Engineering project-oriented digital engineering management system and method

Abstract

According to the engineering project-oriented digital engineering management system and method provided by the embodiment of the invention, the sample digital engineering monitoring data sequence is acquired and the engineering progress state prediction network is initialized, so that the accurate prediction of the engineering progress state is realized, and the sample digital engineering parameters are firstly loaded to the prediction network; and evaluating the network convergence according to the comparison between the actual project progress state label and the prediction result. And for the network which does not meet the convergence requirement, iterative training is carried out by determining and applying a target training update index, and the network performance is continuously optimized. The process is cyclically carried out until a training termination condition is reached, and a highly accurate target project progress state prediction network is generated. According to the method, the digitization level of project management is remarkably improved, the project progress state is accurately monitored and predicted in real time, and the overall execution efficiency and the quality control capability of a project are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of digital engineering technology, and in particular to a digital engineering management system and method for engineering projects. Background Art

[0002] In the field of engineering project management, with the rapid development of information technology, digital management has become an important means to improve project management efficiency and quality. Traditional engineering project management often relies on manual experience and paper records, making it difficult to achieve real-time and accurate monitoring of the progress of the project. In order to overcome this problem, digital engineering monitoring technology has gradually emerged in recent years. By collecting and analyzing various types of data in the engineering process, it provides more scientific and efficient decision-making support for engineering project management.

[0003] However, in the practical application of digital engineering monitoring technology, how to accurately predict the progress of the project is still an urgent problem to be solved. Most of the existing methods rely on simple data statistics or empirical models, which are difficult to fully consider the complexity and uncertainty of the engineering process, resulting in a large deviation between the prediction results and the actual situation. In addition, with the continuous expansion of the scale of engineering projects and the surge in data volume, traditional methods are unable to cope with large-scale data and cannot meet the needs of modern engineering project management. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a digital engineering management system and method for engineering projects.

[0005] In conjunction with the first aspect of the present application, a digital engineering management method for engineering projects is provided, which is applied to a digital engineering management system for engineering projects, and the method comprises: Acquire a sample digital engineering monitoring data sequence and initialize a project progress status prediction network, wherein the sample digital engineering monitoring data sequence includes a plurality of sample digital engineering monitoring data, and the sample digital engineering monitoring data includes sample digital engineering parameters and project progress status labels corresponding to the sample digital engineering parameters; Loading a sample digitized engineering parameter of any sample digitized engineering monitoring data in the sample digitized engineering monitoring data sequence into the initialized engineering progress status prediction network to obtain an engineering progress status prediction result, and determining whether the initialized engineering progress status prediction network meets the network convergence requirement based on the engineering progress status label of the sample digitized engineering monitoring data and the engineering progress status prediction result; If the network convergence requirement is not met, determining a target training update index, and training the initialized engineering progress state prediction network according to the target training update index; The sample digital engineering parameters and the engineering progress status prediction results are loaded into the next sample digital engineering monitoring data to be loaded into the initialized engineering progress status prediction network, and the trained iterative engineering progress status prediction network is trained until the training termination conditions are met, thereby generating a target engineering progress status prediction network that has completed the training.

[0006] In a possible implementation of the first aspect, determining whether the initialized engineering progress status prediction network meets the network convergence requirement based on the engineering progress status label of the sample digital engineering monitoring data and the engineering progress status prediction result includes: Obtaining a target training cost function of the initialized engineering progress status prediction network; Calculating the engineering progress status label and the engineering progress status prediction result according to the target training cost function to determine a training cost parameter; Determine whether the initialized engineering progress status prediction network meets the network convergence requirement according to the training cost parameter.

[0007] In a possible implementation manner of the first aspect, determining whether the initialized engineering progress status prediction network meets the network convergence requirement according to the training cost parameter includes: Comparing the training cost parameter with the threshold cost; If the training cost parameter is less than the threshold cost, it is determined that the initialized engineering progress status prediction network meets the network convergence requirement.

