Project progress prediction method and device based on AIoT and storage medium

Abstract

The invention relates to an AIoT-based project progress prediction method and device and a storage medium, and the method comprises the steps: obtaining a target construction range of a to-be-predicted project and a progress impact factor of a first historical time period, the progress influence factors comprise project progress, target project amount, working states of equipment in the first type of equipment, energy data, position data and state time of the equipment in each working state; determining the effective working time of the first type of equipment according to the working state of the equipment in the first type of equipment and the state time of the equipment in each working state; determining energy consumption data of the first type of equipment according to the energy data of the equipment in the first type of equipment; determining an actual construction range according to the position data of each piece of equipment; and inputting the target construction range, the actual construction range and the project progress of the plurality of historical time periods and the effective working time and the energy consumption data of each type of equipment into a preset model for iteration so as to predict the project progress based on AIoT.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically to an AIoT-based method, device, and storage medium for predicting project progress. Background Technology

[0002] Project schedule forecasting is a core component of full-cycle project management. Its core value lies in proactively controlling schedule risks, optimizing resource allocation, and ensuring project objectives are achieved. Currently, during project implementation, data collection is often delayed and inefficient. Construction data is primarily recorded manually by on-site personnel and then reported up the chain of command to the management platform. Data goes through multiple stages from collection to decision-makers, often resulting in a time lag of several days. There is a lack of effective mechanisms for integrating multi-source data, and various construction-related information is scattered across different departments and independent systems, forming "information silos." This hinders centralized data integration and unified analysis, further reducing data availability. This forecasting method relies heavily on the construction experience of management personnel, failing to fully consider the complex logical relationships between work processes. The overly simplistic forecasting models lead to low accuracy and reliability, failing to provide effective support for project decision-making and easily causing resource waste and schedule derailment. Summary of the Invention

[0003] In view of this, the present invention provides a method, device and storage medium for predicting project progress based on Internet of Things (AIoT, Artificial Intelligence of Things) to solve the problem of low accuracy in project progress prediction.

[0004] In a first aspect, the present invention provides an AIoT-based method for predicting project progress, comprising:

[0005] Obtain the target construction scope of the project to be predicted, as well as the progress influencing factors of the first historical time period. The progress influencing factors include: the working status of at least one piece of equipment in the first category of equipment, the state time of the equipment in each working status, the energy data of the equipment, the location data of the equipment, the project progress of the first historical time period, and the target project quantity of the project to be predicted. The first historical time period is any one of multiple historical time periods, and the first category of equipment is any one of the multiple categories of equipment constructed within the first historical time period.

[0006] Aggregate the working status of at least one device in the first category of devices, as well as the state time of the device in each working status, to determine the effective working time of the first category of devices.

[0007] The energy consumption data of the first category of equipment is determined based on the energy data of at least one of the first category of equipment.

[0008] The actual construction area is determined based on the location data of each piece of equipment;

[0009] The target construction area, actual construction area, project progress, effective working time and energy consumption data for each type of equipment corresponding to multiple historical time periods are input into the AIoT model for iteration to obtain at least one prediction result.

[0010] The AIoT model is used to predict the project progress for the next time period based on at least one prediction result.

[0011] This method obtains the target construction scope of the project to be predicted, as well as the progress influencing factors for the first historical time period. These progress influencing factors include: the working status of at least one piece of equipment in the first category, the state time of each working status, the equipment's energy data, the equipment's location data, the project progress for the first historical time period, and the target workload of the project to be predicted. The working status of at least one piece of equipment in the first category and the state time of each working status are aggregated to determine the effective working time of the first category of equipment. Based on the energy data of at least one piece of equipment in the first category, the energy consumption data of the first category of equipment is determined. Based on the location data of each piece of equipment, the actual construction scope is determined. The target construction scope, actual construction scope, project progress, and the effective working time and energy consumption data for each category of equipment for multiple historical time periods are input into the AIoT model for iteration to obtain at least one prediction result. The AIoT model is then used to predict the project progress for the next time period based on at least one prediction result. This method allows for timely acquisition of various construction data, timely data integration and processing, and analysis and prediction through the model. It avoids the problems of insufficient data consideration and low prediction accuracy when using manual prediction, thus improving the timeliness and accuracy of predictions.

[0012] In one optional implementation, the working state of at least one device in the first type of devices, and the state time of the device in each working state, are aggregated to determine the effective working time of the first type of devices, including:

[0013] Filter out the valid working status from all working statuses of at least one device;

[0014] Aggregate the state times corresponding to all valid working states to determine the individual valid working time of the first device.

[0015] The sum of the individual effective working times of each device in the first category is taken as the effective working time of the first category of devices.

[0016] In one optional implementation, the energy data includes: initial energy data, replenishment energy data, and termination energy data. Based on the energy data of at least one device in the first category of devices, the energy consumption data of the first category of devices is determined, including:

[0017] Based on the initial energy data, replenishment energy data and termination energy data corresponding to at least one device, determine the individual energy consumption data corresponding to each device.

[0018] Based on the individual energy consumption data of all devices in the first category, determine the energy consumption data of the first category of devices.

[0019] In one optional implementation, the location data includes: the initial latitude and longitude of the first device at multiple time points within a first historical time period, and the initial location weights corresponding to the first type of device. Based on the location data of each device, the actual construction area is determined, including:

[0020] Determine the quantity of Category I equipment;

[0021] The first transition weight corresponding to the first type of equipment is determined based on the number of first type of equipment and the initial position weight corresponding to the first type of equipment.

[0022] Compare the transition weights corresponding to all types of devices, and determine the target weights corresponding to each type of device based on the comparison results;

[0023] The initial latitude and longitude values ​​collected within the first historical time period are rounded up at a first preset interval to obtain the intermediate latitude and longitude values ​​corresponding to each initial latitude and longitude value.

[0024] The target weight corresponding to the device type of the device that collected the first initial latitude and longitude is used as the target weight of the first intermediate latitude and longitude. The first initial latitude and longitude is any one of the initial latitude and longitude collected in the first historical time period, and the first intermediate latitude and longitude is the intermediate latitude and longitude corresponding to the first initial latitude and longitude.

[0025] The sum of the target weights corresponding to each identical intermediate latitude and longitude is taken as the total weight value of the intermediate latitude and longitude.

[0026] All intermediate latitude and longitude coordinates are filtered according to the total weight value to obtain the target latitude and longitude set;

[0027] The actual construction area is determined based on the coverage of the target latitude and longitude set.

