Closestool intelligent water flow control method and system

Abstract

The invention relates to the technical field of intelligent water saving, in particular to a closestool intelligent water flow control method and system.The closestool intelligent water flow control method comprises the following steps that recombined water flow data is input based on the defecation behavior of a user, the relation between water use characteristics and water pressure is analyzed to recognize an abnormal interval, key nodes are extracted, offset is recognized, and a propagation track is extracted; and water pressure trend superposition water-saving efficiency is identified, and a water consumption behavior linkage response control instruction set is output. According to the method, dynamic matching and self-adaptive regulation and control of the water demand are achieved by analyzing the defecation behavior and the water pressure characteristics of the user, the flushing amount is automatically adjusted along with the water pressure and the use characteristics, waste caused by the fixed water amount is avoided, the abnormal water using interval is accurately positioned by recognizing the water pressure deviation direction and the propagation track, and the water using efficiency is improved. A linkage signal is generated according to the water pressure change to promote the water consumption units to perform cooperative adjustment, the water distribution balance degree and the water-saving efficiency are improved, the cleaning effect and the water-saving target are considered in the flushing process, and an intelligent dynamic management system is formed.

Description

Technical Field

[0001] This invention relates to the field of intelligent water-saving technology, and in particular to an intelligent water flow control method and system for toilets. Background Technology

[0002] The field of intelligent water-saving technology involves the efficient utilization and management of water resources in domestic and industrial water use processes. Core aspects include research and application of water flow monitoring, water pressure regulation, water allocation, water usage behavior recognition, and water-saving control strategies. This technology uses sensor detection and automatic control to manage flow and duration in different water usage scenarios, thereby reducing water waste while ensuring functionality. Traditional intelligent water flow control methods for toilets rely on setting a fixed flush volume or using a mechanical dual-flush structure. These methods adjust the inlet and outlet water times using float valves or mechanical buttons, completing the flushing operation with manually set quantitative drainage. They cannot automatically adjust the flush volume based on user behavior or real-time water pressure changes, often resulting in water volume mismatches in different usage scenarios.

[0003] Traditional toilet water control relies on mechanical structures to achieve fixed drainage, which cannot recognize differences in user toilet behavior or real-time water pressure fluctuations. In cases of unstable water pressure or changes in user habits, problems such as insufficient flushing or excessive drainage often occur, leading to a decrease in water resource utilization. This method still executes a set quantitative discharge when facing different seasons and changes in pipe network pressure, lacking dynamic adjustment capabilities. Moreover, the mechanical control has a lag in response to flow fluctuations, causing an imbalance between water flow distribution and flushing demand. When the water pressure is too low, incomplete flushing may occur, while when the water pressure is too high, water is wasted, making it difficult to achieve a balance between functionality and water conservation. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and to propose a smart water flow control method and system for toilets.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a smart water flow control method for a toilet, comprising the following steps: S1: Based on the initial input of user toilet behavior, the data from different sources in the toilet smart water flow control model are restructured and combined with time labels and spatial identifiers to generate a water demand benchmark parameter set; S2: Based on the water demand benchmark parameter set, analyze the correlation between water use behavior characteristics and water pressure distribution, identify the abnormal water use fluctuation interval data set and water pressure deviation range, filter water use units that exceed the preset threshold, and remove related interference data to generate a water use anomaly diagnosis dataset. S3: Based on the water use anomaly diagnosis dataset, extract water use distribution status and water pressure change values, identify key water use nodes and water pressure combinations, screen water use units that conform to known water use patterns, and overlay location codes to mark the corresponding areas to generate water use behavior distribution results; S4: Based on the continuous change information between multiple time periods in the water use behavior distribution results, identify the water use offset of adjacent areas in the time period, extract the offset direction and propagation trajectory, filter out the area segments with the same continuous offset direction, and obtain the water use dynamic tracking and control path segment.

[0006] As a further embodiment of the present invention, the water demand benchmark parameter set includes a water distribution feature value set, a water pressure attribute grid, and a spatial operation parameter surface; the water anomaly diagnosis dataset includes water fluctuation identification results, water pressure deviation markers, and interference data removal masks; the water behavior distribution results include a target water candidate set, key node response templates, and regional location codes; and the water dynamic tracking and control path segment includes a continuous offset trend trajectory, a path direction vector set, and regional offset nodes.

[0007] As a further aspect of the present invention, the step of obtaining the water demand benchmark parameter set specifically includes: S111: Based on the initial input of the user's toilet behavior, collect data from different sources in the toilet intelligent water flow control model, combine time tags to perform frame sequence matching, remove water use units in the water use distribution sequence whose difference between adjacent frames exceeds the fluctuation critical threshold, and generate a multi-dimensional water use matrix. S112: Based on the multidimensional water use matrix, extract water pressure intensity and water use distribution data under the same time and space identifier, filter out records with missing items, and generate effective water use operation factor data group; S113: Call the effective water use operation factor data group, identify the standard deviation of water pressure intensity in water use unit groups with consistent water use operation modes and normalize it, calculate the normalized water use difference intensity value, reclassify water use units in the region, and establish a water demand benchmark parameter set.

[0008] As a further aspect of the present invention, the step of obtaining the water usage anomaly diagnostic dataset specifically comprises: S211: Based on the water demand benchmark parameter set, extract the water distribution status and water pressure data in the layer, match and compare the fluctuation value of water unit with the water pressure range, analyze the corresponding relationship, and obtain the water fluctuation range data set. S212: Call the water usage fluctuation range data set, combine it with the distribution status of water usage units in the evaluation layer, determine whether it falls into the specified range, identify the difference in water usage units that are not in the range, determine the objects to be removed based on the difference, and obtain a list of removed water usage unit numbers. S213: Call the list of water-using units to be removed, delete the interfering data associated with the corresponding numbers in the evaluation layer, reorganize the spatial distribution of the remaining water-using units, and generate a water-using anomaly diagnostic dataset.

[0009] As a further aspect of the present invention, the step of obtaining the water use behavior distribution results specifically includes: S311: Based on the water use anomaly diagnosis dataset, extract the distribution status and water pressure change value of the water use units in the layer, combine the differentiated water use nodes with the corresponding water pressure data, identify typical water use pattern areas, and obtain the water use pattern representation combination. S312: Call the water use pattern characterization combination, detect the fluctuation difference of water use units and the degree of coordinated change of water pressure in the combination area, aggregate and compare the response values ​​of water use units at key nodes, identify the area of ​​water use behavior potential, and obtain the water use impact sensitive area index set. S313: Call the water use impact sensitive area index set, match the water use units and water use pattern templates in the sensitive area, filter the water use units that meet the feature requirements, and mark the location code information of the corresponding area to generate water use behavior distribution results.

