Engineering whole-process consultation collaborative decision system based on knowledge graph

Abstract

The application discloses an engineering whole-process consultation collaborative decision-making system based on a knowledge graph, relates to the technical field of engineering management, and comprises a data acquisition unit, a knowledge graph construction unit, a scheme generation unit, a risk analysis unit and a collaborative decision-making unit. The scheme generation unit is supported by the knowledge graph, fuses rule reasoning and case reasoning algorithms to generate a set of to-be-selected schemes, makes the schemes more suitable for engineering requirements and have scientific basis, and reduces subjective deviation of artificial decision-making. Meanwhile, the risk analysis unit calculates a risk index by using multi-dimensional risk data of cost deviation rate and progress delay rate, accurately screens low-risk schemes, effectively makes up for defects of insufficient risk prediction of a traditional mode, the collaborative decision-making unit calculates a collaborative decision-making index based on optimal data of investment valuation and quality of the engineering whole-process consultation scheme, quickly locks the optimal scheme, and combines visual comparison and real-time message pushing functions of the interactive display unit to shorten a decision-making cycle.

Description

Technical Field

[0001] This invention relates to the field of engineering management technology, and in particular to a knowledge graph-based collaborative decision-making system for the entire engineering process. Background Technology

[0002] Engineering whole-process consulting is a comprehensive consulting service that spans the entire lifecycle of engineering construction. It covers core aspects such as feasibility studies and planning and design in the early stages of a project, construction management, cost control, and quality supervision in the middle stages, and final acceptance, operation and maintenance support in the later stages. Its core value lies in providing integrated solutions for engineering construction by integrating resources from multiple disciplines and dimensions, helping construction units achieve their goals of improving quality and efficiency. In this process, massive amounts of multi-source heterogeneous data are continuously generated, from geological data and drawings in the survey and design stage, to progress reports, material ledgers, and safety monitoring data in the construction stage, and to equipment operation records and fault repair information in the operation and maintenance stage. This data includes structured cost accounting tables, as well as unstructured engineering drawings, contract texts, and semi-structured progress reports, which form the core foundation supporting consulting decisions.

[0003] However, the traditional engineering whole-process consulting model relies too much on manual data sorting and analysis, and lacks an efficient data integration and knowledge management mechanism. This not only leads to low data processing efficiency, but also often results in missing or biased decision-making information due to scattered data storage and inconsistent formats. At the same time, there are obvious knowledge barriers between different disciplines, making it difficult to achieve collaborative linkage, which prolongs the decision-making cycle and leads to insufficient risk prediction.

[0004] To address the aforementioned technical deficiencies, a solution is proposed. Summary of the Invention

[0005] The purpose of this invention is to address the problems of traditional engineering whole-process consulting models that rely excessively on manual data collection and analysis, lack efficient data integration and knowledge management mechanisms, resulting in low data processing efficiency, and often leading to missing or biased decision-making information due to scattered data storage and inconsistent formats. At the same time, there are obvious knowledge barriers between different professions, making it difficult to achieve collaborative linkage, which in turn prolongs the decision-making cycle and results in insufficient risk prediction.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a knowledge graph-based collaborative decision-making system for the entire engineering process, comprising a data acquisition unit, a knowledge graph construction unit, a solution generation unit, a risk analysis unit, and a collaborative decision-making unit;

[0007] The data acquisition unit is used to collect multi-source heterogeneous data throughout the entire project process. Through data preprocessing technology, the multi-source heterogeneous data is transformed into standardized data, and the standardized data is sent to the knowledge graph construction unit.

[0008] The knowledge graph construction unit is used to receive standardized data collected by the data acquisition unit and constructs a knowledge graph in the engineering field through three steps: knowledge extraction, knowledge fusion, and knowledge storage.

[0009] The solution generation unit uses the engineering domain knowledge graph constructed by the knowledge graph building unit as the core support, combined with the engineering requirements input by the user through the interactive display unit, and uses an algorithm based on rule-based reasoning and case-based reasoning to generate and integrate a set of full-process consulting solutions for candidate projects.

