Intelligent Project Management Method and System Based on Streaming Recorded Texts

Abstract

The present invention belongs to the technical field of project management and relates to a project intelligent management method and system based on a flowing water type record text. The method includes: extracting task information; determining task categories; attributing the task information to the workflow of the target project to determine the project progress; determining the current project plan corresponding to the project progress; allocating the task information to the project member with the highest vector similarity; updating the actual progress of the project; and predicting the project completion probability. The present invention can extract task information according to the flowing water type record text, determine the project progress by automatically attributing the task information, dynamically and immediately update the project progress to avoid information lag; can automatically match the current project plan corresponding to the project progress and allocate the task information to project members; can update the actual progress of the project and predict the project completion probability, reduce manual intervention, realize automatic extraction, analysis and management of tasks, and improve management efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of project management. Specifically, it relates to a project intelligent management method and system based on flowing water record text. Background Art

[0002] The efficiency and accuracy of project management are crucial for the operation of enterprises. In the traditional project management process, the tracking and management of project progress rely on manual input and maintenance. Project members need to manually update task status, time nodes, and related events. This way of manual input and maintenance has significant defects. On the one hand, human operations are prone to information lag. Project managers are difficult to obtain the latest project progress in a timely manner, resulting in insufficient decision-making basis and affecting the timeliness of project promotion. On the other hand, in the manual processing process, the probability of missing key information is relatively high. Once an important task or time node is missed, it may cause disconnection of project links, seriously affecting the coherence of the project. At the same time, manual judgment is also prone to misjudgment, such as inaccurate assessment of task completion progress, which will mislead the overall resource allocation and subsequent planning of the project, ultimately resulting in low overall management efficiency, increased project costs, and even the project may face the risk of failure.

[0003] In addition, in daily work, a large amount of text data in the form of flowing water records is generated, such as meeting records, work logs, email exchanges, etc. These text data contain rich project-related information, but in the process of project management in the existing technology, these valuable data resources have not been fully explored and utilized. The traditional storage method simply records these data, lacking in-depth analysis and effective integration, making these information unable to be transformed into key elements helpful for project management, resulting in waste of data resources.

[0004] The traditional project management method has serious deficiencies in the efficiency and accuracy of progress tracking and management, and does not make full use of the flowing water record text data in daily work. Therefore, there is an urgent need for an innovative project management method that can effectively solve the above problems and improve the intelligent level and overall efficiency of project management. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a project intelligent management method and system based on flowing water record text.

[0006] In the first aspect, the present invention provides a project intelligent management method based on flowing water record text, including:

[0007] Analyze the flowing record text using a natural language model, extract the text data of the target entities associated with project management, and use the method of named entity recognition to extract task information; the text data includes task name, task node, time, and task content; the task information includes time, person, location, and event content;

[0008] Perform semantic analysis on the task information, extract task information keywords, match the task information keywords with the task category keyword library, and determine the task category;

[0009] Based on the task category, combine the recognition of the dependency relationship and execution order of the task information, assign the task information to the workflow of the target project, and determine the project progress according to the node position corresponding to the workflow of the target project;

[0010] Match the project progress with each project plan to determine the current project plan corresponding to the project progress;

[0011] Extract the feature vectors of the task keywords and project member labels through natural language processing algorithms, match the task keywords and project member labels through vector similarity, and assign the task information to the project member with the highest vector similarity;

[0012] Match the time of the task information with the time of the task node of the current project plan to update the actual progress of the project;

[0013] Predict the project completion probability according to the actual progress of the project and the current project plan.

