A big data-based project decision management method

Abstract

The present application relates to the technical field of project management, in particular to a project decision management method based on big data, comprising: collecting data for a target project to form a project data set; splitting the project data set using a variable-length window to obtain a data slice set; filtering personnel change information from the slice data set to obtain a job transfer information set; tracing resource change characteristics of the job transfer information set to construct a resource preemption correlation set; analyzing the resource preemption correlation set to obtain project abnormal risks. The project management scheme in the prior art is difficult to identify the impact on resource consumption rate when personnel cross-sub-project job transfer. Through variable-length window slicing processing of data, a data slice set is obtained, so that the relevant personnel mobilization information in the sub-project is captured, and the resource preemption situation is further judged by tracing the resource change characteristics, and finally the project risk is predicted, realizing more accurate prediction of project risk.

Description

Technical Field

[0001] This invention relates to the field of project management technology, and more specifically to a project decision management method based on big data. Background Technology

[0002] Project decision management is a core control method based on analyzing execution characteristics and predicting abnormal risks through comprehensive project execution data. It directly affects the efficiency of parallel execution of multiple sub-projects and the overall goal achievement rate, and is a key support for the refined management of complex projects. In scenarios where multiple sub-projects are collaboratively promoted, personnel transfer across sub-projects is a common operation during project execution. However, this behavior can easily lead to hidden resource contention issues, resulting in abnormal resource consumption rates and deviations from expected schedules in sub-projects.

[0003] In the prior art, similar technical solutions for predicting personnel changes already exist. For example, patent application CN202110678880.8 discloses an AI and BIM-based IPD (Integrated Design and Production) risk collaborative design management system for building engineering projects. This system includes: a BIM information management module to obtain the three-dimensional structural engineering; a project stage acquisition module to obtain the project stages of the three-dimensional structure during construction in real time; a project stage construction resource allocation module to allocate resources to construction areas within the project stages based on the ideal working efficiency of construction workers from different construction teams; and an actual working efficiency module to obtain the actual working efficiency of construction workers. When resource change risks occur, the resource change risk analysis module reallocates personnel in the construction area based on actual working efficiency, calculates the risk impact after allocation, and adjusts the number of construction workers according to the risk impact until the overall actual efficiency of the construction area meets the requirements. This achieves dynamic adjustment of building engineering project risks under the IPD model, ensuring construction efficiency.

[0004] For example, patent application CN202511537831.7 discloses an adaptive manpower scheduling project management method, system, and computer equipment. The method includes: acquiring an integrated dataset; the dataset includes employee leave data, project data, and human resource data; the employee leave data includes leave applicant information and leave time information; obtaining replacement personnel information based on the project data and human resource data; calculating a project priority score based on the project data, leave applicant information, and replacement personnel information; determining a project scheduling optimization method based on the project priority score and a preset priority threshold; and obtaining a target project scheduling plan based on the project scheduling optimization method, leave time information, project data, and replacement personnel information. This solves the problem of low project scheduling efficiency caused by personnel changes, achieving the effects of reducing reliance on manual project management and improving project scheduling efficiency.

[0005] However, in actual implementation, the inventors found that such technical solutions mostly focus on routine problems such as explicit resource shortages and progress control deviations, while neglecting the easily overlooked implicit triggering link of personnel transfer across sub-projects. This makes it impossible to effectively control the risk of resource anomalies triggered by personnel transfer, ultimately affecting the accuracy and efficiency of project decision-making and management. Summary of the Invention

[0006] To address the aforementioned problems in existing technologies, a project decision management method based on big data is provided.

[0007] The specific technical solution is as follows: A big data-based project decision management method includes: Step S1: Collect data for the target project and preprocess it to form a project data set; Step S2: Use a variable-length window to split the project data set to obtain a data slice set; Step S3: Filter personnel change information from the sliced ​​data set to obtain a set of job transfer information; Step S4: Trace the resource change characteristics of the job transfer information set to construct a resource grabbing association set; Step S5: Analyze the resource preemption association set to obtain project anomaly risks.

[0008] On the other hand, step S1 includes: Step S11: Obtain sub-project information and project-related data for the target project; Step S12: Classify and filter the sub-project information and the project-related data by association attributes, and label the job attributes of the corresponding personnel to obtain a subset of personnel attributes; Step S13: Perform time-series alignment and cleaning on the subset of personnel attributes to obtain the project data set.

