Intelligent management system and method for intelligent washing rental cabinet

Abstract

The invention belongs to the technical field of intelligent management of rental cabinets, and discloses an intelligent management system and method for an intelligent washing rental cabinet. The system comprises an equipment data acquisition module, an influence data acquisition module, a comprehensive feature generation module, an equipment utilization reference value generation module, a resource allocation module, an energy consumption optimization module and a report transmission module, and is used for acquiring an equipment data set, acquiring an influence data set, performing feature extraction on the equipment data set and the influence data set, and transmitting a report to the equipment data acquisition module. The method comprises the steps of obtaining an equipment data set, obtaining a comprehensive feature data set, analyzing the equipment data set, an influence data set and the comprehensive feature data set to obtain an equipment utilization reference value, and analyzing the equipment utilization reference value and regional delivery data to obtain an equipment gap report. The method has the remarkable advantages of being high in equipment distribution reasonability, good in energy consumption optimization effect and large in data feedback information effect.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management of rental cabinets, and more specifically, to an intelligent management system and method for intelligent laundry rental cabinets. Background Art

[0002] With the rapid economic development in my country in recent years, people's living standards have been increasingly improved. However, it is difficult for people to wash expensive clothing made of high-end materials such as fur, silk or cashmere at home. They usually need to be sent to dry cleaners for professional washing. In addition, some people are accustomed to sending clothes to dry cleaners for cleaning due to lack of time or different living habits. Since most dry cleaners and other clothing cleaning places require users to deliver the clothes themselves and the cost of a single cleaning is not cheap, smart washing rental cabinets came into being.

[0003] The patent application publication number CN106991764A discloses a system and method for renting basketballs via mobile phones. By designing a basketball rental cabinet connected to the Internet, combined with a basketball with a special wireless sensing electronic tag chip, and combined with a smartphone application, a convenient basketball rental service can be provided for basketball enthusiasts. In this way, basketball enthusiasts can conveniently use professional, high-quality basketballs when they come to the venue, and return them after the game, avoiding the trouble of carrying basketballs and the risk of losing or taking them by mistake. At the same time, it solves the problem that public venues are usually unmanaged, and the return of public basketballs is not guaranteed and difficult to achieve. By connecting the rental cabinet to the equipment operation and maintenance system of the cloud server, the rental service provider can view the distribution and operation status of the rental cabinets operated after logging into the system, and can perform data statistics and other services, ensuring the normal and efficient operation of the rental system.

[0004] However, the above-mentioned system and method for renting basketballs through mobile phones achieves the purpose of providing basketball rental services to users at basketball venues by setting up basketball rental cabinets. To a certain extent, it coincides with the ultimate purpose and implementation method of smart laundry rental cabinets. However, in the use of smart laundry rental cabinets, it is often affected by problems such as uneven user groups, insufficient energy consumption optimization and data feedback compensation. This will directly affect the company's distributed installation, corporate benefits and information control of smart laundry rental cabinets, thereby directly leading to reduced corporate benefits. Therefore, how to effectively solve the rationality of the distributed installation of smart laundry rental cabinets, the optimality of energy consumption optimization and the timeliness of data feedback has become a major problem that needs to be solved in the current smart laundry rental cabinet industry.