[0010] As a further aspect of the present invention, the step of obtaining the water dynamic tracking and control path segment specifically includes: S411: Based on the water use behavior distribution results, extract continuous change information between multiple time periods in the map, identify the geometric center offset of adjacent areas in the time series, extract the offset direction vector and displacement length, analyze the angle difference of the consistency of offset direction between adjacent areas, and obtain continuous water use offset direction data. S412: Call the continuous offset direction data of water usage, and based on the changing trend of the angle difference, use the formula: ; Calculate the angular fluctuation dispersion value, extract the region segment with stable offset direction, filter the continuous segment with angular change below the preset threshold, and obtain stable offset segment information; in, Represents the angular fluctuation dispersion value. Representing the The offset angle at time, This represents the mean of the offset angle. Represents the number of sampling times. For the increment of angle change, The weighting coefficient for the angle change; S413: Call the stable offset segment information, combine the offset direction angle in each segment, the water distribution intensity between regions and the time series continuity index, identify the trajectory segments with strong continuity and concentrated water use signals, and obtain the water use dynamic tracking and control path segments.

[0011] As a further aspect of the present invention, the method further includes step S5: S5: Based on the water usage dynamic tracking and control path segment, identify the water pressure change trend and water usage level, overlay a water-saving efficiency layer, compare the time synchronization change characteristics of water pressure, identify the segment coordinates and overlapping positions of water usage distribution where a turning point occurs simultaneously, and output a water usage behavior linkage response control instruction set. The water use behavior linkage response control instruction set includes water pressure linkage change zone, water use response intersection point, and abnormal behavior indicator group.

[0012] As a further aspect of the present invention, the step of obtaining the water use behavior linkage response control instruction set specifically includes: S511: Based on the water usage dynamic tracking and control path segment, extract the water pressure change trend and water usage level in the segment, identify the daily water pressure change value and daily average water usage value of the segment, analyze the water pressure change amplitude and water usage fluctuation degree, and generate a synchronous water pressure change characteristic value group. S512: Call the synchronous water pressure change feature value group, and based on the water-saving efficiency layer grid efficiency sequence, combine the water pressure change amplitude, water usage fluctuation degree and water-saving efficiency to extract the turning point of the continuous time period, filter the segment number of the turning feature and summarize it to obtain the sudden change synchronous segment index list. S513: Based on the mutation synchronization section index list, match the water distribution layer coordinate units corresponding to the section number, filter overlapping grids with the same index and mark them, and output the water use behavior linkage response control instruction set.

[0013] The intelligent water flow control system for the toilet is used to execute the aforementioned intelligent water flow control method for the toilet. The system includes: The water demand benchmark construction module collects data from different sources in the intelligent water flow control model of the toilet, extracts water operation data, and formats the water data and water pressure factor in combination with time and space identifiers to generate a water demand benchmark parameter set. The water usage anomaly detection module, based on the water demand baseline parameter set, filters water usage units that exceed a preset threshold according to water usage distribution status and water pressure data, removes interfering data associated with anomalies, integrates the remaining water usage distribution status and operation information, marks abnormal areas, and generates a water usage anomaly diagnostic dataset. Based on the water use anomaly diagnosis dataset, the water use behavior extraction module extracts water use distribution status, water pressure change value, and water use intensity, identifies water use units that conform to the water use pattern, matches water use behavior templates, overlays location codes and time labels, performs spatial positioning, and generates water use behavior distribution results. Based on the water use behavior distribution results, the water use path tracking module extracts time tags and water use operation information, identifies the spatial distance between water use behavior areas in adjacent time periods, determines the offset direction and continuous trajectory, integrates path segments with consistent offset directions, and obtains water use dynamic tracking and control path segments. The water use linkage analysis module, based on the water use dynamic tracking and control path segment, compares the time series according to the water pressure change trend, water use level and water saving efficiency of the path segment, identifies the synchronous turning point, locates the overlapping position of the turning area and water use behavior, and outputs the water use behavior linkage response control instruction set.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In this invention, by analyzing the correlation between user toilet behavior and water pressure characteristics, dynamic matching and adaptive control of water demand parameters are achieved. This allows the flushing volume under different water usage scenarios to be automatically adjusted according to real-time changes in water pressure and usage characteristics, thereby avoiding the waste caused by fixed water volume settings. In continuous monitoring over multiple time periods, the direction and trajectory of water pressure deviation are identified to accurately identify and track abnormal water usage zones. Based on the trend of water pressure changes between areas, a linkage response signal is generated to promote coordinated adjustment of each water-using unit, achieving a balanced distribution of overall water volume and improved water-saving efficiency. This allows the flushing process to reduce unnecessary water consumption while meeting cleaning requirements, achieving a comprehensive effect of intelligent management and dynamic water saving. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the workflow of the present invention; Figure 2 This is a flowchart illustrating the process of obtaining the water demand baseline parameter set in this invention. Figure 3 This is a flowchart illustrating the process of obtaining the water anomaly diagnostic dataset in this invention. Figure 4 This is a flowchart illustrating the process of obtaining the water behavior distribution results in this invention. Figure 5 This is a flowchart illustrating the process of obtaining the path segment for dynamic water tracking and control in this invention. Figure 6 This is a flowchart illustrating the acquisition of the water behavior linkage response control instruction set in this invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0017] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0018] Example 1 Please see Figure 1 This invention provides a technical solution: a method for intelligent water flow control in a toilet, comprising the following steps: S1: Based on the initial input of user toilet behavior, the data from different sources in the toilet smart water flow control model are restructured and combined with time labels and spatial identifiers to generate a water demand benchmark parameter set; S2: Based on the water demand baseline parameter set, analyze the correlation between water use behavior characteristics and water pressure distribution, identify the abnormal water use fluctuation range data set and water pressure deviation range, filter water use units that exceed the preset threshold, remove related interference data, and generate a water use anomaly diagnosis dataset. S3: Based on the water use anomaly diagnosis dataset, extract water use distribution status and water pressure change values, identify key water use nodes and water pressure combinations, screen water use units that conform to known water use patterns, and overlay location codes to mark the corresponding areas to generate water use behavior distribution results; S4: Based on the continuous change information between multiple time periods in the water use behavior distribution results, identify the water use offset in adjacent areas of time periods, extract the offset direction and propagation trajectory, filter out the area segments with the same continuous offset direction, and obtain the water use dynamic tracking and control path segments. "Tracking" refers to the dynamic detection and pattern recognition of the distribution, intensity, and potential trend changes of toilet water use behavior over different time periods. This includes identifying the geometric center offset of adjacent areas, extracting the offset direction vector and displacement length, and analyzing directional consistency to determine stable regional segments. Finally, by combining the offset direction angle, water distribution intensity between areas, and time series continuity index, the system can identify trajectory segments with strong continuity and concentrated water use signals. These steps together construct a real-time, space-time integrated water use pattern evolution trajectory, meaning the system can "track" how water use behavior shifts from one area to another, or how it accumulates, diffuses, and changes within a specific area, thus revealing the spatiotemporal continuity and changing patterns of water use behavior. "Regulation" follows the "tracking" function, utilizing the tracking results to achieve its purpose. According to this method, based on the dynamic tracking and regulation path segments of water usage, the trend of water pressure changes and water usage levels are identified, a water-saving efficiency layer is overlaid, and finally, a set of water usage behavior linkage response control instructions is output. This means that "dynamic tracking and regulation path segments" serve as important inputs and foundations, providing a decision-making basis for subsequent intelligent and precise water volume control of the toilet. Through the analysis of path segments, key areas and time nodes requiring water pressure adjustment or water volume allocation optimization can be identified. For example, if the water usage signal in a certain area is found to continuously increase and form a clear path within a certain period, the water pressure in that area can be adjusted in advance or in real time, or the water supply strategy can be optimized to achieve water conservation, avoid resource waste, or cope with peak water usage. Therefore, "regulation" is an intelligent and forward-looking water flow management action based on a deep understanding of water usage dynamics. "Water usage dynamic tracking and control path segment" represents a dataset that integrates spatiotemporal dynamic information. It records in detail the continuous change trend, deviation direction and intensity of users' toilet water usage behavior in time and space. Its core function is to provide high-precision and dynamic decision-making basis for the intelligent toilet water flow control system. At the "tracking" level, it can visualize and quantify the spatiotemporal evolution of water usage patterns, helping the system understand the "trajectory" of users' water usage habits.

