Project risk prediction method and device, equipment, storage medium and program product

Abstract

The invention relates to a project risk prediction method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring comprehensive information and change information of a target project; analyzing and processing the comprehensive information and the change information by using a pre-trained factor analysis model to obtain a factor list influencing the completion condition of the target project; and performing prediction processing by using a pre-trained risk prediction model and the factor list to obtain a risk prediction result of the target project, the risk prediction result being used for representing a probability that the target project cannot be completed on schedule. By adopting the method, the efficiency is high, and the risk can be accurately and timely predicted.

Description

Technical Field

[0001] The present application relates to the technical field of project management, and particularly to a project risk prediction method, apparatus, device, storage medium, and program product. Background Art

[0002] In today's highly competitive enterprise R & D project environment, project management faces unprecedented complexity and uncertainty. The ever-changing pre-dependence conditions, the difficulties in resource allocation, and the continuous increase in technical difficulty make it very difficult but crucial to control project risks.

[0003] Traditional project risk prediction methods mainly rely on manual experience and limited data. This method is not only inefficient but also difficult to accurately and timely predict risks, resulting in being often caught off guard when risks come. Summary of the Invention

[0004] Based on this, it is necessary to provide a project risk prediction method, apparatus, device, storage medium, and program product for the above technical problems, which is not only highly efficient but also can accurately and timely predict risks.

[0005] In a first aspect, the present application provides a project risk prediction method, which includes:

[0006] Obtain the comprehensive information and change information of the target project;

[0007] Use a pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a list of factors affecting the completion of the target project;

[0008] Use a pre-trained risk prediction model and the list of factors to perform prediction processing to obtain a risk prediction result of the target project, where the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

[0009] In one embodiment, using a pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a list of factors affecting the completion of the target project includes:

[0010] Respectively perform information preprocessing on the comprehensive information and change information to obtain the processed comprehensive information and change information;

[0011] Input the processed comprehensive information and change information into the factor analysis model, and respectively perform feature extraction on the comprehensive information and change information through the factor analysis model to obtain multiple candidate influencing factors, perform sorting processing on the multiple candidate influencing factors, and output a list of factors according to the sorting result.

[0012] In one embodiment, the method further includes:

[0013] Obtain the comprehensive information and change information corresponding to the factor list;

[0014] Use the factor analysis model to analyze and process the re-obtained comprehensive information and change information, and update the factor list according to the analysis results.

[0015] In one embodiment, use the pre-trained risk prediction model and the factor list to perform prediction processing to obtain the risk prediction result of the target project, including:

[0016] Obtain the comprehensive information and change information corresponding to the factor list;

[0017] Input the re-obtained comprehensive information and change information into the risk prediction model for prediction processing to obtain the risk prediction result of the target project.

[0018] In one embodiment, the risk prediction model is obtained by integrating and training multiple different long short-term memory networks and convolutional neural networks using the ensemble learning technique.

[0019] In one embodiment, the method further includes:

[0020] In the case where the risk prediction result indicates that the probability that the target project cannot be completed on schedule is greater than the preset probability, perform risk assessment based on the pre-established risk assessment database, comprehensive information and change information to obtain the risk assessment result; wherein, the risk assessment result includes the risk type that causes the target project to not be completed on schedule;

[0021] Determine the target response strategy of the target project according to the pre-established response strategy library and the risk type.

[0022] In a second aspect, the present application also provides a project risk prediction device, which includes:

[0023] An information acquisition module, configured to acquire the comprehensive information and change information of the target project;

[0024] A factor list determination module, configured to use the pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a factor list that affects the completion of the target project;

[0025] A risk prediction module, configured to use the pre-trained risk prediction model and the factor list to perform prediction processing to obtain the risk prediction result of the target project, wherein the risk prediction result is used to represent the probability that the target project cannot be completed on schedule.

[0026] In a third aspect, the present application also provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0027] Obtain the comprehensive information and change information of the target project;

[0028] Use a pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a list of factors affecting the completion of the target project;

[0029] Use a pre-trained risk prediction model and the list of factors to perform prediction processing to obtain a risk prediction result of the target project, where the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

[0030] Fourthly, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0031] Obtain the comprehensive information and change information of the target project;

[0032] Use a pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a list of factors affecting the completion of the target project;

[0033] Use a pre-trained risk prediction model and the list of factors to perform prediction processing to obtain a risk prediction result of the target project, where the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

[0034] Fifthly, the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0035] Obtain the comprehensive information and change information of the target project;

[0036] Use a pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a list of factors affecting the completion of the target project;

[0037] Use a pre-trained risk prediction model and the list of factors to perform prediction processing to obtain a risk prediction result of the target project, where the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

