Water-saving management system suitable for multiple evaluation standards and method thereof

Abstract

The invention relates to the field of water-saving systems, in particular to a water-saving management system suitable for multiple evaluation standards, which comprises a data acquisition module, a data transmission module, a data processing module, a multiple evaluation standard generation module, an optimization algorithm module, a control module and a user feedback module. The data acquisition module is interconnected with the data transmission module to ensure acquisition and transmission of real-time data; the data processing module is communicated with the multi-evaluation standard generation module, generates a plurality of water utilization evaluation standards by processing the original water utilization data, and provides input data for the optimization algorithm module; the optimization algorithm module generates a water-saving strategy by analyzing an evaluation standard, and performs actual control through the control module to finally realize an automatic water-saving management target; and the user feedback module interacts with the control module and the optimization algorithm module, and can continuously improve a water saving scheme according to user preferences, so that the beneficial effects of remarkable water saving effect, personalized regulation and control and improvement of the resource utilization rate are achieved.

Description

Technical Field

[0001] The present invention relates to the field of water-saving systems, and in particular to a water-saving management system and method thereof applicable to multiple evaluation standards. Background Art

[0002] In the current water resource management system, water conservation, as one of the major challenges facing the world, has received widespread attention from all walks of life. However, existing water conservation management systems generally have technical defects such as inaccurate data collection, inaccurate water efficiency assessment, and lack of intelligent water conservation optimization methods, making it difficult to cope with increasingly complex water use scenarios and diverse user needs. Specifically, existing technologies mainly face the following problems:

[0003] Most existing water-saving management systems rely on regular or manual water meter readings, which cannot achieve real-time monitoring of users' water use behavior. This model results in untimely updates of water use data, affecting the accuracy and response speed of the system. Traditional systems usually rely on a single collection method and fail to fully utilize the Internet of Things (IoT) technology for multi-dimensional data collection, such as water consumption, water use time, ambient temperature, etc., which makes it difficult for the system to capture complex water use behavior characteristics. At the same time, due to data transmission delays and insufficient processing power, the system cannot intervene in abnormal water use behavior in a timely manner, resulting in limited effectiveness of water-saving measures.

[0004] In existing technologies, water efficiency assessment often relies on simple statistical analysis methods, which cannot dynamically reflect users' water use habits and changes in the external environment. These systems cannot effectively use historical data and real-time data for intelligent water-saving assessment and optimization, and lack adaptability and predictive capabilities. For example, existing systems usually formulate water-saving strategies through fixed rules or thresholds, failing to consider individual users' water use habits and the complexity of water use scenarios, resulting in overly rigid water-saving measures and the inability to achieve accurate personalized water-saving optimization.

[0005] A major flaw in existing water-saving systems is the inability to effectively analyze the correlation between water-use behaviors of different users. This means that when formulating water-saving strategies, the system usually only optimizes for individual users, while ignoring the correlation between water-use behavior patterns that may exist between user groups. For example, some users have obvious commonalities in their peak water-use time periods, but the existing system lacks the ability to stagger water use or jointly save water during these peak periods, resulting in low overall water-saving efficiency. In addition, when generating water-saving strategies, existing systems are often based on single-objective optimization and lack linkage analysis of multi-objective optimization. They are unable to take into account both water-use efficiency and user behavior correlation, thus limiting the system's water-saving effect. Summary of the invention

[0006] The purpose of the present invention is to provide a water-saving management system and method applicable to multiple evaluation criteria to solve the technical problems raised in the above-mentioned background technology.

[0007] Based on the above ideas, the present invention provides the following technical solutions: a water-saving management system applicable to multiple evaluation criteria, comprising:

[0008] Data acquisition module, data transmission module, data processing module, multiple evaluation criteria generation module, optimization algorithm module, control module and user feedback module;

[0009] The data collection module is used to collect water use data in real time from water resource use terminals. The water use data includes water consumption, water use time and water use area, and transmits the water use data to the central server through the Internet of Things sensor;

[0010] The data transmission module is used to transmit the data acquired by the data acquisition module to the data processing module in real time through the network;

[0011] The data processing module receives the raw water use data transmitted by the data transmission module, and pre-processes the raw water use data based on predefined standards, wherein the pre-processing includes data cleaning, format conversion, and detection and elimination of abnormal data, and transmits the processed data to the optimization algorithm module;

