An Internet of Things-based integrated data management system and method for intelligent water services

Abstract

The present invention discloses an intelligent water service comprehensive data management system and method based on the Internet of Things, which relates to the technical field of water service data management, and includes the following steps: establishing a data connection with a water service comprehensive database to obtain historical water service data; analyzing the historical water service data to obtain a prediction function; analyzing the change function of the actual water supply volume in the second period to correct the prediction function and obtain a correction parameter; performing real-time monitoring on the water supply volume of the water service system, predicting the water supply demand for the next week when the water supply volume continuously rises, and then producing water based on the water supply demand; the present invention is used to solve the problem that the existing water service data management technology still has a less significant effect on predicting the water consumption of residents and inaccurate prediction results, resulting in easy waste of water resources.

Description

Technical Field

[0001] The present invention relates to the technical field of water service data management, and particularly to an intelligent water service integrated data management system and method based on the Internet of Things. Background Art

[0002] Water service data management technology refers to a series of technologies and methods that apply information technology and data management methods to collect, store, process, analyze, and utilize relevant data in the water service field. Its purpose is to improve the data management efficiency, data quality, and data value of the water service system, and support water service decision-making and operation activities such as water resource management, water environment protection, water supply, and drainage.

[0003] Existing water service data management technologies usually combine all-round water service data such as intelligent water supply, intelligent drainage, intelligent flood control, sewage treatment, and water conservation management to comprehensively manage the operation of the entire water service system. In terms of intelligent water supply, since the water consumption of residents is related to many factors, and the deviation of personal water consumption in daily life is within the controllable range for the entire water supply system. However, at the time points of seasonal alternation, due to temperature changes, the water consumption of residents also changes greatly. Especially when the temperature rises, the water consumption of residents rises sharply. If the water production capacity cannot keep up with the consumption of users, it will lead to water supply interruption in some areas. Therefore, water supply companies need to plan in advance when supplying water. However, when the existing water service data management technology plans the future water supply volume, the prediction of the future water consumption of residents is not accurate enough, and it is easy to cause water resource waste. For example, in the patent application with the publication number CN113420967A, a method for evaluating the operation of an urban water supply network based on prediction is disclosed. This scheme only predicts the water consumption of residents every day. Although the water consumption of each person fluctuates every day, the number of people is too large, resulting in a small change in the total water supply volume of the water service system every day under the same environmental conditions and all within the controllable range. Therefore, the significance and effect of predicting the water consumption of each person are not great. The existing water service data management technology also has the problems that the prediction effect of residents' water consumption is not significant enough and the prediction result is not accurate enough, leading to easy occurrence of water resource waste. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems in the prior art to a certain extent. By establishing a data connection with the integrated water service database, historical water service data is obtained, and then the historical water service data is analyzed, historical data groups are divided, the historical data groups are analyzed, the first period and the second period are obtained by finding historical data groups with an increasing water supply volume trend, and then the first period is analyzed. Based on the increasing trend analysis of the first period, a prediction function is calculated. Then, the water supply volume on the dates within the second period is analyzed to obtain a change function. Based on the change function, the prediction function is corrected to obtain a correction parameter. Finally, the water supply volume of the water service system is monitored in real time. When the water supply volume continuously increases, the water supply demand for the next week is predicted, and water production is carried out based on the water supply demand, so as to solve the problems that the existing water service data management technology still has insufficiently significant prediction effect on the residential water consumption and inaccurate prediction results, resulting in easy occurrence of water resource waste.

[0005] To achieve the above object, in the first aspect, the present application provides an integrated intelligent water service data management method based on the Internet of Things, including the following steps:

[0006] Establish a data connection with the integrated water service database to obtain historical water service data;

[0007] Analyze the historical water service data, find two consecutive weeks with an increasing water supply volume trend, and mark them as the first period and the second period respectively. Analyze the first period to obtain a prediction function;

[0008] Analyze the change function of the actual water supply volume in the second period, and correct the prediction function to obtain a correction parameter;

[0009] Monitor the water supply volume of the water service system in real time. When the water supply volume continuously increases, predict the water supply demand for the next week, and then carry out water production based on the water supply demand.