[0038] The above-mentioned project risk prediction method, device, equipment, storage medium and program product obtain the comprehensive information and change information of the target project; use the pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a list of factors affecting the completion of the target project; use the pre-trained risk prediction model and the list of factors to perform prediction processing to obtain the risk prediction result of the target project. Compared with the traditional method, the risk prediction based on the comprehensive information and change information in the embodiments of the present application not only has high efficiency, but also can accurately and timely predict risks. Moreover, the technical solution provided in the embodiments of the present application has strong data integration capabilities, can effectively integrate the comprehensive information from the project, greatly improves the accuracy of risk prediction, and provides more comprehensive and rich information support for risk prediction; and by monitoring the project progress in real time according to the change information, the risk prediction can be dynamically performed according to the new data, ensuring that risk management is always closely aligned with the actual situation of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is an application environment diagram of the project risk prediction method in an embodiment;

[0041] Figure 2 It is a flowchart of the project risk prediction method in an embodiment;

[0042] Figure 3 It is a flowchart of the step of obtaining the list of factors in an embodiment;

[0043] Figure 4 It is a flowchart of the step of updating the list of factors in an embodiment;

[0044] Figure 5 It is a flowchart of the risk prediction step in an embodiment;

[0045] Figure 6 It is a flowchart of the risk assessment step in an embodiment;

[0046] Figure 7 It is a structural block diagram of the project risk prediction device in an embodiment;

[0047] Figure 8 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] To make the objectives, technical solutions, and advantages of this application more clearly understood, the following further elaborates on this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for explaining this application and are not used to limit this application.

[0049] The project risk prediction method provided by the embodiments of this application can be applied to an application environment as Figure 1 shown. This application environment includes a terminal 102 and a server 104. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed in the cloud or on other network servers. The terminal 102 transmits the comprehensive information and change information of the target project input by the project-related personnel to the server 104. The server 104 predicts the probability that the target project cannot be completed on schedule based on the comprehensive information and change information of the target project, and evaluates the risks of the target project and gives countermeasures in the case where the target project cannot be completed on schedule. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smartphones, tablet computers, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0050] In an exemplary embodiment, as Figure 2 shown, a project risk prediction method is provided. Taking the case where this method is applied to the Figure 1 server as an example, it includes the following steps:

[0051] Step 201, obtain the comprehensive information and change information of the target project.

[0052] Among them, the comprehensive information includes information such as project summary, project objectives, project schedule, project progress, project input-output, components involved, and cross-departmental collaboration; the change information includes information such as code submission frequency, requirement changes, project member daily reports, and test pass rates. The project member daily report also includes task progress description, problems encountered, changes in estimated completion time, resource requirements, etc.

[0053] The server can obtain the comprehensive information of the target project from the data storage system and obtain the change information of the target project input by the project-related personnel from the terminal.

[0054] Taking a new cloud computing IaaS (Infrastructure as a Service) product being developed by a certain technology company as the target project, the server can obtain the comprehensive information of the project from the data storage system. Among them, the comprehensive information includes the requirement specifications of the product, the technical architecture design documents, the skills and experience data of the development team, the complexity and quality indicators of the code library, the requirement lists of each business department within the enterprise, the resource allocation of the development and testing teams, the R & D data of previous similar products, the performance and functional characteristics of competitor products in the market, the industry technology development trend, etc.

[0055] The server can also obtain the change information input by the project-related personnel from the terminal. Among them, the change information includes real-time data such as the development progress of the technical team, the resource consumption situation, and the compatibility test results of the system, as well as dynamic data such as the code submission frequency during the development process, the passing rate of test cases, and the resource utilization situation.

[0056] It should be noted that the comprehensive information, the change information, and the way the server obtains information are not limited to the above examples and can be set according to the actual situation.

[0057] Step 202: Use the pre-trained factor analysis model to analyze and process the comprehensive information and the change information to obtain a list of factors affecting the completion of the target project.

[0058] Pre-train a factor analysis model, which can analyze which factors will affect the project completion situation.

[0059] After obtaining the comprehensive information and the change information of the target project, input the comprehensive information and the change information into the factor analysis model, and the factor analysis model outputs a list of factors.

[0060] For example, input the requirement specifications of the product, the skills and experience data of the development team, the complexity and quality indicators of the code library, the requirement lists of each business department within the enterprise, the resource allocation of the development and testing teams, as well as the development progress of the technical team, the resource consumption situation, and the code submission frequency during the development process into the factor analysis model. The factor analysis model analyzes and processes the above information and outputs a list of factors. This factor analysis list includes the development progress of the technical team, the resource consumption situation, and the resource allocation of the development and testing teams. That is, the development progress of the technical team, the resource consumption situation, and the resource allocation of the development and testing teams are several factors that have a greater impact on whether the project can be completed on schedule.

