Project evaluation method, apparatus, device, medium, and program product

Abstract

The application provides a project evaluation method, device, equipment, medium and program product, relates to the technical field of artificial intelligence, and is used for improving project evaluation accuracy and efficiency. The specific technical scheme is as follows: acquiring demand characteristic information and risk source information corresponding to a first to-be-executed project; inputting the demand characteristic information into a construction period prediction model to output a predicted construction period time corresponding to the first to-be-executed project; inputting the demand characteristic information into a risk classification model to output a risk level corresponding to the first to-be-executed project; and generating a risk evaluation report based on the predicted construction period time, the risk level and the risk source information. The application is applied to a government-enterprise project evaluation execution scene.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a project evaluation method, apparatus, equipment, medium, and program product. Background Technology

[0002] Currently, in the enterprise software technology service field, customized software projects for government and enterprise clients typically have unique requirements, heterogeneous technology stacks (e.g., involving multiple technologies such as Java, Python, big data platforms, and artificial intelligence frameworks), and tight delivery cycles. The industry's current commonly used technical solutions mainly rely on the personal experience of relevant personnel for requirements analysis, workload assessment, and resource planning.

[0003] However, in the above methods, the project evaluation mainly relies on the personal experience of relevant personnel and lacks data support, resulting in low accuracy and efficiency of project evaluation. Summary of the Invention

[0004] This application provides a project evaluation method, apparatus, equipment, medium, and program product to improve the accuracy and efficiency of project evaluation.

[0005] In a first aspect, embodiments of this application provide a project evaluation method, which includes: obtaining demand characteristic information and risk source information corresponding to a first project to be executed; inputting the demand characteristic information into a schedule prediction model and outputting the predicted schedule time corresponding to the first project to be executed; inputting the demand characteristic information into a risk classification model and outputting the risk level corresponding to the first project to be executed; and generating a risk assessment report based on the predicted schedule time, risk level, and risk source information.

[0006] The technical solution provided in this application brings at least the following benefits: by predicting the project duration through the demand characteristics information of the first project to be executed, and by jointly determining the risk assessment report of the first project to be executed with the risk level and risk source information corresponding to the project to be executed, the project assessment is avoided by relying mainly on the personal experience of relevant personnel and lacking data support, thereby improving the efficiency and accuracy of project assessment.

[0007] One possible implementation is that the aforementioned requirement characteristic information includes at least one of the following: total number of requirements, number of functional components developed, number of customized functional components, number of reused functional components, functional component reuse rate, number of technology stacks, average defect rate of functional components, dependency depth information, team capability matching degree, average resource load, number of similar projects, average duration of similar projects, and cost overrun rate of similar projects.

[0008] Another possible implementation method, the above-mentioned acquisition of the requirement feature information corresponding to the first project to be executed, includes: performing entity recognition on the project document of the first project to be executed to obtain the entity information corresponding to the first project to be executed, the entity information including: function point entity information, project data entity information, project constraint entity information, and technology stack requirement entity information; determining at least one functional component that matches the entity information based on the semantic information of the entity information; and generating the requirement feature information corresponding to the first project to be executed based on the entity information and at least one functional component.

[0009] Another possible implementation, based on the semantic information of entity information, determines at least one functional component that matches the entity information, including: calculating the cosine similarity between the semantic information of the entity information and M stored functional components, where M is a positive integer; and determining at least one functional component corresponding to a cosine similarity greater than or equal to a preset threshold as at least one functional component that matches the entity information.

[0010] Another possible implementation, after generating a risk assessment report based on predicted project duration, risk level, and risk source information, further includes: decomposing the project document of the first project to be executed into at least two first sub-tasks; determining the resource scheduling strategy corresponding to each sub-task based on the first conditions and the task requirements of each sub-task, wherein the first conditions include at least one of the following: functional matching, maximum number of parallel tasks, resource load limit, and task dependencies. Based on the risk assessment report and the resource scheduling strategy corresponding to each sub-task, a project delivery feasibility assessment strategy is generated, which includes: requirements analysis results, component reuse strategy, risk assessment conclusions, resource optimization strategy, and implementation suggestions.

[0011] Secondly, embodiments of this application provide a project evaluation apparatus, including: an acquisition module, a processing module, and a generation module. The acquisition module is used to acquire demand characteristic information and risk source information corresponding to a first project to be executed. The processing module is used to input the demand characteristic information into a schedule prediction model and output the predicted schedule time corresponding to the first project to be executed; and to input the demand characteristic information into a risk classification model and output the risk level corresponding to the first project to be executed. The generation module is used to generate a risk assessment report based on the predicted schedule time, risk level, and risk source information.

[0012] Another possible implementation method is that the above-mentioned requirement characteristics information includes at least one of the following: total number of requirements, number of functional components developed, number of customized functional components, number of reused functional components, functional component reuse rate, number of technology stacks, average defect rate of functional components, dependency depth information, team capability matching degree, average resource load, number of similar projects, average duration of similar projects, and cost overrun rate of similar projects.

[0013] Another possible implementation is that the above processing module is specifically used to perform entity recognition on the project document of the first project to be executed, to obtain entity information corresponding to the first project to be executed, the entity information including: function point entity information, project data entity information, project constraint entity information and technology stack requirement entity information; and based on the semantic information of the entity information, to determine at least one functional component that matches the entity information.