[0028] In one optional implementation, when the device types include two categories, the transition weights include a first transition weight corresponding to the first category of devices and a second transition weight corresponding to the second category of devices. All transition weights are compared, and a target weight corresponding to each category of devices is determined based on the comparison results, including:

[0029] When the first transition weight is less than the second transition weight, the first transition weight is used as the first target weight corresponding to the first type of equipment.

[0030] The second transition weight is used as the second target weight corresponding to the second type of equipment;

[0031] or,

[0032] When the first transition weight is greater than or equal to the second transition weight, the third transition weight is determined based on the first initial position weight, the first transition weight, and the second transition weight.

[0033] The third transition weight is used as the first target weight corresponding to the first type of equipment;

[0034] The second transition weight is used as the second target weight corresponding to the second type of equipment.

[0035] In one optional implementation, a third transition weight is determined based on a first initial position weight, a first transition weight, and a second transition weight, specifically including:

[0036]

[0037] in, As the first transition weight, For the number of Class I equipment, The initial position weights are for the first type of equipment.

[0038] In one optional implementation, the actual construction area for the first historical time period is determined based on the latitude and longitude of all time points, including:

[0039] Select multiple target latitude and longitude coordinates from all time points;

[0040] Perform coordinate mapping operations on multiple target latitude and longitude coordinates to obtain planar coordinates;

[0041] Perform sampling operations at preset intervals in planar coordinates to obtain multiple sampling points;

[0042] The actual construction area is obtained by performing inverse coordinate transformation on multiple sampling points.

[0043] Secondly, the present invention provides an AIoT-based engineering progress prediction device, comprising:

[0044] The acquisition module is used to acquire the target construction scope of the project to be predicted, as well as the progress influencing factors of the first historical time period. The progress influencing factors include: the working status of at least one piece of equipment in the first type of equipment, the state time of the equipment in each working status, the energy data of the equipment, the location data of the equipment, the project progress of the first historical time period, and the target project quantity of the project to be predicted. The first historical time period is any one of multiple historical time periods, and the first type of equipment is any one of the multiple types of equipment constructed within the first historical time period.

[0045] The aggregation module is used to aggregate the working status of at least one device in the first type of devices, as well as the state time of the device in each working status, to determine the effective working time of the first type of devices.

[0046] The first determining module is used to determine the energy consumption data of the first type of equipment based on the energy data of at least one of the first type of equipment.

[0047] The second determining module is used to determine the actual construction area based on the location data of each piece of equipment;

[0048] The iteration module is used to input the target construction scope, actual construction scope, project progress, effective working time and energy consumption data corresponding to each type of equipment into the AIoT model for iteration, and obtain at least one prediction result.

[0049] The prediction module is used to predict the project progress results for the next time period based on at least one prediction result using an AIoT model.

[0050] In one alternative implementation, the aggregation module includes...

[0051] The first filtering submodule is used to filter out valid working states from all working states of at least one device;

[0052] The aggregation submodule is used to aggregate the state times corresponding to all valid working states to determine the individual valid working time of the first device.

[0053] The first processing submodule is used to take the sum of the individual effective working time of each device in the first type of equipment as the effective working time of the first type of equipment.

[0054] In one optional implementation, the energy data includes: initial energy data, supplementary energy data, and termination energy data; the first determining module includes:

[0055] The first determining submodule is used to determine the individual energy consumption data corresponding to each device based on the initial energy data, replenished energy data and termination energy data corresponding to at least one device respectively.

[0056] The second determining submodule is used to determine the energy consumption data of the first type of equipment based on the individual energy consumption data of all equipment in the first type of equipment.

[0057] In one optional implementation, the location data includes: the initial latitude and longitude of the first device at multiple time points in a first historical time period, and the initial location weights corresponding to the first type of device; the second determination module includes:

[0058] The third determining submodule is used to determine the number of the first type of equipment; and to determine the first transition weight corresponding to the first type of equipment based on the number of the first type of equipment and the initial position weight corresponding to the first type of equipment.

[0059] The first comparison submodule is used to compare the transition weights corresponding to all types of devices and determine the target weights corresponding to each type of device based on the comparison results.

[0060] The rounding submodule is used to perform rounding operations on the initial latitude and longitude collected within the first historical time period at a first preset interval to obtain the intermediate latitude and longitude corresponding to each initial latitude and longitude value.

[0061] The second processing submodule is used to take the target weight corresponding to the device type of the device that collected the first initial latitude and longitude as the target weight of the first intermediate latitude and longitude, wherein the first initial latitude and longitude is any one of the initial latitude and longitude collected within the first historical time period, and the first intermediate latitude and longitude is the intermediate latitude and longitude corresponding to the first initial latitude and longitude; and to take the sum of the target weights corresponding to each identical intermediate latitude and longitude as the total weight value of the intermediate latitude and longitude.

[0062] The second filtering submodule is used to filter all intermediate latitude and longitude according to the total weight value to obtain the target latitude and longitude set;

[0063] The fourth submodule is used to determine the actual construction area based on the coverage of the target latitude and longitude set.

[0064] In an optional implementation, when the device types include two categories, the transition weight includes a first transition weight corresponding to the first type of device and a second transition weight corresponding to the second type of device. The first comparison submodule includes:

[0065] The third processing submodule is used to, when the first transition weight is less than the second transition weight, take the first transition weight as the first target weight corresponding to the first type of device; and take the second transition weight as the second target weight corresponding to the second type of device.

[0066] or,

[0067] The fourth processing submodule is used to determine the third transition weight based on the first initial position weight, the first transition weight, and the second transition weight when the first transition weight is greater than or equal to the second transition weight; to use the third transition weight as the first target weight corresponding to the first type of device; and to use the second transition weight as the second target weight corresponding to the second type of device.

[0068] In one alternative implementation, the second processing submodule is specifically used for:

[0069]

[0070] in, As the first transition weight, For the number of Class I equipment, The initial position weights are for the first type of equipment.

[0071] In one alternative implementation, the fifth determining submodule includes:

[0072] The third filtering submodule is used to filter out multiple target latitude and longitude coordinates from all time points;

[0073] The mapping submodule is used to perform coordinate mapping operations on multiple target latitude and longitude coordinates to obtain planar coordinates;

[0074] The sampling submodule allows users to perform sampling operations at preset intervals in a planar coordinate system to obtain multiple sampling points.

[0075] The reverse coordinate transformation submodule is used to perform reverse coordinate transformation on multiple sampling points to obtain the actual construction range.

