, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. 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 network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more collections of available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0126] Those of ordinary skill in the art will appreciate that the units and algorithm steps of the examples described in connection with the embodiments disclosed in the present invention can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

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

[0128] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one way, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed with each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0129] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

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

[0131] As mentioned above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0132] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A campus self-service laundry management system based on a cloud platform, characterized in that The system includes: A first data acquisition module, configured to acquire the laundry tasks of all reserved users at a future reserved time, and acquire the optional washing machines at the future reserved time; A second data acquisition module, configured to acquire the fatigue degree data of the optional washing machines, where the fatigue degree data includes the short-term fatigue index of each optional washing machine at the future reserved time; A reservation matching module, configured to match the same number of target washing machines as the reserved users from all the optional washing machines according to the fatigue degree index, and form multiple laundry matching strategies based on all the target washing machines and the reserved users; A decision-making optimization module, configured to obtain the best laundry matching strategy from multiple laundry matching strategies by using a pre-configured genetic algorithm; An adaptive allocation module, configured to allocate each target washing machine to the corresponding reserved user according to the best laundry matching strategy, so that each target washing machine executes the laundry task of the corresponding reserved user at the future reserved time.

2. The campus self-service laundry management system based on a cloud platform according to claim 1, wherein, The laundry task includes laundry task data, where the laundry task data includes the reserved time, the type of laundry to be washed, the quantity of laundry to be washed, and the planned washing duration; Wherein, the acquisition of the fatigue degree data of the optional washing machines includes: Acquiring the fatigue impact characteristic data of the optional washing machines, where the fatigue impact characteristic data includes the number of laundry tasks in the past L hours, the motor temperature, the motor power, and the planned washing duration under each laundry task, and L is an integer greater than zero; Inputting the fatigue impact characteristic data into a pre-trained first LSTM neural network model to predict the short-term fatigue index of the optional washing machine at the future reserved time; Repeating the above steps until the short-term fatigue index of each optional washing machine at the future reserved time is obtained; Taking the short-term fatigue index of each optional washing machine at the future reserved time as the fatigue degree data of the optional washing machines.

3. The campus self-service laundry management system based on a cloud platform according to claim 2, characterized in that, The training method of the first LSTM neural network model is as follows: Collecting historical fatigue degree training data, and dividing the historical fatigue degree training data into a fatigue degree training set and a fatigue degree test set, where the historical fatigue degree training data includes the fatigue impact characteristic data and its corresponding short-term fatigue index; Wherein, the calculation logic of the short-term fatigue index in the historical fatigue degree training data is as follows: In the formula: is the short-term fatigue index, is the motor power of the optional washing machine during the k-th laundry task, is the motor temperature of the optional washing machine during the k-th laundry task, is the planned washing duration of the k-th laundry task, R is the number of laundry tasks, is the reference set operation duration, is the natural constant; Constructing a regression network with an LSTM neural network as the architecture, taking the fatigue impact characteristic data in the fatigue degree training set as the input of the regression network, and taking the short-term fatigue index as the output, training the regression network to obtain an initial fatigue degree regression model; Using the fatigue degree test set to perform model verification on the initial fatigue degree regression model, and outputting the initial fatigue degree regression model with a prediction test error threshold less than or equal to, as the trained first LSTM neural network model.

4. A campus self-service laundry management system based on a cloud platform according to claim 1, characterized in that, The matching of the same number of target washing machines as the reserved users from all the optional washing machines includes: Obtaining the number M of all reserved users, and M is an integer greater than zero; Sorting the fatigue degree indexes of all the optional washing machines from small to large, and selecting the first N optional washing machines as the target washing machines to obtain the same number of target washing machines as the reserved users, where N = M.

5. The campus self-service laundry management system based on a cloud platform according to claim 4, wherein Obtaining the best laundry matching strategy from multiple laundry matching strategies includes: a1: Initializing the population: Randomly select a certain laundry matching strategy as the original population. The original population contains X individuals, each individual representing a laundry matching strategy. There are multiple reserved users and corresponding target washing machines in each laundry matching strategy. X is an integer greater than zero. a2: Fitness evaluation: For each individual, obtain the cumulative running duration of all target washing machines; and input the cumulative running duration into a pre-constructed fitness function to calculate the fitness of each individual. a3: Selection: Use the roulette wheel method to select two individuals with high fitness in the original population as the father and mother. a4: Crossover: Perform a crossover operation on the father and mother to generate 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 the above steps a2 - a5 until the fitness of the individuals in the original population or the new population is greater than or equal to a preset fitness threshold, or the number of iterations is greater than or equal to a preset maximum iteration threshold. Output the laundry matching strategy represented by the corresponding individual as the best laundry matching strategy.

6. The campus self-service laundry management system based on a cloud platform according to claim 5, wherein, The method for obtaining the cumulative running duration of all target washing machines is as follows: Obtain the running time characteristic data of the target washing machine. The running time characteristic data includes the past usage characteristic data of the past S hours and the future reservation characteristic data within the next W hours. S and W are integers greater than zero. Input the running time characteristic data into a pre-trained second LSTM neural network model to predict the cumulative running duration of the target washing machine at the future reservation time. Among them, the training method of the second LSTM neural network model is as follows: Obtain historical running duration training data, and divide the historical running duration training data into a running duration prediction training set and a running duration prediction test set. The historical running duration training data includes the running time characteristic data and its corresponding cumulative running duration. Construct a regression network with an LSTM neural network as the architecture. Use the running time characteristic data in the running duration prediction training set as the input of the regression network, and the cumulative running duration as the output of the regression network. Train the regression network to obtain an initial running duration regression network. Use the running duration prediction test set to verify the model of the initial running duration regression network, and output the initial running duration regression network with a prediction test error less than or equal to the threshold as the trained second LSTM neural network model.

7. A campus self-service laundry management system based on a cloud platform according to claim 5, characterized in that, The calculation formula of the pre-built fitness function is as follows: ; where: is the fitness, is the cumulative operation duration of the i-th target washing machine, is the average operation duration of all target washing machines, is the total number of target washing machines.

8. A campus self-service laundry management method based on a cloud platform, which is implemented based on the campus self-service laundry management based on a cloud platform described in any one of claims 1-7, characterized in that, The method includes: Obtain the laundry tasks of all reserved users at the future reservation time, and obtain the optional washing machines at the future reservation time. Obtain the fatigue degree data of the optional washing machines. The fatigue degree data includes the short-term fatigue index of each optional washing machine at the future reservation time. Match the same number of target washing machines as the reserved users from all optional washing machines according to the fatigue degree index, and form multiple laundry matching strategies based on all target washing machines and reserved users. Obtain the optimal laundry matching strategy from multiple laundry matching strategies by using a pre-configured genetic algorithm; Allocate each target washing machine to the corresponding reserved user according to the optimal laundry matching strategy, so that each target washing machine executes the laundry task of the corresponding reserved user at the future reserved time.

9. An electronic device, comprising a memory, a processor, and a computer program stored on 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 the cloud platform described in claim 8.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed, it implements the campus self-service laundry management method based on the cloud platform described in claim 8.

Images