Intelligent examination and approval management method for housing and construction industry

Abstract

The invention discloses an intelligent examination and approval management method for the housing and construction industry, and the method comprises the steps: collecting examination and approval application data, carrying out the data cleaning, data deduplication and data standardization operation of the examination and approval application data, and obtaining preprocessed data; constructing a data classification model based on a machine learning algorithm, and performing material classification on the preprocessed data by using the data classification model to obtain a material classification result; according to a material classification result, performing primary processing and risk assessment on the preprocessed data by using an intelligent auditing system to obtain a risk score; performing secondary processing on the pre-processed data by using an expert system to obtain a personalized approval scheme; and examining and approving the preprocessed data according to the personalized examination and approval scheme, and storing the risk score and the examination and approval result to an intelligent examination and approval system. The invention relates to the technical field of examination and approval management, and solves the technical problems of low data quality, lack of flexibility and intelligence and the like of an existing residence construction examination and approval system.

Description

Technical Field

[0001] The present invention belongs to the field of data management in the construction and housing industry, relates to approval management technology, and specifically is an intelligent approval management method for the construction and housing industry. Background Art

[0002] Approval in the construction and housing industry is crucial for ensuring the quality and safety of construction projects, safeguarding public interests, and the orderly development of cities. From project planning to construction, and then to completion acceptance, the approval of each link is directly related to whether the building meets safety standards, complies with urban planning requirements, and has no adverse impact on the surrounding environment and residents' lives. However, the approval process in the construction and housing industry is extremely complex, covering the review of various materials such as construction project plans, design drawings, and construction plans, involving knowledge in many professional fields and various types of data, including filled-in text structured materials, as well as unstructured data such as drawings, videos, and data files.

[0003] In the existing construction and housing approval methods, there are many deficiencies. On the one hand, the data quality relied on by the system is not high. There may be missing, incorrect, or inconsistent information in the data, which will directly affect the subsequent risk assessment results, leading to assessment deviations, unable to accurately judge the potential risks of projects, and leaving safety hazards for construction projects. On the other hand, for special or complex projects, such as super high-rise buildings, cultural heritage renovations, etc., the system lacks the ability to generate personalized approval plans, and the approval process is rigid, unable to dynamically adjust the decision-making logic according to user feedback. For example, when encountering special projects involving special geographical locations, complex environmental impact assessment results, etc., it is difficult to conduct targeted reviews based on the unique circumstances of the project, and only conventional standards can be applied, which may lead to unreasonable approval results, unable to ensure the smooth progress of the project and fully meet the management needs in special situations. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; for this purpose, the present invention proposes an intelligent approval management method for the construction and housing industry to solve technical problems such as low data quality, lack of flexibility and intelligence in the existing construction and housing approval system. The present invention improves data quality through data cleaning, deduplication, and standardization operations; conducts risk assessment and analysis using a risk assessment model; introduces an expert system for complex or special situations, and adopts an interactive mode design to dynamically adjust the decision-making logic according to user feedback, realizing full-process sharing and timely feedback of approval information, and solving the above problems.

[0005] To achieve the above object, the present invention provides an intelligent approval management method for the construction and housing industry, including:

[0006] S1. Collect the approval application materials, and perform data cleaning, data deduplication, and data standardization operations on the approval application materials to obtain preprocessed data;

[0007] S2. Build a data classification model based on machine learning algorithms, and use the data classification model to classify the preprocessed data to obtain a material classification result;

[0008] S3. According to the material classification result, use the intelligent review system to perform preliminary processing and risk assessment on the preprocessed data to obtain a risk score;

[0009] S4. Use the expert system to perform secondary processing on the preprocessed data to obtain a personalized approval plan;

[0010] S5. Approve the preprocessed data according to the personalized approval plan, and store the risk score and approval result in the intelligent review system.

[0011] Furthermore, the approval application materials include: the planning report, design drawings, construction plan of the construction project, as well as relevant legal documents and certification materials, and the approval application materials are stored in the database of the intelligent review system.

