Task workload assessment method and device, equipment and medium
By identifying project requirements information and data, and using the workload evaluation model, the subjectivity and accuracy of task workload evaluation in traditional methods are solved, and more accurate and efficient task workload evaluation and resource allocation are achieved.
Patent Information
- Application Number
- CN202411075144.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-11-26
AI Technical Summary
Traditional task workload assessment methods rely on professional experience, have strong subjectivity and poor accuracy, and are difficult to adapt to complex and changeable project environments, and cannot accurately evaluate task workload.
By obtaining project development document information, identifying requirements information and splitting tasks, extracting project data, entering trained workload evaluation models, determining task complexity and workload, using machine learning methods to predict task workload, and reducing dependence on professional experience .
It improves the accuracy and efficiency of task workload assessment, adapts to complex project environments, reduces manual intervention, and achieves more scientific resource allocation and project management.
Smart Images

Figure CN119027049A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer information processing, and in particular to a task workload assessment method, device, equipment and medium. Background Art
[0002] In task management, accurate workload assessment is the key to ensuring that projects are completed on time, on quality, and on budget. Traditional task workload assessment methods usually require users to assess the workload of each task in the project based on their professional experience. This task workload assessment method mainly relies on the user's professional experience, and has the problems of strong subjectivity and poor accuracy. With the increasing complexity of projects, traditional task workload assessment methods can no longer meet actual needs.
[0003] Therefore, how to more accurately evaluate the workload of a task is a technical problem that needs to be solved urgently. Summary of the invention
[0004] The embodiments of the present application provide a task workload assessment method, apparatus, device and medium for more accurately assessing the workload of each task to be assessed in a project to be assessed.
[0005] In a first aspect, the present application provides a task workload assessment method, the method comprising:
[0006] Acquire project development document information of the project to be evaluated, identify multiple pieces of requirement information in the project development document information, and divide the project to be evaluated into multiple tasks to be evaluated according to the multiple pieces of requirement information;
[0007] Extracting project data of the project to be evaluated from the project development document information, wherein the project data is used to characterize attribute characteristics of the project to be evaluated;
[0008] Inputting the project information into a trained workload assessment model for processing to obtain the workload of the project to be assessed;
[0009] The complexity of each task to be evaluated is determined based on the content information corresponding to each task to be evaluated in the project development document information, and the workload of each task to be evaluated is determined based on the workload of the project to be evaluated and the complexity of each task to be evaluated.
[0010] In the embodiment of the present application, the project development document information of the project to be evaluated is obtained, and multiple demand information in the project development document information is identified, and the project to be evaluated is split into multiple tasks to be evaluated according to the multiple demand information, so as to improve the splitting efficiency of the project to be evaluated and improve the accuracy of the project splitting. In addition, the present application determines the project data of the project to be evaluated from the project development document information to characterize the attribute characteristics of the project to be evaluated, inputs the project information into the workload evaluation model, obtains the workload of the project to be evaluated, and improves the accuracy of the workload of the project to be evaluated. The present application determines the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information, and determines the workload of each task to be evaluated based on the workload of the project to be evaluated and the complexity of each task to be evaluated, without relying on the workload of the user's professional experience to manually evaluate the workload of the task, more accurately evaluates the workload of each task to be evaluated in the project to be evaluated, and can better adapt to the complex and changeable project environment and improve the applicability of the evaluation.
[0011] In a possible embodiment, after splitting the project to be evaluated into multiple tasks to be evaluated according to the multiple pieces of requirement information, the method further includes:
[0012] Determine task data of each task to be evaluated based on content information corresponding to each task to be evaluated in the project development document information, wherein the task data of each task to be evaluated is used to characterize attribute characteristics of the task to be evaluated;
[0013] The task data of each task to be evaluated is respectively input into the workload evaluation model for processing to determine the workload of each task to be evaluated.
[0014] In an embodiment of the present application, the task data of each task to be evaluated is input into the workload evaluation model for processing to determine the workload of each task to be evaluated, thereby more accurately evaluating the workload of each task to be evaluated in the project to be evaluated and improving the efficiency of the evaluation.
[0015] In a possible embodiment, after determining the workload of each task to be evaluated, the method further includes:
[0016] Based on the workload of each task to be evaluated, resources are allocated to each task to be evaluated in the manner that the greater the workload, the more resources are allocated.
[0017] In the embodiment of the present application, resources are allocated to each task to be evaluated based on the workload of each task to be evaluated, thereby improving resource utilization efficiency and work efficiency.
[0018] In a possible embodiment, determining the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information includes:
[0019] For each task to be evaluated, based on the set multiple attribute fields, the content information corresponding to the task to be evaluated in the project development document information is identified and processed to obtain a field value corresponding to each attribute field;
[0020] The task complexity of the task to be evaluated is determined based on the field value corresponding to each attribute field and the set weight corresponding to each attribute field.
[0021] In an embodiment of the present application, by identifying and processing the content information corresponding to the task to be evaluated in the project development document information, the field value corresponding to each attribute field is obtained, and based on the field value corresponding to each attribute field and the set weight corresponding to each attribute field, the task complexity of the task to be evaluated is determined, thereby improving the accuracy of the determined task complexity of the task to be evaluated.
[0022] In a possible embodiment, the workload assessment model is trained in the following manner:
[0023] Acquire a training data set, wherein the training data set includes a plurality of historical data, each of which includes historical task data and historical workload corresponding to a historical task;
[0024] Inputting each piece of historical data in the training data set into a preset workload assessment model respectively, processing it using the preset workload assessment model, and training the preset workload assessment model with the goal of outputting the historical workload of the historical data;
[0025] Until the preset workload assessment model converges, the workload assessment model is obtained.
[0026] In a possible embodiment, obtaining a training data set includes:
[0027] Acquire an initial data set including a plurality of initial historical data;
[0028] The initial data set is filtered according to the set filtering rules to obtain a training data set.
[0029] In an embodiment of the present application, an initial data set including multiple initial historical data is filtered according to set filtering rules to obtain a training data set, so as to ensure the diversity, completeness and accuracy of the historical data in the training data set.
[0030] In a possible embodiment, the setting rule includes part or all of the following:
[0031] Deleting target initial historical data in the initial data set, wherein the similarity between the target initial historical data and at least one other initial historical data in the initial data set except the target initial historical data exceeds a set threshold;
[0032] Delete the initial historical data in the initial data set that does not match at least one set data validation rule.
[0033] In an embodiment of the present application, the initial data set is filtered based on the complexity between the initial historical data and / or the set data validation rules to obtain a training data set to ensure the diversity, completeness and accuracy of the historical data in the training data set.