[0019] S5: Based on the dynamic tracking and control path segments of water use, identify the trend of water pressure change and water use level, overlay a water-saving efficiency layer, compare the time synchronization change characteristics of water pressure, identify the coordinates of segments that change at the same time and the overlapping positions of water use distribution, and output a set of linkage response control instructions for water use behavior.

[0020] The water demand baseline parameter set includes a water distribution feature value set, a water pressure attribute grid, and a spatial operation parameter surface. The water anomaly diagnosis dataset includes water fluctuation identification results, water pressure deviation markers, and interference data removal masks. The water behavior distribution results include a target water candidate set, key node response templates, and regional location codes. The water dynamic tracking and control path segments include continuous offset trend trajectories, path direction vector sets, and regional offset nodes. The water behavior linkage response control instruction set includes water pressure linkage change zones, water response intersection points, and abnormal behavior indicator groups.

[0021] Please see Figure 2 The specific steps for obtaining the water demand baseline parameter set are as follows: S111: Based on the initial input of the user's toilet behavior, collect data from different sources in the toilet intelligent water flow control model, combine time tags to perform frame sequence matching, remove water use units in the water use distribution sequence whose difference between adjacent frames exceeds the fluctuation critical threshold, and generate a multi-dimensional water use matrix. Based on the initial input of user toilet behavior in the intelligent toilet water flow control model, such as the time and duration of the user pressing the flush button, differentiated data recorded by sensors inside the toilet are collected. This data includes the water inlet flow rate of the toilet tank, the instantaneous flow velocity in the pipes, and the pressure value recorded by the water pressure sensor. All data is timestamped. Frame sequence matching is performed based on the timestamps to ensure that the flow rate, velocity, and pressure data are synchronized within the same time frame. For example, in a flushing operation, starting from t=0 seconds, flow rate, velocity, and pressure data are collected every 0.1 seconds to generate a continuous data sequence. The system then iterates through adjacent frames in the water usage distribution sequence, calculating the water pressure difference or flow rate difference between each two frames. For example, at t=1.0 seconds, the water pressure is 0.25 MPa, and at t=1.1 seconds, the water pressure is 0.15 MPa, with a difference of 0.10 MPa. The critical threshold for water pressure fluctuation is set to 0.08 MPa, and the critical threshold for flow rate fluctuation is set to 1.5 L / min. When the calculated difference exceeds the critical threshold for fluctuation, for example, 0.10 MPa > 0.08 MPa, the water usage unit is determined to be abnormally fluctuating and is removed from the sequence. For example, if the water pressure drops sharply within 0.1 seconds and exceeds the threshold, the data for that 0.1 second is removed. Through this process, a multi-dimensional water usage matrix reflecting the actual water usage pattern is generated. The matrix contains standardized water usage parameters such as flow rate, velocity, water pressure, and flushing duration for each valid time frame.

[0022] S112: Based on the multidimensional water use matrix, extract water pressure intensity and water use distribution data under the same time and space identifier, filter out records with missing items, and generate effective water use operation factor data set; Based on the multi-dimensional water usage matrix, water pressure intensity data and water usage distribution data are extracted for each time and space identifier. The time identifier is accurate to the second, and the space identifier corresponds to the location of the toilet sensor inside the toilet. For example, at the 5th second of a specific flushing operation, the water pressure intensity is read as 0.28 MPa from the main inlet pipe pressure sensor, and at the same time, the water usage distribution data of 3.5 L / min is obtained from the flush outlet flow meter. The extracted data is screened for integrity, and all missing records are identified and removed. For example, if the water pressure data exists at a certain time point but the flow data is empty, the record is determined to be a missing item and is filtered out. The data integrity judgment standard is that all preset parameters (water pressure, flow rate, flow velocity, flushing duration) in the record must exist and be non-zero. For example, in the record at t=10 seconds, the water pressure value is 0.27 MPa, but the flushing duration data is missing, so the record is filtered out. Finally, an effective water usage operation factor data group is generated, consisting of water pressure intensity data and water usage distribution data with integrity verification. Each item in this data group reflects the complete water usage status of the smart toilet at a specific time and space.