[0014] In a second aspect, the present invention provides a project intelligent management system based on flowing record text, including a task information extraction unit, a task classification unit, a project progress analysis unit, a project plan matching unit, a project member assignment unit, an actual progress update unit, and a prediction unit;

[0015] The task information extraction unit is used to analyze the flowing record text using a natural language model, extract the text data of the target entities associated with project management, and use the method of named entity recognition to extract task information; the text data includes task name, task node, time, and task content; the task information includes time, person, location, and event content;

[0016] The task classification unit is used to perform semantic analysis on the task information, extract task information keywords, match the task information keywords with the task category keyword library, and determine the task category;

[0017] The project progress analysis unit is used to, based on the task category, combine the recognition of the dependency relationship and execution order of the task information, assign the task information to the workflow of the target project, and determine the project progress according to the node position corresponding to the workflow of the target project;

[0018] A project plan matching unit, configured to match the project progress with each project plan to determine the current project plan corresponding to the project progress;

[0019] A project member assignment unit, configured to extract the feature vectors of the task keywords and project member labels through a natural language processing algorithm, match the task keywords and project member labels through vector similarity, and assign the task information to the project member with the highest vector similarity;

[0020] An actual progress update unit, configured to update the actual progress of the project by matching the time of the task information with the time of the task nodes of the current project plan;

[0021] A prediction unit, configured to predict the project completion probability according to the actual progress of the project and the current project plan.

[0022] Based on the above technical solution, the present invention can also be improved as follows.

[0023] Further, collect the daily transaction record texts of project members through an API interface or regular data scraping; perform text cleaning on the daily transaction record texts; the text cleaning includes data format standardization, missing data filling, and interpolation.

[0024] Further, use the named entity recognition method to extract task information, including:

[0025] Determine the basic entity information corresponding to the task information; the basic entity information includes task name, person in charge, deadline, and priority;

[0026] Split the continuous text data into independent word segmentation units and label each independent word segmentation unit;

[0027] Perform vector representation on the independent word segmentation units to obtain word segmentation vectors;

[0028] Construct a pre-trained model based on the Transformer model, use the word segmentation vectors as input, use the entity labels corresponding to the basic entity information as output, add a custom NER layer, configure the loss function, set the learning rate and the number of training rounds, train the pre-trained model and monitor the validation set metrics to obtain a task information extraction model; the validation set metrics include F1 score and accuracy;

[0029] Input the word segmentation vectors corresponding to the text data into the task extraction model to obtain the entity labels corresponding to the basic entity information, and check the integrity of the entity labels in the basic entity information corresponding to the task information.

[0030] Further, perform semantic analysis on the task information, extract the task information keywords, match the task information keywords with the task category keyword library, and determine the task category, including:

[0031] Collect samples of project management task descriptions, extract task category keywords, and perform vector representation to construct a task category keyword library; the task category keywords include meetings, development, testing, and delivery;

[0032] Perform semantic analysis on the task information, use dependency syntactic analysis to extract the subject-predicate-object structure, and use semantic role labeling to identify actions and objects to generate word vectors;

[0033] Calculate the cosine similarity between the word vector corresponding to the task information and the word vectors of the task category keywords, and use the task category keyword with the largest cosine similarity as the task category corresponding to the task information.

[0034] Further, based on the task category, combine the recognition of the dependency relationship and execution order of the task information, and assign the task information to the workflow of the target project, including: collecting the shared data flow between tasks, the conditions that need to be met for task execution, and the association between the output of the previous task and the input of the subsequent task, as well as the adjacent tasks of the task information, and perform feature matching with each node of the target project, and use the nodes of the target project with the highest matching degree as the target nodes.

[0035] Further, match the project progress with each project plan to determine the current project plan corresponding to the project progress, including: sorting out all project plans, establishing the hierarchical relationship and association matrix between project plans, setting a unique identifier for each project plan; setting key milestone nodes in each project plan; quantifying the project progress percentage and establishing a project progress evaluation standard; associating the project progress with the key milestone nodes in the project plan to determine the project plan with the highest degree of association to obtain the current project plan.

[0036] Further, match the time of the task information with the time of the task nodes in the current project plan to update the actual progress of the project, including: calculating the difference between the time of the task information and the time of the task nodes in the current project plan, and determining the task nodes within the elastic time window range where the time of the task information is located to obtain the actual progress of the project.

