Project progress estimation method and system, electronic equipment and storage medium

Abstract

The invention provides a project progress estimation method and system, electronic equipment and a storage medium, and the method comprises the steps: determining a K value parameter of a to-be-established project progress estimation model according to historical task data and a preset algorithm, and establishing the project progress estimation model according to the K value parameter; obtaining task feature data of a target project task to be subjected to project progress estimation at present; estimating a target value of the target project task by using a project progress estimation model according to the task feature data of the target project task; and calculating the project progress of the target project task according to the target value of the target project task.

Description

Technical Field

[0001] The present invention relates to the fields of project management and information technology, and more specifically, to a project progress estimation method, system, electronic device, and storage medium. Background Art

[0002] With the rapid development of technological innovation, scientific research institutions are facing higher requirements for R & D cycles and R & D efficiency, increasing project scales and complexities, and a large number of participants, etc., resulting in difficulties in project progress control; if the project progress is not properly controlled, it will affect the work mood of R & D entities. Thus, it can be seen that project progress control is one of the most important links in the project R & D process; moreover, management needs to conduct refined management of a large number of projects, intervene in a timely manner when project progress problems occur, find out the reasons for the progress lag, and coordinate resources for handling. Currently, project leaders in scientific research institutions are generally professional R & D personnel, and their project management levels vary. Project management tools on the market also cannot achieve sufficient refinement and reasonable progress estimation; for scientific research institutions, to master the progress of a large number of projects, a unified standard and business system are required to objectively reflect the project progress in a timely manner.

[0003] Therefore, how to provide a project progress estimation method that can accurately and reasonably estimate the project progress, and at the same time objectively reflect the project progress in a unified standard is an urgent problem to be solved in the present application. Summary of the Invention

[0004] In view of this, the present invention provides a project progress estimation method, system, electronic device, and storage medium, aiming to accurately and reasonably estimate the project progress, and at the same time objectively reflect the project progress in a unified standard.

[0005] The first aspect of the present application provides a project progress estimation method, and the method includes:

[0006] Determine the K - value parameter of the project progress estimation model to be established according to historical task data and a preset algorithm, and establish a project progress estimation model according to the K - value parameter;

[0007] Obtain the task feature data of the target project task for which the project progress is to be estimated currently;

[0008] Use the project progress estimation model to estimate the target value of the target project task according to the task feature data of the target project task;

[0009] Calculate the project progress of the target project task according to the target value of the target project task.

[0010] Optionally, determining the K-value parameter of the project progress prediction model to be established according to historical task data and a preset algorithm, and establishing a project progress prediction model according to the K-value parameter includes:

[0011] Obtain historical task data, and extract historical task feature data of each historical project task from the historical task data;

[0012] Select a plurality of target historical project tasks from each of the historical project tasks according to the historical task feature data of each of the historical project tasks;

[0013] Determine the K-value parameter of the project progress prediction model to be established according to a preset algorithm and each of the target historical project tasks, and establish a project progress prediction model according to the K-value parameter.

[0014] Optionally, the historical task feature data of the historical project task at least includes the task type and the start and end times of task execution of the historical project task;

[0015] Selecting a plurality of target historical project tasks from each of the historical project tasks according to the historical task feature data of each of the historical project tasks includes:

[0016] Obtain a preset time period and the target task type of the target project task for which the current project progress is to be predicted;

[0017] Select a plurality of initial historical project tasks from each of the historical project tasks whose start and end times of task execution are within the preset time period;

[0018] Select a plurality of target historical project tasks from each of the initial historical project tasks whose task type is the target task type.

[0019] Optionally, determining the K-value parameter of the project progress prediction model to be established according to a preset algorithm and each of the target historical project tasks, and establishing a project progress prediction model according to the K-value parameter includes:

[0020] Perform data cleaning on the historical task feature data of each of the target historical project tasks, and perform normalization processing on the historical task feature data of each of the target historical project tasks after data cleaning to obtain the normalized data of each of the target historical project tasks, where the normalized data at least includes the target value of the target historical project task, and the target value is the value obtained by normalizing the task completion time in the historical task feature data of the target historical project task;

[0021] Divide each of the target historical project tasks into a training sample set and a test sample set; wherein, the training sample set includes multiple training samples, and the test set includes multiple test samples;

[0022] For each test sample, use a preset algorithm to calculate the distance between the test sample and each training sample according to the n-dimensional feature vector of the test sample and the n-dimensional feature vectors of each training sample;

[0023] According to the distances between the test sample and each training sample, select a target training sample set that matches the test sample from each of the training samples; wherein, the target training sample set includes multiple target training samples;

[0024] According to the distances between the test sample and each target training sample and the actual completion time of each target training sample, calculate the predicted target value of the test sample;

[0025] Calculate the sum of squared errors according to the predicted target values and the target values of each of the test samples;

[0026] Reduce the number of training samples in the training sample set and increase the number of test samples in the test sample set to update the training sample set and the test sample set, and increment the corresponding update count by 1;

[0027] Determine whether the updated count after incrementing by 1 reaches the target update count; wherein, the target update count is a positive integer greater than 1;

[0028] If the target update count is not reached, return to execute for each test sample, use a preset algorithm to calculate the distance between the test sample and each training sample according to the n-dimensional feature vector of the test sample and the n-dimensional feature vectors of each training sample;

[0029] If the target update count is reached, determine the K-value parameter of the project progress prediction model to be trained according to each sum of squared errors, and establish a project progress prediction model according to the K-value parameter.