[0061] Step 203: Use the pre-trained risk prediction model and the list of factors to perform prediction processing to obtain the risk prediction result of the target project.

[0062] Among them, the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

[0063] Pre-train a risk prediction model, which can predict whether a project can be completed on schedule and output the probability of not being completed on schedule. For example, if the risk prediction model predicts that the project can be completed on schedule, it outputs a probability y = 0; if the risk prediction model predicts that there is a certain delay in the project or the customer is not fully satisfied but the delivery is finally completed, it outputs a probability y = 0.5; if the risk prediction model predicts that the project is severely delayed or even not successfully delivered in the end, it outputs a probability y = 1.

[0064] After determining the factor list, screen and process the obtained comprehensive information and change information according to the factor list to screen out the information corresponding to each influencing factor in the factor list. Then, input the screened information into the risk prediction model for prediction processing to obtain the risk probability prediction result of the target project output by the risk prediction model.

[0065] In the above embodiment, the comprehensive information and change information of the target project are obtained; the pre-trained factor analysis model is used to analyze and process the comprehensive information and change information to obtain a factor list affecting the completion of the target project; the pre-trained risk prediction model and the factor list are used for prediction processing to obtain the risk prediction result of the target project. Compared with the traditional method, the risk prediction based on the comprehensive information and change information in the embodiment of the present application not only has high efficiency, but also can accurately and timely predict risks. Moreover, the technical solution provided by the embodiment of the present application has strong data integration capabilities, can effectively integrate the comprehensive information from the project, greatly improves the accuracy of risk prediction, and provides more comprehensive and rich information support for risk prediction; and by monitoring the project progress according to the change information in real time, risk prediction can be dynamically performed according to new data to ensure that risk management is always closely aligned with the actual situation of the project. Further, the technical solution provided by the embodiment of the present application has good cross-platform compatibility, can run stably in different operating systems and hardware environments, and is easy to expand and integrate into the existing project management system, providing a convenient user experience.

[0066] In an exemplary embodiment, as Figure 3 shown, the above embodiment of "using the pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a factor list affecting the completion of the target project" may include the following steps:

[0067] Step 301, perform information preprocessing on the comprehensive information and change information respectively to obtain the processed comprehensive information and change information.

[0068] Perform information preprocessing on the comprehensive information and the changing information. Among them, the information preprocessing may include at least one of cleaning processing, conversion processing, standardization processing, and normalization processing.

[0069] The cleaning processing may include: detecting outliers by using statistical methods or rules based on domain knowledge, and removing outliers, noise data, significantly unreasonable progress data, etc. according to the detection results. The cleaning processing may also include processing missing values, that is, using the method of mean filling to ensure the integrity of the data.

[0070] The conversion processing may include: converting different types of information. For example, encoding text information, performing one-hot encoding on categorical information, etc.

[0071] The standardization processing may include: standardizing the daily reports of project members extracted. For example, expressing the task progress as a percentage, classifying and coding the problem descriptions, etc.

[0072] The normalization processing includes: performing normalization processing on the information by using the Z-score normalization algorithm to make the information of different features have similar scales.

[0073] It should be noted that the information preprocessing is not limited to the above examples and can be set according to the actual situation.

[0074] It can be understood that the information preprocessing can ensure the quality and consistency of the information and improve the analysis accuracy of the factor analysis model.

[0075] Step 302, input the processed comprehensive information and the changing information into the factor analysis model, and respectively extract features from the comprehensive information and the changing information through the factor analysis model to obtain multiple candidate influencing factors, perform sorting processing on the multiple candidate influencing factors, and output a factor list according to the sorting result.

[0076] After the information preprocessing, input the processed comprehensive information and the changing information into the factor analysis model. The factor analysis model first performs feature extraction processing on the comprehensive information and the changing information to obtain multiple candidate influencing factors and the influence degree of each candidate influencing factor on whether the project can be completed on schedule. Then, the factor analysis model sorts the multiple candidate influencing factors according to the influence degree to obtain a sorting result from high to low in terms of influence degree. Finally, the factor analysis model eliminates some candidate influencing factors from the sorting result according to the influence degree, and outputs a factor list according to the candidate influencing factors after the elimination processing.