[0009] On the other hand, step S2 includes: Step S21: Obtain the sub-project execution cycle duration and personnel change frequency from the project data set; Step S22: Generate the window length according to the ratio of the sub-project execution cycle duration to the personnel change frequency; Step S23: Based on the window length and according to a preset step size, split the project data set to obtain a data slice set.

[0010] On the other hand, step S3 includes: Step S31: Extract social security data, job transfer data, and job completion rate data for each participant from the data slice set; Step S32: Perform rule matching based on the social security data, the job transfer data, and the job completion rate data to generate a set of personnel change types; Step S33: Determine the cross-sub-project transfer scenario based on the set of personnel change types and project execution time, and retrieve the transfer association information of the corresponding personnel; Step S34: Generate the job transfer information set based on the cross-sub-project job transfer scenario and the job transfer association information.

[0011] On the other hand, step S4 includes: Step S41: Obtain the job transfer time point from the job transfer information set, obtain the associated data slice based on the job transfer time point, and filter the resource preemption data and resource consumption rate from the associated data slice based on the change characteristics of resource occupancy data. Step S42: Match resource supply sources according to the resource consumption rate and find the affected sub-project data; Step S43: Generate the resource preemption association set based on the resource preemption data and the affected sub-project data.

[0012] On the other hand, step S5 includes: Step S51: Generate a set of change feature data based on the resource preemption association set; Step S52: Establish an abnormal threshold model for resource consumption rate based on the data slice set; Step S53: Based on the abnormal threshold model of the resource consumption rate, identify the resource consumption rate change data in the change feature data set to obtain the risk result.

[0013] On the other hand, step S51 includes: Step S511: Extract the identification information of the affected sub-items based on the resource preemption association set; Step S512: Extract resource consumption data and progress data from the data slice set according to the identification information, and calculate the resource consumption rate change data and progress achievement rate change data respectively; Step S513: Based on the resource consumption rate change data and the progress achievement rate change data, classify and process them according to the identification information to generate the change feature data set.

[0014] On the other hand, step S52 includes: Step S521: Calculate and statistically analyze the resource consumption distribution characteristics of each type of sub-project based on the data slice set; Step S522: Generate an anomaly threshold model for each type of sub-project by combining the resource consumption distribution characteristics of the sub-projects with a trend fitting algorithm; Step S523: Generate the resource consumption rate abnormal threshold model based on the sub-project abnormal threshold model.

[0015] On the other hand, step S52 includes: Step S531: Adjust the sliding step size of the abnormal threshold model of resource consumption rate according to the statistical results of the data slice set; Step S532: Determine the resource consumption rate change data according to the adjusted resource consumption rate anomaly threshold model to obtain the risk result.

[0016] A storage medium includes computer instructions that, when executed by a computer device, perform the aforementioned project decision management method.

[0017] The above technical solution has the following advantages or beneficial effects: To address the issue that existing project management solutions struggle to identify the impact of personnel reassignment across sub-projects on resource consumption rates, this solution employs a variable-length window to slice data into a data slice set. Based on this, personnel change information is filtered to obtain a reassignment information set, thereby capturing relevant personnel movement within sub-projects. Furthermore, by tracing resource change characteristics, resource contention is assessed, ultimately predicting project risks and achieving a more accurate assessment of project risks. Attached Figure Description

[0018] Embodiments of the invention will be described more fully with reference to the accompanying drawings. However, the drawings are for illustration and explanation only and do not constitute a limitation on the scope of the invention.

[0019] Figure 1 This is an overall schematic diagram of an embodiment of the present invention; Figure 2 This is a schematic diagram of step S1 in an embodiment of the present invention; Figure 3 This is a schematic diagram of step S2 in an embodiment of the present invention; Figure 4 This is a schematic diagram of step S3 in an embodiment of the present invention; Figure 5 This is a schematic diagram of step S4 in an embodiment of the present invention; Figure 6 This is a schematic diagram of step S5 in an embodiment of the present invention; Figure 7 This is a schematic diagram of step S51 in an embodiment of the present invention; Figure 8This is a schematic diagram of step S52 in an embodiment of the present invention; Figure 9 This is a schematic diagram of step S53 in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0022] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but this is not intended to limit the scope of the invention.