[0014] The generation module is specifically used to generate requirement feature information corresponding to the first project to be executed based on the entity information and the at least one functional component.

[0015] Another possible implementation is that the above processing module is specifically used to calculate the cosine similarity between the semantic information of the entity information and the stored M functional components, where M is a positive integer; and to determine at least one functional component corresponding to the cosine similarity that is greater than or equal to a preset threshold as at least one functional component that matches the entity information.

[0016] In another possible implementation, the aforementioned processing module is further configured to generate a risk assessment report based on the predicted project duration, risk level, and risk source information; then, decompose the project document of the first project to be executed into at least two first sub-tasks; and, based on the first conditions and the task requirements of each sub-task, determine the resource scheduling strategy corresponding to each sub-task. The first conditions include at least one of the following: functional matching, maximum number of parallel tasks, resource load limit, and task dependencies. The generation module is further configured to generate a project delivery feasibility assessment strategy based on the risk assessment report and the resource scheduling strategy corresponding to each sub-task. The project delivery feasibility assessment strategy includes: requirements analysis results, component reuse strategy, risk assessment conclusions, resource optimization strategy, and implementation suggestions.

[0017] Thirdly, this application provides an electronic device comprising: a processor and a memory; the memory stores a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the method of the first aspect described above.

[0018] Fourthly, this application provides a readable storage medium on which a program or instructions are stored, which, when executed by a computer, implement the method of the first aspect described above.

[0019] Fifthly, this application provides a computer program product stored in a storage medium, which, when executed by a computer, implements the method described in the first aspect.

[0020] In a sixth aspect, embodiments of this application provide a chip including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0021] The beneficial effects of the second to sixth aspects mentioned above are described in the corresponding description of the first aspect and will not be repeated here. Attached Figure Description

[0022] Figure 1 A schematic diagram of a network architecture for an application of a project evaluation method provided in this application embodiment;

[0023] Figure 2 A flowchart illustrating a project evaluation method provided in this application embodiment;

[0024] Figure 3 A flowchart illustrating another project evaluation method provided in this application embodiment;

[0025] Figure 4 A flowchart illustrating yet another project evaluation method provided in this application embodiment;

[0026] Figure 5 A flowchart illustrating yet another project evaluation method provided in this application embodiment;

[0027] Figure 6 A flowchart illustrating yet another project evaluation method provided in this application embodiment;

[0028] Figure 7 This application provides a schematic diagram of the structure of a project evaluation system.

[0029] Figure 8 This is a schematic diagram of the structure of a project evaluation device provided in an embodiment of this application;

[0030] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0032] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0033] The terms "at least one," "at least one of," etc., used in the specification and claims of this application refer to any one, any two, or a combination of two or more of the included items. For example, at least one of a, b, and c can mean: "a," "b," "c," "a and b," "a and c," "b and c," and "a, b, and c," where a, b, and c can be single or multiple. Similarly, "at least two" refers to two or more items, and its meaning is similar to that of "at least one."

[0034] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0035] The embodiments of this application provide a project evaluation method, apparatus, equipment, medium, and program product that can be applied to government and enterprise project evaluation execution scenarios.

[0036] Currently, in the enterprise-level software technology service field, the delivery of customized software projects for government and enterprise clients faces numerous technical challenges. These projects typically feature unique requirements, heterogeneous technology stacks (involving multiple technologies such as Java, Python, big data platforms, and artificial intelligence frameworks), and tight delivery cycles. In the pre-sales phase, the industry's commonly used technical solutions rely heavily on the project manager's personal experience for requirements analysis, workload assessment, and resource planning, lacking systematic and quantitative decision support tools. This traditional model has significant limitations: first, it lacks a deep understanding of requirements, easily underestimating technical complexity and leading to project delays or cost overruns; second, it lacks systematic management of existing software assets within the organization, making it difficult to quickly identify reusable components and resulting in redundant development; and third, resource allocation relies primarily on manual experience, hindering collaborative optimization between internal teams and ecosystem partners.

[0037] To solve the above problems, the following three solutions can be used in the prior art.

[0038] Option 1: Knowledge Graph-Based Capability Assessment Solution: This solution primarily targets the capability assessment of operations and maintenance (O&M) personnel. It assesses the types and levels of O&M personnel's capabilities by constructing a capability evaluation index system. The technical approach involves building a personnel capability knowledge graph and improving work order processing efficiency through quantitative evaluation of indicators. However, this solution is limited to the scope of personnel capability assessment and does not address key technical aspects such as software component reuse and quantitative project risk assessment, thus failing to solve decision support issues before project delivery.

[0039] Option 2, Project Delivery Reasonableness Assessment: This option uses a decision tree model to process project documents, extracting parameters such as actual stages, amounts, and processing cycles. It then compares these parameters with a normal distribution established from historical data to verify the compliance of the project plan. This technical approach is a post-audit model, only assessing reasonableness after the project plan is formed, and cannot proactively generate optimization plans at the initial project stage.

[0040] Option 3, Resource Scheduling Optimization Scheme: This scheme is designed for vehicle embedded system environments and optimizes computing resource allocation by analyzing task runtime latency. Its core technology is a task scheduling strategy based on hardware performance metrics, primarily addressing resource allocation issues in real-time systems. However, this scheme is not applicable to the optimized allocation of soft resources such as human resources and knowledge assets in software project management.

