Water conservancy project progress prediction system based on big data

Abstract

The invention discloses a water conservancy project progress prediction system based on big data, and relates to the technical field of project progress prediction, and the system comprises the steps: collecting historical progress data, building an initial prediction model, collecting water consumption conditions, building a water consumption priority mechanism, obtaining a second prediction model, collecting physiological data, building a project amount change mechanism, and obtaining a third prediction model. According to the method, an initial water conservancy project prediction model is established based on historical data, and a water utilization priority mechanism and a construction progress change mechanism are respectively established by collecting water utilization conditions of residents and heart rate data of workers; and the mechanisms are embedded into a prediction model. According to the comprehensive prediction method, the accuracy and reliability of project progress prediction are improved, scientific decision support is provided for hydraulic engineering construction, the cost is reduced, the efficiency is improved, and the project is ensured to be smoothly carried out according to a plan.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering progress prediction, and particularly to a water conservancy project progress prediction system based on big data. Background Art

[0002] With the continuous growth of the global water resource demand, the construction of water conservancy projects has become an important means to ensure the sustainable development of social economy. However, the long construction period, large investment, and complex involved factors of water conservancy projects make the project progress management an extremely challenging task.

[0003] Currently, the Chinese invention patent with the application number CN202010872868.6 discloses a building project progress prediction system and method based on deep learning, belonging to the field of the construction industry. The model construction process includes: extracting historical data; performing data cleaning, correction, supplementation, and regularization processing on the historical data to obtain data to be trained; constructing an initial prediction model and training it; verifying the model based on special data, and taking the initial prediction model that passes the verification as the progress prediction model for output; the progress prediction process includes: obtaining the current actual project information and inputting it into the progress prediction model, and predicting the predicted project progress information associated with the actual project information.

[0004] The above technology is difficult to combine historical progress data, residents' water usage situations, and workers' status information, and use the impact of human activities on project progress as one of the bases for prediction, which affects the accuracy of the prediction results. Summary of the Invention

[0005] The technical problem solved by the present invention is that the prior art is difficult to combine historical progress data, residents' water usage situations, and workers' status information, and use the impact of human activities on project progress as one of the bases for prediction, which affects the accuracy of the prediction results.

[0006] To solve the above technical problem, the present invention provides the following technical solution:

[0007] A water conservancy project progress prediction system based on big data, including an initial model establishment module, a resident demand analysis module, a worker status analysis module, a data processing and integration module, and a prediction result output module:

[0008] The initial model establishment module is used to collect historical progress data and establish an initial prediction model;

[0009] The resident demand analysis module is used to collect real-time water usage situation data and historical water usage situation data of residents, establish a water usage priority mechanism, and embed the water usage priority mechanism into the initial prediction model to obtain a second prediction model;

[0010] The worker status analysis module is used to collect the real-time physiological data and historical physiological data of workers, extract the features of the real-time physiological data and historical physiological data, establish a project quantity change mechanism, embed the project quantity change mechanism into the second prediction model, and obtain the third prediction model;

[0011] The data processing and integration module is used to integrate the logic of the third prediction model, establish a weight mechanism, take the real-time water usage data and real-time physiological data as input data, and input them into the third prediction model to obtain the analysis result;

[0012] The prediction result output module is used to output an adjustment signal according to the analysis result and send the adjustment signal to the notification end.

[0013] Preferably, the initial model establishment module includes a historical data collection unit and an initial model establishment unit;

[0014] The historical data collection unit is used to collect historical progress data, and the historical progress data includes daily work progress, total completion volume, construction date, number of personnel, and climate conditions;

[0015] The initial model establishment unit is used to establish an initial prediction model according to the historical progress data. The input data of the initial prediction model is the total project quantity data, and the output data of the initial prediction model is the completion time data.

[0016] Preferably, the logic of the initial prediction model is:

[0017] Divide the historical progress data into a training set, a validation set, and a test set according to a preset division ratio value, use the training set to adjust the parameters of the multiple linear regression model, select the parameter combination through the validation set, take the daily work progress and construction date as input data, and take the total project duration estimation data as output data.

