Deviation prediction system and method

Abstract

The invention belongs to the technical field of deviation prediction, and particularly relates to a deviation prediction system and method. The deviation prediction system comprises a planning management module, a recording module, a comparison module and a deviation prediction module. The planning management module is used for determining planning correction data of each task stage according to the task planning data of the target task; the recording module is used for recording execution data of each executed task stage; the comparison module is connected with the planning management module and the recording module, and is used for determining the execution deviation of each executed task stage according to the planning correction data and the execution data; and the deviation prediction module is connected with the comparison module and is used for performing deviation prediction on the non-executed task stage according to the execution deviation of each executed task stage. The problems that in the prior art, due to lack of systematicness and scientificity, deviation is difficult to accurately predict, and deviation cannot be comprehensively analyzed are solved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of deviation prediction, and particularly relates to a deviation prediction system and method. BACKGROUND

[0002] In the oil exploration industry, the planning and management of tasks is crucial. Oil exploration projects usually involve the expenditure of a large number of resources such as equipment, materials and labor, and the timeliness of tasks, and the effectiveness of planning and management directly affects the completion effect of tasks and the consumption of resources. Therefore, using a deviation prediction system can help oil exploration companies better manage task planning and improve the completion effect of tasks.

[0003] In the oil exploration industry, traditional deviation prediction methods often rely on manual experience and simple data comparison, which have the following defects: lack of systematicness and scientificity, difficult to accurately predict deviation trend; unable to comprehensively analyze the causes of cost deviation, resulting in the root of the problem not being solved; lack of real-time and early warning mechanism, difficult to discover and respond to deviation problems in time. SUMMARY

[0004] To solve the above technical problems, the application provides a deviation prediction system and method. The application provides a deviation prediction system, which comprises a planning and management module, a recording module, a comparison module and a deviation prediction module; the planning and management module is used to determine planning correction data of each task stage according to task planning data of a target task, wherein the target task comprises a plurality of task stages; the recording module is used to record execution data of each executed task stage; the comparison module is connected with the planning and management module and the recording module, and is used to determine execution deviation of each executed task stage according to the planning correction data and the execution data; the deviation prediction module is connected with the comparison module, and is used to perform deviation prediction on unexecuted task stages according to the execution deviation of each executed task stage, to obtain deviation prediction results of each unexecuted task stage. The application solves the problems in the prior art that deviation cannot be accurately predicted due to lack of systematicness and scientificity, and deviation cannot be comprehensively analyzed.

[0005] To solve the above technical problems, the application provides a technical solution comprising two aspects.

[0006] In a first aspect, the application provides a deviation prediction system, comprising a planning management module, a record module, a comparison module and a deviation prediction module; the planning management module is configured to determine planning correction data of each task stage according to task planning data of a target task, wherein the target task comprises a plurality of task stages; the record module is configured to record execution data of each executed task stage; the comparison module is connected with the planning management module and the record module, and is configured to determine execution deviation of each executed task stage according to the planning correction data and the execution data; the deviation prediction module is connected with the comparison module, and is configured to perform deviation prediction on unexecuted task stages according to the execution deviation of each executed task stage, to obtain deviation prediction results of each unexecuted task stage.

[0007] In some embodiments, the planning management module comprises: an input acquisition module, a historical data management module, a relationship corresponding module, a historical deviation determination module and a planning data correction module; the input acquisition module is configured to acquire task planning data of a target task, wherein the task planning data comprises: stage task planning data of each task stage, stage time planning data of each task stage, stage resource consumption planning data of each task stage, total task data, total task time consumption data and total task resource consumption data; the historical data management module is configured to record historical task data of completed tasks, wherein the historical task data comprises: historical task execution data and historical task planning data of each historical task, the historical task execution data comprises: stage time historical execution data and stage resource consumption historical execution data of each task stage, and the historical task planning data comprises: historical stage task planning data of each task stage; the relationship corresponding module is connected with the historical data management module and the input acquisition module, and is configured to determine a task corresponding relationship according to the historical task planning data and the task planning data of the target task, determine a stage corresponding relationship of the stage task planning data and the historical stage task planning data of each task stage according to the task corresponding relationship, and determine stage time historical execution data and stage resource consumption historical execution data corresponding to each task stage according to the stage corresponding relationship; the historical deviation determination module is connected with the relationship corresponding module and the input acquisition module, and is configured to determine stage time deviation data of each task stage according to corresponding stage time planning data and stage time historical execution data, and determine stage resource consumption deviation data of each task stage according to corresponding stage resource consumption planning data and stage resource consumption historical execution data; and the planning data correction module is connected with the historical deviation determination module and the input acquisition module, and is configured to determine stage resource consumption correction data and stage time correction data of each task stage according to the stage time deviation data, the stage resource consumption deviation data, the stage time planning data, the stage resource consumption planning data, and the total task time consumption data and the total task resource consumption data of each task stage, and further determine planning correction data of each task stage.