[0034] In a second aspect, the present application provides a task workload evaluation device, the device comprising:
[0035] A splitting module is used to obtain project development document information of the project to be evaluated, identify multiple demand information in the project development document information, and split the project to be evaluated into multiple tasks to be evaluated according to the multiple demand information;
[0036] An extraction module, used to extract the project data of the project to be evaluated from the project development document information, wherein the project data is used to characterize the attribute characteristics of the project to be evaluated;
[0037] A first determination module is used to input the project information into a trained workload assessment model for processing to obtain the workload of the project to be assessed;
[0038] The second determination module is used to determine the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information, and to determine the workload of each task to be evaluated based on the workload of the project to be evaluated and the complexity of each task to be evaluated.
[0039] In a third aspect, the present application provides an electronic device, including:
[0040] A memory for storing program instructions;
[0041] The processor is used to call the program instructions stored in the memory, and execute the steps included in any one of the methods in the first aspect according to the obtained program instructions.
[0042] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes any one of the methods described in the first aspect.
[0043] In a fifth aspect, the present application provides a computer program product, comprising: a computer program code, when the computer program code is run on a computer, the computer executes any one of the methods described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 A schematic diagram of an application scenario provided for an embodiment of the present application;
[0045] Figure 2 A flowchart of a task workload evaluation method provided in an embodiment of the present application;
[0046] Figure 3 A flowchart of a method for determining the workload of each task to be evaluated provided in an embodiment of the present application;
[0047] Figure 4 A detailed flow chart of the first task workload evaluation method provided in the embodiment of the present application;
[0048] Figure 5 A detailed flow chart of the second task workload evaluation method provided in the embodiment of the present application;
[0049] Figure 6 A flowchart of a method for training a workload evaluation model provided in an embodiment of the present application;
[0050] Figure 7 A flowchart of a method for obtaining a training data set provided in an embodiment of the present application;
[0051] Figure 8 A flowchart of a method for determining the complexity of each task to be evaluated provided in an embodiment of the present application;
[0052] Fig. 9 A structural diagram of a task workload evaluation device provided in an embodiment of the present application;
[0053] Fig.10 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0054] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.
[0055] The terms "first" and "second" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any of their variations are intended to cover non-exclusive protection. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. "Multiple" in the present application can mean at least two, for example, two, three or more, and the embodiments of the present application are not limited.
[0056] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.
[0057] In the technical solution of this application, the acquisition, transmission, storage, and use of data are in compliance with the requirements of relevant national laws and regulations.
[0058] Before introducing the task workload evaluation method provided in the embodiment of the present application, in order to facilitate understanding, the technical background of the embodiment of the present application is first introduced in detail below.
[0059] In task management, accurate workload assessment is the key to ensuring that projects are completed on time, on quality, and on budget. Traditional task workload assessment methods usually require users to assess the workload of each task in the project based on their professional experience. This task workload assessment method mainly relies on the user's professional experience, and has the problems of strong subjectivity and poor accuracy. With the increasing complexity of projects, traditional task workload assessment methods can no longer meet actual needs.
[0060] Therefore, how to more accurately evaluate the workload of a task is a technical problem that needs to be solved urgently.
[0061] In order to solve the above problems, the present application proposes a task workload assessment method, device, equipment and medium to more accurately assess the workload of each task to be assessed in the project to be assessed.
[0062] First reference Figure 1 , which is a schematic diagram of an application scenario of an embodiment of the present application, including a user device 11 and a server 12. Among them, the user device 11 and the server 12 are connected by a network for communication, and the network can be a local area network, a wide area network, etc. The user device 11 can be a convenient device (for example: a mobile phone, a tablet, a laptop, etc.), or a personal computer (Personal Computer, PC). The server 12 can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, and big data and artificial intelligence platforms. The user 10 logs in to the server 12 through the client installed in the user device 11, wherein the client can be a web browser, or it can be an application client installed in a mobile user device, such as a mobile phone, a tablet computer, etc. The user device 11 is used to collect the project development document information of the project to be evaluated, and send it to the server 12, and the server 12 is used to determine the workload of each task to be evaluated of the project to be evaluated based on the project development document of the project to be evaluated. During the entire interaction process, data encryption technology is used to protect data security and privacy.
[0063] In the embodiment of the present disclosure, as an optional implementation, the server 12 obtains the project development document information of the project to be evaluated uploaded by the user 10 on the client of the user device 11, and identifies multiple requirement information in the project development document information, and divides the project to be evaluated into multiple tasks to be evaluated according to the multiple requirement information; extracts project data of the project to be evaluated from the project development document information, wherein the project data is used to characterize the attribute characteristics of the project to be evaluated; inputs the project information into the trained workload evaluation model for processing to obtain the workload of the project to be evaluated; determines the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information, and determines the workload of each task to be evaluated based on the workload of the project to be evaluated and the complexity of each task to be evaluated.
[0064] Reference below Figure 2 The flowchart of a task workload evaluation method is shown to illustrate the technical solution provided by the embodiment of the present application:
[0065] Step 201 : obtaining project development document information of a project to be evaluated, identifying multiple pieces of requirement information in the project development document information, and dividing the project to be evaluated into multiple tasks to be evaluated according to the multiple pieces of requirement information.
[0066] The project development document information of the project to be evaluated records the detailed design information of the project to be evaluated. For example, the project development document information includes information such as the project name, the functions that the project needs to achieve, the estimated start time, and the estimated end time.
[0067] Optionally, after the project to be evaluated is divided into multiple tasks to be evaluated according to multiple demand information, task data of each task to be evaluated may be determined based on the project development document information, and the workload of each task to be evaluated may be determined based on the task data of each task to be evaluated. Figure 3 A flowchart of a method for determining the workload of each task to be evaluated provided in an embodiment of the present application, such as Figure 3 As shown, at least the following steps 301-302 are included:
[0068] Step 301, determining task data of each task to be evaluated based on content information corresponding to each task to be evaluated in the project development document information;
[0069] The task data of each task to be evaluated is used to characterize the attribute characteristics of the task to be evaluated.
[0070] Step 302: Input the task data of each task to be evaluated into the workload evaluation model for processing to determine the workload of each task to be evaluated.
[0071] The workload evaluation model can be pre-trained using a machine learning method (such as a supervised learning method). The basic model used to train the workload evaluation model can be various models with evaluation functions, such as a convolutional neural network model, a neural network model, and the like.
[0072] Step 202: extracting project data of the project to be evaluated from the project development document information.
[0073] Among them, project data is used to characterize the attribute characteristics of the project to be evaluated.
[0074] Step 203: Input the project information into the trained workload assessment model for processing to obtain the workload of the project to be assessed.
[0075] In the embodiments of the present application, the workload is expressed in a certain unit of measurement (eg, man-day, man-month). Man-day is a unit of workload, which means the workload done by one person in one day.
