Project management method and device and electronic equipment

Abstract

The invention discloses a project management method and device and electronic equipment, and the method comprises the steps: obtaining a task list of a to-be-managed project, constructing a first prompt word according to the task list and a personnel information base, inputting the first prompt word into a preset large language model, and obtaining a task distribution list, the task allocation list comprises a task allocation relationship corresponding to the at least one task. Thus, the task list and the first cue word constructed by the personnel information base are input into the preset large language model to obtain the task allocation list, the task allocation list can be intelligently obtained by adopting the model, manual calculation is not needed, and the project management efficiency can be improved.

Description

Technical Field

[0001] The present application belongs to the technical field of project management, and in particular, relates to a project management method, device and electronic equipment. Background Art

[0002] Project management refers to the management of a specific project under the constraints of limited resources, such as task splitting, task allocation, scheduling and critical path planning, and risk analysis, in order to ultimately achieve the project goals. Among them, task allocation is to split the specific project into multiple tasks in task splitting, and then assign the multiple tasks to different technical personnel for processing. However, currently, task allocation is usually achieved by manually allocating tasks based on experience, resulting in low project management efficiency. Summary of the invention

[0003] The embodiments of the present application provide a project management method, device and electronic device, which can improve project management efficiency.

[0004] In a first aspect, an embodiment of the present application provides a project management method, the method comprising:

[0005] Obtaining a task list of the project to be managed, the task list including at least one task corresponding to the project to be managed and task description information corresponding to each task, the at least one task being obtained by splitting the project to be managed;

[0006] Constructing a first prompt word according to the task list and the personnel information database, wherein the personnel information database includes personnel information of at least one technician associated with the project to be managed, and the personnel information is used to describe the technical capabilities of the corresponding technician;

[0007] The first prompt word is input into a preset large language model to obtain a task assignment list, wherein the task assignment list includes a task assignment relationship corresponding to the at least one task.

[0008] In some embodiments, the above-mentioned inputting the first prompt word into the preset large language model to obtain the task assignment list includes: inputting the first prompt word into the preset large language model to obtain difficulty information of at least one task event in each of the tasks in the task list; the difficulty information is used to characterize the processing difficulty of the corresponding task event; determining the target technician for each task event in each of the tasks through the preset large language model to form the task assignment list, wherein the technical capabilities of the target technician match the difficulty information of each task event in each of the tasks.

[0009] In some embodiments, the above-mentioned obtaining of the difficulty information of at least one task event in each of the tasks in the task list includes: obtaining, by the preset large language model, the number of components contained in each of the task events in each of the tasks and the number of branch processes of each of the task events in each of the tasks according to the first prompt word; wherein the number of branch processes is used to characterize the number of implementation methods for completing the task event; and determining, by the preset large language model, the difficulty information of each task event in each of the tasks according to the number of components contained in each of the task events in each of the tasks and the corresponding number of branch processes.

[0010] In some embodiments, constructing the first prompt word according to the task list and the personnel information library includes: constructing the first prompt word according to the task list, the preset component library and the personnel information library, wherein the preset component library includes at least one component included in at least one preset task event;

[0011] The first prompt word is input into a preset large language model to obtain a task assignment list, wherein the task assignment list also includes the time taken by each technician to complete the corresponding task event, and further includes: inputting the first prompt word into a preset large language model, and according to the first prompt word, obtaining the number of branch processes of the task event and the first number of components and the second number of components corresponding to the task event; wherein the number of branch processes is used to characterize the number of implementation methods for completing the task event, the first number of components is the number of components included in the task event that exist in the preset component library, and the second number of components is the number of components included in the task event that do not exist in the preset component library; the preset large language model determines the time taken by the task event according to the first number of components, the second number of components and the number of branch processes corresponding to the task event.

[0012] In some embodiments, the task assignment list further includes key information of each of the task events in each of the tasks, and the key information is used to characterize the criticality of the corresponding task event in the task; the step of inputting the first prompt word into the preset large language model to obtain the task assignment list further includes: inputting the first prompt word into the preset large language model to obtain key information of each of the task events in each of the tasks; the task assignment list further includes difficulty information corresponding to each of the task events in each of the tasks; after the step of inputting the first prompt word into the preset large language model to obtain the task assignment list, the method further includes: constructing a second prompt word according to the dependency relationship between each of the task events in each of the tasks, the project key information and the task assignment list; the project key information is obtained by extracting key information from the project requirement specification of the project to be managed; the second prompt word is input into the preset large language model to obtain a scheduling plan output by the preset large language model, wherein the scheduling plan includes a task scheduling relationship corresponding to the at least one task.

[0013] In some embodiments, after the second prompt word is input into the preset large language model to obtain the scheduling plan output by the preset large language model, the method further includes: obtaining the processing progress information of each of the task events in each of the tasks; constructing a third prompt word according to the task assignment list, the scheduling plan, the dependency relationship between each of the task events in each of the tasks, the processing progress information of each of the task events in each of the tasks, and the project key information; inputting the third prompt word into the preset large language model to obtain the risk analysis result of each of the task events in each of the tasks output by the preset large language model, wherein the risk analysis result is used to indicate whether there is a risk in the processing progress of the corresponding task event.

[0014] In some embodiments, the above-mentioned inputting the third prompt word into the preset large language model to obtain the risk analysis result of each of the task events in each of the tasks output by the preset large language model includes: inputting the third prompt word into the preset large language model, and according to the third prompt word, matching the processing progress indicated by the processing progress information of the task event with the preset target processing progress to obtain a matching result; wherein the target processing progress is the processing progress that should be completed at the current moment according to the scheduling plan corresponding to the task event; the current moment is the moment of obtaining the current processing progress information of the task event; the preset large language model outputs the risk analysis result of the task event according to the matching result, including: when the matching result indicates that the processing progress of the task event has not reached the preset target processing progress, outputting the risk analysis result to indicate that there is a risk in the processing progress of the task event.

[0015] In some embodiments, after the first prompt word is input into the preset large language model to obtain the task assignment list, the method further includes: constructing a second prompt word according to the dependency relationship between each task event in each task, the project key information and the task assignment list; inputting the second prompt word into the preset large language model, and obtaining the key task event of each task according to the second prompt word; wherein the key task event is a task event whose corresponding key information indicates a criticality greater than a preset degree threshold; obtaining the key task path corresponding to each task output by the preset large language model according to the key task event of each task, wherein the key task path is used to indicate the processing order of the key task events in the corresponding task.

[0016] In some embodiments, after obtaining the critical task paths corresponding to each of the tasks output by the preset large language model according to the critical task events in each of the tasks, the method further includes: obtaining the processing progress information of each of the task events in each of the tasks; constructing a third prompt word according to the scheduling plan, the critical task paths, the task allocation list, the dependencies between each of the task events in each of the tasks, the processing progress information of each of the task events in each of the tasks, and the project key information; inputting the third prompt word into the preset large language model to obtain the risk analysis results of each of the task events in each of the tasks, and the risk analysis results are used to indicate whether there is a risk in the processing progress of the corresponding task event.

[0017] In a second aspect, an embodiment of the present application further provides a project management device, including:

[0018] A task list acquisition module is used to acquire a task list of a project to be managed, wherein the task list includes at least one task corresponding to the project to be managed and task description information corresponding to each task, wherein the at least one task is obtained by splitting the project to be managed;

[0019] A prompt word construction module, used to construct a first prompt word according to the task list and a personnel information database, wherein the personnel information database includes personnel information of at least one technician associated with the project to be managed, and the personnel information is used to describe the technical capabilities of the corresponding technician;

[0020] The task assignment module is used to input the first prompt word into a preset large language model to obtain a task assignment list, wherein the task assignment list includes a task assignment relationship corresponding to the at least one task.

[0021] In a third aspect, an embodiment of the present application further provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;

[0022] When the processor executes the computer program instructions, the project management method as described in any one of the first aspects is implemented.

[0023] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the project management method as described in any one of the first aspects is implemented.

[0024] In a fifth aspect, an embodiment of the present application further provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the project management method as described in the first aspect.