[0008] In some embodiments, the comparison module comprises a time deviation determination module and a resource consumption deviation determination module; wherein the execution data comprises stage time execution data and stage resource consumption execution data of each executed task stage; the time deviation determination module is connected with the record module and the planning data correction module, and is configured to determine a time execution deviation of each executed task stage according to the stage time execution data and stage time correction data of each executed task stage; the resource consumption deviation determination module is connected with the record module and the planning data correction module, and is configured to determine a resource consumption execution deviation of each executed task stage according to the stage resource consumption execution data and stage resource consumption correction data of each executed task stage.

[0009] In some embodiments, the deviation prediction module comprises a deviation reason analysis module and a prediction module; the deviation reason analysis module is connected with the resource consumption deviation determination module and the time deviation determination module, and is configured to determine a deviation reason of each executed task stage according to the resource consumption execution deviation and the time execution deviation of each executed task stage; the prediction module is connected with the deviation reason analysis module and the planning data correction module, and is configured to perform deviation prediction on each unexecuted task stage according to the deviation reason, to obtain a deviation prediction result of each unexecuted task.

[0010] In some embodiments, the system further comprises a warning module, a report generation module and a permission management module; the warning module is connected with the deviation prediction module, and is configured to determine whether to issue a warning according to the deviation prediction result of the deviation prediction module; the report generation module is connected with the record module, the planning management module, the comparison module and the deviation prediction module, and is configured to generate a report according to the planning data, the execution data, the execution deviation and the deviation prediction result of each task stage; and the permission management module is configured to manage the permission of a currently logged-in user.

[0011] In a second aspect, the present application provides a deviation prediction method, comprising: determining planning correction data of each task stage according to task planning data of a target task, wherein the target task comprises a plurality of task stages; obtaining execution data of each executed task stage; determining an execution deviation of each executed task stage according to the planning correction data and the execution data; and performing deviation prediction on an unexecuted task stage according to the execution deviation of each executed task stage, to obtain a deviation prediction result of each unexecuted task stage.

[0012] In some embodiments, determining the planning correction data for each task stage based on the task planning data of the target task includes: acquiring the task planning data of the target task, wherein the task planning data includes: stage task planning data for each task stage, stage time planning data for each task stage, stage resource consumption planning data for each task stage, total task data, total task time data, and total task resource consumption data; acquiring historical task data of completed tasks, wherein the historical task data includes: historical task execution data and historical task planning data for each historical task, wherein the historical task execution data includes: historical execution data of stage time and historical execution data of stage resource consumption for each task stage, and the historical task planning data includes: historical stage task planning data for each task stage; determining the task correspondence based on the historical task planning data and the task planning data of the target task; and determining each task stage based on the task correspondence. The process involves: establishing a phase correspondence between the phase task planning data and the historical phase task planning data; determining the historical execution data of phase time and phase resource consumption corresponding to each task phase based on the phase correspondence; determining the phase time deviation data for each task phase based on the corresponding phase time planning data and the historical execution data of phase time; determining the phase resource consumption deviation data for each task phase based on the corresponding phase resource consumption planning data and the historical execution data of phase resource consumption; determining the phase time correction data for each task phase based on the phase time deviation data, the phase time planning data, and the total task time data; and determining the phase resource consumption correction data for each task phase based on the phase resource consumption deviation data, the phase resource consumption planning data, and the total task resource consumption data, thereby determining the planning correction data for each task phase.

[0013] In some embodiments, the execution data includes: stage time execution data and stage resource consumption execution data for each executed task stage; determining the execution deviation of each executed task stage based on the planning correction data and the execution data includes: determining the time execution deviation of each executed task stage based on the stage time execution data and stage time correction data for each executed task stage; and determining the resource consumption execution deviation of each executed task stage based on the stage resource consumption execution data and stage resource consumption correction data for each executed task stage.