[0076] Step 204, determining the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information, and determining the workload of each task to be evaluated based on the workload of the project to be evaluated and the complexity of each task to be evaluated.
[0077] Since the greater the complexity of the task to be evaluated, the greater the workload of the task to be evaluated, therefore, based on the workload of the project to be evaluated and the complexity of each task to be evaluated, the workload of each task to be evaluated is determined according to the principle that the greater the complexity, the greater the workload.
[0078] In the embodiment of the present application, the project development document information of the project to be evaluated is obtained, and multiple demand information in the project development document information is identified, and the project to be evaluated is split into multiple tasks to be evaluated according to the multiple demand information, so as to improve the splitting efficiency of the project to be evaluated and improve the accuracy of the project splitting. In addition, the present application determines the project data of the project to be evaluated from the project development document information to characterize the attribute characteristics of the project to be evaluated, inputs the project information into the workload evaluation model, obtains the workload of the project to be evaluated, and improves the accuracy of the workload of the project to be evaluated. The present application determines the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information, and determines the workload of each task to be evaluated based on the workload of the project to be evaluated and the complexity of each task to be evaluated, without relying on the workload of the user's professional experience to manually evaluate the workload of the task, more accurately evaluates the workload of each task to be evaluated in the project to be evaluated, and can better adapt to the complex and changeable project environment and improve the applicability of the evaluation.
[0079] In an embodiment of the present application, the method for determining the workload of each task to be evaluated includes two cases. The first case is to determine the workload of each task to be evaluated based on the workload of the project to be evaluated and the complexity of each task to be evaluated. The second case is to determine the workload of each task to be evaluated based on the task data of each task to be evaluated.
[0080] For the first case mentioned above, the specific steps of the first task workload evaluation method provided are described in detail below. Figure 4 As shown:
[0081] Step 401: Obtain project development document information of the project to be evaluated.
[0082] The project development document information of the project to be evaluated may be obtained by identifying information on documents such as the project requirement document and the project design document of the project to be evaluated.
[0083] Step 402: identifying multiple pieces of requirement information in the project development document information, and dividing the project to be evaluated into multiple tasks to be evaluated according to the multiple pieces of requirement information.
[0084] Step 403: extracting project data of the project to be evaluated from the project development document information.
[0085] Among them, project data is used to characterize the attribute characteristics of the project to be evaluated. Project data includes basic project information, resource information and external influence information. Basic project information includes project name, project type, project complexity, number of function points (FP) of the project, etc. Resource information includes human resources, material resources, time constraints and other information. External influence information is external conditions that may affect the workload, including policy changes, market environment and other information.
[0086] FP is a method to measure the functional scale of a software system. It estimates the time and human resources required for software development by quantifying the functional requirements of the software. In the field of software development, FP is often used as an indicator to calculate the cost and progress of software development. Currently, the FP of a task / project can be determined using the Function Point Analysis Method (IFPUG).
[0087] In the embodiment of the present application, the project type of the project to be evaluated is determined by the following method:
[0088] The project development document information is matched with a plurality of set standard project development document information respectively, the matched standard project development document information is determined, and the project type corresponding to the matched project development document information is used as the project type of the project to be evaluated.
[0089] Specifically, the similarities between the project development document information and multiple set standard project development document information are calculated respectively, the standard project development document information corresponding to the maximum similarity is determined, and the project type corresponding to the determined standard project development document information is used as the project type of the project to be evaluated.
[0090] Each standard project development document information corresponds to a project type. The set multiple standard project development document information can be set according to actual conditions.
[0091] In the embodiment of the present application, if there is no set multiple standard project development document information, the project development document information of multiple projects is obtained, clustered using a clustering method, and the project type of each project is determined. Any one of the projects is used as a document to be evaluated, and the project type corresponding to any one of the projects is used as the project type of the project to be evaluated. Among them, the clustering algorithm can be set according to the actual situation. For example, the clustering algorithm can be a K-means algorithm (K-means), a density-based spatial clustering of applications with noise (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) and other algorithms.
[0092] In the embodiment of the present application, cluster analysis is used to identify the characteristics of different project types, and similar projects are grouped together to obtain multiple clusters, thereby explaining the similarities and differences between different clusters. Cluster analysis provides richer information for workload assessment, and for projects in different clusters, users can formulate differentiated strategies and management measures to improve the flexibility and effectiveness of project management.
[0093] Step 404: input the project information into the trained workload assessment model for processing to obtain the workload of the project to be assessed.
[0094] Step 405 : determining the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information.
[0095] Step 406: Determine the workload of each task to be evaluated based on the workload of the project to be evaluated and the complexity of each task to be evaluated.
[0096] In view of the second situation mentioned above, the specific steps of the second task workload evaluation method provided are described in detail below. Figure 5 As shown:
[0097] Step 501: Obtain project development document information of the project to be evaluated.
[0098] Step 502: identifying multiple pieces of requirement information in the project development document information, and dividing the project to be evaluated into multiple tasks to be evaluated according to the multiple pieces of requirement information.
[0099] Step 503: determine task data of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information.
[0100] Among them, the task data of each task to be evaluated is used to characterize the attribute characteristics of the task to be evaluated. The task data includes basic task information, resource information and external influence information. The basic task information includes task name, task type, task complexity, number of FPs of the task and other information. The resource information includes human resources, material resources, time constraints and other information. The external influence information includes policy changes, market environment and other information.
[0101] In the embodiment of the present application, the method for determining the task type of the task to be evaluated is the same as the method for determining the project type of the project to be evaluated, and will not be repeated here.
[0102] Step 504 , input the task data of each task to be evaluated into the workload evaluation model for processing, and determine the workload of each task to be evaluated.
[0103] Since the project splitting methods in the prior art usually remain at a relatively rough level, this coarse-grained splitting method is difficult to accurately reflect the complexity and diversity of the tasks, resulting in errors in the subsequent workload assessment. Therefore, in order to solve the above problems, this application identifies multiple requirement information in the project development document information, and splits the project to be evaluated into multiple tasks to be evaluated according to the multiple requirement information, thereby ensuring that each task to be evaluated has a clear input-output relationship and dependency relationship, thereby improving the efficiency and accuracy of project management.
[0104] Among them, the above-mentioned demand information can be set according to actual conditions. The user needs to clarify the overall strategy for splitting the project, which includes which demand information is used for splitting, for example, functions, stages, difficulty, technical dependence and other information, to ensure that this information can comprehensively cover all aspects of the project, so as to form a multi-level and clear task structure. Therefore, in the embodiment of the present application, according to the characteristics and needs of the project, detailed splitting rules are preset, that is, based on which demand information is split, these splitting rules can be based on the best practices of project management, or they can be rules summarized based on past project experience. The splitting rules need to be clear and specific, which is convenient for the system to automatically identify and split the project, and also provide guidance for manual adjustment.
