Infrastructure subcontractor project input assessment method based on large model retrieval augmented generation

Abstract

The application discloses a capital construction subcontractor project input evaluation method based on large model retrieval enhanced generation, which constructs a personnel portrait library, a team portrait library and a capital construction subcontractor portrait library based on manager dimension data, construction personnel dimension data and capital construction subcontractor dimension data, evaluates the portrait data in each portrait library of the large model and the expert scoring rule to evaluate the manager input score and the construction personnel input score of the capital construction subcontractor, and obtains a project input comprehensive score based on the manager input score and the construction personnel input score. By fusing the expert scoring rule and the reasoning ability of the large model, the consistency of the evaluation standard is ensured, the evaluation result is more objective and accurate, and the evaluation efficiency is also significantly improved. Moreover, the evaluation large model is obtained by fusing the expert scoring rule into the initial large model based on the retrieval enhanced generation technology, the retrieval enhanced generation technology can provide detailed scoring reasons for each score, so that the evaluation result is more persuasive.

Description

Technical Field

[0001] This application relates to the field of infrastructure subcontractor project investment assessment technology, and in particular to an infrastructure subcontractor project investment assessment method based on large model retrieval enhancement generation. Background Technology

[0002] In power grid construction, the level of investment by infrastructure subcontractors is a key factor affecting project success, making the assessment of their investment a crucial step in ensuring project success.

[0003] In existing technologies, assessments are mainly conducted by expert teams through on-site inspections, document review, and interviews. This relies on the professional level and subjective judgment of the assessors, and different assessors may give different scores to the same infrastructure subcontractor, resulting in a lack of objectivity and consistency in the assessment results. Summary of the Invention

[0004] To achieve an objective and efficient assessment of infrastructure subcontractors' project investment, this application provides a method, electronic device, and computer-readable storage medium for assessing infrastructure subcontractors' project investment based on large model retrieval enhancement.

[0005] According to one aspect of the embodiments of this application, a method for evaluating the investment of infrastructure subcontractors based on large model retrieval enhancement is disclosed, including:

[0006] Obtain data on management personnel, construction workers, and infrastructure subcontractors from infrastructure subcontractors;

[0007] Based on the management personnel dimension data, the construction personnel dimension data, and the infrastructure subcontractor dimension data, a personnel profile library, a work team profile library, and an infrastructure subcontractor profile library are constructed. The personnel profile library includes one or more indicators for each individual, the work team profile library includes one or more indicators for the construction team, and the infrastructure subcontractor profile library includes one or more indicators for the infrastructure subcontractor as a whole.

[0008] The portrait data from the personnel portrait database, the work team portrait database, and the infrastructure subcontractor portrait database are input into the evaluation model. The evaluation model evaluates the management personnel input score and construction personnel input score of the infrastructure subcontractor based on the portrait data and expert scoring rules. Based on the management personnel input score and construction personnel input score, the comprehensive project input score of the infrastructure subcontractor is obtained.

[0009] The evaluation model is obtained by incorporating the expert scoring rules into the initial model through retrieval enhancement generation technology.

[0010] In one exemplary embodiment, the personnel profile database includes one or more indicators selected from personal resume, work experience, qualification certificates, and personnel stability.

[0011] In one exemplary embodiment, the team profile database includes one or more indicators from team attendance, overall deduction status, human resource strength, and daily safety training.

[0012] In one exemplary embodiment, the infrastructure subcontractor profile database includes one or more indicators among general contractor evaluation, work team profile, basic characteristics, operational risks, and construction capabilities.

[0013] In one exemplary embodiment, the step of evaluating the management personnel input score and construction personnel input score of the infrastructure subcontractor based on the profile data and expert scoring rules includes: evaluating the management personnel input score of the infrastructure subcontractor based on the profile data in the personnel profile database and the infrastructure subcontractor profile database and expert scoring rules; and evaluating the construction personnel input score of the infrastructure subcontractor based on the profile data in the personnel profile database and the work team profile database and expert scoring rules.

[0014] In one exemplary embodiment, evaluating the management personnel input score of the infrastructure subcontractor based on the profile data in the personnel profile database and the infrastructure subcontractor profile database, as well as expert scoring rules, includes: obtaining the scores corresponding to each indicator included in the personnel profile database and the infrastructure subcontractor profile database based on expert scoring rules; and obtaining the management personnel input score of the infrastructure subcontractor based on the scores corresponding to each indicator included in the personnel profile database and the infrastructure subcontractor profile database, and the weights corresponding to each indicator.

[0015] In one exemplary embodiment, evaluating the construction worker input score of the infrastructure subcontractor based on the portrait data in the personnel portrait library and the work team portrait library, as well as expert scoring rules, includes: obtaining the scores corresponding to each indicator contained in the personnel portrait library and the work team portrait library based on expert scoring rules; and obtaining the construction worker input score of the infrastructure subcontractor based on the scores corresponding to each indicator contained in the personnel portrait library and the work team portrait library and the weights corresponding to each indicator.