[0010] The risk analysis unit is used to conduct risk assessment on the generated engineering whole-process consulting plan, obtain risk data, perform analysis and calculation, derive the implementation risk index of the engineering whole-process consulting plan, and classify the engineering whole-process consulting plan into high-risk plan and low-risk plan.

[0011] The collaborative decision-making unit is used to analyze low-risk solutions, obtain optimal data for low-risk solutions, perform analysis and calculation, derive the collaborative decision-making index of low-risk solutions, and select the optimal engineering whole-process consulting solution.

[0012] Furthermore, the system also includes an interactive display unit, which is used to display an interface through a terminal, supporting the visualization of knowledge graphs in the engineering field, comparison of decision-making schemes, and real-time message push.

[0013] Furthermore, the multi-source heterogeneous data includes data from full-process engineering project management, as well as investment consulting, feasibility study consulting, surveying, design, cost consulting, bidding agency, supervision, and operation and maintenance consulting.

[0014] Furthermore, the data preprocessing technology processes multi-source heterogeneous data as follows: invalid data is removed using outlier detection algorithms, redundant information is removed using data cleaning tools, and different types of data are uniformly converted into standard formats for standardized encapsulation using format conversion technology to form standardized data, providing a high-quality data source for knowledge graph construction.

[0015] Furthermore, the knowledge extraction employs a BERT-based named entity recognition algorithm to extract engineering entities from standardized data, utilizes a dependency parsing algorithm to extract relationships between entities, and simultaneously extracts entity attributes to form triplet data and entity-attribute pairs. The knowledge fusion eliminates ambiguity between synonymous entities through an entity alignment algorithm, integrates multi-source attribute information of the same entity using attribute fusion rules, removes duplicate triples, and forms a unified knowledge dataset. The knowledge storage uses the graph database Neo4j to store the processed knowledge data, constructing an engineering domain knowledge graph to provide knowledge support for solution generation, risk analysis, and collaborative decision-making.

[0016] Furthermore, the risk data includes the cost deviation rate of the whole-process consulting solution, the schedule delay rate of the whole-process consulting solution, the quality non-compliance rate of the whole-process consulting solution, and the feasibility value data of the whole-process consulting solution. The preferred data includes the investment valuation of the whole-process consulting solution of the low-risk solution and the quality non-compliance rate data of the low-risk solution.

[0017] Furthermore, the calculation process for the implementation risk index of the whole-process engineering consulting solution is as follows:

[0018] S11. Obtain and analyze the cost deviation rate, schedule delay rate, quality non-compliance rate, and feasibility data of the whole-process consulting solution.

[0019] S12. Calculate the implementation risk index of the whole-process consulting solution for engineering according to the following formula. : in, The feasible value for the whole-process consulting solution, This represents the maximum feasible value among all historical consultation proposals. This represents the minimum feasible value among all historical consultation solutions. The cost deviation rate of the whole-process consulting solution. This represents the maximum allowable cost deviation rate for a pre-defined engineering whole-process consulting solution. The schedule delay rate for the whole-process consulting solution. This represents the average schedule delay rate for the entire consulting solution for historical engineering projects. The standard schedule delay rate that can be allowed under the pre-set engineering whole-process consulting plan;

[0020] S13. Obtain the preset implementation risk threshold. Risk index of the implementation of the whole-process consulting solution for engineering Comparative analysis, when If the implementation of the full-process engineering consulting solution is deemed to be of high risk, it will be classified as a high-risk solution and removed from the pool of candidate full-process engineering consulting solutions.

[0021] S14, when If the risk of implementation of the whole-process consulting solution is low, it is classified as a low-risk solution. The low-risk solution will be retained in the pool of candidate whole-process consulting solutions and analyzed further.

[0022] Furthermore, the calculation process for the collaborative decision-making index of low-risk solutions is as follows:

[0023] S21. Obtain the investment valuation of the engineering whole-process consulting plan for low-risk solutions and the quality non-compliance rate data of low-risk solutions, and perform analysis and calculation.