[0008] In a possible implementation of the first aspect, determining the target training update indicator includes: Get the training update indicator sequence; For any one of the training update indicators in the training update indicator sequence, overwriting the corresponding neuron weight information of the initialized engineering progress status prediction network with the training update indicator to generate a reference engineering progress status prediction network; An iterative training cost parameter of the reference engineering progress status prediction network is determined, and the target training update index is determined from the training update index sequence according to the iterative training cost parameter.

[0009] In a possible implementation manner of the first aspect, determining an iterative training cost parameter of the reference engineering progress status prediction network includes: Loading the sample digital engineering parameters of the sample digital engineering monitoring data into the reference engineering progress status prediction network to obtain adjustment results; The iterative training cost parameter is determined according to the adjustment result and the engineering progress status label.

[0010] In a possible implementation manner of the first aspect, loading the sample digital engineering parameter and the engineering progress status prediction result into the next sample digital engineering monitoring data to be loaded into the initialized engineering progress status prediction network includes: Fuzzy sample data is generated according to the sample digital engineering parameters and the engineering progress status prediction result, and the fuzzy sample data is loaded into the next sample digital engineering monitoring data to be loaded into the initialized engineering progress status prediction network.

[0011] In a possible implementation of the first aspect, the method further includes: The target digital engineering monitoring data is acquired, and the digital engineering monitoring data is loaded into the target engineering progress status prediction network to acquire the target engineering progress status prediction result.

[0012] In a possible implementation of the first aspect, the method further includes: Generate corresponding project push information based on the target project progress status prediction result.

[0013] In combination with the second aspect of the present application, a digital engineering management system for engineering projects is provided, wherein the digital engineering management system for engineering projects comprises a machine-readable storage medium and a processor, wherein the machine-readable storage medium stores machine-executable instructions, and when the processor executes the machine-executable instructions, the digital engineering management system for engineering projects implements the aforementioned digital engineering management method for engineering projects.

[0014] In conjunction with the third aspect of the present application, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When the computer-executable instructions are executed, the aforementioned digital engineering management method for engineering projects is implemented.

[0015] In combination with any of the above aspects, the embodiment of the present application achieves accurate prediction of the engineering progress status by acquiring a sample digital engineering monitoring data sequence and initializing the engineering progress status prediction network. First, the sample digital engineering parameters are loaded into the prediction network, and the network convergence is evaluated based on the comparison between the actual engineering progress status label and the prediction result. For networks that do not meet the convergence requirements, iterative training is performed by determining and applying the target training update index to continuously optimize network performance. This process is repeated until the training termination condition is reached, generating a highly accurate target engineering progress status prediction network. This method significantly improves the digital level of engineering management, realizes real-time and accurate monitoring and prediction of engineering progress status, and effectively improves the overall execution efficiency and quality control capabilities of engineering projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained by combining these drawings without paying creative work.

[0017] Figure 1 A flowchart of a digital engineering management method for engineering projects provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0020] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] Figure 1 The flowchart of the digital engineering management method for engineering projects provided by the embodiment of the present application is shown. It should be understood that in other embodiments, the order of some steps in the digital engineering management method for engineering projects of this embodiment can be shared with each other based on actual needs, or some steps can be omitted or maintained. The details of the digital engineering management method for engineering projects include: Step S110, obtaining a sample digital engineering monitoring data sequence and initializing a project progress status prediction network, wherein the sample digital engineering monitoring data sequence includes a plurality of sample digital engineering monitoring data, and the sample digital engineering monitoring data includes sample digital engineering parameters and project progress status labels corresponding to the sample digital engineering parameters.

[0022] Step S120, loading the sample digitized engineering parameters of any one sample digitized engineering monitoring data in the sample digitized engineering monitoring data sequence into the initialized engineering progress status prediction network to obtain the engineering progress status prediction result, and determining whether the initialized engineering progress status prediction network meets the network convergence requirements based on the engineering progress status label of the sample digitized engineering monitoring data and the engineering progress status prediction result.