[0012] The multiple evaluation criteria generation module generates multiple evaluation criteria according to different water use scenarios and needs by analyzing the data from the data processing module;

[0013] The optimization algorithm module receives the evaluation data provided by the multiple evaluation criteria generation module, performs water efficiency optimization analysis, calculates water-saving potential and water-saving suggestions by comparing historical data with current water use patterns, and transmits the optimization results to the control module;

[0014] The control module receives the water-saving optimization result output by the optimization algorithm module, and adjusts the user's water-using equipment in real time through the automatic control system. The specific control actions include adjusting the water supply flow, limiting the water use during peak hours, and enabling or disabling the automatic equipment for a specific time period;

[0015] The user feedback module is interconnected with the control module and displays the operating status, optimization suggestions and actual water use data of the water-saving management system to the user through the human-computer interface; the user feedback module is also used to receive manual feedback and preference settings from the user and further adjust the output results of the optimization algorithm module.

[0016] Through the modular design of data collection, transmission, processing, analysis, optimization and control, all-round, real-time monitoring and automatic optimization of users' water use behavior are realized. The linkage between modules not only improves the accuracy of water use data, but also automatically generates water-saving strategies and performs equipment regulation based on multiple evaluation criteria. The user feedback module provides the system with the ability of adaptive optimization, and can continuously improve water-saving plans according to user preferences, thereby achieving significant water-saving effects, personalized regulation, and improved resource utilization.

[0017] Preferably, the optimization algorithm module includes a dynamic water efficiency optimization algorithm, and the dynamic water efficiency optimization algorithm includes the following steps:

[0018] S1. Collect historical water use data and pre-process it;

[0019] S2. Use linear regression model to predict water use efficiency based on water use period and efficiency index;

[0020] S3. Calculate the water-saving potential based on the water usage habits of different users and generate an optimized adjustment plan.

[0021] The dynamic water efficiency optimization algorithm can conduct in-depth learning of users' historical water use data and conduct predictive analysis based on current water use patterns. Through the linear regression model, it can accurately calculate the user's water saving potential and generate customized optimization and adjustment plans to help users achieve the best water saving effect in different water use scenarios. The algorithm improves the intelligence level of water use management and has dynamic adjustment capabilities, which can flexibly respond to water use behaviors in different time periods.

[0022] Preferably, the dynamic water efficiency optimization algorithm implementation formula includes:

[0023] E(t)=a×U(t)+b×T(t)

[0024] Among them, E(t) represents the water use efficiency in period t, U(t) is the water consumption of the user in period t, T(t) is the ambient temperature in period t, and a and b are weight coefficients obtained by data regression in the algorithm.

[0025] The specific implementation of the formula can comprehensively consider external factors such as user water consumption and ambient temperature to accurately calculate water use efficiency. The introduction of this formula enables the algorithm to have the ability to make fine adjustments, dynamically optimize water use strategies based on real-time data, ensure that the optimization results of the water-saving system meet actual needs, and provide clear optimization directions to improve the operability and accuracy of the system.

[0026] Preferably, the data processing module includes a user behavior correlation analysis algorithm, which is used to calculate the correlation between different water use behaviors, including the following steps:

[0027] S1, identify user groups with similar water use behaviors through clustering algorithms;

[0028] S2. Analyze the peak water usage time period of users based on the water usage patterns of user groups and calculate their correlation;

[0029] S3. Generate water-saving improvement suggestions for different users.

[0030] Preferably, the user behavior correlation analysis algorithm can identify similar user groups based on the water use behavior data of large-scale users, and perform correlation analysis on the water use patterns of these groups. This can not only identify the peak water use periods of users and help optimize the overall water management, but also provide targeted water-saving suggestions for specific user groups, thereby achieving more effective water-saving measures.

[0031] Preferably, the user behavior correlation analysis algorithm is embodied in the following formula:

[0032]

[0033] Among them, C(u i ,u j ) represents user u i and user u j Correlation between water use behaviors, U i,k is the k-th water consumption of the i-th user, P i is the average water consumption of the ith user, U j,k is the k-th water consumption of the j-th user, P j is the average water consumption of the jth user.