[0010] Further, the historical water service data includes the recording date and the historical water supply volume.

[0011] Further, analyzing the historical water service data, finding two consecutive weeks with an increasing water supply volume trend, and marking them as the first period and the second period respectively. Analyzing the first period to obtain a prediction function includes the following sub-steps:

[0012] Analyze the historical water service data, divide historical data groups, analyze the historical data groups, and obtain the first period and the second period by finding historical data groups with an increasing water supply volume trend;

[0013] Analyze the first period, and calculate and obtain a prediction function based on the increasing trend analysis of the first period.

[0014] Further, analyze the historical water service data, divide the historical data groups, analyze the historical data groups, and obtain the first period and the second period by finding the historical data groups with an increasing water supply trend, including the following sub-steps:

[0015] Group the historical water service data with Monday to Sunday as a group, name it the historical data group, sort the historical data group from early to late in time, and use the symbol S n to represent, where n is a positive integer and n is the serial number of S. Name the record date in the historical data group as the data date, and mark the historical water supply as the daily water supply;

[0016] Sort the historical water service data in the historical data group in ascending order of the data date, and check whether the daily water supply shows an increasing trend. The so-called increasing trend means that the daily water supply on the next day is greater than the daily water supply on the previous day;

[0017] If so, mark the historical data group as the water supply increasing period, otherwise mark the historical data group as the daily water supply period;

[0018] Find the historical data groups where both S n and S n+1 are the water supply increasing periods, and jointly mark them as the rising analysis period. Among them, mark S n as the first period and S n+1 as the second period.

[0019] Further, analyze the first period, and calculate the prediction function based on the rising trend analysis of the first period, including the following sub-steps:

[0020] Number the daily water supply within the first period in ascending order of the data date, and use the symbol G m to represent, where 1 ≤ m ≤ 7 and m is the serial number of G;

[0021] Establish a plane rectangular coordinate system with m as the X-axis and the daily water supply as the Y-axis, name it the water supply prediction coordinate system, and input G m and the corresponding daily water supply into the water supply prediction coordinate system;

[0022] Perform linear regression on the water supply prediction coordinate system to obtain the prediction function.

[0023] Further, analyze the change function of the actual water supply in the second period, and correct the prediction function to obtain the water supply correction prediction function, including the following sub-steps:

[0024] Analyze the daily water supply within the second period to obtain the change function;

[0025] Based on the variation function, correct the prediction function to obtain the correction parameter.

[0026] Further, analyzing the water supply for each date in the second period to obtain the variation function includes the following sub-steps:

[0027] Mark the water supply on the last date in the first period and the water supply for all dates in the second period as the actual water supply;

[0028] Number the actual water supply in chronological order of dates, denoted by the symbol P i where 1 ≤ i ≤ 8 and i is the serial number of P, and i is a positive integer;

[0029] Taking i as the horizontal axis and the actual water supply as the vertical axis, establish a plane rectangular coordinate system, named the actual water supply coordinate system, and input P i and the actual water supply into the actual water supply coordinate system;

[0030] Perform linear regression on the actual water supply coordinate system to obtain the variation function.

[0031] Further, based on the variation function, correcting the prediction function to obtain the correction parameter includes the following sub-steps:

[0032] Obtain the slope of the prediction function, named the prediction slope; obtain the slope of the variation function, named the actual slope;

[0033] Calculate the quotient of the actual slope divided by the prediction slope to obtain the slope parameter;

[0034] Count all historical water service data in the historical first reference period and calculate all the slope parameters among them;

[0035] Count all the slope parameters and calculate the average value to obtain the correction parameter.