[0037] Further, based on the actual progress of the project and the current project plan, predict the project completion probability, including: collecting historical data, calculating the time deviation coefficient, resource consumption rate, and critical path deviation to construct a sample data set; constructing a probability prediction model, using the Monte Carlo simulation engine to train the probability prediction model, and inputting the data in the sample data set into the probability prediction model to obtain the project completion probability;

[0038] Let the time deviation coefficient be , the actual completion time is , the planned completion time is , the total duration of the critical path is , then:

[0039] ;

[0040] Let the resource consumption rate be , the actual resource usage is , the total planned resource is , the operation weight factor is , then:

[0041] ;

[0042] Let the critical path deviation be , the number of completed critical operations is , the total number of critical operations is , then:

[0043] ;

[0044] Let the project completion probability be , , , and are the model parameters of the probability prediction model, then the probability prediction model is expressed as:

[0045] .

[0046] Furthermore, after predicting the project completion probability, a task reminder is pushed to the project members.

[0047] The beneficial effects of the present invention are as follows: The present invention can extract task information from the flowing water type record text, determine the project progress by automatically attributing the task information, dynamically and instantaneously update the project progress to avoid information lag; it can automatically match the current project plan corresponding to the project progress and allocate task information to project members; it can update the actual progress of the project and predict the project completion probability, reduce manual intervention, realize automatic extraction, analysis and management of tasks, and improve management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is the schematic diagram of the project intelligent management method based on the flowing water type record text provided in Embodiment 1 of the present invention;

[0049] Figure 2 is the system block diagram of the project intelligent management system based on the flowing water type record text provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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 part of the embodiments of the present invention, rather than all of the embodiments. Components of the embodiments of the present invention usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0051] Embodiment 1

[0052] As an embodiment, as shown in the attached Figure 1 figure, to solve the above technical problems, this embodiment provides an intelligent project management method based on flowing water record text, including:

[0053] Analyze the flowing water record text using a natural language model, extract the text data of the target entity associated with project management, and use the method of named entity recognition to extract task information; the text data includes task name, task node, time, and task content; the task information includes time, person, location, and event content;

[0054] Perform semantic analysis on the task information, extract task information keywords, match the task information keywords with the task category keyword library, and determine the task category;

[0055] Based on the task category, combine the recognition of the dependency relationship and execution order of the task information, assign the task information to the workflow of the target project, and determine the project progress according to the node position corresponding to the workflow of the target project;

[0056] Match the project progress with each project plan to determine the current project plan corresponding to the project progress;

[0057] Extract the feature vectors of the task keywords and project member labels through natural language processing algorithms, match the task keywords and project member labels through vector similarity, and assign the task information to the project member with the highest vector similarity;

[0058] Match the time of the task information with the time of the task node of the current project plan to update the actual progress of the project;

[0059] Predict the project completion probability according to the actual progress of the project and the current project plan.

[0060] The present invention can extract task information according to the flowing water type record text, determine the project progress by automatically attributing the task information, dynamically and immediately update the project progress to avoid information lag; can automatically match the current project plan corresponding to the project progress and allocate project members to the task information; can update the actual progress of the project and predict the project completion probability, reduce manual intervention, realize automatic extraction, analysis and management of tasks, and improve management efficiency.

[0061] Optionally, collect the daily flowing water record text of project members through an API interface (Application Programming Interface) or regular data scraping; clean the text of the daily flowing water record text; the text cleaning includes data format standardization, missing data filling and interpolation.

[0062] Specifically, collect data through an API interface such as: construct an API request based on an HTTP request library, and after sending the request, receive the response data containing the daily flowing water record text returned by the API.

[0063] The data format is standardized to JSON format or XML format, etc. For the missing values of numerical fields, methods such as mean, median and mode are selected for filling. If the data has time series characteristics, methods such as linear interpolation and polynomial interpolation are used for missing value estimation.

[0064] Optionally, use the method of named entity recognition to extract task information, including:

[0065] Determine the basic entity information corresponding to the task information; the basic entity information includes task name, person in charge, deadline and priority;

[0066] Split the continuous text data into independent word segmentation units and label each independent word segmentation unit;

[0067] Perform vectorization representation on the independent word segmentation units to obtain word segmentation vectors;

[0068] Construct a pre-trained model based on the Transformer model, use the word segmentation vectors as input, use the entity labels corresponding to the basic entity information as output, add a custom NER (Named Entity Recognition) layer, configure the loss function, set the learning rate and the number of training rounds, train the pre-trained model and monitor the validation set metrics to obtain a task information extraction model; the validation set metrics include F1 score and accuracy;

[0069] Input the word segmentation vectors corresponding to the text data into the task extraction model to obtain the entity labels corresponding to the basic entity information, and check the integrity of the entity labels in the basic entity information corresponding to the task information.