[0034] The user behavior correlation analysis formula can quantify the correlation between users' water use behaviors. This formula provides accurate data support for the optimization algorithm by calculating the similarity of users' water consumption, helping to identify the commonalities and differences in water use patterns. This can generate more accurate water-saving strategies, improve the accuracy and efficiency of water-saving management, and avoid resource waste.

[0035] Preferably, a multi-objective water-saving linkage optimization algorithm is further included, which is used to perform a comprehensive linkage analysis on the results of the dynamic water use efficiency optimization algorithm and the user behavior correlation analysis algorithm. The multi-objective water-saving linkage optimization algorithm includes the following steps:

[0036] S1. receiving the water use efficiency prediction result output by the dynamic water use efficiency optimization algorithm and the user behavior correlation analysis result output by the user behavior correlation analysis algorithm;

[0037] S2, based on the multi-objective optimization method, use the formula to determine the optimal water-saving strategy;

[0038] S3. Output the optimized water-saving control command to the control module.

[0039] The multi-objective water-saving linkage optimization algorithm can achieve comprehensive water-saving strategy optimization by integrating the results of the dynamic water-use efficiency optimization algorithm and the user behavior correlation analysis algorithm. This algorithm not only takes into account the water-use efficiency of individual users, but also improves the overall water-saving effect through the correlation analysis of group behavior. Its linkage analysis ensures the balance of multiple factors, helps the system make more reasonable water-use regulation decisions, and further improves the system's intelligence level and water-saving effect.

[0040] Preferably, the implementation formula of the multi-objective water-saving linkage optimization algorithm is:

[0041] O(u)=αE(u)+βC(u,U ref )

[0042] Among them, O(u) represents the water-saving optimization result of the u-th user, E(u) is the water use efficiency of the user, and C(u,U ref ) is the correlation between the water use behavior of the user and the reference user, and α and β are the optimization weight parameters.

[0043] Through the implementation of the formula, the multi-objective water-saving linkage optimization algorithm can comprehensively evaluate the water efficiency of individual users and the correlation between users, and generate the optimal water-saving strategy. The formula quantifies and weighs multi-dimensional user behaviors, effectively balancing the needs of individual users and group users, enabling the water-saving system to demonstrate efficient and flexible regulation capabilities in large-scale applications, thereby realizing a wider range of water-saving application scenarios.

[0044] A water-saving management method applicable to multiple evaluation criteria, using the water-saving management system applicable to multiple evaluation criteria;

[0045] The data acquisition module is interconnected with the data transmission module to ensure the acquisition and transmission of real-time data; the data processing module is connected with the multiple evaluation standard generation module to generate multiple water use evaluation standards by processing the original water use data, and provide input data for the optimization algorithm module; the optimization algorithm module generates water-saving strategies by analyzing the evaluation standards, and performs actual control through the control module, ultimately achieving the goal of automated water-saving management; the user feedback module interacts with the control module and the optimization algorithm module to ensure that adaptive adjustments can be made based on user feedback.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] Through the collaborative work of data collection, transmission, processing, analysis and control modules, real-time monitoring and precise management of users' water use behavior are achieved. The system can automatically collect water use data, and pre-process and analyze it through the data processing module to generate multiple evaluation criteria, thereby providing accurate data input for the optimization algorithm. By calculating and predicting water use efficiency through the optimization algorithm module, the system can dynamically adjust water-saving strategies in different scenarios, and adjust water-using equipment in real time through the control module, such as adjusting water flow and limiting water use during peak hours. This fully automated water-saving management mechanism greatly improves water use efficiency, reduces human intervention, and ensures that the system can continuously achieve water-saving goals in different water use environments.

[0048] Through the system's built-in dynamic water efficiency optimization algorithm, a personalized water-saving optimization plan can be generated based on the user's historical water use data and current water use patterns. According to the changes in water use period, water consumption and environmental factors, the system calculates the user's water-saving potential through a linear regression model and gives reasonable water-saving suggestions. This intelligent optimization algorithm not only takes into account the specific water use situation of each user, but also can flexibly adjust the water use strategy according to changes in external factors (such as temperature, etc.). Through this intelligent water-saving optimization plan, users can obtain personalized and refined water-saving management in daily water use, and achieve higher water use efficiency and economic benefits.