[0036] Further, conduct real-time monitoring of the water supply volume of the water service system. When the water supply volume continuously rises, predict the water supply demand for the next week, and then produce water based on the water supply demand, including the following sub-steps:

[0037] Conduct real-time monitoring of the water supply volume of the water service system and mark it as the real-time water supply volume;

[0038] Taking Monday to Sunday as an evaluation period, if the real-time water supply volume shows an upward trend within the evaluation period, then analyze the prediction function of the evaluation period;

[0039] Multiply the slope in the prediction function by the correction parameter to obtain the prediction correction function;

[0040] Substitute 8 to 14 into the prediction correction function and calculate to obtain seven predicted water supply volumes, representing the water supply volume for each day of the next week;

[0041] Add the predicted water supply amounts to obtain the water supply demand, and arrange the water production work for the next week according to the water supply demand.

[0042] In a second aspect, the present application provides an intelligent water service integrated data management system based on the Internet of Things, including a historical data acquisition module, a prediction analysis module, a prediction correction module, and a water supply prediction module; the historical data acquisition module, the prediction analysis module, and the water supply prediction module are respectively connected to the prediction correction module for data connection;

[0043] The historical data acquisition module is used to establish a data connection with the integrated water service database to obtain historical water service data;

[0044] The prediction analysis module is used to analyze the historical water service data, find two consecutive weeks in which the water supply amount shows an upward trend, and mark them as the first period and the second period respectively, and analyze the first period to obtain a prediction function;

[0045] The prediction correction module is used to analyze the change function of the actual water supply amount in the second period and correct the prediction function to obtain a correction parameter;

[0046] The water supply prediction module is used to monitor the water supply amount of the water service system in real time, predict the water supply demand for the next week when the water supply amount continuously rises, and then produce water based on the water supply demand.

[0047] Advantages of the present invention: By establishing a data connection with the integrated water service database, the present invention obtains historical water service data, then analyzes the historical water service data, divides the historical data groups, analyzes the historical data groups, obtains the first period and the second period by finding the historical data groups in which the water supply amount shows an upward trend, and then analyzes the first period. Based on the upward trend analysis of the first period, a prediction function is calculated. The advantage is that when the temperature rises every year, the water consumption of residents changes greatly. Therefore, predicting the water supply amount for the next week can effectively prevent the situation of water shortage, and improve the effectiveness and rationality of water supply analysis in water service data management;

[0048] The present invention analyzes the water supply amount of the dates in the second period to obtain a change function, corrects the prediction function based on the change function to obtain a correction parameter, and finally monitors the water supply amount of the water service system in real time. When the water supply amount continuously rises, it predicts the water supply demand for the next week, and then produces water based on the water supply demand. The advantage is that based on the prediction situation and the actual situation of the water supply amount in the historical water service data, the prediction function is corrected to more accurately predict the water supply amount required by residents in the next week, so as to formulate a corresponding water production plan, and improve the accuracy and effectiveness of water supply analysis in water service data management. Description of the Drawings

[0049] Figure 1 is the principle block diagram of the system of the present invention;

[0050] Figure 2 is the water supply prediction coordinate system of the present invention;

[0051] Figure 3 is the actual water supply coordinate system of the present invention;

[0052] Figure 4 is the step flow chart of the method of the present invention. Detailed implementation manners

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0054] Example 1, please refer to Figure 1 As shown, the present application provides an Internet of Things-based intelligent water service comprehensive data management system, including a historical data acquisition module, a prediction analysis module, a prediction correction module, and a water supply prediction module; the historical data acquisition module, the prediction analysis module, and the water supply prediction module are respectively connected to the prediction correction module for data connection;

[0055] The historical data acquisition module is used to establish a data connection with the water service comprehensive database to obtain historical water service data; the historical water service data includes the record date and the historical water supply volume;

[0056] In actual application, part of the historical water service data is shown in Table 1 below:

[0057] Table 1 Part of the historical water service data

[0058] Recording Date <![CDATA[Historical water supply volume (m 3 )]]> 2023.04.15 (Monday) 2000 2023.04.16 (Tuesday) 2074 2023.04.17 (Wednesday) 2138 2023.04.18 (Thursday) 2221 2023.04.19 (Friday) 2301 2023.04.20 (Saturday) 2413 2023.04.21 (Sunday) 2528 2023.04.22 (Monday) 2783 2023.04.23 (Tuesday) 2942 2023.04.24 (Wednesday) 3158 2023.04.25 (Thursday) 3308 2023.04.26 (Friday) 3479 2023.04.27 (Saturday) 3643 2023.04.28 (Sunday) 3822