[0005] In view of this, the present invention proposes an intelligent management system and method for intelligent laundry rental cabinets to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions, including: The device data collection module is used to collect device data sets, including device utilization data, regional deployment data, time period usage data and washing power consumption data; The impact data collection module is used to collect the impact data set, which includes real-time order data and ambient temperature data; The comprehensive feature generation module is used to preprocess the equipment data set and the impact data set, and perform feature extraction to obtain a comprehensive feature data set Furthermore, the pre-processing methods for the device dataset and the impact dataset include: Use historical mean filling for device datasets; Use a sliding window mean on the impact dataset; Methods for feature extraction include: By extracting device density features from the regional deployment data in the device dataset, we can obtain device density feature data. ,The specific calculation formula for device density feature extraction is: ; in, Deliver data to the region. is the area of ​​the region; By extracting the order change features of the real-time order data in the impact data set, we can obtain the order change feature data. ,The specific calculation formula for order change feature extraction is: ; in, It is the real-time order data in the current hour time period. Real-time order data for the next hour; Packing equipment density feature data and order change feature data to obtain a comprehensive feature data set; The device utilization reference value generation module is used to analyze the device data set, the impact data set and the comprehensive feature data set to obtain the device utilization reference value; Furthermore, the device utilizes a reference value generation module further comprising a historical data reading module, a model support module, a manual data input module and a data transmission module, wherein: The historical data reading module is used to retrieve the historical equipment data set, historical impact data set, historical comprehensive feature data set and actual equipment utilization value stored in the database; The model support module is used to support the system in establishing the required model; The manual data input module is used to support the preset limit threshold Y1 and the preset limit threshold Y2 required for manual input model training; The data transmission module is used to support the transmission of the device utilization reference value calculated by the model; Furthermore, the steps of analyzing the device dataset, the impact dataset, and the comprehensive feature dataset include: Step 1: Based on the historical data reading module, a set of historical device data sets, historical impact data sets, and historical comprehensive feature data sets stored in the database are retrieved and grouped and labeled accordingly based on the timestamp from recent to old. The labeled results are W1, W2, W3, ..., Wn, and the labeled results are used as the sample set; Step 2: Based on the model support module, the sample set obtained in step 2 is divided into an 80% training set and a 20% validation set, and an initial utilization calculation model is established; Step 3: Convert the historical equipment data set, historical impact data set, and historical comprehensive feature data set into corresponding data matrices, respectively, to obtain the historical equipment data matrix, historical feature data matrix, and historical impact data matrix, where: The specific formula of the historical equipment data matrix is: ; in, For the Days of equipment utilization data, For the Regional delivery data for the day, For the Use data for each day, For the Daily washing power consumption data; The specific formula of the historical feature data matrix is: ; in, For the Days of device density feature data, For the The order change characteristic data of the day, For the Daily ambient temperature data; The specific formula of the historical impact data matrix is: ; in, For the Hours of real-time order data, For the Hourly ambient temperature data; Step 4: Substitute into the calculation formula: , get the initial equipment utilization reference value, where, is the sample size, For the The weight factor of the samples, For the The splitting rules generated by each sample are based on historical data. is the time decay weight factor, is the spatiotemporal weight factor, is the spatiotemporal attention mechanism function; Step 5: Based on the initial equipment utilization reference value obtained in step 4, calculate the predicted error value and the average error value. The specific calculation formula of the predicted error value is: ; Get the prediction error value, where is the sample size, For the The actual device utilization value of samples, For the Initial equipment utilization reference value for each sample; The specific calculation formula of the average error value is: ; Get the average error value, where is the sample size; Step 6: Based on the initial equipment utilization reference value obtained in step 4, the actual equipment utilization value is subtracted from the initial equipment utilization reference value to obtain the residual value. When the absolute value of the residual value is less than twice the residual standard deviation, return to step 4 to recalibrate the weights. Step 7: Based on the prediction error value and average error value obtained in step 5, according to the preset limit threshold Y1 and the preset limit threshold Y2, when the prediction error value is less than the preset limit threshold Y1 and the average error value is less than the preset limit threshold Y2, the utilization calculation model is output; otherwise, return to step 1 to expand the sample data retrieval date; Step 8: Input the equipment data set, impact data set, and comprehensive feature data set into the utilization calculation model, output the equipment utilization reference value, and output the equipment utilization reference value to the resource allocation module based on the data transmission module; Furthermore, the specific methods of weight recalibration include: The weight factor is adjusted based on the prediction error value and the average error value. and spatiotemporal weight factors Optimize, the specific calculation formula group of optimization is: ; in, and are the optimized weight factors and spatiotemporal weight factors , and is the learning rate coefficient; The resource allocation module is used to analyze the equipment utilization reference value and regional deployment data to obtain an equipment gap report; Further, the methods for analyzing the equipment utilization reference values ​​and regional deployment data include: The resource gap value is calculated based on the equipment utilization reference value and regional deployment data. The specific calculation formula for the gap calculation is: ; Get the gap reference value, where The number of washing equipment available; When the gap reference value is less than 5% of the total number of washing equipment, a low-risk gap report is generated; when the gap reference value is greater than or equal to 5% of the total number of washing equipment and less than or equal to 15% of the total number of washing equipment, a medium-risk gap report is generated; when the gap reference value is greater than 15% of the total number of washing equipment, a high-risk gap report is generated; Package low-risk gap reports, medium-risk gap reports, and high-risk gap reports to obtain equipment gap reports; Furthermore, the equipment gap report specifically includes: The low-risk gap report includes a statement that the current washing equipment is sufficient, and staff are asked to prioritize user incentives to encourage users to disperse to low-washing periods, without the need to add more washing equipment; The medium-risk gap report includes an explanation of the current shortage of washing equipment. Staff are asked to temporarily deploy 50% of the washing equipment required to meet the gap. Before the deployment of the deployed washing equipment, 20% of users will be forced to move to the off-peak washing period. The high-risk gap report includes an explanation of the current severe shortage of washing equipment, requiring staff to quickly purchase washing equipment, and displaying a message in the washing equipment display area that "the current area is fully loaded." It automatically rejects new orders before the purchase of washing equipment and recommends that users use washing equipment in a low-risk gap area within three kilometers. Energy consumption optimization module, used to analyze equipment data sets and impact data sets to obtain adjustment measures reports; Furthermore, the methods for analyzing the device dataset and the impact dataset include: The washing cost is obtained by cost calculation of the equipment dataset and the impact dataset , the specific calculation formula for cost calculation is: ; in, Hourly time period Real-time order data at the time, Hourly time period The electricity price at that time; Analyze washing cost and ambient temperature data to obtain adjustment measures report; The adjustment measures reported include prioritizing washing orders during periods with low electricity prices and reducing the washing water heating time by 5% when the ambient temperature is greater than 28 degrees Celsius; The report transmission module is used to process and output the equipment gap report, the adjustment measure report and the model accuracy report, the model accuracy report including the prediction error value and the average error value; Furthermore, the methods for processing and outputting the equipment gap report, the adjustment measure report, and the model accuracy report include: Provide visualization support for equipment gap reports, adjustment measures reports, and model accuracy reports; Analyze the adjustment measures report and separately display the usage percentage during low-price periods and the expected energy saving rate; Push equipment gap reports, adjustment measures reports, model accuracy reports, usage percentages during low-price periods, and expected energy saving rates to staff receiving terminals according to preset time units; Furthermore, S1: collecting equipment data sets, the equipment data sets include equipment utilization data, regional deployment data, time period usage data and washing power consumption data; S2: Collect impact data sets, including real-time order data and ambient temperature data; S3: Preprocess the device dataset and impact dataset, and perform feature extraction to obtain a comprehensive feature dataset; S4: Analyze the equipment data set, impact data set, and comprehensive feature data set to obtain equipment utilization reference values; S5: Analyze the equipment utilization reference value and regional deployment data to obtain an equipment gap report; S6: Analyze the equipment data set and the impact data set to obtain an adjustment measure report; S7: Process and output the equipment gap report, adjustment measure report and model accuracy report. The model accuracy report includes the prediction error value and the average error value.