[0030] Optionally, the method further includes:

[0031] Generate and output project progress warning information for the target project task according to the task feature data and the project progress of the target project task.

[0032] The second aspect of this application provides a project progress prediction system, the system includes:

[0033] A model building unit, configured to determine the K value parameter of the project progress prediction model to be built according to historical task data and a preset algorithm, and build a project progress prediction model according to the K value parameter;

[0034] A first acquisition unit, configured to acquire the task feature data of the target project task for which the project progress is to be predicted currently;

[0035] A prediction unit, configured to predict the target value of the target project task by using the project progress prediction model according to the task feature data of the target project task;

[0036] A first calculation unit, configured to calculate the project progress of the target project task according to the target value of the target project task.

[0037] Optionally, the model building unit includes:

[0038] A second acquisition unit, configured to acquire historical task data and extract the historical task feature data of each historical project task from the historical task data;

[0039] A first screening unit, configured to screen out a plurality of target historical project tasks from each of the historical project tasks according to the historical task feature data of each of the historical project tasks;

[0040] A first model building subunit, configured to determine the K value parameter of the project progress prediction model to be built according to a preset algorithm and each of the target historical project tasks, and build a project progress prediction model according to the K value parameter.

[0041] Optionally, the historical task feature data of the historical project task at least includes the task type and the start and end times of task execution of the historical project task, and the first screening unit includes:

[0042] A third acquisition unit, configured to acquire a preset time period set in advance and the target task type of the target project task for which the project progress is to be predicted currently;

[0043] A first screening subunit, configured to screen out a plurality of initial historical project tasks from each of the historical project tasks, the start and end times of task execution of which are within the preset time period;

[0044] A second screening subunit, configured to screen out a plurality of target historical project tasks from each of the initial historical project tasks, the task type of which is the target task type.

[0045] A third aspect of the present application provides an electronic device, including: a processor and a memory, where the processor and the memory are connected through a bus; wherein, the processor is configured to call and execute a program stored in the memory; the memory is configured to store a program, and the program is used to implement a project progress prediction method provided in the first aspect of the present application.

[0046] A fourth aspect of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are used to execute a project progress prediction method provided in the first aspect of the present application.

[0047] The present application provides a project progress prediction method, system, electronic device and storage medium. By determining the K value parameter of the project progress prediction model to be established according to historical task data and a preset algorithm, and establishing a project progress prediction model according to the K value parameter; obtaining task feature data of a target project task for which project progress prediction is to be performed currently; using the project progress prediction model to calculate a target value of the target project task according to the task feature data of the target project task; calculating the project progress of the target project task according to the target value of the target project task. It can be seen that the present application pre-establishes a corresponding project progress prediction model so as to use the project progress prediction model to predict the project progress of the target project task according to the task feature data of the target project task for which project progress prediction is to be performed currently. Compared with the existing manual prediction method, the present application can not only accurately and reasonably predict the project progress, but also objectively reflect the progress of the project with a unified standard. Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0049] Figure 1 It is a schematic flowchart of a project progress prediction method provided by an embodiment of the present application;

[0050] Figure 2 It is a schematic flowchart of a method for determining the K value parameter of a project progress prediction model to be established according to historical task feature data in historical task data and a preset algorithm, and establishing a project progress prediction model according to the K value parameter provided by an embodiment of the present application;

[0051] Figure 3 It is a schematic structural diagram of a project progress prediction system provided by an embodiment of the present invention;

[0052] Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0054] In the present application, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0055] See Figure 1 , which shows a flowchart of a project progress prediction method provided by an embodiment of the present application. The process of the project progress prediction method specifically includes the following steps:

[0056] S101: Determine the K value parameter of the project progress prediction model to be established according to the historical task feature data and the preset algorithm in the historical task data, and establish the project progress prediction model according to the K value parameter.

[0057] In the process of specifically executing step S101, historical task data can be obtained, and the historical task feature data and the preset algorithm of each historical project task can be extracted from the historical task data to determine the K value parameter of the project progress prediction model to be established, and the project progress prediction model can be established according to the K value parameter.

[0058] See Figure 2 , which shows a flowchart of a method for determining the K value parameter of the project progress prediction model to be established according to the historical task feature data and the preset algorithm in the historical task data, and establishing the project progress prediction model according to the K value parameter. The method specifically includes the following steps:

[0059] S201: Obtain historical task data, and extract historical task feature data of each historical project task from the historical task data.

[0060] In the specific process of executing step S201, obtain historical task data, and perform preprocessing operations such as data cleaning on the historical task data, so as to extract historical task feature data of each historical project task in the historical task data after the preprocessing operation.

[0061] It should be noted that the historical task feature data of the historical project task at least includes task-related parameters, user-related parameters of the users participating in the historical tasks in the historical project task, other related parameters, etc., which are not limited in the embodiments of the present application herein.