[0023] S113: Call the effective water use operation factor data set, identify the standard deviation of water pressure intensity in water use unit groups with consistent water use operation modes, and normalize it using the following formula: ; Calculate the normalized water use difference intensity value, reclassify water use units in the region, and establish a water demand benchmark parameter set; in, This represents the normalized intensity of water use differences. This represents the standard deviation of the water pressure intensity values ​​in the first water unit group. This represents the average water pressure intensity value of the first water unit group. This represents the standard deviation of the water pressure intensity value of the j-th water unit group. represents the mean water pressure intensity value of the j-th water unit group, and n represents the total number of water unit groups; The effective water use operation factor data set is invoked. First, groups of water-using units with consistent water use operation patterns are identified. For example, all water-using units operating under the "standard flushing" mode are grouped together, and all water-using units operating under the "water-saving flushing" mode are grouped together. For each water-using unit group, the standard deviation of the water pressure intensity values ​​is calculated. For example, if there are N water-using units in the "standard flushing" mode group, their water pressure intensities are... Then calculate the average water pressure of the group. And calculate its standard deviation. Next, the standard deviation is normalized using an inline LaTeX formula. Calculate the normalized water use difference intensity value, where, This represents the normalized intensity of water use variation, which measures the relative difference in water pressure fluctuation characteristics between a specific water unit group and the overall water pressure fluctuation characteristics of all water unit groups. Represents the total number of water unit groups, for example, the total number identified in a certain area. The water use patterns are divided into three water use unit groups: standard flushing group (group 1), water-saving flushing group (group 2), and nighttime flushing group (group 3). The standard deviation and mean of the water pressure intensity for each group are assumed to be as follows: Group 1 (Standard Flushing Set): , ; Group 2 (Water-saving flushing group): , ; Group 3 (Nighttime Flushing Group): , ; formula The calculation logic is as follows: First, for each water unit group... Calculate its standard deviation of water pressure strength. with the mean absolute difference between The operation aims to quantify the degree to which the water pressure fluctuations of a group deviate from its average level, reflecting the internal consistency of the group's water use patterns. A larger absolute difference indicates a greater deviation between the water pressure fluctuations and the average level within the group. Secondly, calculations are performed for all water unit groups. The square root of the sum, with the denominator representing the overall dispersion of water pressure fluctuation characteristics across all water unit groups, provides a comprehensive benchmark for comparing differences between individual water unit groups. The denominator, by taking the square root of the sum of squares, effectively avoids cancellation of positive and negative values ​​and ensures dimensional consistency of the results, thus defining the specific water unit group... Divide by the overall dispersion to obtain the normalized result. Value, this The value quantifies the degree of deviation of the water pressure fluctuation characteristics of the first water unit group from the overall fluctuation characteristics of all water unit groups, and realizes a standardized comparison of the differences in water pressure fluctuations between different water unit groups. Calculate the normalized water use difference intensity value for group 1 : ; The advantage of this formula lies in its ability to effectively assess and quantify the relative differences in water pressure fluctuation characteristics among various water-using units by calculating the absolute difference between the standard deviation and the mean of water pressure intensity in a single water unit group and normalizing it with the overall dispersion of all water unit groups. This allows for the objective identification of water use pattern groups with abnormal or unique water pressure fluctuation characteristics, providing a precise quantitative basis for subsequent regional reclassification. This result... This indicates that the water pressure fluctuation characteristics of the standard flushing group have a difference intensity of 0.663 relative to the overall fluctuation of all water usage patterns, based on the calculated normalized water usage difference intensity value. Reclassify all water-using units within the region, for example, by setting... Water use units with a value higher than 0.6 are classified as "high-fluctuation water use mode". Values ​​between 0.3 and 0.6 are classified as "medium-fluctuation water use pattern". Values ​​below 0.3 are classified as "low-fluctuation water use pattern". In this way, a set of water demand benchmark parameters that accurately reflects the characteristics of water use units in the region is established.

[0024] Please see Figure 3 The specific steps for obtaining the water anomaly diagnosis dataset are as follows: S211: Based on the water demand baseline parameter set, extract the water distribution status and water pressure data in the layer, match and compare the fluctuation value of water use unit with the water pressure range, analyze the corresponding relationship, and obtain the water fluctuation range data set. Based on a baseline set of water demand parameters, water distribution data and corresponding water pressure data for each water-using unit are extracted from the digital geographic information layer. For example, for toilet M1 in area A, the instantaneous flow rate at the flush outlet under normal flushing mode is extracted to be 3.8 L / min, and the pipe water pressure is 0.26 MPa. Then, the fluctuation values ​​of the water-using unit are matched and compared with the water pressure range. For example, typical water fluctuation ranges and water pressure ranges for different water-using modes (such as standard flushing and water-saving flushing) are preset. For the standard flushing mode, the water fluctuation range is defined as 3.5-4.5 L / min, and the water pressure... The range is 0.25-0.30 MPa. The flow rate of toilet M1 (3.8 L / min) and water pressure (0.26 MPa) are compared with the preset range of the standard flushing mode. If both the flow rate and water pressure of M1 fall within the preset range, it is considered to meet the characteristics of the mode. Through comparative analysis, the water consumption fluctuation range of each water-using unit is determined. For example, if the water consumption fluctuation value of toilet M1 is concentrated between 3.7 L / min and 3.9 L / min in multiple time periods, and the water pressure is stable between 0.255 MPa and 0.265 MPa, this is defined as the specific water consumption fluctuation range data set of toilet M1.

[0025] S212: Call the water usage fluctuation range data set, combine it with the distribution status of water usage units in the evaluation layer, determine whether it falls into the specified range, identify the difference of water usage units that are not in the range, determine the objects to be removed based on the difference, and obtain a list of removed water usage unit numbers. The system retrieves a data set of water usage fluctuation ranges and monitors a flush of toilet M1 at 9:00 AM with a flow rate of 3.2 L / min and a water pressure of 0.24 MPa. It then determines whether the real-time water usage data falls within a defined water usage fluctuation range. For example, if the water usage fluctuation range for toilet M1 is set to a flow rate of 3.5-4.5 L / min and a water pressure of 0.25-0.30 MPa, the monitored flow rate of 3.2 L / min and water pressure of 0.24 MPa do not fall within the specified range. Therefore, it is determined that toilet M1's water usage behavior is not within the specified range. Subsequently, the system calculates the difference in water usage between units outside the range, such as the flow rate difference. (Take the lower limit of the interval), water pressure difference (Taking the lower limit of the interval), set the threshold for judging and removing differences: the difference in flow rate exceeds 0.2L / min, or the difference in water pressure exceeds 0.005MPa. Based on this, 0.3L / min > 0.2L / min and 0.01MPa > 0.005MPa, toilet M1 is judged to be a water-using unit with significant differences. According to the difference, toilet M1 is judged to be removed and its number "Toilet_M1_ID" is recorded. This process is continued until all water-using units in the evaluation layer are traversed and a list of removed water-using unit numbers is obtained. For example, the list is ["Toilet_M1_ID", "Toilet_M5_ID", "Toilet_M12_ID"].

[0026] S213: Call the list of water-using unit numbers to be removed, delete the interfering data associated with the corresponding numbers in the evaluation layer, reorganize the spatial distribution of the remaining water-using units, and generate a water-using anomaly diagnostic dataset. The system retrieves a list of excluded water-using unit numbers, for example, a list containing [“Toilet_M1_ID”, “Toilet_M5_ID”, “Toilet_M12_ID”]. In the evaluation layer, it locates and removes all interfering data associated with these numbers. For example, for “Toilet_M1_ID”, it removes all real-time monitoring data records identified as abnormal, such as flow rate and water pressure, as well as the timestamps and spatial coordinates associated with the abnormal data. This ensures that all excluded water-using unit data no longer affects subsequent analysis. After removing interfering data, the spatial distribution of the remaining water-using units (i.e., operational water-using units) in the evaluation layer is reorganized. For example, if Toilet_M1 is located in the center of the area, its data is removed, and the spatial distribution map of the regional water-using units is updated to no longer contain Toilet_M1 information. By recalculating the relative positions, density distributions, and spatial topological relationships of the remaining water-using units, an accurate, interference-free, and spatially distributed water-using anomaly diagnostic dataset is generated. This dataset contains only water-using unit data that conforms to the water-using pattern and has complete spatial location information, providing a data foundation for subsequent water-using pattern identification.