[0105] Taking the requirement information as task function as an example, identify the task functions in the project development document information, determine three task functions, namely task function 1, task function 2 and task function 3, and split the project to be evaluated into three tasks to be evaluated according to the three task functions, namely task 1 to be evaluated corresponding to task function 1, task 2 to be evaluated corresponding to task function 2, and task 3 to be evaluated corresponding to task function 3.
[0106] Optionally, the present application supports automatic identification and splitting of partial tasks, while also allowing users to manually adjust and optimize the splitting results, thereby ensuring the accuracy and flexibility of the splitting. Specifically, multiple demand information in the project development document information is identified, and the project to be evaluated is split into multiple tasks to be evaluated according to the multiple demand information, which generally involves analyzing the task description, expected goals, technical requirements and other information in the project development document information of the project to be evaluated, so as to determine which parts of the project to be evaluated can be independently formed into tasks to be evaluated. This automatic splitting method can significantly improve the splitting efficiency of the project and reduce manual intervention. Since the automatic splitting method may not fully meet all the needs of the project, especially when dealing with complex or special situations, therefore, on the basis of the automatic splitting method, the user is allowed to manually adjust and optimize the splitting results to ensure the accuracy and flexibility of the project splitting, so that the task structure is more in line with the actual needs of the project.
[0107] In an embodiment of the present application, after the project to be evaluated is split into multiple tasks to be evaluated according to multiple demand information, the input-output relationship, dependency relationship, estimated start time and end time, required resources and other information of each task to be evaluated are recorded. This information is crucial for subsequent resource allocation and progress control, thereby ensuring that each task to be evaluated has a clear goal and executability.
[0108] Among them, dependency refers to the fact that one task depends on the completion or result of another one or more tasks during execution. This application divides dependencies into direct dependencies and indirect dependencies. Direct dependency means that a task must wait for the completion of another task before it can start, and indirect dependency refers to the dependency generated through multiple intermediate tasks. This application can identify the dependencies between each task to be evaluated through project planning, historical experience, expert consultation, etc. Dependencies are usually represented as arrows or connecting lines, pointing from one task to another, indicating that the former is a prerequisite or dependency of the latter.
[0109] For example, a software development project includes four tasks: "requirements analysis", "design", "coding" and "testing". The "design" task depends on the completion of the "requirements analysis" task, because the design needs to be based on the requirements; the "coding" task depends on the completion of the "design" task, because the coding is based on the design document; the "testing" task depends on the completion of the "coding" task, because the test is performed on the coded software.
[0110] Among them, the input in the input-output relationship refers to the input data or resources required before each task is executed, and the output in the input-output relationship refers to the output data or results generated after each task is executed. This application matches the output of any task to be evaluated with the input of other tasks to be evaluated, forming a clear input-output chain, which is represented by data flow arrows, from the output of the task to be evaluated to the input of the subsequent task to be evaluated, indicating the transmission and flow of data.
[0111] For example, a software development project includes four tasks: "requirements analysis", "design", "coding" and "testing". The output of the "requirements analysis" task is the requirements specification, which serves as the input of the "design" task; the output of the "design" task is the design document, which serves as the input of the "coding" task; the output of the "coding" task is the executable code, which serves as the input of the "testing" task.
[0112] In the embodiment of the present application, after the project to be evaluated is split into multiple tasks to be evaluated according to multiple demand information, it is necessary to verify and adjust the entire project structure based on the recorded information of each task to be evaluated to ensure the effectiveness and feasibility of the task structure and provide strong support for subsequent project management. Specifically, it includes checking whether the dependencies between the tasks to be evaluated are correct, whether the estimated time is reasonable, and whether the required resources are sufficient.
[0113] Specifically, the dependency and input-output relationships between the tasks to be evaluated are documented in the form of charts, flow charts, etc., so that users can check whether the dependency and input-output relationships between the tasks to be evaluated are correct based on relevant documents, and check whether the input-output relationships between the tasks to be evaluated are correct. By clarifying the dependency and input-output relationships between tasks, a reasonable project plan and schedule can be formulated, and potential dependency conflicts or input-output mismatches can be identified, which helps to carry out risk warning and management in advance and ensure the accuracy of project splitting. For example, project management software is used for visual display, where the project management software can be Gantt charts, Performance Evaluation and Review Technique (PERT) charts, Work Breakdown Structure (WBS) and other software.
[0114] Among them, the Gantt chart can also be called a bar chart or a bar chart. It uses a bar chart to show the internal relationship of the progress of projects, schedules and other time-related systems over time. The Gantt chart is basically a line chart. The horizontal axis represents time, the vertical axis represents the activities to be scheduled, and the lines represent the planned and actual completion of activities over the entire period. It can intuitively show when the task is planned to be carried out, and the comparison between the actual progress and the planned requirements.
[0115] The PERT chart uses a network diagram to describe the task network of a project. It can not only express the planning and arrangement of subtasks, but also estimate the completion of tasks during the execution of task plans, analyze the impact of the completion of certain subtasks on the overall situation, and find out the areas and key subtasks that affect the overall situation. The PERT chart can depict the sequence of various activities included in the project, indicate the time or related cost of each activity, and clearly describe the dependencies between subtasks.
[0116] WBS decomposes a project according to certain principles. The project is decomposed into tasks, and the tasks are decomposed into multiple tasks. Then each task is assigned to each person's daily activities until it can no longer be decomposed. That is, project → task → work → daily activities. WBS is oriented to deliverables, and the grouping of project elements summarizes and defines the entire scope of work of the project. Each descending level represents a more detailed definition of the project work.
[0117] In the embodiment of the present application, the workload assessment model in the above steps 404 and 504 can be obtained by training a preset workload assessment model using the acquired training data set. Figure 6 A flowchart of a method for training a workload evaluation model provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, at least the following steps 601-603 are included:
[0118] Step 601, obtaining a training data set.
[0119] The training data set includes multiple historical data, and each historical data includes historical task data and historical workload of the corresponding historical task.
[0120] Step 602, input each piece of historical data in the training data set into a preset workload assessment model, process it using the preset workload assessment model, and train the preset workload assessment model with the historical workload of the output historical data as the goal.
[0121] Step 603, until the preset workload assessment model converges, a workload assessment model is obtained.
[0122] In the embodiment of the present application, in order to ensure the accuracy and consistency of the historical data in the training data set, it is necessary to filter the acquired initial data set to obtain the training data set. Figure 7 A flowchart of a method for obtaining a training data set provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the above step 601 at least includes the following steps 701-702:
[0123] Step 701: Acquire an initial data set including a plurality of initial historical data.
[0124] This application supports obtaining initial historical data from multiple data sources. The initial historical data can be imported into the system through a data interface or an application programming interface (API).