[0016] In one exemplary embodiment, before constructing the personnel profile library, work team profile library, and infrastructure subcontractor profile library based on the management personnel dimension data, the construction personnel dimension data, and the infrastructure subcontractor dimension data, the method further includes: preprocessing the management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data, including: converting data from different sources into a unified format; identifying missing values, outliers, and redundant data in the management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data, and filling the missing values ​​with the mode, mean, or median, or deleting the missing values, and replacing the outliers with upper or lower limits truncation or the median; and normalizing or standardizing the management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data.

[0017] In one exemplary embodiment, after obtaining the comprehensive project investment score of the infrastructure subcontractor based on the investment scores of the management personnel and the investment scores of the construction personnel, the method further includes: generating a project investment evaluation report of the infrastructure subcontractor, the evaluation report including one or more of the following data: comprehensive project investment score, comprehensive rating level, scores and reasons for the scores corresponding to the indicators contained in each profile library, and improvement suggestions for low-scoring indicators.

[0018] In one exemplary embodiment, after obtaining the comprehensive project investment score of the infrastructure subcontractor based on the management personnel investment score and the construction personnel investment score, the method further includes: generating a scoring radar chart of the comprehensive project investment score, wherein the scoring radar chart includes the management personnel investment score, the construction personnel investment score, and the scores corresponding to the indicators contained in each profile database.

[0019] In one exemplary embodiment, after obtaining the comprehensive project investment score of the infrastructure subcontractor based on the investment scores of the management personnel and the investment scores of the construction personnel, the method further includes: determining the performance risk of the infrastructure subcontractor based on the comprehensive project investment score of the infrastructure subcontractor; determining the performance risk level of the infrastructure subcontractor; and outputting the performance risk level information and early warning information.

[0020] In one exemplary embodiment, after obtaining the comprehensive project input score of the infrastructure subcontractor based on the input scores of the management personnel and the input scores of the construction personnel, the method further includes: acquiring on-site data and management data of the infrastructure subcontractor during the construction process, wherein the management data includes one or more indicators among material arrival records, quality inspection reports, plan execution status, and changes in resource input; determining the actual project input of the infrastructure subcontractor based on the on-site data and the management data; calculating the difference between the actual project input and the planned project input; and assessing the risk of insufficient input by the infrastructure subcontractor based on the difference.

[0021] According to one aspect of the embodiments of this application, an electronic device is disclosed, the electronic device including one or more processors and a memory, the memory being used to store one or more programs, which, when executed by the one or more processors, cause the electronic device to perform the aforementioned method.

[0022] According to one aspect of the embodiments of this application, a computer-readable storage medium is disclosed, the computer-readable storage medium storing computer-readable instructions, which, when executed by a computer's processor, cause the computer to perform the aforementioned method.

[0023] The technical solutions provided by the embodiments of this application have at least the following beneficial effects:

[0024] The technical solution provided in this application constructs personnel profile databases, work team profile databases, and infrastructure subcontractor profile databases based on management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data. An evaluation model uses the profile data from these databases, along with expert scoring rules, to assess the management personnel input scores and construction personnel input scores of infrastructure subcontractors. Based on these scores, a comprehensive project input score for the infrastructure subcontractor is obtained. By integrating expert scoring rules with the reasoning capabilities of the large-scale model, the consistency of evaluation standards is ensured, resulting in more objective and accurate evaluation results. The automated evaluation process also significantly improves evaluation efficiency, saving time and labor costs. Furthermore, the evaluation model is obtained by incorporating expert scoring rules into an initial large-scale model through retrieval-enhanced generation technology. This technology provides detailed justifications for each score, making the final evaluation results more convincing.

[0025] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0027] Figure 1 A flowchart illustrating an embodiment of this application shows a method for evaluating the investment of infrastructure subcontractors based on large model retrieval enhancement.

[0028] Figure 2 A detailed flowchart of the data preprocessing steps of an embodiment of this application is shown.

[0029] Figure 3A flowchart detailing some steps of the project input evaluation process according to an embodiment of this application is shown.

[0030] Figure 4 It shows Figure 3 The detailed flowchart of step S310 is shown.

[0031] Figure 5 It shows Figure 3 The detailed flowchart of step S320 is shown.

[0032] Figure 6 A detailed flowchart of the potential risk warning steps in one embodiment of this application is shown.

[0033] Figure 7 This application illustrates an overall flowchart of the infrastructure subcontractor project input evaluation according to an embodiment of the present application.

[0034] Figure 8 A flowchart illustrating the risk assessment of insufficient investment by infrastructure subcontractors according to an embodiment of this application is shown.

[0035] Figure 9 A block diagram of an electronic device according to an embodiment of this application is shown.

[0036] Figure 10 A computer system architecture block diagram is shown for implementing some embodiments of this application.