[0076] This method obtains the target construction scope of the project to be predicted, as well as the progress influencing factors for the first historical time period. These progress influencing factors include: the working status of at least one piece of equipment in the first category, the state time of each working status, the equipment's energy data, the equipment's location data, the project progress for the first historical time period, and the target workload of the project to be predicted. The working status of at least one piece of equipment in the first category and the state time of each working status are aggregated to determine the effective working time of the first category of equipment. Based on the energy data of at least one piece of equipment in the first category, the energy consumption data of the first category of equipment is determined. Based on the location data of each piece of equipment, the actual construction scope is determined. The target construction scope, actual construction scope, project progress, and the effective working time and energy consumption data for each category of equipment for multiple historical time periods are input into the AIoT model for iteration to obtain at least one prediction result. The AIoT model is then used to predict the project progress for the next time period based on at least one prediction result. This method allows for timely acquisition of various construction data, timely data integration and processing, and analysis and prediction through the model. It avoids the problems of insufficient data consideration and low prediction accuracy when using manual prediction, thus improving the timeliness and accuracy of predictions.

[0077] Thirdly, the present invention provides a computer device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the AIoT-based engineering progress prediction method described in the first aspect or any corresponding embodiment thereof.

[0078] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the AIoT-based engineering progress prediction method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0079] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0080] Figure 1 This is a flowchart illustrating an AIoT-based engineering progress prediction method according to an embodiment of the present invention.

[0081] Figure 2This is a flowchart illustrating another AIoT-based engineering progress prediction method according to an embodiment of the present invention.

[0082] Figure 3 This is a flowchart illustrating another AIoT-based engineering progress prediction method according to an embodiment of the present invention;

[0083] Figure 4 This is a system-level data flow diagram of an AIoT-based engineering progress prediction method according to an embodiment of the present invention;

[0084] Figure 5 This is a GPS point range map of the project according to an embodiment of the present invention;

[0085] Figure 6 This is a GPS point range map of the current construction according to an embodiment of the present invention;

[0086] Figure 7 This is a schematic diagram of an AIoT model iteration method according to an embodiment of the present invention;

[0087] Figure 8 This is a structural block diagram of an AIoT-based engineering progress prediction device according to an embodiment of the present invention;

[0088] Figure 9 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0089] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0090] To address the issues of poor timeliness and low accuracy in manually predicting project progress, this invention provides an embodiment of an AIoT-based project progress prediction method. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0091] This embodiment provides an AIoT-based project progress prediction method, which can be used with the aforementioned computer equipment. Figure 1 This is a flowchart of an AIoT-based engineering progress prediction method according to an embodiment of the present invention, as shown below. Figure 1As shown, the process includes the following steps:

[0092] Step S101: Obtain the target construction scope of the project to be predicted, and the progress influencing factors of the first historical time period. The progress influencing factors include: the working status of at least one piece of equipment in the first type of equipment, the state time of the equipment in each working status, the energy data of the equipment, the location data of the equipment, the project progress of the first historical time period, and the target project quantity of the project to be predicted.

[0093] Specifically, the first historical time period is any one of multiple historical time periods, and the first type of equipment is any one of multiple types of equipment constructed within the first historical time period.

[0094] The target construction scope of the project to be predicted can be obtained by obtaining a project map from the project planning and project plan of the project to be predicted, and by performing a Global Positioning System (GPS) mapping operation on the project map, the target construction scope of the project to be predicted can be obtained.

[0095] In one optional implementation, multiple latitude and longitude values ​​are selected from the coordinates obtained by GPS mapping. For example, a polygon is drawn along the edge of the project construction area, and the latitude and longitude inside the polygon are mapped to planar coordinates. The coordinates are then rounded to the nearest 10-meter interval to generate a grid or sampling points, and then the GPS latitude and longitude are calculated back to obtain the GPS construction area of ​​the project.

[0096] In one optional example, the historical time period can be a past year, month, week, day, or hour, etc., which can be set according to the actual situation.

[0097] In one alternative example, project construction typically involves multiple types of machinery and equipment, with each type of machinery and equipment potentially consisting of multiple units, such as excavators and bulldozers. Positioners, oil level sensors, and other tools are installed on each piece of equipment to collect real-time or periodic data on the equipment's location and oil level. The energy source can be fuel, electricity, or other energy sources.

[0098] In an optional example, the daily operating status of each device and the operating time of the device in that operating status are recorded. The operating status can be a stationary state, an idling state, or a high-speed operating state, etc.

[0099] The target quantity of work can be obtained from the bill of quantities.

[0100] Project progress over a historical period can be estimated. For example, the project progress over a historical period can be obtained by comparing the construction area of ​​the project with the total construction area.

[0101] Step S102: Aggregate the working status of at least one device in the first type of devices and the state time of the device in each working status to determine the effective working time of the first type of devices.

[0102] Specifically, the equipment can be categorized, such as excavators and bulldozers. Effective working states can be selected from the working states of a single excavator. The effective working hours of that excavator can be obtained by combining the time spent in the effective working state. Then, the effective working hours of all excavators can be aggregated to obtain the effective working time of the excavator equipment.

[0103] In an optional implementation, different weights can be assigned to various effective working states. For example, a higher weight can be assigned to high-level working states and a lower weight can be assigned to low-level working states, so that the final effective working time can be more accurate.

[0104] Step S103: Determine the energy consumption data of the first type of equipment based on the energy data of at least one of the first type of equipment.

[0105] Specifically, energy consumption data for a single device can be obtained by monitoring changes in the energy data of that device. Then, by integrating the energy consumption data of all devices in a category, the energy consumption data for that category of devices can be obtained.

[0106] Step S104: Determine the actual construction area based on the location data of each piece of equipment.

[0107] Specifically, the location data of each device is obtained within a historical time period, that is, multiple location information of the device within a historical time period is determined, and the location information of all devices within this historical time period is integrated to obtain the actual construction scope.

[0108] In an optional example, the actual construction area can be calculated based on the latitude and longitude values ​​of the four furthest corners (e.g., northwest, northeast, southwest, and southeast) from the GPS latitude and longitude data uploaded from all devices.

[0109] Step S105: Input the target construction scope, actual construction scope, project progress, effective working time and energy consumption data corresponding to each type of equipment for multiple historical time periods into AIoT for iteration to obtain at least one prediction result.

[0110] Specifically, the target construction scope, actual construction scope, project progress, effective working time and energy consumption data for each type of equipment corresponding to multiple historical time periods are input into AIoT for iteration, the number of output results is set, and at least one prediction result is obtained.

[0111] Step S106: Use the AIoT model to predict the project progress result for the next time period based on at least one prediction result.