[0024] S22. Calculate the collaborative decision-making index of low-risk solutions using the following formula. : in, The risk index for implementing low-risk solutions. The preset implementation risk threshold, Investment valuation for a low-risk, full-process engineering consulting solution. The standard engineering cost for a pre-designed full-process engineering consulting solution. The quality non-compliance rate of low-risk solutions. The average quality non-conformity rate in the low-risk scheme. The preset cost weighting coefficient, These are preset quality weighting coefficients;

[0025] S23, Collaborative Decision-Making Index for Multiple Low-Risk Options Sort and select The solution with the highest value is selected as the optimal engineering whole-process consulting solution and output to the interactive display unit.

[0026] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0027] This knowledge graph-based collaborative decision-making system for the entire engineering process integrates multi-source heterogeneous data from the entire engineering lifecycle through a data acquisition unit. Combined with preprocessing techniques such as outlier detection, data cleaning, and XML format standardization, it effectively solves the problems of scattered data storage and inconsistent formats in traditional models, significantly improving data processing efficiency and providing high-quality data sources for decision-making, avoiding information loss or bias caused by data clutter. Secondly, the knowledge graph construction unit uses BERT model named entity recognition, dependency parsing, and other techniques to extract knowledge, eliminates ambiguity through entity alignment, and relies on Neo4j... The system stores and constructs a unified knowledge graph for the engineering field, breaking down knowledge barriers between different disciplines and enabling the integration and sharing of multi-dimensional knowledge, laying the foundation for cross-disciplinary collaboration. Furthermore, the solution generation unit, supported by the knowledge graph, integrates rule-based reasoning and case-based reasoning algorithms to generate a set of candidate solutions, making the solutions more aligned with engineering needs and scientifically grounded, reducing the subjective bias of human decision-making. Simultaneously, the risk analysis unit calculates and implements a risk index using multi-dimensional risk data such as cost deviation rate and schedule delay rate, accurately screening low-risk solutions and effectively compensating for the shortcomings of traditional risk prediction models. In addition, the collaborative decision-making unit calculates a collaborative decision-making index based on cost and quality optimization data, quickly identifying the optimal solution. Combined with the interactive display unit's visual comparison and real-time message push functions, this promotes efficient communication among all participants and shortens the decision-making cycle. Attached Figure Description

[0028] Figure 1 A schematic diagram of the system flow of the present invention is shown. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] Example:

[0031] like Figure 1 As shown, the knowledge graph-based collaborative decision-making system for the entire engineering process first collects multi-source heterogeneous data from the entire engineering process through the data acquisition unit. Then, through data preprocessing technology, the multi-source heterogeneous data is transformed into standardized data, and the standardized data is sent to the knowledge graph construction unit.

[0032] Multi-source heterogeneous data includes data from the entire process of engineering project management, as well as investment consulting, feasibility study consulting, surveying, design, cost consulting, bidding agency, supervision, and operation and maintenance consulting. The sources of multi-source heterogeneous data cover the terminals of engineering participants, sensor equipment, industry databases, and literature databases.

[0033] The process of data preprocessing technology for processing multi-source heterogeneous data is as follows: invalid data is removed by using outlier detection algorithms (such as those based on the 3σ criterion), redundant information is removed by using data cleaning tools, and different types of data are uniformly converted into standard formats (including but not limited to XML format) for standardized encapsulation to form standardized data, providing a high-quality data source for knowledge graph construction.

[0034] Then, the standardized data collected by the data collection unit is received by the knowledge graph construction unit, and the knowledge graph of the engineering field is constructed through three steps: knowledge extraction, knowledge fusion and knowledge storage.

[0035] Knowledge extraction employs a BERT-based named entity recognition algorithm to extract engineering entities (such as construction procedures, material types, and equipment models) from standardized data. Dependency parsing algorithms are used to extract relationships between entities (such as "construction procedure - required materials" and "equipment model - applicable scenarios"), while entity attributes (such as material strength and equipment power) are also extracted, forming triplet data (entity 1, relation, entity 2) and entity-attribute pairs. Knowledge fusion uses entity alignment algorithms (such as cosine similarity-based string matching) to eliminate ambiguity between synonymous entities and attribute fusion rules to integrate multi-source attribute information of the same entity, removing duplicate triples to form a unified knowledge dataset. Knowledge storage uses the Neo4j graph database to store the processed knowledge data, constructing an engineering domain knowledge graph to provide knowledge support for solution generation, risk analysis, and collaborative decision-making.