[0037] 900. Electronic device; 901. Processor; 902. Memory; 1000. Computer system; 1001. CPU; 1002. ROM; 1003. RAM; 1004. Bus; 1005. I / O interface; 1006. Input section; 1007. Output section; 1008. Storage section; 1009. Communication section; 1010. Driver; 1011. Removable media. Detailed Implementation

[0038] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this application will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0039] The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0040] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0041] First, let me explain some of the terms used in this application:

[0042] Large models, also known as large AI models, refer to a class of AI models with a large number of parameters constructed from artificial neural networks.

[0043] Retrieval-augmented Generation (RAG) is a model that combines retrieval and generation techniques, comprising three main processes: retrieval, augmentation, and generation. It generates answers or content by referencing information from external knowledge bases, offering strong interpretability and customizability, and is suitable for various natural language processing tasks such as question-answering systems, document generation, and intelligent assistants.

[0044] Team profiling refers to a model or tool that uses data analysis and feature extraction to systematically describe and evaluate the comprehensive capabilities, behavioral patterns, and performance of construction teams.

[0045] The intelligent engineering foundation refers to a project site operation and management data platform that extracts and aggregates data from multiple heterogeneous systems such as construction sites, personnel, qualifications, attendance, and safety inspections, providing real-time and dynamic engineering data support for evaluation.

[0046] Infrastructure Subcontractor Profiling Base: This is a data platform for systematically modeling infrastructure subcontractors, covering registration information, financial data, credit rating, historical illegal records, etc., forming a structured information infrastructure for a comprehensive profile of infrastructure subcontractors.

[0047] In the past, applicants have used the following methods to evaluate the project inputs of infrastructure subcontractors.

[0048] I. Expert Review Method: This method involves an expert team conducting assessments through on-site inspections, document review, and interviews. The primary focus is on the infrastructure subcontractor's corporate qualifications, past project experience, and the capabilities of key personnel. The assessment period is 7-15 working days, with results presented in a written report. This method heavily relies on the professional expertise and subjective judgment of the assessors; different assessors can yield scores for the same infrastructure subcontractor that differ by 15-30%, leading to a lack of objectivity and consistency in the assessment results. Furthermore, it requires significant manpower, making it difficult to support large-scale, high-frequency infrastructure subcontractor assessment needs.

[0049] II. Standardized Scoring Card Assessment Method: This method uses a fixed scoring form designed based on the ISO 9001 quality management system or Capability Maturity Model Integration (CMMI) for assessment. Assessment indicators include company qualifications, personnel quality, equipment, financial strength, and past performance. Scoring is combined with document review and on-site verification, and the assessment results are presented in radar charts and bar graphs. This shortens the assessment cycle to 3-5 working days. While this method improves consistency, it is too rigid and difficult to adapt to the differentiated needs of different project types and scales.

[0050] III. Data-Driven Statistical Analysis and Evaluation Method: This method establishes regression or decision tree models based on historical project data. It analyzes indicators such as the subcontractor's performance rate, number of quality issues, and accident rate in past projects. Weights are calculated using a sliding time window, and Principal Component Analysis (PCA) is used to reduce the dimensionality of multidimensional indicators, generating predictive scores to estimate the subcontractor's performance probability in future projects. The evaluation process is highly automated, typically requiring only 1-2 working days. However, this method has high requirements for sample size and quality, and its accuracy drops significantly when data is sparse.

[0051] IV. Analytic Hierarchy Process (AHP): Constructs a three-layer evaluation structure: target layer, criterion layer, and indicator layer. A judgment matrix is ​​constructed through expert scoring, the weights of each indicator are calculated, consistency checks are used to ensure the reliability of the evaluation, uncertainty is handled by combining fuzzy comprehensive evaluation method, and qualitative and quantitative indicators are normalized through mathematical modeling to finally form a comprehensive score and graded results.

[0052] V. Knowledge Graph-Based Evaluation Method: Construct a knowledge graph of infrastructure subcontractors, including enterprise entities, personnel entities, project entities, and equipment entities and their relationships. Analyze the resource network structure and connection strength of infrastructure subcontractors through graph algorithms, identify key nodes and potential risk points, and capture the dynamic changes in the resource input of infrastructure subcontractors by combining time series analysis. Support multi-dimensional query and visualization display.

[0053] This application proposes a method for evaluating the project input of infrastructure subcontractors based on large-scale model retrieval enhancement generation. It constructs personnel profile databases, work team profile databases, and infrastructure subcontractor profile databases based on management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data. An evaluation large-scale model then assesses the management personnel input scores and construction personnel input scores of infrastructure subcontractors based on these databases and expert scoring rules. Finally, a comprehensive project input score for the infrastructure subcontractor is obtained based on these scores. By integrating expert scoring rules with the reasoning capabilities of the large-scale model, the consistency of evaluation standards is ensured, resulting in more objective and accurate evaluation results. The automated evaluation process also significantly improves evaluation efficiency, saving time and labor costs. Furthermore, the evaluation large-scale model is obtained by incorporating expert scoring rules into the initial large-scale model through retrieval enhancement generation technology. This technology provides detailed scoring reasons for each score, making the final evaluation results more convincing.

[0054] The following describes in detail the infrastructure subcontractor project investment evaluation method based on large model retrieval enhancement provided in this application, with reference to specific implementation methods and accompanying drawings.