[0112] Specifically, in an optional example, each prediction result output by the AIoT model can be assigned a corresponding weight, and the project progress can be predicted based on all prediction results and their respective weights.

[0113] In an optional example, the prediction results include a first prediction result corresponding to working hours, a second prediction result corresponding to fuel consumption, and a third prediction result corresponding to the construction scope, with the schedule weight of the first prediction result set to [value missing]. The progress weight value of the second prediction result is The progress weight value of the third prediction result is Assuming the first prediction result is The second prediction result is The third prediction result is ,but .

[0114] The AIoT-based project progress prediction method provided in this embodiment obtains the target construction area of ​​the project to be predicted, as well as the progress influencing factors for a first historical time period. The progress influencing factors include: the working status of at least one device in the first type of equipment, the state time of each device in its various working states, the energy data of the device, the location data of the device, the project progress for the first historical time period, and the target project quantity. The method aggregates the working status of at least one device in the first type of equipment and the state time of each device in its various working states to determine the effective working time of the first type of equipment. Based on the energy data of at least one device in the first type of equipment, the method determines the energy consumption data of the first type of equipment. Based on the location data of each device, the method determines the actual construction area. The method inputs the target construction area, actual construction area, project progress, and the effective working time and energy consumption data corresponding to each type of equipment for multiple historical time periods into an AIoT model for iteration to obtain at least one prediction result. Finally, the method uses the AIoT model to predict the project progress for the next time period based on at least one prediction result. It can obtain various construction data in a timely manner, and integrate and process the data promptly. Through model analysis and prediction, it avoids the problems of untimely data acquisition, insufficient data consideration, and low prediction accuracy when the logic is complex, thus improving the timeliness and accuracy of prediction.

[0115] This embodiment provides an AIoT-based project progress prediction method, which can be used with the aforementioned computer equipment. Figure 2 This is a flowchart of an AIoT-based engineering progress prediction method according to an embodiment of the present invention, as shown below. Figure 2As shown, the process includes the following steps:

[0116] Step S201: Obtain the target construction scope of the project to be predicted, and the progress influencing factors for the first historical time period. The progress influencing factors include: the operating status of at least one piece of equipment in the first category, the state time of the equipment in each operating status, the equipment's energy data, the equipment's location data, the project progress for the first historical time period, and the target project quantity for the project to be predicted. For details, please refer to [link to details]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0117] Step S202: Aggregate the working status of at least one device in the first type of devices and the state time of the device in each working status to determine the effective working time of the first type of devices.

[0118] Specifically, step S202 includes:

[0119] Step S2021: Filter out the valid working status from all working statuses of at least one device.

[0120] Specifically, the effective working status is determined from all working statuses.

[0121] In one optional example, the state of engineering equipment is divided into three main categories: working, idling, and stationary.

[0122] When in working condition, the power system of the engineering equipment outputs effective power to drive the execution equipment to complete the specified work tasks. Typical scenarios include excavators digging and loading trucks, loaders shoveling and transporting materials, and cranes lifting heavy objects. Its operating characteristics include: the engine speed is in the medium to high speed range, fuel consumption is high, and the equipment exhibits obvious working movements. Sub-states include driving (transportation equipment), rotating (cement mixer truck), high-level operation (construction equipment), and low-level operation (construction equipment), etc. The time when the equipment is in the working state is usually defined as the effective working time.

[0123] When idling, the engineering equipment has no work tasks, and the power system has no effective power output. Typical scenarios include waiting for instructions during work breaks, preheating after equipment startup, and preparation stages. The operating characteristics are that the engine idles at the lowest stable speed, resulting in low fuel consumption.

[0124] When stationary, the engine is completely stopped, the equipment is not operating, and it is in a parked state.

[0125] You can use the working state as the effective working state, or you can use each sub-state of the working state as the effective working state. You can set it according to the actual situation.

[0126] Step S2022: Aggregate the state times corresponding to all valid working states to determine the individual valid working time of the first device.

[0127] In an optional example, we define high-level and low-level work as effective working states, with a weight of 1 for high-level work and a weight of 0.8 for low-level work. The duration of high-level work is 10 minutes, and the duration of low-level work is 10 minutes. Then, the individual effective working time of this excavator is: minute.

[0128] Step S2023: The sum of the individual effective working times corresponding to each device in the first type of equipment is taken as the effective working time of the first type of equipment.

[0129] Step S203: Determine the energy consumption data of the first type of equipment based on the energy data of at least one of the first type of equipment. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0130] Step S204: Determine the actual construction area based on the location data of each piece of equipment. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0131] Step S205 involves inputting the target construction area, actual construction area, project progress, and effective working time and energy consumption data for each type of equipment across multiple historical time periods into the AIoT model for iteration, yielding at least one prediction result. For details, please refer to [link to relevant documentation]. Figure 1 Step S105 of the illustrated embodiment will not be described again here.

[0132] Step S206: Utilize the AIoT model to predict the project progress for the next time period based on at least one prediction result. See details below. Figure 1 Step S106 of the illustrated embodiment will not be described again here.

[0133] In one optional implementation, the energy data includes: initial energy data, supplementary energy data, and termination energy data, and step S103 includes:

[0134] Step a1: Based on the initial energy data, replenishment energy data and termination energy data corresponding to at least one device, determine the individual energy consumption data corresponding to each device.

[0135] Specifically, individual energy consumption data can be represented by Formula 1:

[0136] (Formula 1)

[0137] in, Individual energy consumption data, For initial energy data, To supplement energy data, To terminate energy data.

[0138] Step a2: Determine the energy consumption data of the first category of devices based on the individual energy consumption data of all devices in the first category of devices.

[0139] Specifically, the sum of all individual energy consumption data in the first category of devices can be used as the energy consumption data of the first category of devices.

[0140] This embodiment provides an AIoT-based project progress prediction method, which can be used in the aforementioned mobile terminals, such as computer devices. Figure 3 This is a flowchart of an AIoT-based engineering progress prediction method according to an embodiment of the present invention, as shown below. Figure 3 As shown, the process includes the following steps:

[0141] Step S301: Obtain the target construction scope of the project to be predicted, and the progress influencing factors of the first historical time period. The progress influencing factors include: the working status of at least one piece of equipment in the first type of equipment, the state time of the equipment in each working status, the energy data of the equipment, the location data of the equipment, the project progress of the first historical time period, and the target project quantity of the project to be predicted.

[0142] Please see details Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0143] Step S302: Aggregate the operating status of at least one device in the first category of devices, and the time spent in each operating status, to determine the effective operating time of the first category of devices. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0144] Step S303: Determine the energy consumption data of the first type of equipment based on the energy data of at least one of the first type of equipment. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0145] Step S304: Determine the actual construction area based on the location data of each piece of equipment.