[0027] Please see Figure 4 The specific steps for obtaining the water behavior distribution results are as follows: S311: Based on the water use anomaly diagnosis dataset, extract the distribution status and water pressure change value of water use units in the layer, combine the differentiated water use nodes with the corresponding water pressure data, identify typical water use pattern areas, and obtain the combination of water use pattern representations. Based on the water usage anomaly diagnosis dataset, the distribution status and corresponding water pressure variation values ​​of each water usage unit are extracted from the digital geographic information layer. For example, toilet M2 located in region A is shown as a fixed installation point, with an average water pressure variation of 0.015 MPa over the past 24 hours. Combining the identified differentiated water usage node data with the corresponding real-time water pressure data, nodes represent internal toilet flush valves, water supply valves, etc. For example, a flush valve opening record is a differentiated water usage node with a water pressure of 0.28 MPa, while a water supply valve opening results in a water pressure of 0.25 MPa. Through comprehensive analysis of the information, typical water usage patterns within the region are identified. For example, based on the frequency, duration, and water pressure variation characteristics of flush valve opening, a "high-frequency standard flushing area" or a "low-frequency water-saving flushing area" can be identified. If most toilet flush valves in a certain area open more than 3 times per hour during the morning peak period (7:00-9:00), and each flush lasts for 5-7 seconds with water pressure fluctuations between 0.02-0.03 MPa, it is marked as a "high-frequency standard flushing area". Through this identification process, a combination of water use pattern characteristics is obtained, including area identification, typical water use pattern type, and its key parameters (such as flush frequency, duration, and water pressure variation range).

[0028] S312: Call the water use pattern characterization combination, detect the fluctuation difference of water use units and the degree of coordinated change of water pressure in the combined area, aggregate and compare the response values ​​of water use units at key nodes, identify the areas with water use behavior potential, and obtain the index set of water use impact sensitive areas. The system utilizes water usage pattern characterization combinations, such as "high-frequency standard flushing zones" and "low-frequency water-saving flushing zones." Fluctuation differences and water pressure coordination changes are detected among water-using units within these zones. For example, in the "high-frequency standard flushing zone," the system checks whether the fluctuating flow rate of all water-using units remains within the range of 3.5 L / min ± 0.5 L / min. Simultaneously, it analyzes whether the water pressure synchronously decreases by approximately 0.02 MPa during each flush and quickly recovers after refilling. The degree of coordinated water pressure change is assessed by calculating the correlation coefficient of water pressure changes across all water-using units in the zone during the same flushing event. A correlation coefficient higher than 0.8 is considered high coordination. The system also aggregates and compares the response values ​​of water-using units at key points (such as the opening and closing of the flush valve). For example, it collects water pressure data from all toilets in the zone at the moment the flush valve opens. Pressure drop values ​​are calculated, and their average and dispersion are determined. Average pressure drop values ​​between 0.02 and 0.03 MPa with a dispersion less than 0.005 MPa are considered consistent responses. Through comprehensive analysis, potential water use behavior areas are identified. For example, if a water use unit in a region exhibits high synergistic water pressure changes and low fluctuation differences, it indicates that the water use behavior pattern in that region is stable and predictable, and is marked as a "high water use behavior potential area." Finally, a set of water use impact sensitive area indicators is obtained, including regional identifiers, water use behavior potential levels, and relevant quantitative indicators. For example, this indicator set is {Region A: {Potential Level: High, Water Pressure Synergistic Coefficient: 0.85, Flow Fluctuation Range: 3.6-4.2 L / min}, Region B: {Potential Level: Medium, Water Pressure Synergistic Coefficient: 0.70, Flow Fluctuation Range: 3.0-4.8 L / min}}.

[0029] S313: Call the water use impact sensitive area index set, match the water use units and water use pattern templates in the sensitive area, filter the water use units that meet the feature requirements, and mark the location coding information of the corresponding area to generate water use behavior distribution results; Based on a set of indicators for water use impact sensitive areas, for example, if the indicator set identifies "Area A" as a high-potential area for water use behavior, then water-using units within this sensitive area are matched with preset water use pattern templates. For example, the water use pattern templates include "office peak-hour water use pattern" (high-frequency, high-flow flushing) and "residential nighttime water use pattern" (low-frequency, low-flow flushing). For each water-using unit within "Area A," its historical water use behavior data (such as flushing frequency, flow rate, and water pressure variation) is compared with the templates for feature similarity. For example, a cosine similarity algorithm is used to calculate the similarity score, and templates with a similarity score higher than 0.9 are considered... If a match is successful, water-using units that meet the feature requirements are filtered out. For example, in "Area A", if the water-using pattern of toilet M2 has a similarity score of 0.92 with the template "office peak water-using pattern", then M2 is filtered out and its corresponding area location code information is labeled. For example, the location code of M2 is "Building_1_Floor_3_Restroom_South". The matching and filtering process continues for all sensitive areas, and finally, a water-using behavior distribution result containing all water-using units that meet the specific water-using pattern features and their location codes is generated. The result shows the spatial distribution of different water-using behavior patterns.

[0030] Please see Figure 5 The specific steps for obtaining the path segment for dynamic water tracking and control are as follows: S411: Based on the distribution results of water use behavior, extract continuous change information between multiple time periods in the map, identify the geometric center offset of adjacent areas in the time series, extract the offset direction vector and displacement length, analyze the angle difference of the consistency of offset direction between adjacent areas, and obtain continuous offset direction data of water use. Based on the water use behavior distribution results, continuous change information across multiple time periods is extracted from the water use behavior distribution map. For example, from 8:00 AM to 6:00 PM, the center position of the water use behavior pattern within the region is recorded hourly. The offset of the geometric center of adjacent regions in the time series is identified. For example, the geometric center of water use behavior in region A is located at coordinates (X1, Y1) at 9:00 AM and moves to (X2, Y2) at 10:00 AM. The offset is calculated, and the offset direction vector and displacement length are extracted. The offset direction vector is the vector pointing from (X1, Y1) to (X2, Y2). The displacement length is the aforementioned offset. For example, the displacement length is 15 meters, and the direction is 30 degrees northeast. The angle difference between adjacent areas is analyzed to ensure the consistency of the offset direction. For example, if the offset direction is 30 degrees northeast in the previous hour and 35 degrees northeast in the next hour, the angle difference is 5 degrees. An angle difference of less than 15 degrees is set as high directional consistency. Through this analysis, continuous water use offset direction data containing timestamps, area identifiers, offset direction vectors, displacement lengths, and angle differences between adjacent time periods are obtained. This data depicts the evolution trajectory and directional stability of water use behavior patterns over time.