[0018] Preferably, the resident demand analysis module includes a resident data collection unit and a first mechanism establishment unit;

[0019] The resident data collection unit is used to collect the real-time water usage data and historical water usage data of residents. The real-time water usage data includes the real-time water usage time and the real-time water usage volume data corresponding to the real-time water usage time, and the historical water usage data includes the historical water usage time and the historical water usage volume data corresponding to the historical water usage time;

[0020] The first mechanism establishing unit is used to extract the characteristics of historical water usage data. The characteristics of the historical water usage data include dividing the historical water usage time into peak daily water usage periods, low daily water usage periods, peak water usage seasons, and low water usage seasons according to a preset water usage threshold, and assigning values to the peak daily water usage periods, low daily water usage periods, peak water usage seasons, and low water usage seasons, and outputting them as representative values of water usage time. According to the characteristics of the historical water usage data, a water usage priority mechanism is established, and the water usage priority mechanism is embedded in the initial prediction model to obtain a second prediction model.

[0021] Preferably, the logic of the water usage priority mechanism is as follows:

[0022] Establish a water usage priority level, where the water usage priority level is that residential water usage is of high water usage priority, and engineering water usage is of low water usage priority;

[0023] Establish a mathematical model for water usage demand. The mathematical expression of the mathematical model for water usage demand is:

[0024] ;

[0025] Wherein, is the water usage demand weight, is the preset first water usage weight coefficient, is the real-time water usage data, is the preset second water usage weight coefficient, is the representative value of water usage time.

[0026] Preferably, the worker status analysis module includes a worker data collection unit and a second mechanism establishing unit;

[0027] The worker data collection unit is used to collect the real-time physiological data and historical physiological data of workers. The real-time physiological data includes real-time heart rate data, real-time blood oxygen saturation data, and real-time status time data corresponding to the real-time heart rate data and real-time blood oxygen saturation data. The historical physiological data includes historical heart rate data, historical blood oxygen saturation data, and historical status time data corresponding to the historical heart rate data and historical blood oxygen saturation data;

[0028] The second mechanism establishing unit is used to extract the characteristics of historical physiological data. The characteristics of the historical physiological data include dividing the historical heart rate data and historical blood oxygen saturation data into a fatigue state and a normal state according to a preset heart rate threshold and blood oxygen saturation threshold. According to the characteristics of the historical physiological data, a project quantity change mechanism is established, and the project quantity change mechanism is embedded in the initial prediction model to obtain a third prediction model.

[0029] Preferably, the logic of the project quantity change mechanism is as follows:

[0030] If the number of historical physiological data with the characteristic of fatigue state is within the preset high fatigue total number threshold, reduce the engineering quantity by the first percentage;

[0031] If the number of historical physiological data with the characteristic of normal state is within the preset low fatigue total number threshold, the engineering quantity remains unchanged;

[0032] Obtain the worker information with the characteristic of fatigue state in historical physiological data and the worker information with the characteristic of normal state in historical physiological data, output as the worker information in fatigue state and the worker information in normal state, send a rest signal to the worker corresponding to the worker information in fatigue state, and send an increased work signal to the worker corresponding to the worker information in normal state.

[0033] Preferably, the data processing and integration module includes a logic integration processing unit and an analysis result acquisition unit;

[0034] The logic integration processing unit is used to integrate the logic of the second prediction model and establish a weight mechanism;

[0035] The analysis result acquisition unit is used to take the real-time water consumption data and real-time physiological data as input data, input them into the third prediction model, and obtain the analysis result.

