Project plan prediction method, equipment and medium
By combining external data in the market field and internal project data and using LSTM models to predict the project plan, the problem of insufficient prediction accuracy in the existing technology is solved, and more accurate and flexible project plan adjustments are achieved, helping enterprises better respond to market changes. .
Patent Information
- Application Number
- CN202411272228.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-11
- Publication Date
- 2024-12-13
AI Technical Summary
In the context of rapid market changes, existing prediction technologies rely on historical data to insufficient prediction accuracy, and traditional prediction methods are difficult to adapt to rapid market changes, resulting in companies missing opportunities or facing greater risks.
Using external prediction data and internal project data based on market field, project planning prediction is carried out through long and short-term memory network (LSTM) model, and combined with historical project data for training and correction, resource requirements and project plans are generated, and resource allocation and real-time adjustments are made. Task Scheduling.
It improves the accuracy and flexibility of project planning prediction, can respond to market changes more accurately, reduce execution deviations, and improve operational efficiency and market competitiveness.
Smart Images
Figure CN119130063A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of project plan forecasting, and in particular to a method, device and medium for project plan forecasting. Background Art
[0002] In recent years, with the acceleration of digital transformation of enterprises, the application of digital management tools in enterprise management has become increasingly popular. As a kind of digital management tool, the dynamic rolling forecast planning management platform can provide enterprises with more accurate and real-time forecast data, helping enterprises to better respond to market changes and achieve sustainable development.
[0003] Existing forecasting technologies often rely on historical data, but in an environment where the market changes rapidly and uncertainty is high, the reference value of historical data is limited, resulting in insufficient forecasting accuracy. In addition, traditional forecasting methods often use annual or quarterly forecasting cycles, which are difficult to adapt to the rapidly changing needs of the market. In a rapidly changing market environment, an excessively long forecasting cycle may cause companies to miss market opportunities or face greater risks. In addition, some forecasting models fail to fully consider external factors such as market trends and competitor behavior, which also affects the accuracy of the forecast. These forecasting models lack flexibility after they are established and are difficult to adjust in real time according to market changes. This results in the inability of corporate project plans to make effective responses in a timely manner when facing market fluctuations. Summary of the invention
[0004] The present invention provides a method, device and medium for project plan forecasting, which are used to solve the technical problem of insufficient accuracy of existing forecasting methods.
[0005] The present invention adopts the following technical solutions:
[0006] In a first aspect, the present invention provides a method for project plan forecasting, the method comprising: obtaining external forecast data based on the market field corresponding to the current project; obtaining internal forecast data within the executed items of the current project; inputting the internal forecast data and the external forecast data into a pre-trained project plan forecasting model to obtain a forecast result; and adjusting the project plan of the current project based on the forecast result.
[0007] In a possible implementation of the present invention, the external forecast data includes at least development trend data of the market field; the internal forecast data includes at least production data, sales data, maintenance data and financial data of the current project.
[0008] In a possible implementation of the present invention, the training process of the project plan prediction model includes: obtaining a set of historical projects in the same market field as the current project in a completed project library; determining a split ratio of the historical project set based on the proportion of completed items of the current project, the split ratio being a ratio interval including the proportion of completed items; for any project in the historical project set, splitting according to the split ratio to obtain a set of completed items and a set of unfinished items corresponding to the historical project set; using the completed item set as training data to train the project plan prediction model, and using the unfinished item set to correct the training results and the training process.
[0009] In a possible implementation of the present invention, the project planning prediction model is trained using a long short-term memory network LSTM model, and the set of completed items input during training has been processed by time series analysis.
[0010] In a possible implementation of the present invention, obtaining the prediction result includes: receiving the output of the project plan prediction model, the output at least including the resource requirements and project plan corresponding to the current project; the resource requirements are used to indicate the resource information required for the execution of unfinished items in the current project, and the project plan is used to indicate the completion plan data of the unfinished items in the current project.
[0011] In a possible implementation of the present invention, after obtaining the prediction results, the method also includes: adjusting the resource allocation plan of the current project according to the resource requirements, the resources at least including at least one of the human resources, financial resources and computing resources required for the execution of the current project; and adjusting the task scheduling and timetable arrangement of the current project according to the project plan.
[0012] In a possible implementation of the present invention, the method further includes: providing a plan display interface on the front end, wherein the plan display interface is used to display the completion progress of the current project and the adjusted project plan, and supports the generation of project reports.
[0013] In a possible implementation of the present invention, after adjusting the project plan, the method also includes: obtaining the actual execution status of the current project; determining an adjustment optimization plan for the project plan prediction model by comparing the actual execution status and the project plan in the prediction results; and feeding back the adjustment optimization plan to the project plan prediction model so that it performs model optimization according to the adjustment optimization plan.