[0062] It should also be noted that the task-related parameters of the historical project task at least include: project level, belonging stage, stage type, person in charge, participants, start and end time of task execution, task type, quantity, task content, involved processes, test plan, whether parallel, related equipment, related materials, etc. parameters related to the historical project task; the user-related parameters of the historical project task at least include: professional skill level, performance level, age, working years, etc. related parameters of the users participating in the historical project task; the other related parameters of the historical project task at least include: status, use, procurement cycle, etc. related parameters of the equipment and related materials involved in the execution process of the historical project task.

[0063] For example, the parameters of the task-related parameters in the historical task feature data of each historical project task extracted from the historical task project data are shown in Table 1:

[0064] Table 1:

[0065] Task Type Responsible Person Participants Start Time Number of Process Nodes Project Level Quantity Equipment Materials End Time Chemical Inspection Zhang San Liu Yi, Huang Er 2021.06.0509：23：12 9 A 15 Hydrogen, Oxygen, Nitrogen Analyzer 2021.06.0909：56：00 Chemical Inspection Zhao Si Zhang San 2023.07.1115：25：11 9 B 75 ICP Hydrochloric Acid 2023.07.1609：58：11 Chemical Inspection Li Si Wang Er 2023.01.1210：05：45 9 C 3 Spectrometer 2023.01.1419：08：38 Chemical Inspection Li Wu Deng San 2022.06.2511：15：02 9 B 8 Spectrometer Sulfuric Acid 2022.06.2816：17：00

[0066] It should be noted that as can be seen from Table 1, the currently obtained historical task data altogether includes 4 historical project historical task-related parameters.

[0067] S202: Screen out multiple target historical project tasks from each historical project task according to the historical task feature data of each historical project task.

[0068] In the specific process of executing step S202, obtain the target task type of the target project task for which the progress needs to be estimated currently, and screen out multiple target historical project tasks from each historical project task according to the preset time, target task type, and historical task feature data of each historical project task, so that the screened target historical project tasks can be used to establish a more accurate project progress prediction model for predicting the project progress of the target project task subsequently.

[0069] Optionally, the historical task feature data of the historical project tasks includes at least the task type and the start and end times of task execution of the historical project tasks. The process of screening out multiple target historical project tasks from each historical project task according to the historical task feature data of each historical project task may be as follows: obtaining a preset time period set in advance and the target task type of the target project task for which the current project progress is to be estimated; screening out multiple initial historical project tasks from each historical project task whose start and end times of task execution are within the preset time period; and screening out multiple target historical project tasks from each initial historical project task whose task type is the target task type.

[0070] It should be noted that the preset time period may be within the past two years. For example, multiple initial historical project tasks within the past two years can be screened out from each historical project task, so that the task data source for establishing the project progress estimation model can be closer to the current technical level. At the same time, screening out target historical project tasks with the same target task type from each initial historical project task can improve the accuracy of the project progress estimation of the project progress estimation model established using historical project tasks.

[0071] It should also be noted that screening out target historical project tasks with the same target task type from each initial historical project task can ensure that the task types of each target historical project task used when establishing the project progress estimation model are consistent, that is, ensure that the types of each historical project task are the same when performing subsequent corresponding calculations.

[0072] S203: Determine the K-value parameter of the project progress estimation model to be established according to the preset algorithm and each target historical project task, and establish the project progress estimation model according to the K-value parameter.

[0073] In the process of specifically executing step S203, after screening out each target historical project task, the historical task feature data of each historical project task can be processed to obtain the normalized data of each historical project task; divide each target historical project task into a training sample set and a test sample set; where the training sample set includes multiple training samples, and the test set includes multiple test samples; for each test sample, calculate the predicted target value of the test sample according to the test sample and each training sample; according to the predicted target values and target values of each test sample, calculate the sum of squared errors; update the training sample set and the test sample set, and increment the corresponding number of updates by 1; determine whether the incremented number of updates reaches the target number of updates; where the target number of updates is a positive integer greater than 1; if the target number of updates is not reached, return to the step of calculating the predicted target value of each test sample according to the test sample and each training sample; if the target number of updates is reached, determine the K-value parameter of the project progress prediction model to be trained according to each sum of squared errors, and establish a project progress prediction model according to the K-value parameter.

[0074] Optionally, determining the K value parameter of the project progress prediction model to be established according to a preset algorithm and each target historical project task, and the process of establishing the project progress prediction model according to the K value parameter can be specifically as follows: cleaning the historical task feature data of each target historical project task, and normalizing the historical task feature data of each target historical project task after data cleaning to obtain the normalized data of each target historical project task, where the normalized data at least includes the target value of the target historical project task, and the target value is the value obtained by normalizing the task completion time in the historical task feature data of the target historical project task; dividing each target historical project task into a training sample set and a test sample set; where the training sample set includes multiple training samples, and the test set includes multiple test samples; for each test sample, using a preset algorithm to calculate the distance between the test sample and each training sample according to the n-dimensional feature vector of the test sample and the n-dimensional feature vectors of each training sample; according to the distance between the test sample and each training sample, screening out the target training sample set that the test sample matches from each training sample; where the target training sample set includes multiple target training samples; calculating the predicted target value of the test sample according to the distance between the test sample and each target training sample and the actual completion time of each target training sample; calculating the sum of squared errors according to the predicted target values and target values of each test sample; reducing the number of training samples in the training sample set and increasing the number of test samples in the test sample set to update the training sample set and the test sample set, and adding 1 to the corresponding update times; determining whether the update times after adding 1 reach the target update times; where the target update times is a positive integer greater than 1; if the target update times is not reached, return to execute for each test sample, using a preset algorithm to calculate the distance between the test sample and each training sample according to the n-dimensional feature vector of the test sample and the n-dimensional feature vectors of each training sample; if the target update times is reached, determining the K value parameter of the project progress prediction model to be trained according to each sum of squared errors, and establishing the project progress prediction model according to the K value parameter.