[0041] In summary, the three technical solutions described above suffer from several drawbacks: High dependency on experience: Project evaluation heavily relies on personal experience, lacks data support, and accuracy is difficult to guarantee. Low asset reuse rate: A large number of software components accumulated within the institute have not been effectively inventoried and deconstructed, making them unsuitable for rapid matching and reuse in new projects. Delayed risk assessment: Potential project risks (such as delays and cost overruns) often only emerge in the middle or even later stages of project execution, resulting in high error correction costs. Inefficient resource allocation: Resource allocation lacks optimization algorithms, making it difficult to achieve optimal overall delivery efficiency.

[0042] To address the aforementioned technical issues, embodiments of this application provide a risk assessment method, apparatus, equipment, medium, and program product. By predicting the project duration using the demand characteristic information of the first project to be executed, and jointly determining the risk assessment report of the first project to be executed using the risk level and risk source information corresponding to the project to be executed, this approach avoids the lack of data support due to reliance on the personal experience of relevant personnel in project assessment, thereby improving the efficiency and accuracy of project assessment.

[0043] The risk assessment methods, apparatus, equipment, media, and program products provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0044] Figure 1 The diagram illustrates a network architecture for applying a risk assessment method according to an embodiment of this application. For example... Figure 1As shown, the network architecture includes a risk assessment device 101 and a terminal device 102. The risk assessment device 101 and the terminal device 102 are interconnected.

[0045] In some embodiments, the risk assessment device 101 may be a server, a computer, or a processor or processing unit within a server or computer. The server may be a single server or a server cluster comprising multiple servers. It should be noted that the embodiments of this application do not limit the specific device form of the risk assessment device 101. Figure 1 The risk assessment device 101 is illustrated as a single server.

[0046] In some embodiments, the terminal device may be a mobile phone, tablet computer, laptop computer, handheld computer, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, personal computer (PC), ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc., and the embodiments of this application do not specifically limit it. Figure 1 The example shown is a mobile phone, with terminal device 102 as an example.

[0047] In some embodiments, the terminal device 102 sends a first project to be executed to the risk assessment device 101, and the risk assessment device 101 receives the first project to be executed sent by the terminal device 102; then, it obtains the demand characteristic information and risk source information corresponding to the first project to be executed; then, it inputs the demand characteristic information into the project duration prediction model and outputs the predicted project duration corresponding to the first project to be executed; and inputs the demand characteristic information into the risk classification model and outputs the risk level corresponding to the first project to be executed; then, based on the predicted project duration, risk level and risk source information, it generates a risk assessment report; finally, it sends the risk assessment report to the terminal device 102.

[0048] It should be noted that the network architecture described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As network architectures evolve, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0049] See Figure 2This is a flowchart illustrating a project evaluation method provided in an embodiment of this application. Figure 2 As shown, the project evaluation method provided in this application embodiment can be implemented by the above-mentioned project evaluation device, specifically including the following steps 201 to 203.

[0050] Step 201: The project evaluation device acquires the demand characteristics information and risk source information corresponding to the first project to be executed.

[0051] In some embodiments, the aforementioned requirement characteristic information includes at least one of the following: total number of requirements, number of functional components developed, number of customized functional components, number of reused functional components, functional component reuse rate, number of technology stacks, average defect rate of functional components, dependency depth information, team capability matching degree, average resource load, number of similar projects, average duration of similar projects, and cost overrun rate of similar projects.

[0052] In some embodiments, the document format corresponding to the first project to be executed can be PDF, Word, PNG, JPG, etc. The specific format can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.

[0053] In some embodiments, the project evaluation device may perform semantic parsing on the project document of the first project to be executed using a first model to obtain the aforementioned requirement feature information.

[0054] For example, the first model mentioned above can be a large language model, an artificial intelligence (AI) model, or a neural network model, etc. The specific model can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.

[0055] In some embodiments, the aforementioned risk source information may include technology unfamiliarity, reuse rate, customization quantity, and resource usage information. The specific details can be determined based on actual usage needs, and this application embodiment does not impose any limitations.

[0056] It should be noted that the specific implementation of step 201 above can be found in the following embodiments, and will not be repeated here to avoid repetition.

[0057] In some embodiments, combined with Figure 2 ,like Figure 3 As shown, step 201 can be implemented through steps 201a to 201c as described below.

[0058] Step 201a: The project evaluation device performs entity recognition on the project document of the first project to be executed, and obtains the entity information corresponding to the first project to be executed.

[0059] In some embodiments, the aforementioned entity information includes: function point entity information, project data entity information, project constraint entity information, and technology stack requirement entity information.

[0060] For example, the project evaluation device can input project documents into the BERT+BiLSTM+CRF model to obtain entity information corresponding to the first project to be executed.

[0061] In some embodiments, the BERT+BiLSTM+CRF model described above can output a structured entity list, which may include: entity content, entity confidence level, entity location information, entity corresponding requirement number, etc. The specific details can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.

[0062] In some embodiments, the project evaluation device can verify the file size, number of pages, and content integrity of the first document corresponding to the first project to be executed. After the verification is passed, the device can extract the text content of the first document according to its type to obtain the project content, and then perform text processing on the project content to obtain the aforementioned project document.

[0063] For example, PDF documents can use Apache PDFBox to extract text content; image-based PDFs or image documents can use Tesseract OCR for text recognition; and Word documents can use Apache POI to extract the main text content.