[0146] Specifically, the location data includes: the longitude and latitude values ​​of the first device at multiple time points in the first historical time period, and the initial location weights corresponding to the first type of device. Step S304 above includes:

[0147] Step S3041: Determine the number of the first type of equipment.

[0148] Step S3042: Determine the first transition weight corresponding to the first type of equipment based on the number of first type of equipment and the initial position weight corresponding to the first type of equipment.

[0149] Specifically, initial position weights are set based on the degree of influence of each type of equipment on the actual construction location. For example, construction equipment has a small movement range and more accurately reflects the actual construction location, so its initial position weight can be set to 1.5. Transportation equipment, on the other hand, has a large movement range and is prone to deviating from the actual construction location during transportation, so its initial position weight can be set to 0.5. However, if there are too many transportation equipment, their total weight may exceed that of construction equipment, which is not conducive to determining the true construction location. Therefore, it is necessary to adjust the position weights of each type of equipment according to the quantity of each type, that is, to calculate the transition weights for each type of equipment.

[0150] In an optional example, the first transition weight can be represented by Equation 2:

[0151] (Formula 2)

[0152] in, As the first transition weight, For the number of Class I equipment, The initial position weights are for the first type of equipment.

[0153] For example, if there are 5 construction machines, then the transition weight of the construction machines is: .

[0154] Step S3043: Compare the transition weights corresponding to all types of devices, and determine the target weight corresponding to each type of device based on the comparison results.

[0155] Specifically, in order to more accurately locate the actual construction location, the transition weight of equipment types that have a greater impact on the actual construction location should be greater than the transition weight of equipment types that have a smaller impact. For example, the transition weight of construction equipment should be greater than the transition weight of transportation equipment. When the transition weight of construction equipment is less than the transition weight of transportation equipment, the target weight of each type of equipment should be reset.

[0156] In an optional example, when the device types include two categories, the transition weight includes a first transition weight corresponding to the first category of devices and a second transition weight corresponding to the second category of devices. Step S3043 above includes:

[0157] When the first transition weight is less than the second transition weight, the first transition weight is used as the first target weight corresponding to the first type of equipment.

[0158] The second transition weight is used as the second target weight corresponding to the second type of equipment.

[0159] Specifically, in an optional example, when the transition weight of transportation equipment is less than the weight of construction equipment, the initial position weight remains unchanged, and the initial position weight can be used as the target weight for each type of equipment.

[0160] or,

[0161] When the first transition weight is greater than or equal to the second transition weight, the third transition weight is determined based on the first initial position weight, the first transition weight, and the second transition weight.

[0162] Specifically, the second transition weight is first calculated, which can be represented by Formula 3:

[0163] (Formula 3)

[0164] in, As the second transition weight, For the number of Class II equipment, The initial position weights are for the second type of equipment.

[0165] The third transition weight can be represented by Formula 4:

[0166] (Formula 4)

[0167] in, As the third transition weight, The initial position weights are for the first type of equipment. As the first transition weight, This is the second transition weight.

[0168] The third transition weight is used as the first target weight corresponding to the first type of equipment;

[0169] The second transition weight is used as the second target weight corresponding to the second type of equipment.

[0170] In an optional example, if there are 20 transport devices and 5 construction devices, then the weight of the construction devices... Smaller than transportation equipment Adjust the weight of construction equipment The weight of transportation equipment remains at 0.5.

[0171] Step S3044: The initial latitude and longitude values ​​collected within the first historical time period are rounded up at a first preset interval to obtain the intermediate latitude and longitude values ​​corresponding to each initial latitude and longitude value.

[0172] Specifically, the preset interval can be 10 meters. Each initial latitude and longitude is rounded up every 10 meters. The intermediate latitude and longitude corresponding to the initial latitude and longitude can be rounded up or down. The specific rounding method should be the same as the rounding method of the total construction scope of the project.

[0173] Step S3045: Use the target weight corresponding to the device type of the device that collected the first initial latitude and longitude as the target weight of the first intermediate latitude and longitude.

[0174] Specifically, the first initial latitude and longitude is any one of the initial latitude and longitudes collected within the first historical time period, and the first intermediate latitude and longitude is the intermediate latitude and longitude corresponding to the first initial latitude and longitude. In an optional example, for instance, if the target weight corresponding to the excavator is 1.5, then the target weight corresponding to all the collected latitude and longitudes of the excavator is 1.5.

[0175] The following example uses the dump truck positioning data in Table 1 and the excavator positioning data in Table 2.

[0176] In one optional example, the location data for dump trucks 21 to 25 are shown in Table 1:

[0177]

[0178] (Table 1)

[0179] The positioning data of excavators No. 1 to No. 5 are shown in Table 2:

[0180]

[0181] (Table 2)

[0182] The GPS latitude and longitude (rounded) and weights for the time point 17:26:25 are summarized in Table 3:

[0183]

[0184] (Table 3)

[0185] Step S3046: The sum of the target weights corresponding to each identical intermediate latitude and longitude is taken as the total weight value of the intermediate latitude and longitude.

[0186] Specifically, as shown in Table 3, the total weight of latitude and longitude (117.787928, 35.783827) is...

[0187] By summing up the target weights of all rounded latitude and longitude coordinates for this historical period, we obtain the data in Table 4, as follows:

[0188]

[0189] (Table 4)

[0190] Step S3047: Filter all intermediate latitude and longitude coordinates according to the total weight value to obtain the target latitude and longitude set.

[0191] Specifically, in an optional example, GPS points with excessively low weights in the first historical time period can be discarded. The discard rule is that the total weight is less than a threshold of 1, and these points are used as the latitude and longitude information for the first historical time period. The filtering rules can be limited according to the actual situation.

[0192] Step S3048: Determine the actual construction area based on the coverage of the target latitude and longitude set.

[0193] Specifically, lines can be drawn along the edges of the target latitude and longitude; the load range within the lines is the actual construction area.

[0194] In an optional example, step S3048 above includes:

[0195] Step b1: Select multiple target latitude and longitude coordinates from all time points.

[0196] Step b2 involves performing a coordinate mapping operation on the latitude and longitude of multiple targets to obtain planar coordinates.

[0197] Step b3 involves performing sampling operations at preset intervals in planar coordinates to obtain multiple sampling points.

[0198] Step b4 involves performing a reverse coordinate transformation on multiple sampling points to obtain the actual construction area.