[0014] In a second aspect, the present invention also provides a device for project plan forecasting, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor so that the at least one processor can execute, based on the market field corresponding to the current project, to obtain external forecast data; to obtain internal forecast data within the executed items of the current project; to input the internal forecast data and the external forecast data into a pre-trained project plan forecasting model to obtain a forecast result; and to adjust the project plan of the current project based on the forecast result.
[0015] In a third aspect, the present invention further provides a non-volatile computer storage medium having computer executable instructions stored thereon, wherein the computer executable instructions are configured to execute, based on the market field corresponding to the current project, obtaining external forecast data; obtaining internal forecast data within the executed items of the current project; inputting the internal forecast data and the external forecast data into a pre-trained project plan forecast model to obtain a forecast result; and adjusting the project plan of the current project based on the forecast result.
[0016] The present invention provides a method, device and medium for project plan prediction, which have the following beneficial effects: by extracting external prediction data and internal prediction data of the project, the project plan is predicted, so that the data used in the prediction is closer to the project itself and the actual situation of the project, and the internal and external situations are comprehensively considered, avoiding the problem of inaccurate prediction results obtained by using historical data for traditional prediction data. At the same time, the model in the present invention is trained using an LSTM neural network, and the data used in the training are data from historical completed projects. The training data is authentic and reliable, which provides a certain guarantee for the effectiveness of the trained model, and when using the trained model, the model can be adjusted or fine-tuned according to the actual situation of the project or the actual situation of the market field, which also ensures the precision or accuracy of the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0018] Figure 1 A flow chart of a method for project planning prediction provided by the present invention;
[0019] Figure 2A project planning forecasting process diagram for an application scenario provided by the present invention;
[0020] Figure 3 A schematic diagram of the structure of a project planning forecasting device provided by the present invention. DETAILED DESCRIPTION
[0021] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in 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 this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0022] The method of the present invention is described in detail below with reference to the accompanying drawings.
[0023] Figure 1 A method flow chart of project planning forecasting provided by the present invention is as follows: Figure 1 As shown, the project planning forecasting method in the present invention at least includes the following execution steps:
[0024] Step 101: Obtain external forecast data based on the market field corresponding to the current project.
[0025] The current project here refers to the project that needs to be planned and predicted, and the plan prediction can predict the future implementation process, implementation progress, resource allocation, completion time and other information of the project through the model. Because the project plan prediction in the present invention is mainly realized through the model, and the use of the model inevitably requires data input, the data input here is the data required for project plan prediction.
[0026] In order to avoid the problem in traditional forecasting methods that the historical data used affects the prediction accuracy of the model, the present invention uses development trend data in the field or industry related to the current project when determining the input data of the model, that is, the aforementioned external forecast data. The so-called development trend data refers to data in the industry or field where the current project is located that can affect the schedule plan of the current project.
[0027] Step 102: Obtain internal prediction data in the executed items of the current project.
[0028] Another part of the data required by the model used in project planning forecasting is internal forecasting data. The so-called internal forecasting data refers to the data obtained from the executed items of the current project. These data may include production data, sales data, maintenance data and financial data related to the current project. It should be noted that the executed items here refer to the content that has been executed in the current project. Based on the production, sales and other data in these contents, as the internal forecasting data, the forecasting data used in the project planning forecasting can be closer to the project itself, thereby ensuring the accuracy or precision of the project planning forecasting results.
[0029] Step 103: Input the internal prediction data and the external prediction data into a pre-trained project planning prediction model to obtain a prediction result.
[0030] After obtaining the internal prediction data and the external prediction data, these two data are input into the pre-trained project planning prediction model, and the prediction results are obtained through the prediction of the model.
[0031] In a possible implementation of the present invention, the project planning prediction model is trained using a long short-term memory network LSTM model, and the training process includes obtaining a set of historical projects in the same market field as the current project in the completed project library, the completed project library stores a number of completed or completed projects, and extracts projects in the same market field or industry as the current project from these projects as a set of historical projects. In an example, projects of the same type as the current project stored in the completed project library can also be extracted to enrich the training data of the model; then, the segmentation ratio range of the historical projects is calculated based on the proportion of completed items in the current project. Assuming that the current project has been completed by 30%, it can be determined The split ratio range is 20%-40%. For a certain historical project, any ratio in the split ratio range is selected for splitting, for example, 35% is split, and the split content is used as the completed items, and the remaining content is used as the unfinished items. A completed item set and an unfinished item set are constructed, and the completed item set is used as training data to train the project plan prediction model. After the training is completed, the unfinished item set is used to correct the training results and the training process. The training result correction here can be to input the completed items of a certain historical project into the model to predict its project plan, and then verify the predicted project plan according to the unfinished items corresponding to the historical project, and adjust the model training through the verification results, so that the trained model has higher accuracy in the end.