[0036] Next, the solution generation unit uses the engineering domain knowledge graph constructed by the knowledge graph construction unit as its core support, combined with the engineering requirements (such as project scale, construction period, and cost budget) input by the user through the interactive display unit. An algorithm combining rule-based reasoning and case-based reasoning is then used to generate and integrate a set of candidate full-process engineering consulting solutions. Rule-based reasoning builds a reasoning rule base based on engineering specification knowledge (such as "concrete pouring-curing time ≥ 7 days") in the engineering domain knowledge graph, while case-based reasoning matches similar cases from engineering cases in the engineering domain knowledge graph. The combined results output an initial full-process engineering consulting solution including construction process, material list, equipment configuration, and schedule.

[0037] Subsequently, the risk analysis unit conducts a risk assessment on the generated engineering whole-process consulting plan to obtain risk data, including the cost deviation rate, schedule delay rate, quality non-compliance rate, and feasibility data of the whole-process consulting plan. The data is then analyzed and calculated to obtain the implementation risk index of the engineering whole-process consulting plan, and the engineering whole-process consulting plan is divided into high-risk and low-risk plans.

[0038] The calculation process for the implementation risk index of the whole-process engineering consulting solution is as follows:

[0039] S11. Obtain and analyze the cost deviation rate, schedule delay rate, quality non-compliance rate, and feasibility data of the whole-process consulting solution.

[0040] S12. Calculate the implementation risk index of the whole-process consulting solution for engineering according to the following formula. : in, The feasibility value of the whole-process consulting solution is obtained through a comprehensive evaluation of the solution using a scale. The higher the feasibility value, the more feasible the whole-process consulting solution is. This represents the maximum feasible value among all historical consultation proposals. This represents the minimum feasible value among all historical consultation solutions. The cost deviation rate of the whole-process consulting solution. This represents the maximum allowable cost deviation rate for a pre-defined engineering whole-process consulting solution. The schedule delay rate for the whole-process consulting solution. This represents the average schedule delay rate for the entire consulting solution for historical engineering projects. The standard schedule delay rate that can be allowed under the pre-set engineering whole-process consulting plan;

[0041] S13. Obtain the preset implementation risk threshold. Risk index of the implementation of the whole-process consulting solution for engineering Comparative analysis, when If the implementation of the full-process engineering consulting solution is deemed to be of high risk, it will be classified as a high-risk solution and removed from the pool of candidate full-process engineering consulting solutions.

[0042] S14, when If the risk of implementation of the whole-process consulting solution is low, it is classified as a low-risk solution. The low-risk solution will be retained in the pool of candidate whole-process consulting solutions and analyzed further.

[0043] Finally, the low-risk solutions are analyzed by the collaborative decision-making unit to obtain the optimal data for the low-risk solutions. The optimal data includes the investment valuation of the engineering whole-process consulting solution of the low-risk solution and the quality non-compliance rate data of the low-risk solution. The collaborative decision-making index of the low-risk solution is obtained through analysis and calculation, and the optimal engineering whole-process consulting solution is selected. It should be noted that the risk data and the optimal data are obtained through the correlation between the solution and historical engineering data in the engineering domain knowledge graph.

[0044] The calculation process for the collaborative decision-making index of low-risk solutions is as follows:

[0045] S21. Obtain the investment valuation of the engineering whole-process consulting plan for low-risk solutions and the quality non-compliance rate data of low-risk solutions, and perform analysis and calculation.

[0046] S22. Calculate the collaborative decision-making index of low-risk solutions using the following formula. : in, The risk index for implementing low-risk solutions. The preset implementation risk threshold, Investment valuation for a low-risk, full-process engineering consulting solution. The standard engineering cost for a pre-designed full-process engineering consulting solution. The quality non-compliance rate of low-risk solutions. The average quality non-conformity rate in the low-risk scheme. The preset cost weighting coefficient, These are preset quality weighting coefficients;