[0012] Furthermore, the data cleaning includes:

[0013] According to the formula Calculate the mean value of numerical data

[0014] Use the mean value Replace the missing value X in the numerical data i ; where X j represents the jth numerical data, and n represents the number of numerical data;

[0015] Manually process the missing values of non-numerical data.

[0016] Furthermore, the data deduplication includes:

[0017] S11. Initialize an empty hash table hash_table;

[0018] S12. Traverse the original data set data, and calculate the hash value hash_value = hash_function(data[i]) of each data record data[i];

[0019] S13. Determine whether there is an entry with a hash value of hash_value in the hash table hash_table; if yes, jump to S14; if no, insert hash_value into the hash table hash_table and retain the corresponding data record data[i];

[0020] S14, determine whether the data data[i] is equal to the data record at the corresponding position in the hash table hash_table; if so, it means duplication and skip this record; if not, create a new linked list node, store data[i] in the linked list node, and insert the linked list node into the head of the linked list corresponding to hash_value.

[0021] Through data cleaning operations, review and organize the input data to identify and correct any missing, incorrect or inconsistent information. At the same time, perform data deduplication to avoid interference from duplicate data in subsequent processing. Finally, perform data standardization to unify the data format and specifications to ensure data consistency.

[0022] Furthermore, constructing the data classification model based on the machine learning algorithm includes:

[0023] Collect a number of approval materials, convert the unstructured data in the approval materials into structured data, and perform feature extraction and vectorization processing to obtain preprocessed data;

[0024] Use the machine learning algorithm to train the preprocessed data, and obtain an optimized data classification model through cross-validation and hyperparameter tuning;

[0025] Deploy the data classification model to the intelligent audit system for automatically classifying approval materials.

[0026] Furthermore, the preliminary processing of the preprocessed data using the intelligent audit system includes:

[0027] Obtain the drawing data in the preprocessed data according to the material classification result, parse the drawing data to obtain structured data;

[0028] Perform preliminary processing on the structured data and other data in the preprocessed data according to the preset rule library, check the file type, file quantity, file format and file content, and obtain the preliminary processing result.

[0029] Furthermore, the risk assessment includes:

[0030] S31, determine whether the preliminary processing result is qualified; if so, jump to S32; if not, send an abnormal information of the approval application materials;

[0031] S32, use the pre-trained risk assessment model to perform risk assessment on the structured data to obtain the risk assessment result; among them, the pre-trained risk assessment model is constructed based on the probability statistical model, and the risk assessment result includes risk points and risk scores;

[0032] S33. Display the risk assessment results in the form of visual charts.

[0033] Furthermore, the secondary processing of the preprocessed data using the expert system includes:

[0034] Collect a number of laws, regulations, industry standards, and historical case data to construct an expert knowledge base; among them, the expert knowledge base will be updated periodically;

[0035] Judge whether the current construction project is a special case based on the geographical location and environmental data of the construction project; if so, use the interactive mode to perform secondary processing on the preprocessed data; if not, complete the approval.

[0036] Furthermore, the secondary processing of the preprocessed data using the interactive mode includes:

[0037] Start the interactive mode of the expert system through specific functions or specific commands;

[0038] Use text, voice, or graphical interfaces to guide users to provide information, and collect the input information of users to obtain user input;

[0039] Infer and analyze the user input based on the expert knowledge base and rule engine technology to obtain a recommended approval plan;

[0040] Push the recommended approval plan to the user and collect user feedback;

[0041] Confirm the final approval plan according to the user feedback to obtain a personalized approval plan, and give the logic and reasons for the personalized approval plan.

[0042] Furthermore, the intelligent review system includes:

[0043] Database management module: used to store approval application materials, risk scores, and approval results;

[0044] Approval record module: used to record decision points and approval results during the approval process;

[0045] Log record module: used to record the operation logs of the intelligent review system;

[0046] Notification and feedback module: used to notify users of the preliminary processing results and approval results, and receive feedback from users;

[0047] Permission control module: used to manage user roles and permissions.

