Engineering consultation value list comprehensive evaluation system based on target data analysis

Abstract

The invention discloses an engineering consultation value list comprehensive evaluation system based on target data analysis, and belongs to the technical field of engineering evaluation, and the system comprises a target setting module which is configured to set target data; the data collection module is configured to collect engineering project multi-source data and perform preprocessing; the feature extraction module is configured to perform feature extraction on the engineering project multi-source data; the model construction module is configured to construct an engineering consultation value list comprehensive evaluation model; and the result output module is configured to output a comprehensive evaluation result of the project consultation value list. The problem that the comprehensive evaluation efficiency of the project consultation value list is low because the project consultation value list cannot be comprehensively evaluated based on target data analysis in the prior art is solved. According to the method, the engineering consultation value list can be comprehensively evaluated based on the target data analysis, the comprehensiveness of the evaluation result is ensured, the automation and intelligence of the evaluation process are realized, and the comprehensive evaluation efficiency of the engineering consultation value list is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering evaluation, and in particular to a comprehensive evaluation system for an engineering consulting value list based on target data analysis. Background Art

[0002] Engineering consulting and evaluation is an important step before project implementation, aiming to provide a scientific basis for project investment decisions, reduce risks and optimize resource allocation.

[0003] The Chinese patent application with publication number CN111476425A discloses a system and method for supervising the construction cost progress of an engineering project. The system includes a cloud server and a project terminal: the project terminal is in communication with the cloud server and is used to send construction photos of the construction site to the cloud server; the cloud server includes a project planning module, a blockchain building module, and a project progress module: the project planning module is used to obtain cost-related engineering cost documents, plan and arrange the engineering cost according to the engineering cost process, and obtain a planned progress data table; the blockchain building module is used to obtain the corresponding processing nodes in the planned progress data table, and form the processing nodes into an engineering cost blockchain according to the engineering cost process; the project progress module obtains the construction progress of the current processing node based on the obtained construction photos. When there is an abnormality between the construction progress and the progress of the planned data table, the BIM system is used to generate a three-dimensional model diagram, and the time and construction cost to complete the current processing node are predicted based on the information in the project list. However, this patent has the following defects: Existing technologies cannot conduct a comprehensive evaluation of the engineering consulting value list based on target data analysis, and cannot accurately and efficiently evaluate the value of engineering projects, making the comprehensive evaluation of the engineering consulting value list inefficient and unable to provide strong support for project decision-making. Summary of the Invention

[0004] The purpose of the present invention is to provide a comprehensive evaluation system for engineering consulting value lists based on target data analysis, which can conduct a comprehensive evaluation of engineering consulting value lists based on target data analysis, accurately and efficiently evaluate the value of engineering projects, ensure the comprehensiveness of the evaluation results, realize the automation and intelligence of the evaluation process, improve the efficiency of the comprehensive evaluation of engineering consulting value lists, provide strong support for project decision-making, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The comprehensive evaluation system of engineering consulting value list based on target data analysis includes: A data collection module configured to collect multi-source data of engineering projects and perform pre-processing; Use the data item fluctuation parameters within a preset time period to set the dynamic phase difference trigger threshold, monitor the data fluctuation range of each data type, and determine whether to trigger the re-collection of multi-source data for the engineering project based on the data fluctuation range monitoring results; A feature extraction module configured to extract engineering project feature data; The result output module is configured to analyze the engineering project characteristic data and comprehensively evaluate the engineering consulting value list.

[0006] Preferably, the multi-source data of the engineering project is collected, including: Collect bill of quantities, cost data, schedule information and environmental impact data of engineering projects to determine multi-source data of engineering projects; Classify the multi-source data of the engineering project through the established digital quantum state modeling engine, obtain the data types contained in the multi-source data of the engineering project, and generate a unique hash code for each data type; The data activity amplitude corresponding to each data type is set to the maximum value of 1.0, the updated perturbation amplitude β is initialized to 0.0, and a quantum random number generator is used to randomly generate a dynamic phase initial value through the environmental noise injection method, and a data field mapping relationship diagram is generated at the same time; The dynamic phase initial value ranges from (0, 2π) and is unpredictable using a quantum random number generator. A data field mapping relationship diagram is generated simultaneously. Furthermore, the data field mapping relationship diagram is used to record quantum entanglement associations between data items in the form of a graph database, with edge weights determined by the frequency of data interaction. A data quantum state registry containing the states of all data items corresponding to each data type is constructed based on the data items of each data type. The storage structure corresponding to the data quantum state registry is a key-value pair database, where the key is the data item ID and the value is a four-tuple <α,θ,β,φ>. α represents the data activity amplitude, β represents the update disturbance amplitude; θ represents the phase angle corresponding to the mathematical mapping of the 128-bit hash value corresponding to the data item; and φ represents the dynamic phase. The dynamic phase difference trigger threshold is set using the data item fluctuation parameters within a preset time period, the data fluctuation range of each data type is monitored, and based on the data fluctuation range monitoring results, it is determined whether to trigger the re-collection of multi-source data for the engineering project.

[0007] Preferably, the dynamic phase difference trigger threshold is set using the data item fluctuation parameter within a preset time period, the data fluctuation range of each data type is monitored, and based on the data fluctuation range monitoring result, it is determined whether to trigger the re-collection of multi-source data of the engineering project, including: For the initial stable period quantum state data within a preset time period after system deployment, the natural fluctuation pattern of each data item in each data type within the multi-source data of the engineering project is continuously monitored through time series analysis and sliding window statistics, and the data fluctuation range is recorded; wherein the value range of the preset time period is 12 hours to 36 hours; Obtain a quaternary group <α,θ,β,φ> according to each data fluctuation of each data item in each data type in the multi-source data of the engineering project; Setting a dynamic phase difference trigger threshold corresponding to each data item according to the four-tuple <α, θ, β, φ> corresponding to each data fluctuation of each data item in each data type in the multi-source data of the engineering project; Real-time monitoring of the phase difference of the dynamic phase corresponding to each data fluctuation of each data item in each data type in the multi-source data of the engineering project; comparing the phase difference of the dynamic phase with a dynamic phase difference trigger threshold corresponding to each data item; When the phase difference of the dynamic phase of each data item is not lower than the dynamic phase difference trigger threshold corresponding to each data item, re-collection of data of the data item is triggered.