[0055] Figure 1 A flowchart illustrating an embodiment of this application shows a method for evaluating the investment of infrastructure subcontractors based on large model retrieval enhancement.

[0056] See Figure 1 As shown, the infrastructure subcontractor project investment evaluation method includes at least the following steps: data acquisition, data preprocessing, profile database construction, and project investment evaluation, corresponding to steps S110, S120, S130, and S140, respectively, which are detailed below:

[0057] In step S110, data on the management personnel, construction personnel, and infrastructure subcontractors of the infrastructure subcontractors are obtained. Then, step S120 is executed.

[0058] Management personnel data can include one or more of the following: personal resume, work experience, qualification certificates, and employee stability. Personal resume can include one or more of the following: education level, age group, length of service, and length of service in the same job type. Work experience can include one or more of the following: number of jobs completed, number of work days completed. Qualification certificates can include one or more of the following: management qualifications, construction qualifications, etc. Employee stability refers to the continuity and loyalty of employees within the company, involving their work attitude, engagement, and sense of identification with the company culture. It can include one or more of the following: continuity of work experience, fit between career development goals and job requirements, alignment of personal character and values, and support from family and living environment.

[0059] Construction personnel data can include one or more of the following: personal resume, work experience, qualification certificates, and personnel stability. Personal resume can include one or more of the following: education level, age group, length of service, and length of service in the same job type. Work experience can include one or more of the following: number of jobs completed and number of working days completed. Qualification certificates can include one or more of the following: management qualifications and construction qualifications.

[0060] Data on infrastructure subcontractors can include one or more of the following: basic characteristics, operational risks, and work team profiles. Basic characteristics can include one or more of the following: company qualification level, project performance, and financial status. Operational risks can include one or more of the following: internal risks, historical risks, and legal cases. Internal risks are current risks caused by internal or external factors that directly affect the company's development and interests, such as strategic risks, market risks, and product risks. Historical risks are past risks caused by internal or external factors that directly affect the company's development and interests. Legal cases refer to disputes or conflicts involving two or more parties within the legal framework, which can be civil, criminal, or administrative cases. Work team profile indicators include one or more of the following: average work team score and work team acceptance pass rate.

[0061] In some embodiments, management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data are collected through multiple data sources. These multiple data sources may include a smart engineering platform and an infrastructure subcontractor profiling platform. The smart engineering platform can collect data such as personnel information, daily attendance, company qualifications, training records, safety inspection reports, work plans, and violations. The infrastructure subcontractor profiling platform can collect data such as company registration information, company patent qualifications, financial revenue data, company violation data, and company credit rating. These multiple data sources may also include other data sources, such as social public systems.

[0062] In step S120, the data on management personnel, construction personnel, and infrastructure subcontractors are preprocessed. Then, step S130 is executed.

[0063] In some embodiments, the preprocessing of management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data includes the following steps S210, S220, and S230, which are detailed below:

[0064] In step S210, data from different sources are converted into a unified format.

[0065] In step S220, missing values, outliers, and redundant data in the management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data are identified and processed.

[0066] Different processing strategies are employed for different data types. Specifically, for numerical fields with a small proportion of missing data (such as training hours or work experience), the mean or median is used for imputation. For categorical variables (such as enterprise qualification level), the mode is used for imputation or the data is set to the "missing" category. If key fields (such as enterprise registered capital or individual resume) are severely missing, the record is deleted. IQR box plots are used to identify numerical outliers, and upper and lower limits are used for truncation or the median is used to replace outliers. Logical errors (such as unreasonable time sequences or negative scores) are corrected or deleted to ensure data consistency.

[0067] For duplicate records from multiple data sources, deduplication is performed by aligning IDs. For highly related redundant fields (such as annual revenue and monthly revenue), the main indicators are retained and the redundant fields are removed. Duplicate personnel records are aggregated to avoid duplicate scoring.

[0068] In step S230, the data of management personnel, construction personnel, and infrastructure subcontractors are normalized or standardized.

[0069] This includes normalizing data that has frequency, a fixed range, or is count-based, such as daily attendance (e.g., attendance rate), training records (e.g., training hours), safety inspections (e.g., pass rate), work plan completion rate, number of violations, enterprise credit rating, and number of enterprise patents. Standardizing data that fluctuates significantly and has no fixed upper limit, such as enterprise financial revenue data, enterprise qualification level, enterprise registered capital, and number of enterprise violations.

[0070] By preprocessing data from management personnel, construction workers, and infrastructure subcontractors, errors, incompleteness, or inaccuracies in the data can be identified and corrected, which helps improve the efficiency of subsequent processing steps and the accuracy and reliability of the assessment results.

[0071] In step S130, personnel profile databases, work team profile databases, and infrastructure subcontractor profile databases are constructed based on management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data. Then, step S140 is executed.