[0077] For example, the product's requirement specifications, the development team's skills and experience data, the complexity and quality indicators of the code base, the requirements lists of various business departments within the enterprise, the resource allocation of the development and testing teams, as well as the technical team's development progress, resource consumption, and the frequency of code submission during the development process are input into the factor analysis model. The factor analysis model analyzes and processes the above information to obtain candidate influencing factors including the development team's skills and experience data, the technical team's development progress, resource consumption, the resource allocation of the development and testing teams, and the frequency of code submission during the development process; then, the candidate influencing factors are sorted according to their degree of influence to obtain a sorting result; finally, the candidate influencing factors whose degree of influence is lower than the preset degree threshold are eliminated, and a factor list is output, which includes the technical team's development progress, resource consumption, and the resource allocation of the development and testing teams.

[0078] In the above embodiment, indicators with less correlation are eliminated to provide high-quality data input for risk prediction.

[0079] In the above embodiment, information preprocessing is performed on the comprehensive information and the change information respectively to obtain the processed comprehensive information and the change information; the processed comprehensive information and the change information are input into the factor analysis model, and the comprehensive information and the change information are respectively feature extracted by the factor analysis model to obtain multiple candidate influencing factors, and the multiple candidate influencing factors are sorted, and a factor list is output according to the sorting result. The embodiment of the present application eliminates some candidate influencing factors through information preprocessing and factor analysis model, reduces interference information, can improve the accuracy of risk prediction, and thus better assist project management.

[0080] In an exemplary embodiment, Figure 4 As shown, the following steps may also be included:

[0081] Step 303: Obtain comprehensive information and change information corresponding to the factor list.

[0082] After the factor analysis model outputs a factor list, the comprehensive information and change information can be re-acquired according to the influencing factors in the factor list to obtain the comprehensive information and change information corresponding to the factor list.

[0083] For example, if the factor list includes the development progress of the technical team, resource consumption, and resource allocation of the development and testing teams, the information corresponding to the development progress of the technical team, resource consumption, and resource allocation of the development and testing teams can be retrieved from the data storage system, or the information corresponding to the development progress of the technical team, resource consumption, and resource allocation of the development and testing teams input by project-related personnel can be retrieved.

[0084] Step 304: Analyze and process the re-obtained comprehensive information and change information using a factor analysis model, and update the factor list according to the analysis results.

[0085] Input the re-obtained comprehensive information and change information into the factor analysis model. The factor analysis model performs feature extraction processing on the re-obtained comprehensive information and change information to obtain multiple candidate influencing factors and the corresponding influence degrees of each candidate influencing factor; sort the candidate influencing factors according to the influence degrees to obtain a sorting result. Then, update the previously determined factor list according to the sorting result to obtain an updated factor list.

[0086] In the above embodiment, obtain the comprehensive information and change information corresponding to the factor list; analyze and process the re-obtained comprehensive information and change information using a factor analysis model, and update the factor list according to the analysis results. By re-extracting features and updating the factor list in the embodiments of the present application, the accuracy of the factor list can be improved, thereby improving the accuracy of risk prediction.

[0087] In an exemplary embodiment, as Figure 5 shown, the above embodiment of "performing prediction processing using a pre-trained risk prediction model and a factor list to obtain a risk prediction result of a target project" may include the following steps:

[0088] Step 401: Obtain the comprehensive information and change information corresponding to the factor list.

[0089] After the factor analysis model outputs the factor list, the comprehensive information and change information can be re-obtained according to the influencing factors in the factor list to obtain the comprehensive information and change information corresponding to the factor list.

[0090] Step 402: Input the re-obtained comprehensive information and change information into the risk prediction model for prediction processing to obtain a risk prediction result of the target project.

[0091] Input the re-obtained comprehensive information and change information into the risk prediction model. The risk prediction model performs prediction processing according to the re-obtained comprehensive information and change information and outputs a risk prediction result of the target project.

[0092] In some embodiments, if the factor list is updated, obtain the comprehensive information and change information corresponding to the updated factor list, and input the re-obtained comprehensive information and change information into the risk prediction model for prediction processing to obtain a risk prediction result of the target project.

[0093] In the above embodiments, comprehensive information and change information corresponding to the factor list are obtained; the re-obtained comprehensive information and change information are input into the risk prediction model for prediction processing to obtain the risk prediction result of the target project. In the embodiments of the present application, when the factor list is updated, the updated factor list is used for risk prediction, and the prediction accuracy is relatively high, providing a more reliable basis for managing the project.

[0094] In an exemplary embodiment, the risk prediction model is obtained by integrating and training multiple different long short-term memory networks and convolutional neural networks using the ensemble learning technique.

[0095] Based on the historical database, for the projects completed on schedule, the probability y of not being completed on schedule is marked as 0; for the projects with a certain delay or incomplete customer satisfaction but finally delivered, the probability y of not being completed on schedule is marked as 0.5; for the projects with serious delays and finally not successfully delivered, the probability y of not being completed on schedule is marked as 1. The sorted historical project data is divided into a training set and a validation set according to a preset ratio.