[0199] Specifically, the four corner latitude and longitude coordinates can be selected from the latitude and longitude coordinates of multiple time points, such as the latitude and longitude coordinates of the four directions of east, west, south and north. The four corner latitude and longitude coordinates are mapped to obtain plane coordinates. In the plane coordinates, samples are taken every 10 meters to obtain multiple sampling points. The multiple sampling points are then subjected to inverse coordinate transformation to obtain the actual construction range, that is, the construction range of the GPS points.

[0200] Similarly, by performing coordinate mapping on the target construction area of ​​the project to be predicted, the planar coordinates of the entire project are obtained. By sampling every 10 meters, the construction area of ​​the project's GPS points can be obtained.

[0201] Step S305 involves iteratively processing the target construction area, actual construction area, project progress, and effective working time and energy consumption data for each type of equipment across multiple historical time periods using the AIoT model to obtain at least one prediction result. For details, please refer to [link to relevant documentation]. Figure 1 Step S105 of the illustrated embodiment will not be described again here.

[0202] Step S306: Utilize the AIoT model to predict the project progress for the next time period based on at least one prediction result. See details below. Figure 1 Step S106 of the illustrated embodiment will not be described again here.

[0203] To clarify the AIoT-based project progress prediction method of this invention, a specific application scenario is provided, utilizing an AIoT large-scale model to predict the progress of a road construction project. This system is configured to perform daily progress predictions, and the system's hierarchical data flow diagram is as follows: Figure 4 As shown.

[0204] The data acquisition layer collects data such as the working status, location, and oil level of each device in real time or at regular intervals by equipping each device with positioning terminals and oil level sensors. The core engineering quantity data of the project is obtained through the bill of quantities. The project map can be obtained from the project planning and project plan. The map range is then mapped to GPS and rounded every 10 meters to obtain the GPS point range of the project, which is the target construction range of the project to be predicted. The daily project progress can be estimated based on the actual construction situation.

[0205] The data transmission layer is responsible for transmitting project data, using 4G / 5G networks or other communication methods, such as Message Queuing Telemetry Transport (MQTT) networks. The data processing layer performs data cleaning and processing, including outlier handling and data integration.

[0206] The feature fusion layer is used to extract features from the upper layer data and integrate multi-source data in a unified manner. The prediction model layer is used to train the model on the data and generate prediction progress and risk warning information. The application layer is used to display real-time progress prediction information and risk warning information, etc., so as to make it easy to intuitively obtain the project progress.

[0207] Table 5 shows the operating status of the equipment and the corresponding operating time for each status. This is illustrated using a single unit as an example.

[0208] Table 5 shows the daily working status of Excavator No. 1 and the corresponding working time for each working status:

[0209]

[0210] (Table 5)

[0211] Based on the statistics in Table 5, the effective working status of each device and the corresponding time are calculated. The effective working time of each device in each type of device is then summarized to obtain the effective working time of that type of device.

[0212] The oil volume data is shown in Table 6, using only a single unit as an example:

[0213] The daily fuel consumption data for bulldozer No. 232 is shown in Table 6:

[0214]

[0215] (Table 6)

[0216] According to Table 6, the initial fuel level of bulldozer #232 was 700.1, the final fuel level was 681, and the fuel refueling was 0. Therefore, the fuel consumption data for bulldozer #232 is as follows: .

[0217] Location data is collected using a positioning device; this can be illustrated using a single device as an example:

[0218] The location time-series data for "Dump Truck No. 25" on November 5th is shown in Table 7:

[0219]

[0220] (Table 7)

[0221] By collecting data from various devices at multiple time points, the GPS construction area for the day can be obtained. The specific operation method has been described in detail above and will not be repeated here.

[0222] The bill of quantities is shown in Table 8:

[0223]

[0224] (Table 8)

[0225] Based on all the above data, data feature extraction is performed, including:

[0226] The first type of characteristic is the effective working time characteristic. According to Table 8, the effective working status of each piece of equipment and the time corresponding to the effective working status are counted. The effective working time of each piece of equipment in each type of equipment is summarized to obtain the effective working time of that type of equipment on that day.

[0227] Fuel consumption data characteristics: Formula 1 is used to calculate the daily fuel consumption data of a single device.

[0228] For missing working status data and oil quantity data, interpolation can be used to fill in the gaps.

[0229] Table 9 shows the daily summary of effective working hours and fuel consumption data.

[0230]

[0231] (Table 9)

[0232] The second type of characteristic: The core quantities of the work (the first 3-5 items) are derived from the bill of quantities, as shown in Table 10:

[0233]

[0234] (Table 10)

[0235] Each project is broken down by day to obtain daily project volume data.

[0236] The third type of characteristic: the characteristics of the project's GPS construction scope.

[0237] The project map, obtained from the project plan, is mapped using GPS. The GPS point range for the project is then calculated by rounding down to the nearest 10 meters. Figure 5 As shown. The specific operation method has been described in detail above and will not be repeated here.

[0238] The project's GPS range characteristics are broken down by day to obtain daily GPS range characteristic data.

[0239] The fourth type of feature: Daily project GPS construction scope features.

[0240] The current GPS point range map of the project is obtained by converting the GPS construction scope of the project on that day, such as... Figure 6 As shown, the conversion method must be the same as the method of obtaining the GPS point range map of the entire project, so as to facilitate matching by point count and obtain the project progress.

[0241] The GPS construction area can also be used to generate a GPS heat map using a heat map generation tool. Comparing this heat map with the GPS heat map of the entire project provides a more intuitive understanding of the current construction area and status.

[0242] Optionally, when calculating the construction scope, different weights may be assigned to different types of equipment based on the actual situation (transportation equipment has a larger range of activity, while construction equipment better reflects the current progress of the project, so the latter has a larger weight; the weights can be adjusted according to the actual situation), as shown in Table 11:

[0243]

[0244] (Table 11)

[0245] After obtaining the four types of data features, construct the model input according to Table 12.

[0246]

[0247] (Table 12)

[0248] The input data is shown in Table 13. Here, only one feature from each of the first and second categories is selected. The project progress feature can be estimated based on the daily construction situation. The number of features can be flexibly changed according to the actual project construction situation.

[0249]

[0250] (Table 13)

[0251] Input the data from Table 13 into the model for training. The training set takes the first 70% of the project duration data (e.g., if the project has 180 days, take the first 126 days), the validation set takes the middle 20% of the project duration data (127-162 days), and the test set takes the last 10% of the project duration data (163-180 days).

[0252] The model output results are shown in Table 14:

[0253]

[0254] The data in D5 and D6 in Table 13 are the model output results.