[0007] The technical effects and advantages of the intelligent management system and method for intelligent laundry rental cabinets of the present invention are as follows: The present invention collects equipment data sets, which include equipment utilization data, regional delivery data, time period usage data, and washing power consumption data; collects impact data sets, which include real-time order data and ambient temperature data; pre-processes the equipment data sets and the impact data sets, and performs feature extraction to obtain a comprehensive feature data set; analyzes the equipment data sets, the impact data sets, and the comprehensive feature data sets to obtain equipment utilization reference values; analyzes the equipment utilization reference values ​​and regional delivery data to obtain an equipment gap report; analyzes the equipment data sets and the impact data sets to obtain an adjustment measure report; processes and outputs the equipment gap report, the adjustment measure report, and the model accuracy report; the model accuracy report includes a prediction error value and an average error value, so that the system can be under the dynamic influence of real-time order data, Accurately calculate the utilization rate of washing equipment, thereby providing a data basis for the staff to distribute and install the washing equipment. In addition, the present invention can further improve the accuracy of data calculation and intuitively display the accuracy of system calculation through multiple data re-verification and training of the initial utilization calculation model. At the same time, the resource allocation module is used to effectively empower the calculation results, so that the calculation results can directly feedback the rationality of the current washing equipment installation, greatly reducing the workload of the staff. Moreover, through the energy consumption optimization module, the system can further reduce the power consumption of the washing equipment according to the ambient temperature, and recommend washing services during off-peak hours in combination with real-time electricity prices, thereby achieving the purpose of increasing corporate benefits. Overall, the present invention has the significant advantages of strong equipment distribution rationality, good energy consumption optimization effect and great data feedback information function. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a schematic diagram of an intelligent management system for an intelligent laundry rental cabinet according to the present invention; Figure 2 This is a schematic diagram of an intelligent management method for an intelligent laundry rental cabinet according to the present invention. DETAILED DESCRIPTION