[0064] For example, the above text processing can be used to clean up project content, such as removing headers, footers, tables of contents, comments, special symbols, and extra blank lines, and logically segmenting it according to chapters, clauses, serial numbers, and numbering to form standardized text blocks.

[0065] Step 201b: The project evaluation device determines at least one functional component that matches the entity information based on the semantic information of the entity information.

[0066] In some embodiments, the project evaluation apparatus may determine at least one functional component that matches the entity information from a storage of M functional components based on the semantic information of the entity information.

[0067] It should be noted that the specific implementation of step 202b above can be found in the following embodiments, and will not be repeated here to avoid repetition.

[0068] In this embodiment, the project evaluation device determines at least one functional component that matches the entity information in the project document of the first project to be executed. Thus, the project evaluation device can directly reuse the at least one functional component, thereby improving the efficiency of the project evaluation device in executing the project.

[0069] In some embodiments, combined with Figure 3 ,like Figure 4 As shown, step 201b can be implemented through steps 201b1 and 201b2 as described below.

[0070] Step 201b1: The project evaluation device calculates the cosine similarity between the semantic information of the entity information and the stored M functional components, where M is a positive integer.

[0071] In some embodiments, the project evaluation device can generate a first semantic vector corresponding to entity information, then read the functional description vectors of all functional components from the component capability map, and then calculate the cosine similarity between the first semantic vector corresponding to entity information and the functional description vectors of all functional components.

[0072] For example, the project evaluation device can generate a 768-dimensional semantic vector from the identified entity information using Sentence BERT.

[0073] It should be noted that the specific process by which the above-mentioned project evaluation device calculates the cosine similarity between the first semantic vector corresponding to the entity information and the functional description vectors of all functional components can be found in the description in the relevant technology. To avoid repetition, it will not be repeated here.

[0074] Step 201b2: The project evaluation device determines at least one functional component corresponding to a cosine similarity greater than or equal to a preset threshold as at least one functional component that matches the entity information.

[0075] In some embodiments, the aforementioned preset threshold can be preset by the project evaluation device; or it can be user-defined, and can be determined according to actual usage needs. This application embodiment does not impose any restrictions.

[0076] For example, the project evaluation device can filter out the top 3 functional components with the highest cosine similarity based on cosine similarity, then perform hard constraint filtering on the top 3 functional components with the highest similarity to obtain the filtered functional components, and then determine the functional components with cosine similarity greater than or equal to a preset threshold from the filtered functional components as at least one functional component that matches the entity information.

[0077] For example, the above hard constraint filtering may include at least one of the following: technology stack conflict, deployment environment incompatibility, or constraint failure.

[0078] For example, when the cosine similarity is greater than or equal to 0.9, the project evaluation device can directly reuse at least one functional component that matches the entity information; when the cosine similarity is in the range of 0.7 to 0.9, the project evaluation device can customize a new functional component based on at least one functional component that matches the entity information; when the cosine similarity is less than 0.7, the project evaluation device can redevelop a new functional component based on the entity information.

[0079] Step 201c: The project evaluation device generates the requirement characteristic information corresponding to the first project to be executed based on the entity information and at least one functional component, and obtains the risk source information.

[0080] In some embodiments, the project evaluation device can splice entity information and at least one functional component to obtain the requirement feature information corresponding to the first project to be executed.

[0081] For example, the project evaluation device can generate a structured JSON-formatted requirement-capability mapping report based on entity information and at least one functional component. Then, the project evaluation device can extract requirement feature information from the requirement-capability mapping report.

[0082] For example, the above requirement-capability mapping report may include at least one of the following: project number, total number of requirements, number of reusable components, number of customizations required, number of new developments required, reuse rate, total estimated standard man-days, requirement-component matching details, confidence level, and matching type.

[0083] For example, the vector dimension of the aforementioned requirement feature information can be 18 dimensions.

[0084] In this embodiment, the project evaluation device improves the accuracy of project evaluation by generating a demand-capacity mapping report and obtaining demand characteristic information based on the report.

[0085] Step 202: The project evaluation device inputs the demand characteristic information into the project duration prediction model and outputs the predicted project duration corresponding to the first project to be executed; and inputs the demand characteristic information into the risk classification model and outputs the risk level corresponding to the first project to be executed.

[0086] For example, the above-mentioned project duration prediction model can be an XGBoost regression model, and the above-mentioned risk classification model can be an XGBoost classification model.

[0087] For example, the risk level mentioned above can be low, medium or high.

[0088] In some embodiments, the predicted construction period may include the predicted construction period and its upper and lower fluctuation ranges.

[0089] In some embodiments, the risk classification model described above can also output the probability of risk level.

[0090] In some embodiments, the project assessment device can generate the aforementioned risk source information based on the predicted construction period, risk level, risk level probability, and demand characteristic information.

[0091] For example, the project assessment device can extract text content from predicted project duration, risk level, risk level probability, and demand characteristic information, and integrate the data to obtain the aforementioned risk source information.

[0092] Step 203: The project assessment device generates a risk assessment report based on the predicted construction period, risk level, and risk source information.

[0093] In some embodiments, the project assessment device can integrate the predicted project duration, risk level, and risk level probability into a textual analysis to obtain the aforementioned risk assessment report.

[0094] For example, the risk assessment report may include: project number, predicted duration range, risk level, list of key risk points, causes of risk, optimization directions, and recommended measures.