[0255] (Table 14)

[0256] Depending on the actual situation, the model can be set to output multiple prediction results, such as the progress prediction result corresponding to working hours, the progress prediction result corresponding to fuel consumption, and the progress prediction result corresponding to the construction scope. Each prediction result is assigned a corresponding weight value, and the final progress prediction result can be expressed as the following formula 5:

[0257] (Formula 5)

[0258] Where M represents the predicted project schedule, and A represents the project schedule prediction corresponding to the work hours. B represents the weight of the schedule forecast result corresponding to working hours, and B represents the schedule forecast result corresponding to fuel consumption. C represents the weight of the schedule prediction result corresponding to fuel consumption, and C represents the schedule prediction result corresponding to the construction scope. Weights are assigned to the progress forecast results corresponding to the construction scope.

[0259] The system will then synchronize the latest working hours, fuel levels, and GPS range data daily, and retrain the model weekly, adjusting weights as needed. The system will also update the workload per unit working hour (e.g., excavator digging efficiency) quarterly to adapt to changes in machine wear and operating conditions.

[0260] Project engineering work mode such as Figure 7As shown, feature engineering is extracted and input into the model for prediction, and progress and early warning information are output (project early warning can be issued when the progress deviation is large). Feedback is given in combination with the actual progress every day, and the newly generated features are re-input into the model for iterative optimization to make the model's prediction results more accurate.

[0261] Compared with traditional methods, this model significantly improves prediction accuracy, enhances data integrity, enables daily progress updates and predictions, allows for earlier detection of progress deviations and early warnings, and also provides data support for resource allocation.

[0262] This embodiment also provides an AIoT-based engineering progress prediction device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0263] This embodiment provides an AIoT-based engineering progress prediction device, such as... Figure 8 As shown, it includes:

[0264] The acquisition module 801 is used to acquire the target construction scope of the project to be predicted, and the progress influencing factors of the first historical time period. The progress influencing factors include: the working status of at least one piece of equipment in the first type of equipment, the state time of the equipment in each working status, the energy data of the equipment, the location data of the equipment, the project progress of the first historical time period, and the target project quantity of the project to be predicted. The first historical time period is any one of multiple historical time periods, and the first type of equipment is any one of multiple types of equipment constructed within the first historical time period.

[0265] The aggregation module 802 is used to aggregate the working status of at least one device in the first type of devices and the state time of the device in each working status to determine the effective working time of the first type of devices.

[0266] The first determining module 803 is used to determine the energy consumption data of the first type of equipment based on the energy data of at least one of the first type of equipment.

[0267] The second determining module 804 is used to determine the actual construction area based on the location data of each piece of equipment;

[0268] The iteration module 805 is used to input the target construction scope, actual construction scope, project progress, effective working time and energy consumption data corresponding to each type of equipment into the AIoT model for iteration to obtain at least one prediction result.

[0269] The prediction module 806 is used to predict the project progress results for the next time period based on at least one prediction result using an AIoT model.

[0270] In one alternative implementation, the aggregation module 802 includes...

[0271] The first filtering submodule is used to filter out valid working states from all working states of at least one device;

[0272] The aggregation submodule is used to aggregate the state times corresponding to all valid working states to determine the individual valid working time of the first device.

[0273] The first processing submodule is used to take the sum of the individual effective working time of each device in the first type of equipment as the effective working time of the first type of equipment.

[0274] In one optional implementation, the energy data includes: initial energy data, supplementary energy data, and termination energy data; the first determining module 803 includes:

[0275] The first determining submodule is used to determine the individual energy consumption data corresponding to each device based on the initial energy data, replenished energy data and termination energy data corresponding to at least one device respectively.

[0276] The second determining submodule is used to determine the energy consumption data of the first type of equipment based on the individual energy consumption data of all equipment in the first type of equipment.

[0277] In one optional implementation, the location data includes: the initial latitude and longitude of the first device at multiple time points in a first historical time period, and the initial location weights corresponding to the first type of device; the second determining module 804 includes:

[0278] The third determining submodule is used to determine the number of the first type of equipment; and to determine the first transition weight corresponding to the first type of equipment based on the number of the first type of equipment and the initial position weight corresponding to the first type of equipment.

[0279] The first comparison submodule is used to compare the transition weights corresponding to all types of devices and determine the target weights corresponding to each type of device based on the comparison results.

[0280] The rounding submodule is used to perform rounding operations on the initial latitude and longitude collected within the first historical time period at a first preset interval to obtain the intermediate latitude and longitude corresponding to each initial latitude and longitude value.

[0281] The second processing submodule is used to take the target weight corresponding to the device type of the device that collected the first initial latitude and longitude as the target weight of the first intermediate latitude and longitude, wherein the first initial latitude and longitude is any one of the initial latitude and longitude collected within the first historical time period, and the first intermediate latitude and longitude is the intermediate latitude and longitude corresponding to the first initial latitude and longitude; and to take the sum of the target weights corresponding to each identical intermediate latitude and longitude as the total weight value of the intermediate latitude and longitude.

[0282] The second filtering submodule is used to filter all intermediate latitude and longitude according to the total weight value to obtain the target latitude and longitude set;

[0283] The fourth submodule is used to determine the actual construction area based on the coverage of the target latitude and longitude set.

[0284] In an optional implementation, when the device types include two categories, the transition weight includes a first transition weight corresponding to the first type of device and a second transition weight corresponding to the second type of device. The first comparison submodule includes:

[0285] The third processing submodule is used to, when the first transition weight is less than the second transition weight, take the first transition weight as the first target weight corresponding to the first type of device; and take the second transition weight as the second target weight corresponding to the second type of device.

[0286] or,

[0287] The fourth processing submodule is used to determine the third transition weight based on the first initial position weight, the first transition weight, and the second transition weight when the first transition weight is greater than or equal to the second transition weight; to use the third transition weight as the first target weight corresponding to the first type of device; and to use the second transition weight as the second target weight corresponding to the second type of device.

[0288] In one alternative implementation, the second processing submodule is specifically used for:

[0289]

[0290] in, As the first transition weight, For the number of Class I equipment, The initial position weights are for the first type of equipment.

[0291] In one alternative implementation, the fifth determining submodule includes:

[0292] The third filtering submodule is used to filter out multiple target latitude and longitude coordinates from all time points;

[0293] The mapping submodule is used to perform coordinate mapping operations on multiple target latitude and longitude coordinates to obtain planar coordinates;

[0294] The sampling submodule allows users to perform sampling operations at preset intervals in a planar coordinate system to obtain multiple sampling points.