[0023] Step S130: If the network convergence requirement is not met, a target training update index is determined, and the initialized engineering progress status prediction network is trained according to the target training update index.

[0024] Step S140, loading the sample digital engineering parameters and the engineering progress status prediction results into the next sample digital engineering monitoring data to be loaded into the initialized engineering progress status prediction network, training the trained iterative engineering progress status prediction network until the training termination conditions are met, and generating a target engineering progress status prediction network that has completed the training.

[0025] In this embodiment, the server is processing a task of predicting the progress of a large-scale construction project. In this project, various digital engineering parameters are collected to monitor the progress of the project, and these parameters constitute a sample digital engineering monitoring data sequence.

[0026] For each sample digital engineering monitoring data in the sample digital engineering monitoring data sequence, it contains two parts of important information. For example, one of the sample digital engineering monitoring data may have sample digital engineering parameters, such as the amount of concrete poured, the amount of steel bars used, the number of construction workers, and the working hours of construction equipment at a certain stage in the construction project. The corresponding project progress status label is an accurate description of the project status at this stage, such as "50% completion of foundation construction" and "initial construction of the main structure".

[0027] The server also initializes the engineering progress status prediction network. This network can be a neural network-based model, such as a multilayer perceptron (MLP) network structure. When initializing the network, the server sets the initial architecture of the network, including determining the number of neurons in the input layer, which is determined according to the type of sample digital engineering parameters. For example, if there are 5 different engineering parameters, then the input layer may have 5 neurons. At the same time, the number of hidden layers, the number of neurons in each layer, and the number of neurons in the output layer are also determined. The number of neurons in the output layer is usually determined according to the number of categories of the engineering progress status label. For example, if the engineering progress status label is divided into 10 different states, then the output layer has 10 neurons. In addition, the server will initialize the weights of the connections between all neurons in the network. These weights are usually randomly initialized and may be in a small range, such as [-0.1, 0.1], and the bias term is initialized to 0 or a small value.

[0028] Next, a sample digital engineering monitoring data is selected from the sample digital engineering monitoring data sequence. For example, the monitoring data containing the sample digital engineering parameters such as the concrete pouring volume of 500 cubic meters, the steel bar usage of 30 tons, the number of construction workers of 50 people, and the working time of construction equipment of 100 hours are selected. The server loads these parameters as input into the previously initialized engineering progress status prediction network.

[0029] Inside the network, after the neurons in the input layer receive these parameter values, they perform weighted summation and add bias terms according to the connection weights between the neurons in the hidden layer, and then perform nonlinear transformation through the activation function (such as the ReLU function) and pass the result to the hidden layer. The neurons in the hidden layer repeat similar operations, passing the processed results to the next hidden layer (if there are multiple hidden layers), until the final result is passed to the output layer. Each neuron in the output layer will output a value, indicating the probability that the project is in a certain progress state. For example, the output result may be that the probability of "foundation construction is 30% completed" is 0.1, the probability of "foundation construction is 50% completed" is 0.3, and the probability of "main structure construction is in the early stage" is 0.4, etc. The project progress state corresponding to the one with the highest probability among these output results is the project progress state prediction result. Assuming that the probability of "main structure construction is in the early stage" is the highest here, then this is the prediction result.

[0030] Next, the server determines whether the initialized engineering progress status prediction network meets the network convergence requirements based on the engineering progress status label of the sample digital engineering monitoring data and the engineering progress status prediction result. First, the server obtains the target training cost function of the initialized engineering progress status prediction network. This target training cost function can be a cross-entropy function, which is used to measure the difference between the prediction result and the true label.