[0095] In some embodiments, the project assessment device can input the predicted construction period, risk level, and risk level probability into the first model, and perform risk assessment analysis through the first model to obtain the risk assessment report.

[0096] In the project evaluation method provided in this application embodiment, the requirement characteristic information and risk source information corresponding to the first project to be executed are obtained; the requirement characteristic information is input into the schedule prediction model, and the predicted schedule time corresponding to the first project to be executed is output; the requirement characteristic information is input into the risk classification model, and the risk level corresponding to the first project to be executed is output; based on the predicted schedule time, risk level, and risk source information, a risk assessment report is generated. In this solution, the risk assessment report of the first project to be executed is jointly determined by the predicted schedule time based on the requirement characteristic information of the first project to be executed, the risk level corresponding to the project to be executed, and the risk source information, avoiding the lack of data support due to the reliance on the personal experience of relevant personnel in project evaluation, thus improving the efficiency and accuracy of project evaluation.

[0097] In some embodiments, combined with Figure 2 ,like Figure 5 As shown, after step 203 above, the project evaluation method provided in this application embodiment further includes steps 301 to 303 as described below.

[0098] Step 301: The project evaluation device decomposes the project document of the first project to be executed into at least two first sub-tasks.

[0099] In some embodiments, the first subtask may include a task number, task name, estimated workload, required skills, preceding dependent tasks, module to which it belongs, and associated risk level.

[0100] In some embodiments, the project evaluation device can decompose the project document of the first project to be executed into at least two first sub-tasks using the first model described above.

[0101] In some embodiments, the project evaluation apparatus can break down new or customized requirements into fine-grained development tasks.

[0102] It should be noted that the specific implementation process of step 301 above can be found in the description in the relevant technology. To avoid repetition, it will not be repeated here.

[0103] Step 302: Based on the first condition and the task requirements of each sub-task, the project evaluation device determines the resource scheduling strategy corresponding to each sub-task.

[0104] In some embodiments, the first condition mentioned above includes at least one of the following: functional matching, maximum number of parallel tasks, resource load limit, and task dependency.

[0105] For example, the project evaluation device can load the internal team resource pool and the partner resource pool; then, it verifies the hard constraints (i.e., the first condition mentioned above) for each subtask; then, it uses "minimize duration + minimize cost + minimize risk" as the multi-objective optimization function; it iteratively solves the problem through a genetic algorithm to generate a resource allocation scheme that satisfies all constraints; finally, it outputs the Top 3 resource scheduling strategies.

[0106] For example, the aforementioned hard constraints for verification include skill matching, maximum number of parallel tasks, resource load limit, and task dependencies.

[0107] For example, the above resource scheduling strategy includes: task allocation, start and end time, responsible person, cost, duration, and risk level.

[0108] Step 303: The project evaluation device generates a project delivery feasibility evaluation strategy based on the risk assessment report and the resource scheduling strategy corresponding to each sub-task.

[0109] In some embodiments, the above-mentioned project delivery feasibility assessment strategy includes: requirements analysis results, component reuse strategy, risk assessment conclusions, resource optimization strategy, and implementation recommendations.

[0110] In some embodiments, the project evaluation device can integrate the risk assessment report and the resource scheduling strategy corresponding to each sub-task to obtain the aforementioned project delivery feasibility assessment strategy.

[0111] In this embodiment, the project evaluation device generates a project delivery feasibility evaluation strategy based on the risk assessment report and the resource scheduling strategy corresponding to each sub-task, which can ensure the efficiency of project execution while ensuring the timeliness of project delivery.

[0112] The project evaluation method of this application will be described below through specific embodiments.

[0113] like Figure 6 As shown, the implementation process of the project evaluation method provided in this application embodiment includes the following S1 to S11.

[0114] S1. Obtain the requirements document for the project evaluation device.

[0115] For example, the requirements document can be uploaded as a project tender document or requirements specification through the front end, supporting formats such as PDF, Word, PNG, and JPG. The project evaluation device verifies the file size, number of pages, and content completeness; once the verification is passed, it enters the preprocessing process.

[0116] S2. The project evaluation device performs document preprocessing.

[0117] For example, PDF documents use Apache PDFBox to extract text content; (2) image PDFs or image documents use Tesseract OCR for text recognition; (3) Word documents use Apache POI to extract the main text content; (4) clean the text, removing headers, footers, tables of contents, notes, special symbols, and extra blank lines; (5) logically segment the text according to chapters, clauses, serial numbers, and numbering to form standardized text blocks.

[0118] S3. The project evaluation device identifies entity information in the preprocessed requirements document.

[0119] For example, the project evaluation device can input the cleaned text into the BERT+BiLSTM+CRF model to perform domain-customized entity recognition. The recognition types include: (1) FUNC: function point entity; (2) DATA: data entity; (3) CONSTRAINT: non-functional constraint entity; (4) TECH: technology stack requirement entity. The model outputs a structured entity list, including entity content, confidence level, location information, and corresponding requirement number.

[0120] S4. The project evaluation device performs demand-capability semantic matching.