[0070] Build pre-trained models based on the Transformer model, such as the BERT (Bidirectional Encoder Representations from Transformers) model and the RoBERTa (Robustly Optimized BERT Approach) model. These models are pre-trained on large-scale corpora and have language understanding capabilities. Add a custom named entity recognition layer, which is used to process the tokenized vectors of the input and predict the entity labels corresponding to each token. The learning rate controls the step size of parameter updates during model training.

[0071] Configure a loss function such as the cross-entropy loss function to measure the difference between the model's prediction results and the true labels. The accuracy rate is the proportion of samples correctly predicted by the model to the total samples.

[0072] Optionally, perform semantic analysis on the task information, extract the task information keywords, match the task information keywords with the task category keyword library, and determine the task category, including:

[0073] Collect samples of project management task descriptions, extract task category keywords, and perform vector representation to build a task category keyword library; the task category keywords include meetings, development, testing, and delivery;

[0074] Perform semantic analysis on the task information, use dependency syntactic analysis to extract the subject-predicate-object structure, and use semantic role labeling to identify actions and objects to generate word vectors;

[0075] Calculate the cosine similarity between the word vectors corresponding to the task information and the word vectors of the task category keywords, and use the task category keyword with the largest cosine similarity as the task category corresponding to the task information.

[0076] In the actual application process, the sample of project management task descriptions can come from different sources such as project documents, task assignment records, and work reports. Use a word embedding model (such as the Word2Vec (Word to Vector) model, the GloVe (Global Vectors for Word Representation) model, or a Transformer-based word vector model) to vectorize the extracted task category keywords. Word vectors map words into numerical vectors in a low-dimensional space, so that words with similar semantics are closer in the vector space. Thus, the semantic similarity between words can be measured by calculating the distance between vectors. Convert each task category keyword into its corresponding word vector and store it in the task category keyword library. Through semantic role labeling, the relationship between actions and objects in task information can be grasped more accurately, thereby understanding the semantics of tasks more deeply.

[0077] Judge the similarity between two vectors by calculating the cosine value of the included angle between them. The value range is between -1 and 1, and the closer the value is to 1, the more similar the two vectors are. After calculating all the cosine similarities, find the task category keyword with the largest cosine similarity to the task information word vector, and determine the task category corresponding to this task category keyword as the task category of this task information, realizing the classification of task information.

[0078] Optionally, based on the task category, combine the recognition of the dependency relationship and execution order of task information, and assign the task information to the workflow of the target project, including: collecting the shared data flow between tasks, the conditions that need to be met for task execution, the association between the output of the previous task and the input of the subsequent task, and the adjacent tasks of the task information. Match the features with each node of the target project, and use the nodes of the target project with the highest matching degree as the target nodes.

[0079] Specifically, conduct a detailed analysis of the task information for each task category, sort out the data input and output involved in the task execution process. For example, a data processing task may receive data from another data collection task as input, record the flow direction and transfer relationship of these data, and form a shared data flow between tasks.

[0080] According to the dependency relationship and execution order of task information, find the adjacent tasks of each task information. Adjacent tasks can be previous tasks and subsequent tasks, and there is a logical connection between adjacent tasks. For example, in a project, the previous task of the "design product prototype" task is "clarify product requirements", and the subsequent task is "conduct product testing".

[0081] The workflow of the target project includes the various stages of the project, the task nodes included in each stage, and the relationships between the task nodes. Clearly define the information such as the function, input requirements, output results, and execution conditions of each node. For example, the workflow of a software development project may include stages such as requirements analysis, design, coding, testing, and deployment, and each stage contains multiple specific nodes.

[0082] Match each feature of the task information (task category, input / output data, execution conditions, adjacent tasks, etc.) with the features of each node of the target project one by one. For the task category, directly compare whether the task category to which the task information belongs is the same or similar to the task category of the node; for the input / output data, check whether the input data requirements and output data characteristics of the task information match the input / output of the node; for the execution conditions, check whether the execution conditions of the task information match the execution conditions of the node; for the adjacent tasks, analyze whether the adjacent task relationship of the task information is consistent with the front and back task relationships of the node in the workflow.