[0032] By inputting the above two internal prediction data and external prediction data into the above-mentioned trained project plan prediction model, the resource requirements and project plan corresponding to the current project can be output. It should be noted that before inputting the internal prediction data and external prediction data into the model, since the model used is based on LSTM neural network training, the prediction data needs to be analyzed and processed in time series when inputting the data, which can be understood as inputting the data into the model in time series or processing it in time series before inputting it.
[0033] Step 104: Adjust the project plan of the current project based on the prediction result.
[0034] In one possible implementation of the present invention, the project planning prediction model outputs the prediction results of the current project based on the input internal prediction data and external prediction data. The prediction results here include the resource requirements and project plans corresponding to the current project. The resource requirements here refer to the resource information required to complete the unfinished items in the current project in the future, such as at least one of the human resources, financial resources and computing power resources required to execute the unfinished items, and the project plan refers to the planned data for completing the unfinished items in the current project, such as completion time, completion progress, etc.
[0035] In a possible implementation of the present invention, after obtaining the project plan and resource requirements, the resource allocation plan of the current project can be adjusted according to the project requirements, and the task scheduling and project timetable of the current task can also be adjusted according to the project plan.
[0036] Furthermore, after the adjustment is completed, the current project will continue to be executed based on the adjusted information. After the execution is completed, the actual execution status of the current project is obtained, and the actual execution status is compared with the project plan in the prediction results. When there is a deviation between the two, the optimization adjustment plan of the project plan prediction model is determined based on the deviation, and the plan is fed back to the model to optimize the model so that the project plan predicted by the model is more accurate and precise.
[0037] In one possible implementation of the present invention, a plan display interface can also be provided on the front end of the project monitoring terminal to display the completion progress of the current project and the adjusted project plan, so that project monitoring personnel can obtain the progress of the project in real time. At the same time, the front-end page can also support the generation of data such as project reports, thereby providing further convenience.
[0038] In order to explain the project planning forecasting scheme in the present invention in more detail, the present invention also provides the following supplementary description.
[0039] The present invention mainly focuses on improving the flexibility, accuracy and efficiency of project plan forecasting. Traditional project plan management often relies on static data or simple forecasting models, which is difficult to accurately reflect the rapid changes in the actual environment. Changes in factors such as market environment, resource supply, and technical conditions often lead to the need to adjust the original project plan, and under traditional management methods, the adjustment of project plans often lags behind actual changes, ultimately affecting the execution effect of the project. At the same time, project plan management also involves the collaborative work of multiple departments and teams. Under traditional management methods, poor information communication and low collaborative efficiency are also common problems.
[0040] Figure 2 A project planning forecasting process diagram for an application scenario provided by the present invention, such as Figure 2 As shown in the figure, the project planning and forecasting scheme can also integrate advanced data analysis technology, machine learning algorithms and cloud computing capabilities to achieve real-time monitoring and forecasting of market trends, internal resource status and project progress, so as to formulate more accurate and flexible plans for enterprises, including the following:
[0041] 1) Data collection and integration: Collect data from multiple dimensions such as market, production, sales, finance, etc., and clean and integrate them to form a unified data foundation.
[0042] 2) Dynamic prediction model construction: Use time series analysis, machine learning algorithms (such as long short-term memory LSTM neural network) and other technologies to build a dynamic prediction model to conduct rolling predictions on market changes, resource requirements, project progress, etc.
[0043] 3) Intelligent planning optimization engine: Based on the prediction results, combined with the company's strategic goals and constraints, the plan is automatically adjusted, including resource allocation, task scheduling, timetable adjustment, etc., to maximize the efficiency and effectiveness of plan execution.
[0044] 4) Visual monitoring and interactive interface: Provides an intuitive plan display interface, supports multi-dimensional data analysis and report generation, and enables managers to understand the execution of plans in real time and make necessary manual adjustments.
[0045] 5) Feedback and learning mechanism: The platform continuously collects actual execution data, and continuously optimizes the prediction model and planning optimization algorithm through machine learning mechanism to form a closed-loop feedback system.
[0046] Through the above process, the present invention realizes accurate prediction of project plans, improves the prediction precision and accuracy of project plans, helps enterprises to respond to market fluctuations more efficiently, optimizes project resource allocation, reduces execution deviations of project plans, and improves overall operational efficiency and market competitiveness.
[0047] Based on the same inventive concept, the present invention also provides a project plan forecasting device, the structure of which is as follows: Figure 3 shown.