[0125] Step 702: Filter the initial data set according to the set filtering rules to obtain a training data set.
[0126] Optionally, the filtering rules are set to include some or all of the following:
[0127] Deleting target initial historical data in the initial data set, wherein the similarity between the target initial historical data and at least one other initial historical data in the initial data set except the target initial historical data exceeds a set threshold;
[0128] Delete the initial historical data in the initial data set that does not match at least one of the set data validation rules.
[0129] Since the training data set includes a large amount of similar historical data, the workload assessment model obtained by training the preset workload assessment model using the training data set is difficult to capture the overall distribution of historical data and is easily affected by extreme values, that is, the workload assessment model performs too well in the training data set, but performs poorly in the verification data set and the test data set, that is, the generalization error is large and the generalization ability is poor, which causes the problem of overfitting of the workload assessment model. Therefore, in the embodiment of the present application, the target initial historical data in the initial data set is deleted, and the similarity between the target initial historical data and at least one other initial historical data in the initial data set except the target initial historical data exceeds the set threshold, that is, the number of initial historical data with large similarity in the initial data set is reduced to ensure the diversity and integrity of the historical data in the training data set finally obtained, and reduce the situation where the workload assessment model overfits. Among them, the threshold value can be set according to the actual situation. For example, the threshold value is set to 0.9, and the similarity between the target initial historical data and other initial historical data can be calculated using the existing similarity calculation method, which is not limited here.
[0130] The data validation rules set in the embodiments of the present application can be set according to actual conditions. For example, the data validation rules can include whether there are missing values in the initial historical data, whether there are abnormal values (extreme values) in the initial historical data, whether the information in the initial historical data satisfies the set data type, whether the information in the initial historical data satisfies the set data range, and other rules.
[0131] In the embodiment of the present application, for each piece of initial historical data in the initial data set, the initial historical data is identified for missing values, and if the initial historical data has missing values, the initial historical data is deleted from the initial data set. In addition, the present application can also use the mean, median, mode or predicted value to fill in the missing values in the initial historical data.
[0132] In an embodiment of the present application, for each initial historical data in the initial data set, outlier identification is performed on the initial historical data. If there is an outlier in the initial historical data, the initial historical data is deleted from the initial data set. Outliers may be caused by measurement errors, data entry errors, or abnormal events. The present application can use statistical methods to identify and process outliers in the initial historical data. For example, the statistical method can be a standard score method (Z-score, Z score), an interquartile range method (Inter-Quartile Range, IQR) and other methods.
[0133] Among them, the Z score is the process of dividing the difference between a number and the mean by the standard deviation. In statistics, the standard score is the number of symbols of the standard deviation of the value of an observation or data point above the mean of the observed or measured value. IQR is used to describe the degree of dispersion or dispersion of data. It is obtained by calculating the difference between the third quartile and the first quartile in the data set. These two quartiles represent the values at 75% and 25% of the positions in the data set, respectively. IQR reflects the degree of dispersion of the middle 50% of the data, which plays an important role in identifying abnormal values or outliers in the data.
[0134] In the embodiment of the present application, each piece of initial historical data is verified using a logic verification and cross-validation method. Specifically, business logic rules are applied to verify the rationality of each piece of initial historical data. For example, check whether the task completion time is within the set data range, and check whether the workload data conforms to common sense. And use multiple data sources for cross-validation to ensure the accuracy and consistency of the initial historical data.
[0135] In addition to filtering the initial data set using set filtering rules as described above, the present application can also use a machine learning algorithm to filter the initial data set to obtain a training data set, which is used to automatically learn and identify data patterns in the absence of clear rules, improve filtering efficiency, and ensure the accuracy of historical data in the training data set.
[0136] Optionally, before inputting each historical data in the training data set into the preset workload assessment model, the format of each historical data is adjusted and converted into the input format required by the preset workload assessment model, that is, by ensuring that the data type and format of each historical data are unified, subsequent data processing and data analysis are facilitated.
[0137] Optionally, after the initial data set is filtered according to the set filtering rules to obtain the training data set, the historical data in the training data set is analyzed using a statistical analysis method to discover the rules and trends in the historical data.
[0138] Specifically, a statistical analysis method is used to analyze the historical data in the training data set to obtain a statistical analysis result. The statistical analysis method includes at least one of descriptive statistics and inferential statistics. Descriptive statistics refers to calculating the central tendency (such as mean, median, mode) and dispersion (such as standard deviation, variance) of all historical data in the training data set to obtain distribution feature information, which describes the distribution characteristics of the historical data (such as normal distribution, skewed distribution). Inferential statistics refers to inferring overall feature information based on all historical data in the training data set. The statistical analysis result includes at least one of distribution feature information and overall feature information.
[0139] In an embodiment of the present application, the user can set splitting rules based on the statistical analysis results to help identify the complexity and workload differences between different tasks, or quantify the workload of each task based on the statistical analysis results to provide a basis for project planning. The user can also discover tasks with abnormal or unstable workloads based on the statistical analysis results, identify project risks in advance and formulate corresponding response measures.
[0140] Optionally, data quality is monitored in real time during data processing and analysis, erroneous or irrelevant data is discovered and processed in a timely manner, and a feedback mechanism is established to allow users or system administrators to intervene and correct data problems when they are discovered.
[0141] Optionally, in the above step 405, the complexity of each task to be evaluated is determined based on the content information corresponding to each task to be evaluated in the project development document information. Figure 8 A flowchart of a method for determining the complexity of each task to be evaluated provided in an embodiment of the present application, such as Figure 8As shown, the above step 405 at least includes the following steps 801-802:
[0142] Step 801, for each task to be evaluated, based on multiple set attribute fields, the content information corresponding to the task to be evaluated in the project development document information is identified and processed to obtain a field value corresponding to each attribute field;
[0143] Among them, the multiple attribute fields set above include fields such as the number of FPs, task scale, technical complexity, number of personnel required, task implementation cycle and difficulty of requirements.
[0144] Step 802 : determining the task complexity of the task to be evaluated based on the field value corresponding to each attribute field and the set weight corresponding to each attribute field.
[0145] The multiple attribute fields set include attribute field 1, attribute field 2 and attribute field 3, and the weight corresponding to attribute field 1 is P A , the weight corresponding to attribute field 2 is P B , the weight corresponding to attribute field 3 is P C For example, if the content information corresponding to the task to be evaluated in the project development document information is identified and processed based on three attribute fields, it is determined that the field value corresponding to attribute field 1 is A1, the field value corresponding to attribute field 2 is B1, and the field value corresponding to attribute field 3 is C1, then the task complexity of the task to be evaluated is Q = A1*P A +B1*P B +C1*P C .