[0059] The prediction analysis module is used to analyze the historical water service data, find two consecutive weeks in which the water supply volume shows an upward trend, and mark them as the first cycle and the second cycle respectively, and analyze the first cycle to obtain a prediction function; the prediction analysis module includes a cycle selection unit and a prediction analysis unit;

[0060] The cycle selection unit is used to analyze the historical water service data, divide the historical data group, analyze the historical data group, and obtain the first cycle and the second cycle by finding the historical data group in which the water supply volume shows an upward trend;

[0061] The cycle selection unit is configured with a cycle selection strategy, and the cycle selection strategy includes:

[0062] Group the historical water service data with Monday to Sunday as a group, name it the historical data group, sort the historical data group in ascending order of time, and use the symbol S n to represent. Among them, n is a positive integer and n is the serial number of S. Name the record date in the historical data group as the data date, and mark the historical water supply as the daily water supply;

[0063] Sort the historical water service data in the historical data group in ascending order of the data date, and check whether the daily water supply shows an upward trend. An upward trend means that the daily water supply of the next day is greater than that of the previous day;

[0064] If so, mark the historical data group as the water supply rising period, otherwise mark the historical data group as the daily water supply period;

[0065] Search for S n and S n+1 Both historical data groups that are the water supply rising period are jointly marked as the rising analysis period. Among them, mark S n as the first period and S n+1 as the second period;

[0066] In practical applications, taking Table 1 as an example, the historical water service data from April 15, 2023 to April 21, 2023 form a historical data group, and the historical water service data from April 22, 2023 to April 28, 2023 form a historical data group. In this embodiment, they are respectively referred to as the first data group and the second data group, and are numbered to obtain S 1 and S 2 . This numbering is only for the historical water service data in Table 1. In actual use, it is usually necessary to analyze the historical water service data in the past few years, so there will be a large number of S n for easy reference to a certain historical data group; through analysis, it is obtained that the daily water supply in the first historical data group and the second historical data group shows an upward trend, that is, the daily water supply of each day is greater than that of the previous day. Mark the first historical data group and the second historical data group as the water supply rising period. Since the first historical data group and the second historical data group are two adjacent weeks, mark the first historical data group as the first period and the second historical data group as the second period;

[0067] The prediction analysis unit is used to analyze the first period and calculate the prediction function based on the upward trend analysis of the first period;

[0068] The prediction analysis unit is configured with a prediction analysis strategy, and the prediction analysis strategy includes:

[0069] Number the daily water supply in the first cycle in ascending order of data date, and represent it by the symbol G m where 1 ≤ m ≤ 7 and m is the serial number of G;

[0070] Please refer to Figure 2 As shown, establish a plane rectangular coordinate system with m as the X-axis and the daily water supply as the Y-axis, named the water supply prediction coordinate system, and input G m and the corresponding daily water supply into the water supply prediction coordinate system;

[0071] Perform linear regression on the water supply prediction coordinate system to obtain a prediction function;

[0072] In practical applications, the numbered G 1 to G 7 are 2000, 2074, 2138, 2221, 2301, 2413, and 2528 in sequence. The constructed water supply prediction coordinate system is as Figure 2 shown. Through linear regression, the prediction function is obtained as YR = 86.607×X + 1892.9, where YR is the daily water supply and X is the serial number m of G m in, referring to the data date.