[0075] It should be noted that each dimension of the n-dimensional feature vector of the sample is the feature vector corresponding to each parameter in the task-related parameters of the sample.

[0076] In some embodiments, the preset algorithm can be the KNN (K-Nearest Neighbor) algorithm, and the corresponding preset algorithm can be selected according to the actual application, which is not limited in the embodiments of the present application.

[0077] It should be noted that data cleaning of the historical task feature data means eliminating the outliers and error values in the historical task feature data.

[0078] In some embodiments, for each target historical project task, data cleaning is performed on the historical task feature data of the target historical project task, and among the various parameters of the task-related parameters in the historical task feature data after data cleaning, the parameter values of the parameters whose parameter value types are non-numerical are converted into numerical-type parameter values to ensure that the parameter value types of each parameter are all numerical types; normalization processing is performed on each parameter according to the parameter value of each parameter to obtain the numerical value corresponding to each parameter, and finally, the numerical value corresponding to the task completion time among the various parameters can be used as the target value of the target historical project task. For example, taking Table 1 as an example, among the task-related parameters of the first historical project task, the parameter value corresponding to the start time is 2021.06.05 09:23:12, and the parameter value of the parameter can be determined according to the actual situation, which is not limited in the embodiments of the present application.

[0079] It should be noted that the method for normalizing the parameters of the target historical project task is shown in Formula (1).

[0080] (1)

[0081] Among them, is the parameter value of the i-th parameter of the target historical project task that needs to be normalized currently; is the minimum value among the parameter values of the i-th parameter of each target historical project task; is the maximum value among the parameter values of the i-th parameter of each target historical project task; x is the numerical value of the i-th parameter of the target historical project task that needs to be normalized currently.

[0082] For example, taking each parameter of the task-related data in the historical task feature data of the target project task shown in Table 1 as an example, after normalizing each parameter of the task-related data in the historical task feature data of the target project task according to Formula (1), the numerical values of each parameter are shown in Table 2:

[0083] Table 2:

[0084] Task Type Responsible Person Participant 1 Participant 2 Start Time Number of Process Nodes Project Level Quantity Equipment Materials End Time 1 0.159 0.611 1.0 0.0 0.714 0.0 0.167 1.0 0.0 0.0 1 0.0 0.857 0.0 1.0 1.0 0.5 1.0 0.0 0.975 1.0 1 1.0 1.0 0.0 0.717 0.0 1.0 0.0 0.525 0.0 0.717 1 0.008 0.0 0.0 0.462 0.0 0.5 0.069 0.527 1.0 0.462

[0085] It should be noted that as can be seen from Table 2, by normalizing each parameter, each parameter can be scaled within the range of (0, 1).

[0086] In some embodiments, when dividing the training sample set and the test sample set for the first time, each target historical project task can be divided into a training sample set and a test sample set according to a preset ratio. For example, if the preset ratio is 9:1, then 90% of each target historical project task can be divided into the training sample set, and 10% of each target historical project task can be divided into the test sample set. The preset ratio can be set according to actual applications, and the embodiments of this application do not limit it here.

[0087] In the embodiments of this application, for each test sample, the n-dimensional feature vector corresponding to the test sample and the n-dimensional feature vectors of each training sample can be extracted, and the Euclidean distance / Manhattan distance / Minkowski distance of the test sample can be calculated according to the n-dimensional feature vector corresponding to the test sample and the n-dimensional feature vectors of each training sample by using a preset algorithm. Among them, the calculation method of the Euclidean distance of the test sample is shown in formula (2); the calculation method of the Manhattan distance of the test sample is shown in formula (3); the calculation method of the Minkowski distance of the test sample is shown in formula (4).

[0088] (2)

[0089] (3)

[0090] (4)

[0091] Among them, x is the test sample, y is the training sample, is the i-th dimensional feature vector of the test sample, that is, the value of the i-th parameter in the task-related data of the test sample; is the i-th dimensional feature vector of the training sample, that is, the value of the i-th parameter in the task-related data of the training sample. In formula (4), p is a hyperparameter, and its value ranges from 1 to infinity.

[0092] It should be noted that the distance between every two training samples in the training sample set can also be calculated.

[0093] For example, taking the values of each parameter of the 4 target historical project tasks shown in Table 2 as an example, assuming that these 4 target historical project tasks are all training samples, the Euclidean distance between every two training samples is calculated using formula (2), as shown in Table 3.