[0009] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0010] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," "the," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0011] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0012] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0013] In fact, the server-side device deployed by the smart management system of the smart laundry rental cabinet may be composed of one or more devices. The smart management system of the above-mentioned smart laundry rental cabinet can be implemented as: business instance, virtual machine, hardware device. For example, the smart management system of the smart laundry rental cabinet can be implemented as a business instance deployed on one or more devices in the cloud node. In simple terms, the smart management system of the smart laundry rental cabinet can be understood as a software deployed on the cloud node, which is used to provide the smart management system of the smart laundry rental cabinet for each user terminal. Alternatively, the smart management system of the smart laundry rental cabinet can also be implemented as a virtual machine deployed on one or more devices in the cloud node. The virtual machine is installed with application software for managing each user terminal. Alternatively, the smart management system of the smart laundry rental cabinet can also be implemented as a server composed of many hardware devices of the same or different types, and one or more hardware devices are set to provide the smart management system of the smart laundry rental cabinet for each user terminal.

[0014] In terms of implementation, the smart management system and user end of the smart laundry rental cabinet are mutually compatible. Specifically, if the smart management system is an application installed on a cloud service platform, the user end serves as a client that establishes a communication connection with the application. Alternatively, if the smart management system is implemented as a website, the user end serves as a webpage. Alternatively, if the smart management system is implemented as a cloud service platform, the user end serves as a mini-program within an instant messaging application.

[0015] like Figure 1 , which is a system architecture diagram of an intelligent management system for intelligent laundry rental cabinets provided by one embodiment of the present invention.

[0016] The intelligent management system of the smart laundry rental cabinet described in the present invention can be set in a cloud server. In terms of implementation, it can be used as one or more service devices, or it can be installed as an application on the cloud (such as a mobile service operator's server, server cluster, etc.), or it can be developed as a website. According to the functions implemented, the intelligent management system of the smart laundry rental cabinet can include an equipment data acquisition module, an impact data acquisition module, a comprehensive feature generation module, an equipment utilization reference value generation module, a resource allocation module, an energy consumption optimization module and a report transmission module. The module described in the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0017] In an embodiment of the present invention, in the intelligent management system of the smart laundry rental cabinet, each of the above modules can be implemented independently and called with other modules. The call here can be understood as a module that can connect to multiple modules of another type and provide corresponding services to the multiple modules connected to it. For example, the sharing evaluation module can call the same information collection module to obtain the information collected by the information collection module. Based on the above characteristics, in the intelligent management system of the smart laundry rental cabinet provided by the embodiment of the present invention, the scope of application of the intelligent management system architecture of the smart laundry rental cabinet can be adjusted by adding modules and directly calling them without modifying the program code, thereby realizing cluster-based horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the intelligent management system of the smart laundry rental cabinet. In actual applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers.