[0048] Compared with the prior art, the beneficial effects of the present invention are:

[0049] Through data cleaning, deduplication, and standardization operations, the present invention can ensure data quality, and then perform automatic review and risk assessment analysis. Moreover, for special cases, an expert system can be introduced to assist in decision-making and provide personalized approval solutions to meet the requirements in different situations;

[0050] In data preprocessing, the mean filling algorithm and the deduplication algorithm based on hashing are adopted, which simplifies the data processing steps and improves the processing efficiency; The expert system incorporates an interactive mode design, enabling more in-depth communication and feedback with users, further optimizing the approval process, and ensuring the accuracy and rationality of the final approval result. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a schematic diagram of the technical process of an intelligent approval management method for the construction industry provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0054] Please refer to Figure 1 , the first aspect embodiment of the present invention provides an intelligent approval management method for the construction industry, including:

[0055] S1, collect approval application materials, and perform data cleaning, data deduplication, and data standardization operations on the approval application materials to obtain preprocessed data;

[0056] Among them, the approval application materials include, but are not limited to: the planning report, design drawings, construction plan of the construction project, as well as relevant legal documents and certification materials; Then, the approval application materials are preliminarily electronically processed and entered into the system database to ensure that all materials are accurately entered into the system;

[0057] In one implementation, when performing step S1, the following steps can be adopted for data cleaning operations:

[0058] For numerical data, use the mean filling method to handle its missing values:

[0059] According to the formula calculate the mean value of numerical data and then replace the missing values with this mean value; where, X i represents the i-th missing observation value in the numerical data, X j represents the value in the j-th variable column, and n represents the number of data in the variable column;

[0060] For non-numerical data, sort it manually or by other algorithms to supplement its missing values.

[0061] In one implementation, when performing step S1, the following steps can be used to perform data deduplication:

[0062] Initialize an empty hash table hash_table;

[0063] Traverse the original data set data;

[0064] For each data record data[i], calculate its hash value hash_value = hash_function(data[i]);

[0065] Check whether there is an entry with the hash value hash_value in the hash table hash_table;

[0066] If the hash value does not exist in the hash table, insert hash_value into the hash table and retain the corresponding data record data[i];

[0067] If the hash value already exists in the hash table, determine whether data[i] is equal to the data record at the corresponding position in the hash table; if they are equal, it means duplication, skip this record; if they are not equal, create a new linked list node, store data[i] in the linked list node, and insert the linked list node into the head of the linked list corresponding to hash_value.

[0068] In one implementation, when performing step S1, the following steps can be used to standardize the data:

[0069] Unify the data format, date format, and units;

[0070] Convert all data to the same encoding, UTF-8;

[0071] For text data, perform case conversion and punctuation removal.

[0072] S2. Based on the machine learning algorithm, construct a data classification model, and use the data classification model to classify the preprocessed data to obtain the material classification result;

[0073] In one implementation, when performing step S2, the following steps can be adopted to construct a data classification model:

[0074] Collect a number of approval materials, convert the unstructured data in the approval materials into structured data, and perform feature extraction and vectorization processing to obtain preprocessed data;

[0075] Use machine learning algorithms to train the preprocessed data, and obtain an optimized data classification model through cross-validation and hyperparameter tuning;

[0076] Deploy the data classification model to the intelligent review system for automatically classifying approval materials; among them, the classification results include but are not limited to planning reports, design drawings, construction plans, and relevant legal documents and supporting materials.

[0077] S3. According to the material classification results, use the intelligent review system to perform preliminary processing and risk assessment on the preprocessed data to obtain a risk score;

[0078] The data classification model will classify the approval application materials to obtain the category to which each material belongs, and then use the intelligent review system to perform a preliminary review on the preprocessed data according to the material category;

[0079] In one implementation, when performing step S3, the following operating steps can be adopted for preliminary processing:

[0080] Obtain the drawing data in the preprocessed data according to the material classification results, and based on the drawing large model of the Pangu large model, parse the drawing data to convert the unstructured design drawings into structured building structure descriptions to obtain structured data;

[0081] Then, according to the preset rule library, perform preliminary processing on the structured data and other data in the preprocessed data, check whether the file type, file quantity, file format, and file content meet the requirements in the preset rule library. If they meet the requirements, further risk assessment will be carried out; if they do not meet the requirements, the intelligent review system's notification and feedback module will be used to feedback abnormal information of the approval application materials to the user.