[0073] The prediction correction module is used to analyze the variation function of the actual water supply in the second cycle, correct the prediction function, and obtain correction parameters; the prediction correction module includes an actual variation analysis unit and a prediction correction unit;

[0074] The actual variation analysis unit is used to analyze the daily water supply in the second cycle to obtain a variation function;

[0075] The actual variation analysis unit is configured with an actual variation analysis strategy, and the actual variation analysis strategy includes:

[0076] Mark the last daily water supply in the first cycle and all the daily water supplies in the second cycle as the actual water supply;

[0077] Number the actual water supply in chronological order, and represent it by the symbol P i where 1 ≤ i ≤ 8 and i is the serial number of P, and i is a positive integer;

[0078] Please refer to Figure 3 As shown, establish a plane rectangular coordinate system with i as the horizontal axis and the actual water supply as the vertical axis, named the actual water supply coordinate system, and input P i and the actual water supply into the actual water supply coordinate system;

[0079] Perform linear regression on the actual water supply coordinate system to obtain a variation function;

[0080] In practical applications, the numbered P1 to P 8 They are 2528, 2783, 2942, 3158, 3308, 3479, 3643, and 3822 in sequence. An actual water supply coordinate system is constructed as Figure 3 shown. Through linear regression, the variation function is obtained as YS = 179.99×X + 2397.9, where YS is the actual water supply volume and X is the serial number P of the data date i of i in

[0081] The prediction correction unit is used to correct the prediction function based on the variation function to obtain correction parameters;

[0082] The prediction correction unit is configured with a prediction correction strategy, and the prediction correction strategy includes:

[0083] Obtain the slope of the prediction function, named as the prediction slope; obtain the slope of the variation function, named as the actual slope;

[0084] Calculate the quotient of the actual slope divided by the prediction slope to obtain the slope parameter;

[0085] Statistically analyze all historical water service data within the historical first reference period, and calculate all the slope parameters therein;

[0086] Statistically analyze all the slope parameters and calculate the average value to obtain the correction parameter;

[0087] In practical applications, the obtained prediction slope is 86.607, the actual slope is 179.99. Calculate 179.99 / 86.607, and the obtained slope parameter is 2.08. The calculation result is reserved to two decimal places. In this embodiment, only a set of slope parameters obtained from the rising analysis period is listed. By statistically analyzing all historical water service data within three years in history, several slope parameters are obtained, that is, the first reference period is set to three years, and the setting of the first reference period is formulated according to the specific situation in the water service comprehensive database; since the amount of data of the slope parameters is too large, specific display is not carried out in this embodiment, and only the specific analysis and calculation process is shown through the display of the slope parameters in this embodiment; statistically analyze the slope parameters and calculate the average value, and the obtained correction parameter is 2.11. The calculation result is reserved to two decimal places.

[0088] The water supply prediction module is used to monitor the water supply volume of the water service system in real time, predict the water supply demand for the next week when the water supply volume is continuously rising, and then produce water based on the water supply demand;

[0089] The water supply prediction module is configured with a water supply prediction strategy, and the water supply prediction strategy includes:

[0090] Monitor the water supply volume of the water service system in real time, and mark it as the real-time water supply volume;

[0091] Take Monday to Sunday as an evaluation cycle. If the real-time water supply in the evaluation cycle shows an upward trend, analyze the prediction function of the evaluation cycle.

[0092] Multiply the slope in the prediction function by the correction parameter to obtain a prediction correction function;

[0093] Substituting 8 to 14 into the forecast correction function, seven forecast water supplies are calculated, representing the forecast water supply for each day of the next week;

[0094] Add up the predicted water supply to get the water demand, and arrange water production for the next week based on the water demand;

[0095] In practical applications, when the real-time water supply in the evaluation period shows an upward trend, the prediction function of each evaluation period is analyzed in real time based on the analysis method of the water supply prediction coordinate system, and the prediction function is YR=86.472×X+1927.6, and the prediction slope is 86.472. The prediction function is corrected to obtain the prediction correction function YR=2.11×86.472×X+1927.6. X=8, X=9, X=10, X=11, X=12, X=13 and X=14 are substituted into the prediction correction function to predict the water supply of the next week. 8 to 14 represent next Monday to next Sunday respectively. The calculated predicted water supply is 3387m3, 3570m3, and 1660m3 respectively. 3 、3752m 3 、3935m 3 、4117m 3 、4300m 3 and 4482m 3 , keep the integer in the calculation result, add the predicted water supply, and get the water demand as 27543m 3 , that is, the water output of the water supply system in the smart water system next week is 27543m 3 .