[0036] Preferably, the weight mechanism is as follows:

[0037] Calculate the demand weight of the water consumption according to the water use priority mechanism, obtain the water use demand weight, and perform a primary calculation on the engineering quantity;

[0038] If the water use demand weight is within the preset first water use demand weight threshold, reduce the engineering quantity by the second percentage;

[0039] If the water use demand weight is within the preset second water use demand weight threshold, the engineering quantity remains unchanged;

[0040] Output the engineering quantity after the primary calculation as the first engineering quantity;

[0041] Take the first engineering quantity as input data and input it into the engineering quantity change mechanism for secondary calculation;

[0042] If the number of historical physiological data with the characteristic of fatigue state is within the preset high fatigue total number threshold, reduce the first engineering quantity by the first percentage;

[0043] If the number of historical physiological data with the characteristic of normal state is within the preset low fatigue total number threshold, the first engineering quantity remains unchanged;

[0044] Output the engineering quantity after the secondary calculation as the predicted total engineering quantity;

[0045] Take the predicted total project volume as input data, input it into the initial prediction model to obtain the completion time data, and output the completion time data as the analysis result.

[0046] Preferably, the prediction result output module includes an analysis result response unit and a response signal implementation unit;

[0047] The analysis result response unit is used to obtain the analysis result;

[0048] If the completion time data is within the preset qualified completion time threshold, no adjustment signal is issued;

[0049] If the completion time data is within the preset unqualified completion time threshold, an adjustment signal is issued, and the adjustment signal includes increasing the number of workers and increasing the external water storage volume;

[0050] The response signal implementation unit is used to send the adjustment signal to the notification end to adjust the number of workers and the external water storage volume.

[0051] Advantages of the present invention: The present invention establishes an initial water conservancy project prediction model based on historical data. By collecting the residential water consumption situation and the workers' heart rate data, a water use priority mechanism and a construction progress change mechanism are respectively established and embedded in the prediction model. This comprehensive prediction method improves the accuracy and reliability of the project progress prediction, provides scientific decision-making support for the construction of water conservancy projects, helps to reduce costs, improve efficiency, and ensure the smooth progress of the project according to the plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the basic process of a water conservancy project progress prediction system based on big data provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention.

[0054] Embodiment, referring to Figure 1 , a water conservancy project progress prediction system based on big data is provided, including an initial model establishment module, a resident demand analysis module, a worker status analysis module, a data processing and integration module, and a prediction result output module:

[0055] The initial model establishment module is used to collect historical progress data and establish an initial prediction model.

[0056] The resident demand analysis module is used to collect real-time water usage data and historical water usage data of residents, establish a water usage priority mechanism, embed the water usage priority mechanism into the initial prediction model, and obtain the second prediction model.

[0057] The worker status analysis module is used to collect real-time physiological data and historical physiological data of workers, extract the characteristics of the real-time physiological data and historical physiological data, establish a project quantity change mechanism, embed the project quantity change mechanism into the second prediction model, and obtain the third prediction model.

[0058] The data processing and integration module is used to integrate the logic of the third prediction model, establish a weight mechanism, use the real-time water usage data and real-time physiological data as input data, and input them into the third prediction model to obtain the analysis result.

[0059] The prediction result output module is used to output an adjustment signal according to the analysis result and send the adjustment signal to the notification end.

[0060] The initial model establishment module includes a historical data collection unit and an initial model establishment unit.

[0061] The historical data collection unit is used to collect historical progress data, and the historical progress data includes daily work progress, total completed quantity, construction date, number of personnel, and climate conditions.

[0062] The historical data collection unit effectively collects comprehensive historical progress data from multiple channels, including daily work progress, total completed quantity, construction date, number of personnel, and climate conditions, etc., providing a rich and accurate data basis for the establishment of the initial prediction model.

[0063] The initial model establishment unit is used to establish an initial prediction model according to the historical progress data. The input data of the initial prediction model is the total project quantity data, and the output data of the initial prediction model is the completion time data.

[0064] The logic of the initial prediction model is:

[0065] Divide the historical progress data into a training set, a validation set, and a test set according to a preset division ratio value, use the training set to adjust the parameters of the multiple linear regression model, select the parameter combination through the validation set, use the daily work progress and construction date as input data, and use the total project duration estimation data as output data.