[0083] Set corresponding weights for each feature matching item, and calculate the matching degree score between the task information and each node according to the degree of matching. For example, the weight of task category matching can be set relatively high because it is an important attribute of the task; the weight of input / output data matching is the second; appropriate values are also set for the weights of execution condition and adjacent task matching according to their importance. By comprehensively calculating the matching scores of each feature, obtain the overall matching degree between the task information and each node.

[0084] Optionally, match the project progress with each project plan to determine the current project plan corresponding to the project progress, including: organizing all project plans, establishing the hierarchical relationship and association matrix between project plans, setting a unique identifier for each project plan; setting key milestone nodes in each project plan; quantifying the project progress percentage, establishing a project progress evaluation standard; associating the project progress with the key milestone nodes in the project plan to determine the project plan with the highest degree of association as the current project plan.

[0085] Optionally, match the time of the task information with the time of the task nodes of the current project plan to update the actual progress of the project, including: calculating the difference between the time of the task information and the time of the task nodes of the current project plan, determining the task nodes within the flexible time window range where the time of the task information is located, and obtaining the actual progress of the project.

[0086] Optionally, according to the actual progress of the project and the current project plan, predict the project completion probability, including: collecting historical data, calculating the time deviation coefficient, resource consumption rate, and critical path deviation degree to construct a sample data set; constructing a probability prediction model, using a Monte Carlo simulation engine to train the probability prediction model, and inputting the data of the sample data set into the probability prediction model to obtain the project completion probability;

[0087] Let the time deviation coefficient be , the actual completion time be , the planned completion time be , and the total duration of the critical path be , then:

[0088] ;

[0089] Let the resource consumption rate be , the actual resource usage be , the total planned resource quantity be , and the process weight factor be , then:

[0090] ;

[0091] Let the critical path deviation degree be , the number of completed critical processes be , and the total number of critical processes be , then:

[0092] ;

[0093] Let the project completion probability be , , , , and be the model parameters of the probability prediction model, then the probability prediction model is expressed as:

[0094] .

[0095] Optionally, after predicting the project completion probability, push a task reminder to the project members.

[0096] Notify the system (such as email, instant messaging applications, and calendar applications, etc.) to push task reminders in real time.

[0097] Example 2

[0098] Based on the same principle as the method shown in Embodiment 1 of the present invention, as shown in the appendix Figure 2As shown in the figure, an intelligent project management system for streaming-recorded text is also provided in an embodiment of the present invention, including a task information extraction unit, a task classification unit, a project progress analysis unit, a project plan matching unit, a project member assignment unit, an actual progress update unit, and a prediction unit;

[0099] The task information extraction unit is used to analyze the streaming-recorded text by using a natural language model, extract the text data of the target entity associated with project management, and extract task information by using the method of named entity recognition; the text data includes task name, task node, time, and task content; the task information includes time, person, location, and event content;

[0100] The task classification unit is used to perform semantic analysis on the task information, extract the task information keywords, match the task information keywords with the task category keyword library, and determine the task category;

[0101] The project progress analysis unit is used to, based on the task category, combine the recognition of the dependency relationship and execution order of the task information, assign the task information to the workflow of the target project, and determine the project progress according to the node position corresponding to the workflow of the target project;

[0102] The project plan matching unit is used to match the project progress with each project plan and determine the current project plan corresponding to the project progress;

[0103] The project member assignment unit is used to extract the feature vectors of the task keywords and project member labels through a natural language processing algorithm, match the task keywords and project member labels through vector similarity, and assign the task information to the project member with the highest vector similarity;

[0104] The actual progress update unit is used to match the time of the task information with the time of the task node of the current project plan and update the actual progress of the project;

[0105] The prediction unit is used to predict the project completion probability according to the actual progress of the project and the current project plan.

[0106] Optionally, collect the daily streaming-recorded text of project members through the API interface or the method of regular data scraping; perform text cleaning on the daily streaming-recorded text; the text cleaning includes data format standardization, missing data filling, and interpolation.