[0025] The project management method, device, electronic device and storage medium of the embodiment of the present application obtain a task list of the project to be managed, the task list includes at least one task corresponding to the project to be managed and task description information corresponding to each task, and constructs a first prompt word according to the task list and the personnel information library, wherein the personnel information library includes personnel information of at least one technician associated with the project to be managed, and the personnel information is used to describe the technical capabilities of the corresponding technician; the first prompt word is input into a preset large language model to obtain a task assignment list output by the preset large language model, wherein the task assignment list includes task assignment relationships corresponding to each task. In this way, by inputting the first prompt word constructed by the task list and the personnel information library into the preset large language model to obtain the task assignment list, it is possible to achieve the intelligent acquisition of the task assignment list using the model without the need for manual calculation, thereby improving the efficiency of project management. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0027] Figure 1 It is a flowchart of a project management method provided by this application;

[0028] Figure 2 It is a flowchart of a task allocation provided by this application;

[0029] Figure 3 This is a flowchart for formulating a scheduling plan and key task paths provided by this application;

[0030] Figure 4 It is a flow chart of a risk analysis provided by this application;

[0031] Figure 5 It is a structural diagram of a project management device provided in an embodiment of the present application;

[0032] Figure 6 It is a schematic diagram of the structure of an embodiment of the electronic device provided by the present application. DETAILED DESCRIPTION

[0033] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0034] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0035] The embodiment of the present application provides a project management method, wherein project management may include at least one of task splitting, task allocation, scheduling plan and key task path and risk analysis, task splitting is splitting the project task into multiple tasks, task allocation is assigning the multiple tasks obtained after splitting to the corresponding technical personnel for processing, scheduling plan is planning the processing time period corresponding to each task after splitting, key task path is the processing order of key tasks in the split tasks, and risk analysis is analyzing whether there is a risk in the processing progress of the split tasks during execution. The project management method can be applied to electronic devices, and the project management method can be executed by electronic devices.

[0036] In order to facilitate understanding of the project management method of the embodiment of the present application, Figure 1 A schematic diagram of a project management method provided by an embodiment of the present invention is shown as follows: Figure 1 As shown, the project management method specifically includes the following steps S101 to S103. The steps S101 to S103 are the task allocation link in task management. In order to facilitate understanding of the steps S101 to S103, the steps S101 to S103 are first roughly described:

[0037] The large language model is preset as the large language model Qwen2.5. The total tasks of the project to be managed are split into task A and task B. The task list is as follows:

[0038] Task A: Name: A; Description: Description of Task A

[0039] Task B: Name: B; Description: Description of Task B.

[0040] The personnel information database is as follows:

[0041] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0042] Mr. Li: Front-end developer, junior engineer, average engineering ability.

[0043] The first prompt word constructed according to the above task list and personnel information database can be as follows:

[0044] “You are an architect with strong professional skills and are good at assigning tasks. Your task is to determine which employee to assign the task to based on the task list and personnel information database.

[0045] #The personnel information database is as follows:

[0046] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0047] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0048] #The task list is as follows:

[0049] Task A: Name: A; Description: Description of Task A;

[0050] Task B: Name: B; Description: Description of Task B;

[0051] Please provide the technician who last performed the task."

[0052] The first prompt word is input into the large language model Qwen2.5, and the task allocation list obtained by the large language model Qwen2.5 is:

[0053] Task A; Technical staff: Mr. Zhang

[0054] Task B; Technical personnel: Mr. Li.

[0055] The above is a rough description of step S101 to step S103. The following is a specific description of step S101 to step S103.

[0056] Step S101, obtaining a task list of a project to be managed.

[0057] The above-mentioned task list includes at least one task corresponding to the project to be managed and task description information corresponding to each task. The various tasks in the above-mentioned task list are obtained after splitting the project to be managed. The above-mentioned at least one task may include the various tasks obtained by splitting the project tasks of the project to be managed. The above-mentioned task contains at least one task event. The task event can be understood as the task action corresponding to each step of completing the corresponding task. For example, if task A is to place an order for Taobao, you must first log in, then create an order, and then display the order details, etc., so the task events included in this task are login, order creation, and order details.

[0058] The task description information corresponding to the above tasks may include the task description information of each task event in the task. For example, the task list includes task A, and task A is placing an order for Taobao. The task events included in the Taobao order are login, order creation, and order details. The information included in the task list may be as follows:

[0059] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0060] Task event 2: Name: Order creation; Description: Create a purchase order;

[0061] Task event 3: Name: Order details; Description: Display of order details, order status, payment information, and delivery address.

[0062] In step S101 of some embodiments, a task list is obtained by executing the task splitting step in task management. The specific steps of task splitting may be as follows:

[0063] Obtain the project requirements specification of the project to be managed and extract the key project information from the project requirements specification.

[0064] The above-mentioned project requirement specification is used to describe the project requirements of the project to be managed. The above-mentioned project key information represents the core information associated with task splitting. For example, the project key information includes functional requirements, non-functional requirements, data flows, business flows and other information.

[0065] A prompt word is constructed according to the key information of the project and the task splitting requirements, wherein the prompt word is used to prompt information associated with the current task splitting action.

[0066] For example, the prompt words may be:

[0067] “#You are a project architect. Your task is to understand the project requirements and split a large project task into independent small tasks according to modules;

[0068] #Each task contains the following information:

[0069] 1. Task name;

[0070] 2. Task description;

[0071] #Key project information is as follows:

[0072] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0073] #Split requirements:

[0074] Tasks and events should be as independent as possible, and each task and event should be completed by a single person;

[0075] Please separate the tasks and get a task list."

[0076] The above prompt words are input into the preset large language model to obtain a task list output by the preset large language model.

[0077] In a possible implementation, the preset large language model may be the large language model Qwen2.5.

[0078] Step S102: construct a first prompt word according to the task list and the personnel information database.

[0079] The above-mentioned personnel information database includes personnel information of at least one technician associated with the project to be managed. The personnel information is used to describe the technical capabilities of the corresponding technician. For example, the personnel information database is as follows:

[0080] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0081] Mr. Li: Front-end developer, junior engineer, average engineering ability.

[0082] The first prompt word is used to indicate information associated with the task assignment action. For example,

[0083] The personnel information database is as follows:

[0084] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0085] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0086] The task list is as follows:

[0087] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0088] Task event 2: Name: Order creation; Description: Create a purchase order;

[0089] Task event 3: Name: Order details; Description: Display of order details, order status, payment information, and delivery address.

[0090] Based on the above personnel information database and task list, the first prompt word constructed by this application can be as follows:

[0091] “You are an architect with strong professional skills and are good at assigning tasks. Your task is to determine which technician should be assigned the task based on the task list and personnel information.

[0092] #The personnel information database is as follows:

[0093] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0094] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0095] #The task list is as follows:

[0096] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0097] Task event 2: Name: Order creation; Description: Create a purchase order;

[0098] Task event 3: Name: Order details; Description: Display order details, order status, payment information, delivery address;

[0099] Please give the technical personnel corresponding to each task event."

[0100] Step S103: input the first prompt word into a preset large language model to obtain a task assignment list.

[0101] Among them, the above-mentioned task allocation list includes task allocation relationships corresponding to each task in the task list, and each task allocation relationship is used to indicate: the corresponding task, and the technical personnel who have the technical ability to complete the task. Specifically, each task allocation relationship can be used to indicate: the task event of the corresponding task, and the technical personnel who have the technical ability to complete the task event.

[0102] For example, the task list includes Task A, which includes Task Event 1, Task Event 2, and Task Event 3. Task Event 1, Task Event 2, and Task Event 3 are Login, Order Creation, and Order Details, respectively. Then the task assignment list is:

[0103] Task event 1: Name: Login; Technical staff: Mr. Zhang;

[0104] Task event 2: Name: Order creation; Technical staff: Mr. Li;

[0105] Task event 3: Name: Order details; Technical staff: Mr. Wang.

[0106] The embodiment of the present application obtains a task assignment list by inputting the first prompt word constructed by the task list and the personnel information database into a preset large language model. This can realize the intelligent acquisition of the task assignment list using the model without the need for manual calculation, thereby improving the efficiency of project management.

[0107] In some embodiments, the above step S103 may include but is not limited to the following steps:

[0108] The first prompt word is input into a preset large language model to obtain difficulty information of at least one task event in each task in the task list.

[0109] The at least one task event may include each task event of the corresponding task in the task list, and the difficulty information is used to characterize the processing difficulty of the corresponding task event. In a possible implementation, the difficulty information may be a difficulty level, which is divided into level one, level two, level three, etc. The higher the level, the greater the processing difficulty indicated by the difficulty level, or the lower the level, the greater the processing difficulty indicated by the difficulty level. In another possible implementation, the difficulty information may be a specific value, such as represented by a difficulty coefficient. The greater the difficulty coefficient, the greater the processing difficulty indicated by the difficulty coefficient, and the smaller the difficulty coefficient, the smaller the processing difficulty indicated by the difficulty coefficient.

[0110] The target technicians for each task event in each task are determined by presetting a large language model to form a task assignment list.

[0111] Among them, the technical capabilities of the target technicians are matched with the difficulty information of each task event in each task.

[0112] Specifically, the preset large language model determines the target technician whose technical ability matches the difficulty information of at least one task event in each task. The preset large language model establishes a correspondence between at least one task event in each task and the matching target technician to form a task assignment list.