[0023] This invention includes: A project decision management method based on big data, such as Figure 1 As shown, it includes: Step S1: Collect data for the target project and preprocess it to form a project data set; Step S2: Use a variable-length window to split the project data set to obtain a data slice set; Step S3: Filter personnel change information from the sliced ​​data set to obtain the job transfer information set; Step S4: Trace the resource change characteristics of the job transfer information set to construct a resource grabbing association set; Step S5: Analyze the resource preemption association set to obtain project anomaly risks.

[0024] Specifically, addressing the issue in existing project management solutions that struggle to identify the impact of personnel reassignment across sub-projects on resource consumption rates, this solution employs a variable-length window to slice data into a data slice set. Based on this, personnel change information is filtered to obtain a reassignment information set, thereby capturing the reassignment information of relevant personnel within sub-projects. Furthermore, by tracing resource change characteristics, resource contention can be assessed, and ultimately, project risks can be predicted, achieving a more accurate assessment of project risks.

[0025] In one embodiment, such as Figure 2 As shown, step S1 includes: Step S11: Obtain sub-project information and project-related data for the target project; Step S12: Classify and filter the sub-project information and project-related data by their associated attributes, and label the corresponding personnel's job attributes to obtain a subset of personnel attributes; Step S13: Perform time-series alignment and cleaning on the subset of personnel attributes to obtain the project data set.

[0026] Specifically, in order to achieve better data collection results, in this embodiment, the sub-project information and project-related data of the target project are first obtained.

[0027] The target project includes the main project and related sub-projects, as well as the corresponding sub-project information. The project-related data includes the association information of personnel and resources, and the implicit verification data of third parties. The implicit verification data of third parties includes social security enrollment records, personnel approval records, and job delivery data, which fully record the association information of the project execution in all dimensions.

[0028] Subsequently, the sub-project information and project-related data are integrated with third-party implicit verification data to form an initial project-related data set. The data is then classified and filtered according to the domain of the main project and the related attributes of the sub-project execution stage to obtain a classified project-related data set. Then, according to the classification of management positions and construction positions, the personnel data in the classified project-related data set are labeled with job attributes one by one, forming a subset of personnel attributes with attribute labels.

[0029] Then, the personnel attribute subset is resampled. During the resampling process, a fixed time unit is set as a unified time granularity according to the regular execution time span of the sub-project. With the start time of the target project as the starting point of the time axis, the progress and resource consumption time series data of all sub-projects in the standardized time series data set are mapped to the same time axis to complete the time series alignment.

[0030] After alignment, the time-series data is standardized by filling in missing values ​​and removing redundant values. Missing data is filled in using the average of data of the same type in the same time period, and redundant data that is collected repeatedly or entered incorrectly is removed, thus obtaining the project data set.

[0031] In one embodiment, such as Figure 3 As shown, step S2 includes: Step S21: Obtain the sub-project execution cycle duration and personnel change frequency from the project data set; Step S22: Generate the window length based on the ratio of the sub-project execution cycle duration to the frequency of personnel changes; Step S23: Split the project data set according to the window length and the preset step size to obtain a data slice set.

[0032] Specifically, addressing the issue that existing technologies use continuous time-series project execution data, which cannot accurately capture the dynamic changes in personnel, resources, and progress at different times, this embodiment first extracts the sub-project execution cycle duration and personnel change frequency from the project dataset. The sub-project execution cycle duration corresponds to the execution cycle of each completed sub-project, and the corresponding personnel change frequency within that sub-project.

[0033] The window length is obtained by calculating the ratio of the sub-project execution cycle duration to the frequency of personnel changes, while the previously calculated uniform single-time granularity of sub-project execution is set as the overall sliding step size.

[0034] Then, the project data set is split into data slices according to the window length and the preset step size. The data slices are then integrated to form a data slice set. This set is a slice data set containing all dimensions of project data, extracted according to the time dimension. Each data slice contains personnel change status, resource consumption data and sub-project progress data within the corresponding time range, realizing the fine-grained time dimension splitting of continuous time series data of the project.

[0035] In one embodiment, such as Figure 4 As shown, step S3 includes: Step S31: Extract social security data, job transfer data, and job completion rate data for each participant from the data slice set; Step S32: Perform rule matching based on social security data, job transfer data, and job completion rate data to generate a set of personnel change types; Step S33: Determine the cross-sub-project transfer scenario based on the set of personnel change types and project execution time, and retrieve the transfer association information of the corresponding personnel; Step S34: Generate a set of job transfer information based on the cross-sub-project job transfer scenario and job transfer association information.