[0031] S412: Call the continuous offset direction data for water usage, and based on the changing trend of the angle difference, use the following formula: ; Calculate the angular fluctuation dispersion value, extract the region segment with stable offset direction, filter the continuous segment with angular change below the preset threshold, and obtain stable offset segment information; in, Represents the angular fluctuation dispersion value. Representing the The offset angle at time, This represents the mean of the offset angle. Represents the number of sampling times. For the increment of angle change, The weighting coefficient for the angle change; By calling up continuous offset direction data for water usage, and calculating the angular fluctuation dispersion value based on the changing trend of the angular difference, an inline LaTeX formula is used. ,in, The value represents the angular fluctuation dispersion, which measures the stability and consistency of the water use behavior offset direction over time. The smaller the value, the more stable the direction. Representing the The offset angle of time, for example, 30 degrees at t=1 hour and 35 degrees at t=2 hours; The mean offset angle at each sampling time is the value of all... The arithmetic mean of the values ​​provides a reference benchmark for measuring the degree of deviation of the offset angle at a single moment; This represents the number of sampling times, i.e., the number of offset angle data points contained in the time series; The increment of the angle change represents the angle difference between adjacent sampling times, for example, and ,but ; This is the weighting coefficient for angle changes. This coefficient is used to adjust the degree to which angle changes affect the dispersion value. The larger the weighting coefficient, the more significant the impact of angle changes on the dispersion. It is used to highlight small changes in angle, for example... ; formula The calculation logic is as follows: First, calculate the offset angle at each moment. With average offset angle The difference of squares between This part quantifies the degree to which each instantaneous offset angle deviates from the overall average direction. The squaring operation ensures that all deviations are positive, and larger deviations are amplified more significantly. Then, the squared differences are summed and divided by the number of sampling times. This yields the mean squared difference, which represents the average fluctuation range of the offset angle. The increment of the angle change is then calculated. The square of the product, multiplied by the weighting factor. Adding 1 to form a correction factor The correction factor incorporates consideration of the instantaneous rate of angle change, when the angle change increment... When the value is large, the correction factor will also be large, thus increasing the dispersion. The increased value highlights the impact of rapid angle changes on overall stability. Finally, the mean squared difference is multiplied by the correction factor, and the square root is taken to obtain the final angular fluctuation dispersion. By combining the overall dispersion of the angle with the instantaneous rate of change, this formula can comprehensively and precisely assess the stability of the water behavior offset direction. Suppose we have offset angle data at 3 sampling times: (t=1 hour) (t=2 hours) (t=3 hours); Number of sampling times Average offset angle ; The increment of the angle change is: (From the previous time point to time point 1, let's assume it's 0); ; ; When calculating the summation part, consider As a moment Relative to time The changes, in order to make the formula applicable In the case of, or adopt For the current moment Its mean The difference is calculated by using the square of the difference between the two time points, and it is assumed that... A reasonable setting is 0.01, for the purpose of calculation. ,need and The summation of products, here, in the formula It should be understood as each moment To ensure continuity, the corresponding angular change increments are considered. for To simplify calculations, for The definition can be adjusted to relate only to fluctuations at the current moment; for example, it could be defined as follows: for Or, more commonly, when assessing continuity, It can refer to the angular difference between adjacent moments. In this context, assuming the correction factor... This refers to the absolute difference between the angle at the current moment and the angle at the previous moment, and each term is calculated separately during summation. If a correction factor is used in the formula design... It is for each If the item is corrected, then Should refer to Compared to its previous angle The change, for the first sampling point, It can be set to 0; Therefore, the calculations are as follows: : , , , (Set to 0, or no previous time step); : , , , ; : , , , ; To simplify the calculation and conform to the weighted average form, a correction factor is considered. Applied to the entire mean squared difference, or It inherently represents the total angular change over a period of time. To strictly adhere to the formula structure, it is interpreted as each... Each term will be multiplied by a correction factor based on the angle change at the current or adjacent time points. If the change specifically refers to a global change, then it needs to be redefined. If the change is local at each point, then: Assume In the correction factor, it refers to the absolute difference between the angle at the current moment and the angle at the previous moment. For simplicity, for the first sampling point, its... The item is set to 0.

[0032] ; ; ; Summation term

[0033] ; The advantage of this formula lies in its ability to more comprehensively and sensitively assess the stability of the water use behavior pattern shift direction by combining the dispersion of the offset angle with the instantaneous rate of change. This correction factor... This allows for a significant increase in the dispersion value due to drastic changes in instantaneous angles, thereby more accurately identifying unstable regions with drastic dynamic changes and providing a more reliable basis for precise control. This represents the dispersion of water behavior offset angle fluctuations in the time series. A lower dispersion value (e.g., G < 3) indicates relatively stable direction. Based on this, regions with stable offset directions are extracted. For example, a preset threshold is set. If the calculated If the value is less than or equal to 3, the segment is identified as a stable offset segment. Further filtering is then performed on continuous segments with angle changes below a preset threshold. For example, setting the angle change threshold to 10 degrees means that the angle difference between any two adjacent hours does not exceed 10 degrees. This identifies time periods within a continuous 10-hour period where the angle change in each hour does not exceed 10 degrees. For instance, in a certain area, from 8 AM to 3 PM, a continuous 7-hour period... If all values ​​are below 3 and the difference between adjacent angles is less than 10 degrees, then this 7-hour period is identified as a stable offset segment, and stable offset segment information including start time, end time, area identifier, and stability quantification index is obtained.

[0034] S413: Call up the stable offset segment information, combine the offset direction angle in each segment, the water use distribution intensity between regions and the time series continuity index, identify the trajectory segments with strong continuity and concentrated water use signals, and obtain the water use dynamic tracking and control path segments; The system retrieves information on stable offset segments. For example, it identifies a stable offset segment that lasts from 8:00 AM to 3:00 PM, with an average offset direction angle of 32 degrees. It then performs a comprehensive analysis of the offset direction angle, water usage intensity across areas within the segment, and the time series continuity index. Water usage intensity, for example, refers to the average water consumption per unit area within the segment, which is 15 L / hour. The time series continuity index measures the duration of water usage patterns within the segment; for example, a continuity index of 0.9 or higher is defined as high continuity, and the time series continuity index for this segment is 0.95. By combining and calculating parameters, trajectory segments with strong continuity and concentrated water use signals are identified. For example, if the average offset direction angle change of a stable offset segment is less than 5 degrees, the water use distribution intensity between regions is higher than 20L / hour, and the time series continuity index exceeds 0.9, then the segment is identified as a trajectory segment with highly concentrated water use signals. Through this process, segments with stable offsets but dispersed or poorly continuous water use are eliminated. Finally, a water use dynamic tracking and control path segment containing start time, end time, spatial trajectory description, and quantitative indicators of water use signal concentration is obtained.