[0107] Optionally, use the method of named entity recognition to extract task information, including:

[0108] Determine the basic entity information corresponding to the task information; the basic entity information includes task name, person in charge, deadline, and priority;

[0109] Split continuous text data into independent token units and label each independent token unit;

[0110] Perform vector representation on the independent token units to obtain token vectors;

[0111] Build a pre-trained model based on the Transformer model, use the token vectors as input, use the entity labels corresponding to the basic entity information as output, add a custom NER layer, configure the loss function, set the learning rate and the number of training epochs, train the pre-trained model and monitor the validation set metrics to obtain a task information extraction model; The validation set metrics include F1 score and accuracy;

[0112] Input the token vectors corresponding to the text data into the task extraction model to obtain the entity labels corresponding to the basic entity information, and check the integrity of the entity labels in the basic entity information corresponding to the task information.

[0113] Optionally, perform semantic analysis on the task information, extract task information keywords, match the task information keywords with the task category keyword library to determine the task category, including:

[0114] Collect project management task description samples, extract task category keywords, and perform vector representation to build a task category keyword library; Task category keywords include meetings, development, testing, and delivery;

[0115] Perform semantic analysis on the task information, use dependency syntactic analysis to extract the subject-predicate-object structure, use semantic role labeling to identify actions and objects, and generate word vectors;

[0116] Calculate the cosine similarity between the word vectors corresponding to the task information and the word vectors of the task category keywords, and use the task category keyword with the largest cosine similarity as the task category corresponding to the task information.

[0117] Optionally, based on the task category, combine the recognition of the dependency relationship and execution order of the task information, and assign the task information to the workflow of the target project, including: collecting the shared data flow between tasks, the conditions that need to be met for task execution, and the association between the output of the previous task and the input of the subsequent task, as well as the adjacent tasks of the task information, and perform feature matching with each node of the target project, and use the nodes of the target project with the highest matching degree as the target nodes.

[0118] Compare the matching degree scores between the task information and each node of the target project, and find the node with the highest matching degree. Use this node with the highest matching degree as the target node of the task information in the target project workflow, which means that the task information should be assigned to the position where this node is located and become a part of the target project workflow.

[0119] Optionally, match the project progress with each project plan to determine the current project plan corresponding to the project progress, including: sorting out all project plans, establishing the hierarchical relationship and association matrix between project plans, and setting a unique identifier for each project plan; setting key milestone nodes in each project plan; quantifying the project progress percentage and establishing a project progress evaluation criterion; associating the project progress with the key milestone nodes in the project plan to determine the project plan with the highest degree of association as the current project plan.

[0120] Specifically, collect all project plan documents that are in progress or have been formulated. These project plan documents come from various project leaders and cover various types of projects, such as software development project plans, engineering project construction plans, and marketing campaign plans. Summarize the collected project plan documents and remove duplicate or invalid project plan documents.

[0121] Specifically, create an association matrix with project plans as rows and columns. The elements in the matrix are used to represent the degree of association between different project plans. The association relationships may include resource sharing, task dependencies, and data interactions, etc.

[0122] According to the task process and time arrangement of each project plan, find out the key milestone nodes that have a key impact on the success of the project and mark them in the corresponding project plan document. For example, assign a unique number to each milestone node to accurately identify it in project progress tracking and association analysis. Select appropriate metrics to measure the project progress. Common metrics include the number of tasks completed, the proportion of work completed, the proportion of project cost expenditure, and the delivery of key results, etc. Divide the project progress into different key milestone nodes, set the corresponding progress percentage range for each key milestone node, and calculate the current project progress percentage.

[0123] Optionally, update the actual progress of the project by matching the time of the task information with the task nodes of the current project plan, including: calculating the difference between the time of the task information and the task nodes of the current project plan, determining the task nodes within the flexible time window of the time of the task information, and obtaining the actual progress of the project.