[0094] Table 3:

[0095] Sample Sample 1 Sample 2 Sample 3 Sample 4 Sample 1 0 1.732 1.414 0.837 Sample 2 1.732 0 1.732 1.732 Sample 3 1.414 1.732 0 0.837 Sample 4 0.837 1.732 0.837 0

[0096] In some embodiments, a corresponding target distance K can be preset. After calculating the distances between the test sample and each training sample, the target training samples with a distance of the target distance K can be screened out from each training sample, and a set of target training samples matching the test sample can be formed according to each target training sample.

[0097] In the embodiments of the present application, for each target training sample in the set of target training samples, according to the majority decision rule, each target training sample has one vote, and the reciprocal of the distance between each target training sample and the test sample is used as the distance weight of each target training sample (as shown in Table 4). Then, the weighted average value is calculated according to the distance weights of each target training sample and the actual completion time of each target training sample to obtain the predicted target value of the test sample; among them, the calculation method of the predicted target value of the test sample is shown in formula (5).

[0098] (5)

[0099] Where k is the number of target training samples in the set of target training samples, w(x) is the distance weight between the test sample x and the target training sample X, f(X) is the actual completion time of the target training sample X, and Z is the predicted target value of the test sample.

[0100] Table 4:

[0101] Sample Distance Weight (1 / Distance) Sample 1 1.953 0.512 Sample 2 1.859 0.538 Sample 3 1.835 0.545

[0102] Among them, it can be seen from Table 4 that the test sample is sample 4, and the target training samples are samples 1 - 3.

[0103] In some embodiments, after obtaining the predicted target value of each test sample in the test sample set, the target value of each test sample can be de-normalized to obtain the actual completion time of each test sample, and the corresponding sum of squared errors can be calculated according to the predicted target value and the actual completion time of each test sample. Among them, the calculation method of the sum of squared errors is shown in formula (6).

[0104] (6)

[0105] Where is the sum of squared errors, n is the number of test samples in the test sample set, is the predicted target value of test sample i, is the actual completion time of test sample i.

[0106] In some embodiments, corresponding preset numbers and target update times can be set in advance. After obtaining the error sum of squares corresponding to the current test sample set, the test sample set and the training sample set can be updated according to the preset number, that is, reduce the preset number of training samples in the training sample set, and at the same time add the preset number of test samples to the test sample set, so as to achieve the purpose of updating the training sample set and the test sample set.

[0107] For example, the preset number is 1 and the target update time is 3. One training sample in the training sample set can be reduced, and the reduced training sample can be added to the test sample set. At the same time, the current update time is incremented by 1, and it is determined whether the updated update time reaches 3; if so, determine the K-value parameter of the project progress prediction model to be trained according to the obtained error sum of squares, and establish a project progress prediction model according to the K-value parameter; if not, return to execute the calculation of the distance between the test sample and each training sample according to the n-dimensional feature vector of the test sample and the n-dimensional feature vectors of each training sample by using the preset algorithm, so as to recalculate the error sum of squares of the updated test sample set.

[0108] In some embodiments, after obtaining each error sum of squares, in the case of calculating each error sum of squares as the K-value parameter of the project progress prediction model to be trained by means of cross-validation, calculate the accuracy of the project progress prediction model to be trained; finally, the K-value parameter corresponding to the project progress prediction model with higher accuracy can be selected as the final K-value parameter, that is, select the update time corresponding to the smallest error sum of squares among the error sum of squares as the final K-value parameter, and establish a project progress prediction model by using the finally determined K-value parameter. For example, when the update time = 2, the error sum of squares is 0.497; when the update time = 3, the error sum of squares is 0.391. By means of the cross-validation method, calculate the model accuracy; finally, select the update time corresponding to the higher accuracy, that is, the smallest error sum of squares, as the K-value parameter of the model, that is, the final K-value parameter is selected as 3.

[0109] S102: Obtain the task feature data of the target project task for which the project progress is to be predicted currently.

[0110] In the process of specifically executing step S102, obtain the task data of the target project task for which the project progress is to be predicted currently, and perform preprocessing operations such as data cleaning on the task data, so as to extract the task feature data of the target project task from the task data after the preprocessing operation.

[0111] It should be noted that the task feature data of the target project task includes at least target task-related parameters, user-related parameters of the users participating in the target project task, other related parameters, etc., which are not limited in the embodiments of the present application here.

[0112] It should also be noted that the task-related parameters of the target project task at least include: the project level of the target project task, the belonging stage, the stage type, the person in charge, the participants, the preset start and end times of task execution, the task type, the quantity, the task content, the involved processes, the test plan, whether it is parallel, the relevant equipment, the relevant materials, and other parameters related to the target project task; the user-related parameters of the target project task at least include: the professional skill level, performance level, age, working years, and other relevant parameters of the users participating in the target project task; the other relevant parameters of the target project task at least include: the status, use, procurement cycle, and other relevant parameters of the equipment and relevant materials involved in the execution of the target project task.

[0113] S103: Use the project progress prediction model to calculate the target value of the target project task according to the task characteristic data of the target project task.