[0072] Based on data from management personnel, construction workers, and infrastructure subcontractors, we construct personnel profile databases, work team profile databases, and infrastructure subcontractor profile databases. Specifically, the personnel profile database is built based on data related to individual personnel from these three dimensions, such as personal resumes, work experience, qualification certificates, and personnel stability. The work team profile database is built based on data related to both individual construction workers and work teams from these dimensions, such as work team attendance, overall deductions, human resource strength, and daily safety training. Finally, the work team profile database is built based on data related to both work teams and the overall infrastructure subcontractor from these dimensions, such as general contractor evaluations, work team profiles, basic characteristics, operational risks, and construction capabilities.

[0073] The personnel profile database is used to assess the professional competence and work performance of individual personnel, including one or more indicators for each individual. Specifically, the personnel profile database may include one or more indicators such as personal resume, work experience, qualification certificates, and personnel stability.

[0074] The team profile database is used to assess the collaboration and execution capabilities of construction teams, including one or more indicators of the team. Specifically, the team profile database may include one or more indicators from team attendance, overall deductions, human resource strength, and daily safety training.

[0075] The infrastructure subcontractor profile database is used for comprehensive evaluation of subcontractors from aspects such as overall management, contract performance capabilities, and project quality, including one or more indicators of the subcontractor as a whole. Specifically, the infrastructure subcontractor profile database may include one or more indicators such as general contractor evaluation, work team profile, basic characteristics, operational risks, and construction capabilities.

[0076] In some embodiments, the personnel profile database includes individual resumes, work experience, qualification certificates, and personnel stability; the work team profile database includes work team attendance, overall deductions, human resource strength, and daily safety training; and the infrastructure subcontractor profile database includes general contractor evaluations, work team profiles, basic characteristics, operational risks, and construction capabilities. The specific meanings of each indicator are described above and will not be repeated here.

[0077] In step S140, the portrait data from the personnel portrait library, work team portrait library, and infrastructure subcontractor portrait library are input into the evaluation model. The evaluation model evaluates the management personnel input score and construction personnel input score of the infrastructure subcontractor based on the portrait data and expert scoring rules, and obtains the comprehensive project input score of the infrastructure subcontractor based on the management personnel input score and construction personnel input score.

[0078] The process of inputting portrait data from the personnel portrait database, work team portrait database, and infrastructure subcontractor portrait database into the large-scale evaluation model can involve inputting a portion of the portrait data from these databases, or inputting all of the portrait data from these databases.

[0079] In some embodiments, such as Figure 3 As shown, the evaluation of the input scores of management personnel and construction personnel of infrastructure subcontractors based on profile data and expert scoring rules includes the following steps S310 and S320, which are detailed below:

[0080] In step S310, the input score of the management personnel of the infrastructure subcontractor is evaluated based on the portrait data in the personnel portrait database and the infrastructure subcontractor portrait database, as well as the expert scoring rules.

[0081] In step S320, the construction personnel input score of the infrastructure subcontractor is evaluated based on the portrait data in the personnel portrait database and the work team portrait database, as well as the expert scoring rules.

[0082] Understandably, assessing the input score of management personnel in infrastructure subcontractors based on profile data from personnel and subcontractor profile databases, along with expert scoring rules, can be done by using some or all indicators from the personnel and subcontractor profile databases. Similarly, assessing the input score of construction workers in infrastructure subcontractors based on profile data from personnel and work team profile databases, along with expert scoring rules, can also be done by using some or all indicators from the personnel and work team profile databases.

[0083] For example, the input score of the management personnel of the infrastructure subcontractor is evaluated based on the personal resumes, work experience, qualification certificates, and personnel stability of the management personnel in the personnel profile database, and the basic characteristics, operational risks, and work team profiles in the infrastructure subcontractor profile database, as well as expert scoring rules. Similarly, the input score of the construction personnel of the infrastructure subcontractor is evaluated based on the personal resumes, work experience, qualification certificates, and personnel stability of the construction personnel in the personnel profile database, and the work team profiles in the work team database, including work team attendance, overall deductions, human resource strength, daily safety training, and expert scoring rules.

[0084] In some embodiments, such as Figure 4 As shown, the evaluation of the management personnel input scores of infrastructure subcontractors is based on the profile data in the personnel profile database and the infrastructure subcontractor profile database, as well as expert scoring rules. This includes the following steps S410 and S420, detailed below:

[0085] In step S410, scores corresponding to each indicator in the personnel profile database and the infrastructure subcontractor profile database are obtained based on expert scoring rules.

[0086] In step S420, the input score of the management personnel of the infrastructure subcontractor is obtained based on the scores and weights of each indicator contained in the personnel profile database and the infrastructure subcontractor profile database.

[0087] For example, a hierarchical model is constructed by using managerial input evaluation as the target layer and managers' personal resumes, work experience, qualifications, and staff stability as the criteria layer. The scores and weights of each indicator are calculated using the analytic hierarchy process (AHP) to form a comprehensive score for managerial input evaluation.