[0096] Example 2, please refer to Figure 4 As shown, the present application provides a smart water integrated data management method based on the Internet of Things, comprising the following steps:

[0097] Step S1, establishing a data connection with a comprehensive water affairs database to obtain historical water affairs data; the historical water affairs data includes a recording date and historical water supply volume;

[0098] Step S2, analyzing the historical water service data, finding two consecutive weeks in which the water supply shows an upward trend, marking them as the first cycle and the second cycle respectively, analyzing the first cycle to obtain a prediction function; Step S2 includes the following sub-steps:

[0099] Step S201: Analyze the historical water supply data, divide the historical data into groups, analyze the historical data groups, and obtain the first period and the second period by finding the historical data groups with an upward trend in water supply volume.

[0100] Step S201 includes the following sub-steps:

[0101] Step S2011: Group the historical water supply data with each group being from Monday to Sunday, name it the historical data group, sort the historical data group in ascending order of time, and represent it by the symbol S n where n is a positive integer and n is the serial number of S. Name the record date in the historical data group as the data date, and mark the historical water supply volume as the daily water supply volume.

[0102] Step S2012: Sort the historical water supply data in the historical data group in ascending order of the data date, and check whether the daily water supply volume shows an upward trend, that is, the daily water supply volume of the next day is greater than that of the previous day.

[0103] Step S2013: If so, mark the historical data group as the water supply rising period; otherwise, mark the historical data group as the daily water supply period.

[0104] Step S2014: Find the historical data groups where both S n and S n+1 are the water supply rising periods, and jointly mark them as the rising analysis period. Among them, mark S n as the first period and S n+1 as the second period.

[0105] Step S202: Analyze the first period and calculate the prediction function based on the upward trend analysis of the first period.

[0106] Step S202 includes the following sub-steps:

[0107] Step S2021: Number the daily water supply volumes within the first period in ascending order of the data date, and represent it by the symbol G m where 1 ≤ m ≤ 7 and m is the serial number of G.

[0108] Step S2022: Establish a plane rectangular coordinate system with m as the X-axis and the daily water supply volume as the Y-axis, name it the water supply prediction coordinate system, and input G m and the corresponding daily water supply volume into the water supply prediction coordinate system.

[0109] Step S2023: Conduct linear regression on the water supply prediction coordinate system to obtain the prediction function.

[0110] Step S3: Analyze the variation function of the actual water supply volume in the second period, correct the prediction function, and obtain the correction parameter. Step S3 includes the following sub-steps:

[0111] Step S301: Analyze the water supply volume by date in the second period to obtain the variation function.

[0112] Step S301 includes the following sub-steps:

[0113] Step S3011: Mark the water supply volume on the last date in the first period and all the water supply volumes by date in the second period as the actual water supply volume.

[0114] Step S3012: Number the actual water supply volumes in chronological order of dates, denoted by the symbol P i where 1 ≤ i ≤ 8 and i is the serial number of P, and i is a positive integer.

[0115] Step S3013: Establish a plane rectangular coordinate system with i as the horizontal axis and the actual water supply volume as the vertical axis, named the actual water supply coordinate system, and enter P i and the actual water supply volume into the actual water supply coordinate system.

[0116] Step S3014: Conduct linear regression on the actual water supply coordinate system to obtain the variation function.

[0117] Step S302: Based on the variation function, correct the prediction function to obtain the correction parameter.

[0118] Step S302 includes the following sub-steps:

[0119] Step S3021: Obtain the slope of the prediction function, named the prediction slope; obtain the slope of the variation function, named the actual slope.

[0120] Step S3022: Calculate the quotient of the actual slope divided by the prediction slope to obtain the slope parameter.

[0121] Step S3023: Statistically analyze all the historical water service data in the historical first reference period and calculate all the slope parameters among them.

[0122] Step S3024: Statistically analyze all the slope parameters and calculate the average value to obtain the correction parameter.