[0036] Specifically, to achieve effective statistics on personnel transfer information across sub-projects, this embodiment first defines three types of personnel changes: full participation, mid-term resignation, and cross-sub-project job transfer, and configures corresponding matching rules. Then, from the data slice set, social security data, job transfer data, and job completion rate data are extracted for each participant and matched using the corresponding matching rules. Based on a multi-dimensional judgment method, each person is judged individually to identify those who have undergone job transfers and label the personnel change type.

[0037] Then, the judgment results are categorized and organized according to the type of personnel change, forming a set of personnel change types that includes all personnel and corresponding work status change type data.

[0038] Based on this, scenarios where personnel are transferred from their original sub-project to other sub-projects within the target project during the incomplete phase of the sub-project execution are identified as cross-sub-project transfer scenarios. Then, the transfer-related information is recorded for each of the selected cross-sub-project transfer scenarios.

[0039] The information associated with job transfers includes the employee's identity information, the original sub-project identifier, the new sub-project identifier, the transfer time, the employee's job type, the resource type associated with the employee, and resource allocation data.

[0040] Finally, the job transfer information of all cross-sub-project job transfer scenarios is integrated to form a job transfer information set containing data corresponding to all cross-sub-project job transfer scenarios, so as to achieve accurate identification of job transfer behavior and standardized collection of core job transfer information.

[0041] In one embodiment, such as Figure 5 As shown, step S4 includes: Step S41: Obtain the job transfer time point from the job transfer information set, obtain the associated data slice based on the job transfer time point, and filter the resource preemption data and resource consumption rate from the associated data slice based on the change characteristics of resource occupancy data. Step S42: Match resource supply sources based on resource consumption rates and locate data on affected sub-projects; Step S43: Generate a resource preemption association set based on the resource preemption data and the affected sub-project data.

[0042] Specifically, to identify resource usage, the system first extracts the transfer time point from the transfer information set. Using this time point as a dividing point, it extracts corresponding data slices before and after the transfer from the data slice set using a truncation length. This allows the system to trace the changes in the progress speed, resource consumption rate, and resource grabbing data of the new sub-project to which the transferred personnel belong. Among these, the resource grabbing data refers to the speed and proportion of resources acquired by the sub-project.

[0043] Then, based on the resource allocation ledger of the new sub-project, the key values ​​of the corresponding resource occupancy column are extracted, the resource types and resource suppliers corresponding to the changes in resource consumption of the new sub-project are sorted out, the resource sources and supply scope are obtained, and other sub-projects that share the same resources with the above-mentioned resource suppliers are screened out based on the resource sources and supply scope.

[0044] Subsequently, the associated data of the new sub-projects, affected sub-projects, resource types, and supply entities are integrated to form a resource grabbing association set that records the relationship between the relevant entities and resource types. This establishes a direct link between job transfer behavior and resource grabbing, and accurately identifies the sub-projects and resource types involved in resource grabbing.

[0045] In one embodiment, such as Figure 6 As shown, step S5 includes: Step S51: Generate a set of change feature data based on the resource preemption association set; Step S52: Establish an abnormal threshold model for resource consumption rate based on the data slice set; Step S53: Based on the abnormal threshold model of resource consumption rate, identify the resource consumption rate change data in the change feature data set to obtain the risk result.

[0046] Specifically, in order to effectively extract the risk of resource occupation changes caused by personnel reassignment, this embodiment first generates a set of change feature data based on the resource preemption association set, which describes the trend of numerical changes of the sub-items corresponding to the preempted resources, and extracts the data of the corresponding sub-items as samples based on the completed sub-items in the data slice set. Then, modeling is performed to obtain the threshold of abnormal resource consumption rate in the corresponding sub-items, and a resource consumption rate abnormal threshold model is established.

[0047] Finally, an abnormal threshold model for resource consumption rate is used to identify various data in the slice to indicate risk items.

[0048] In one embodiment, such as Figure 7 As shown, step S51 includes: Step S511: Extract the identification information of the affected sub-projects based on the resource preemption association set; Step S512: Extract resource consumption data and progress data from the data slice set based on the identification information, and calculate the resource consumption rate change data and progress achievement rate change data respectively; Step S513: Based on the resource consumption rate change data and the progress achievement rate change data, classify and process them according to the identification information to generate a set of change feature data.