[0048] Figure 3 A schematic diagram of the structure of a project planning forecasting device provided by the present invention. Figure 3 As shown, the device 300 for project plan prediction in the present invention specifically includes: at least one processor 301; and a memory 303 that is communicatively connected to the at least one processor 301 (connected via a bus 302); wherein the memory 303 stores instructions that can be executed by the at least one processor 301, so that the at least one processor 301 can execute a method for project plan prediction as described in the above embodiment.
[0049] In one possible implementation of the present invention, the aforementioned processor is used to execute: based on the market field corresponding to the current project, obtain external prediction data; obtain internal prediction data within the executed items of the current project; input the internal prediction data and the external prediction data into a pre-trained project plan prediction model to obtain a prediction result; and adjust the project plan of the current project based on the prediction result.
[0050] In addition, the present invention also provides a non-volatile computer storage medium on which computer executable instructions are stored, and the computer executable instructions are configured to execute a project plan forecasting method as described in the above embodiment.
[0051] In one possible implementation of the present invention, the aforementioned computer executable instructions are configured to execute, based on the market field corresponding to the current project, obtaining external forecast data; obtaining internal forecast data within the executed items of the current project; inputting the internal forecast data and the external forecast data into a pre-trained project plan forecast model to obtain a forecast result; and adjusting the project plan of the current project based on the forecast result.
[0052] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0053] The system and medium provided by the present invention correspond one-to-one to the method, and therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.
[0054] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0055] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0056] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0058] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0059] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0060] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0061] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0062] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for project planning forecasting, characterized in that: The method comprises: Obtain external forecast data based on the market area corresponding to the current project; Obtaining internal forecast data within an executed item of the current project; Inputting the internal prediction data and the external prediction data into a pre-trained project plan prediction model to obtain a prediction result; The project plan of the current project is adjusted based on the prediction result.
2. A project plan forecasting method according to claim 1, characterized in that: The external forecast data at least includes development trend data of the market field; The internal forecast data includes at least production data, sales data, maintenance data and financial data of the current project.
3. A project plan forecasting method according to claim 1, characterized in that: The training process of the project plan prediction model includes: Acquire a collection of historical projects in the same market field as the current project in a closed project library; Determine the split ratio of the historical project set according to the proportion of completed items of the current project, where the split ratio is a ratio interval that includes the proportion of completed items; For any item in the historical item set, segmenting is performed according to the segmentation ratio to obtain a completed item set and an uncompleted item set corresponding to the historical item set; The project planning prediction model is trained using the completed item set as training data, and the training result and training process are corrected using the unfinished item set.
4. A project plan forecasting method according to claim 3, characterized in that: The project plan prediction model is trained using a long short-term memory network (LSTM) model, and the completed item set input during training has been processed by time series analysis.
5. A project plan forecasting method according to claim 1, characterized in that: The prediction results obtained include: Receiving an output of the project plan prediction model, the output at least including resource requirements and a project plan corresponding to the current project; The resource requirement is used to indicate the resource information required for executing the unfinished items in the current project, and the project plan is used to indicate the completion plan data of the unfinished items in the current project.
6. A project plan forecasting method according to claim 5, characterized in that: After obtaining the prediction result, the method further includes: Adjust the resource allocation plan of the current project according to the resource demand, wherein the resource includes at least one of human resources, financial resources and computing resources required for the execution of the current project; And, adjusting the task scheduling and timetable arrangement of the current project according to the project plan.
7. A project plan forecasting method according to claim 1, characterized in that: The method further comprises: A plan display interface is provided on the front end, which is used to display the completion progress of the current project and the adjusted project plan, and supports the generation of project reports.
8. A project plan forecasting method according to claim 1, characterized in that: After adjusting the project plan, the method further includes: Obtaining the actual execution status of the current project; By comparing the actual execution status with the project plan in the forecast result, determining an adjustment and optimization plan for the project plan forecast model; The adjustment and optimization plan is fed back to the project planning forecasting model so that the model is optimized according to the adjustment and optimization plan.
9. A device for project planning forecasting, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to: Obtain external forecast data based on the market area corresponding to the current project; Obtaining internal forecast data within an executed item of the current project; Inputting the internal prediction data and the external prediction data into a pre-trained project plan prediction model to obtain a prediction result; The project plan of the current project is adjusted based on the prediction result.
10. A non-volatile computer storage medium having computer executable instructions stored thereon, characterized in that: The computer executable instructions are configured to perform: Obtain external forecast data based on the market area corresponding to the current project; Obtaining internal forecast data within an executed item of the current project; Inputting the internal prediction data and the external prediction data into a pre-trained project plan prediction model to obtain a prediction result; The project plan of the current project is adjusted based on the prediction result.