[0031] Then, the server calculates the project progress status label and the project progress status prediction result based on this target training cost function to determine the training cost parameter. For example, if the project progress status label is "50% completed foundation construction" and the prediction result is "initial construction of the main structure", a larger training cost parameter will be calculated according to the calculation rules of the cross entropy function. If the project progress status label and the prediction result are very close, the calculated training cost parameter will be relatively small.

[0032] Finally, the server determines whether the initialized engineering progress status prediction network meets the network convergence requirements based on this training cost parameter. The server compares the training cost parameter with the threshold cost. Assuming the threshold cost is set to 0.1, if the calculated training cost parameter is less than 0.1, it means that the prediction result is very close to the true label, then the server determines that the initialized engineering progress status prediction network meets the network convergence requirements. If the training cost parameter is greater than 0.1, it means that the prediction result is very different from the true label, and the network needs further training, which does not meet the network convergence requirements.

[0033] When the server determines that the initialization engineering progress status prediction network does not meet the network convergence requirements, it is necessary to determine the target training update indicator to train the network.

[0034] First, the server obtains the training update indicator sequence. This training update indicator sequence may contain a variety of different update strategies, such as different learning rate values, different weight update algorithms, etc.

[0035] Then, for any training update indicator in the training update indicator sequence, the server overwrites the corresponding neuron weight information of the initialized engineering progress status prediction network with this training update indicator to generate a reference engineering progress status prediction network. For example, one of the training update indicators in the training update indicator sequence is the Stochastic Gradient Descent (SGD) algorithm with a learning rate of 0.01. The server applies this learning rate to the initialized engineering progress status prediction network, that is, adjusts the weights of the connections between neurons in the network according to this learning rate, thereby generating a reference engineering progress status prediction network.

[0036] Next, the server needs to determine the iterative training cost parameters of the reference engineering progress status prediction network. The server loads the sample digital engineering parameters of the sample digital engineering monitoring data into the reference engineering progress status prediction network. For example, the parameters of 500 cubic meters of concrete pouring, 30 tons of steel bars, 50 construction workers, and 100 hours of construction equipment working time are still loaded into the reference engineering progress status prediction network. The network calculates according to the new weights and learning rates and other settings to obtain an adjustment result, which is also the probability value of each engineering progress status. Then, the server determines the iterative training cost parameters based on this adjustment result and the engineering progress status label. The iterative training cost parameters are also calculated based on the cross entropy function.

[0037] Finally, the server determines the target training update indicator from the training update indicator sequence based on this iterative training cost parameter. The server will compare the iterative training cost parameters of the reference engineering progress status prediction network corresponding to different training update indicators. Assume that there are three different training update indicators in the training update indicator sequence, and three reference engineering progress status prediction networks are generated respectively, and the corresponding iterative training cost parameters are 0.15, 0.12 and 0.1 respectively. The server will select the training update indicator with the smallest iterative training cost parameter, that is, the training update indicator with the corresponding iterative training cost parameter of 0.1 as the target training update indicator. Then, the server trains the initialized engineering progress status prediction network based on this target training update indicator. For example, if the target training update indicator is the stochastic gradient descent algorithm with a learning rate of 0.005, the server will adjust the connection weights between neurons in the initialized engineering progress status prediction network according to this learning rate and algorithm rules, and perform a round of training.

[0038] After the server performs a round of training on the initial engineering progress status prediction network, a trained iterative engineering progress status prediction network is obtained. Now the server needs to load the sample digital engineering parameters and engineering progress status prediction results into the next sample digital engineering monitoring data to continue training the network.

[0039] The server first generates fuzzy sample data based on the sample digitized engineering parameters and the engineering progress status prediction results. For example, in the previous round, the sample digitized engineering parameters were 500 cubic meters of concrete pouring, 30 tons of steel bars, 50 construction workers, and 100 hours of construction equipment working time, and the engineering progress status prediction result was "the initial stage of main structure construction". The server may fuse this information to generate fuzzy sample data according to some rules, such as combining the engineering progress status prediction results with the sample digitized engineering parameters with a certain weight to generate a new sample data containing more information.