[0082] As a further solution of this embodiment: during the preliminary review process, the system will, according to the material classification results, identify the drawing frames in the design drawings or construction plans, and parse the drawing attributes, such as drawing names, drawing numbers, etc. from the title block; understand the layout of the drawing frame content, including all sub-drawings, tables, and text paragraphs; establish cross-drawing frame associations, such as detail drawing indexes;

[0083] Then, based on the preset rule library, the system automatically detects whether the materials meet the specified requirements, including dimension specifications and safety standards, etc.

[0084] In one implementation, when performing step S3, the following operating steps can be adopted for risk assessment:

[0085] Use a pre-trained risk assessment model to perform risk assessment on structured data to obtain a risk assessment result; among them, the pre-trained risk assessment model is constructed based on a probability statistical model, and the risk assessment result includes risk points and risk scores that may exist in the design drawings and construction plans;

[0086] Display the risk assessment result in the form of a visual chart, clearly indicating possible risk points and recommended preventive measures.

[0087] S4. Use an expert system to perform secondary processing on the preprocessed data to obtain a personalized approval plan;

[0088] In one implementation, before performing step S4, the following steps are required to determine whether to start the expert system:

[0089] Formulate special situation determination rules based on the geographical location and environmental data of the construction project, and then judge whether the current project belongs to a special situation according to the determination rules. In the expert knowledge base, the processing procedures and precautions for each special situation are collected and sorted to ensure that all possible problems are properly handled;

[0090] Among them, the expert knowledge base also contains several data such as laws and regulations, industry standards, and historical cases.

[0091] When the determination rules judge that the construction project to which the current approval application materials belong belongs to a special situation, introduce an expert system for auxiliary decision-making and secondary processing.

[0092] In one implementation, the expert system in step S4 adopts an interactive mode to perform secondary processing on the preprocessed approval application materials, specifically including the following steps:

[0093] Start the interactive mode of the expert system through a specific function or specific command;

[0094] Use text, voice, or graphical interfaces to guide users to provide information, and collect the input information of users to obtain user input;

[0095] Infer and analyze the user input based on the expert knowledge base and rule engine technology to obtain a recommended approval plan;

[0096] Push the recommended approval plan to the user and collect user feedback;

[0097] Confirm the final approval plan according to the user feedback to obtain a personalized approval plan, and give the logic and reasons for the personalized approval plan.

[0098] The following gives an example to illustrate the processing process of the expert system:

[0099] Suppose that during the approval process in the construction and housing industry, a construction project is located in a special geographical location prone to earthquakes, which is a special situation that requires the activation of a special approval process. At this time, an expert system is introduced to assist in decision-making and processing:

[0100] Step 1. Activate the interactive mode: The intelligent review system detects through optical character recognition that the project is in an earthquake-prone area and automatically triggers the interactive mode, or the reviewer manually activates this mode to interact with the expert system;

[0101] Step 2. System guidance: Through means such as text prompts, voice prompts, and graphical interface guidance, inform the reviewer of the special geographical location of the current project, and prompt the reviewer to provide relevant information such as the seismic design standards of the project and the geological exploration report. At the same time, explain the subsequent interaction process and possible results, such as professional advice and approval opinions on the earthquake resistance of the project;

[0102] Step 3. User input: The reviewer uploads materials such as the seismic design standards of the project and a detailed geological exploration report to the system according to the system prompts. These information will be used as the basis for the expert system's reasoning;

[0103] Step 4. System reasoning: After receiving the information input by the reviewer, the expert system uses the earthquake-related regulations, historical earthquake disaster cases, and professional knowledge and rules of seismic design in its knowledge base to reason and analyze the project materials. For example, according to information such as soil type and earthquake activity frequency in the geological exploration report, combined with the seismic design standards, judge whether the current seismic design meets the requirements;

[0104] Step 5. User feedback: The system proposes possible solutions or approval plans to the reviewer based on the reasoning results of the expert system. For example, if the expert system analyzes that there are some weak links in the seismic design, the system will give specific improvement suggestions, such as increasing the number of seismic structural columns and improving the seismic performance of building materials, and ask for the reviewer's opinion. The reviewer can choose to accept these proposals, or provide more actual situation information on the project site, or express different opinions on the plan given by the system;