[0049] Through the user behavior correlation analysis algorithm, the system can identify the water use patterns of different user groups and analyze the correlation between these users' water use behaviors. The algorithm identifies user groups with similar water use behaviors through cluster analysis, and provides group water-saving suggestions based on data such as the time period and water consumption during the peak period of the group's water use pattern. This function can not only help optimize the water use strategy of individual users, but also improve the overall water use efficiency in a larger scope (such as communities and enterprises). Through the correlation analysis of group water use behaviors, the system has achieved all-round optimization from individual water saving to group water saving, further improving the wide applicability and effectiveness of the water-saving management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 The present invention is a schematic diagram of the module relationship of a water-saving management system and method applicable to multiple evaluation criteria. DETAILED DESCRIPTION

[0051] A water-saving management system applicable to multiple evaluation criteria, comprising:

[0052] Data acquisition module, data transmission module, data processing module, multiple evaluation criteria generation module, optimization algorithm module, control module and user feedback module;

[0053] The data collection module is used to collect water use data in real time from water resource use terminals. The water use data includes water consumption, water use time and water use area, and transmits the water use data to the central server through the Internet of Things sensor;

[0054] The data transmission module is used to transmit the data acquired by the data acquisition module to the data processing module in real time through the network;

[0055] The data processing module receives the raw water use data transmitted by the data transmission module, and pre-processes the raw water use data based on predefined standards, wherein the pre-processing includes data cleaning, format conversion, and detection and elimination of abnormal data, and transmits the processed data to the optimization algorithm module;

[0056] The multiple evaluation criteria generation module generates multiple evaluation criteria according to different water use scenarios and needs by analyzing the data from the data processing module;

[0057] The optimization algorithm module receives the evaluation data provided by the multiple evaluation criteria generation module, performs water efficiency optimization analysis, calculates water-saving potential and water-saving suggestions by comparing historical data with current water use patterns, and transmits the optimization results to the control module;

[0058] The control module receives the water-saving optimization result output by the optimization algorithm module, and adjusts the user's water-using equipment in real time through the automatic control system. The specific control actions include adjusting the water supply flow, limiting the water use during peak hours, and enabling or disabling the automatic equipment for a specific time period;

[0059] The user feedback module is interconnected with the control module and displays the operating status, optimization suggestions and actual water use data of the water-saving management system to the user through the human-computer interface; the user feedback module is also used to receive manual feedback and preference settings from the user and further adjust the output results of the optimization algorithm module.

[0060] Through the modular design of data collection, transmission, processing, analysis, optimization and control, all-round, real-time monitoring and automatic optimization of users' water use behavior are realized. The linkage between modules not only improves the accuracy of water use data, but also automatically generates water-saving strategies and performs equipment regulation based on multiple evaluation criteria. The user feedback module provides the system with the ability of adaptive optimization, and can continuously improve water-saving plans according to user preferences, thereby achieving significant water-saving effects, personalized regulation, and improved resource utilization.

[0061] Specifically, the optimization algorithm module includes a dynamic water use efficiency optimization algorithm, and the dynamic water use efficiency optimization algorithm includes the following steps:

[0062] S1. Collect historical water use data and pre-process it;

[0063] S2. Use linear regression model to predict water use efficiency based on water use period and efficiency index;

[0064] S3. Calculate the water-saving potential based on the water usage habits of different users and generate an optimized adjustment plan.

[0065] The dynamic water efficiency optimization algorithm can conduct in-depth learning of users' historical water use data and conduct predictive analysis based on current water use patterns. Through the linear regression model, it can accurately calculate the user's water saving potential and generate customized optimization and adjustment plans to help users achieve the best water saving effect in different water use scenarios. The algorithm improves the intelligence level of water use management and has dynamic adjustment capabilities, which can flexibly respond to water use behaviors in different time periods.

[0066] When in use, the user's water use efficiency is analyzed through historical data and real-time data, and the water use strategy is adjusted dynamically. The specific steps include:

[0067] IoT sensors are used to collect water use data from users' water use devices (such as household water meters, smart water pumps, etc.) in real time. The data includes parameters such as water consumption, water use time, and user ambient temperature. The data is transmitted to the central server via a wireless network.