[0014] In some embodiments, the step of predicting deviations for unexecuted task stages based on the execution deviations of each executed task stage to obtain deviation prediction results for each unexecuted task stage includes: determining the cause of deviations for each executed task stage based on the resource consumption execution deviations and time execution deviations of each executed task stage; and predicting deviations for each unexecuted task stage based on the cause of deviations to obtain deviation prediction results for each unexecuted task.

[0015] In some embodiments, the method further includes: obtaining a preset deviation threshold; and determining whether to issue an early warning based on the deviation prediction results of each unexecuted task stage and the deviation threshold.

[0016] The beneficial effects of this invention are as follows: (1) This invention can promptly detect and resolve deviation problems, which helps improve project execution efficiency and ensures that tasks are completed on time and with high quality. (2) By establishing a predictive model and setting early warning indicators, this invention can detect potential deviation problems in advance, which helps to take timely measures to avoid or reduce deviations. (3) Through trend analysis and cause analysis, the predictive model established by this invention can accurately predict the development trend of deviations, which helps managers make timely decisions. Attached Figure Description

[0017] The scope of this disclosure can be better understood by reading the following detailed description of exemplary embodiments in conjunction with the accompanying drawings. The accompanying drawings are:

[0018] Figure 1 This is a schematic diagram of the overall structure of a deviation prediction system provided in an embodiment of this application;

[0019] Figure 2 A rectification flowchart of a deviation prediction method provided in an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0022] If the application documents contain similar descriptions such as "first, second, third", the following explanation shall be added: In the following description, the terms "first, second, third" are used only to distinguish similar objects and do not represent a specific order of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0024] Example 1:

[0025] In the oil exploration industry, traditional deviation prediction methods often rely on manual experience and simple data comparison, which have the following drawbacks: lack of systematicness and scientific rigor, making it difficult to accurately predict deviation trends; inability to comprehensively analyze the causes of cost deviations, resulting in the failure to address the root causes of the problems; and lack of real-time and early warning mechanisms, making it difficult to detect and respond to deviation problems in a timely manner.

[0026] To address the problems existing in the current technology, such as Figure 1 As shown, this application provides a deviation prediction system. The method is applied to electronic devices, and the system can be mounted on servers, mobile terminals, computers, cloud platforms, etc. The functions implemented by the device data processing provided in this application embodiment can be achieved by the processor of the electronic device calling program code, wherein the program code can be stored in a computer storage medium. The deviation prediction system includes: a planning management module 100, a recording module 200, a comparison module 300, and a deviation prediction module 400.

[0027] The planning management module 100 is used to determine the planning correction data for each task stage based on the task planning data of the target task, wherein the target task includes multiple task stages.

[0028] In some embodiments, the planning management module 100 includes: an input acquisition module, a historical data management module, a relationship mapping module, a historical deviation determination module, and a planning data correction module.

[0029] The input acquisition module is used to acquire the task planning data of the target task, wherein the task planning data includes: stage task planning data of each task stage, stage time planning data of each task stage, stage resource consumption planning data of each task stage, total task data, total task time data, and total task resource consumption data.

[0030] The historical data management module is used to record historical task data of completed tasks. The historical task data includes: historical task execution data and historical task planning data for each historical task. The historical task execution data includes: historical execution data of stage time and historical execution data of stage resource consumption for each task stage. The historical task planning data includes: historical stage task planning data for each task stage.

[0031] The relationship correspondence module is connected to the historical data management module and the input acquisition module. It is used to determine the task correspondence relationship based on the historical task planning data and the task planning data of the target task, determine the stage correspondence relationship between the stage task planning data and the historical stage task planning data of each task stage based on the task correspondence relationship, and determine the stage time historical execution data and stage resource consumption historical execution data corresponding to each task stage based on the stage correspondence relationship.

[0032] The historical deviation determination module is connected to the relationship correspondence module and the input acquisition module, and is used to determine the stage time deviation data of each task stage based on the corresponding stage time planning data and the stage time historical execution data, and to determine the stage resource consumption deviation data of each task stage based on the corresponding stage resource consumption planning data and the stage resource consumption historical execution data.

[0033] The planning data correction module is connected to the historical deviation determination module and the input acquisition module, and is used to determine the stage resource consumption correction data and stage time correction data for each task stage based on the stage time deviation data, stage resource consumption deviation data, stage time planning data, stage resource consumption planning data, total task time data, and total task resource consumption data for each task stage, thereby determining the planning correction data for each task stage.