[0121] For example, (1) the project evaluation device can generate a 768-dimensional semantic vector from the identified functional point descriptions using Sentence BERT; (2) the project evaluation device reads the functional description vectors of all components from the capability map; (3) calculates the cosine similarity and filters the top 3 components with the highest similarity; (4) performs hard constraint filtering, including technology stack conflicts, deployment environment incompatibility, and constraint non-compliance; (5) determines the matching type according to the similarity threshold: ≥0.9 is directly reusable; 0.7~0.9 is customized; <0.7 is newly developed.

[0122] S5. The project evaluation device generates a requirements-capacity mapping report.

[0123] S6. The project evaluation device extracts 18 core feature information from the demand-capacity mapping report.

[0124] S7. The project evaluation device conducts a dual-model risk assessment.

[0125] For example, the project evaluation device can input 18-dimensional features into the project duration prediction model (XGBoost regression) and output the predicted project duration and its fluctuation range; and input the same feature into the cost risk classification model (XGBoost classification) and output the risk level 0 / 1 / 2 (low / medium / high) and the probability of each level; the project evaluation device automatically analyzes the sources of risk, including technical unfamiliarity, low reuse rate, large customization, and resource shortage.

[0126] S8. The project assessment device generates a risk quantification report.

[0127] For example, the aforementioned risk quantification report may include: project number, predicted duration range, risk level, list of key risk points, causes of risk, areas for optimization, and recommended measures.

[0128] S9. The project evaluation device breaks down the requirements for new development and customization into tasks.

[0129] S10, the project evaluation device performs multi-objective resource optimization scheduling for the dismantling task.

[0130] S11. The project evaluation device generates a project delivery feasibility assessment report based on multi-objective resource optimization scheduling and risk quantification reports.

[0131] It should be noted that the descriptions of each step S1 to S11 in this embodiment can be found in the descriptions in the above embodiments, and will not be repeated here.

[0132] It should be noted that the above-described method embodiments, or the various possible implementations of the method embodiments, can be executed individually, or, provided there is no conflict, they can be combined with each other. The specific implementation can be determined according to actual usage requirements, and this application embodiment does not impose any restrictions on this.

[0133] Figure 7 This is a schematic diagram of the structure of a project evaluation system provided in an embodiment of this application. Figure 7 As shown, the project evaluation system 800 may include: a front-end interaction layer 801, a service orchestration layer 802, a core algorithm layer 803, a data persistence layer 804, and a basic support layer 805.

[0134] The front-end interaction layer 801 is primarily responsible for receiving user-uploaded requirement documents, including PDF tender documents, Word requirement specifications, and scanned image documents. It also provides functions such as displaying requirement parsing results, risk assessment reports, comparing resource scheduling schemes, and exporting the final feasibility report. The front-end interaction layer only handles interface display and user operation functions; it does not participate in any core calculations or logical judgments. All calculation, parsing, matching, evaluation, and scheduling tasks are completed in the back-end service to ensure system stability, security, and scalability, and is applied to steps 201 and related solutions.

[0135] Service Orchestration Layer 802 is the central hub for process control in the entire system. It is responsible for uniformly scheduling the execution order of various modules, data routing between modules, task status monitoring, exception handling and retry mechanisms, result callbacks, and data archiving. The Service Orchestration Layer executes scheduling according to a fixed process: after the intelligent deconstruction and mapping module completes requirement analysis and component matching, it automatically pushes the results to the risk assessment model engine; after risk assessment, it automatically pushes the risk quantification report to the resource optimization scheduling engine; after resource optimization, it automatically generates a delivery plan and returns it to the front end for display. The entire process requires no manual intervention, achieving fully automated closed-loop execution, ensuring the completeness and coherence of the technical solution, without any missing links or discrete steps, and is applied to step 202 and related solutions.

[0136] The core algorithm layer 803 consists of four interconnected modules that work together and share data:

[0137] (1) Capability Map Management Module: It is responsible for building, storing and maintaining standardized data such as reusable software components, interface information, dependencies, historical defect rates, and standard man-day quotas within the enterprise, providing a unique, unified and reliable data foundation for the entire system, and serving as the basis for demand matching, risk assessment and resource scheduling.

[0138] (2) Intelligent deconstruction and mapping module: responsible for format conversion, text cleaning, OCR recognition, and NLP named entity recognition of unstructured requirement documents, and semantic matching of the identified functional requirements, data requirements, constraints, technical requirements and capability maps, and outputting a standardized requirement-capability mapping report. (3) Risk assessment model engine: responsible for reading the requirement-capability mapping report, constructing model input vectors through multi-dimensional feature engineering, and using pre-trained dual models (schedule prediction model and cost risk level classification model) for quantitative calculation, and outputting quantifiable schedule intervals, risk levels, key risk points and risk causes.

[0139] (4) Resource Optimization and Scheduling Engine: Responsible for reading the risk quantification report, breaking down development tasks into fine-grained parts, loading the internal team resource pool and the ecosystem partner resource pool, and generating the optimal resource allocation scheme through a multi-objective optimization algorithm under multiple constraints such as skill matching, load limit, task dependency, and cost constraints, and outputting multiple optional schemes for decision-making. Applied to step 202 and related schemes in step 202 above.

[0140] The data persistence layer 804 is responsible for the storage, reading, writing, and synchronization of all system data, including: a relational database, a graph database, a model repository, file storage, and a message queue. The relational database stores component metadata, requirement information, task information, team information, and project history data; the graph database stores component dependencies, functional similarity relationships, requirement matching relationships, and resource capability relationships; the model repository stores trained machine learning models, model versions, and inference configurations; file storage stores user-uploaded requirement documents, preprocessed intermediate files, and generated evaluation reports; and the message queue enables asynchronous communication between modules, ensuring high concurrency and high availability. This is applied to step 203 and related solutions.