[0113] The difficulty information corresponding to each task event in each task is matched with the technical capabilities of the technicians in the personnel information database, and the technicians whose corresponding technical capabilities match the difficulty information of the task event are assigned to the task event. It should be noted that a technician does not necessarily develop only one task event, but can also develop multiple task events.

[0114] For example, the task list includes task A, which has task events of login, order creation, and order details. The difficulty information corresponding to the task events login, order creation, and order details are 0.3, 0.5, and 0.8 respectively. The personnel information database is:

[0115] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0116] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0117] Engineer Wang: Front-end development, mid-level engineer, good engineering ability;

[0118] The task assignment list is:

[0119] Task event 1: Name: Login; Technical staff: Mr. Li;

[0120] Task event 2: Name: Order creation; Technical staff: Mr. Wang;

[0121] Task event 3: Name: Order details; Technical staff: Mr. Zhang.

[0122] In this embodiment, the difficulty information of the task event is used to determine the corresponding matching technician, which can ensure that the matching technician can successfully complete the task event, making the task allocation list more rational and improving the efficiency of project management.

[0123] In some embodiments, the method for obtaining the difficulty information of each task event may include but is not limited to the following steps:

[0124] The preset large language model obtains the number of components included in each task event in each task and the number of branch processes of each task event in each task according to the first prompt word.

[0125] A task event may include multiple branch processes. Branch processes can be understood as the implementation methods of completing the task event. Different branch processes can be different implementation methods of the corresponding task event. For example, the order creation task can be divided into four branch processes: multi-product order, single product order, self-pickup or logistics delivery. Login can be divided into two branch processes: overseas login and domestic login.

[0126] The above-mentioned number of branch processes is used to represent the number of implementation methods for completing a task event. For example, for a task event for creating an order, the corresponding branch processes include multi-product orders, single-product orders, and whether to pick up the order by yourself or by logistics delivery. The number of branch processes corresponding to the order creation task is 4.

[0127] A task event may include multiple components. For example, for an order creation task, the required components include database, form validation, message notification, etc., so the number of components included in the order creation task is 3.

[0128] The preset large language model determines the difficulty information of each task event in each task according to the number of components contained in each task event in each task and the corresponding number of branch processes.

[0129] In a possible implementation, each task event is processed as follows: the number of components and the number of branch processes corresponding to the task event obtained in the above steps are evaluated to obtain the difficulty information of the task event.

[0130] Since the more components or branch processes included in a task event, the more complex the task is, in this embodiment, the difficulty information of the task event is evaluated based on the number of components and branch processes corresponding to the task event, so that the difficulty information of the task event can be effectively obtained.

[0131] In some embodiments, the above step of determining the difficulty information of each task event in each task according to the number of components and the corresponding number of branch processes contained in each task event in each task by the preset large language model may include but is not limited to the following steps:

[0132] A first difficulty evaluation value preset for the number of components of the task event is obtained, and a second difficulty evaluation value preset for the number of branch processes of the task event is obtained.

[0133] In one possible implementation, corresponding difficulty assessment values ​​are set in advance for different numbers of components, and a first correspondence between the number of components and the difficulty assessment value can be established. The first difficulty assessment value corresponding to the task event is obtained by obtaining the difficulty assessment value corresponding to the number of components of the task event from the first correspondence.

[0134] For example, the first correspondence is:

[0135] Number of components: 1-4, the corresponding difficulty assessment value is 0.2;

[0136] Number of components: 5-6, corresponding to a difficulty assessment value of 0.5;

[0137] Number of components: 6 or more, the corresponding difficulty assessment value is 0.8,

[0138] When the number of components of the task event is 4, the first difficulty evaluation value obtained from the above first corresponding relationship is 0.2.

[0139] Corresponding difficulty assessment values ​​can be set in advance for different numbers of branch processes, and a second correspondence between the number of branch processes and the difficulty assessment value can be established. By obtaining the difficulty assessment value corresponding to the number of branch processes of the task event from the second correspondence, the second difficulty assessment value corresponding to the task event is obtained.

[0140] For example, the second correspondence is:

[0141] Number of branch processes: 1-4, the corresponding difficulty assessment value is 0.2;

[0142] Number of branch processes: 5-6, corresponding to a difficulty assessment value of 0.5;

[0143] Number of branch processes: more than 6, the corresponding difficulty assessment value is 0.8,

[0144] When the number of branch processes of the task event is 4, the second difficulty evaluation value obtained from the above second corresponding relationship is 0.2.

[0145] A comprehensive evaluation is performed based on the first difficulty evaluation value and the second difficulty evaluation value corresponding to the task event to obtain difficulty information of the task event.

[0146] In one possible implementation, when the difficulty information is a specific numerical value, the difficulty information can be obtained by summing the first difficulty assessment value and the second difficulty assessment value corresponding to the task event. For example, the first difficulty assessment value and the second difficulty assessment value corresponding to the task event are 0.2 and 0.2 respectively, then the difficulty information obtained is 0.2+0.2=0.4.

[0147] In another possible implementation, the difficulty information can be obtained by taking a weighted sum of the first difficulty assessment value and the second difficulty assessment value corresponding to the task event. For example, the first difficulty assessment value and the second difficulty assessment value corresponding to the task event are 0.2 and 0.2 respectively, and the weights corresponding to the first difficulty assessment value and the second difficulty assessment value are 0.4 and 0.6 respectively, then the difficulty information obtained is 0.2×0.4+0.2×0.6=0.2.

[0148] In this embodiment, by comprehensively calculating the first difficulty evaluation value and the second difficulty evaluation value of the task event, a specific value can be obtained as difficulty information, which can more intuitively reflect the difficulty level of the task event.

[0149] In some embodiments, the task allocation list also includes the time taken by each technician to complete the corresponding task event. Then, constructing the first prompt word according to the task list and the personnel information database in step S102 may also include but is not limited to the following steps:

[0150] A first prompt word is constructed according to the task list, the preset component library and the personnel information library.

[0151] The preset component library includes at least one component included in at least one preset task event, wherein the preset task event may be a task event that has been developed. The components in the preset component library may be components included in the preset task event that has been developed before.

[0152] For example, the default component library is:

[0153] Login module: personnel login includes front-end, back-end interface, authentication, etc.;

[0154] Front-end form UI components: front-end UI components;

[0155] Order center services: order creation, payment, basic information maintenance, etc.

[0156] For example,

[0157] The preset component libraries are:

[0158] Login module: personnel login includes front-end, back-end interface, authentication, etc.;

[0159] Front-end form UI components: front-end UI components;

[0160] Order center services: order creation, payment, basic information maintenance, etc.

[0161] Personnel database:

[0162] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0163] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0164] Mr. Wang: Front-end developer, junior engineer, good engineering skills.

[0165] The task list is as follows:

[0166] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0167] Task event 2: Name: Order creation; Description: Create a purchase order;

[0168] Task event 3: Name: Order details; Description: Display of order details, order status, payment information, and delivery address.

[0169] Based on the above task list, preset component library and personnel information library, the first prompt word constructed by the present application can also be as follows:

[0170] “#You are an architect with strong professional ability and good at assigning tasks. Your task is to determine how long the task will take and which technician to assign it to based on the task list, component library information, and personnel information library.

[0171] #The preset component library is as follows:

[0172] Login module: personnel login includes front-end, back-end interface, authentication, etc.;

[0173] Front-end form UI components: front-end UI components;

[0174] Order center services: order creation, payment, basic information maintenance, etc.;

[0175] #There are the following personnel information databases:

[0176] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0177] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0178] Mr. Wang: Front-end development, junior engineer, good engineering ability;

[0179] #The task list is as follows:

[0180] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0181] Task event 2: Name: Order creation; Description: Create a purchase order;

[0182] Task event 3: Name: Order details; Description: Display order details, order status, payment information, delivery address;

[0183] Please provide the technicians corresponding to each task event and the duration it takes."

[0184] In some embodiments, the step of obtaining the task allocation list including the time-consuming duration in the above step S103 may also include but is not limited to the following steps:

[0185] The first prompt word is input into a preset large language model, and the preset large language model obtains the number of branch processes of the task event and the number of first components and the number of second components corresponding to the task event according to the first prompt word.

[0186] The first number of components is the number of components included in the task event that exist in the preset component library, and the second number of components is the number of components included in the task event that do not exist in the preset component library. For example, the task event includes components 1, 2, and 3, and component 1 already exists in the preset component library, but components 2 and 3 do not exist in the preset component library. Then the first number of components is 1 and the second number of components is 2.

[0187] In a possible implementation, the components included in the task event are matched with the components in the preset component library according to the first prompt word by using a preset large language model to obtain the first component number and the second component number.