[0034] In practice, task planning data for the target task needs to be manually created based on experience and requirements during task execution. However, since this data is based on experience and requirements, significant deviations are prone to occur during execution. Therefore, this application requires the planning management module 100 to correct the manually created task planning data. During correction, historical data can provide good accuracy, and the historical database contains many historical tasks, but these historical tasks will differ from the target task to varying degrees. Therefore, it is necessary to re-identify the historical task closest to the target task from among these historical tasks, i.e., the task correspondence. Of course, existing technologies can be used to determine the closest historical task, such as calculating the similarity between the target task and historical tasks or other methods. Alternatively, a trained neural network can be used to extract features of the target task, and historical tasks with high feature matching in the historical task database can be searched as the closest historical tasks to establish the task correspondence.

[0035] After establishing the task correspondence, although historical tasks and target tasks are relatively similar, the division of their various stages may not be quite the same. Therefore, it is necessary to map each stage of the target task to each stage of the historical task to form a task correspondence. In forming the task correspondence, the correspondence between each task stage can be determined by calculating similarity or by using neural networks to calculate feature values.

[0036] Once the task relationships are established, the data between each task stage can be mapped. Therefore, historical deviation data can be determined based on the corresponding historical execution data and planning data, and then the corresponding planning data can be corrected based on the historical deviation data to obtain the corrected data.

[0037] The recording module 200 is used to record the execution data of each stage of the executed task.

[0038] Although the corrected data has been adjusted based on historical tasks, various situations can still occur during task execution, leading to discrepancies between the actual execution data and the corrected data. These discrepancies can amplify in subsequent stages. Therefore, to improve the overall execution performance of the target task, task execution records for each executed task stage are recorded, i.e., execution data. This execution data includes: the execution time and resource consumption data for each executed task stage.

[0039] The comparison module 300 is connected to the planning management module 100 and the recording module 200, and is used to determine the execution deviation of each executed task stage based on the planning correction data and the execution data.

[0040] In some embodiments, the comparison module 300 includes: a time deviation determination module and a resource consumption deviation determination module.

[0041] The time deviation determination module is connected to the recording module 200 and the planning data correction module, and is used to determine the time deviation of each executed task stage based on the stage time execution count and stage time correction data of each executed task stage.

[0042] The resource consumption deviation determination module is connected to the recording module 200 and the planning data correction module, and is used to determine the resource consumption execution deviation of each executed task stage based on the stage resource consumption execution data and the stage resource consumption correction data of each executed task stage.

[0043] To achieve good task results, it is essential to consider the execution deviations at each stage. Each task stage can be further divided into different specific tasks during execution. The execution data records the completion time and resources consumed for each specific task. These consumed resources include materials, money, or other resources, all of which can be quantified and statistically analyzed. Therefore, we can determine the execution deviations by comparing the execution time and resource consumption data of each completed task stage with the corresponding corrected execution time and resource consumption data.

[0044] The deviation prediction module 400 is connected to the comparison module 300 and is used to predict the deviation of the unexecuted task stage based on the execution deviation of each executed task stage, so as to obtain the deviation prediction result of each unexecuted task stage.

[0045] In some embodiments, the deviation prediction module 400 includes a deviation cause analysis module and a prediction module.

[0046] The deviation cause analysis module is connected to the resource consumption deviation determination module and the time usage deviation determination module, and is used to determine the deviation cause of each executed task stage based on the resource consumption execution deviation and the time usage execution deviation of each executed task stage.

[0047] The prediction module is connected to the deviation cause analysis module and the planning data correction module, and is used to predict the deviation for each unexecuted task stage based on the deviation cause, so as to obtain the deviation prediction result for each unexecuted task.

[0048] To achieve accurate deviation analysis of the unexecuted task phase, it is essential to analyze the causes of deviations in the executed tasks. This analysis can utilize neural network models or other methods to identify the primary controlling factors causing the deviations and determine their influence coefficients on the deviation outcomes. Then, based on these primary controlling factors and their corresponding influence coefficients, combined with corrected data from the unexecuted task phase, deviation prediction is performed to obtain the predicted results. Of course, the techniques used for prediction can include neural network models or other existing methods.

[0049] The analysis of deviation causes is categorized as needed, including human factors and technical factors. It utilizes an information-based knowledge base and the reasoning capabilities of large models to provide more accurate and comprehensive cause analysis and solution suggestions. Combined with the natural language processing capabilities of large models, it automatically generates detailed deviation cause reports, allowing the report generation module to directly obtain data.