[0066] Based on the collected historical data, the initial model establishment unit successfully established a multiple linear regression model, and through the scientific division of the training set, validation set, and test set, optimized the model parameters, enabling the model to accurately predict the total project duration and providing strong support for the reasonable arrangement of the project progress.

[0067] The initial model establishment module systematically collects historical progress data and uses this data to establish an accurate initial prediction model that can accurately predict the completion time based on the total project volume data, providing reliable progress prediction support for water conservancy project construction and helping to improve the scientific nature and efficiency of project management.

[0068] The resident demand analysis module includes a resident data collection unit and a first mechanism establishment unit.

[0069] The resident data collection unit is used to collect real-time water usage data and historical water usage data of residents. The real-time water usage data includes real-time water usage time and real-time water consumption data corresponding to the real-time water usage time, and the historical water usage data includes historical water usage time and historical water consumption data corresponding to the historical water usage time.

[0070] The resident data collection unit collects the water usage data of residents in real time and accurately, including real-time water usage time and corresponding water consumption, as well as historical water usage time and corresponding water consumption, providing a detailed data basis for the subsequent establishment of the water usage priority mechanism.

[0071] The first mechanism establishment unit is used to extract the characteristics of the historical water usage data. The characteristics of the historical water usage data include dividing the historical water usage time into daily water usage peak periods, daily water usage low peak periods, water usage peak seasons, and water usage low peak seasons according to a preset water consumption threshold, and assigning values to the daily water usage peak periods, daily water usage low peak periods, water usage peak seasons, and water usage low peak seasons, and outputting them as water usage time representative values. Establish a water usage priority mechanism based on the characteristics of the historical water usage data, and embed the water usage priority mechanism into the initial prediction model to obtain a second prediction model.

[0072] The logic of the water usage priority mechanism is as follows:

[0073] Establish a water usage priority, where the water usage priority is that resident water usage is a high water usage priority and project water usage is a low water usage priority.

[0074] Establish a water usage demand mathematical model, and the mathematical expression of the water usage demand mathematical model:

[0075] ;

[0076] Among them, is the water usage demand weight, is the preset first water usage weight coefficient, is the real-time water consumption data, is the preset second water usage weight coefficient, is the water usage time representative value.

[0077] The first mechanism establishment unit successfully extracted water usage characteristics through in-depth analysis of historical water usage data, including the division and assignment of daily water usage peak periods, off-peak periods, as well as peak seasons and off-peak seasons of water usage, providing a scientific basis for establishing a water usage priority mechanism. It successfully established a water usage priority mechanism, clarified the priorities between residential water usage and project water usage, and through the establishment of a mathematical model, achieved accurate calculation and prediction of water usage demand, providing strong support for the construction of the second prediction model.

[0078] The resident demand analysis module successfully established a water usage priority mechanism by comprehensively collecting and analyzing real-time and historical water usage data of residents and embedded it into the initial prediction model to form a more refined second prediction model. This module not only improves the scientific nature of decision-making in water conservancy project construction but also ensures the priority of residential water usage, effectively balancing the relationship between residential domestic water usage and project construction water usage, and achieving the rational allocation and utilization of water resources.

[0079] The worker status analysis module includes a worker data collection unit and a second mechanism establishment unit.

[0080] The worker data collection unit is used to collect real-time physiological data and historical physiological data of workers. The real-time physiological data includes real-time heart rate data, real-time blood oxygen saturation data, and real-time status time data corresponding to the real-time heart rate data and real-time blood oxygen saturation data. The historical physiological data includes historical heart rate data, historical blood oxygen saturation data, and historical status time data corresponding to the historical heart rate data and historical blood oxygen saturation data.

[0081] The worker data collection unit collected real-time and comprehensive key physiological data of workers such as heart rate and blood oxygen saturation, as well as the time stamps corresponding to these data, providing detailed data support for accurately evaluating the physical status of workers. At the same time, it also collected the historical physiological data of workers, providing a rich information basis for in-depth analysis of the changing trends and laws of the physical status of workers.