[0049] Specifically, in order to obtain the sub-projects to be modeled later, in this embodiment, the identification information of the affected sub-projects is first extracted from the resource preemption association set, and the resource consumption data and progress data of the affected sub-projects before and after the resources are preempted are retrieved from the sliding window data slice set based on the identification information. Subsequently, by comparing the resource consumption data of the affected sub-projects before and after the resources were preempted, the change in resource consumption per unit time was calculated to obtain the resource consumption rate change data; by comparing the progress data of the affected sub-projects before and after the resources were preempted, the change in the progress completion ratio was calculated to obtain the progress achievement rate change data. All data on changes in resource consumption rates and schedule achievement rates of affected sub-projects are categorized and organized according to sub-project identifiers, and integrated into a set of change feature data that records the characteristics of resource and schedule changes in affected sub-projects. This enables quantitative analysis and feature solidification of the impact of resource grabbing on project execution.

[0050] In one embodiment, such as Figure 8 As shown, step S52 includes: Step S521: Calculate and statistically analyze the resource consumption distribution characteristics of each type of sub-project based on the data slice set; Step S522: Combine the resource consumption distribution characteristics of sub-projects with a trend fitting algorithm to generate an anomaly threshold model for each type of sub-project; Step S523: Generate a resource consumption rate abnormal threshold model based on the sub-project abnormal threshold model.

[0051] Specifically, after constructing the above data slice set, according to the corresponding sub-projects that need to be predicted, the corresponding entries are extracted from the data slice set, and the historical resource consumption rate data of the executed sub-projects are obtained, and the resource consumption distribution characteristics of the sub-projects are calculated respectively.

[0052] Then, by combining the trend fitting algorithm, we can train the sub-item anomaly threshold model for each type of resource and each type of sub-item. We then integrate all the trained sub-item anomaly threshold models to form a set of resource consumption rate anomaly threshold models.

[0053] In one embodiment, such as Figure 9 As shown, step S52 includes: Step S531: Adjust the sliding step size of the abnormal threshold model for resource consumption rate based on the statistical results of the data slice set; Step S532: Based on the adjusted abnormal threshold model of resource consumption rate, the data on changes in resource consumption rate are judged to obtain the risk result.

[0054] Specifically, after constructing the aforementioned model, based on historical data statistics of the sliding window data slice set, the standard for determining the number of consecutive sliding steps is determined. This standard is the maximum number of steps in which the resource consumption rate of the same type of sub-project and the same type of resources continuously exceeds the threshold during the historical normal execution process, plus one. Then, for each affected sub-project in the resource preemption association set according to resource type and sub-project type, match the corresponding model in the resource consumption rate abnormal threshold model set, and compare the actual resource consumption rate of the affected sub-project with the abnormal threshold in the matching model one by one.

[0055] Finally, when the actual resource consumption rate continuously reaches the sliding step size of the above-mentioned judgment quantity standard and exceeds the abnormal threshold, it is judged as an abnormal risk in project decision-making and management and an early warning signal is issued. This abnormal risk is a risk state in which the execution of sub-projects deviates from expectations due to resource grabbing, thus realizing accurate quantitative judgment and risk warning of resource anomalies triggered by job transfer.

[0056] A storage medium includes computer instructions that, when executed by a computer device, perform the aforementioned project decision management method.

[0057] Those skilled in the art will understand that various aspects, or possible implementations of various aspects, of the present invention can be embodied as systems, methods, or computer program products. Therefore, various aspects, or possible implementations of various aspects, of the present invention can take the form of entirely hardware embodiments, entirely software embodiments (including firmware, resident software, etc.), or embodiments combining software and hardware aspects, all collectively referred to herein as "circuit," "module," or "system." Furthermore, various aspects, or possible implementations of various aspects, of the present invention can take the form of computer program products, which are computer instructions stored in memory.

[0058] The memory can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or apparatuses, or any suitable combination thereof, such as random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, and portable read-only memory (CD-ROM).

[0059] A processor in a computer reads computer instructions stored in memory, enabling the processor to execute the functional actions specified in each step or combination of steps in a flowchart; and to generate means for implementing the functional actions specified in each block or combination of blocks in a flowchart.

[0060] It should be understood that a processor in a computer can be understood as one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components used to execute the aforementioned computer instructions.

[0061] Computer instructions may be executed entirely on the user's local computer, partially on the user's local computer, as a separate software package, partially on the user's local computer and partially on a remote computer, or entirely on a remote computer or server. It should also be noted that in some alternative implementations, the functions indicated by the steps in the flowchart or the blocks in the block diagram may not occur in the order shown in the diagram. For example, depending on the functions involved, two consecutive steps or blocks may actually be executed approximately simultaneously, or these blocks may sometimes be executed in reverse order.