[0114] In the specific execution process of step S103, after obtaining the task characteristic data of the target project task, the task-related parameters of the target project task can be extracted from the task characteristic data of the target project task. For example, for a chemical test (the task type of the target task project), the task-related parameters include: Li Ming and Zhang San are implementing, the start time is 2024.11.25 14:25:22, passing through 9 nodes, the execution project level is B, the test quantity is 21, and the involved resources are spectrometers and sulfuric acid, etc.; the extracted task-related parameters of the target project task are input into the project progress prediction model, so that the project progress prediction model performs project progress prediction according to the input task-related parameters to obtain the target value of the target project task.

[0115] In the actual application process, after inputting the task-related parameters of the target project task into the project progress prediction model, the project progress prediction model can extract the feature vectors of each parameter of the task-related parameters of the target project task, and perform a new project progress prediction on the target project task according to the extracted feature vectors of each parameter to obtain the target value of the target project task.

[0116] S104: Calculate the project progress of the target project task according to the target value of the target project task.

[0117] In the specific execution process of step S104, after obtaining the target value of the target project task, the target value of the target project task can be de-normalized to obtain the project progress of the target project task. Among them, the project progress is the completion time of the target project task.

[0118] Furthermore, in the embodiment of the present application, after obtaining the project progress of the target project task, the project progress warning information of the target project task can be generated and output according to the task characteristic data and the project progress of the target project task.

[0119] In some embodiments, parameters such as the dependency relationship and whether it is parallel of the target project task can be extracted from the task-related parameters of the task feature data of the target project task, and based on the extracted parameters and the project progress of the target project task, the critical path experiment plan and the completion progress of the project phase of the target project task can be calculated, so as to obtain the overall project progress of the target project task based on the critical path experiment plan and the completion progress of the project phase of the target project task. Finally, reports related to the target project task and project progress warning information such as the execution status of the project process are generated according to the overall project progress.

[0120] In the actual application process, according to the project progress of the target project task, combined with conditions such as the dependency relationship and whether it is parallel of the target project task, the progress of the critical path of the target project task is calculated to establish a corresponding scientific research project progress management system. Among them, the functions of the system can include function modules such as project phase management, test plan management, test task management, progress prediction model management, progress calculation, progress classification view, and progress warning information of the target project task.

[0121] It should be noted that the project phase management decomposes the R & D content of the target project task according to the milestone nodes, generally segments it according to the important time nodes of the target project task, edits it, and designates relevant responsible persons, start time, completion time, completion status, etc.; the test plan module clarifies the specific content of the test plan, responsible person, start time, completion time, test type, milestone phase to which it belongs, weight, whether it can be parallel, completion status, etc. according to the milestone content of the target project task; the test task module is subdivided according to the test content and objectives of the target project task, including various test tasks such as experiments, meetings, procurement, processing, inspections, simulations, designs, etc., and clarifies the responsible person, participants, start and end times, content objectives, weight, dependency relationship, completion status, etc.; the progress prediction model management includes data preprocessing, model creation, prediction result display, etc.; the progress calculation module calculates the progress of each test task, test plan, phase plan and project development of the target project task to form a calculation result; the progress classification view module marks the test tasks, test plans, phase plans, and projects undertaken by it in different colors according to the different role permissions of the logged-in personnel for display according to the progress being normal, behind schedule, or ahead of schedule; the progress warning information provides warning information about the project progress for relevant personnel of the target project task, such as reminding of projects, phases, test plans, test tasks, etc. that may be behind schedule. If the relevant person in charge determines that there is a greater risk that may affect the progress, after confirmation, a risk warning process for the target project task will be initiated to carry out relevant risk handling work.

[0122] This application provides a project progress estimation method. By using historical task data and a preset algorithm, the K-value parameter of the project progress estimation model to be established is determined, and the project progress estimation model is established based on the K-value parameter. The task feature data of the target project task for which the project progress is to be estimated currently is obtained. The project progress estimation model is used to calculate the target value of the target project task according to the task feature data of the target project task. The project progress of the target project task is calculated according to the target value of the target project task. It can be seen that this application pre-establishes a corresponding project progress estimation model so as to use the project progress estimation model to estimate the project progress of the target project task according to the task feature data of the target project task for which the project progress is to be estimated currently. Compared with the existing manual estimation method, this application can not only accurately and reasonably estimate the project progress, but also objectively reflect the development of the project with a unified standard. That is, this application can improve the efficiency of scientific research project progress management, has scientificity and objectivity, and provides important support for enterprises to effectively manage scientific research projects, quickly respond to risks, and improve R & D efficiency.

[0123] Based on the project progress estimation method provided in the above embodiments of this application, correspondingly, the embodiments of this application also provide a project progress estimation system, as Figure 3 shown. The project progress estimation system includes:

[0124] A model establishment unit 31, configured to determine the K-value parameter of the project progress estimation model to be established according to historical task data and a preset algorithm, and establish the project progress estimation model according to the K-value parameter;

[0125] A first acquisition unit 32, configured to acquire the task feature data of the target project task for which the project progress is to be estimated currently;

[0126] An estimation unit 33, configured to estimate the target value of the target project task by using the project progress estimation model according to the task feature data of the target project task;

[0127] A first calculation unit 34, configured to calculate the project progress of the target project task according to the target value of the target project task.