[0096] The model architecture of the risk prediction model adopts a combined design of LSTM (Long Short-Term Memory) and CNN (Convolutional Neural Network). Among them, the LSTM model is used to process time series data, including the change of project progress over time, the dynamics of resource usage, etc. Appropriate numbers of LSTM layers, neurons, and activation functions are designed to capture the time-dependent features in the project data. The CNN model part is used to process spatial data, including the text information in the daily reports of project members, the structural features of the code library, etc. Different sizes of convolutional kernels and pooling layers are designed to extract the spatial features in the project data. The use of LSTM and CNN is integrated by the ensemble learning method, and Boosting is used to integrate multiple different combined models of LSTM and CNN.

[0097] The model is trained using the training set, the validation set, and the above model architecture. Appropriate hyperparameters such as the learning rate, batch size, and number of iterations are determined, and the hyperparameters are optimized through the grid search method to improve the performance and convergence speed of the model. The structural parameters such as the numbers of LSTM and CNN layers and neurons are continuously adjusted, and the performance changes of the model under different parameter settings are observed to find the optimal model architecture and obtain the risk prediction model.

[0098] Moreover, as the historical database is continuously updated and improved, the risk prediction model is continuously optimized to ensure that it always maintains excellent performance.

[0099] In some embodiments, the change information of the target project is monitored in real time, and the risk prediction model is automatically updated and optimized according to the new information to ensure that the model always adapts to the changes of the project and provides timely and accurate risk prediction for project management.

[0100] In the above embodiments, a specific combination of deep learning algorithms is adopted, which combines two deep learning models, namely the long short-term memory network and the convolutional neural network, to give full play to the advantages of the two algorithms to capture the spatio-temporal features and complex patterns in the project data, greatly improving the accuracy of risk prediction. Moreover, as the project-related information continues to accumulate, the risk prediction model can be automatically updated and optimized, continuously improving the prediction and response performance, and providing more intelligent and efficient support for project management.

[0101] In an exemplary embodiment, as Figure 6 shown, the following steps may further be included:

[0102] Step 501, when the probability that the risk prediction result indicates that the target project cannot be completed on schedule is greater than the preset probability, perform a risk assessment based on the pre-established risk assessment database, comprehensive information, and change information to obtain a risk assessment result.

[0103] The risk assessment result is used to characterize the risk types that cause the target project to not be completed on schedule, and the risk types include at least one of the risks of unstable requirements, technical risks, requirements integration risks, and resource scarcity risks.

[0104] Based on rich internal resources such as enterprise project documents, historical databases, and project review and retrospective documents, a powerful risk assessment database is constructed. For example, project-related information can be obtained from internal documents such as project plans, requirement documents, and test reports, including technical parameters, schedule plans, cost budgets, personnel configurations, market environments, etc. Deeply understand common risks from the historical data of similar projects; according to the professional opinions provided by internal experts of the enterprise, make an accurate definition of the project completion situation for the actual situation of each project.

[0105] When the probability that the target project cannot be completed on schedule is greater than the preset probability, determine the schedule plan data of the project according to the comprehensive information and change information of the target project, including the start time, end time, key milestones, etc. of each stage, and combine the pre-established risk assessment database to evaluate the impact of the risk of unstable requirements on the project schedule, the impact of technical risks on product quality and stability, the impact of requirements integration risks on the functional integrity of the project, and the impact of resource scarcity risks on the project delivery time, comprehensively evaluate the severity and possibility of each risk, and obtain a risk assessment result.

[0106] Step 502: Determine the target response strategy for the target project according to the pre-established response strategy library and risk type.

[0107] Pre-establish a response strategy library, which includes response strategies corresponding to different risk types. For example, for the risk of unstable requirements, the response strategies include establishing a more rigorous requirement change management process and increasing communication and confirmation links with customers; for technical risks, the response strategies include proposing code review and optimization, introducing performance testing tools and security scanning tools, etc.; for the risk of scarce resources, the response strategies include optimizing resource allocation and considering outsourcing or temporarily hiring technical personnel, etc.

[0108] After determining the risk assessment result of the target project, find the target response strategy corresponding to the target project from the response strategy library according to the risk assessment result.

[0109] In some embodiments, visually display the risk assessment results, such as a trend chart of schedule risk and a bar chart of cost risk. Visually display the list and detailed description of the response strategies, as well as the operations that users can perform, such as selecting strategies and adjusting parameters.

[0110] It can be understood that providing an intuitive and clear visual display presents the risk prediction results, risk assessment results, and target response strategies to users in an easy-to-understand and operate manner, providing strong assistance for users' decision-making.