[0062] Of course, in practical applications, the various components of a computer system are coupled together through a bus system. The bus system is used to enable communication and connection between these components. In addition to the data bus, the bus system also includes a power bus, a control bus, and a status signal bus.

[0063] The above are merely preferred embodiments of the present invention and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should recognize that any equivalent substitutions and obvious changes made based on the description and illustrations of the present invention should be included within the protection scope of the present invention.

Claims

1. A project decision management method based on big data, characterized in that, include: Step S1: Collect data for the target project and preprocess it to form a project data set; Step S2: Use a variable-length window to split the project data set to obtain a data slice set; Step S3: Filter personnel change information from the sliced ​​data set to obtain a set of job transfer information; Step S4: Trace the resource change characteristics of the job transfer information set to construct a resource grabbing association set; Step S5: Analyze the resource preemption association set to obtain project anomaly risks.

2. The project decision management method according to claim 1, characterized in that, Step S1 includes: Step S11: Obtain sub-project information and project-related data for the target project; Step S12: Classify and filter the sub-project information and the project-related data by association attributes, and label the job attributes of the corresponding personnel to obtain a subset of personnel attributes; Step S13: Perform time-series alignment and cleaning on the subset of personnel attributes to obtain the project data set.

3. The project decision management method according to claim 1, characterized in that, Step S2 includes: Step S21: Obtain the sub-project execution cycle duration and personnel change frequency from the project data set; Step S22: Generate the window length according to the ratio of the sub-project execution cycle duration to the personnel change frequency; Step S23: Based on the window length and according to a preset step size, split the project data set to obtain a data slice set.

4. The project decision management method according to claim 1, characterized in that, Step S3 includes: Step S31: Extract social security data, job transfer data, and job completion rate data for each participant from the data slice set; Step S32: Perform rule matching based on the social security data, the job transfer data, and the job completion rate data to generate a set of personnel change types; Step S33: Determine the cross-sub-project transfer scenario based on the set of personnel change types and project execution time, and retrieve the transfer association information of the corresponding personnel; Step S34: Generate the job transfer information set based on the cross-sub-project job transfer scenario and the job transfer association information.

5. The project decision management method according to claim 1, characterized in that, Step S4 includes: Step S41: Obtain the job transfer time point from the job transfer information set, obtain the associated data slice based on the job transfer time point, and filter the resource preemption data and resource consumption rate from the associated data slice based on the change characteristics of resource occupancy data. Step S42: Match resource supply sources according to the resource consumption rate and find the affected sub-project data; Step S43: Generate the resource preemption association set based on the resource preemption data and the affected sub-project data.

6. The project decision management method according to claim 1, characterized in that, Step S5 includes: Step S51: Generate a set of change feature data based on the resource preemption association set; Step S52: Establish an abnormal threshold model for resource consumption rate based on the data slice set; Step S53: Based on the abnormal threshold model of the resource consumption rate, identify the resource consumption rate change data in the change feature data set to obtain the risk result.

7. The project decision management method according to claim 6, characterized in that, Step S51 includes: Step S511: Extract the identification information of the affected sub-items based on the resource preemption association set; Step S512: Extract resource consumption data and progress data from the data slice set according to the identification information, and calculate the resource consumption rate change data and progress achievement rate change data respectively; Step S513: Based on the resource consumption rate change data and the progress achievement rate change data, classify and process them according to the identification information to generate the change feature data set.

8. The project decision management method according to claim 6, characterized in that, Step S52 includes: Step S521: Calculate and statistically analyze the resource consumption distribution characteristics of each type of sub-project based on the data slice set; Step S522: Generate an anomaly threshold model for each type of sub-project by combining the resource consumption distribution characteristics of the sub-projects with a trend fitting algorithm; Step S523: Generate the resource consumption rate abnormal threshold model based on the sub-project abnormal threshold model.

9. The project decision management method according to claim 6, characterized in that, Step S52 includes: Step S531: Adjust the sliding step size of the abnormal threshold model of resource consumption rate according to the statistical results of the data slice set; Step S532: Determine the resource consumption rate change data according to the adjusted resource consumption rate anomaly threshold model to obtain the risk result.

10. A storage medium comprising computer instructions, characterized in that, When the computer device executes the computer instructions, it performs the project decision management method as described in any one of claims 1-9.

Images