[0128] For the specific principles and execution processes of each unit in the project progress estimation system disclosed in the above embodiments of this application, they are the same as those of the project progress estimation method disclosed in the above embodiments of this application. Refer to the corresponding parts in the project progress estimation method disclosed in the above embodiments of this application, and details will not be elaborated here.

[0129] The present application provides a project progress prediction system. By using historical task data and a preset algorithm, the K-value parameter of the project progress prediction model to be established is determined, and the project progress prediction model is established according to the K-value parameter; the task feature data of the target project task for which the project progress is to be predicted currently is obtained; the project progress prediction model is used to calculate the target value of the target project task according to the task feature data of the target project task; and the project progress of the target project task is calculated according to the target value of the target project task. It can be seen that the present application establishes a corresponding project progress prediction model in advance so as to use the project progress prediction model to predict the project progress of the target project task for which the project progress is to be predicted currently according to the task feature data of the target project task. Compared with the existing manual prediction method, the present application can not only accurately and reasonably predict the project progress, but also objectively reflect the development of the project with a unified standard.

[0130] Optionally, the model establishment unit includes:

[0131] The second acquisition unit is configured to acquire historical task data and extract the historical task feature data of each historical project task from the historical task data;

[0132] The first screening unit is configured to screen out a plurality of target historical project tasks from each historical project task according to the historical task feature data of each historical project task;

[0133] The first model establishment subunit is configured to determine the K-value parameter of the project progress prediction model to be established according to the preset algorithm and each target historical project task, and establish the project progress prediction model according to the K-value parameter.

[0134] Optionally, the historical task feature data of the historical project task includes at least the task type and the start and end times of task execution of the historical project task. The first screening unit includes:

[0135] The third acquisition unit is configured to acquire a preset time period set in advance and the target task type of the target project task for which the project progress is to be predicted currently;

[0136] The first screening subunit is configured to screen out a plurality of initial historical project tasks from each historical project task whose start and end times of task execution are within the preset time period;

[0137] The second screening subunit is configured to screen out a plurality of target historical project tasks from each initial historical project task whose task type is the target task type.

[0138] Optionally, the first model establishment subunit includes:

[0139] A normalization processing unit is configured to perform data cleaning on the historical task feature data of each target historical project task, and perform normalization processing on the historical task feature data of each target historical project task after data cleaning to obtain the normalized data of each target historical project task. The normalized data includes at least the target value of the target historical project task, and the target value is the value obtained by normalizing the task completion time in the historical task feature data of the target historical project task.

[0140] A partitioning unit is configured to partition each target historical project task into a training sample set and a test sample set. The training sample set includes multiple training samples, and the test set includes multiple test samples.

[0141] A second calculation unit is configured to, for each test sample, calculate the distance between the test sample and each training sample according to the n-dimensional feature vector of the test sample and the n-dimensional feature vectors of each training sample by using a preset algorithm.

[0142] A second screening unit is configured to screen out a target training sample set matching the test sample from each training sample according to the distance between the test sample and each training sample. The target training sample set includes multiple target training samples.

[0143] A third calculation unit is configured to calculate the predicted target value of the test sample according to the distance between the test sample and each target training sample and the actual completion time of each target training sample.

[0144] A fourth calculation unit is configured to calculate the sum of squared errors according to the predicted target values and the target values of each test sample.

[0145] An update unit is configured to reduce the number of training samples in the training sample set and increase the number of test samples in the test sample set to update the training sample set and the test sample set, and add 1 to the corresponding update times.

[0146] A judgment unit is configured to judge whether the updated times after adding 1 reach the target update times. The target update times is a positive integer greater than 1.

[0147] A return execution unit is configured to, if the target update times is not reached, return to execute the second calculation unit.

[0148] A second model establishment subunit is configured to, if the target update times is reached, determine the K value parameter of the project progress prediction model to be trained according to each sum of squared errors, and establish the project progress prediction model according to the K value parameter.

[0149] Optionally, the project progress prediction system provided by the present application further includes:

[0150] An output unit, configured to generate and output project progress warning information of a target project task according to the task feature data and project progress of the target project task.

[0151] The present application also provides a storage medium, in which program instructions are stored, and when the program instructions are loaded and executed by a processor, the embodiments of any of the above project progress prediction methods are implemented.

[0152] The present application also provides an electronic device, as Figure 4 shown, the device includes a processor 401 and a memory 402, the processor and the memory are connected through a bus; program instructions are stored in the memory; the processor calls the program instructions in the memory to execute the embodiments of any of the above project progress prediction methods.

[0153] The processor in this article may be the CPU of the terminal, or an MCU integrated in the terminal, or a combination of the CPU and the MCU. Moreover, the processor includes a kernel, and the kernel retrieves the corresponding program from the memory, and one or more kernels can be set.

[0154] The memory may include non-permanent memory in a computer-readable medium, forms such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

[0155] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment. The systems and system embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0156] Those skilled in the art may further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered as exceeding the scope of the present invention.

[0157] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0158] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A project progress estimation method, characterized in that, The method includes: Determining the K value parameter of the project progress prediction model to be established according to historical task data and a preset algorithm, and establishing a project progress prediction model according to the K value parameter; Obtaining the task feature data of the target project task for which the project progress is to be predicted currently; Using the project progress prediction model to predict the target value of the target project task according to the task feature data of the target project task; Calculating the project progress of the target project task according to the target value of the target project task.