[0188] The preset large language model determines the duration of the task event according to the number of first components, the number of second components, and the number of branch processes corresponding to the task event.

[0189] In this embodiment, when the component of the task event exists in the preset component library, it can be directly reused from the preset component library without the need for further development, thereby reducing the development time. However, when the component of the task event does not exist in the preset component library, it is necessary to develop the component, which requires a certain amount of development time. Therefore, the development time required for different task events varies depending on the number of first components, second components and branch processes of different task events. By evaluating the time-consuming duration based on the number of first components, second components and branch processes of the task event, the effectiveness of obtaining the time-consuming duration can be improved.

[0190] In one possible implementation, a first preset time, a second preset time, and a third preset time may be pre-set. The first preset time is the time required for the task event to execute docking only when a corresponding component already exists. The second preset time is the time required to develop the component when no corresponding component exists. The third preset time is the time required to execute a single branch process.

[0191] If the second number of components is zero, the duration of the task event is obtained by calculating the product of the first preset duration and the first number of components. Since, if the second number of components is zero, it means that the components included in the task event are all present in the preset component library, and do not need to be redeveloped, and can be directly obtained and used from the preset component library, therefore, the duration of the task event is only the duration of component docking.

[0192] For example, for task event A, the first component number, second component number, and branch process number of task event A are 2, 0, and 3 respectively, and the first preset duration, the second preset duration, and the third preset duration are all 0.5 days. Then the duration of task event A is 2×0.5=1 day.

[0193] If the second number of components is not zero, a comprehensive calculation is performed based on the first number of components, the second number of components, the number of branch processes, the first preset duration, the second preset duration, and the third preset duration to obtain the duration of the task event. Specifically, a first product between the first preset duration and the first number of components is calculated, a second product between the second preset duration and the second number of components is calculated, and a third product between the second preset duration and the number of branch processes is calculated, and the sum of the first product, the second product, and the third product is determined as the duration of the task event.

[0194] For example, for task event A, the first component number, second component number, and branch process number of task event A are 2, 3, and 3 respectively, and the first preset duration, the second preset duration, and the third preset duration are all 0.5 days. Then the duration of task event A is 2×0.5+3×0.5+3×0.5=4 days.

[0195] Get the task allocation list output by the preset large language model according to the duration of the task event.

[0196] For example, the task assignment list could be:

[0197] Task event 1: Name: Login; Technical staff: Mr. Zhang; Duration: 1 day;

[0198] Task event 2: Name: Order creation; Technical staff: Mr. Li; Duration: 2 days;

[0199] Task event 3: Name: Order details; Technical staff: Mr. Wang; Duration: 3 days.

[0200] In this embodiment, the duration of the task event is comprehensively evaluated based on the first component number, the second component number, the number of branch processes, the first preset duration, the second preset duration, and the third preset duration. This can avoid a large difference between the evaluated duration and the actual duration, thereby improving the accuracy of obtaining the duration of the task event.

[0201] In some embodiments, the task assignment list obtained in the above step S102 based on the first prompt word constructed according to the task list, the preset component library and the personnel information library may not include task events consistent with the preset task events, that is, the developed task events are not included in the task assignment list, and the task events in the task assignment list are all undeveloped task events.

[0202] In a possible implementation, the above step S103 may include but is not limited to the following steps:

[0203] The first prompt word is input into a preset large language model, and the preset large language model matches each task event in each task with a preset component library according to the first prompt word to obtain a target task event of each task.

[0204] The above-mentioned target task event is a task event that is not a preset task event.

[0205] The preset large language model determines the target technicians whose technical capabilities match the difficulty information of each target task event in each task.

[0206] The preset large language model establishes the correspondence between each target task event in each task and the matching target technician to form a task assignment list.

[0207] For example, the first prompt word can be:

[0208] “#You are an architect with strong professional skills and are good at assigning tasks. Your task is to determine whether the task needs to be done, how long it will take, and which technician to assign it to based on the task list, preset component library, and personnel information library.

[0209] #The preset component library is as follows:

[0210] Login module: personnel login includes front-end, back-end interface, authentication, etc.;

[0211] Front-end form UI components: front-end UI components;

[0212] Order center services: order creation, payment, basic information maintenance, etc.;

[0213] #The personnel information database is as follows:

[0214] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0215] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0216] #The task list is as follows:

[0217] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0218] Task event 2: Name: Order creation; Description: Create a purchase order;

[0219] Task event 3: Name: Order details; Description: Display order details, order status, payment information, delivery address;

[0220] Please provide the tasks, technicians and time required.

[0221] The first prompt word is input into the preset large language model, and the task allocation list output by the preset large language model is as follows:

[0222] Task event 1: Order details; Technical staff: Mr. Zhang; Duration: 4 days.

[0223] In some embodiments, the task allocation list also includes key information of each task event in each task, and the key information is used to characterize the criticality of the corresponding task event in the task. The above step S103 also includes but is not limited to the following steps:

[0224] The first prompt word is input into a preset large language model, and key information of each task event in each task is obtained according to the first prompt word.

[0225] The first prompt word is also used to prompt the user to perform a key information acquisition action.

[0226] For example,

[0227] The preset component library is as follows:

[0228] Login module: personnel login includes front-end, back-end interface, authentication, etc.;

[0229] Front-end form UI components: front-end UI components;

[0230] Order center services: order creation, payment, basic information maintenance, etc.;

[0231] The personnel information database is as follows:

[0232] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0233] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0234] The task list is as follows:

[0235] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0236] Task event 2: Name: Order creation; Description: Create a purchase order;

[0237] Task event 3: Name: Order details; Description: Display of order details, order status, payment information, and delivery address.

[0238] Based on the above task list, preset component library and personnel information library, the first prompt word constructed by the present application can also be as follows:

[0239] “#You are an architect with strong professional ability and good at assigning tasks. Your task is to determine which tasks are needed, how long they will take, which technician will be assigned to do them, and how critical they are based on the task list, component library information, and personnel information library.

[0240] #The preset component library is as follows:

[0241] Login module: personnel login includes front-end, back-end interface, authentication, etc.;

[0242] Front-end form UI components: front-end UI components;

[0243] Order center services: order creation, payment, basic information maintenance, etc.;

[0244] #The personnel information database is as follows:

[0245] Mr. Zhang: JAVA development, senior engineer, with strong engineering capabilities;

[0246] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0247] #The task list is as follows:

[0248] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0249] Task event 2: Name: Order creation; Description: Create a purchase order;

[0250] Task event 3: Name: Order details; Description: Display order details, order status, payment information, delivery address;

[0251] Please provide the final tasks, events, technical personnel, time required, and key information, etc."

[0252] In a possible implementation, the key information may be a specific value, which may be represented by a key weight. For tasks in a business process, the key information of the task events in the task flow with the smallest demand in the entire task may be determined as a preset first key weight, and the key information of the task events in the task that do not exist in the task flow may be determined as a preset second key weight, wherein the first key weight is greater than the second key weight. For tasks outside the business process, the key information of each task event in the task may be determined as a preset third key weight.

[0253] For example, the first key weight is 0.8, the second key weight is 0.4, and the third key weight is 0.3. The task list includes task events in the order system, log operations, performance optimization, and other task events. The order system is a task within the business process. The task events of the order system include creating an order, order details, order list display, order modification, order deletion, etc., and creating an order → order details → order list display is the task flow with the smallest demand. The key information of creating an order, order details, and order list display is 0.8, and the key information of modifying an order and deleting an order is 0.4. The key information of task events outside the business process, such as log operations and performance optimization, is determined to be 0.3.

[0254] Obtain a task assignment list output by a preset large language model according to key information of each task event in each task.

[0255] For example, the task assignment list is as follows:

[0256] Task event 1: Create an order; technician: Mr. Zhang; time taken: 3 days; key information: 0.8;

[0257] Task event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Key information: 0.5.

[0258] In this embodiment, the corresponding key information is determined based on the impact of the task event in the business process, which can effectively reflect the criticality of each task event in the task and facilitate subsequent task management.

[0259] In some embodiments, the task allocation list also includes difficulty information of each task event in each task. Based on the task allocation list including the duration, key information and difficulty information of the task event, after step S103, a scheduling plan can be formulated. The project management method also includes but is not limited to the following steps:

[0260] The second prompt word is constructed according to the dependency relationship between each task event in each task, the key information of the project and the task allocation list.

[0261] The above dependency relationship can be understood as representing the execution order of each task event in the task. For example, the task events of Task A include login, order creation, and order details. You must log in before you can create an order, and you can view the order details after creating an order. Therefore, the dependency relationship between these three task events is that order creation depends on login, and order details depend on order creation.

[0262] The second prompt word is used to prompt information associated with the task scheduling action.