[0105] Step 6. Result confirmation: After the reviewer provides feedback, the system confirms the final approval plan or processing decision. If the reviewer accepts the improvement suggestions, the system confirms that the approval is temporarily not passed and requires the construction party to make rectifications according to the suggestions; if the reviewer provides new information, the system conducts reasoning and analysis again and gives a new plan, and explains the logic and reasons behind the final decision, such as which regulations and which cases are used to draw the current conclusion, to obtain a personalized approval plan.

[0106] In the approval management of the construction industry, the expert system can, in the face of complex or special situations such as special geographical locations and complex environmental impact assessment results, based on the knowledge base and rules, combined with the user input information, conduct reasoning and analysis to customize personalized approval plans for different projects. At the same time, the expert system uses a large amount of professional knowledge, regulations and historical cases for reasoning, avoiding the subjectivity and limitations of manual review, and can comprehensively and meticulously analyze project materials, accurately judge problems, improve the accuracy of approval, and ensure the objectivity and fairness of approval results. Moreover, through the interactive mode, it can adjust strategies in a timely manner according to user feedback, enhance the flexibility of the system, and adapt to the diverse needs of projects;

[0107] In terms of optimizing the approval process, the fast and accurate analysis ability of the expert system shortens the approval cycle, reduces the manual repeated communication and confirmation links, reduces time and labor costs, realizes the full-process automated management, and improves the overall approval efficiency. In addition, based on accurate knowledge and rule reasoning, the expert system maintains a stable judgment standard, avoids errors caused by human negligence and insufficient knowledge, effectively reduces the risk of human errors, and improves the reliability and stability of approval.

[0108] S5. Approve the preprocessed data according to the personalized approval plan, and store the risk score and approval result in the intelligent review system.

[0109] In the local example, the intelligent review system mainly includes the following modules:

[0110] Database management module: used to store approval application materials, risk scores and approval results, maintain the data consistency of the whole system, and ensure the security and availability of data;

[0111] Approval record module: used to record decision-making points and approval results in the approval process for easy traceability and auditing;

[0112] Log record module: used to record the operation logs of the intelligent review system for easy troubleshooting and technical support;

[0113] Notification and feedback module: used to notify the user of the preliminary processing results, approval progress and approval results in a timely manner, and receive the user's feedback;

[0114] Permission control module: used to manage user roles and permissions to ensure the security and compliance of data access.

[0115] Through the above detailed steps and implementation methods, the construction approval system can realize the full-process automated management from data collection, data processing, intelligent review, risk assessment to the final approval result. With the intervention of the expert system, the approval efficiency is improved, and the risk of human errors is also reduced.

[0116] Some of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is the one that is closest to the actual situation obtained through software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0117] The working principle of the present invention:

[0118] In the initial review process, a machine learning model or a rule engine is used to automatically identify and classify the approval materials. By parsing and analyzing the unstructured drawing data, the unstructured design drawings are converted into structured building structure descriptions, and a preliminary review is carried out according to the set standards. For example, it is checked whether the documents are complete and whether the formats are correct. In terms of risk assessment and analysis, a pre-trained risk assessment model is used to analyze the results of the preliminary review, analyze the possible risk points, and give a risk score. After the above work is completed, an expert system is introduced for auxiliary decision-making and processing, which is carried out in six steps designed in an interactive mode. After the approval process is completed, the system records the approval results and updates the database information.

[0119] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent approval management method for the construction industry, characterized in that, Including: S1, collect approval application materials, and perform data cleaning, data deduplication, and data standardization operations on the approval application materials to obtain preprocessed data; S2, construct a data classification model based on machine learning algorithms, and use the data classification model to classify the preprocessed data to obtain a material classification result; S3, according to the material classification result, use the intelligent review system to perform preliminary processing and risk assessment on the preprocessed data to obtain a risk score; S4, use the expert system to perform secondary processing on the preprocessed data to obtain a personalized approval plan; S5, approve the preprocessed data according to the personalized approval plan, and store the risk score and approval result in the intelligent review system.