[0008] Preferably, collecting multi-source data of engineering projects also includes: Real-time monitoring of the phase difference value of the dynamic phase corresponding to each data item when re-collecting data; Real-time monitoring of the data re-collection frequency of each data item; comparing a data recollection frequency of the data item with a preset data recollection frequency reference value; When the data recollection frequency of the data item exceeds a preset data recollection frequency reference value, retrieving a frequency excess rate of the data recollection frequency exceeding the preset data recollection frequency reference value; When the data re-collection frequency of the data item exceeds a preset data re-collection frequency reference value, taking the data item as a target data item; Retrieving a phase difference value of the dynamic phase corresponding to the target data item at each re-data collection; A phase excess rate according to which the phase difference value of the dynamic phase during each re-data collection exceeds the dynamic phase difference trigger threshold corresponding to the target data item; comparing the frequency excess rate and the phase excess rate corresponding to the target data item; When the frequency excess rate corresponding to the target data item exceeds the phase excess rate by an amplitude greater than a preset amplitude threshold, the frequency excess rate and the phase excess rate are used to compensate the dynamically adjusted dynamic phase difference trigger threshold corresponding to the target data item to obtain the compensated dynamic phase difference trigger threshold.

[0009] Preferably, it further comprises: a target setting module configured to set target data according to project requirements and evaluation targets; According to the project requirements and assessment objectives, determine multiple dimensions and indicators of project assessment, including technical dimension, quality dimension, economic dimension, environmental dimension and social dimension of the project; Determine the target data for project evaluation based on the technical, quality, economic, environmental and social dimensions of the project; Among them, the technical dimension of engineering projects includes technical capabilities, design quality and risk management; the quality dimension of engineering projects includes service quality and process quality; the economic dimension of engineering projects includes cost-effectiveness and financial stability; the environmental dimension of engineering projects includes environmental impact and sustainability impact; and the social dimension of engineering projects includes customer satisfaction and social impact.

[0010] Preferably, preprocessing the multi-source data of the engineering project includes: Clean the multi-source data of engineering projects and remove the noise data that is useless for the comprehensive evaluation of the engineering consulting value list; Check the multi-source data of engineering projects, identify missing values ​​and outliers in the multi-source data of engineering projects, and process the identified missing values ​​and outliers in the multi-source data of engineering projects; The multi-source data of the engineering project is converted into a unified data format, the dimensional differences in the multi-source data of the engineering project are removed, and the standardized multi-source data of the engineering project is determined.

[0011] Preferably, extracting engineering project feature data includes: Based on the principal component analysis method, feature vectors useful for the comprehensive evaluation of engineering consulting value lists are extracted from multi-source data of engineering projects. The extracted feature vectors are weighted and fused to determine the characteristic data of engineering projects, including the characteristics of the bill of quantities, cost data, schedule information and environmental impact data.

[0012] Preferably, it further comprises: a model building module configured to build a comprehensive evaluation model of the engineering consulting value list; According to the comprehensive evaluation requirements of the engineering consulting value list based on target data analysis, historical data of engineering projects are collected and divided into training sets and test sets; Based on deep learning technology, a training set is used to train the deep learning model, so that the deep learning model can autonomously learn the comprehensive evaluation behavior of the engineering consulting value list from the training set, and determine the comprehensive evaluation model of the engineering consulting value list based on target data analysis; The test set is used to test the comprehensive evaluation model of the engineering consulting value list based on target data analysis, evaluate the performance of the comprehensive evaluation model of the engineering consulting value list based on target data analysis, and determine whether the comprehensive evaluation model of the engineering consulting value list based on target data analysis can comprehensively evaluate the engineering consulting value list; According to the test evaluation results, the parameters of the comprehensive evaluation model of the engineering consulting value list based on target data analysis are adjusted and optimized to determine the best comprehensive evaluation model of the engineering consulting value list.

[0013] Preferably, the characteristic data of the engineering project is analyzed and the engineering consulting value list is comprehensively evaluated, including: Deploy the best engineering consulting value list comprehensive evaluation model and deploy the best engineering consulting value list comprehensive evaluation model in the actual engineering consulting value list comprehensive evaluation environment based on target data analysis; Input the engineering project characteristic data into the comprehensive evaluation model of the engineering consulting value list, analyze the engineering project characteristic data according to the comprehensive evaluation model of the engineering consulting value list, and comprehensively evaluate the engineering consulting value list, determine the comprehensive evaluation results of the engineering consulting value list based on the target data analysis, and output the comprehensive evaluation results of the engineering consulting value list.

[0014] Preferably, the comprehensive evaluation results of the engineering consulting value list are output, including: Obtain comprehensive evaluation results of the engineering consulting value list based on target data analysis, and output the comprehensive evaluation results of the engineering consulting value list in a visual form on the mobile terminal and display them to users. Users make decisions based on the comprehensive evaluation results of the engineering consulting value list and then manage the engineering projects.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention determines multiple dimensions and indicators of engineering project evaluation based on engineering project requirements and evaluation objectives, determines target data for engineering project evaluation based on engineering project technical dimensions, quality dimensions, economic dimensions, environmental dimensions, and social dimensions, collects multi-source data of the engineering project based on the engineering project's bill of quantities, cost data, progress information, and environmental impact data, preprocesses and extracts features from the multi-source data of the engineering project, determines engineering project feature data, constructs an engineering consulting value list comprehensive evaluation model based on the comprehensive evaluation requirements of the engineering consulting value list based on target data analysis, analyzes the engineering project feature data based on the comprehensive evaluation model of the engineering consulting value list, comprehensively evaluates the engineering consulting value list, determines a comprehensive evaluation result of the engineering consulting value list based on the target data analysis, outputs the result in a visual form on a mobile terminal, and displays it to a user, allowing the user to make decisions based on the comprehensive evaluation result of the engineering consulting value list and then manage the engineering project. The engineering consulting value list can be comprehensively evaluated based on the target data analysis, accurately and efficiently evaluating the value of the engineering project, ensuring the comprehensiveness of the evaluation result, realizing the automation and intelligence of the evaluation process, improving the efficiency of the comprehensive evaluation of the engineering consulting value list, and providing strong support for project decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a module diagram of the engineering consulting value list comprehensive evaluation system of the present invention; Figure 2 This is a flow chart of the engineering consulting value list comprehensive evaluation system of the present invention; Figure 3 This is a framework diagram of the engineering consulting value list comprehensive evaluation system of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] In order to solve the existing problem that the comprehensive evaluation of engineering consulting value list cannot be carried out based on target data analysis, the value of engineering projects cannot be accurately and efficiently evaluated, which makes the comprehensive evaluation of engineering consulting value list inefficient and unable to provide strong support for project decision-making, please refer to Figure 1-Figure 3 , this embodiment provides the following technical solutions: The comprehensive evaluation system of engineering consulting value list based on target data analysis includes: target setting module, data collection module, feature extraction module, model construction module and result output module.