[0050] In some embodiments, the system further includes: an early warning module, a report generation module, and an access control module.

[0051] The early warning module is connected to the deviation prediction module 400 and is used to determine whether to issue an early warning based on the deviation prediction result of the deviation prediction module 400.

[0052] Deviation prediction results can predict the deviations that are most likely to occur in the unexecuted task phase. In order to improve the final task execution effect, certain measures need to be taken based on the prediction results. A simpler approach is to determine whether to issue a deviation warning for the unexecuted task phase based on the preset deviation threshold and the prediction results. This will alert relevant personnel that there may be significant deviations in future task execution, allowing staff to revise the task data in a timely manner to ensure the smooth execution of the task and guarantee its effectiveness.

[0053] The report generation module is connected to the recording module 200, the planning management module 100, the comparison module 300, and the deviation prediction module 400, and is used to generate reports based on the planning data, execution data, execution deviation, and deviation prediction results of each task stage.

[0054] The permission management module is used to manage the permissions of the currently logged-in user.

[0055] Of course, to enable staff and managers to more intuitively understand the task execution progress and the predicted deviations, this system also includes a report generation module. This module can determine the most representative report format based on the data type to generate reports, allowing for better understanding of relevant data during task execution. Given that a system has many functions, and not all staff require them all, this application also includes a permissions management module, granting different access rights to users logging into the system.

[0056] Furthermore, different permissions are set according to user roles to ensure the security and compliance of various operations. Permission management is combined with information-based identity authentication and access control technologies to achieve more granular permission control. At the same time, large-scale models are used to analyze user behavior, promptly identifying abnormal permission operations and potential security risks. The risk assessment capabilities of large-scale models are used to quantitatively assess the potential risks of user permissions.

[0057] The deviation prediction system of this application addresses the problems mentioned in the background technology, such as the lack of systematic and scientific approach, which makes it difficult to accurately predict deviation trends, comprehensively analyze cost deviations, and thus lack real-time performance and early warning mechanisms, hindering timely detection and response to deviations. Therefore, the technical solution of this application can predict deviations based on historical data analysis, trend prediction, and cause classification. Combined with a prediction model and early warning mechanism, it effectively solves the problems existing in the prior art and improves the scientific nature and efficiency of budget management.

[0058] Example 2:

[0059] Regarding the system proposed in Embodiment 1, this application also proposes a deviation prediction method. The method can be applied to servers, mobile terminals, computers, cloud platforms, etc. The functions implemented by the device data processing provided in this application embodiment can be implemented by the processor of the electronic device calling program code, wherein the program code can be stored in a computer storage medium. The deviation prediction method includes:

[0060] Step S1: Determine the planning correction data for each task stage based on the task planning data of the target task, wherein the target task includes multiple task stages.

[0061] In some embodiments, step S1, "determining planning correction data for each task stage based on the task planning data of the target task, wherein the target task includes multiple task stages," includes:

[0062] Step S11: Obtain the task planning data for the target task, wherein the task planning data includes: stage task planning data for each task stage, stage time planning data for each task stage, stage resource consumption planning data for each task stage, total task data, total task time data, and total task resource consumption data.

[0063] Step S12: Obtain historical task data of completed tasks, wherein the historical task data includes: historical task execution data and historical task planning data of each historical task, the historical task execution data includes: historical execution data of stage time and historical execution data of stage resource consumption of each task stage, and the historical task planning data includes: historical stage task planning data of each task stage.

[0064] Step S13: Determine the task correspondence based on the historical task planning data and the target task's task planning data.

[0065] Step S14: Determine the stage correspondence between the stage task planning data and the historical stage task planning data for each task stage based on the task correspondence.

[0066] Step S15: Determine the historical execution data of stage time and stage resource consumption corresponding to each task stage based on the stage correspondence relationship.

[0067] Step S16: Determine the stage time deviation data for each task stage based on the corresponding stage time planning data and the stage time historical execution data.

[0068] Step S17: Determine the stage resource consumption deviation data for each task stage based on the corresponding stage resource consumption planning data and the stage resource consumption historical execution data.

[0069] Step S18: Determine the stage time correction data for each task stage based on the stage time deviation data, the stage time planning data, and the total task time data.

[0070] Step S19: Determine the stage resource consumption correction data for each task stage based on the stage resource consumption deviation data, the stage resource consumption planning data, and the total task resource consumption data, and then determine the planning correction data for each task stage.