[0146] Optionally, after determining the workload of each task to be evaluated, the following is also included:
[0147] Based on the workload of each task to be evaluated, resources are allocated to each task to be evaluated in the manner that the greater the workload, the more resources are allocated.
[0148] Optionally, after allocating resources to each task to be evaluated according to the method that the greater the workload, the more resources, an association analysis method is used to analyze the variables related to the workload in the project development document information of the project to be evaluated, and the association strength and confidence between the variables are obtained. Based on the association strength and confidence between the variables, association rules are identified, and the resources allocated to each task to be evaluated in the project to be evaluated are adjusted using the association rules, thereby improving resource utilization efficiency and work efficiency, and identifying redundancy and dependency between tasks to be evaluated, optimizing task design to reduce unnecessary workload. Among them, the association analysis method can be to use an association rule mining algorithm (Apriori algorithm) to calculate the association strength and confidence between variables.
[0149] Among them, the Apriori algorithm itself is an algorithm for mining frequent itemsets in a data set, and then association rules can be discovered from these frequent itemsets. In the workload evaluation process of the tasks to be evaluated, the Apriori algorithm can be used to analyze the correlation and mutual influence between the tasks to be evaluated, so as to more accurately evaluate the workload. Association rules describe the relationship between variables (items), such as "if you buy product A, then you are likely to buy product B." In the Apriori algorithm, an item is the most basic unit in a data set, representing a specific product, service or feature. For example, in the sales data of a supermarket, an item can be a product such as "milk" and "bread."
[0150] While the Apriori algorithm itself focuses on the discovery of frequent itemsets, relevance is often measured using metrics such as support, confidence, and lift. Support represents how often itemsets appear in a dataset, while relevance may refer more broadly to these metrics, especially lift, which compares the frequency of itemsets appearing together with the product of their individual frequencies, thereby assessing the true strength of the association between items.
[0151] In association rules, confidence indicates the conditional probability that the consequent will also appear when the antecedent of the rule appears. It can be expressed as: Where A and B are item sets, and support(X) represents the frequency of item set X in the data set.
[0152] In the Apriori algorithm, "variables" specifically refer to different items or features in a data set used for analysis, which can be any data elements that can be observed and recorded as discrete units. Therefore, in the embodiments of the present application, the "variables" in the Apriori algorithm generally refer to the different data items or features involved in the process of project splitting, workload assessment, etc. of the system or method. These variables may include, but are not limited to, the following: task type, task difficulty, task dependencies, resource requirements, historical data, and other factors.
[0153] Among them, since different types of tasks to be evaluated may have different complexities and workloads in the project splitting, the task type can be regarded as a variable to analyze the impact of different tasks to be evaluated on the overall workload. Task difficulty is also an important factor affecting workload evaluation. Tasks to be evaluated with higher difficulty may require more time and resources to complete, so task difficulty can also be used as a variable. Since there are usually dependencies between tasks to be evaluated during the splitting of the project to be evaluated, the completion of a task to be evaluated may depend on the completion results of other tasks to be evaluated. This dependency can be regarded as a variable to analyze the mutual influence between tasks to be evaluated and the distribution of workload.
[0154] Resource requirements, that is, the various resources (such as manpower, material resources, time, etc.) required to complete the task to be evaluated are also variables that need to be considered when evaluating workload. Different tasks to be evaluated have different resource requirements, which directly affects the workload evaluation. In the process of workload evaluation of tasks to be evaluated, historical data is an important reference. By analyzing the workload of similar historical tasks in historical data, the workload of the current task to be evaluated can be predicted. Therefore, historical data can also be regarded as a variable. In addition to the above five variables, there may be other factors that affect workload evaluation, such as task urgency, priority, executor's skill level, etc. These factors can also be used as variables to improve the accuracy and scientificity of workload evaluation.
[0155] In the embodiment of the present application, based on the workload and time limit of each task to be evaluated, the required resource types (such as human resources, material resources, technical resources, etc.) and quantity are analyzed. For tasks to be evaluated with excessive workload, consider allocating resources from other tasks or adding new resource inputs. For tasks to be evaluated with tight time but moderate workload, it may be necessary to strengthen monitoring and coordination to ensure timely completion. Ensure that resource allocation matches task priority and workload to avoid waste or over-concentration of resources, thereby optimizing resource utilization and improving overall efficiency by reallocating or adjusting the resources of each task to be evaluated.
[0156] Optionally, after determining the workload of each task to be evaluated, the workload of each task to be evaluated is presented to the user in the form of a chart, report, etc., including the workload of each subtask, the workload of the project to be evaluated, workload distribution, etc. The user can adjust the project plan or resource allocation based on the presentation results.
[0157] The workload distribution displays the user's working hours and work content at the hourly or daily granularity. The fixed working hours per day can be set according to the actual situation.
[0158] In the embodiment of the present application, based on the workload of each task to be evaluated, the project plan and resource allocation are flexibly adjusted to ensure that the project proceeds smoothly and achieves the expected goals, which helps to improve the flexibility and adaptability of project management, reduce project risks and improve overall efficiency.
[0159] After determining the workload of each task to be evaluated, the user needs to re-sort out the dependencies between the tasks to be evaluated to ensure that the order and relevance between the tasks to be evaluated are arranged reasonably. For tasks to be evaluated that have dependencies, it is necessary to ensure that each preceding task to be evaluated is completed before each subsequent task to be evaluated begins.
[0160] Optionally, the priority of each task to be evaluated is evaluated based on the workload of each task to be evaluated and the dependency relationship of each task to be evaluated.
[0161] Optionally, based on the priority and time limit of each task to be evaluated, the project milestones of the project to be evaluated are reset to ensure that the setting of the project milestones of the project to be evaluated is consistent with the project goals and schedule plan of the project to be evaluated.
[0162] Since the project to be evaluated may encounter various changes during the execution process, it is necessary to support the ability to update the workload of each task to be evaluated and adjust the task structure in real time during the execution of the project to be evaluated. This includes the ability to re-evaluate the workload of each task to be evaluated, adjust the dependencies and estimated time of each task to be evaluated according to the progress of the project to be evaluated. In addition, during the execution of the project to be evaluated, based on the established project monitoring mechanism, project management tools (such as Gantt charts, Kanban boards, etc.) are used to regularly monitor the progress and resource usage of the project to be evaluated, obtain monitoring results, and provide timely feedback to users based on the monitoring results and actual conditions. Users adjust the project plan and resource allocation of the project to be evaluated based on feedback and new changes in requirements.
[0163] The task workload assessment system provided by this application has a fault tolerance and recovery mechanism, which can automatically identify anomalies and perform error handling and recovery operations. This can ensure the stability and reliability of the system and avoid data loss or workload assessment errors caused by system failures.
[0164] In the task workload assessment system, the types of anomalies that may be encountered include but are not limited to: data anomalies, system anomalies, and algorithm anomalies.