[0124] Specifically, if the actual start time or actual completion time of the task information is within the flexible time window of the task node, it is considered that the task information matches the task node. For example: the flexible time window of the task node is between 9 days and 11 days after the planned completion time, and the difference between the actual completion time of the task information and the planned completion time is within this range, then it is considered that the task information matches the task node. In the actual application process, preferentially select the task node with the smallest time difference as the matching object, or determine the matching task node according to the logical order and dependency relationship of the tasks as the actual progress of the project.

[0125] Optionally, predict the project completion probability according to the actual progress of the project and the current project plan, including: collecting historical data, calculating the time deviation coefficient, resource consumption rate, and critical path deviation degree to construct a sample data set; constructing a probability prediction model, training the probability prediction model using a Monte Carlo simulation engine, inputting the data of the sample data set into the probability prediction model to obtain the project completion probability;

[0126] Let the time deviation coefficient be , the actual completion time be , the planned completion time be , and the total duration of the critical path be , then:

[0127] ;

[0128] Let the resource consumption rate be , the actual resource usage be , the total planned resources be , and the process weight factor be , then:

[0129] ;

[0130] Let the critical path deviation degree be , the number of completed critical processes be , and the total number of critical processes be , then:

[0131] ;

[0132] Let the project completion probability be , , , and be the model parameters of the probability prediction model, then the probability prediction model is expressed as:

[0133] .

[0134] Simulate various possible project execution situations through multiple random samplings, input the sample data set into the probability prediction model, and continuously adjust the model parameters , , and so that the project completion probability predicted by the probability prediction model is as close as possible to the actual completion situation of historical projects, thereby determining the optimal model parameters.

[0135] Optionally, after predicting the project completion probability, push task reminders to project members.

[0136] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. The project intelligent management method based on the flow-through recording text is characterized by: include: Use natural language models to analyze the stream-type record text, extract text data of target entities related to project management, and use named entity recognition methods to extract task information; text data includes task name, task node, time and task content; task information includes time, person, place and event content; Perform semantic analysis on task information, extract task information keywords, match task information keywords with task category keyword library, and determine task category; Based on the task category, combined with the identification of task information dependencies and execution order, the task information is attributed to the workflow of the target project, and the project progress is determined according to the node position corresponding to the workflow of the target project; Match the project progress with each project plan and determine the current project plan corresponding to the project progress; The feature vectors of task keywords and project member labels are extracted through natural language processing algorithms, and task keywords and project member labels are matched by vector similarity, and task information is assigned to the project member with the highest vector similarity. Match the time of task information with the time of task nodes in the current project plan to update the actual progress of the project; According to the actual progress of the project and the current project plan, the probability of project completion is predicted, including: collecting historical data, calculating the time deviation coefficient, resource consumption rate and critical path deviation to construct a sample data set; Build a probability prediction model, use the Monte Carlo simulation engine to train the probability prediction model, input the data of the sample data set into the probability prediction model, and obtain the probability of project completion; Assume the time deviation coefficient is The actual completion time is The planned completion time is , the total critical path duration is ,but: ； Assume that the resource consumption rate is , the actual resource usage is The total planned resources are , the process weight factor is ,but: ； Assume the critical path deviation is , the number of key processes completed is The total number of key processes is ,but: ； Assume that the probability of project completion is , , , and is the model parameter of the probability prediction model, then the probability prediction model is expressed as: 。 2. According to claim 1, the project intelligent management method based on the running record text is characterized in that: Collect the daily transaction record text of project members through API interface or regular data crawling; perform text cleaning on the daily transaction record text; text cleaning includes data format standardization and missing data filling and interpolation.

3. The project intelligent management method based on the running record text according to claim 1 is characterized in that: Using named entity recognition methods, we extract task information, including: Determine the basic entity information corresponding to the task information; the basic entity information includes the task name, person in charge, deadline and priority; Split the continuous text data into independent word segmentation units and label each independent word segmentation unit; Vectorize the independent word segmentation units to obtain the word segmentation vectors; Build a pre-trained model based on the Transformer model, take the word segmentation vector as input, take the entity label corresponding to the basic entity information as output, add a custom NER layer, configure the loss function, set the learning rate and the number of training rounds, train the pre-trained model and monitor the validation set indicators to obtain the task information extraction model; the validation set indicators include F1 score and accuracy; The word segmentation vector corresponding to the text data is input into the task extraction model to obtain the entity label corresponding to the basic entity information, and the integrity of the entity label in the basic entity information corresponding to the task information is verified.