[0071] In practice, task planning data for the target task needs to be manually created based on experience and requirements during task execution. However, since this data is based on experience and requirements, significant deviations are prone to occur during execution. Therefore, this application requires a planning management module to correct the manually created task planning data. During correction, historical data can provide good accuracy, and the historical database contains many historical tasks, but these historical tasks will differ from the target task to varying degrees. Therefore, it is necessary to re-identify the historical task closest to the target task from among these historical tasks, i.e., the task correspondence. Of course, existing technologies can be used to determine the closest historical task, such as calculating the similarity between the target task and historical tasks or other methods. Alternatively, a trained neural network can be used to extract features of the target task, and historical tasks with high feature matching in the historical task database can be searched as the closest historical tasks to establish the task correspondence.

[0072] After establishing the task correspondence, although historical tasks and target tasks are relatively similar, the division of their various stages may not be quite the same. Therefore, it is necessary to map each stage of the target task to each stage of the historical task to form a task correspondence. In forming the task correspondence, the correspondence between each task stage can be determined by calculating similarity or by using neural networks to calculate feature values.

[0073] Once the task relationships are established, the data between each task stage can be mapped. Therefore, historical deviation data can be determined based on the corresponding historical execution data and planning data, and then the corresponding planning data can be corrected based on the historical deviation data to obtain the corrected data.

[0074] Step S2: Obtain execution data for each stage of the executed tasks.

[0075] Although the corrected data has been adjusted based on historical tasks, various situations can still occur during task execution, leading to discrepancies between the actual execution data and the corrected data. These discrepancies can amplify in subsequent stages. Therefore, to improve the overall execution performance of the target task, task execution records for each executed task stage are recorded, i.e., execution data. This execution data includes: the execution time and resource consumption data for each executed task stage.

[0076] Step S3: Determine the execution deviation of each executed task stage based on the planning correction data and the execution data.

[0077] In some embodiments, step S3, "determining the execution deviation of each executed task stage based on the planning correction data and the execution data," includes:

[0078] Step S31: Determine the execution time deviation of each executed task stage based on the stage execution time count and stage time correction data of each executed task stage.

[0079] Step S32: Determine the resource consumption execution deviation for each executed task stage based on the stage resource consumption execution data and the stage resource consumption correction data for each executed task stage.

[0080] To achieve good task results, it is essential to consider the execution deviations at each stage. Each task stage can be further divided into different specific tasks during execution. The execution data records the completion time and resources consumed for each specific task. These consumed resources include materials, money, or other resources, all of which can be quantified and statistically analyzed. Therefore, we can determine the execution deviations by comparing the execution time and resource consumption data of each completed task stage with the corresponding corrected execution time and resource consumption data.

[0081] Step S4: Based on the execution deviation of each executed task stage, perform deviation prediction for the unexecuted task stages to obtain the deviation prediction results for each unexecuted task stage.

[0082] In some embodiments, step S4, "predicting deviations for unexecuted task stages based on the execution deviations of each executed task stage, and obtaining deviation prediction results for each unexecuted task stage," includes:

[0083] Step S41: Determine the cause of deviation for each executed task stage based on the resource consumption execution deviation and the time execution deviation for each executed task stage.

[0084] Step S42: Based on the reasons for the deviation, perform deviation prediction for each unexecuted task stage to obtain the deviation prediction results for each unexecuted task.

[0085] To achieve accurate deviation analysis of the unexecuted task phase, it is essential to analyze the causes of deviations in the executed tasks. This analysis can utilize neural network models or other methods to identify the primary controlling factors causing the deviations and determine their influence coefficients on the deviation outcomes. Then, based on these primary controlling factors and their corresponding influence coefficients, combined with corrected data from the unexecuted task phase, deviation prediction is performed to obtain the predicted results. Of course, the techniques used for prediction can include neural network models or other existing methods.

[0086] The analysis of deviation causes is categorized as needed, including human factors and technical factors. It utilizes an information-based knowledge base and the reasoning capabilities of large models to provide more accurate and comprehensive cause analysis and solution suggestions. Combined with the natural language processing capabilities of large models, it automatically generates detailed deviation cause reports, allowing the report generation module to directly obtain data.

[0087] In the process of analyzing the causes of deviations, historical task data can also be used. Furthermore, the deviation data at each stage of the historical task execution can be determined based on the execution data and correction data in the historical task data, and then the causes of deviations can be determined by combining the deviation data at each stage of the target task.