2. The method according to claim 1, wherein The determining the K value parameter of the project progress prediction model to be established according to historical task data and a preset algorithm, and establishing a project progress prediction model according to the K value parameter includes: Obtaining historical task data, and extracting the historical task feature data of each historical project task from the historical task data; Screening out a plurality of target historical project tasks from each of the historical project tasks according to the historical task feature data of each of the historical project tasks; Determining the K value parameter of the project progress prediction model to be established according to a preset algorithm and each of the target historical project tasks, and establishing a project progress prediction model according to the K value parameter.

3. The method according to claim 2, characterized in that The historical task feature data of the historical project task at least includes the task type and the start and end times of task execution of the historical project task; Screening out a plurality of target historical project tasks from each of the historical project tasks according to the historical task feature data of each of the historical project tasks includes: Obtaining a preset time period set in advance and the target task type of the target project task for which the project progress is to be predicted currently; Screening out a plurality of initial historical project tasks from each of the historical project tasks whose start and end times of task execution are within the preset time period; Screening out a plurality of target historical project tasks from each of the initial historical project tasks whose task type is the target task type.

4. The method according to claim 2, wherein The determining the K value parameter of the project progress prediction model to be established according to a preset algorithm and each of the target historical project tasks, and establishing a project progress prediction model according to the K value parameter includes: Performing data cleaning on the historical task feature data of each of the target historical project tasks, and performing normalization processing on the historical task feature data of each of the target historical project tasks after data cleaning to obtain the normalized data of each of the target historical project tasks, where the normalized data at least includes the target value of the target historical project task, and the target value is the value obtained by normalizing the task completion time in the historical task feature data of the target historical project task; Dividing each of the target historical project tasks into a training sample set and a test sample set; where the training sample set includes a plurality of training samples, and the test set includes a plurality of test samples; For each test sample, calculating the distance between the test sample and each of the training samples according to the n-dimensional feature vector of the test sample and the n-dimensional feature vectors of each of the training samples by using a preset algorithm; Screen out a set of target training samples that match the test sample from each of the training samples according to the distance between the test sample and each of the training samples; wherein, the set of target training samples includes a plurality of target training samples. Calculate a predicted target value of the test sample according to the distance between the test sample and each target training sample and the actual completion time of each target training sample. Calculate the sum of squared errors according to the predicted target values and the target values of each of the test samples. Reduce the number of training samples in the training sample set and increase the number of test samples in the test sample set to update the training sample set and the test sample set, and increment the corresponding update count by 1. Determine whether the update count after incrementing by 1 reaches the target update count; wherein, the target update count is a positive integer greater than 1. If the target update count is not reached, return and execute for each test sample, calculate the distance between the test sample and each of the training samples according to the n-dimensional feature vector of the test sample and the n-dimensional feature vectors of each of the training samples using a preset algorithm. If the target update count is reached, determine the K value parameter of the project progress prediction model to be trained according to each sum of squared errors, and establish a project progress prediction model according to the K value parameter.

5. The method according to claim 1, wherein The method further includes: Generate and output project progress warning information for the target project task according to the task feature data and the project progress of the target project task.

6. A project progress estimation system, characterized in that, The system includes: A model establishment unit, configured to determine the K value parameter of the project progress prediction model to be established according to historical task data and a preset algorithm, and establish a project progress prediction model according to the K value parameter. A first acquisition unit, configured to acquire task feature data of a target project task for which project progress prediction is to be performed currently. An estimation unit, configured to estimate the target value of the target project task by using the project progress prediction model according to the task feature data of the target project task. A first calculation unit, configured to calculate the project progress of the target project task according to the target value of the target project task.

7. The system according to claim 6, wherein The model establishment unit includes: A second acquisition unit, configured to acquire historical task data and extract historical task feature data of each historical project task from the historical task data. A first screening unit, configured to screen out a plurality of target historical project tasks from each of the historical project tasks according to the historical task feature data of each of the historical project tasks. A first model establishment subunit, configured to determine the K value parameter of the project progress prediction model to be established according to a preset algorithm and each of the target historical project tasks, and establish a project progress prediction model according to the K value parameter.

8. The system according to claim 7, wherein The historical task feature data of the historical project task includes at least the task type and the start and end times of task execution of the historical project task, and the first screening unit includes: A third acquisition unit, configured to acquire a preset time period set in advance and the target task type of the target project task for which project progress prediction is to be performed currently. The first screening subunit is configured to screen out a plurality of initial historical project tasks from each of the historical project tasks, where the start and end times of task execution are within the preset time period; The second screening subunit is configured to screen out a plurality of target historical project tasks of the target task type from each of the initial historical project tasks.

9. An electronic device, characterized in that, Comprising: A processor and a memory, the processor and the memory are connected by a bus; wherein, the processor is configured to call and execute a program stored in the memory; The memory is configured to store a program, and the program is used to implement a project progress estimation method according to any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and the computer-executable instructions are used to execute a project progress estimation method according to any one of claims 1-5.

Images