[0123] Step S4: Conduct real-time monitoring of the water supply volume of the water service system. When the water supply volume continuously rises, predict the water supply demand for the next week, and then produce water based on the water supply demand. Step S4 includes the following sub-steps:

[0124] Step S401: Conduct real-time monitoring of the water supply volume of the water service system and mark it as the real-time water supply volume.

[0125] Step S402: Taking Monday to Sunday as an evaluation period, if the real-time water supply shows an upward trend within the evaluation period, analyze the prediction function of the evaluation period.

[0126] Step S403: Multiply the slope in the prediction function by the correction parameter to obtain a prediction correction function.

[0127] Step S404: Substitute 8 to 14 into the prediction correction function to calculate seven predicted water supplies, representing the predicted daily water supplies for the next week.

[0128] Step S405: Add up the predicted water supplies to obtain the water supply demand, and arrange the water production work for the next week according to the water supply demand.

[0129] Embodiment 3: The present application provides a structural schematic diagram of an electronic device, which may include: a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in a comprehensive data management method for intelligent water affairs based on the Internet of Things are run to achieve the following functions: establishing a data connection with the comprehensive water affairs database to obtain historical water affairs data; analyzing the historical water affairs data to obtain a prediction function; analyzing the change function of the actual water supply in the second period to correct the prediction function to obtain a correction parameter; real-time monitoring the water supply of the water affairs system, predicting the water supply demand for the next week when the water supply continuously rises, and then producing water based on the water supply demand.

[0130] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of software function units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0131] Example 4. The present application further provides a computer-readable storage medium. The present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned integrated data management method for intelligent water services based on the Internet of Things are run to achieve the following functions: establish a data connection with the integrated water service database to obtain historical water service data; analyze the historical water service data to obtain a prediction function; analyze the variation function of the actual water supply volume in the second period, correct the prediction function to obtain a correction parameter; monitor the water supply volume of the water service system in real time, predict the water supply demand for the next week when the water supply volume continuously rises, and then produce water based on the water supply demand.