[0018] Example 1 See also Figure 1 As shown, the present embodiment provides a smart management system and method for a smart laundry rental cabinet, the system comprising: The device data collection module is used to collect device data sets, including device utilization data, regional deployment data, time period usage data and washing power consumption data; It should be explained that the total operating time and actual usage time of all washing equipment in a designated area are collected through the status monitoring system, and the calculation formula is substituted into the following: , get equipment utilization data, where, For single use duration, The total running time; through the washing equipment deployment record, the number of washing equipment currently online in the specified area is collected to obtain regional deployment data; through the timestamp usage record, the usage records of the equipment in the specified area in each time period within 24 hours are collected to obtain time period usage data; through the energy consumption monitor, the average energy consumption value of a single wash of all equipment in the specified area is collected to obtain washing power consumption data; The impact data collection module is used to collect the impact data set, which includes real-time order data and ambient temperature data; It should be explained that the order management system collects the new order volume of all devices in the specified area during the current period to obtain real-time order data; the temperature sensor collects the ambient temperature value around the equipment in the specified area to obtain ambient temperature data; The comprehensive feature generation module is used to preprocess the device data set and the impact data set, and perform feature extraction to obtain a comprehensive feature data set; Furthermore, the pre-processing methods for the device dataset and the impact dataset include: Use historical mean filling for device datasets; Use a sliding window mean on the impact dataset; Methods for feature extraction include: By extracting device density features from the regional deployment data in the device dataset, we can obtain device density feature data. ,The specific calculation formula for device density feature extraction is: ; in, Deliver data to the region. is the area of ​​the region; By extracting the order change features of the real-time order data in the impact data set, we can obtain the order change feature data. ,The specific calculation formula for order change feature extraction is: ; in, It is the real-time order data in the current hour time period. Real-time order data for the next hour; Packing equipment density feature data and order change feature data to obtain a comprehensive feature data set; The device utilization reference value generation module is used to analyze the device data set, the impact data set and the comprehensive feature data set to obtain the device utilization reference value; Furthermore, the device utilizes a reference value generation module that also includes a historical data reading module, a model support module, a manual data input module, and a data transmission module, wherein: The historical data reading module is used to retrieve the historical equipment data set, historical impact data set, historical comprehensive feature data set and actual equipment utilization value stored in the database; The model support module is used to support the system in establishing the required model; The manual data input module is used to support the preset limit threshold Y1 and the preset limit threshold Y2 required for manual input model training; The data transmission module is used to support the transmission of the device utilization reference value calculated by the model; Furthermore, the steps of analyzing the device dataset, the impact dataset, and the comprehensive feature dataset include: Step 1: Based on the historical data reading module, a set of historical device data sets, historical impact data sets, and historical comprehensive feature data sets stored in the database are retrieved and grouped and labeled accordingly based on the timestamp from recent to old. The labeled results are W1, W2, W3, ..., Wn, and the labeled results are used as the sample set; Step 2: Based on the model support module, the sample set obtained in step 2 is divided into an 80% training set and a 20% validation set, and an initial utilization calculation model is established; Step 3: Convert the historical equipment data set, historical impact data set, and historical comprehensive feature data set into corresponding data matrices, respectively, to obtain the historical equipment data matrix, historical feature data matrix, and historical impact data matrix, where: The specific formula of the historical equipment data matrix is: ; in, For the Days of equipment utilization data, For the Regional delivery data for the day, For the Use data for each day, For the Daily washing power consumption data; The specific formula of the historical feature data matrix is: ; in, For the Days of device density feature data, For the The order change characteristic data of the day, For the Daily ambient temperature data; The specific formula of the historical impact data matrix is: ; in, For the Hours of real-time order data, For the Hourly ambient temperature data; Step 4: Substitute into the calculation formula: , get the initial equipment utilization reference value, where, is the sample size, For the The weight factor of the samples, For the The splitting rules generated by each sample are based on historical data. is the time decay weight factor, is the spatiotemporal weight factor, is the spatiotemporal attention mechanism function; What needs to be explained is that To capture the spatiotemporal correlation between real-time order data and ambient temperature data, for example, if there is a sudden increase in real-time order data or abnormal ambient temperature data in a certain hourly period, the spatiotemporal attention mechanism function will give this hourly period a higher weight to increase the impact on the calculation of the initial device utilization reference value.