[0035] Please see Figure 6 The specific steps for obtaining the water behavior linkage response control instruction set are as follows: S511: Based on the dynamic tracking and control path segment of water use, extract the water pressure change trend and water use level in the segment, identify the daily water pressure change value and the daily average water use value of the segment, analyze the water pressure change amplitude and water use fluctuation degree, and generate a synchronous water pressure change characteristic value group. Based on dynamic water usage tracking and control of specific pathways, for example, obtaining a specific pathway from 9:00 AM to 11:00 AM, the water pressure change trend and water usage level data are extracted from real-time monitoring data within this pathway. For instance, between 9:00 AM and 11:00 AM, the water pressure in this pathway drops from 0.28 MPa to 0.25 MPa, and the water consumption fluctuates from 25 L / hour to 30 L / hour. The daily water pressure variation and daily average water consumption of this pathway are identified. For example, the average difference between the highest and lowest water pressure in this pathway over the past 7 consecutive days is recorded as 0.04 MPa, and the average daily water consumption is 200 L. Subsequently, the magnitude of water pressure variation and... The degree of water usage fluctuation is analyzed. For example, the range of water pressure change is obtained by calculating the difference between the daily maximum and minimum water pressure values, while the degree of water usage fluctuation is quantified by calculating the daily standard deviation of water consumption. For example, if the water pressure change range is 0.035 MPa and the water consumption fluctuation (standard deviation) is 15 L on a certain day, the analysis generates a set of synchronous water pressure change characteristic values ​​that include the daily water pressure change range, water consumption fluctuation, average water pressure, and average daily water consumption for that section. For example, this set of data is {Date: 10-21, Water pressure change range: 0.035 MPa, Water consumption fluctuation: 15 L, Average water pressure: 0.26 MPa, Average daily water consumption: 200 L}.

[0036] S512: Call the synchronous water pressure change feature value group, and based on the water-saving efficiency layer grid efficiency sequence, combined with the water pressure change amplitude, water usage fluctuation degree and water-saving efficiency, extract the turning point of the continuous time period, filter the segment number of the turning feature and summarize it to obtain the index list of the synchronous segment of sudden change. The system calls upon the synchronous water pressure change feature value group and simultaneously references the grid efficiency sequence data in the water-saving efficiency layer. For example, if a grid's water-saving efficiency sequence shows a change from "high efficiency" to "medium efficiency," the system performs correlation analysis on the three parameters: water pressure change amplitude, water usage fluctuation degree, and water-saving efficiency. For instance, if the water pressure change amplitude in a certain section suddenly increases to over 0.05 MPa, and the water usage fluctuation degree also rises to over 20 L, while the corresponding water-saving efficiency decreases from 0.9 to 0.7, the system identifies continuous periods of simultaneous parameter changes as inflection points. The inflection point determination criteria are: when the water pressure change amplitude exceeds 0.04 MPa and the water usage fluctuation degree exceeds 18 L. Furthermore, when the water-saving efficiency decreases by more than 0.1, this time point is marked as an inflection point. For example, in a 24-hour continuous monitoring data, it is found that during the period from the 12th to the 14th hour, the above three parameters simultaneously meet the inflection point judgment criteria. The segment numbers with turning point characteristics are selected and summarized. For example, all the segment numbers corresponding to the period of decreased water-saving efficiency and increased water pressure fluctuation (such as Path_Segment_003, Path_Segment_007) are summarized into a list. Finally, a list of mutation synchronization segment indexes containing all segment numbers with mutation synchronization characteristics is obtained. The list indicates the areas that need attention and regulation.

[0037] S513: Based on the list of mutation synchronization section indexes, match the water distribution layer coordinate units corresponding to the section number, filter and mark overlapping grids with the same index, and output the water use behavior linkage response control instruction set. Based on the mutation synchronization segment index list, for example, the list contains [Path_Segment_003, Path_Segment_007], the coordinate units corresponding to the segment numbers are matched in the water distribution layer. For example, Path_Segment_003 corresponds to multiple toilet coordinate units in the restroom area on the third floor of Building A. Then, grids with consistent indices and spatial overlap are selected. For example, if the coordinate units corresponding to Path_Segment_003 and Path_Segment_007 have spatial intersection or are closely adjacent in the geographic information layer, and both show similar mutation characteristics, they are marked as linkage response areas, for example, marked as "linkage area 001". Water use behavior within overlapping grids needs to be processed collaboratively, and a water use behavior linkage response control instruction set containing the coordinate information of the marked areas and control suggestions is output. For example, the instruction set contains "For linkage area 001, from 10:00 am to 2:00 pm, reduce the flushing flow of all toilets in the area by 10% and send a water pressure abnormality warning to the property management." The instruction set provides specific and executable linkage control strategies.

[0038] The intelligent water flow control system for toilets is used to execute the aforementioned intelligent water flow control method for toilets. The system includes: The water demand benchmark construction module collects data from different sources in the intelligent water flow control model of the toilet, extracts water operation data, and formats the water data and water pressure factor in combination with time and space identifiers to generate a water demand benchmark parameter set. The water usage anomaly detection module is based on the water demand baseline parameter set. According to the water usage distribution status and water pressure data, it filters water usage units that exceed the preset threshold, removes interference data associated with anomalies, integrates the remaining water usage distribution status and operation information, marks abnormal areas, and generates a water usage anomaly diagnosis dataset. The water use behavior extraction module extracts water use distribution status, water pressure change value, and water use intensity based on the water use anomaly diagnosis dataset, identifies water use units that conform to the water use pattern, matches water use behavior templates, overlays location codes and time labels, performs spatial positioning, and generates water use behavior distribution results. Based on the distribution results of water use behavior, the water use path tracking module extracts time tags and water use operation information, identifies the spatial distance between water use behavior areas in adjacent time periods, determines the offset direction and continuous trajectory, integrates path segments with consistent offset direction, and obtains water use dynamic tracking and control path segments. The water use linkage analysis module is based on the dynamic tracking and control path segment of water use. According to the water pressure change trend, water use level and water saving efficiency of the path segment, it performs time series comparison, identifies the synchronous turning point, locates the overlapping position of the turning area and water use behavior, and outputs the water use behavior linkage response control instruction set.

[0039] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for intelligent water flow control in a toilet, characterized in that, Includes the following steps: S1: Based on the initial input of user toilet behavior, the data from different sources in the toilet smart water flow control model are restructured and combined with time labels and spatial identifiers to generate a water demand benchmark parameter set; S2: Based on the water demand benchmark parameter set, analyze the correlation between water use behavior characteristics and water pressure distribution, identify the abnormal water use fluctuation range data set and water pressure deviation range, filter water use units that exceed the preset threshold, and remove related interference data to generate a water use anomaly diagnosis dataset. S3: Based on the water use anomaly diagnosis dataset, extract the water use distribution status and water pressure change value, identify key water use nodes and water pressure combinations, screen water use units that conform to known water use patterns, and overlay location codes to mark the corresponding areas to generate water use behavior distribution results; S4: Based on the continuous change information between multiple time periods in the water use behavior distribution results, identify the water use offset in adjacent areas of the time period, extract the offset direction and propagation trajectory, filter out the area segments with the same continuous offset direction, and obtain the water use dynamic tracking and control path segment.