[0132] Through the description of the above embodiments, the embodiments of the present invention can be provided as a method, a system or a computer program product. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0133] In the embodiments provided by the present application, it should be understood that the disclosed system or method can be implemented in other ways. The above-described embodiments are merely illustrative. For example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some communication interfaces. The indirect coupling or communication connection of the system, modules and units can be in an electrical, mechanical or other form.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A smart water integrated data management method based on the Internet of Things, characterized in that: The steps include: Establish data connection with the comprehensive water affairs database to obtain historical water affairs data; Analyze historical water service data and find two consecutive weeks in which water supply shows an upward trend. Mark them as the first cycle and the second cycle respectively. Analyze the first cycle and obtain the prediction function. Analyze the variation function of the actual water supply in the second period, calibrate the prediction function, and obtain the correction parameter; Monitor the water supply of the water system in real time, predict the water demand for the next week when the water supply continues to increase, and then produce water based on the water demand; Analyze the historical water service data and find two consecutive weeks in which the water supply shows an upward trend. Mark them as the first cycle and the second cycle respectively. Analyze the first cycle and obtain the prediction function, which includes the following sub-steps: Analyze the historical water affairs data, divide the historical data groups, analyze the historical data groups, and obtain the first cycle and the second cycle by finding the historical data groups showing an upward trend in water supply; The first period is analyzed, and the prediction function is calculated based on the rising trend analysis of the first period; Analyze the historical water affairs data, divide the historical data groups, analyze the historical data groups, and obtain the first cycle and the second cycle by finding the historical data groups showing an upward trend in water supply, including the following sub-steps: The historical water service data are grouped from Monday to Sunday and named as historical data groups. The historical data groups are sorted from early to late according to the time. n It represents, where n is a positive integer and n is the serial number of S, the record date in the historical data group is named as data date, and the historical water supply is marked as date water supply; Sort the historical water affairs data in the historical data group in the order of data date from small to large, and find out whether the date water supply shows an upward trend, where the upward trend means that the date water supply of the next day is larger than the date water supply of the previous day; If yes, the historical data group is marked as a water supply rising period, otherwise the historical data group is marked as a daily water supply period; Find S n With S n+1 All of them are historical data groups of the water supply rising period, collectively marked as the rising analysis period, among which S n Marked as the first cycle, S n+1 Marked as the second cycle; The first cycle is analyzed, and the prediction function is calculated based on the rising trend analysis of the first cycle, including the following sub-steps: The water supply in the first cycle is numbered in ascending order according to the data date, and the symbol G is used to represent the water supply in the first cycle. m It means that 1≤m≤7 and m is the serial number of G; With m as the X-axis and the date water supply as the Y-axis, a rectangular coordinate system is established, named the water supply prediction coordinate system. m The water supply volume corresponding to the date is entered into the water supply forecast coordinate system; Perform linear regression on the water supply prediction coordinate system to obtain the prediction function; Analyzing the variation function of the actual water supply in the second period and correcting the prediction function to obtain the water supply correction prediction function includes the following sub-steps: The water supply on the dates in the second period is analyzed to obtain the variation function; Based on the change function, the prediction function is corrected to obtain correction parameters; The water supply volume on the date in the second period is analyzed to obtain a variation function including the following sub-steps: The water supply on the last date in the first cycle and the water supply on all dates in the second cycle are marked as the actual water supply; The actual water supply is numbered in chronological order of date, and the symbol P i represents, where 1≤i≤8 and i is the serial number of P, i is a positive integer; With i as the horizontal axis and the actual water supply as the vertical axis, a rectangular coordinate system is established, named the actual water supply coordinate system. i And the actual water supply is entered into the actual water supply coordinate system; Perform linear regression on the actual water supply coordinate system to obtain the change function; Based on the change function, the prediction function is corrected to obtain the correction parameters, including the following sub-steps: Get the slope of the prediction function and name it the predicted slope; get the slope of the change function and name it the actual slope; Calculate the actual slope and divide it by the predicted slope to obtain the slope parameter; Collect all historical water service data within the first historical reference period and calculate all slope parameters therein; Count all slope parameters and calculate the average value to obtain the correction parameter; Real-time monitoring of the water supply of the water system, forecasting the water demand for the next week when the water supply continues to increase, and then producing water based on the water supply demand includes the following sub-steps: Monitor the water supply of the water system in real time and mark it as real-time water supply; Take Monday to Sunday as an evaluation cycle. If the real-time water supply in the evaluation cycle shows an upward trend, analyze the prediction function of the evaluation cycle. Multiply the slope in the prediction function by the correction parameter to obtain a prediction correction function; Substituting 8 to 14 into the forecast correction function, seven forecast water supplies are calculated, representing the forecast water supply for each day of the next week; Add up the predicted water supplies to get the water demand, and arrange water production for the next week based on the water demand.

2. According to the method for comprehensive data management of smart water affairs based on the Internet of Things according to claim 1, it is characterized in that: The historical water service data includes a recording date and historical water supply volume.

3. A smart water affairs integrated data management system based on the Internet of Things, used to implement a smart water affairs integrated data management method based on the Internet of Things as described in claim 1 or 2, characterized in that: It includes a historical data acquisition module, a prediction analysis module, a prediction correction module and a water supply prediction module; the historical data acquisition module, the prediction analysis module and the water supply prediction module are respectively connected with the prediction correction module data; The historical data acquisition module is used to establish a data connection with the water affairs comprehensive database to acquire historical water affairs data; The prediction analysis module is used to analyze historical water service data, find two consecutive weeks in which water supply shows an upward trend, mark them as the first cycle and the second cycle respectively, analyze the first cycle, and obtain a prediction function; The prediction correction module is used to analyze the variation function of the actual water supply in the second period, correct the prediction function, and obtain the correction parameter; The water supply prediction module is used to monitor the water supply of the water system in real time, predict the water supply demand for the next week when the water supply continues to increase, and then produce water based on the water supply demand.

Images