[0111] In the above embodiments, when the risk prediction result indicates that the probability that the target project cannot be completed on schedule is greater than the preset probability, perform a risk assessment based on the pre-established risk assessment database, comprehensive information, and change information to obtain a risk assessment result; determine the target response strategy for the target project according to the pre-established response strategy library and risk type. The embodiments of the present application establish a quantitative and reasonable risk assessment index system, including multiple dimensions such as the likelihood of project risk occurrence, the corresponding impact degree of the risk, and the urgency of the risk, providing a reliable basis for the accurate assessment and priority ranking of risks. And, based on the characteristics of the project, risk assessment results, and the effectiveness of historical response strategies, intelligently generate personalized and highly targeted response strategies to meet the specific needs of different projects. Further, due to fully considering various factors, such as risk type, impact degree, project stage, resource constraints, etc., it can ensure that the response strategies have high feasibility and effectiveness.

[0112] In an exemplary embodiment, a project risk prediction method is provided. Taking the method applied to Figure 1 the server in

[0113] Step 1: Obtain the comprehensive information and change information of the target project.

[0114] Step 2: Perform information preprocessing on the comprehensive information and the change information respectively to obtain the processed comprehensive information and change information.

[0115] Step 3: Input the processed comprehensive information and change information into the factor analysis model. Through the factor analysis model, perform feature extraction on the comprehensive information and change information respectively to obtain multiple candidate influencing factors, perform sorting processing on the multiple candidate influencing factors, and output a factor list according to the sorting result.

[0116] Step 4: Obtain the comprehensive information and change information corresponding to the factor list.

[0117] Step 5: Use the factor analysis model to perform analysis processing on the re-obtained comprehensive information and change information, and update the factor list according to the analysis result.

[0118] Step 6: Obtain the comprehensive information and change information corresponding to the updated factor list.

[0119] Step 7: Input the re-obtained comprehensive information and change information into the risk prediction model for prediction processing to obtain the risk prediction result of the target project.

[0120] Among them, the risk prediction model is obtained by integrating and training multiple different long short-term memory networks and convolutional neural networks using the ensemble learning technique.

[0121] Step 8: In the case where the risk prediction result indicates that the probability that the target project cannot be completed on schedule is greater than the preset probability, perform risk assessment based on the pre-established risk assessment database, comprehensive information, and change information to obtain a risk assessment result; among them, the risk assessment result includes the risk types that cause the target project to not be completed on schedule.

[0122] Step 9: Determine the target response strategy of the target project according to the pre-established response strategy library and risk types.

[0123] The technical solution provided by the embodiment of the present application can significantly improve the quality and efficiency of project risk management. The limitation of traditional project risk management methods lies in over-reliance on manual experience and limited data, which are prone to omissions and misjudgments. However, the embodiment of the present application uses artificial intelligence technology to quickly process a large amount of complex data, more accurately predict potential risks, and provide a scientific basis for project management.

[0124] The technical solution provided by the embodiment of the present application can identify and prevent project risks in advance. It helps the project team detect the signs of risks before they occur or cause serious impacts, so as to take effective preventive measures, take corresponding measures in advance, and prevent the project from developing in a more serious direction.

[0125] The technical solution provided by the embodiments of the present application can optimize resource allocation. Under limited resources, according to the risk prediction results, the human resources including various positions such as development, testing, and operation and maintenance, as well as the test resources, online devices and other resources required for the project are reasonably allocated, and the resources are concentrated on dealing with high-risk areas to improve the utilization efficiency of resources.

[0126] The technical solution provided by the embodiments of the present application brings new management concepts and methods to the industry, improves the management level of the entire industry, and leads project management into a new era of intelligence.

[0127] It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps in other steps.

[0128] Based on the same inventive concept, the embodiments of the present application also provide a project risk prediction device for implementing the above-mentioned project risk prediction method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following project risk prediction device can refer to the limitations on the project risk prediction method in the above text, and will not be repeated here.

[0129] In an exemplary embodiment, as Figure 7 shown, a project risk prediction device is provided, including:

[0130] An information acquisition module 601, configured to acquire the comprehensive information and change information of the target project;

[0131] A factor list determination module 602, configured to analyze and process the comprehensive information and change information by using a pre-trained factor analysis model to obtain a factor list affecting the completion of the target project;

[0132] A risk prediction module 603, configured to perform prediction processing by using a pre-trained risk prediction model and the factor list to obtain a risk prediction result of the target project, where the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

[0133] In one embodiment, the factor list determination module 602 is specifically configured to perform information preprocessing on the comprehensive information and the change information respectively to obtain the processed comprehensive information and change information; input the processed comprehensive information and change information into a factor analysis model, extract features from the comprehensive information and the change information respectively through the factor analysis model to obtain a plurality of candidate influencing factors, perform sorting processing on the plurality of candidate influencing factors, and output a factor list according to the sorting result.