[0019] Specifically, through the interaction between the goal setting module, data collection module, feature extraction module, model building module and result output module, a comprehensive evaluation of the engineering consulting value list can be carried out based on target data analysis, which can accurately and efficiently evaluate the value of engineering projects, ensure the comprehensiveness of the evaluation results, realize the automation and intelligence of the evaluation process, improve the efficiency of the comprehensive evaluation of the engineering consulting value list, and provide strong support for project decision-making.

[0020] Among them, the target setting module is used to set target data according to engineering project requirements and evaluation goals; In this embodiment, target data is set according to project requirements and assessment objectives, including: According to the project requirements and assessment objectives, determine multiple dimensions and indicators of project assessment, including technical dimension, quality dimension, economic dimension, environmental dimension and social dimension of the project; Determine the target data for project evaluation based on the technical, quality, economic, environmental and social dimensions of the project; Among them, the technical dimension of engineering projects includes technical capabilities, design quality and risk management; the quality dimension of engineering projects includes service quality and process quality; the economic dimension of engineering projects includes cost-effectiveness and financial stability; the environmental dimension of engineering projects includes environmental impact and sustainability impact; and the social dimension of engineering projects includes customer satisfaction and social impact.

[0021] Among them, the data collection module is used to collect multi-source data of engineering projects and perform preprocessing; In this embodiment, multi-source data of the engineering project is collected, including: Collect the quantities of each part of the project, the bill of materials and the bill of equipment to determine the bill of quantities of the project; Collect project budgets, actual costs, and cost deviation analysis of engineering projects to determine project cost data; Collect the construction progress plan, actual construction progress, and progress deviation analysis of the project to determine the progress information of the project; Collect environmental impact assessment reports, environmental monitoring data, waste disposal conditions, and energy conservation and emission reduction measures for engineering projects to determine environmental impact data for engineering projects; Determine multi-source data for engineering projects based on the project's bill of quantities, cost data, schedule information, and environmental impact data.

[0022] Preferably, the multi-source data of the engineering project is collected, including: Collect the quantities of each part of the project, the bill of materials and the bill of equipment to determine the bill of quantities of the project; Collect project budgets, actual costs, and cost deviation analysis of engineering projects to determine project cost data; Collect the construction progress plan, actual construction progress, and progress deviation analysis of the project to determine the progress information of the project; Collect environmental impact assessment reports, environmental monitoring data, waste disposal conditions, and energy conservation and emission reduction measures for engineering projects to determine environmental impact data for engineering projects; Determine multi-source data for engineering projects based on the project's bill of quantities, cost data, schedule information, and environmental impact data.

[0023] Specifically, the collection of multi-source data for engineering projects also includes: The established digital quantum state modeling engine is used to classify the multi-source data of the engineering project, obtain the data types contained in the multi-source data of the engineering project, and generate a unique hash code for each data type. Specifically, a 128-bit hash value is calculated based on the data content and type characteristics, and mapped to the theta phase base value; The data activity amplitude corresponding to each data type is set to the maximum value of 1.0, the updated perturbation amplitude β is initialized to 0.0, and a quantum random number generator is used to randomly generate a dynamic phase initial value through the environmental noise injection method, and a data field mapping relationship diagram is generated at the same time; The dynamic phase initial value ranges from (0, 2π) and is unpredictable using a quantum random number generator. A data field mapping relationship diagram is generated simultaneously. Furthermore, the data field mapping relationship diagram is used to record quantum entanglement associations between data items in the form of a graph database, with edge weights determined by the frequency of data interaction. A data quantum state registry containing the states of all data items corresponding to each data type is constructed based on the data items of each data type. The storage structure corresponding to the data quantum state registry is a key-value pair database, where the key is the data item ID and the value is a four-tuple <α,θ,β,φ>. α represents the data activity amplitude, β represents the update disturbance amplitude; θ represents the phase angle corresponding to the mathematical mapping of the 128-bit hash value corresponding to the data item; and φ represents the dynamic phase. The dynamic phase difference trigger threshold is set using the data item fluctuation parameters within a preset time period, the data fluctuation range of each data type is monitored, and based on the data fluctuation range monitoring results, it is determined whether to trigger the re-collection of multi-source data for the engineering project.

[0024] The technical solution described above achieves the following: A digital quantum state modeling engine is used to classify multi-source data from engineering projects and identify the various data types contained within the data. A 128-bit hash value is calculated based on the data content and type characteristics and mapped to a θ phase base value. The hash value uniquely identifies the data characteristics, and the θ phase base value obtained through mapping is used to subsequently represent the data state. The data activity amplitude α corresponding to each data type is set to a maximum value of 1.0, indicating that the data is fully active in the initial state. The update perturbation amplitude β is initialized to 0.0, indicating that there is no update perturbation at the initial stage. A quantum random number generator is used to randomly generate a dynamic phase initial value φ in the range (0, 2π) using an environmental noise injection method. The quantum random number generator ensures the unpredictability of the dynamic phase initial value, enhancing the randomness and security of the data state. A data field mapping relationship graph is generated, recording the quantum entanglement relationships between data items in the form of a graph database, with edge weights determined by the frequency of data interactions. This mapping relationship graph reflects the degree of association and interaction between data items. A data quantum state registry is constructed based on the data items of each data type, with a key-value database storage structure. The key is the data item ID, and the value is a four-tuple <α,θ,β,φ>, representing the data activity amplitude, update disturbance amplitude, phase angle of the 128-bit hash value mapping corresponding to the data, and dynamic phase, respectively. This registry allows for convenient recording and querying of the status of each data item. The dynamic phase difference trigger threshold is set using the data item fluctuation parameters within a preset time period. The data fluctuation range of each data type is monitored, and the actual dynamic phase difference is compared with the trigger threshold. Based on the monitoring results, a decision is made as to whether to trigger re-collection of multi-source data for the project. If the dynamic phase difference exceeds the trigger threshold, indicating significant data fluctuation, re-collection may be necessary to ensure data accuracy and validity.