[0068] The server pre-processes the collected raw data through the data processing module, performs data cleaning (such as outlier removal and data missing filling) and format conversion (such as unit unification and time series conversion), and then stores the cleaned data in the database.

[0069] By comparing real-time water use data with historical data, the system calculates the current water-saving potential. If the user's current water use efficiency is lower than the historical average, the system will give water-saving suggestions, such as reducing water use during peak hours, adjusting water supply, etc. The optimization results will be sent to the user's automated water use equipment through the control module.

[0070] IoT sensors are used to collect data in real time, and the server uses databases and linear regression models for data processing and prediction.

[0071] Specifically, the dynamic water use efficiency optimization algorithm implementation formula includes:

[0072] E(t)=a×U(t)+b×T(t)

[0073] Among them, E(t) represents the water use efficiency in period t, U(t) is the water consumption of the user in period t, T(t) is the ambient temperature in period t, and a and b are weight coefficients obtained by data regression in the algorithm.

[0074] The specific implementation of the formula can comprehensively consider external factors such as user water consumption and ambient temperature to accurately calculate water use efficiency. The introduction of this formula enables the algorithm to have the ability to make fine adjustments, dynamically optimize water use strategies based on real-time data, ensure that the optimization results of the water-saving system meet actual needs, and provide clear optimization directions to improve the operability and accuracy of the system.

[0075] The weight coefficients of the formula are trained by machine learning methods (such as the least squares method), and the system dynamically adjusts the strategy based on water use data in different time periods. The water use efficiency value E(t) calculated by the formula ultimately determines the system's regulation of user equipment, such as adjusting water flow or limiting water use during peak hours. The optimized water-saving strategy can be directly executed by smart water pumps or other automated equipment.

[0076] Specifically, the data processing module includes a user behavior correlation analysis algorithm, which is used to calculate the correlation between different water use behaviors, including the following steps:

[0077] S1, identify user groups with similar water use behaviors through clustering algorithms;

[0078] S2. Analyze the peak water usage time period of users based on the water usage patterns of user groups and calculate their correlation;

[0079] S3. Generate water-saving improvement suggestions for different users.

[0080] Specifically, the user behavior correlation analysis algorithm can identify similar user groups based on large-scale user water use behavior data, and conduct correlation analysis on the water use patterns of these groups. This can not only identify the peak water use periods of users and help optimize overall water management, but also provide targeted water-saving suggestions for specific user groups, thereby achieving more effective water-saving measures.

[0081] In specific use, the IoT sensors collect real-time water use data from different users, and send the data to the central server for preprocessing. The system uses the K-means clustering algorithm to cluster users' water use behaviors, and divides users into different groups based on parameters such as water consumption and water use time. Each group represents users with similar water use habits, such as a user group whose water use peaks in a certain period of time.

[0082] Specifically, the user behavior correlation analysis algorithm is expressed as follows:

[0083]

[0084] Among them, C(u i ,u j ) represents user u iand user u j Correlation between water use behaviors, U i,k is the k-th water consumption of the i-th user, P i is the average water consumption of the ith user, U j,k is the k-th water consumption of the j-th user, P j is the average water consumption of the jth user.

[0085] The user behavior correlation analysis formula can quantify the correlation between users' water use behaviors. This formula provides accurate data support for the optimization algorithm by calculating the similarity of users' water consumption, helping to identify the commonalities and differences in water use patterns. This can generate more accurate water-saving strategies, improve the accuracy and efficiency of water-saving management, and avoid resource waste.

[0086] The system gives group water-saving suggestions based on the user's peak water use period and correlation analysis. For example, during peak concentrated periods, it is recommended that users postpone or reduce water use, or coordinate different users in the group to use water at off-peak times to reduce resource pressure. The K-means clustering algorithm is used to cluster user water use data, and the server processes large-scale data through distributed computing. The correlation calculation is implemented through numerical computing libraries (such as NumPy) in languages ​​such as Python. The correlation value C(ui,uj) calculated by the formula is used to generate a group water-saving strategy. For example, if the correlation between two users is high, the system can recommend that they use water at off-peak times to reduce water waste, and the strategy is sent to the user device through the control module.