[0019] Step 5: Based on the initial equipment utilization reference value obtained in step 4, calculate the predicted error value and the average error value. The specific calculation formula of the predicted error value is: ; Get the prediction error value, where is the sample size, For the The actual device utilization value of samples, For the Initial equipment utilization reference value for each sample; The specific calculation formula of the average error value is: ; Get the average error value, where is the sample size; Step 6: Based on the initial equipment utilization reference value obtained in step 4, the actual equipment utilization value is subtracted from the initial equipment utilization reference value to obtain the residual value. When the absolute value of the residual value is less than twice the residual standard deviation, return to step 4 to recalibrate the weights. Step 7: Based on the prediction error value and average error value obtained in step 5, according to the preset limit threshold Y1 and the preset limit threshold Y2, when the prediction error value is less than the preset limit threshold Y1 and the average error value is less than the preset limit threshold Y2, the utilization calculation model is output; otherwise, return to step 1 to expand the sample data retrieval date; Step 8: Input the equipment data set, impact data set, and comprehensive feature data set into the utilization calculation model, output the equipment utilization reference value, and output the equipment utilization reference value to the resource allocation module based on the data transmission module; Furthermore, the specific methods for weight recalibration include: The weight factor is adjusted based on the prediction error value and the average error value. and spatiotemporal weight factors Optimize, the specific calculation formula group of optimization is: ; in, and are the optimized weight factors and spatiotemporal weight factors , and is the learning rate coefficient; The resource allocation module is used to analyze the equipment utilization reference value and regional deployment data to obtain an equipment gap report; Further, methods for analyzing equipment utilization reference values ​​and regional deployment data include: The resource gap value is calculated based on the equipment utilization reference value and regional deployment data. The specific calculation formula for the gap calculation is: ; Get the gap reference value, where The number of washing equipment available; When the gap reference value is less than 5% of the total number of washing equipment, a low-risk gap report is generated; when the gap reference value is greater than or equal to 5% of the total number of washing equipment and less than or equal to 15% of the total number of washing equipment, a medium-risk gap report is generated; when the gap reference value is greater than 15% of the total number of washing equipment, a high-risk gap report is generated; Package low-risk gap reports, medium-risk gap reports, and high-risk gap reports to obtain equipment gap reports; Furthermore, the equipment gap report specifically includes: The low-risk gap report includes a statement that the current washing equipment is sufficient, and staff are asked to prioritize user incentives to encourage users to disperse to low-washing periods, without the need to add more washing equipment; The medium-risk gap report includes an explanation of the current shortage of washing equipment. Staff are asked to temporarily deploy 50% of the washing equipment required to meet the gap. Before the deployment of the deployed washing equipment, 20% of users will be forced to move to the off-peak washing period. The high-risk gap report includes an explanation of the current severe shortage of washing equipment, requiring staff to quickly purchase washing equipment, and displaying a message in the washing equipment display area that "the current area is fully loaded." It automatically rejects new orders before the purchase of washing equipment and recommends that users use washing equipment in a low-risk gap area within three kilometers. Energy consumption optimization module, used to analyze equipment data sets and impact data sets to obtain adjustment measures reports; Further, methods for analyzing the device dataset and impact dataset include: The washing cost is obtained by cost calculation of the equipment dataset and the impact dataset , the specific calculation formula for cost calculation is: ; in, Hourly time period Real-time order data at the time, Hourly time period The electricity price at that time; Analyze washing cost and ambient temperature data to obtain adjustment measures report; The adjustment measures reported include prioritizing washing orders during periods with low electricity prices and reducing the washing water heating time by 5% when the ambient temperature is greater than 28 degrees Celsius; The report transmission module is used to process and output the equipment gap report, the adjustment measure report and the model accuracy report, the model accuracy report including the prediction error value and the average error value; Furthermore, the methods for processing and outputting the equipment gap report, adjustment measure report and model accuracy report include: Provide visualization support for equipment gap reports, adjustment measures reports, and model accuracy reports; Analyze the adjustment measures report and separately display the usage percentage during low-price periods and the expected energy saving rate; Push equipment gap reports, adjustment measures reports, model accuracy reports, usage percentages during low-price periods, and expected energy saving rates to staff receiving terminals according to preset time units; This embodiment has the beneficial effects of collecting equipment data sets, which include equipment utilization data, regional deployment data, time period usage data, and washing power consumption data; collecting impact data sets, which include real-time order data and ambient temperature data; preprocessing the equipment data sets and impact data sets, and performing feature extraction to obtain a comprehensive feature data set; analyzing the equipment data sets, impact data sets, and comprehensive feature data sets to obtain equipment utilization reference values; analyzing the equipment utilization reference values ​​and regional deployment data to obtain an equipment gap report; analyzing the equipment data sets and impact data sets to obtain an adjustment measure report; processing and outputting the equipment gap report, adjustment measure report, and model accuracy report; the model accuracy report includes a prediction error value and an average error value, so that the system can dynamically influence the real-time order data. Under the influence, the utilization rate of the washing equipment can be accurately calculated, thereby providing a data basis for the staff to distribute and install the washing equipment. In addition, the present invention can further improve the accuracy of data calculation and intuitively display the system calculation accuracy through multiple data re-examinations and training of the initial utilization calculation model. At the same time, the resource allocation module is used to effectively empower the calculation results, so that the calculation results can directly feedback the rationality of the current washing equipment installation, which greatly reduces the workload of the staff. Moreover, through the energy consumption optimization module, the system can further reduce the power consumption of the washing equipment according to the ambient temperature, and recommend washing services during off-peak hours in combination with real-time electricity prices, thereby achieving the purpose of increasing corporate benefits. Generally speaking, the present invention has the significant advantages of strong equipment distribution rationality, good energy consumption optimization effect and great data feedback information function.

[0020] Example 2 See also Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description of Example 1. A smart management method for a smart laundry rental cabinet is provided, the method comprising: S1: collecting a device data set, the device data set including device utilization data, regional deployment data, time period usage data, and washing power consumption data; S2: Collect impact data sets, including real-time order data and ambient temperature data; S3: Preprocess the device dataset and impact dataset, and perform feature extraction to obtain a comprehensive feature dataset; S4: Analyze the equipment data set, impact data set, and comprehensive feature data set to obtain equipment utilization reference values; S5: Analyze the equipment utilization reference value and regional deployment data to obtain an equipment gap report; S6: Analyze the equipment data set and the impact data set to obtain an adjustment measure report; S7: Process and output the equipment gap report, adjustment measure report and model accuracy report. The model accuracy report includes the prediction error value and the average error value.

[0021] Example 3 It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0022] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0023] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0024] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. Terms such as "first" and "second" are used to indicate names and do not imply any particular order.