[0263] For example,

[0264] The key information of the project is as follows:

[0265] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0266] The task assignment list is as follows:

[0267] Task event 1: Create an order; technician: Zhang Gong; time required: 3 days; difficulty information: 0.5; key information: 0.8;

[0268] Mission event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Difficulty information: 0.6; Key information: 0.5;

[0269] The task event dependencies are as follows:

[0270] Task event 1: Create order; Dependency: Login;

[0271] Task event 2: order details; dependency: task event 1.

[0272] Based on the above dependency relationship, key project information and task allocation list, the second prompt word constructed by the present application may be as follows:

[0273] “#You are an architect with project management capabilities. Your task is to provide a specific scheduling plan based on the dependencies between various task events, key project information, and task assignment lists.

[0274] #Key project information is as follows:

[0275] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0276] #The task assignment list is as follows:

[0277] Task event 1: Create an order; technician: Mr. Zhang; duration: 3 days; difficulty information: 0.5; key information: 0.8;

[0278] Mission event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Difficulty information: 0.6; Key information: 0.5;

[0279] #Task event dependencies are as follows:

[0280] Task event 1: Create order; Dependency: Login;

[0281] Task event 2: order details; dependency: task event 1;

[0282] Please provide a detailed schedule."

[0283] The second prompt word is input into the preset large language model to obtain a scheduling plan output by the preset large language model.

[0284] The scheduling plan includes a task scheduling relationship corresponding to at least one task, the at least one task includes each task in the task allocation list, and the task scheduling relationship is used to indicate: the corresponding tasks, and the processing time period of each task event in the task.

[0285] For example, the scheduling plan can be as follows:

[0286] Task event 1: Create an order; Processing period: November 1 to November 3;

[0287] Task event 2: Order details; processing time period: November 2nd to November 5th.

[0288] In this embodiment, a scheduling plan is obtained based on the dependencies between various task events, project key information and task allocation lists, which can effectively arrange the development order and development duration of task events, ensure that task events are developed in an orderly and accurate manner, and improve project management efficiency.

[0289] In some embodiments, after the second prompt word is input into the preset large language model and the scheduling plan output by the preset large language model is obtained, a risk assessment step may be performed. The project management method may further include but is not limited to the following steps:

[0290] Get the processing progress information of each task event in each task.

[0291] The above processing progress information may be represented in the form of a numerical value, such as a percentage value.

[0292] The third prompt word is constructed according to the task allocation list, the scheduling plan, the dependency relationship between each task event in each task, the processing progress information of each task event in each task, and the key information of the project.

[0293] The third prompt word may be generated by splicing together the task allocation list, the scheduling plan, the dependency relationship between each task event in each task, the processing progress information of each task event in each task, and the key information of the project.

[0294] For example,

[0295] The key information of the project is as follows:

[0296] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0297] The task assignment list is as follows:

[0298] Task event 1: Create an order; technician: Zhang Gong; time required: 3 days; difficulty information: 0.5; key information: 0.8;

[0299] Mission event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Difficulty information: 0.6; Key information: 0.5;

[0300] The task event dependencies are as follows:

[0301] Task event 1: Create order; Dependency: Login;

[0302] Task event 2: order details; dependency: task event 1;

[0303] The schedule is as follows:

[0304] Task event 1: Create an order; Processing period: November 1 to November 3;

[0305] Task event 2: Order details; Processing period: November 2 to November 5;

[0306] The processing progress information is as follows:

[0307] Task event 1: Create order; 80%;

[0308] Mission Event 2: Order details; 50%.

[0309] According to the above task allocation list, scheduling plan, dependency relationship of each task event in each task, processing progress information of each task event in each task, and key project information, the third prompt word constructed can be as follows:

[0310] “#You are an architect with project management capabilities. Your task is to provide risk analysis results based on the task allocation list, scheduling plan, processing progress information of each task event in each task, and key project information.

[0311] #Key project information is as follows:

[0312] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0313] #The task assignment list is as follows;

[0314] Task event 1: Create an order; technician: Mr. Zhang; duration: 3 days; difficulty information: 0.5; key information: 0.8;

[0315] Mission event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Difficulty information: 0.6; Key information: 0.5;

[0316] #Task event dependencies are as follows:

[0317] Task event 1: Create order; Dependency: Login;

[0318] Task event 2: order details; dependency: task event 1;

[0319] #The schedule is as follows:

[0320] Task event 1: Create an order; Processing period: November 1 to November 3;

[0321] Task event 2: Order details; Processing period: November 2 to November 5;

[0322] #Processing progress information is as follows:

[0323] Task event 1: Create order; 80%;

[0324] Mission event 2: Order details; 50%;

[0325] Please analyze whether the mission event is risky."

[0326] The third prompt word is input into the preset large language model to obtain the risk analysis result of each task event in each task output by the preset large language model.

[0327] The above risk analysis result is used to indicate whether there is a risk in the processing progress of the corresponding task event.

[0328] In this embodiment, the risk analysis results of each task event are evaluated through the third prompt word, so as to realize intelligent, timely and effective discovery of risky task events in project management, thereby improving the effectiveness of project management.

[0329] In some embodiments, the above-mentioned method steps for obtaining risk analysis results include but are not limited to the following steps:

[0330] The third prompt word is input into the preset large language model, and according to the third prompt word, the processing progress indicated by the processing progress information of the task event is matched with the preset target processing progress to obtain a matching result.

[0331] The target processing progress is the processing progress that the task event should complete at the current moment according to the scheduling plan corresponding to the task event, and the target processing progress can be a preset value. The current moment is the moment to obtain the current processing progress information of the task event.

[0332] For example, if task event A obtains processing progress information at 12:00 on November 4, the current time is 12:00 on November 4, and the scheduling plan for task event A is: November 3 to November 5, the target processing progress of task event A at 12:00 on November 4 can be set to 50%.

[0333] The above matching result is used to indicate whether the processing progress of the task event reaches the target processing progress.

[0334] The preset large language model obtains the processing progress indicated by the processing progress information by identifying the processing progress information representing the task event from the third prompt word, and the preset large language model matches the processing progress with the preset target processing progress to obtain a matching result.

[0335] When the matching result indicates that the processing progress of the task event has not reached a preset target processing progress, the risk analysis result is output to indicate that there is a risk in the processing progress of the task event.

[0336] For example, the scheduling plan for task event A is: November 3rd to November 5th, and the target processing progress of task event A at 12:00 on November 4th is set to 50%, and the processing progress information of task event A obtained at 12:00 on November 4th indicates a processing progress of 30%. The matching result obtained is an indication that the processing progress of task event A has not reached the target processing progress, and the risk analysis result output for task event A is an indication that there is a risk in the processing progress of task event A.

[0337] In this embodiment, by matching the processing progress of the task event with the preset target processing progress, the risk of the task event processing can be determined promptly and quickly.

[0338] In some embodiments, the project management further includes determining a key task path. After the first prompt word is input into a preset large language model to obtain a task assignment list output by the preset large language model, the project management method includes but is not limited to the following steps:

[0339] The second prompt word is constructed according to the dependency relationship between each task event in each task, the key information of the project and the task allocation list.

[0340] The second prompt word is input into the preset large language model, and the key task events of each task are obtained according to the second prompt word.

[0341] The above-mentioned critical task event is a task event whose corresponding critical information indicates a criticality greater than a preset threshold, and the above-mentioned preset threshold is a threshold set according to demand.

[0342] Specifically, by using a preset large language model, key information of each task event in each task is obtained according to the second prompt word, and task events whose key information indicates a criticality greater than a preset threshold are determined as key task events, thereby obtaining key task events for each task.

[0343] For example, the preset degree threshold is 0.5, and the task events of Task A include logging in, creating an order, and order details. The criticality indicated by the key information of logging in, creating an order, and order details are 0.2, 0.6, and 0.8, respectively. The criticality of creating an order and order details is greater than 0.5, and the key task events of Task A are creating an order and order details.

[0344] Obtain a key task path corresponding to each task output by a preset large language model according to a key task event of each task.

[0345] The above critical task paths are used to indicate the processing order of critical task events in the corresponding tasks.

[0346] In a possible implementation, a large language model is preset to determine the processing order between key task events in the task according to the dependency relationship between each task event in the task in the second prompt word, and obtain the key task path corresponding to the task.

[0347] For example, the key task events of Task A are Create Order and Order Details, where the dependency relationship is Order Details depends on Create Order. Then the key task path corresponding to Task A is Create Order → Order Details.

[0348] In this embodiment, the development sequence of task events is effectively obtained through the dependency relationship between various task events, and the key task path is obtained through the dependency relationship between task events, which can improve the effectiveness of obtaining the key task path.