[0295] The reverse coordinate transformation submodule is used to perform reverse coordinate transformation on multiple sampling points to obtain the actual construction range.

[0296] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0297] In this embodiment, the AIoT-based engineering progress device is presented in the form of functional units. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0298] This invention also provides a computer device having the above-described features. Figure 8 The example shown is an AIoT-based engineering progress device.

[0299] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 9 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 9 Take a processor 10 as an example.

[0300] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0301] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0302] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0303] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0304] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 9 Taking the example of a connection between China and Israel via a bus.

[0305] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0306] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0307] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for predicting project progress based on AIoT, characterized in that, The method includes: The target construction scope of the project to be predicted and the progress influencing factors of the first historical time period are obtained. The progress influencing factors include: the working status of at least one piece of equipment in the first type of equipment, the state time of the equipment in each working status, the energy data of the equipment, the location data of the equipment, the project progress of the first historical time period, and the target project quantity of the project to be predicted. The first historical time period is any one of the multiple historical time periods, and the first type of equipment is any one of the multiple types of equipment constructed within the first historical time period. The effective working time of the first type of devices is determined by aggregating the working state of at least one of the devices in the first type of devices and the state time of the device in each working state. Based on the energy data of at least one of the devices in the first type of devices, determine the energy consumption data of the first type of devices; The actual construction area is determined based on the location data of each of the aforementioned devices; The target construction area, actual construction area, project progress corresponding to multiple historical time periods, as well as the effective working time and energy consumption data corresponding to each type of equipment, are input into the AIoT model for iteration to obtain at least one prediction result. The AIoT model is used to predict the project progress results for the next time period based on at least one of the prediction results.

2. The method according to claim 1, characterized in that, The step of aggregating the working states of at least one of the devices in the first type of devices, and the state times of the devices in each working state, to determine the effective working time of the first type of devices includes: Filter out the valid operating states from all operating states of at least one of the devices; Aggregate the state times corresponding to all valid working states to determine the individual valid working time of the first device. The sum of the individual effective working time corresponding to each device in the first type of equipment is taken as the effective working time of the first type of equipment.

3. The method according to claim 1, characterized in that, The energy data includes: initial energy data, replenishment energy data, and termination energy data. Determining the energy consumption data of the first type of devices based on the energy data of at least one of the devices in the first type includes: Based on the initial energy data, replenished energy data and terminated energy data corresponding to at least one of the devices, determine the individual energy consumption data corresponding to each device. The energy consumption data of the first type of equipment is determined based on the individual energy consumption data of all equipment in the first type of equipment.

4. The method according to any one of claims 1 to 3, characterized in that, The location data includes: the initial latitude and longitude of the first device at multiple time points in the first historical time period, and the initial location weight corresponding to the first type of device. Determining the actual construction area based on the location data of each device includes: Determine the quantity of Category I equipment; The first transition weight corresponding to the first type of equipment is determined based on the number of the first type of equipment and the initial position weight corresponding to the first type of equipment. Compare the transition weights corresponding to all types of devices, and determine the target weights corresponding to each type of device based on the comparison results; The initial latitude and longitude values ​​collected within the first historical time period are rounded up at a first preset interval to obtain the intermediate latitude and longitude values ​​corresponding to each initial latitude and longitude value. The target weight corresponding to the device type of the device that collected the first initial latitude and longitude is used as the target weight of the first intermediate latitude and longitude. The first initial latitude and longitude is any one of the initial latitude and longitude collected within the first historical time period, and the first intermediate latitude and longitude is the intermediate latitude and longitude corresponding to the first initial latitude and longitude. The sum of the target weights corresponding to each identical intermediate latitude and longitude is taken as the total weight value of the intermediate latitude and longitude. All intermediate latitude and longitude coordinates are filtered according to the total weight value to obtain the target latitude and longitude set; The actual construction area is determined based on the range covered by the target latitude and longitude set.

5. The method according to claim 4, characterized in that, When the equipment types include two categories, the transition weights include a first transition weight corresponding to the first category of equipment and a second transition weight corresponding to the second category of equipment. The step of comparing all the transition weights and determining the target weight corresponding to each category of equipment based on the comparison results includes: When the first transition weight is less than the second transition weight, the first transition weight is used as the first target weight corresponding to the first type of device; The second transition weight is used as the second target weight corresponding to the second type of equipment; or, When the first transition weight is greater than or equal to the second transition weight, the third transition weight is determined based on the first initial position weight, the first transition weight, and the second transition weight. The third transition weight is used as the first target weight corresponding to the first type of device; The second transition weight is used as the second target weight corresponding to the second type of equipment.

6. The method according to claim 5, wherein determining the third transition weight based on the first initial position weight, the first transition weight, and the second transition weight specifically includes: ， in, As the first transition weight, For the number of Class I equipment, The initial position weights are for the first type of equipment.

7. The method according to any one of claims 4 to 6, characterized in that, The determination of the actual construction scope for the first historical time period based on the latitude and longitude of all time points includes: Select multiple target latitude and longitude coordinates from all time points; The coordinate mapping operation is performed on the latitude and longitude of the multiple targets to obtain planar coordinates; A second preset interval sampling operation is performed in the plane coordinates to obtain multiple sampling points; The actual construction area is obtained by performing a reverse coordinate transformation on multiple sampling points.

8. An AIoT-based engineering progress prediction device, characterized in that, The device includes: The acquisition module is used to acquire the target construction scope of the project to be predicted and the progress influencing factors of the first historical time period. The progress influencing factors include: the working status of at least one piece of equipment in the first type of equipment, the state time of the equipment in each working status, the energy data of the equipment, the location data of the equipment, the project progress of the first historical time period, and the target project quantity of the project to be predicted. The first historical time period is any one of the multiple historical time periods, and the first type of equipment is any one of the multiple types of equipment constructed within the first historical time period. An aggregation module is used to aggregate the working state of at least one of the devices in the first type of devices, as well as the state time of the device in each working state, to determine the effective working time of the first type of devices. The first determining module is used to determine the energy consumption data of the first type of devices based on the energy data of at least one of the devices in the first type of devices; The second determining module is used to determine the actual construction area based on the location data of each of the devices. The iteration module is used to input the target construction scope, actual construction scope, project progress, effective working time and energy consumption data corresponding to each type of equipment into the AIoT model for iteration, and obtain at least one prediction result. The prediction module is used to predict the project progress results for the next time period based on at least one of the prediction results using the AIoT model.

9. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the AIoT-based engineering progress prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the AIoT-based engineering progress prediction method according to any one of claims 1 to 7.

Images