[0165] Among them, data anomalies include but are not limited to missing data, data errors and data inconsistency. Missing data refers to certain key fields or data items being empty or not filled in. Data errors refer to anomalies such as data type mismatch, data format error, and data outside a reasonable range. Data inconsistency refers to conflicts or inconsistencies in data between different data sources. System anomalies include but are not limited to system crashes, insufficient resources and network problems. System crashes refer to the inability of a system to operate normally due to software defects, hardware failures or external interference. Insufficient resources refer to insufficient system resources, such as insufficient resources such as the central processing unit (CPU), memory, and disk space, which affect system performance. Network problems refer to data transmission problems caused by network delays, interruptions or instability. Algorithm anomalies include but are not limited to algorithm failure and parameter errors. Algorithm failure refers to the inability of the workload assessment model to correctly assess the workload or the results are seriously inconsistent with the actual situation. Parameter errors refer to improper parameter settings of the workload assessment model, resulting in inaccurate assessed workload.
[0166] This application can identify anomalies through methods such as data verification, real-time monitoring and algorithm evaluation. Among them, the data verification method refers to identifying anomalies by setting verification rules during data input or processing, and the verification rules include data type, format, range and other rules. The real-time monitoring method is to deploy monitoring tools to monitor the operating status, resource usage, network status and other information of the task workload assessment system in real time, and compare the monitored information with the set monitoring threshold, and trigger an alarm when the monitored information exceeds the set monitoring threshold. The algorithm evaluation method refers to regularly evaluating the effectiveness and accuracy of the workload assessment model, verifying the reliability of the algorithm by comparing the actual results with the evaluation results, and using cross-validation, holdout and other techniques to evaluate the generalization ability of the workload assessment model.
[0167] When data anomalies are identified through data verification methods, anomaly records are made, including the type of anomaly, time of occurrence, data involved, etc. Appropriate processing measures are taken according to the type of anomaly, such as data correction (for correctable erroneous data), data elimination (for data that cannot be corrected or is seriously erroneous), and data interpolation (for missing data). If the data anomaly affects the workload assessment results, the assessment algorithm needs to be rerun to obtain accurate results. After the anomaly is handled, data recovery operations are required to ensure that the system can resume normal operation and continue to provide accurate workload assessment results. Among them, data recovery operations refer to the use of data backups to restore lost or damaged data.
[0168] When an algorithm anomaly is identified through the algorithm evaluation method, check whether the algorithm parameter settings are correct. If the parameter settings are correct, debug and optimize the algorithm to improve its accuracy and stability. If the algorithm itself has defects and cannot be repaired, you need to consider replacing the algorithm or seeking professional help. After the anomaly is handled, an algorithm re-evaluation operation is required to ensure that the system can resume normal operation and continue to provide accurate workload evaluation results. The algorithm re-evaluation operation refers to re-running the evaluation algorithm after fixing the algorithm anomaly to obtain accurate workload evaluation results.
[0169] Based on the same inventive concept, the present application embodiment provides a task workload evaluation device, please refer to Fig. 9 , the device comprises:
[0170] The splitting module 901 is used to obtain the project development document information of the project to be evaluated, identify multiple demand information in the project development document information, and split the project to be evaluated into multiple tasks to be evaluated according to the multiple demand information;
[0171] An extraction module 902 is used to extract the project data of the project to be evaluated from the project development document information, wherein the project data is used to characterize the attribute characteristics of the project to be evaluated;
[0172] A first determination module 903 is used to input the project information into a trained workload assessment model for processing to obtain the workload of the project to be assessed;
[0173] The second determination module 904 is used to determine the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information, and to determine the workload of each task to be evaluated based on the workload of the project to be evaluated and the complexity of each task to be evaluated.
[0174] As an optional implementation manner, after splitting the project to be evaluated into multiple tasks to be evaluated according to the multiple pieces of requirement information, the splitting module 901 is further used to:
[0175] Determine task data of each task to be evaluated based on content information corresponding to each task to be evaluated in the project development document information, wherein the task data of each task to be evaluated is used to characterize attribute characteristics of the task to be evaluated;
[0176] The task data of each task to be evaluated is respectively input into the workload evaluation model for processing to determine the workload of each task to be evaluated.
[0177] As an optional implementation manner, after determining the workload of each task to be evaluated, the second determination module 904 is further configured to:
[0178] Based on the workload of each task to be evaluated, resources are allocated to each task to be evaluated in the manner that the greater the workload, the more resources are allocated.
[0179] As an optional implementation manner, the second determining module 904 is configured to:
[0180] For each task to be evaluated, based on the set multiple attribute fields, the content information corresponding to the task to be evaluated in the project development document information is identified and processed to obtain a field value corresponding to each attribute field;
[0181] The task complexity of the task to be evaluated is determined based on the field value corresponding to each attribute field and the set weight corresponding to each attribute field.
[0182] As an optional implementation manner, the first determining module 903 is used to train the workload assessment model in the following manner:
[0183] Acquire a training data set, wherein the training data set includes a plurality of historical data, each of which includes historical task data and historical workload corresponding to a historical task;
[0184] Inputting each piece of historical data in the training data set into a preset workload assessment model respectively, processing it using the preset workload assessment model, and training the preset workload assessment model with the goal of outputting the historical workload of the historical data;
[0185] Until the preset workload assessment model converges, the workload assessment model is obtained.
[0186] As an optional implementation manner, the first determining module 903 is used to:
[0187] Acquire an initial data set including a plurality of initial historical data;
[0188] The initial data set is filtered according to the set filtering rules to obtain a training data set.
[0189] As an optional implementation, the setting rule includes part or all of the following:
[0190] Deleting target initial historical data in the initial data set, wherein the similarity between the target initial historical data and at least one other initial historical data in the initial data set except the target initial historical data exceeds a set threshold;
[0191] Delete the initial historical data in the initial data set that does not match at least one set data validation rule.
[0192] Based on the same inventive concept, the present application embodiment provides an electronic device, which can realize the function of the task workload evaluation device discussed above, please refer to Fig.10 , the device comprises a processor 101 and a memory 102, wherein the memory 102 is used to store program instructions;
[0193] The processor 101 calls the program instructions stored in the memory and executes the program instructions to implement the following steps:
[0194] Acquire project development document information of the project to be evaluated, identify multiple pieces of requirement information in the project development document information, and divide the project to be evaluated into multiple tasks to be evaluated according to the multiple pieces of requirement information;
[0195] Extracting project data of the project to be evaluated from the project development document information, wherein the project data is used to characterize attribute characteristics of the project to be evaluated;
[0196] Inputting the project information into a trained workload assessment model for processing to obtain the workload of the project to be assessed;
[0197] The complexity of each task to be evaluated is determined based on the content information corresponding to each task to be evaluated in the project development document information, and the workload of each task to be evaluated is determined based on the workload of the project to be evaluated and the complexity of each task to be evaluated.