2. The intelligent approval management method for the construction industry according to claim 1, wherein The data cleaning includes: According to the formula Calculate the mean value of numerical data Using the mean value Replace the missing value X in the numerical data i ; where X j represents the j-th numerical data, and n represents the number of numerical data.

3. The intelligent approval management method for the construction industry according to claim 1, wherein, The data deduplication includes: S11, initialize an empty hash table hash_table; S12, traverse the original data set data, and calculate the hash value hash_value = hash_function(data[i]) of each data record data[i]; S13, determine whether there is an entry with the hash value hash_value in the hash table hash_table; if yes, jump to S14; if not, insert hash_value into the hash table hash_table and retain the corresponding data record data[i]; S14, determine whether the data record at the corresponding position in data[i] and the hash table hash_table is equal; if yes, it means it is a duplicate, skip this record; if not, create a new linked list node, store data[i] in the linked list node, and insert the linked list node into the head of the linked list corresponding to hash_value.

4. The intelligent approval management method for the construction industry according to claim 1, wherein The constructing of the data classification model based on machine learning algorithms includes: Collect a number of approval materials, convert the unstructured data in the approval materials into structured data, and perform feature extraction and vectorization processing to obtain preprocessed data; Use machine learning algorithms to train the preprocessed data, and obtain an optimized data classification model through cross-validation and hyperparameter tuning; Deploy the data classification model to the intelligent review system for automatically classifying approval materials.

5. The intelligent approval management method for the construction industry according to claim 1, wherein, The using of the intelligent review system to perform preliminary processing on the preprocessed data includes: Obtain the drawing data in the preprocessed data according to the material classification result, parse the drawing data to obtain structured data; Perform preliminary processing on the structured data and other data in the preprocessed data according to the preset rule library, check the file type, file quantity, file format, and file content to obtain a preliminary processing result.

6. The intelligent approval management method for the construction industry according to claim 1, characterized in that The risk assessment includes: S31, determine whether the preliminary processing result is qualified; if yes, jump to S32; if not, send an abnormal information of the approval application materials; S32, use the pre-trained risk assessment model to perform risk assessment on the structured data to obtain a risk assessment result; among them, the pre-trained risk assessment model is constructed based on a probability statistical model, and the risk assessment result includes risk points and risk scores; S33, display the risk assessment result in the form of a visual chart.

7. An intelligent approval management method for the construction industry according to claim 1, characterized in that, The secondary processing of the preprocessed data by using an expert system includes: Collecting a number of laws, regulations, industry standards, and historical case data to build an expert knowledge base; among them, the expert knowledge base is updated periodically; Judging whether the current construction project is a special case according to the geographical location and environmental data of the construction project; if so, using the interactive mode to perform secondary processing on the preprocessed data; if not, completing the approval.

8. The intelligent approval management method for the construction industry according to claim 7, wherein The secondary processing of the preprocessed data by using the interactive mode includes: Starting the interactive mode of the expert system through a specific function or a specific command; Guiding the user to provide information by using a text, voice, or graphical interface, and collecting the user's input information to obtain the user input; Inferring and analyzing the user input based on the expert knowledge base and the rule engine technology to obtain a recommended approval plan; Pushing the recommended approval plan to the user and collecting the user feedback; Confirming the final approval plan according to the user feedback to obtain a personalized approval plan, and giving the logic and reasons of the personalized approval plan.

9. The intelligent approval management method for the construction industry according to claim 1, wherein The approval application materials include: the planning report, design drawings, construction plan of the construction project in the housing and urban-rural development department, as well as relevant legal documents and supporting materials, and the approval application materials are stored in the database of the intelligent review system.

10. The intelligent approval management method for the construction industry according to claim 1, characterized in that, The intelligent review system includes: Database management module: used to store approval application materials, risk scores, and approval results; Approval record module: used to record decision-making points and approval results during the approval process; Log record module: used to record the operation logs of the intelligent review system; Notification and feedback module: used to notify the user of the preliminary processing results and approval results, and receive the user's feedback opinions; Permission control module: used to manage user roles and permissions.

Images