[0082] The second mechanism establishment unit is used to extract the characteristics of historical physiological data. The characteristics of the historical physiological data include dividing the historical heart rate data and historical blood oxygen saturation data into fatigue status and normal status according to preset heart rate thresholds and blood oxygen saturation thresholds, establishing a project quantity change mechanism based on the characteristics of the historical physiological data, and embedding the project quantity change mechanism into the initial prediction model to obtain a third prediction model.

[0083] The logic of the project quantity change mechanism is as follows:

[0084] If the number of historical physiological data with the characteristic of fatigue status is within the preset high fatigue total number threshold, the project quantity is reduced by the first percentage.

[0085] If the number of historical physiological data with normal characteristics is within the preset threshold of the total number of low-fatigue workers, the engineering quantity remains unchanged.

[0086] Obtain the worker information with the characteristic of fatigue state in historical physiological data and the worker information with the characteristic of normal state in historical physiological data, output as the worker information in fatigue state and the worker information in normal state, send a rest signal to the worker corresponding to the worker information in fatigue state, and send a signal to increase work to the worker corresponding to the worker information in normal state.

[0087] The second mechanism establishment unit successfully divides the historical physiological data into the fatigue state and the normal state based on the preset heart rate threshold and blood oxygen saturation threshold, provides a scientific basis for establishing the engineering quantity change mechanism, establishes the engineering quantity change mechanism, can dynamically adjust the engineering quantity according to the physical state of the workers, ensures the project progress, and also protects the physical health of the workers. Through the accurate identification of the physical state of the workers, a rest signal is sent to the workers in the fatigue state, and a signal to increase work is sent to the workers in the normal state, realizing the intelligent management and optimization of the working state of the workers.

[0088] The worker status analysis module successfully establishes an engineering quantity change mechanism based on the physical state of the workers through the comprehensive collection and analysis of real-time and historical physiological data, integrates it into the initial prediction model, and upgrades it to the third prediction model. This not only improves the intelligent level of project management but also can dynamically adjust the engineering quantity according to the real-time physical state of the workers, ensuring the dual optimization of worker health and work efficiency, and effectively preventing potential safety hazards and efficiency decline caused by worker fatigue.

[0089] The data processing and integration module includes a logical integration processing unit and an analysis result acquisition unit.

[0090] The logical integration processing unit is used to integrate the logic of the second prediction model and establish a weight mechanism;

[0091] The weight mechanism is as follows:

[0092] Calculate the demand weight of the water consumption according to the water use priority mechanism to obtain the water use demand weight, and perform a primary calculation on the engineering quantity.

[0093] If the water use demand weight is within the preset first water use demand weight threshold, reduce the engineering quantity by the second percentage.

[0094] If the water use demand weight is within the preset second water use demand weight threshold, the engineering quantity remains unchanged.

[0095] Output the engineering quantity after the primary calculation as the first engineering quantity.

[0096] Take the first engineering quantity as input data and input it into the engineering quantity change mechanism for secondary calculation.

[0097] If the number of historical physiological data with the characteristic of fatigue state is within the preset high fatigue total number threshold, the first project quantity is reduced by the first percentage.

[0098] If the number of historical physiological data with the characteristic of normal state is within the preset low fatigue total number threshold, the first project quantity remains unchanged.

[0099] Output the project quantity after the secondary calculation as the predicted total project quantity.

[0100] Take the predicted total project quantity as input data, input it into the initial prediction model to obtain the completion time data, and output the completion time data as the analysis result.

[0101] The logic integration processing unit successfully integrated the logic of the second prediction model and established a scientific weight mechanism. This mechanism achieved accurate assessment of water consumption by calculating the water demand weight, and based on this, performed a primary calculation on the project quantity, providing basic data for the subsequent secondary calculation. The establishment of the weight mechanism enabled the module to dynamically adjust the project quantity according to the urgency of water demand, ensuring the rationality of the project progress and the effective utilization of water resources.