[0134] In one embodiment, the device further includes:

[0135] An information re-acquisition module, configured to acquire the comprehensive information and the change information corresponding to the factor list;

[0136] A list update module, configured to perform analysis processing on the re-acquired comprehensive information and change information by using the factor analysis model, and update the factor list according to the analysis result.

[0137] In one embodiment, the factor list determination module 602 is specifically configured to acquire the comprehensive information and the change information corresponding to the factor list; input the re-acquired comprehensive information and change information into a risk prediction model for prediction processing to obtain a risk prediction result of the target project.

[0138] In one embodiment, the risk prediction model is obtained by integrating and training a plurality of different long short-term memory networks and convolutional neural networks by using an ensemble learning technique.

[0139] In one embodiment, the device further includes:

[0140] A risk assessment module, configured to, when the risk prediction result indicates that the probability that the target project cannot be completed on schedule is greater than a preset probability, perform risk assessment based on a pre-established risk assessment database, the comprehensive information, and the change information to obtain a risk assessment result; wherein, the risk assessment result includes the risk type that causes the target project to not be completed on schedule;

[0141] A coping strategy determination module, configured to determine a target coping strategy for the target project according to a pre-established coping strategy library and the risk type.

[0142] Each module in the above project risk prediction device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above respective modules.

[0143] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store XX data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. The computer program, when executed by the processor, implements a project risk prediction method.

[0144] Those skilled in the art can understand that Figure 8 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0145] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0146] Obtain the comprehensive information and change information of the target project;

[0147] Use a pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a list of factors affecting the completion of the target project;

[0148] Use a pre-trained risk prediction model and the factor list to perform prediction processing to obtain a risk prediction result of the target project, where the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

[0149] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0150] Perform information preprocessing on the comprehensive information and change information respectively to obtain the processed comprehensive information and change information;

[0151] Input the processed comprehensive information and change information into the factor analysis model, extract features from the comprehensive information and change information respectively through the factor analysis model to obtain a plurality of candidate influencing factors, perform sorting processing on the plurality of candidate influencing factors, and output a factor list according to the sorting result.

[0152] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0153] Obtain the comprehensive information and change information corresponding to the factor list;

[0154] Use the factor analysis model to analyze and process the re-obtained comprehensive information and change information, and update the factor list according to the analysis results.

[0155] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0156] Obtain the comprehensive information and change information corresponding to the factor list;

[0157] Input the re-obtained comprehensive information and change information into the risk prediction model for prediction processing to obtain the risk prediction result of the target project.

[0158] In one embodiment, the risk prediction model is obtained by integrating and training multiple different long short-term memory networks and convolutional neural networks using the ensemble learning technique.

[0159] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0160] In the case where the risk prediction result indicates that the probability that the target project cannot be completed on schedule is greater than the preset probability, perform a risk assessment based on the pre-established risk assessment database, comprehensive information, and change information to obtain a risk assessment result; wherein, the risk assessment result includes the risk type that causes the target project to not be completed on schedule;

[0161] Determine the target response strategy for the target project according to the pre-established response strategy library and risk type.

[0162] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0163] Obtain the comprehensive information and change information of the target project;

[0164] Use the pre-trained factor analysis model to analyze and process the comprehensive information and change information to obtain a factor list affecting the completion of the target project;

[0165] Use the pre-trained risk prediction model and the factor list for prediction processing to obtain the risk prediction result of the target project, wherein the risk prediction result is used to represent the probability that the target project cannot be completed on schedule.

[0166] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0167] Preprocess the comprehensive information and the change information respectively to obtain the processed comprehensive information and change information;

[0168] Input the processed comprehensive information and change information into the factor analysis model, extract features from the comprehensive information and change information respectively through the factor analysis model to obtain multiple candidate influencing factors, perform sorting processing on the multiple candidate influencing factors, and output a factor list according to the sorting result.

[0169] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0170] Obtain the comprehensive information and change information corresponding to the factor list;

[0171] Use the factor analysis model to analyze and process the re-obtained comprehensive information and change information, and update the factor list according to the analysis result.

[0172] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0173] Obtain the comprehensive information and change information corresponding to the factor list;

[0174] Input the re-obtained comprehensive information and change information into the risk prediction model for prediction processing to obtain the risk prediction result of the target project.