[0025] Furthermore, the digital quantum state modeling engine classifies multi-source data, accurately identifying different data types and preventing data confusion, providing an accurate foundation for subsequent data processing and analysis. A 128-bit hash value generated based on data content and type characteristics and mapped to a θ phase base value ensures unique identification for each data type, improving data traceability and accuracy. The data quantum state registry records the state of each data item in the form of key-value pairs. The four-tuple <α,θ,β,φ> comprehensively and accurately describes information such as activity, characteristics, perturbations, and dynamic phase of the data item, helping to accurately understand data state changes. The use of a quantum random number generator to generate dynamic phase initial values ​​increases the security of the data state and prevents malicious tampering or cracking. The data field mapping diagram records the quantum entanglement relationships between data items. Edge weights are determined by the frequency of data interactions. This complex relationship and dynamic weighting enhance data security and privacy. By setting a dynamic phase difference trigger threshold to monitor data fluctuations, abnormal data fluctuations can be detected promptly. When data fluctuations exceed a threshold, data recollection is triggered, enabling the system to adapt to data changes and ensuring data timeliness and accuracy. The environmental noise injection method introduces randomness, enabling the system to adapt to varying environmental conditions and data changes, enhancing system robustness. The data quantum state registry utilizes a key-value database storage structure, enabling convenient and rapid querying and management of data item status, improving data processing efficiency. Real-time monitoring of data fluctuations and a threshold-based decision mechanism enable rapid decisions on whether to recollect data, reducing unnecessary resource waste and improving system operational efficiency.

[0026] Specifically, the dynamic phase difference trigger threshold is set using the data item fluctuation parameters within a preset time period, the data fluctuation range of each data type is monitored, and based on the data fluctuation range monitoring results, it is determined whether to trigger the re-collection of multi-source data for the engineering project, including: For the initial stable period quantum state data within a preset time period after system deployment, the natural fluctuation pattern of each data item in each data type within the multi-source data of the engineering project is continuously monitored through time series analysis and sliding window statistics, and the data fluctuation range is recorded; wherein the value range of the preset time period is 12 hours to 36 hours; Obtain a quaternary group <α,θ,β,φ> according to each data fluctuation of each data item in each data type in the multi-source data of the engineering project; Setting a dynamic phase difference trigger threshold corresponding to each data item according to the four-tuple <α, θ, β, φ> corresponding to each data fluctuation of each data item in each data type in the multi-source data of the engineering project; The dynamic phase difference trigger threshold corresponding to each data item is obtained by the following formula: ; Where R(t) represents the dynamic phase difference trigger threshold corresponding to each data item; λ represents the baseline phase weight coefficient, which ranges from 0.3 to 0.8 and is an empirical coefficient that controls the weight of the historical phase influence; n represents the number of data fluctuations for each data item in each data type within the multi-source data of the engineering project; represents the moving amplitude of the phase difference in the sliding window corresponding to the i-th data fluctuation; ε represents the amplitude-frequency coupling coefficient, which ranges from 0.1 to 0.6 and is used to characterize the synergistic effect strength of the adjustment amplitude and frequency fluctuation; α(t) represents the instantaneous fluctuation amplitude of the current data item; α ref Indicates the reference fluctuation range benchmark value; θ w Represents the phase angle data set recorded in the sliding window, that is, the phase angle value set at all times in the window; δ[θ w ] represents the standard deviation of the phase angle in the sliding window; μ represents the frequency mutation penalty factor, which ranges from 0.2 to 1.5 and is used to characterize the fixed phase offset penalty imposed during overclocking; β(t) represents the instantaneous fluctuation frequency of the current data item, which can be set to be automatically generated by the 90% quantile of the α value in the sliding window. The window length is recommended to cover the system stability period (e.g., 10 seconds to 60 seconds); β th Represents the preset frequency mutation judgment threshold, which is specifically set to the moving average of β + 3 times the standard deviation; Partly through the weighted average of historical fluctuation phase information, a basic value based on past fluctuation patterns is provided for the setting of the current dynamic phase difference trigger threshold, reflecting the impact of the historical trend of data fluctuation in phase on the current threshold. The synergistic effect between the fluctuation amplitude and the phase angle fluctuation is fully considered. When the instantaneous fluctuation amplitude changes relative to the reference amplitude and the fluctuation degree (standard deviation) of the phase angle within the sliding window is large, the trigger threshold will be adjusted according to the amplitude-frequency coupling coefficient, reflecting the influence of the mutual correlation between the data fluctuation amplitude and the phase angle fluctuation frequency on the threshold. In the example, μ is the frequency mutation penalty factor, β(t) is the instantaneous fluctuation frequency of the current data item, and β th is the preset frequency mutation threshold. The sgn function outputs -1, 0, or 1 depending on the relationship between the current frequency and the threshold. Its physical principle is that when the instantaneous fluctuation frequency of a data item exceeds the preset frequency mutation threshold (i.e., a frequency mutation occurs), a fixed phase offset penalty determined by μ is applied, causing the trigger threshold to change accordingly. This penalizes this abnormal frequency mutation and adjusts the threshold accordingly.

[0027] Real-time monitoring of the phase difference of the dynamic phase corresponding to each data fluctuation of each data item in each data type in the multi-source data of the engineering project; comparing the phase difference of the dynamic phase with a dynamic phase difference trigger threshold corresponding to each data item; When the phase difference of the dynamic phase of each data item is not lower than the dynamic phase difference trigger threshold corresponding to each data item, re-collection of data of the data item is triggered.

[0028] The technical effect of the above technical solution is that, during the initial stabilization period within a preset time period (12-36 hours) after system deployment, time series analysis and a sliding window counter are used to continuously monitor the natural fluctuation patterns of each data item in each data type within the multi-source data of the engineering project. Time series analysis captures the temporal changes in data, while the sliding window counter performs statistical analysis on data within different time windows, thereby determining and recording the normal fluctuation range of each data item. Each time a data fluctuation occurs, a four-tuple <α, θ, β, φ> is obtained for the corresponding data item. This four-tuple contains the data activity amplitude α, the update disturbance amplitude β, the phase angle θ mapped to the corresponding 128-bit hash value of the data, and the dynamic phase φ, comprehensively describing the state of the data item at the time of the fluctuation. Based on the four-tuple corresponding to each data fluctuation, a dynamic phase difference trigger threshold is set for each data item. This threshold combines information about the data item's activity, disturbance, and phase status to determine whether the data fluctuation exceeds the normal range. The dynamic phase difference of each data item in each data type within the multi-source data of the engineering project is monitored in real time during each fluctuation, continuously tracking changes in the data state. The phase difference of the dynamic phase monitored in real time is compared with the dynamic phase difference trigger threshold corresponding to each data item. If the phase difference is not lower than the trigger threshold, it indicates that the data fluctuation is abnormal, and the data of the data item is triggered to be re-collected.