[0087] Specifically, it also includes a multi-objective water-saving linkage optimization algorithm, which is used to perform a comprehensive linkage analysis on the results of the dynamic water use efficiency optimization algorithm and the user behavior correlation analysis algorithm. The multi-objective water-saving linkage optimization algorithm includes the following steps:

[0088] S1. receiving the water use efficiency prediction result output by the dynamic water use efficiency optimization algorithm and the user behavior correlation analysis result output by the user behavior correlation analysis algorithm;

[0089] S2, based on the multi-objective optimization method, use the formula to determine the optimal water-saving strategy;

[0090] S3. Output the optimized water-saving control command to the control module.

[0091] The multi-objective water-saving linkage optimization algorithm can achieve comprehensive water-saving strategy optimization by integrating the results of the dynamic water-use efficiency optimization algorithm and the user behavior correlation analysis algorithm. This algorithm not only takes into account the water-use efficiency of individual users, but also improves the overall water-saving effect through the correlation analysis of group behavior. Its linkage analysis ensures the balance of multiple factors, helps the system make more reasonable water-use regulation decisions, and further improves the system's intelligence level and water-saving effect.

[0092] Specifically, the implementation formula of the multi-objective water-saving linkage optimization algorithm is:

[0093] O(u)=αE(u)+βC(u,U ref )

[0094] Among them, O(u) represents the water-saving optimization result of the u-th user, E(u) is the water use efficiency of the user, and C(u,U ref ) is the correlation between the water use behavior of the user and the reference user, and α and β are the optimization weight parameters.

[0095] Through the implementation of the formula, the multi-objective water-saving linkage optimization algorithm can comprehensively evaluate the water efficiency of individual users and the correlation between users, and generate the optimal water-saving strategy. The formula quantifies and weighs multi-dimensional user behaviors, effectively balancing the needs of individual users and group users, enabling the water-saving system to demonstrate efficient and flexible regulation capabilities in large-scale applications, thereby realizing a wider range of water-saving application scenarios.

[0096] The system uses a multi-objective optimization algorithm (such as Pareto optimality) to optimize the weight coefficients α and β. The algorithm processes large-scale user data through parallel computing of the server.

[0097] The calculation of the formula is implemented by an optimization solver (such as the optimize function in SciPy).

[0098] Practical application: The calculated O(u) value reflects the user's water-saving potential and behavior relevance. A higher O(u) value means that the user has a larger space for water saving, and the system will generate a stricter water-saving strategy for the user, such as delaying water supply or limiting water consumption. The optimization strategy directly affects the operation of the user's equipment and ensures the implementation of water-saving effects.

[0099] A water-saving management method applicable to multiple evaluation criteria, using the water-saving management system applicable to multiple evaluation criteria;

[0100] The data acquisition module is interconnected with the data transmission module to ensure the acquisition and transmission of real-time data; the data processing module is connected with the multiple evaluation standard generation module to generate multiple water use evaluation standards by processing the original water use data, and provide input data for the optimization algorithm module; the optimization algorithm module generates water-saving strategies by analyzing the evaluation standards, and performs actual control through the control module, ultimately achieving the goal of automated water-saving management; the user feedback module interacts with the control module and the optimization algorithm module to ensure that adaptive adjustments can be made based on user feedback.

Claims

1. A water-saving management system applicable to multiple evaluation criteria, characterized in that: include: Data acquisition module, data transmission module, data processing module, multiple evaluation criteria generation module, optimization algorithm module, control module and user feedback module; The data collection module is used to collect water use data in real time from water resource use terminals. The water use data includes water consumption, water use time and water use area, and transmits the water use data to the central server through the Internet of Things sensor; The data transmission module is used to transmit the data acquired by the data acquisition module to the data processing module in real time through the network; The data processing module receives the raw water use data transmitted by the data transmission module, and pre-processes the raw water use data based on predefined standards, wherein the pre-processing includes data cleaning, format conversion, and detection and elimination of abnormal data, and transmits the processed data to the optimization algorithm module; The multiple evaluation criteria generation module generates multiple evaluation criteria according to different water use scenarios and needs by analyzing the data from the data processing module; The optimization algorithm module receives the evaluation data provided by the multiple evaluation criteria generation module, performs water efficiency optimization analysis, calculates water-saving potential and water-saving suggestions by comparing historical data with current water use patterns, and transmits the optimization results to the control module; The control module receives the water-saving optimization result output by the optimization algorithm module, and adjusts the user's water-using equipment in real time through the automatic control system. The specific control actions include adjusting the water supply flow, limiting the water use during peak hours, and enabling or disabling the automatic equipment for a specific time period; The user feedback module is interconnected with the control module and displays the operating status, optimization suggestions and actual water use data of the water-saving management system to the user through the human-computer interface; the user feedback module is also used to receive manual feedback and preference settings from the user and further adjust the output results of the optimization algorithm module.