[0088] In the deviation prediction phase, when determining the controlling factors of deviation, the development trend of deviations can be statistically analyzed based on historical data, and the controlling factors can be identified based on this trend. For example, outliers in the development trend can be identified to determine the controlling factors, or significant changes in deviation trends can be used to determine the controlling factors. Then, a prediction model is constructed based on the controlling factors, and the prediction model is used to predict deviations in the unexecuted task phase.

[0089] In some embodiments, the method further includes:

[0090] Step S51: Obtain the preset deviation threshold.

[0091] Step S52: Determine whether to issue an early warning based on the deviation prediction results and the deviation threshold for each unexecuted task stage.

[0092] Deviation prediction results can predict the deviations that are most likely to occur in the unexecuted task phase. In order to improve the final task execution effect, certain measures need to be taken based on the prediction results. A simpler approach is to determine whether to issue a deviation warning for the unexecuted task phase based on the preset deviation threshold and the prediction results. This will alert relevant personnel that there may be significant deviations in future task execution, allowing staff to revise the task data in a timely manner to ensure the smooth execution of the task and guarantee its effectiveness.

[0093] The deviation prediction method of this application can solve the problems mentioned in the background technology, which are difficult to accurately predict deviation trends due to a lack of systematicness and scientific rigor, and are unable to comprehensively analyze cost deviations, resulting in a lack of real-time performance and early warning mechanisms, making it difficult to detect and respond to deviations in a timely manner. Therefore, the technical solution of this application can predict deviations based on historical data analysis, trend prediction, and cause classification. Combined with prediction models and early warning mechanisms, it can effectively solve the problems existing in the prior art and improve the scientificity and efficiency of budget management.

[0094] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. 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.

[0095] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0096] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0098] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. They can be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0099] Furthermore, in the various embodiments of this application, all functional units can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0100] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium, and when the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0101] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a controller to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0102] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A deviation prediction system, characterized in that, include: The module includes a planning management module, a recording module, a comparison module, and a deviation prediction module. The planning management module is used to determine the planning correction data for each task stage based on the task planning data of the target task, wherein the target task includes multiple task stages; The recording module is used to record the execution data of each stage of the executed task; The comparison module is connected to the planning management module and the recording module, and is used to determine the execution deviation of each executed task stage based on the planning correction data and the execution data; The deviation prediction module is connected to the comparison module and is used to predict the deviation of the unexecuted task stage based on the execution deviation of each executed task stage, so as to obtain the deviation prediction result of each unexecuted task stage.

2. The deviation prediction system according to claim 1, characterized in that, The planning management module includes: an input acquisition module, a historical data management module, a relationship mapping module, a historical deviation determination module, and a planning data correction module; The input acquisition module is used to acquire the task planning data of the target task, wherein the task planning data includes: stage task planning data of each task stage, stage time planning data of each task stage, stage resource consumption planning data of each task stage, total task data, total task time data and total task resource consumption data. The historical data management module is used to record historical task data of completed tasks. The historical task data includes: historical task execution data and historical task planning data of each historical task. The historical task execution data includes: historical execution data of stage time and historical execution data of stage resource consumption of each task stage. The historical task planning data includes: historical stage task planning data of each task stage. The relationship correspondence module is connected to the historical data management module and the input acquisition module. It is used to determine the task correspondence relationship based on the historical task planning data and the task planning data of the target task, determine the stage correspondence relationship between the stage task planning data and the historical stage task planning data of each task stage based on the task correspondence relationship, and determine the stage time historical execution data and stage resource consumption historical execution data corresponding to each task stage based on the stage correspondence relationship. The historical deviation determination module is connected to the relationship correspondence module and the input acquisition module, and is used to determine the stage time deviation data of each task stage based on the corresponding stage time planning data and the stage time historical execution data, and to determine the stage resource consumption deviation data of each task stage based on the corresponding stage resource consumption planning data and the stage resource consumption historical execution data. The planning data correction module is connected to the historical deviation determination module and the input acquisition module, and is used to determine the stage resource consumption correction data and stage time correction data for each task stage based on the stage time deviation data, stage resource consumption deviation data, stage time planning data, stage resource consumption planning data, total task time data, and total task resource consumption data for each task stage, thereby determining the planning correction data for each task stage.