[0102] The analysis result acquisition unit is used to take the real-time water usage situation data and real-time physiological data as input data, input them into the third prediction model, and obtain the analysis result.

[0103] The analysis result acquisition unit accurately input the real-time water usage situation data and real-time physiological data as input data into the second prediction model, ensuring the objectivity and accuracy of the analysis result. By inputting the project quantity after the primary calculation into the project quantity change mechanism for secondary calculation, it further considered the impact of the physiological state of workers on the project quantity, thus obtaining a predicted total project quantity that is more in line with the actual situation. Finally, taking the predicted total project quantity as input data, input it into the initial prediction model, successfully obtain the completion time data, and output this data as the analysis result, providing strong data support for the decision-making of project management.

[0104] The data processing and integration module realized the comprehensive processing and in-depth integration of the real-time water usage situation data and real-time physiological data through two functional units: logic integration processing and analysis result acquisition. It not only considered the direct impact of water consumption on the project quantity, but also incorporated the physiological state factors of workers, so as to be able to more accurately predict the project quantity and completion time. Through the established weight mechanism and project quantity change mechanism, the module can dynamically adjust the project quantity according to actual needs, ensuring the project progress while fully considering the physical state and water demand of workers, achieving the dual guarantee of resource optimization and worker health.

[0105] The prediction result output module includes an analysis result response unit and a response signal implementation unit.

[0106] The analysis result response unit is used to obtain the analysis result.

[0107] If the completion time data is within the preset qualified completion time threshold, no adjustment signal is sent.

[0108] If the completion time data is within the preset unqualified completion time threshold, an adjustment signal is sent, and the adjustment signal includes increasing the number of workers and increasing the external water storage volume.

[0109] The analysis result response unit can accurately obtain the analysis result, especially the completion time data, providing a reliable basis for subsequent decision-making. By intelligently judging whether the completion time data is within the preset qualified or unqualified completion time threshold, the unit can automatically decide whether to send an adjustment signal, avoiding the delay and error of human intervention. When the completion time does not meet the standard, it can quickly generate an adjustment signal containing information such as increasing the number of workers and increasing the external water storage volume, providing a clear instruction for the response signal implementation unit.

[0110] The response signal implementation unit is used to send the adjustment signal to the notification end to adjust the number of workers and the external water storage volume.

[0111] The response signal implementation unit can quickly receive and analyze the adjustment signal sent by the analysis result response unit to ensure the accuracy and integrity of the information. It can send the adjustment signal to the notification end in a timely manner, such as the project management department, the worker team, or the water resource management department, etc., so that all parties can take action quickly. By adjusting measures such as the number of workers and the external water storage volume, it can effectively shorten the completion time, ensure that the project proceeds according to the plan, and at the same time optimize the resource allocation and improve the overall efficiency.

[0112] The prediction result output module is an efficient and intelligent system component. Through the analysis result response unit and the response signal implementation unit, it realizes the accurate evaluation and timely response to the completion time data, automatically judges whether the completion time meets the standard, and sends an adjustment signal when necessary to ensure that the project can proceed smoothly according to the plan. By adjusting the number of workers and the external water storage volume in real time, the module effectively improves the flexibility and efficiency of project management, providing a strong guarantee for the successful implementation of the project.

[0113] By collecting historical progress data, including daily work progress, total completion volume, construction date, number of personnel, and climate conditions, etc., an initial prediction model is established using these data. This method can make full use of historical experience and provide a reliable basis for project progress prediction.