4. The project intelligent management method based on the streamlining record text according to claim 1 is characterized in that: Perform semantic analysis on task information, extract task information keywords, match task information keywords with task category keyword library, and determine task category, including: Collect project management task description samples, extract task category keywords, and perform vector representation to build a task category keyword library; task category keywords include meeting, development, testing, and delivery; Perform semantic analysis on task information, extract subject-verb-object structure through dependency syntactic analysis, identify actions and objects through semantic role labeling, and generate word vectors; The cosine similarity between the word vector corresponding to the task information and the word vector of the task category keyword is calculated, and the task category keyword with the largest cosine similarity is used as the task category corresponding to the task information.

5. The project intelligent management method based on the streamlining record text according to claim 1 is characterized in that: Based on the task category, combined with the identification of the dependencies and execution order of task information, the task information is attributed to the workflow of the target project, including: collecting shared data flows between tasks, the conditions that need to be met for executing tasks and the association between the output of the previous task and the input of the subsequent task, as well as the adjacent tasks of the task information, and performing feature matching with each node of the target project, and taking each node of the target project with the highest matching degree as the target node.

6. The project intelligent management method based on the running record text according to claim 1 is characterized in that: Match the project progress with each project plan to determine the current project plan corresponding to the project progress, including: organizing all project plans, establishing hierarchical relationships and association matrices between project plans, and setting a unique identifier for each project plan; setting key milestone nodes in each project plan; quantifying the project progress percentage and establishing project progress evaluation standards; associating the project progress with the key milestone nodes in the project plan, and determining the project plan with the highest degree of association to obtain the current project plan.

7. The project intelligent management method based on the running record text according to claim 1 is characterized in that: According to the matching of the time of the task information with the time of the task node of the current project plan, the actual progress of the project is updated, including: calculating the difference between the time of the task information and the time of the task node of the current project plan, determining the task node within the flexible time window in which the time of the task information is located, and obtaining the actual progress of the project.

8. The project intelligent management method based on the running record text according to claim 1 is characterized in that: After predicting the probability of project completion, push task reminders to project members.

9. The project intelligent management system based on the running record text is characterized by: It includes task information extraction unit, task classification unit, project progress analysis unit, project plan matching unit, project member allocation unit, actual progress update unit and prediction unit; The task information extraction unit is used to analyze the stream-type record text using a natural language model, extract the text data of the target entity associated with project management, and extract the task information using the named entity recognition method; the text data includes the task name, task node, time and task content; the task information includes time, person, place and event content; A task classification unit is used to perform semantic analysis on task information, extract task information keywords, match the task information keywords with a task category keyword library, and determine the task category; The project progress analysis unit is used to attribute the task information to the workflow of the target project based on the task category, combined with the identification of the dependency relationship and execution order of the task information, and determine the project progress according to the node position corresponding to the workflow of the target project; The project plan matching unit is used to match the project progress with each project plan and determine the current project plan corresponding to the project progress; A project member assignment unit is used to extract feature vectors of task keywords and project member labels through a natural language processing algorithm, match task keywords and project member labels through vector similarity, and assign task information to the project member with the highest vector similarity; The actual progress update unit is used to match the time of the task information with the time of the task node in the current project plan and update the actual progress of the project; The prediction unit is used to predict the probability of project completion based on the actual progress of the project and the current project plan, including: collecting historical data, calculating the time deviation coefficient, resource consumption rate and critical path deviation to construct a sample data set; Build a probability prediction model, use the Monte Carlo simulation engine to train the probability prediction model, input the data of the sample data set into the probability prediction model, and obtain the probability of project completion; Assume the time deviation coefficient is The actual completion time is The planned completion time is , the total critical path duration is ,but: ； Assume that the resource consumption rate is , the actual resource usage is The total planned resources are , the process weight factor is ,but: ； Assume the critical path deviation is , the number of key processes completed is The total number of key processes is ,but: ； Assume that the probability of project completion is , , , and is the model parameter of the probability prediction model, then the probability prediction model is expressed as: 。

Images