[0349] In some embodiments, after the critical task path is obtained, risk assessment is performed based on the critical task path. The project management method further includes but is not limited to the following steps:

[0350] Get the processing progress information of each task event in each task.

[0351] The third prompt word is constructed according to the scheduling plan, the key task path, the task allocation list, the dependency relationship between each task event in each task, the processing progress information of each task event in each task, and the key information of the project.

[0352] The third prompt word is obtained by splicing the scheduling plan, the key task path, the task allocation list, the dependency relationship between each task event in each task, the processing progress information of each task event in each task, and the key information of the project.

[0353] For example,

[0354] The key information of the project is as follows:

[0355] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0356] The task assignment list is as follows:

[0357] Task event 1: Create an order; technician: Mr. Zhang; duration: 3 days; difficulty information: 0.5; key information: 0.8;

[0358] Mission event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Difficulty information: 0.6; Key information: 0.5;

[0359] The task event dependencies are as follows:

[0360] Task event 1: Create order; Dependency: Login;

[0361] Task event 2: order details; dependency: task event 1;

[0362] The schedule is as follows:

[0363] Task event 1: Create an order; Processing period: November 1 to November 3;

[0364] Task event 2: Order details; Processing period: November 2 to November 5;

[0365] The key mission paths are as follows:

[0366] Mission event 1 → Mission event 2;

[0367] The processing progress information is as follows:

[0368] Mission event 1: 80%;

[0369] Mission Event 2: 50%.

[0370] Based on the above scheduling plan, key task path, task allocation list, dependency relationship, processing progress information and project key information, the third prompt word constructed by the present application may be as follows:

[0371] “#You are an architect with project management capabilities. Your task is to conduct risk assessment based on the schedule, key task path, task assignment list, processing progress information of each task event in each task, and key project information.

[0372] #Key project information is as follows:

[0373] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0374] #The task assignment list is as follows:

[0375] Task event 1: Create an order; technician: Zhang Gong; time required: 3 days; difficulty information: 0.5; key information: 0.8;

[0376] Mission event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Difficulty information: 0.6; Key information: 0.5;

[0377] #Task event dependencies are as follows:

[0378] Task event 1: Create order; Dependency: Login;

[0379] Task event 2: order details; dependency: task event 1;

[0380] #The schedule is as follows:

[0381] Task event 1: Create an order; Processing period: November 1 to November 3;

[0382] Task event 2: Order details; Processing period: November 2 to November 5;

[0383] #The key task path is as follows:

[0384] Mission event 1 → Mission event 2;

[0385] #Processing progress information is as follows:

[0386] Mission event 1: 80%;

[0387] Mission event 2: 50%;

[0388] Please analyze whether the mission event is risky."

[0389] The third prompt word is input into the preset large language model to obtain the risk analysis results of each task event in each task.

[0390] In this embodiment, by adding the critical task path into the third prompt word, the efficiency of risk analysis can be improved.

[0391] In a possible implementation, the preset large language model obtains corresponding risk analysis results by adopting different risk analysis methods for task events that are not in the critical task path and task events that are in the critical task path.

[0392] In some embodiments, if the task event is a task event in a critical task path, the processing progress indicated by the processing progress information corresponding to the task event is matched with a preset target processing progress to obtain a matching result; when the matching result indicates that the processing progress of the task event has not reached the preset target processing progress, it is determined that the risk analysis result of the task event indicates that there is a risk in the processing progress.

[0393] The method steps in this embodiment are similar to the method steps for obtaining the risk analysis results described above, and reference may be made to the method steps for obtaining the risk analysis results described above, which will not be described in detail here.

[0394] If the task event is not a task event in the critical task path, if the processing progress indicated by the processing progress information of the task event has not reached the processing progress that characterizes the completion of the task event, and the current moment has exceeded the processing time period corresponding to the task event, then it is determined that the risk analysis result of the task event indicates that there is a risk in the processing progress.

[0395] If the processing progress information is represented by a percentage value, the processing progress indicating that the task event has been completed may be 100%.

[0396] For example, the processing progress indicated by the processing progress information of the task event obtained at 12:00 on November 3 is 30%, and the processing time period of the task event is November 1-November 2, and the processing progress representing the completed task event is 100%. Then 30% < 100%, indicating that the processing progress indicated by the processing progress information of the task event has not reached the processing progress representing the completed task event, and the current time is 12:00 on November 3, which exceeds the processing time period of the task event. Then, there is a risk in the processing progress of the task event, and the risk analysis result of the task event output by the preset large language model indicates that there is a risk in the processing progress.

[0397] Technical personnel can intervene in risky mission events based on the instructions of risk analysis results to resolve risk issues of mission events.

[0398] In this embodiment, different risk analysis methods are used for task events that are not in the critical task path and task events that are in the critical task path to obtain corresponding risk analysis results, wherein the risk analysis method for task events in the critical task path is more stringent. Since task events in the critical task path have a greater impact on tasks, by improving the stringency of the risk analysis method for task events in the critical task path, the risk of task events in the critical task path can be better controlled. As for task events that are not in the critical task path, their impact on tasks is relatively small. By reducing the stringency of their risk analysis methods, excessive use of human resources to handle the task events can be avoided.

[0399] It should be noted that the preset large language model can be a model that has been fine-tuned and trained. A specific data set related to project management can be obtained, and the rules related to project management mentioned in the above content can be used to train the model through the specific data set to solidify it into model parameters. The specific data set can include the various rules described above.

[0400] Taking the task splitting example, the specific data set may include the company's internal project management specification documents, etc.

[0401] In order to better understand the above project management method, the embodiment of the present invention provides a complete embodiment of the project management method, and the complete embodiment is as follows:

[0402] Reference Figure 2 , Figure 2 A flowchart of a task allocation provided in this embodiment is as follows: Figure 2 As shown, the electronic device obtains the project requirement specification, and extracts the key project information of the project requirement specification, including functional requirements, non-functional requirements, data flow, business flow, etc., and constructs the initial prompt words according to the key project information and task splitting requirements. The initial prompt words are as follows:

[0403] “#You are a project architect. Your task is to understand the project requirements and split a large project task into independent small tasks according to modules;

[0404] ##Each task contains the following information:

[0405] 1. Task name;

[0406] 2. Task description;

[0407] #Key project information is as follows:

[0408] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0409] #Require:

[0410] Tasks should be as independent as possible, and each task can be completed by a single person;

[0411] Please split the task list".

[0412] The initial prompt word is input into the large language model Qwen2.5, and the task list output by the large language model Qwen2.5 according to the initial prompt word is obtained. The task list is as follows:

[0413] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0414] Task event 2: Name: Order creation; Description: Create a purchase order;

[0415] Task event 3: Name: Order details; Description: Display of order details, order status, payment information, and delivery address.

[0416] The company already has the following component libraries:

[0417] Login module: personnel login includes front-end, back-end interface, authentication, etc.;

[0418] Front-end form UI components: front-end UI components;

[0419] Order center services: order creation, payment, basic information maintenance, etc.

[0420] The personnel information database is as follows:

[0421] Mr. Wang: JAVA development, senior engineer, with strong engineering capabilities;

[0422] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0423] Mr. Zhang: Front-end developer, junior engineer, good engineering skills.

[0424] According to the above task list, component library and personnel information library, the first prompt word is further spliced, and the first prompt word is such as:

[0425] “#You are an architect with strong professional skills and are good at assigning tasks. Your task is to determine whether the task needs to be done, how long it will take, and which technician to assign it to based on the task list, component library, and personnel information library.

[0426] #The company already has the following component libraries:

[0427] Login module: personnel login includes front-end, back-end interface, authentication, etc.;

[0428] Front-end form UI components: front-end UI components;

[0429] Order center services: order creation, payment, basic information maintenance, etc.;

[0430] #There are the following personnel information databases:

[0431] Mr. Wang: JAVA development, senior engineer, with strong engineering capabilities;

[0432] Mr. Li: Front-end development, junior engineer, average engineering ability;

[0433] Mr. Zhang: Front-end development, junior engineer, good engineering ability;

[0434] #The task list is as follows:

[0435] Task event 1: Name: Login; Description: Personnel information login, authentication;

[0436] Task event 2: Name: Order creation; Description: Create a purchase order;

[0437] Task event 3: Name: Order details; Description: Display order details, order status, payment information, delivery address;

[0438] Please provide the final tasks that need to be done, the corresponding technical personnel, the time required, the difficulty information and key information, etc."

[0439] The first prompt word is input into the large language model Qwen2.5, and a task allocation list output by the large language model Qwen2.5 according to the first prompt word is obtained. The task allocation list is as follows:

[0440] Task event 1: Create an order; technician: Mr. Zhang; duration: 3 days; difficulty coefficient: 0.5; key weight: 0.8;

[0441] Task event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Difficulty coefficient: 0.6; Key weight: 0.5.