[0088] For example, a hierarchical model is constructed by using the management personnel input assessment as the target layer, and the management personnel's personal resumes, work experience, qualification certificates, and personnel stability, as well as the general contractor's evaluation of infrastructure subcontractors, team profiles, basic characteristics, operational risks, and construction capabilities as the criteria layer. The scores and weights of each indicator are calculated using the analytic hierarchy process (AHP) to form a comprehensive score for the management personnel input assessment.

[0089] The weights for each indicator can be different. By assigning weights to each indicator, and based on the scores and weights of each indicator, the input scores of infrastructure subcontractors' management personnel can be obtained more accurately and reliably.

[0090] In some embodiments, such as Figure 5 As shown, the evaluation of the construction personnel input score of infrastructure subcontractors is based on the portrait data in the personnel portrait database and the work team portrait database, as well as the expert scoring rules. This includes the following steps S510 and S520, which are detailed below:

[0091] In step S510, scores corresponding to each indicator contained in the personnel profile database and the work group profile database are obtained based on expert scoring rules.

[0092] In step S520, based on the scores and weights of each indicator contained in the personnel profile database and the work team profile database, the construction personnel input score of the infrastructure subcontractor is obtained.

[0093] For example, a hierarchical model is constructed by using the assessment of construction personnel input as the target layer and the personal resumes, work experience, qualification certificates, personnel input, and cross-regional mobility of construction personnel as the criteria layer. The scores and weights of each are calculated using the analytic hierarchy process (AHP) to form a comprehensive score for the assessment of construction personnel input.

[0094] For example, a hierarchical model is constructed by using the assessment of construction personnel input as the target layer, and the individual resumes, work experience, qualification certificates, personnel input, cross-regional mobility, team attendance, overall deductions, human resource strength, and daily safety training of construction personnel as the criteria layer. The scores and weights of each are calculated using the analytic hierarchy process (AHP) to form a comprehensive score for the assessment of construction personnel input.

[0095] The weights for each indicator can be different. By assigning weights to each indicator, and based on the scores and weights of each indicator, the scores for construction subcontractors' work input can be obtained more accurately and reliably.

[0096] In the above embodiments, the management personnel input score and construction personnel input score of the infrastructure subcontractor are obtained based on the portrait data in the personnel portrait database, work team portrait database, and infrastructure subcontractor portrait database. This divides the input assessment into two dimensions: management personnel input and construction personnel input. Understandably, in other embodiments, the input assessment may also be divided into more dimensions.

[0097] The overall project contribution score for infrastructure subcontractors can be obtained by combining the input scores of management personnel and construction personnel. This can be achieved by directly summing the scores, or by assigning different weights to the input scores of management personnel and construction personnel, and then weighting the scores accordingly. Other methods can also be used to calculate the overall project contribution score for infrastructure subcontractors.

[0098] In step S140, the evaluation model used is obtained by combining retrieval enhancement generation technology with the large model, based on integrating expert scoring rules into the initial large model through retrieval enhancement generation technology.

[0099] In some embodiments, after obtaining the comprehensive project input score of the infrastructure subcontractor based on the input scores of management personnel and construction personnel, the method further includes: generating a project input assessment report for the infrastructure subcontractor.

[0100] The evaluation report may include one or more of the following data: the overall score of project input, the overall rating level, the scores and reasons for the scores of the indicators contained in each profile library, improvement suggestions for low-scoring indicators, and key explanations of key indicators.

[0101] The evaluation report provides detailed information about the assessment, offering comprehensive data that enhances the persuasiveness of the results and facilitates an accurate understanding of the infrastructure subcontractors' project commitments. Providing detailed justifications for each indicator's score ensures transparency and explainability throughout the evaluation process. Furthermore, it highlights key indicators, emphasizing the main factors influencing the scoring.

[0102] In some embodiments, after obtaining the comprehensive project input score of the infrastructure subcontractor based on the input scores of management personnel and construction personnel, the method further includes: generating a scoring radar chart of the comprehensive project input score, wherein the scoring radar chart includes the input scores of management personnel, the input scores of construction personnel, and the scores corresponding to the indicators contained in each profile database.

[0103] The rating radar chart provides an intuitive display of the strengths and weaknesses of infrastructure subcontractors.

[0104] In some embodiments, after obtaining a comprehensive project input score for the infrastructure subcontractor based on the input scores of management personnel and construction personnel, a step of issuing an early warning about potential risks to the infrastructure subcontractor is also performed. For example... Figure 6 As shown, the process includes the following steps S610 and S620, which are described in detail below:

[0105] In step S610, the performance risks of the infrastructure subcontractors are determined based on their comprehensive project input scores.

[0106] In step S620, the performance risk level of the infrastructure subcontractor is determined, and the performance risk level information and early warning information are output.

[0107] By providing performance risk level information and early warning information, companies can accurately grasp the project investment status of infrastructure subcontractors.

[0108] This application obtains data on management personnel, construction workers, and subcontractors of infrastructure subcontractors from a data source, preprocesses the obtained data, and constructs personnel profile databases, work team profile databases, and infrastructure subcontractor profile databases based on the preprocessed data. The profile data from these databases is then input into a large-scale evaluation model. The model obtains a comprehensive score for the project input of each infrastructure subcontractor and outputs the comprehensive score, explanations of the scoring, improvement suggestions, and risk warnings. The overall process is as follows: Figure 7 As shown.