[0025] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A smart management system for intelligent laundry rental cabinets, characterized by: The system includes: an equipment data acquisition module, an impact data acquisition module, a comprehensive feature generation module, an equipment utilization reference value generation module, a resource allocation module, an energy consumption optimization module and a report transmission module, wherein: The device data collection module is used to collect device data sets, including device utilization data, regional deployment data, time period usage data and washing power consumption data; The impact data collection module is used to collect the impact data set, which includes real-time order data and ambient temperature data; The comprehensive feature generation module is used to preprocess the device data set and the impact data set, and perform feature extraction to obtain a comprehensive feature data set; The device utilization reference value generation module is used to analyze the device data set, the impact data set and the comprehensive feature data set to obtain the device utilization reference value; The resource allocation module is used to analyze the equipment utilization reference value and regional deployment data to obtain an equipment gap report; The energy consumption optimization module is used to analyze the equipment data set and the impact data set to obtain an adjustment measure report; The report transmission module is used to process and output the equipment gap report, the adjustment measure report and the model accuracy report, and the model accuracy report includes the prediction error value and the average error value.

2. The intelligent management system for intelligent laundry rental cabinets according to claim 1 is characterized in that: Methods for preprocessing the device dataset and impact dataset include: Use historical mean filling for device datasets; Use a sliding window mean on the impact dataset; Methods for feature extraction include: By extracting device density features from the regional deployment data in the device dataset, we can obtain device density feature data. ,The specific calculation formula for device density feature extraction is: ; in, Deliver data to the region. is the area of ​​the region; By extracting the order change features of the real-time order data in the impact data set, we can obtain the order change feature data. ,The specific calculation formula for order change feature extraction is: ； in, The current hour time period Real-time order data within For the next hour Real-time order data within; The device density feature data and order change feature data are packaged to obtain a comprehensive feature data set.

3. The intelligent management system for intelligent laundry rental cabinets according to claim 1 is characterized in that: The device utilizes a reference value generation module further comprising a historical data reading module, a model support module, a manual data input module and a data transmission module, wherein: The historical data reading module is used to retrieve the historical equipment data set, historical impact data set, historical comprehensive feature data set and actual equipment utilization value stored in the database; The model support module is used to support the system in establishing the required model; The manual data input module is used to support the preset limit threshold Y1 and the preset limit threshold Y2 required for manual input model training; The data transmission module is used to support the device utilization reference value calculated by the transmission model.

4. The intelligent management system for intelligent laundry rental cabinets according to claim 3 is characterized in that: The steps for analyzing the device dataset, impact dataset, and comprehensive feature dataset include: Step 1: Based on the historical data reading module, a set of historical device data sets, historical impact data sets, and historical comprehensive feature data sets stored in the database are retrieved and grouped and labeled accordingly based on the timestamp from recent to old. The labeled results are W1, W2, W3, ..., Wn, and the labeled results are used as the sample set; Step 2: Based on the model support module, the sample set obtained in step 2 is divided into an 80% training set and a 20% validation set, and an initial utilization calculation model is established; Step 3: Convert the historical equipment data set, historical impact data set, and historical comprehensive feature data set into corresponding data matrices, respectively, to obtain the historical equipment data matrix, historical feature data matrix, and historical impact data matrix, where: The specific formula of the historical equipment data matrix is: ； in, For the Days of equipment utilization data, For the Regional delivery data for the day, For the Use data for each day, For the Daily washing power consumption data; The specific formula of the historical feature data matrix is: ； in, For the Days of device density feature data, For the The order change characteristic data of the day, For the Daily ambient temperature data; The specific formula of the historical impact data matrix is: ； in, For the Hours of real-time order data, For the Hourly ambient temperature data; Step 4: Substitute into the calculation formula: , get the initial equipment utilization reference value, where, is the sample size, For the The weight factor of the samples, For the The splitting rules generated by each sample are based on historical data. is the time decay weight factor, is the spatiotemporal weight factor, is the spatiotemporal attention mechanism function; Step 5: Based on the initial equipment utilization reference value obtained in step 4, calculate the predicted error value and the average error value. The specific calculation formula of the predicted error value is: ； Get the prediction error value, where is the sample size, For the The actual device utilization value of samples, For the Initial equipment utilization reference value for each sample; The specific calculation formula of the average error value is: ; Get the average error value, where is the sample size; Step 6: Based on the initial equipment utilization reference value obtained in step 4, the actual equipment utilization value is subtracted from the initial equipment utilization reference value to obtain the residual value. When the absolute value of the residual value is less than twice the residual standard deviation, return to step 4 to recalibrate the weights. Step 7: Based on the prediction error value and average error value obtained in step 5, according to the preset limit threshold Y1 and the preset limit threshold Y2, when the prediction error value is less than the preset limit threshold Y1 and the average error value is less than the preset limit threshold Y2, the utilization calculation model is output; otherwise, return to step 1 to expand the sample data retrieval date; Step 8: Input the equipment data set, impact data set and comprehensive feature data set into the utilization calculation model, output the equipment utilization reference value, and output the equipment utilization reference value to the resource allocation module based on the data transmission module.