[0442] Reference Figure 3 , Figure 3 A flowchart of a scheduling plan and key task path is provided in this embodiment, such as Figure 3 As shown, the second prompt word is constructed based on the task allocation list, the dependency relationship between each task event of the task and the key information of the project.

[0443] The obtained task event dependencies are as follows:

[0444] Task event 1: Create order; Dependency: Login;

[0445] Task event 2: order details; dependency: task event 1.

[0446] The second prompt word constructed based on the above task assignment list, dependency relationship and project key information is as follows:

[0447] “#You are an architect with project management capabilities. Your task is to provide a specific schedule and key task path based on the project task list, the dependencies between the various task events, and the key project information.

[0448] #Key project information is as follows:

[0449] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0450] #The task assignment list is as follows:

[0451] Task event 1: Create an order; technician: Mr. Zhang; time required: 3 days; difficulty coefficient: 0.5; key weight: 0.8, dependency: login;

[0452] Task event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Difficulty coefficient: 0.6; Key weight: 0.5; Dependency: Task event 1;

[0453] Please provide the scheduling plan and key task path".

[0454] The second prompt word is input into the large language model Qwen2.5, and the scheduling plan and key task path output by the large language model Qwen2.5 according to the second prompt word are obtained. The scheduling plan is as follows:

[0455] Task event 1: Create an order; Processing period: November 1 to November 3;

[0456] Task event 2: Order details; Processing period: November 2 to November 5;

[0457] The key mission paths are as follows:

[0458] Mission event 1 → Mission event 2.

[0459] Reference Figure 4 , Figure 4 A schematic diagram of a risk analysis process provided in this embodiment, such as Figure 4 As shown, the processing progress information of each task event in each task is obtained, where the processing progress information is as follows:

[0460] Mission event 1: 80%;

[0461] Mission Event 2: 50%.

[0462] The third prompt word is obtained by splicing the scheduling plan, the key task path, the task allocation list, the dependency relationship between each task event of the task, the processing progress information of each task event in each task, and the key information of the project. The third prompt word is as follows:

[0463] “#You are an architect with project management capabilities. Your task is to analyze whether there are risks in task events based on the scheduling plan, key task paths, task allocation list, processing progress information of each task event in each task, and key project information.

[0464] #Key project information is as follows:

[0465] Functional requirements, non-functional requirements, data flow, business flow, etc.;

[0466] #The task assignment list is as follows:

[0467] Task event 1: Create an order; technician: Mr. Zhang; duration: 3 days; difficulty coefficient: 0.5; key weight: 0.8;

[0468] Task event 2: Order details; Technical personnel: Mr. Wang; Time required: 4 days; Difficulty coefficient: 0.6; Key weight: 0.5;

[0469] Task event dependencies:

[0470] Task event 1: Create order; Dependency: Login;

[0471] Task event 2: order details; dependency: task event 1;

[0472] #The schedule is as follows:

[0473] Task event 1: Create an order; Processing period: November 1 to November 3;

[0474] Task event 2: Order details; Processing period: November 2 to November 5;

[0475] The key mission paths are as follows:

[0476] Mission event 1 → Mission event 2;

[0477] #The processing progress information of the task event is as follows;

[0478] Mission event 1: 80%;

[0479] Mission event 2: 50%;

[0480] Please analyze whether the mission event is risky."

[0481] The third prompt word is input into the large language model Qwen2.5, and the risk analysis result output by the large language model Qwen2.5 according to the third prompt word is obtained. The risk analysis result is as follows:

[0482] There is a risk. The risk lies in that: Task Event 1 is a task on the critical path but is completed slowly, and Task Event 2 may delay the overall construction period.

[0483] Figure 5 The schematic diagram of the structure of the project management device provided by the embodiment of the present application is shown. Figure 5 As shown, the project management device 500 includes:

[0484] The task list acquisition module 501 is used to acquire a task list of the project to be managed. The task list includes at least one task corresponding to the project to be managed and task description information corresponding to each task. The at least one task is obtained by splitting the project to be managed.

[0485] The prompt word construction module 502 is used to construct a first prompt word according to the task list and the personnel information database, wherein the personnel information database includes personnel information of at least one technician associated with the project to be managed, and the personnel information is used to describe the technical capabilities of the corresponding technician.

[0486] The task assignment module 503 is used to input the first prompt word into a preset large language model to obtain a task assignment list, wherein the task assignment list includes a task assignment relationship corresponding to at least one task.

[0487] The task assignment module 503 can be specifically used to: input the first prompt word into the preset large language model to obtain the difficulty information of at least one task event in each task in the task list; the difficulty information is used to characterize the processing difficulty of the corresponding task event; determine the target technician for each task event in each task through the preset large language model to form a task assignment list, wherein the technical capabilities of the target technician match the difficulty information of each task event in each task.

[0488] The task assignment module 503 can be specifically used to: obtain the number of components contained in each task event in each task and the number of branch processes of each task event in each task according to the first prompt word by a preset large language model; wherein the number of branch processes is used to characterize the number of implementation methods for completing the task event; determine the difficulty information of each task event in each task according to the number of components contained in each task event in each task and the corresponding number of branch processes by the preset large language model.

[0489] The task allocation module 503 can be specifically used to: obtain a first difficulty assessment value preset for the number of components of a task event, and obtain a second difficulty assessment value preset for the number of branch processes of a task event; perform a comprehensive assessment based on the first difficulty assessment value and the second difficulty assessment value corresponding to the task event to obtain the difficulty information of the task event.

[0490] The prompt word construction module 502 may be specifically used to construct a first prompt word according to the task list, the preset component library and the personnel information library, wherein the preset component library includes at least one component included in at least one preset task event.

[0491] The task assignment list also includes the time taken by each technician to complete the corresponding task event. The task assignment module 503 can be specifically used to: input the first prompt word into the preset large language model, and obtain the number of branch processes of the task event and the first number of components and the second number of components corresponding to the task event according to the first prompt word; wherein the number of branch processes is used to characterize the number of implementation methods for completing the task event, the first number of components is the number of components included in the task event that exist in the preset component library, and the second number of components is the number of components included in the task event that do not exist in the preset component library; the preset large language model determines the time taken for the task event according to the first number of components, the second number of components and the number of branch processes corresponding to the task event.

[0492] The task assignment list also includes key information of each task event in each task, and the key information is used to characterize the criticality of the corresponding task event in the task. The task assignment module 503 can be specifically used to: input the first prompt word into the preset large language model, and obtain the key information of each task event in each task according to the first prompt word.

[0493] The task assignment list also includes difficulty information corresponding to each task event in each task. The above-mentioned project management device 500 also includes a scheduling plan module 504, which is used to construct a second prompt word according to the dependency relationship between each task event in each task, project key information and the task assignment list; the project key information is obtained by extracting key information from the project requirement specification of the project to be managed; the second prompt word is input into the preset large language model to obtain a scheduling plan output by the preset large language model, wherein the scheduling plan includes a task scheduling relationship corresponding to at least one task, and the task scheduling relationship is used to indicate: the corresponding task, and the processing time period of each task event in the task.

[0494] The above-mentioned project management device 500 also includes a risk assessment module 505, which is used to obtain the processing progress information of each task event in each task; construct a third prompt word according to the task allocation list, scheduling plan, the dependency relationship between each task event in each task, the processing progress information of each task event in each task and project key information; input the third prompt word into the preset large language model to obtain the risk analysis result of each task event in each task output by the preset large language model, and the risk analysis result is used to indicate whether there is a risk in the processing progress of the corresponding task event.

[0495] The risk assessment module 505 is specifically used to: input the third prompt word into the preset large language model, and according to the third prompt word, match the processing progress indicated by the processing progress information of the task event with the preset target processing progress to obtain a matching result; wherein the target processing progress is the processing progress that the task event should complete at the current moment according to the scheduling plan corresponding to the task event; the current moment is the moment of obtaining the current processing progress information of the task event. The preset large language model outputs the risk analysis result of the task event according to the matching result, including: when the matching result indicates that the processing progress of the task event does not reach the preset target processing progress, outputting the risk analysis result to indicate that the processing progress of the task event is at risk.

[0496] The above-mentioned project management device 500 also includes a critical path determination module 506, which is used to construct a second prompt word according to the dependency relationship between each task event in each task, project key information and task allocation list; input the second prompt word into a preset large language model, and obtain the critical task event of each task according to the second prompt word; wherein the critical task event is a task event whose corresponding key information indicates a criticality greater than a preset degree threshold; obtain the critical task path corresponding to each task output by the preset large language model according to the critical task event of each task, and the critical task path is used to indicate the processing order of the critical task events in the corresponding task.