[0141] The basic support layer 805 provides the underlying services necessary for system operation, including containerized deployment services, logging services, monitoring and alarm services, user permission services, OCR recognition services, and NLP inference acceleration services, ensuring stable, scalable, and maintainable system operation. This is applied to steps 201 and related solutions mentioned above.

[0142] It should be noted that for a detailed explanation of the steps performed by each module and their beneficial effects, please refer to the description in the above embodiments, which will not be repeated here.

[0143] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0144] This application embodiment can divide the project evaluation device into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0145] In some embodiments, this application also provides a project evaluation apparatus. This project evaluation apparatus may include one or more functional modules for implementing the project evaluation method described in the above embodiments.

[0146] For example, Figure 8 This is a schematic diagram of a project evaluation device provided in an embodiment of this application. Figure 8 As shown, the project evaluation device 900 includes: an acquisition module 901, a processing module 902, and a generation module 903.

[0147] The module 901 is used to acquire the demand characteristic information and risk source information corresponding to the first project to be executed. The processing module 902 is used to input the demand characteristic information into the project duration prediction model and output the predicted project duration for the first project to be executed; and to input the demand characteristic information into the risk classification model and output the risk level for the first project to be executed. The generation module 903 is used to generate a risk assessment report based on the predicted project duration, risk level, and risk source information.

[0148] The project assessment device provided in this application predicts the project duration through the demand characteristic information of the first project to be executed, and determines the risk assessment report of the first project to be executed by jointly using the risk level and risk source information of the project to be executed. This avoids the lack of data support due to the reliance on the personal experience of relevant personnel in project assessment, and improves the efficiency and accuracy of project assessment.

[0149] In some embodiments, the aforementioned requirement characteristic information includes at least one of the following: total number of requirements, number of functional components developed, number of customized functional components, number of reused functional components, functional component reuse rate, number of technology stacks, average defect rate of functional components, dependency depth information, team capability matching degree, average resource load, number of similar projects, average duration of similar projects, and cost overrun rate of similar projects.

[0150] In other embodiments, the processing module 902 is specifically used to perform entity recognition on the project document of the first project to be executed, to obtain entity information corresponding to the first project to be executed. The entity information includes: function point entity information, project data entity information, project constraint entity information, and technology stack requirement entity information; and based on the semantic information of the entity information, to determine at least one functional component that matches the entity information. The generation module 903 is specifically used to generate requirement feature information corresponding to the first project to be executed based on the entity information and at least one functional component.

[0151] In some other embodiments, the processing module 903 is specifically used to calculate the cosine similarity between the semantic information of the entity information and the stored M functional components, where M is a positive integer; and to determine at least one functional component corresponding to a cosine similarity greater than or equal to a preset threshold as at least one functional component that matches the entity information.

[0152] In some embodiments, the processing module 903 is further configured to, after generating a risk assessment report based on the predicted project duration, risk level, and risk source information, decompose the project document of the first project to be executed into at least two first sub-tasks; and, based on a first condition and the task requirements of each sub-task, determine the resource scheduling strategy corresponding to each sub-task. The first condition includes at least one of the following: functional matching, maximum number of parallel tasks, resource load limit, and task dependency. The generation module 903 is further configured to, based on the risk assessment report and the resource scheduling strategy corresponding to each sub-task, generate a project delivery feasibility assessment strategy. The project delivery feasibility assessment strategy includes: requirements analysis results, component reuse strategy, risk assessment conclusions, resource optimization strategy, and implementation suggestions.

[0153] It should be noted that the project evaluation device can implement all the processes implemented in the above method embodiments and achieve the same beneficial effects. To avoid repetition, it will not be described again here.

[0154] In the case where the functions of the integrated modules described above are implemented in hardware, this application provides a possible structural schematic diagram of the electronic device involved in the above embodiments. For example... Figure 9 As shown, the electronic device 90 includes: a processor 92, a communication interface 93, and a bus 94. Optionally, the electronic device 90 may also include a memory 91.

[0155] Processor 92 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0156] Communication interface 93 is used to connect with other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0157] The memory 91 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0158] As one possible implementation, the memory 91 can exist independently of the processor 92. The memory 91 can be connected to the processor 92 via a bus 94 and is used to store instructions or program code. When the processor 92 calls and executes the instructions or program code stored in the memory 91, it can implement the project evaluation method provided in the embodiments of this application.

[0159] In another possible implementation, memory 91 can also be integrated with processor 92.

[0160] Bus 94 can be an Extended Industry Standard Architecture (EISA) bus, etc. Bus 94 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0161] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.

[0162] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described project evaluation method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0163] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0164] This application also provides a readable storage medium storing a program or instructions that, when executed by a computer, implement the project evaluation method provided in the above embodiments. It is understood that all or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware; the readable storage medium can be any of the foregoing embodiments or memory; the readable storage medium can also be an external storage device of the service invocation device, such as a pluggable hard drive, Smart MediaCard (SMC), Secure Digital (SD) card, flash card, etc., equipped on the service invocation device. Further, the readable storage medium can include both internal storage units of the service invocation device and external storage devices. The readable storage medium is used to store the computer program and other programs and data required by the service invocation device. The readable storage medium can also be used to temporarily store data that has been output or will be output.