[0175] In one embodiment, the risk prediction model is obtained by integrating and training multiple different long short-term memory networks and convolutional neural networks using the ensemble learning technique.

[0176] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0177] In the case where the risk prediction result indicates that the probability that the target project cannot be completed on schedule is greater than the preset probability, perform risk assessment based on the pre-established risk assessment database, comprehensive information and change information to obtain a risk assessment result; wherein, the risk assessment result includes the risk type that causes the target project to not be completed on schedule;

[0178] Determine the target coping strategy of the target project according to the pre-established coping strategy library and the risk type.

[0179] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0180] Obtain the comprehensive information and change information of the target project;

[0181] Analyze and process the comprehensive information and change information using a pre-trained factor analysis model to obtain a list of factors affecting the completion of the target project;

[0182] Perform prediction processing using the pre-trained risk prediction model and the list of factors to obtain the risk prediction result of the target project, where the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

[0183] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0184] Perform information preprocessing on the comprehensive information and change information respectively to obtain the processed comprehensive information and change information;

[0185] Input the processed comprehensive information and change information into the factor analysis model, extract features from the comprehensive information and change information respectively through the factor analysis model to obtain multiple candidate influencing factors, perform sorting processing on the multiple candidate influencing factors, and output the list of factors according to the sorting result.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0187] Obtain the comprehensive information and change information corresponding to the list of factors;

[0188] Analyze and process the re-obtained comprehensive information and change information using the factor analysis model, and update the list of factors according to the analysis result.

[0189] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0190] Obtain the comprehensive information and change information corresponding to the list of factors;

[0191] Input the re-obtained comprehensive information and change information into the risk prediction model for prediction processing to obtain the risk prediction result of the target project.

[0192] In one embodiment, the risk prediction model is obtained by integrating and training multiple different long short-term memory networks and convolutional neural networks using the ensemble learning technique.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0194] In the case where the risk prediction result characterizes that the probability that the target project cannot be completed on schedule is greater than the preset probability, perform risk assessment based on the pre-established risk assessment database, comprehensive information and change information to obtain the risk assessment result; where the risk assessment result includes the risk type that causes the target project to not be completed on schedule;

[0195] Determine the target coping strategy for the target project according to the pre-established coping strategy library and risk types.

[0196] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0197] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0198] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0199] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A project risk prediction method, characterized in that: The method comprises: Obtain comprehensive information and change information of target projects; Analyze and process the comprehensive information and the change information using a pre-trained factor analysis model to obtain a list of factors that affect the completion of the target project; The pre-trained risk prediction model and the factor list are used to perform prediction processing to obtain a risk prediction result of the target project, wherein the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

2. The method according to claim 1, characterized in that: The pre-trained factor analysis model is used to analyze and process the comprehensive information and the change information to obtain a list of factors affecting the completion of the target project, including: Preprocessing the comprehensive information and the change information respectively to obtain processed comprehensive information and change information; The processed comprehensive information and change information are input into the factor analysis model, and the factor analysis model is used to extract features of the comprehensive information and the change information to obtain multiple candidate influencing factors, and the multiple candidate influencing factors are sorted, and the factor list is output according to the sorting results.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining comprehensive information and change information corresponding to the factor list; The factor analysis model is used to analyze and process the re-acquired comprehensive information and change information, and the factor list is updated according to the analysis results.

4. The method according to claim 1, characterized in that The predictive processing using the pre-trained risk prediction model and the factor list to obtain the risk prediction result of the target project includes: Obtaining comprehensive information and change information corresponding to the factor list; The re-acquired comprehensive information and change information are input into the risk prediction model for prediction processing to obtain the risk prediction result of the target project.

5. The method according to claim 4, characterized in that The risk prediction model is obtained by integrating and training multiple different long short-term memory networks and convolutional neural networks using ensemble learning technology.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: In the case where the risk prediction result indicates that the probability that the target project cannot be completed on schedule is greater than a preset probability, a risk assessment is performed based on a pre-established risk assessment database, the comprehensive information and the change information to obtain a risk assessment result; wherein the risk assessment result includes the risk type that causes the target project to be unable to be completed on schedule; According to the pre-established response strategy library and the risk type, a target response strategy for the target project is determined.

7. A project risk prediction device, characterized in that: The device comprises: Information acquisition module, used to obtain comprehensive information and change information of target projects; A factor list determination module, used to analyze and process the comprehensive information and the change information using a pre-trained factor analysis model to obtain a list of factors that affect the completion of the target project; The risk prediction module is used to perform prediction processing using a pre-trained risk prediction model and the factor list to obtain a risk prediction result of the target project, wherein the risk prediction result is used to characterize the probability that the target project cannot be completed on schedule.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images