[0198] As an optional implementation manner, after splitting the project to be evaluated into multiple tasks to be evaluated according to the multiple pieces of requirement information, the processor 101 is further configured to execute:
[0199] Determine task data of each task to be evaluated based on content information corresponding to each task to be evaluated in the project development document information, wherein the task data of each task to be evaluated is used to characterize attribute characteristics of the task to be evaluated;
[0200] The task data of each task to be evaluated is respectively input into the workload evaluation model for processing to determine the workload of each task to be evaluated.
[0201] As an optional implementation manner, after determining the workload of each task to be evaluated, the processor 101 is further configured to execute:
[0202] Based on the workload of each task to be evaluated, resources are allocated to each task to be evaluated in the manner that the greater the workload, the more resources are allocated.
[0203] As an optional implementation manner, determining the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information includes:
[0204] For each task to be evaluated, based on the set multiple attribute fields, the content information corresponding to the task to be evaluated in the project development document information is identified and processed to obtain a field value corresponding to each attribute field;
[0205] The task complexity of the task to be evaluated is determined based on the field value corresponding to each attribute field and the set weight corresponding to each attribute field.
[0206] As an optional implementation, the workload assessment model is trained in the following manner:
[0207] Acquire a training data set, wherein the training data set includes a plurality of historical data, each of which includes historical task data and historical workload corresponding to a historical task;
[0208] Inputting each piece of historical data in the training data set into a preset workload assessment model respectively, processing it using the preset workload assessment model, and training the preset workload assessment model with the goal of outputting the historical workload of the historical data;
[0209] Until the preset workload assessment model converges, the workload assessment model is obtained.
[0210] As an optional implementation, the obtaining of the training data set includes:
[0211] Acquire an initial data set including a plurality of initial historical data;
[0212] The initial data set is filtered according to the set filtering rules to obtain a training data set.
[0213] As an optional implementation, the setting rule includes part or all of the following:
[0214] Deleting target initial historical data in the initial data set, wherein the similarity between the target initial historical data and at least one other initial historical data in the initial data set except the target initial historical data exceeds a set threshold;
[0215] Delete the initial historical data in the initial data set that does not match at least one set data validation rule.
[0216] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, and a computer program product includes: a computer program code, when the computer program code is executed on a computer, the computer executes any of the task workload evaluation methods discussed above. Since the principle of solving the problem by the above-mentioned computer-readable storage medium is similar to that of the task workload evaluation method, the implementation of the above-mentioned computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be repeated.
[0217] Based on the same inventive concept, the embodiment of the present application also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes any of the task workload evaluation methods discussed above. Since the principle of solving the problem by the above computer program product is similar to that of the task workload evaluation method, the implementation of the above computer program product can refer to the implementation of the method, and the repeated parts will not be repeated.
[0218] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0219] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0220] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0221] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of user-operated steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0222] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A task workload assessment method, It is characterized in that The method includes: Acquire project development document information of the project to be evaluated, identify multiple pieces of requirement information in the project development document information, and divide the project to be evaluated into multiple tasks to be evaluated according to the multiple pieces of requirement information; Extracting project data of the project to be evaluated from the project development document information, wherein the project data is used to characterize attribute characteristics of the project to be evaluated; Inputting the project information into a trained workload assessment model for processing to obtain the workload of the project to be assessed; The complexity of each task to be evaluated is determined based on the content information corresponding to each task to be evaluated in the project development document information, and the workload of each task to be evaluated is determined based on the workload of the project to be evaluated and the complexity of each task to be evaluated.
2. The method according to claim 1, It is characterized in that After the project to be evaluated is divided into multiple tasks to be evaluated according to the multiple demand information, the method further includes: Determine task data of each task to be evaluated based on content information corresponding to each task to be evaluated in the project development document information, wherein the task data of each task to be evaluated is used to characterize attribute characteristics of the task to be evaluated; The task data of each task to be evaluated is respectively input into the workload evaluation model for processing to determine the workload of each task to be evaluated.
3. The method according to claim 1 or 2, It is characterized in that After determining the workload of each task to be evaluated, the following steps are also included: Based on the workload of each task to be evaluated, resources are allocated to each task to be evaluated in the manner that the greater the workload, the more resources are allocated.
4. The method according to claim 1, It is characterized in that The determining the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information includes: For each task to be evaluated, based on the set multiple attribute fields, the content information corresponding to the task to be evaluated in the project development document information is identified and processed to obtain a field value corresponding to each attribute field; The task complexity of the task to be evaluated is determined based on the field value corresponding to each attribute field and the set weight corresponding to each attribute field.
5. The method according to claim 1 or 2, It is characterized in that The workload assessment model is trained in the following way: Acquire a training data set, wherein the training data set includes a plurality of historical data, each of which includes historical task data and historical workload corresponding to a historical task; Inputting each piece of historical data in the training data set into a preset workload assessment model respectively, processing it using the preset workload assessment model, and training the preset workload assessment model with the goal of outputting the historical workload of the historical data; Until the preset workload assessment model converges, the workload assessment model is obtained.
6. The method according to claim 5, It is characterized in that The step of obtaining a training data set includes: Acquire an initial data set including a plurality of initial historical data; The initial data set is filtered according to the set filtering rules to obtain a training data set.
7. The method according to claim 6, It is characterized in that The setting rules include some or all of the following: Deleting target initial historical data in the initial data set, wherein the similarity between the target initial historical data and at least one other initial historical data in the initial data set except the target initial historical data exceeds a set threshold; Delete the initial historical data in the initial data set that does not match at least one set data validation rule.
8. A task workload assessment device, It is characterized in that The device includes: A splitting module is used to obtain project development document information of the project to be evaluated, identify multiple demand information in the project development document information, and split the project to be evaluated into multiple tasks to be evaluated according to the multiple demand information; An extraction module, used to extract the project data of the project to be evaluated from the project development document information, wherein the project data is used to characterize the attribute characteristics of the project to be evaluated; A first determination module is used to input the project information into a trained workload assessment model for processing to obtain the workload of the project to be assessed; The second determination module is used to determine the complexity of each task to be evaluated based on the content information corresponding to each task to be evaluated in the project development document information, and to determine the workload of each task to be evaluated based on the workload of the project to be evaluated and the complexity of each task to be evaluated.
9. An electronic device, It is characterized in that include: A memory for storing program instructions; A processor is used to call the program instructions stored in the memory, and execute the steps included in any one of claims 1-7 according to the obtained program instructions.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method according to any one of claims 1 to 7.
Citation Information
Cited By
Workload assessment device and method based on big data
CN120851421A