[0029] Furthermore, through time series analysis and a sliding window counter, natural fluctuation patterns are precisely monitored. Trigger thresholds are set based on comprehensive quadruple information, accurately distinguishing between normal and abnormal fluctuations, precisely capturing data anomalies, avoiding false positives and missed detections, and ensuring that collected data accurately reflects the project's actual conditions. Setting trigger thresholds based on the quadruple state information of data items during fluctuations ensures that the thresholds closely align with the data's inherent characteristics and fluctuation patterns, enhancing the scientific and reliable nature of threshold setting and, in turn, the accuracy of determining whether data recollection is necessary. Real-time monitoring of the phase difference of data items' dynamic phases allows for immediate recollection upon abnormal fluctuations (when the phase difference reaches or exceeds the threshold), promptly responding to data changes and ensuring the timeliness of collected data for timely analysis and decision-making in the project. Once abnormal data fluctuations are identified, recollection is promptly triggered, reducing delays in subsequent project work caused by unaddressed data anomalies and accelerating the overall workflow. Timely data recollection replaces abnormally fluctuating data, ensuring data quality stability and preventing abnormal data from impacting project analysis, decision-making, and operations, thereby maintaining the stable operation of project-related systems. It effectively responds to abnormal data fluctuations, enabling the system to ensure data reliability through re-collection when facing various internal and external interference factors (such as data fluctuations caused by environmental changes, system failures, etc.), thereby enhancing the system's anti-interference ability and stability.

[0030] On the other hand, the formula proposed in the above technical solution integrates multiple factors such as historical phase fluctuations, amplitude-frequency coupling effects, and frequency mutation penalties to set the threshold. The phase fluctuation basis is obtained from historical data, combined with the synergistic relationship between the current fluctuation amplitude and phase angle fluctuation, and then the frequency mutation situation is considered. The key physical factors affecting data fluctuations are fully covered, so that the threshold setting is more in line with the inherent physical laws of data fluctuations and has higher rationality. By setting multiple adjustable parameters (such as λ, ε, μ, etc.), it can be flexibly adjusted according to different data types, application scenarios and actual needs. For example, for data with relatively stable fluctuations, λ can be appropriately lowered to reduce the weight of historical phase influence; for data with obvious amplitude-frequency coupling effects, ε can be adjusted to more accurately reflect their relationship, thereby ensuring that the threshold setting can adapt to different data characteristics and enhancing the rationality of the threshold setting. The formula is based on the fluctuation amplitude (α(t)), frequency (β(t)) and phase angle (θ w The threshold is calculated based on characteristic parameters such as the instantaneous fluctuation amplitude α(t) and the instantaneous fluctuation frequency β(t). This method closely matches the actual fluctuation of the data item, accurately reflecting the characteristic changes in the fluctuation. This method makes the threshold highly compatible with the fluctuation characteristics of the data item, effectively identifying the true abnormal fluctuation of the data item. As the data fluctuates, parameters such as the instantaneous fluctuation amplitude α(t) and the instantaneous fluctuation frequency β(t) in the formula change in real time, and the threshold is dynamically adjusted accordingly.

[0031] Specifically, the collection of multi-source data for engineering projects also includes: Real-time monitoring of the phase difference value of the dynamic phase corresponding to each data item when re-collecting data; Real-time monitoring of the data re-collection frequency of each data item; comparing a data recollection frequency of the data item with a preset data recollection frequency reference value; When the data recollection frequency of the data item exceeds a preset data recollection frequency reference value, retrieving a frequency excess rate (in percentage) of the data recollection frequency exceeding the preset data recollection frequency reference value; When the data re-collection frequency of the data item exceeds a preset data re-collection frequency reference value, taking the data item as a target data item; Retrieving a phase difference value of the dynamic phase corresponding to the target data item at each re-data collection; A phase excess rate (percentage) according to which the phase difference value of the dynamic phase during each re-data acquisition exceeds the dynamic phase difference trigger threshold corresponding to the target data item; comparing the frequency excess rate and the phase excess rate corresponding to the target data item; When the amplitude of the frequency excess rate corresponding to the target data item exceeding the phase excess rate is greater than a preset amplitude threshold, the frequency excess rate and the phase excess rate are used to compensate the dynamically adjusted dynamic phase difference trigger threshold corresponding to the target data item to obtain the compensated dynamic phase difference trigger threshold; The compensated dynamic phase difference trigger threshold is obtained by the following formula: ; Where R(t) x represents the compensated dynamic phase difference trigger threshold corresponding to each data item; R(t) represents the dynamic phase difference trigger threshold corresponding to each data item; Indicates the phase excess rate; P f The phase exceedance rate reflects the degree to which the actual data fluctuation amplitude exceeds the current threshold, reflecting the amplitude characteristics of data fluctuations. The frequency exceedance rate represents the degree to which the data recollection frequency exceeds the preset reference value, reflecting the frequency of data fluctuations. Incorporating these two factors into the formula comprehensively considers the impact of the threshold from the two key physical dimensions of fluctuation amplitude and frequency, comprehensively measuring the fluctuation status of the data item. Adjust according to the difference between the frequency excess rate and the phase excess rate through trigonometric function. f and As the difference changes, the trigonometric function value fluctuates between -1 and 1, affecting the compensation coefficient. Its physical significance lies in adjusting the compensation amplitude in a nonlinear manner based on the relative magnitude of the frequency and phase excess rate, more flexibly adapting to the fluctuation characteristics of different data items. The whole is used as a compensation coefficient and multiplied by the original threshold R(t) to obtain the compensated threshold R(t) x If the frequency exceedance is higher than the phase exceedance, and the difference meets certain conditions, the compensation coefficient will increase or decrease the original threshold. The adjustment range is determined by the frequency and phase exceedance rates and trigonometric functions. This achieves dynamic compensation of the threshold to make it more consistent with the actual fluctuation of the data item.