2. The intelligent water flow control method for toilets according to claim 1, characterized in that, The water demand baseline parameter set includes a water distribution feature value set, a water pressure attribute grid, and a spatial operation parameter surface. The water anomaly diagnosis dataset includes water fluctuation identification results, water pressure deviation markers, and interference data removal masks. The water behavior distribution results include a target water candidate set, key node response templates, and regional location codes. The water dynamic tracking and control path segment includes a continuous offset trend trajectory, a path direction vector set, and regional offset nodes.

3. The intelligent water flow control method for a toilet according to claim 1, characterized in that, The specific steps for obtaining the water demand baseline parameter set are as follows: S111: Based on the initial input of the user's toilet behavior, collect data from different sources in the toilet intelligent water flow control model, combine time tags to perform frame sequence matching, remove water use units in the water use distribution sequence whose difference between adjacent frames exceeds the fluctuation critical threshold, and generate a multi-dimensional water use matrix. S112: Based on the multidimensional water use matrix, extract water pressure intensity and water use distribution data under the same time and space identifier, filter out records with missing items, and generate effective water use operation factor data group; S113: Call the effective water use operation factor data group, identify the standard deviation of water pressure intensity in water use unit groups with consistent water use operation modes and normalize it, calculate the normalized water use difference intensity value, reclassify water use units in the region, and establish a water demand benchmark parameter set.

4. The intelligent water flow control method for a toilet according to claim 3, characterized in that, The specific steps for obtaining the water usage anomaly diagnostic dataset are as follows: S211: Based on the water demand benchmark parameter set, extract the water distribution status and water pressure data in the layer, match and compare the fluctuation value of water unit with the water pressure range, analyze the corresponding relationship, and obtain the water fluctuation range data set. S212: Call the water usage fluctuation range data set, combine it with the distribution status of water usage units in the evaluation layer, determine whether it falls into the specified range, identify the difference in water usage units that are not in the range, determine the objects to be removed based on the difference, and obtain a list of removed water usage unit numbers. S213: Call the list of water-using units to be removed, delete the interfering data associated with the corresponding numbers in the evaluation layer, reorganize the spatial distribution of the remaining water-using units, and generate a water-using anomaly diagnostic dataset.

5. The intelligent water flow control method for a toilet according to claim 4, characterized in that, The specific steps for obtaining the water use behavior distribution results are as follows: S311: Based on the water use anomaly diagnosis dataset, extract the distribution status and water pressure change value of the water use units in the layer, combine the differentiated water use nodes with the corresponding water pressure data, identify typical water use pattern areas, and obtain the water use pattern representation combination. S312: Call the water use pattern characterization combination, detect the fluctuation difference of water use units and the degree of coordinated change of water pressure in the combination area, aggregate and compare the response values ​​of water use units at key nodes, identify the area of ​​water use behavior potential, and obtain the water use impact sensitive area index set. S313: Call the water use impact sensitive area index set, match the water use units and water use pattern templates in the sensitive area, filter the water use units that meet the feature requirements, and mark the location code information of the corresponding area to generate water use behavior distribution results.

6. The intelligent water flow control method for a toilet according to claim 5, characterized in that, The specific steps for obtaining the water usage dynamic tracking and control path segment are as follows: S411: Based on the water use behavior distribution results, extract continuous change information between multiple time periods in the map, identify the geometric center offset of adjacent areas in the time series, extract the offset direction vector and displacement length, analyze the angle difference of the consistency of offset direction between adjacent areas, and obtain continuous water use offset direction data. S412: Call the continuous offset direction data of water usage, and based on the changing trend of the angle difference, use the formula: ； Calculate the angular fluctuation dispersion value, extract the region segment with stable offset direction, filter the continuous segment with angular change below the preset threshold, and obtain stable offset segment information; in, Represents the angular fluctuation dispersion value. Representing the The offset angle at time, This represents the mean of the offset angle. Represents the number of sampling times. For the increment of angle change, The weighting coefficient for the angle change; S413: Call the stable offset segment information, combine the offset direction angle in each segment, the water distribution intensity between regions and the time series continuity index, identify the trajectory segments with strong continuity and concentrated water use signals, and obtain the water use dynamic tracking and control path segments.

7. The intelligent water flow control method for a toilet according to claim 1, characterized in that, The method also includes step S5: S5: Based on the water usage dynamic tracking and control path segment, identify the water pressure change trend and water usage level, overlay a water-saving efficiency layer, compare the time synchronization change characteristics of water pressure, identify the segment coordinates and overlapping positions of water usage distribution where a turning point occurs simultaneously, and output a water usage behavior linkage response control instruction set. The water use behavior linkage response control instruction set includes water pressure linkage change zone, water use response intersection point, and abnormal behavior indicator group.

8. The intelligent water flow control method for a toilet according to claim 7, characterized in that, The specific steps for obtaining the water usage behavior linkage response control instruction set are as follows: S511: Based on the water usage dynamic tracking and control path segment, extract the water pressure change trend and water usage level in the segment, identify the daily water pressure change value and daily average water usage value of the segment, analyze the water pressure change amplitude and water usage fluctuation degree, and generate a synchronous water pressure change characteristic value group. S512: Call the synchronous water pressure change feature value group, and based on the water-saving efficiency layer grid efficiency sequence, combine the water pressure change amplitude, water usage fluctuation degree and water-saving efficiency to extract the turning point of the continuous time period, filter the segment number of the turning feature and summarize it to obtain the sudden change synchronous segment index list. S513: Based on the mutation synchronization section index list, match the water distribution layer coordinate units corresponding to the section number, filter overlapping grids with the same index and mark them, and output the water use behavior linkage response control instruction set.

9. A smart water flow control system for a toilet, characterized in that, The system is used to implement the intelligent water flow control method for a toilet according to any one of claims 1-8, the system comprising: The water demand benchmark construction module collects data from different sources in the intelligent water flow control model of the toilet, extracts water operation data, and formats the water data and water pressure factor in combination with time and space identifiers to generate a water demand benchmark parameter set. The water usage anomaly detection module, based on the water demand baseline parameter set, filters water usage units that exceed a preset threshold according to water usage distribution status and water pressure data, removes interfering data associated with anomalies, integrates the remaining water usage distribution status and operation information, marks abnormal areas, and generates a water usage anomaly diagnostic dataset. Based on the water use anomaly diagnosis dataset, the water use behavior extraction module extracts water use distribution status, water pressure change value, and water use intensity, identifies water use units that conform to the water use pattern, matches water use behavior templates, overlays location codes and time labels, performs spatial positioning, and generates water use behavior distribution results. Based on the water use behavior distribution results, the water use path tracking module extracts time tags and water use operation information, identifies the spatial distance between water use behavior areas in adjacent time periods, determines the offset direction and continuous trajectory, integrates path segments with consistent offset directions, and obtains water use dynamic tracking and control path segments. The water use linkage analysis module, based on the water use dynamic tracking and control path segment, compares the time series according to the water pressure change trend, water use level and water saving efficiency of the path segment, identifies the synchronous turning point, locates the overlapping position of the turning area and water use behavior, and outputs the water use behavior linkage response control instruction set.

Images