[0040] Then, the server loads this fuzzy sample data into the next sample digital engineering monitoring data. Assuming that the next sample digital engineering monitoring data contains sample digital engineering parameters such as 600 cubic meters of concrete pouring, 35 tons of steel bars, 60 construction workers, and 120 hours of construction equipment working time, the server combines the previously generated fuzzy sample data with it and loads it into the trained iterative engineering progress status prediction network.

[0041] The network will calculate and adjust the connection weights between neurons according to the previously determined network structure and training update indicators (such as learning rate, etc.). This process will be repeated continuously, and each time the fuzzy sample data generated by the current sample digital engineering parameters and engineering progress status prediction results will be loaded into the next sample digital engineering monitoring data to train the network.

[0042] This training process will continue until the training termination conditions are met. The training termination conditions can be a variety of situations, such as reaching a predetermined number of training rounds (such as 100 rounds), or the training cost parameter for several consecutive rounds (such as 5 rounds) is lower than a very small value (such as 0.01). When these training termination conditions are met, the server generates a target engineering progress status prediction network that has completed training. This target engineering progress status prediction network has been fully trained and can accurately predict the progress status of the project based on the input digital engineering parameters.

[0043] Based on the above steps, the embodiment of the present application achieves accurate prediction of the engineering progress status by acquiring a sample digital engineering monitoring data sequence and initializing the engineering progress status prediction network. First, the sample digital engineering parameters are loaded into the prediction network, and the network convergence is evaluated based on the comparison between the actual engineering progress status label and the prediction result. For networks that do not meet the convergence requirements, iterative training is performed by determining and applying the target training update index to continuously optimize network performance. This process is repeated until the training termination condition is reached, and a highly accurate target engineering progress status prediction network is generated. This method significantly improves the digital level of engineering management, realizes real-time and accurate monitoring and prediction of engineering progress status, and effectively improves the overall execution efficiency and quality control capabilities of engineering projects.

[0044] In a possible implementation manner, determining whether the initialized engineering progress status prediction network meets the network convergence requirement based on the engineering progress status label of the sample digital engineering monitoring data and the engineering progress status prediction result includes: Obtain the target training cost function of the initialized engineering progress status prediction network.

[0045] The engineering progress status label and the engineering progress status prediction result are calculated according to the target training cost function to determine the training cost parameter.

[0046] Determine whether the initialized engineering progress status prediction network meets the network convergence requirement according to the training cost parameter.

[0047] In a possible implementation, determining whether the initialized engineering progress state prediction network meets the network convergence requirement according to the training cost parameter includes: The training cost parameter is compared with a threshold cost.

[0048] If the training cost parameter is less than the threshold cost, it is determined that the initialized engineering progress status prediction network meets the network convergence requirement.

[0049] In a possible implementation, determining the target training update index includes: Gets a sequence of training update metrics.

[0050] For any one of the training update indicators in the training update indicator sequence, the training update indicator is overwritten with the corresponding neuron weight information of the initialized engineering progress status prediction network to generate a reference engineering progress status prediction network.

[0051] An iterative training cost parameter of the reference engineering progress status prediction network is determined, and the target training update index is determined from the training update index sequence according to the iterative training cost parameter.

[0052] In a possible implementation manner, determining the iterative training cost parameter of the reference engineering progress status prediction network includes: The sample digitized engineering parameters of the sample digitized engineering monitoring data are loaded into the reference engineering progress status prediction network to obtain adjustment results.

[0053] The iterative training cost parameter is determined according to the adjustment result and the engineering progress status label.

[0054] In a possible implementation manner, the step of loading the sample digital engineering parameter and the engineering progress status prediction result into the next sample digital engineering monitoring data to be loaded into the initialized engineering progress status prediction network includes: Fuzzy sample data is generated according to the sample digital engineering parameters and the engineering progress status prediction result, and the fuzzy sample data is loaded into the next sample digital engineering monitoring data to be loaded into the initialized engineering progress status prediction network.