[0032] The technical solution described above provides real-time monitoring of the dynamic phase difference value during recollection of each data item, as well as the data recollection frequency for each data item. The former reflects data fluctuations, while the latter reflects the frequency of data anomalies. The data recollection frequency is compared with a preset reference value. If it exceeds the reference value, the frequency exceedance rate is calculated, and the data item is designated as a target data item, identifying the data item for focused analysis and processing. For the target data item, the dynamic phase difference value during each recollection is retrieved, and the phase exceedance rate at which it exceeds the corresponding trigger threshold is calculated. The frequency exceedance rate and phase exceedance rate of the target data item are compared. When the frequency exceedance rate exceeds the phase exceedance rate by more than a preset threshold, the dynamic phase difference trigger threshold is compensated based on these two ratios, resulting in a more realistic compensated threshold. The data recollection frequency is an important indicator for measuring whether a data item frequently experiences abnormal fluctuations. When the data recollection frequency of a target data item exceeds the preset reference value, the frequency exceedance rate (percentage) is calculated, indicating that the frequency of abnormal fluctuations in that data item exceeds normal expectations. A high frequency exceedance rate indicates that the currently set dynamic phase difference trigger threshold may not accurately identify anomalies in the data item, or that the current threshold is too lenient for the data item, resulting in frequent recollection triggering. The phase exceedance rate is the percentage of times the dynamic phase difference value during each recollection exceeds the dynamic phase difference trigger threshold for the target data item. It reflects the relationship between the actual data fluctuation amplitude (measured by phase difference) and the current trigger threshold. A low phase exceedance rate indicates that despite the high frequency of data recollection, the fluctuation amplitude does not significantly exceed the threshold, indicating that the current threshold may still be reasonable in measuring fluctuation amplitude. Comparing the frequency exceedance rate with the phase exceedance rate comprehensively determines the appropriateness of the current dynamic phase difference trigger threshold for the target data item. When the frequency exceedance rate exceeds the phase exceedance rate by more than the preset amplitude threshold, this indicates that although data frequently triggers recollection (high frequency exceedance rate), the actual fluctuation amplitude exceeds the current threshold by a relatively small amount (low phase exceedance rate). This indicates that there is a problem with the current threshold setting and that it may not be well adapted to the fluctuation characteristics of the data item. Based on these comparison results, the frequency and phase excess rates are used to compensate for the dynamic phase difference trigger threshold. This allows for targeted adjustments to the threshold based on the frequency and magnitude of fluctuations in the target data item. This allows the threshold to better reflect the actual fluctuation characteristics of the data item, enabling more accurate determination of data anomalies in subsequent monitoring, avoiding excessive or insufficient recollection operations, and ultimately optimizing the data collection process and quality.

[0033] By recollecting frequency and phase difference values ​​from monitoring data, we can accurately identify data items (target data items) with frequent anomalies and unusual fluctuation characteristics, avoiding misclassification of normal data and pinpointing anomalous data requiring attention. Thresholds are compensated based on the frequency and phase excess ratio comparisons, ensuring they better align with the actual fluctuations of the target data items. This ensures more accurate subsequent data anomaly determinations and improves the accuracy of data anomaly detection. Real-time monitoring and dynamic threshold adjustment adapt to changes in data item fluctuations and acquisition frequency, adapting to dynamic data changes and providing continuous and effective anomaly detection. By calculating the frequency and phase excess ratios separately for different data items and adjusting the thresholds accordingly, we can adapt to the fluctuations and acquisition characteristics of different data, ensuring that all data types are appropriately monitored. Accurately identifying and processing anomalous data items and timely adjusting thresholds can reduce interference from anomalous data, ensure consistent data quality, and maintain the stable operation of data-based analysis and decision-making functions. Proper threshold adjustment ensures more scientific identification and processing of data anomalies, reduces the risk of system failures caused by erroneous determinations or improper processing, and enhances system reliability. Furthermore, the above-mentioned technical solution utilizes a comprehensive frequency and phase excess rate for threshold compensation, comprehensively accounting for the diverse aspects of data fluctuation and avoiding the one-sidedness of threshold adjustment based solely on a single factor. By focusing on the two key characteristics of data fluctuation—amplitude and frequency—the compensated threshold setting better reflects the physical nature of data fluctuation, improving the rationality of threshold compensation. The use of trigonometric functions for nonlinear adjustment allows for more precise adaptation to the frequency and phase excess rate combinations of different data items. The fluctuation characteristics of different data items vary significantly. This nonlinear adjustment approach allows for accurate threshold compensation for a variety of complex fluctuation patterns, making the compensation mechanism more flexible and scientific, and enhancing the rationality of threshold setting. The compensated threshold is calculated based on each data item's individual frequency and phase excess rates, closely tailoring it to the data item's unique fluctuation characteristics. Whether fluctuations are frequent but small in amplitude or large in amplitude but low in frequency, the formula accurately adjusts the threshold, ensuring a high degree of adaptation to the data item's fluctuation characteristics and enabling more precise data anomaly detection. As the fluctuation of a data item changes, the frequency and phase excess rates change in real time, and the formula calculates the compensated threshold based on these changes in real time. For example, when the frequency of fluctuation of a data item suddenly increases and the frequency excess rate changes, the formula will adjust the threshold accordingly to achieve dynamic adaptive adjustment and continuously maintain good adaptability to the fluctuation of the data item.

[0034] In this embodiment, preprocessing of multi-source data of engineering projects includes: Clean the multi-source data of engineering projects and remove the noise data that is useless for the comprehensive evaluation of the engineering consulting value list; Check the multi-source data of engineering projects, identify missing values ​​and outliers in the multi-source data of engineering projects, and process the identified missing values ​​and outliers in the multi-source data of engineering projects; The multi-source data of the engineering project is converted into a unified data format, the dimensional differences in the multi-source data of the engineering project are removed, and the standardized multi-source data of the engineering project is determined.

[0035] Among them, the feature extraction module is used to extract features from multi-source data of engineering projects and determine the feature data of engineering projects; In this embodiment, feature extraction is performed on multi-source data of engineering projects, including: Based on the principal component analysis method, feature vectors useful for the comprehensive evaluation of engineering consulting value lists are extracted from multi-source data of engineering projects. The extracted feature vectors are weighted and fused to determine the characteristic data of engineering projects, including the characteristics of the bill of quantities, cost data, schedule information and environmental impact data.