[0497] The risk assessment module 505 is also specifically used to: obtain the processing progress information of each task event in each task; construct a third prompt word according to the scheduling plan, key task path, task allocation list, the dependency relationship between each task event in each task, the processing progress information of each task event in each task and project key information; input the third prompt word into the preset large language model to obtain the risk analysis result of each task event in each task, and the risk analysis result is used to indicate whether there is a risk in the processing progress of the corresponding task event.

[0498] The risk assessment module 505 is also specifically used to: input the third prompt word into the preset large language model; obtain the risk analysis result of each task event in each task according to the third prompt word, including at least one of the following: if the task event is a task event in the critical task path, then the processing progress indicated by the processing progress information corresponding to the task event is matched with the preset target processing progress to obtain a matching result; when the matching result indicates that the processing progress of the task event has not reached the preset target processing progress, it is determined that the risk analysis result of the task event indicates that there is a risk in the processing progress; if the task event is not a task event in the critical task path, then if the processing progress indicated by the processing progress information of the task event has not reached the processing progress that characterizes that the task event has been completed, and the current moment has exceeded the processing time period corresponding to the task event, then it is determined that the risk analysis result of the task event indicates that there is a risk in the processing progress; the current moment is the moment of obtaining the current processing progress information of the task event.

[0499] The project management device 500 provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar and will not be repeated here.

[0500] Figure 6 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0501] The electronic device may include a processor 601 and a memory 602 storing computer program instructions.

[0502] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0503] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0504] In some embodiments, the memory 602 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0505] The processor 601 implements any one of the project management methods in the above embodiments by reading and executing computer program instructions stored in the memory 602 .

[0506] In one example, the electronic device may further include a communication interface 603 and a bus 610. Figure 6 As shown, the processor 601, the memory 602, and the communication interface 603 are connected via a bus 610 and communicate with each other.

[0507] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0508] Bus 610 includes hardware, software or both, and the components of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI → Express (PCI → X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 610 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0509] The electronic device can execute the project management method in the embodiment of the present application, thereby realizing the combination Figures 1 to 6 Describe the project management device.

[0510] In addition, in combination with the project management method in the above embodiment, the present application embodiment also provides a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, the project management method in the above embodiment is implemented.

[0511] In combination with the project management method in the above embodiment, an embodiment of the present application also provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device implements the project management method in the above embodiment.

[0512] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0513] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0514] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0515] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box 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, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0516] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A project management method, characterized in that: The method comprises: Obtaining a task list of the project to be managed, the task list including at least one task corresponding to the project to be managed and task description information corresponding to each task, the at least one task being obtained by splitting the project to be managed; Constructing a first prompt word according to the task list and the personnel information database, wherein the personnel information database includes personnel information of at least one technician associated with the project to be managed, and the personnel information is used to describe the technical capabilities of the corresponding technician; The first prompt word is input into a preset large language model to obtain a task assignment list, wherein the task assignment list includes a task assignment relationship corresponding to the at least one task.

2. The method according to claim 1, characterized in that The step of inputting the first prompt word into a preset large language model to obtain a task assignment list includes: Inputting the first prompt word into a preset large language model to obtain difficulty information of at least one task event in each of the tasks in the task list; the difficulty information is used to characterize the processing difficulty of the corresponding task event; The target technicians for each task event in each of the tasks are determined by the preset large language model to form the task assignment list, wherein the technical capabilities of the target technicians match the difficulty information of each task event in each of the tasks.

3. The method according to claim 2, characterized in that The obtaining difficulty information of at least one task event in each of the tasks in the task list includes: The preset large language model obtains the number of components contained in each task event in each task and the number of branch processes of each task event in each task according to the first prompt word; wherein the number of branch processes is used to represent the number of implementation methods for completing the task event; The preset large language model determines the difficulty information of each task event in each task according to the number of components contained in each task event in each task and the corresponding number of branch processes.

4. The method according to claim 2, characterized in that: The step of constructing a first prompt word according to the task list and the personnel information database includes: Constructing a first prompt word according to the task list, the preset component library and the personnel information library, wherein the preset component library includes at least one component included in at least one preset task event; The first prompt word is input into a preset large language model to obtain a task assignment list, wherein the task assignment list also includes the time taken by each technician to complete the corresponding task event, and also includes: The first prompt word is input into a preset large language model, and according to the first prompt word, the number of branch processes of the task event and the first number of components and the second number of components corresponding to the task event are obtained; wherein the number of branch processes is used to characterize the number of implementation methods for completing the task event, the first number of components is the number of components included in the task event that exist in the preset component library, and the second number of components is the number of components included in the task event that do not exist in the preset component library; The preset large language model determines the time duration of the task event according to the first component number, the second component number and the branch flow number corresponding to the task event.

5. The method according to claim 4, characterized in that The task allocation list also includes key information of each task event in each task, and the key information is used to characterize the criticality of the corresponding task event in the task; The step of inputting the first prompt word into a preset large language model to obtain a task assignment list further includes: Inputting the first prompt word into a preset large language model to obtain key information of each task event in each of the tasks; The task assignment list also includes difficulty information corresponding to each of the task events in each of the tasks. After inputting the first prompt word into a preset large language model to obtain the task assignment list, the method further includes: Constructing a second prompt word according to the dependency relationship between each task event in each task, the key information of the project and the task allocation list; the key information of the project is obtained by extracting key information from the project requirement specification of the project to be managed; The second prompt word is input into the preset large language model to obtain a scheduling plan output by the preset large language model, wherein the scheduling plan includes a task scheduling relationship corresponding to the at least one task.

6. The method according to claim 5, characterized in that After inputting the second prompt word into the preset large language model to obtain the scheduling plan output by the preset large language model, the method further includes: Obtaining processing progress information of each of the task events in each of the tasks; constructing a third prompt word according to the task allocation list, the scheduling plan, the dependency relationship between the task events in the tasks, the processing progress information of the task events in the tasks, and the key information of the project; The third prompt word is input into the preset large language model to obtain a risk analysis result of each of the task events in each of the tasks output by the preset large language model, wherein the risk analysis result is used to indicate whether there is a risk in the processing progress of the corresponding task event.

7. The method according to claim 6, characterized in that The step of inputting the third prompt word into the preset large language model to obtain the risk analysis result of each of the task events in each of the tasks output by the preset large language model includes: The third prompt word is input into the preset large language model, and according to the third prompt word, the processing progress indicated by the processing progress information of the task event is matched with the preset target processing progress to obtain a matching result; wherein the target processing progress is the processing progress that should be completed at the current moment according to the scheduling plan corresponding to the task event; and the current moment is the moment of obtaining the current processing progress information of the task event; The preset large language model outputs a risk analysis result of the task event according to the matching result, including: When the matching result indicates that the processing progress of the task event has not reached a preset target processing progress, the risk analysis result is output to indicate that there is a risk in the processing progress of the task event.

8. The method according to claim 5, characterized in that After inputting the first prompt word into a preset large language model to obtain a task assignment list, the method further includes: Constructing a second prompt word according to the dependency relationship between each task event in each task, the key information of the project and the task allocation list; Inputting the second prompt word into the preset large language model, and obtaining the key task event of each of the tasks according to the second prompt word; wherein the key task event is a task event whose corresponding key information indicates a criticality greater than a preset threshold; Acquire a critical task path corresponding to each of the tasks output by the preset large language model according to the critical task events of each of the tasks, wherein the critical task path is used to indicate a processing order of the critical task events in the corresponding tasks.

9. The method according to claim 8, characterized in that After obtaining the key task paths corresponding to each of the tasks output by the preset large language model according to the key task events in each of the tasks, the method further includes: Obtaining processing progress information of each of the task events in each of the tasks; constructing a third prompt word according to the scheduling plan, the key task path, the task allocation list, the dependency relationship between the task events in the tasks, the processing progress information of the task events in the tasks, and the key information of the project; The third prompt word is input into the preset large language model to obtain a risk analysis result of each of the task events in each of the tasks, wherein the risk analysis result is used to indicate whether there is a risk in the processing progress of the corresponding task event.

10. A project management device, characterized in that: The device comprises: A task list acquisition module is used to acquire a task list of a project to be managed, wherein the task list includes at least one task corresponding to the project to be managed and task description information corresponding to each task, wherein the at least one task is obtained by splitting the project to be managed; A prompt word construction module, used to construct a first prompt word according to the task list and a personnel information database, wherein the personnel information database includes personnel information of at least one technician associated with the project to be managed, and the personnel information is used to describe the technical capabilities of the corresponding technician; The task assignment module is used to input the first prompt word into a preset large language model to obtain a task assignment list, wherein the task assignment list includes a task assignment relationship corresponding to the at least one task.

11. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the project management method according to any one of claims 1 to 9 is implemented.

Images