[0114] Collect the domestic water usage situation of residents and establish a water usage priority mechanism:

[0115] The present invention establishes a water use priority mechanism by collecting real-time and historical water use data of residents. This mechanism can distinguish the priorities between residential water use and project water use, ensuring that project water use is reasonably arranged on the premise that the residential water demand is met. This mechanism improves the water resource utilization efficiency and at the same time ensures that the project progress is not affected by water use restrictions. Embedding the water use priority mechanism into the initial prediction model can dynamically adjust the project progress prediction according to the daily residential water use situation. This dynamic adjustment mechanism makes the prediction results more in line with the actual situation, improving the accuracy and practicality of the prediction. By collecting real-time and historical physiological data of workers, extracting features and establishing a project quantity change mechanism. This mechanism can reflect the fatigue degree and work efficiency of workers, thereby adjusting the construction progress. This method helps to ensure project quality and safety and at the same time avoid construction period delays caused by overwork. Embedding the construction progress change mechanism into the prediction model, comprehensively considering the impact of worker status on the project progress. This comprehensive prediction method makes the model more perfect and can more accurately reflect the actual situation of the project progress. By integrating historical data, residential water use situation and worker status information, the prediction model can be updated in real time, improving the accuracy and reliability of the project progress prediction. This helps decision-makers to timely discover problems and take measures to ensure the smooth progress of the project as planned.

[0116] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 the functions specified in one block or multiple blocks.

[0117] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A water conservancy project progress prediction system based on big data, characterized in that: It includes the initial model building module, resident demand analysis module, worker status analysis module, data processing and integration module and prediction result output module: The initial model building module is used to collect historical progress data and build an initial prediction model; The resident demand analysis module is used to collect the real-time water use data and historical water use data of residents, establish a water use priority mechanism, embed the water use priority mechanism into the initial prediction model, and obtain a second prediction model; The worker status analysis module is used to collect real-time physiological data and historical physiological data of workers, extract features of the real-time physiological data and historical physiological data, establish a construction quantity change mechanism, embed the construction quantity change mechanism into the second prediction model, and obtain a third prediction model; The data processing integration module is used to integrate the logic of the third prediction model, establish a weight mechanism, and input the real-time water usage data and real-time physiological data as input data into the third prediction model to obtain analysis results; The prediction result output module is used to output an adjustment signal according to the analysis result, and send the adjustment signal to the notification end.

2. A water conservancy project progress prediction system based on big data as claimed in claim 1, characterized in that: The initial model building module includes a historical data collection unit and an initial model building unit; The historical data collection unit is used to collect historical progress data, wherein the historical progress data includes daily work progress, total completion amount, construction date, number of personnel and climate conditions; The initial model building unit is used to build an initial prediction model according to historical progress data, the input data of the initial prediction model is the total engineering quantity data, and the output data of the initial prediction model is the completion time data.

3. A water conservancy project progress prediction system based on big data as claimed in claim 2, characterized in that: The logic of the initial prediction model is: The historical progress data is divided into training set, validation set and test set according to the preset division ratio. The training set is used to adjust the parameters of the multivariate linear regression model, and the parameter combination is selected through the validation set. The daily work progress and construction date are used as input data, and the total construction period estimation data is used as output data.

4. A water conservancy project progress prediction system based on big data as claimed in claim 3, characterized in that: The resident demand analysis module includes a resident data collection unit and a first mechanism establishment unit; The resident data collection unit is used to collect real-time water use data and historical water use data of residents, wherein the real-time water use data includes real-time water use time and real-time water consumption data corresponding to the real-time water use time, and the historical water use data includes historical water use time and historical water consumption data corresponding to the historical water use time; The first mechanism establishment unit is used to extract the characteristics of historical water use data, and the characteristics of the historical water use data include dividing the historical water use time into daily water use peak period, daily water use low peak period, water use peak season and water use low peak season according to a preset water use threshold, and assigning values ​​to the daily water use peak period, daily water use low peak period, water use peak season and water use low peak season, and outputting them as representative values ​​of water use time. A water use priority mechanism is established according to the characteristics of the historical water use data, and the water use priority mechanism is embedded in the initial prediction model to obtain a second prediction model.