[0036] It should be noted that the characteristics of the bill of quantities include the project name, quantity, unit of measurement, concrete pouring volume, steel bar usage, etc.; the characteristics of cost data include raw material cost, labor cost, management fee, tax, unit cost, total cost, etc.; the characteristics of progress information include planned start time, planned end time, actual start time, actual end time, progress deviation, progress performance index, etc.; the characteristics of environmental impact data include energy consumption, water resource use, waste gas emissions, wastewater discharge, biodiversity index, habitat destruction degree, etc. Among them, the model building module is used to build a comprehensive evaluation model of the engineering consulting value list; In this embodiment, a comprehensive evaluation model for the engineering consulting value list is constructed, including: According to the comprehensive evaluation requirements of the engineering consulting value list based on target data analysis, historical data of engineering projects are collected and divided into training sets and test sets; Based on deep learning technology, a training set is used to train the deep learning model, so that the deep learning model can autonomously learn the comprehensive evaluation behavior of the engineering consulting value list from the training set, and determine the comprehensive evaluation model of the engineering consulting value list based on target data analysis; The test set is used to test the comprehensive evaluation model of the engineering consulting value list based on target data analysis, evaluate the performance of the comprehensive evaluation model of the engineering consulting value list based on target data analysis, and determine whether the comprehensive evaluation model of the engineering consulting value list based on target data analysis can comprehensively evaluate the engineering consulting value list; According to the test evaluation results, the parameters of the comprehensive evaluation model of the engineering consulting value list based on target data analysis are adjusted and optimized to determine the best comprehensive evaluation model of the engineering consulting value list.

[0037] Among them, the result output module is used to analyze the characteristic data of the engineering project, comprehensively evaluate the engineering consulting value list, and output the comprehensive evaluation results of the engineering consulting value list.

[0038] In this embodiment, the engineering project characteristic data is analyzed and a comprehensive evaluation of the engineering consulting value list is conducted, including: Deploy the best engineering consulting value list comprehensive evaluation model and deploy the best engineering consulting value list comprehensive evaluation model in the actual engineering consulting value list comprehensive evaluation environment based on target data analysis; Input the engineering project characteristic data into the comprehensive evaluation model of the engineering consulting value list, analyze the engineering project characteristic data according to the comprehensive evaluation model of the engineering consulting value list, and comprehensively evaluate the engineering consulting value list to determine the comprehensive evaluation results of the engineering consulting value list based on the target data analysis.

[0039] In this embodiment, the comprehensive evaluation results of the engineering consulting value list are output, including: Obtain comprehensive evaluation results of the engineering consulting value list based on target data analysis, and output the comprehensive evaluation results of the engineering consulting value list in a visual form on the mobile terminal and display them to users. Users make decisions based on the comprehensive evaluation results of the engineering consulting value list and then manage the engineering projects.

[0040] In summary, the characteristic data of engineering projects are analyzed according to the comprehensive evaluation model of the engineering consulting value list, and the engineering consulting value list is comprehensively evaluated. The comprehensive evaluation results of the engineering consulting value list based on the target data analysis are determined, and the results are output in a visual form on the mobile terminal and displayed to the user. The user makes decisions based on the comprehensive evaluation results of the engineering consulting value list and then manages the engineering project. The engineering consulting value list can be comprehensively evaluated based on the target data analysis, and the value of the engineering project can be accurately and efficiently evaluated, the comprehensiveness of the evaluation results can be ensured, the automation and intelligence of the evaluation process can be realized, the efficiency of the comprehensive evaluation of the engineering consulting value list can be improved, and strong support can be provided for project decision-making.

[0041] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0042] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. The comprehensive evaluation system of engineering consulting value list based on target data analysis is characterized by: include: A data collection module configured to collect multi-source data of engineering projects and perform pre-processing; Use the data item fluctuation parameters within a preset time period to set the dynamic phase difference trigger threshold, monitor the data fluctuation range of each data type, and determine whether to trigger the re-collection of multi-source data for the engineering project based on the data fluctuation range monitoring results; A feature extraction module configured to extract engineering project feature data; The result output module is configured to analyze the engineering project characteristic data and comprehensively evaluate the engineering consulting value list.

2. The engineering consulting value list comprehensive evaluation system based on target data analysis according to claim 1 is characterized in that: Collect multi-source data for engineering projects, including: Collect bill of quantities, cost data, schedule information and environmental impact data of engineering projects to determine multi-source data of engineering projects; Classify the multi-source data of the engineering project through the established digital quantum state modeling engine, obtain the data types contained in the multi-source data of the engineering project, and generate a unique hash code for each data type; The data activity amplitude corresponding to each data type is set to the maximum value of 1.0, the updated perturbation amplitude β is initialized to 0.0, and a quantum random number generator is used to randomly generate a dynamic phase initial value through the environmental noise injection method, and a data field mapping relationship diagram is generated at the same time; The dynamic phase initial value ranges from (0, 2π) and is unpredictable using a quantum random number generator. A data field mapping relationship diagram is generated simultaneously. Furthermore, the data field mapping relationship diagram is used to record quantum entanglement associations between data items in the form of a graph database, with edge weights determined by the frequency of data interaction. A data quantum state registry containing the states of all data items corresponding to each data type is constructed based on the data items of each data type. The storage structure corresponding to the data quantum state registry is a key-value pair database, where the key is the data item ID and the value is a four-tuple <α,θ,β,φ>. α represents the data activity amplitude, β represents the update disturbance amplitude; θ represents the phase angle corresponding to the mathematical mapping of the 128-bit hash value corresponding to the data item; and φ represents the dynamic phase. The dynamic phase difference trigger threshold is set using the data item fluctuation parameters within a preset time period, the data fluctuation range of each data type is monitored, and based on the data fluctuation range monitoring results, it is determined whether to trigger the re-collection of multi-source data for the engineering project.