[0165] This application also provides a computer program product, which is stored in a storage medium and implements the project evaluation method provided in the above embodiments when executed by a computer.

[0166] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0167] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0168] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A project evaluation method, characterized in that, include: Obtain the requirement characteristics and risk sources information corresponding to the first project to be executed; Input the demand characteristic information into the project duration prediction model and output the predicted project duration corresponding to the first project to be executed. The demand characteristic information is then input into the risk classification model, which outputs the risk level corresponding to the first project to be executed. Based on the predicted construction period, risk level, and risk source information, a risk assessment report is generated.

2. The project evaluation method according to claim 1, characterized in that, The requirement characteristic information includes at least one of the following: total number of requirements, number of functional components developed, number of customized functional components, number of reused functional components, functional component reuse rate, number of technology stacks, average defect rate of functional components, dependency depth information, team capability matching degree, average resource load, number of similar projects, average duration of similar projects, and cost overrun rate of similar projects.

3. The project evaluation method according to claim 1, characterized in that, The step of obtaining the requirement feature information corresponding to the first project to be executed includes: Entity recognition is performed on the project document of the first project to be executed to obtain the entity information corresponding to the first project to be executed. The entity information includes: function point entity information, project data entity information, project constraint entity information, and technology stack requirement entity information. Based on the semantic information of the entity information, at least one functional component that matches the entity information is determined; Based on the entity information and the at least one functional component, the requirement feature information corresponding to the first project to be executed is generated.

4. The project evaluation method according to claim 3, characterized in that, The determination of at least one functional component matching the entity information based on the semantic information of the entity information includes: Calculate the cosine similarity between the semantic information of the entity information and the stored M functional components, where M is a positive integer; At least one functional component corresponding to a cosine similarity greater than or equal to a preset threshold is identified as at least one functional component that matches the entity information.

5. The project evaluation method according to claim 1, characterized in that, After generating a risk assessment report based on the predicted project duration, risk level, and risk source information, the method further includes: The project document of the first project to be executed is decomposed into tasks to obtain at least two first sub-tasks; Based on the first condition and the task requirements of each subtask, determine the resource scheduling strategy for each subtask. The first condition includes at least one of the following: function matching, maximum number of parallel tasks, resource load limit, and task dependency. Based on the risk assessment report and the resource scheduling strategy corresponding to each sub-task, a project delivery feasibility assessment strategy is generated. The project delivery feasibility assessment strategy includes: requirements analysis results, component reuse strategy, risk assessment conclusions, resource optimization strategy, and implementation suggestions.

6. A project evaluation device, characterized in that, include: Acquisition module, processing module, and generation module; The acquisition module is used to acquire the requirement characteristic information and risk source information corresponding to the first project to be executed; The processing module is used to input the demand feature information into the project duration prediction model and output the predicted project duration corresponding to the first project to be executed. The demand characteristic information is then input into the risk classification model, which outputs the risk level corresponding to the first project to be executed. The generation module is used to generate a risk assessment report based on the predicted construction period, risk level, and risk source information.

7. The project evaluation device according to claim 6, characterized in that, The aforementioned requirement characteristics information includes at least one of the following: total number of requirements, number of functional components developed, number of customized functional components, number of reused functional components, functional component reuse rate, number of technology stacks, average defect rate of functional components, dependency depth information, team capability matching degree, average resource load, number of similar projects, average duration of similar projects, and cost overrun rate of similar projects.

8. The project evaluation device according to claim 6, characterized in that, The processing module is specifically used to perform entity recognition on the project document of the first project to be executed, and obtain entity information corresponding to the first project to be executed. The entity information includes: function point entity information, project data entity information, project constraint entity information, and technology stack requirement entity information; and based on the semantic information of the entity information, determine at least one functional component that matches the entity information. The generation module is specifically used to generate requirement feature information corresponding to the first project to be executed based on the entity information and the at least one functional component.

9. The project evaluation device according to claim 8, characterized in that, The processing module is specifically used to calculate the cosine similarity between the semantic information of the entity information and the stored M functional components, where M is a positive integer; and to determine at least one functional component corresponding to a cosine similarity greater than or equal to a preset threshold as at least one functional component that matches the entity information.

10. The project evaluation device according to claim 6, characterized in that, The processing module is also used to decompose the project document of the first project to be executed into at least two first sub-tasks after generating a risk assessment report based on the predicted project duration, risk level and risk source information. Based on the first condition and the task requirements of each subtask, the resource scheduling strategy corresponding to each subtask is determined. The first condition includes at least one of the following: function matching, maximum number of parallel tasks, resource load limit, and task dependency relationship. The generation module is also used to generate a project delivery feasibility assessment strategy based on the risk assessment report and the resource scheduling strategy corresponding to each sub-task. The project delivery feasibility assessment strategy includes: requirements analysis results, component reuse strategy, risk assessment conclusions, resource optimization strategy, and implementation suggestions.

11. An electronic device, characterized in that, It includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the project evaluation method as described in any one of claims 1-5.

12. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a computer, implement the project evaluation method as described in any one of claims 1-5.

13. A computer program product, characterized in that, The computer program product is stored in a storage medium, and when executed by a computer, the computer program product implements the project evaluation method as described in any one of claims 1-5.

Images