[0055] In a possible implementation, the method further includes: The target digital engineering monitoring data is acquired, and the digital engineering monitoring data is loaded into the target engineering progress status prediction network to acquire the target engineering progress status prediction result.

[0056] In a possible implementation, the method further includes: Generate corresponding project push information based on the target project progress status prediction result.

[0057] In the above embodiments, a digital engineering management system for engineering projects for executing the above method embodiments has at least one processor, a control module (chip set) coupled to at least one of the (at least one) processors, a memory coupled to the control module, a non-volatile memory (NVM) / storage device coupled to the control module, at least one load / output device coupled to the control module, and a network interface coupled to the control module.

[0058] The processor may include at least one single-core or multi-core processor, and the processor may include any combination of general-purpose processors or special-purpose processors (such as graphics processors, application processors, baseband processors, etc.). For some alternative implementations, the digital engineering management system for engineering projects can be based on electronic devices such as the gateway described in the embodiments of the present application.

[0059] For some alternative embodiments, a digital engineering management system for engineering projects may include at least one computer-readable medium (e.g., a memory or NVM / storage device) having instructions and at least one processor integrated with the at least one computer-readable medium and configured to execute the instructions to implement a module to perform the actions described in the present disclosure.

[0060] For one embodiment, the control module may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) and / or any suitable device or component in communication with the control module.

[0061] The control module may include a memory controller module to provide an interface to the memory. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0062] The memory may be used, for example, to load and store data and / or instructions for a digital engineering management system for engineering projects. For one embodiment, the memory may include any suitable volatile memory, for example, a suitable DRAM.

[0063] For one embodiment, the control module may include at least one load-in / load-out controller to provide an interface to the NVM / storage device and the (at least one) load-in / load-out device.

[0064] For example, the NVM / storage device may be used to store data and / or instructions. The NVM / storage device may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (at least one) non-volatile storage device (e.g., at least one hard disk drive (HDD), at least one compact disk (CD) drive, and / or at least one digital versatile disk (DVD) drive).

[0065] The NVM / storage device may include a storage resource that is physically part of a device on which the digital engineering management system for engineering projects is installed, or it may be accessible to the device without being part of the device. For example, the NVM / storage device may be accessed via (at least one) load / output device based on a network.

[0066] The (at least one) load-in / output device may provide an interface for the digital engineering management system for engineering projects to communicate with any other appropriate device, and the load-in / output device may include a communication component, a phonetic component, a sensor component, etc. The network interface may provide an interface for the digital engineering management system for engineering projects to communicate based on at least one network, and the digital engineering management system for engineering projects may wirelessly communicate with at least one component of a wireless network based on any of at least one wireless network priors and / or protocols, such as accessing a wireless network based on a communication prior.

[0067] For one embodiment, at least one of the (at least one) processor may be loaded together with the logic of at least one controller of the control module (e.g., a memory controller module). For one embodiment, at least one of the (at least one) processor may be loaded together with the logic of at least one controller of the control module to form a system level load. For one embodiment, at least one of the (at least one) processor may be fused on the same die with the logic of at least one controller of the control module. For one embodiment, at least one of the (at least one) processor may be fused on the same die with the logic of at least one controller of the control module to form a system on chip (SoC).

[0068] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, based on the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0069] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the digital engineering management method for engineering projects described in the above embodiments.

[0070] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the digital engineering management method for engineering projects described in the above embodiments.

[0071] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed over multiple modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present invention without creative effort.

[0072] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other medium that can be used to be computer-readable with or store data.