2. A water-saving management system and method applicable to multiple evaluation criteria according to claim 1, characterized in that: The optimization algorithm module includes a dynamic water use efficiency optimization algorithm, and the dynamic water use efficiency optimization algorithm includes the following steps: S1. Collect historical water use data and pre-process it; S2. Use linear regression model to predict water use efficiency based on water use period and efficiency index; S3. Calculate the water-saving potential based on the water usage habits of different users and generate an optimized adjustment plan.

3. A water-saving management system and method applicable to multiple evaluation criteria according to claim 2, characterized in that: The dynamic water use efficiency optimization algorithm implementation formula includes: E(t)=a×U(t)+b×T(t) Among them, E(t) represents the water use efficiency in period t, U(t) is the water consumption of the user in period t, T(t) is the ambient temperature in period t, and a and b are weight coefficients obtained by data regression in the algorithm.

4. A water-saving management system and method applicable to multiple evaluation criteria according to claim 3, characterized in that: The data processing module includes a user behavior correlation analysis algorithm, which is used to calculate the correlation between different water use behaviors, including the following steps: S1, identify user groups with similar water use behaviors through clustering algorithms; S2. Analyze the peak water usage time period of users based on the water usage patterns of user groups and calculate their correlation; S3. Generate water-saving improvement suggestions for different users.

5. A water-saving management system and method applicable to multiple evaluation criteria according to claim 4, characterized in that: The formula for the user behavior correlation analysis algorithm is: Among them, C(u i ,u j ) represents user u i and user u j Correlation between water use behaviors, U i,k is the k-th water consumption of the i-th user, P i is the average water consumption of the ith user, U j,k is the k-th water consumption of the j-th user, P j is the average water consumption of the jth user.

6. A water-saving management system and method applicable to multiple evaluation criteria according to claim 5, characterized in that: It also includes a multi-objective water-saving linkage optimization algorithm for performing a comprehensive linkage analysis on the results of the dynamic water use efficiency optimization algorithm and the user behavior correlation analysis algorithm. The multi-objective water-saving linkage optimization algorithm includes the following steps: S1. receiving the water use efficiency prediction result output by the dynamic water use efficiency optimization algorithm and the user behavior correlation analysis result output by the user behavior correlation analysis algorithm; S2, based on the multi-objective optimization method, use formula 3 to determine the optimal water-saving strategy; S3. Output the optimized water-saving control command to the control module.

7. A water-saving management system and method applicable to multiple evaluation criteria according to claim 6, characterized in that: The implementation formula of the multi-objective water-saving linkage optimization algorithm is: O(u)=αE(u)+βC(u,U ref ) Among them, O(u) represents the water-saving optimization result of the u-th user, E(u) is the water use efficiency of the user, and C(u,U ref ) is the correlation between the water use behavior of the user and the reference user, and α and β are the optimization weight parameters.

8. A water-saving management method applicable to multiple evaluation criteria, characterized in that: Using a water-saving management system applicable to multiple evaluation criteria as described in any one of claims 1 to 7; The data acquisition module is interconnected with the data transmission module to ensure the acquisition and transmission of real-time data; the data processing module is connected with the multiple evaluation standard generation module to generate multiple water use evaluation standards by processing the original water use data, and provide input data for the optimization algorithm module; the optimization algorithm module generates water-saving strategies by analyzing the evaluation standards, and performs actual control through the control module, ultimately achieving the goal of automated water-saving management; the user feedback module interacts with the control module and the optimization algorithm module to ensure that adaptive adjustments can be made based on user feedback.

Images