5. The intelligent management system for intelligent laundry rental cabinets according to claim 4 is characterized in that: Specific methods for weight recalibration include: The weight factor is adjusted based on the prediction error value and the average error value. and spatiotemporal weight factors Optimize, the specific calculation formula group of optimization is: ； in, and are the optimized weight factors and spatiotemporal weight factors , and is the learning rate coefficient.

6. The intelligent management system for intelligent laundry rental cabinets according to claim 1 is characterized in that: Methods for analyzing equipment utilization reference values ​​and regional deployment data include: The resource gap value is calculated based on the equipment utilization reference value and regional deployment data. The specific calculation formula for the gap calculation is: ； Get the gap reference value, where The number of washing equipment available; When the gap reference value is less than 5% of the total number of washing equipment, a low-risk gap report is generated; when the gap reference value is greater than or equal to 5% of the total number of washing equipment and less than or equal to 15% of the total number of washing equipment, a medium-risk gap report is generated; when the gap reference value is greater than 15% of the total number of washing equipment, a high-risk gap report is generated; The low-risk gap report, medium-risk gap report and high-risk gap report are packaged to obtain the equipment gap report.

7. The intelligent management system for intelligent laundry rental cabinets according to claim 6 is characterized in that: The Equipment Gap Report specifically includes: The low-risk gap report includes a statement that the current washing equipment is sufficient, and staff are asked to prioritize user incentives to encourage users to disperse to low-washing periods, without the need to add more washing equipment; The medium-risk gap report includes an explanation of the current shortage of washing equipment. Staff are asked to temporarily deploy 50% of the washing equipment required to meet the gap. Before the deployment of the deployed washing equipment, 20% of users will be forced to move to the off-peak washing period. The high-risk gap report includes an explanation of the current severe shortage of washing equipment, requiring staff to quickly purchase washing equipment, prompting "The current area is full" in the washing equipment display area, automatically rejecting new orders for washing equipment before entry, and recommending users to use washing equipment in low-risk gap areas within three kilometers.

8. The intelligent management system for intelligent laundry rental cabinets according to claim 1 is characterized in that: Methods for analyzing device and impact datasets include: The washing cost is obtained by cost calculation of the equipment dataset and the impact dataset , the specific calculation formula for cost calculation is: ； in, Hourly time period Real-time order data at the time, Hourly time period The electricity price at that time; Analyze washing cost and ambient temperature data to obtain adjustment measures report; The adjustment measures report includes prioritizing washing orders to periods with low electricity prices and reducing the washing water heating time by 5% when the ambient temperature is greater than 28 degrees Celsius.

9. The intelligent management system for intelligent laundry rental cabinets according to claim 1 is characterized in that: Methods for processing and outputting equipment gap reports, adjustment measures reports, and model accuracy reports include: Provide visualization support for equipment gap reports, adjustment measures reports, and model accuracy reports; Analyze the adjustment measures report and separately display the usage percentage during low-price periods and the expected energy saving rate; The equipment gap report, adjustment measure report, model accuracy report, usage percentage during low-price periods and expected energy saving rate are pushed to the staff receiving end according to the preset time unit.

10. A smart management method for a smart laundry rental cabinet, implemented according to a smart management system for a smart laundry rental cabinet according to any one of claims 1 to 9, characterized in that: The following steps are included: S1: Collect equipment data sets, including equipment utilization data, regional deployment data, time period usage data, and washing power consumption data; S2: Collect impact data sets, including real-time order data and ambient temperature data; S3: Preprocess the device dataset and impact dataset, and perform feature extraction to obtain a comprehensive feature dataset; S4: Analyze the equipment data set, impact data set, and comprehensive feature data set to obtain equipment utilization reference values; S5: Analyze the equipment utilization reference value and regional deployment data to obtain an equipment gap report; S6: Analyze the equipment data set and the impact data set to obtain an adjustment measure report; S7: Process and output the equipment gap report, adjustment measure report and model accuracy report. The model accuracy report includes the prediction error value and the average error value.

Images