[0047] S23, Collaborative Decision-Making Index for Multiple Low-Risk Options Sort and select The solution with the highest value is selected as the optimal full-process engineering consulting solution and output to the interactive display unit. The interactive display unit, through a terminal interface, supports visualization of the engineering domain knowledge graph, comparison of decision-making solutions, and real-time message push. Specifically, the engineering domain knowledge graph visualization uses a force-directed layout algorithm to display the engineering domain knowledge graph, supporting entity queries, relationship tracing, and graph scaling and rotation. The decision-making solution comparison displays the risk index, collaborative decision-making index, and various sub-indicators of different solutions in table and line chart formats, supporting horizontal comparison of solutions. Real-time message push pushes solution updates, risk warnings, and decision results information to the terminals of all engineering participants, supporting online comments and feedback from multiple participants to achieve collaborative interaction.

[0048] This invention integrates multi-source heterogeneous data from the entire project lifecycle through a data acquisition unit. Combined with preprocessing techniques such as outlier detection, data cleaning, and XML format standardization, it effectively solves the problems of scattered data storage and inconsistent formats in traditional models, significantly improving data processing efficiency and providing a high-quality data source for decision-making, avoiding the loss or bias of decision information due to data clutter. Secondly, the knowledge graph construction unit uses BERT model named entity recognition, dependency parsing, and other techniques to extract knowledge, eliminating ambiguity through entity alignment and relying on Neo4j... The system stores and constructs a unified knowledge graph for the engineering field, breaking down knowledge barriers between different disciplines and enabling the integration and sharing of multi-dimensional knowledge, laying the foundation for cross-disciplinary collaboration. Furthermore, the solution generation unit, supported by the knowledge graph, integrates rule-based reasoning and case-based reasoning algorithms to generate a set of candidate solutions, making the solutions more aligned with engineering needs and scientifically grounded, reducing the subjective bias of human decision-making. Simultaneously, the risk analysis unit calculates and implements a risk index using multi-dimensional risk data such as cost deviation rate and schedule delay rate, accurately screening low-risk solutions and effectively compensating for the shortcomings of traditional risk prediction models. In addition, the collaborative decision-making unit calculates a collaborative decision-making index based on cost and quality optimization data, quickly identifying the optimal solution. Combined with the interactive display unit's visual comparison and real-time message push functions, this promotes efficient communication among all participants and shortens the decision-making cycle.

[0049] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value.

[0050] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0051] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A knowledge graph-based collaborative decision-making system for the entire engineering process, characterized in that: It includes a data acquisition unit, a knowledge graph construction unit, a solution generation unit, a risk analysis unit, and a collaborative decision-making unit; The data acquisition unit is used to collect multi-source heterogeneous data throughout the entire project process. Through data preprocessing technology, the multi-source heterogeneous data is transformed into standardized data, and the standardized data is sent to the knowledge graph construction unit. The knowledge graph construction unit is used to receive standardized data collected by the data acquisition unit and constructs a knowledge graph in the engineering field through three steps: knowledge extraction, knowledge fusion, and knowledge storage. The solution generation unit uses the engineering domain knowledge graph constructed by the knowledge graph building unit as the core support, combined with the engineering requirements input by the user through the interactive display unit, and uses an algorithm based on rule-based reasoning and case-based reasoning to generate and integrate a set of full-process consulting solutions for candidate projects. The risk analysis unit is used to conduct risk assessment on the generated engineering whole-process consulting plan, obtain risk data, perform analysis and calculation, derive the implementation risk index of the engineering whole-process consulting plan, and classify the engineering whole-process consulting plan into high-risk plan and low-risk plan. The collaborative decision-making unit is used to analyze low-risk solutions, obtain optimal data for low-risk solutions, perform analysis and calculation, derive the collaborative decision-making index of low-risk solutions, and select the optimal engineering whole-process consulting solution.

2. The knowledge graph-based collaborative decision-making system for the entire engineering process as described in claim 1, characterized in that, The system also includes an interactive display unit, which is used to display an interface through a terminal, supporting the visualization of knowledge graphs in the engineering field, comparison of decision-making schemes, and real-time message push.

3. The knowledge graph-based collaborative decision-making system for the entire engineering process as described in claim 1, characterized in that, The multi-source heterogeneous data includes data from full-process engineering project management, as well as investment consulting, feasibility study consulting, surveying, design, cost consulting, bidding agency, supervision, and operation and maintenance consulting.