[0109] In some embodiments, after assessing the investment in infrastructure subcontractors, the subcontractors are monitored in real time. Based on the real-time collected data, personnel profiles, work team profiles, and subcontractor profiles are dynamically updated. The difference between planned and actual project investment is compared to assess the risk of insufficient investment. See also Figure 8 As shown, the process includes the following steps: S810, S820, and S830, which are described in detail below:

[0110] In step S810, the site data and management data of the infrastructure subcontractor during the construction process are obtained.

[0111] The on-site data may include one or more of the following: worker attendance data, work data, on-site management status, and safety protection measure implementation status. Worker attendance data and work data can be collected in real time through devices such as smart safety helmets and smart bracelets, while on-site management status and safety protection measure implementation status can be obtained through video surveillance systems.

[0112] Management data includes one or more indicators from the following: material arrival records, quality inspection reports, plan execution status, and changes in resource input.

[0113] In step S820, the actual project investment of the infrastructure subcontractor is determined based on on-site data and management data.

[0114] In step S830, the difference between the actual investment and the planned investment of the project is calculated, and the risk of insufficient investment by the infrastructure subcontractor is assessed based on the difference.

[0115] Among them, the planned input of the project refers to the planned data such as construction organization, manpower input, and material arrangement formulated by the management team before the implementation of the project, which is usually stored in the project management system (such as ERP, PMIS).

[0116] By monitoring infrastructure subcontractors in real time, tracking their investment, and providing timely attention and intervention, we can ensure project success.

[0117] In some embodiments, a tiered early warning mechanism can also be set up. By setting early warning thresholds, different levels of early warning information can be issued based on the risk assessment results of insufficient investment. The different levels of early warning information can include three levels: alert level, attention level, and intervention level. For different levels of early warning, corresponding intervention measures can be recommended. Intervention measures can include increasing the frequency of supervision, requiring increased resource investment, suspending some work, etc.

[0118] In summary, this application provides a project investment evaluation scheme for infrastructure subcontractors based on large-model retrieval enhancement. This scheme ensures consistency in evaluation standards by integrating expert scoring rules with large-model inference capabilities. The automated evaluation process significantly improves evaluation efficiency, reduces manual intervention, and saves time and labor costs. It employs multi-dimensional cross-evaluation, constructing two main evaluation dimensions: management personnel and construction personnel. This improves the accuracy and reliability of the evaluation results. Furthermore, the multi-dimensional data covers indicators from project preparation, implementation, supervision and control to completion, achieving a full lifecycle evaluation. Based on retrieval enhancement generation technology, detailed scoring reasons are provided for each score, and the visualization of these reasons enhances the persuasiveness of the evaluation results. Data-driven improvement suggestions are provided to help infrastructure subcontractors accurately improve. In addition, real-time monitoring of infrastructure subcontractors dynamically captures their resource investment during the project implementation phase, allowing for timely attention and intervention to ensure project success.

[0119] See next. Figure 9 As shown, this embodiment provides an electronic device 900, which includes one or more processors 901 and a memory 902. The memory 902 is used to store one or more programs. When one or more programs are executed by one or more processors 901, the electronic device 900 implements the infrastructure subcontractor project investment evaluation method of this application.

[0120] Figure 10 The diagram shows a computer system architecture block diagram for implementing some embodiments of this application. It should be noted that... Figure 10 The computer system shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0121] like Figure 10 As shown, the computer system 1000 includes a CPU (Central Processing Unit) 1001, which can perform various appropriate actions and processes according to programs stored in ROM (Read-Only Memory) 1002 or loaded from storage portion 1008 into RAM (Random Access Memory) 1003, such as executing the infrastructure subcontractor project investment evaluation method in the above embodiment. The RAM 1003 also stores various programs and data required for system operation. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An I / O (Input / Output) interface 1005 is also connected to the bus 1004.

[0122] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including CRT (Cathode Ray Tube), LCD (Liquid Crystal Display), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. Removable media 1010, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1010 as needed so that computer programs read from them can be installed into storage section 1008 as needed.

[0123] Specifically, according to embodiments of this application, the processes described in the above-referenced flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing all or some of the steps shown in the flowchart of the infrastructure subcontractor project input evaluation method. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable media 1011. When the computer program is executed by the central processing unit (CPU) 1001, it performs various functions defined in the system of this application.

[0124] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0126] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0127] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to implement the methods described in the above embodiments.

[0128] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0129] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0130] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the appended claims.