[0073] Finally, it should be noted that what is disclosed above is only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A digital engineering management method for engineering projects, characterized in that: The method comprises: Acquire a sample digital engineering monitoring data sequence and initialize a project progress status prediction network, wherein the sample digital engineering monitoring data sequence includes a plurality of sample digital engineering monitoring data, and the sample digital engineering monitoring data includes sample digital engineering parameters and project progress status labels corresponding to the sample digital engineering parameters; Loading a sample digitized engineering parameter of any sample digitized engineering monitoring data in the sample digitized engineering monitoring data sequence into the initialized engineering progress status prediction network to obtain an engineering progress status prediction result, and determining whether the initialized engineering progress status prediction network meets the network convergence requirement based on the engineering progress status label of the sample digitized engineering monitoring data and the engineering progress status prediction result; If the network convergence requirement is not met, determining a target training update index, and training the initialized engineering progress state prediction network according to the target training update index; The sample digital engineering parameters and the engineering progress status prediction results are loaded into the next sample digital engineering monitoring data to be loaded into the initialized engineering progress status prediction network, and the trained iterative engineering progress status prediction network is trained until the training termination conditions are met, thereby generating a target engineering progress status prediction network that has completed the training.

2. The digital engineering management method for engineering projects according to claim 1 is characterized in that: The determining, based on the engineering progress status label of the sample digital engineering monitoring data and the engineering progress status prediction result, whether the initialized engineering progress status prediction network meets the network convergence requirement includes: Obtaining a target training cost function of the initialized engineering progress status prediction network; Calculating the engineering progress status label and the engineering progress status prediction result according to the target training cost function to determine a training cost parameter; Determine whether the initialized engineering progress status prediction network meets the network convergence requirement according to the training cost parameter.

3. The digital engineering management method for engineering projects according to claim 2 is characterized in that: The determining, based on the training cost parameter, whether the initialized engineering progress state prediction network meets the network convergence requirement includes: Comparing the training cost parameter with the threshold cost; If the training cost parameter is less than the threshold cost, it is determined that the initialized engineering progress status prediction network meets the network convergence requirement.

4. The digital engineering management method for engineering projects according to claim 1 is characterized in that: The determining of the target training update index includes: Get the training update indicator sequence; For any one of the training update indicators in the training update indicator sequence, overwriting the corresponding neuron weight information of the initialized engineering progress status prediction network with the training update indicator to generate a reference engineering progress status prediction network; An iterative training cost parameter of the reference engineering progress status prediction network is determined, and the target training update index is determined from the training update index sequence according to the iterative training cost parameter.

5. The digital engineering management method for engineering projects according to claim 4 is characterized in that: The step of determining the iterative training cost parameter of the reference engineering progress status prediction network includes: Loading the sample digital engineering parameters of the sample digital engineering monitoring data into the reference engineering progress status prediction network to obtain adjustment results; The iterative training cost parameter is determined according to the adjustment result and the engineering progress status label.

6. The digital engineering management method for engineering projects according to claim 5 is characterized in that: The step of loading the sample digital engineering parameters and the engineering progress status prediction result into the next sample digital engineering monitoring data to be loaded into the initialized engineering progress status prediction network comprises: Fuzzy sample data is generated according to the sample digital engineering parameters and the engineering progress status prediction result, and the fuzzy sample data is loaded into the next sample digital engineering monitoring data to be loaded into the initialized engineering progress status prediction network.

7. The digital engineering management method for engineering projects according to claim 6 is characterized in that: The method further comprises: The target digital engineering monitoring data is acquired, and the digital engineering monitoring data is loaded into the target engineering progress status prediction network to acquire the target engineering progress status prediction result.

8. The digital engineering management method for engineering projects according to claim 1 is characterized in that: The method further comprises: Generate corresponding project push information based on the target project progress status prediction result.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a computer, the digital engineering management method for engineering projects described in any one of claims 1 to 8 is implemented.

10. A digital engineering management system for engineering projects, characterized in that: It comprises a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a computer, the digital engineering management method for engineering projects described in any one of claims 1 to 8 is implemented.

Images