4. The knowledge graph-based collaborative decision-making system for the entire engineering process as described in claim 1, characterized in that, The data preprocessing technology processes multi-source heterogeneous data as follows: outlier detection algorithms are used to remove invalid data, data cleaning tools are used to remove redundant information, and format conversion technology is used to convert different types of data into a standard format for standardized encapsulation, forming standardized data, which provides a high-quality data source for knowledge graph construction.

5. The knowledge graph-based collaborative decision-making system for the entire engineering process as described in claim 1, characterized in that, The knowledge extraction employs a BERT-based named entity recognition algorithm to extract engineering entities from standardized data, and a dependency parsing algorithm to extract relationships between entities. Simultaneously, entity attributes are extracted to form triplet data and entity-attribute pairs. The knowledge fusion eliminates ambiguity between synonymous entities through an entity alignment algorithm, integrates multi-source attribute information of the same entity using attribute fusion rules, removes duplicate triples, and forms a unified knowledge dataset. The knowledge storage uses the Neo4j graph database to store the processed knowledge data, constructing an engineering domain knowledge graph to provide knowledge support for solution generation, risk analysis, and collaborative decision-making.

6. The knowledge graph-based collaborative decision-making system for the entire engineering process as described in claim 1, characterized in that, The risk data includes the cost deviation rate of the whole-process engineering consulting solution, the schedule delay rate of the whole-process engineering consulting solution, the quality non-compliance rate of the whole-process engineering consulting solution, and the feasibility value data of the whole-process consulting solution. The preferred data includes the investment valuation of the whole-process engineering consulting solution of the low-risk solution and the quality non-compliance rate data of the low-risk solution.

7. The knowledge graph-based collaborative decision-making system for the entire engineering process as described in claim 1, characterized in that, The calculation process for the implementation risk index of the whole-process engineering consulting solution is as follows: S11. Obtain and analyze the cost deviation rate, schedule delay rate, quality non-compliance rate, and feasibility data of the whole-process consulting solution. S12. Calculate the implementation risk index of the whole-process consulting solution for engineering according to the following formula. : ; in, The feasible value for the whole-process consulting solution, This represents the maximum feasible value among all historical consultation proposals. This represents the minimum feasible value among all historical consultation solutions. The cost deviation rate of the whole-process consulting solution. This represents the maximum allowable cost deviation rate for a pre-defined engineering whole-process consulting solution. The schedule delay rate for the whole-process consulting solution. This represents the average schedule delay rate for the entire consulting solution for historical engineering projects. The standard schedule delay rate that can be allowed under the pre-set engineering whole-process consulting plan; S13. Obtain the preset implementation risk threshold. Risk index of the implementation of the whole-process consulting solution for engineering Comparative analysis, when If the implementation of the full-process engineering consulting solution is deemed to be of high risk, it will be classified as a high-risk solution and removed from the pool of candidate full-process engineering consulting solutions. S14, when If the risk of implementation of the whole-process consulting solution is low, it is classified as a low-risk solution. The low-risk solution will be retained in the pool of candidate whole-process consulting solutions and analyzed further.

8. The knowledge graph-based collaborative decision-making system for the entire engineering process as described in claim 1, characterized in that, The calculation process for the collaborative decision-making index of low-risk solutions is as follows: S21. Obtain the investment valuation of the engineering whole-process consulting plan for low-risk solutions and the quality non-compliance rate data of low-risk solutions, and perform analysis and calculation. S22. Calculate the collaborative decision-making index of low-risk solutions using the following formula. : ; in, The risk index for implementing low-risk solutions. The preset implementation risk threshold, Investment valuation for a low-risk, full-process engineering consulting solution. The standard engineering cost for a pre-designed full-process engineering consulting solution. The quality non-compliance rate of low-risk solutions. The average quality non-conformity rate in the low-risk scheme. The preset cost weighting coefficient, These are preset quality weighting coefficients; S23, Collaborative Decision-Making Index for Multiple Low-Risk Options Sort and select The solution with the highest value is selected as the optimal engineering whole-process consulting solution and output to the interactive display unit.

Images