3. The engineering consulting value list comprehensive evaluation system based on target data analysis according to claim 2 is characterized in that: Use the data item fluctuation parameters within a preset time period to set the dynamic phase difference trigger threshold, monitor the data fluctuation range of each data type, and determine whether to trigger the re-collection of multi-source data for the engineering project based on the data fluctuation range monitoring results, including: For the initial stable period quantum state data within a preset time period after system deployment, the natural fluctuation pattern of each data item in each data type within the multi-source data of the engineering project is continuously monitored through time series analysis and sliding window statistics, and the data fluctuation range is recorded; wherein the value range of the preset time period is 12 hours to 36 hours; Obtain a quaternary group <α,θ,β,φ> according to each data fluctuation of each data item in each data type in the multi-source data of the engineering project; Setting a dynamic phase difference trigger threshold corresponding to each data item according to the four-tuple <α, θ, β, φ> corresponding to each data fluctuation of each data item in each data type in the multi-source data of the engineering project; Real-time monitoring of the phase difference of the dynamic phase corresponding to each data fluctuation of each data item in each data type in the multi-source data of the engineering project; comparing the phase difference of the dynamic phase with a dynamic phase difference trigger threshold corresponding to each data item; When the phase difference of the dynamic phase of each data item is not lower than the dynamic phase difference trigger threshold corresponding to each data item, re-collection of data of the data item is triggered.

4. The engineering consulting value list comprehensive evaluation system based on target data analysis according to claim 2 is characterized in that: Collect multi-source data for engineering projects, including: Real-time monitoring of the phase difference value of the dynamic phase corresponding to each data item when re-collecting data; Real-time monitoring of the data re-collection frequency of each data item; comparing a data recollection frequency of the data item with a preset data recollection frequency reference value; When the data recollection frequency of the data item exceeds a preset data recollection frequency reference value, retrieving a frequency excess rate of the data recollection frequency exceeding the preset data recollection frequency reference value; When the data re-collection frequency of the data item exceeds a preset data re-collection frequency reference value, taking the data item as a target data item; Retrieving a phase difference value of the dynamic phase corresponding to the target data item at each re-data collection; A phase excess rate according to which the phase difference value of the dynamic phase during each re-data collection exceeds the dynamic phase difference trigger threshold corresponding to the target data item; comparing the frequency excess rate and the phase excess rate corresponding to the target data item; When the frequency excess rate corresponding to the target data item exceeds the phase excess rate by an amplitude greater than a preset amplitude threshold, the frequency excess rate and the phase excess rate are used to compensate the dynamically adjusted dynamic phase difference trigger threshold corresponding to the target data item to obtain the compensated dynamic phase difference trigger threshold.

5. The engineering consulting value list comprehensive evaluation system based on target data analysis according to claim 1 is characterized in that: Also includes: a target setting module configured to set target data based on project requirements and assessment goals; According to the project requirements and assessment objectives, determine multiple dimensions and indicators of project assessment, including technical dimension, quality dimension, economic dimension, environmental dimension and social dimension of the project; Determine the target data for project evaluation based on the technical, quality, economic, environmental and social dimensions of the project; Among them, the technical dimension of engineering projects includes technical capabilities, design quality and risk management; the quality dimension of engineering projects includes service quality and process quality; the economic dimension of engineering projects includes cost-effectiveness and financial stability; the environmental dimension of engineering projects includes environmental impact and sustainability impact; and the social dimension of engineering projects includes customer satisfaction and social impact.

6. The engineering consulting value list comprehensive evaluation system based on target data analysis according to claim 1 is characterized in that: Preprocessing of multi-source data of engineering projects, including: Clean the multi-source data of engineering projects and remove the noise data that is useless for the comprehensive evaluation of the engineering consulting value list; Check the multi-source data of engineering projects, identify missing values ​​and outliers in the multi-source data of engineering projects, and process the identified missing values ​​and outliers in the multi-source data of engineering projects; The multi-source data of the engineering project is converted into a unified data format, the dimensional differences in the multi-source data of the engineering project are removed, and the standardized multi-source data of the engineering project is determined.

7. The engineering consulting value list comprehensive evaluation system based on target data analysis according to claim 1 is characterized in that: Extract engineering project characteristic data, including: Based on the principal component analysis method, feature vectors useful for the comprehensive evaluation of engineering consulting value lists are extracted from multi-source data of engineering projects. The extracted feature vectors are weighted and fused to determine the characteristic data of engineering projects, including the characteristics of the bill of quantities, cost data, schedule information and environmental impact data.

8. The engineering consulting value list comprehensive evaluation system based on target data analysis according to claim 1 is characterized in that: Also includes: A model building module configured to build a comprehensive evaluation model for an engineering consulting value list; According to the comprehensive evaluation requirements of the engineering consulting value list based on target data analysis, historical data of engineering projects are collected and divided into training sets and test sets; Based on deep learning technology, a training set is used to train the deep learning model, so that the deep learning model can autonomously learn the comprehensive evaluation behavior of the engineering consulting value list from the training set, and determine the comprehensive evaluation model of the engineering consulting value list based on target data analysis; The test set is used to test the comprehensive evaluation model of the engineering consulting value list based on target data analysis, evaluate the performance of the comprehensive evaluation model of the engineering consulting value list based on target data analysis, and determine whether the comprehensive evaluation model of the engineering consulting value list based on target data analysis can comprehensively evaluate the engineering consulting value list; According to the test evaluation results, the parameters of the comprehensive evaluation model of the engineering consulting value list based on target data analysis are adjusted and optimized to determine the best comprehensive evaluation model of the engineering consulting value list.

9. The engineering consulting value list comprehensive evaluation system based on target data analysis according to claim 8 is characterized in that: Analyze the characteristic data of engineering projects and comprehensively evaluate the engineering consulting value list, including: Deploy the best engineering consulting value list comprehensive evaluation model and deploy the best engineering consulting value list comprehensive evaluation model in the actual engineering consulting value list comprehensive evaluation environment based on target data analysis; Input the engineering project characteristic data into the comprehensive evaluation model of the engineering consulting value list, analyze the engineering project characteristic data according to the comprehensive evaluation model of the engineering consulting value list, and comprehensively evaluate the engineering consulting value list, determine the comprehensive evaluation results of the engineering consulting value list based on the target data analysis, and output the comprehensive evaluation results of the engineering consulting value list.

10. The engineering consulting value list comprehensive evaluation system based on target data analysis according to claim 9 is characterized in that: Output comprehensive evaluation results of engineering consulting value list, including: Obtain comprehensive evaluation results of the engineering consulting value list based on target data analysis, and output the comprehensive evaluation results of the engineering consulting value list in a visual form on the mobile terminal and display them to users. Users make decisions based on the comprehensive evaluation results of the engineering consulting value list and then manage the engineering projects.

Images