3. The deviation prediction system according to claim 2, characterized in that, The comparison module includes: a time deviation determination module and a resource consumption deviation determination module; The execution data includes: the execution time and resource consumption of each executed task stage; The time deviation determination module is connected to the recording module and the planning data correction module, and is used to determine the time deviation of each executed task stage based on the stage time execution count and stage time correction data of each executed task stage. The resource consumption deviation determination module is connected to the recording module and the planning data correction module, and is used to determine the resource consumption execution deviation of each executed task stage based on the stage resource consumption execution data and the stage resource consumption correction data of each executed task stage.

4. The deviation prediction system according to claim 3, characterized in that, The deviation prediction module includes: a deviation cause analysis module and a prediction module; The deviation cause analysis module is connected to the resource consumption deviation determination module and the time usage deviation determination module, and is used to determine the deviation cause of each executed task stage based on the resource consumption execution deviation and the time usage execution deviation of each executed task stage. The prediction module is connected to the deviation cause analysis module and the planning data correction module, and is used to predict the deviation for each unexecuted task stage based on the deviation cause, so as to obtain the deviation prediction result for each unexecuted task.

5. The deviation prediction system according to claim 1, characterized in that, The system also includes: an early warning module, a report generation module, and an access control module; The early warning module is connected to the deviation prediction module and is used to determine whether to issue an early warning based on the deviation prediction result of the deviation prediction module. The report generation module is connected to the recording module, the planning management module, the comparison module, and the deviation prediction module, and is used to generate reports based on the planning data, execution data, execution deviation, and deviation prediction results of each task stage; The permission management module is used to manage the permissions of the currently logged-in user.

6. A deviation prediction method, characterized in that, include: Based on the task planning data of the target task, determine the planning correction data for each task stage, wherein the target task includes multiple task stages; Obtain execution data for each stage of the executed tasks; The execution deviation of each completed task stage is determined based on the planning correction data and the execution data; Based on the execution deviations of each executed task stage, deviation predictions are performed for the unexecuted task stages to obtain the deviation prediction results for each unexecuted task stage.

7. The method according to claim 6, characterized in that, The process of determining the planning correction data for each task stage based on the task planning data of the target task includes: Obtain task planning data for the target task, wherein the task planning data includes: stage task planning data for each task stage, stage time planning data for each task stage, stage resource consumption planning data for each task stage, total task data, total task time data, and total task resource consumption data. Obtain historical task data of completed tasks, wherein the historical task data includes: historical task execution data and historical task planning data of each historical task; the historical task execution data includes: historical execution data of stage time and historical execution data of stage resource consumption of each task stage; and the historical task planning data includes: historical stage task planning data of each task stage. The task correspondence is determined based on the historical task planning data and the target task's task planning data; The phase correspondence between the phase task planning data and the historical phase task planning data for each task phase is determined based on the task correspondence. Based on the aforementioned stage correspondence, determine the historical execution data of stage time and stage resource consumption corresponding to each task stage; The phase time deviation data for each task phase is determined based on the corresponding phase time planning data and the phase time historical execution data. And determine the stage resource consumption deviation data for each task stage based on the corresponding stage resource consumption planning data and the stage resource consumption historical execution data; The stage time correction data for each task stage is determined based on the stage time deviation data, the stage time planning data, and the total task time data for each task stage. Based on the stage resource consumption deviation data, the stage resource consumption planning data, and the total task resource consumption data for each task stage, the stage resource consumption correction data for each task stage is determined, and then the planning correction data for each task stage is determined.

8. The method according to claim 7, characterized in that, The execution data includes: execution time data and resource consumption data for each executed task stage; determining the execution deviation of each executed task stage based on the planning correction data and the execution data includes: The execution time deviation for each executed task stage is determined based on the stage execution time count and stage time correction data for each executed task stage. The resource consumption execution deviation for each executed task stage is determined based on the stage resource consumption execution data and the stage resource consumption correction data for each executed task stage.

9. The method according to claim 8, characterized in that, The step of predicting deviations for unexecuted task stages based on the execution deviations of each executed task stage, to obtain deviation prediction results for each unexecuted task stage, includes: The reasons for the deviations in each executed task stage are determined based on the resource consumption execution deviations and time execution deviations in each executed task stage. Based on the reasons for the deviation, deviation prediction is performed for each stage of the unexecuted task to obtain the deviation prediction results for each unexecuted task.

10. The method according to claim 6, characterized in that, The method further includes: Obtain the preset deviation threshold; Whether to issue an early warning is determined based on the deviation prediction results and the deviation threshold for each unexecuted task phase.

Images