Claims

1. A method for evaluating the investment of infrastructure subcontractors based on large model retrieval enhancement, characterized in that, The method includes: Obtain data on management personnel, construction workers, and infrastructure subcontractors from infrastructure subcontractors; Based on the management personnel dimension data, the construction personnel dimension data, and the infrastructure subcontractor dimension data, a personnel profile library, a work team profile library, and an infrastructure subcontractor profile library are constructed. The personnel profile library includes one or more indicators for each individual, the work team profile library includes one or more indicators for the construction team, and the infrastructure subcontractor profile library includes one or more indicators for the infrastructure subcontractor as a whole. The portrait data from the personnel portrait database, the work team portrait database, and the infrastructure subcontractor portrait database are input into the evaluation model. The evaluation model evaluates the management personnel input score and construction personnel input score of the infrastructure subcontractor based on the portrait data and expert scoring rules. Based on the management personnel input score and construction personnel input score, the comprehensive project input score of the infrastructure subcontractor is obtained. The evaluation model is obtained by incorporating the expert scoring rules into the initial model through retrieval enhancement generation technology.

2. The method according to claim 1, characterized in that, The personnel profile database includes one or more indicators such as personal resume, work experience, qualification certificates, and personnel stability. or The team profile database includes one or more indicators from team attendance, overall deductions, human resource strength, and daily safety training. or The infrastructure subcontractor profile database includes one or more indicators such as general contractor evaluation, work team profile, basic characteristics, operational risks, and construction capabilities.

3. The method according to claim 1 or 2, characterized in that, The evaluation of the management personnel input score and construction personnel input score of the infrastructure subcontractor based on the profile data and expert scoring rules includes: The personnel profile database and the infrastructure subcontractor profile database are used to evaluate the input score of the management personnel of the infrastructure subcontractor based on the profile data and expert scoring rules. The construction subcontractor's personnel input score is evaluated based on the portrait data in the personnel portrait database and the work team portrait database, as well as the expert scoring rules.

4. The method according to claim 3, characterized in that, The evaluation of the management personnel input scores of the infrastructure subcontractors is based on the profile data in the personnel profile database and the infrastructure subcontractor profile database, as well as expert scoring rules, including: The scores for each indicator in the personnel profile database and the infrastructure subcontractor profile database are obtained based on the expert scoring rules. Based on the scores and weights of each indicator contained in the personnel profile database and the infrastructure subcontractor profile database, the management personnel input score of the infrastructure subcontractor is obtained. or The evaluation of the construction subcontractor's personnel input score is based on the personnel profile database and the work team profile database, as well as expert scoring rules, including: The scores corresponding to each indicator contained in the personnel profile database and the work group profile database are obtained based on the expert scoring rules. Based on the scores and weights of each indicator contained in the personnel profile database and the work team profile database, the construction personnel input score of the infrastructure subcontractor is obtained.

5. The method according to claim 1, characterized in that, Before constructing the personnel profile database, work team profile database, and infrastructure subcontractor profile database based on the management personnel dimension data, the construction personnel dimension data, and the infrastructure subcontractor dimension data, the following steps are also included: Preprocessing is performed on the management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data, including: Convert data from different sources into a unified format; Identify missing values, outliers, and redundant data in the management personnel dimension data, construction personnel dimension data, and infrastructure subcontractor dimension data, and fill the missing values ​​with the mode, mean, or median, or delete the missing values, and replace the outliers with upper or lower limits or the median; The management personnel dimension data, the construction personnel dimension data, and the infrastructure subcontractor dimension data are normalized or standardized.

6. The method according to claim 1, characterized in that, After obtaining the comprehensive project input score of the infrastructure subcontractor based on the input scores of the management personnel and the construction personnel, the following is also included: Generate a project investment evaluation report for the infrastructure subcontractor. The evaluation report includes one or more of the following data: overall project investment score, overall rating level, scores and reasons for scores for indicators included in each profile database, and improvement suggestions for low-scoring indicators. or Generate a scoring radar chart of the overall project input score. The scoring radar chart includes the input score of the management personnel, the input score of the construction personnel, and the scores corresponding to the indicators contained in each profile database.

7. The method according to claim 1, characterized in that, After obtaining the comprehensive project input score of the infrastructure subcontractor based on the input scores of the management personnel and the construction personnel, the following is also included: Based on the comprehensive project investment score of the infrastructure subcontractor, the performance risk of the infrastructure subcontractor is determined; Determine the performance risk level of the infrastructure subcontractor and output the performance risk level information and early warning information.

8. The method according to claim 1, characterized in that, After obtaining the comprehensive project input score of the infrastructure subcontractor based on the input scores of the management personnel and the construction personnel, the following is also included: Acquire on-site and management data of the infrastructure subcontractor during the construction process. The management data includes one or more indicators such as material arrival records, quality inspection reports, plan execution status, and changes in resource input. Based on the on-site data and the management data, the actual project investment of the infrastructure subcontractor is determined; Calculate the difference between the actual investment and the planned investment of the project, and assess the risk of insufficient investment by the infrastructure subcontractor based on the difference.

9. An electronic device, characterized in that, include: One or more processors; A memory for storing one or more programs that, when executed by one or more processors, cause the electronic device to perform the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions that, when executed by a computer's processor, cause the computer to perform the method as described in any one of claims 1 to 8.

Images