5. A water conservancy project progress prediction system based on big data as claimed in claim 4, characterized in that: The logic of the water priority mechanism is: Establish water use priorities, where residential water use is a high priority and engineering water use is a low priority; A water demand mathematical model is established, and the mathematical expression of the water demand mathematical model is: ； in, is the water demand weight, is the preset first water use weight coefficient, For real-time water consumption data, is the preset second water use weight coefficient, It is the representative value of water usage time.

6. A water conservancy project progress prediction system based on big data as claimed in claim 5, characterized in that: The worker status analysis module includes a worker data collection unit and a second mechanism establishment unit; The worker data collection unit is used to collect real-time physiological data and historical physiological data of the worker, wherein the real-time physiological data includes real-time heart rate data, real-time blood oxygen saturation data and real-time state time data corresponding to the real-time heart rate data and the real-time blood oxygen saturation data, and the historical physiological data includes historical heart rate data, historical blood oxygen saturation data and historical state time data corresponding to the historical heart rate data and the historical blood oxygen saturation data; The second mechanism establishing unit is used to extract the characteristics of historical physiological data, and the characteristics of the historical physiological data include dividing the historical heart rate data and the historical blood oxygen saturation data into fatigue state and normal state according to preset heart rate thresholds and blood oxygen saturation thresholds, establishing an engineering quantity change mechanism according to the characteristics of the historical physiological data, embedding the engineering quantity change mechanism into the initial prediction model, and obtaining a third prediction model.

7. A water conservancy project progress prediction system based on big data as claimed in claim 6, characterized in that: The logic of the engineering quantity change mechanism is: If the number of historical physiological data characterized as fatigue status is within a preset high fatigue total number threshold, reducing the engineering workload by a first percentage; If the historical physiological data is characterized by the number of historical physiological data in a normal state being within the preset low fatigue total number threshold, the engineering workload remains unchanged; The worker information whose historical physiological data is characterized by fatigue state and the worker information whose historical physiological data is characterized by normal state are obtained, and the information is output as fatigue state worker information and normal state worker information. A rest signal is sent to the worker corresponding to the fatigue state worker information, and an increase work signal is sent to the worker corresponding to the normal state worker information.

8. A water conservancy project progress prediction system based on big data as claimed in claim 7, characterized in that: The data processing integration module includes a logic integration processing unit and an analysis result acquisition unit; The logic integration processing unit is used to integrate the logic of the second prediction model and establish a weight mechanism; The analysis result acquisition unit is used to input the real-time water use data and the real-time physiological data as input data into the third prediction model to obtain the analysis result.

9. A water conservancy project progress prediction system based on big data as claimed in claim 8, characterized in that: The weighting mechanism is: Calculate the water demand weight according to the water use priority mechanism, obtain the water demand weight, and calculate the engineering quantity once; If the water demand weight is at a preset first water demand weight threshold, the engineering quantity is reduced by a second percentage; If the water demand weight is within the preset second water demand weight threshold, the project quantity remains unchanged; Output the engineering quantity calculated once as the first engineering quantity; The first engineering quantity is used as input data and input into the engineering quantity change mechanism for secondary calculation; If the number of historical physiological data characterized as fatigue status is within a preset high fatigue total number threshold, reducing the first engineering quantity by a first percentage; If the characteristic of the historical physiological data is that the number of historical physiological data in a normal state is within the preset low fatigue total number threshold, the first engineering quantity remains unchanged; Output the engineering quantity after secondary calculation as the predicted total engineering quantity; The predicted total engineering quantity is used as input data and input into the initial prediction model to obtain the completion time data, which is then output as the analysis result.

10. A water conservancy project progress prediction system based on big data as claimed in claim 9, characterized in that: The prediction result output module includes an analysis result response unit and a response signal implementation unit; The analysis result response unit is used to obtain the analysis result; If the completion time data is within the preset qualified completion time threshold, no adjustment signal is issued; If the completion time data is within the preset unqualified completion time threshold, an adjustment signal is issued, and the adjustment signal includes increasing the number of workers and increasing the external water storage; The response signal implementation unit is used to send an adjustment signal to the notification end to adjust the number of workers and the external water storage capacity.

Images