A smart verification method for the arrival of building materials
By constructing standard template files and digital twin models, and combining multi-dimensional sensing devices and AI algorithms, the problems of low efficiency, high error, and difficulty in tracing the arrival of building materials have been solved, achieving efficient and accurate multi-dimensional verification and full-process traceable data management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGHAI ZHONGWU SUPPLY CHAIN MANAGEMENT CO LTD
- Filing Date
- 2026-03-01
- Publication Date
- 2026-06-02
AI Technical Summary
Existing methods for verifying the arrival of building materials are inefficient, have high error rates, and are difficult to trace. They cannot meet the needs of multi-dimensional verification and lack the ability to provide early warning of anomalies and trace data.
We construct standard template files and digital twin models, collect data through multi-dimensional sensing devices, perform hierarchical intelligent verification, combine AI anomaly recognition algorithms and blockchain databases to achieve data archiving and traceability, and dynamically optimize the verification process.
It achieves comprehensive multi-dimensional verification with a verification error rate of less than 0.8%, strong data traceability, adaptability to different engineering needs, and improved verification efficiency and consistency.
Smart Images
Figure CN122134263A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of building material verification technology, specifically a method for intelligent verification and validation of building materials upon delivery. Background Technology
[0002] In construction projects, material quality directly determines project safety and lifespan. Arrival inspection, as a crucial step in material quality control, requires a comprehensive verification of material specifications, models, quantities, quality certificates, and appearance. Currently, the construction industry commonly uses manual verification, where staff manually check against purchase contracts, design drawings, and other documents, filling out verification record forms. However, this existing technology has several shortcomings. Manual verification is inefficient and prone to omissions and errors when dealing with large batches and multiple types of materials, resulting in a high error rate. Furthermore, verification standards rely on personnel experience, and different personnel may have different understandings, leading to poor consistency in verification results. At the same time, verification data is stored in a scattered manner, making it difficult to trace the entire process and hold those responsible for subsequent quality issues accountable. Finally, there is a lack of accurate detection methods for material appearance defects and hidden physical properties, making it difficult to meet the requirements of high-standard engineering. The barcode scanning verification technology introduced by some enterprises can only achieve basic verification of quantity and model, which cannot cover multi-dimensional verification needs and lacks the ability to provide anomaly warnings and data traceability. Therefore, there is an urgent need for an intelligent verification method for the arrival of building materials that is comprehensive, accurate, automated and traceable. Summary of the Invention
[0003] In view of the above situation and to overcome the shortcomings of the prior art, the present invention provides an intelligent verification method for the arrival of building materials, which effectively solves the problems of low efficiency, high error and difficulty in traceability of the existing building material arrival verification in the background art.
[0004] To achieve the above objectives, the present invention provides the following technical solution: a method for intelligent verification and validation of delivered building materials, comprising the following steps: S1: Construct standard template files and digital twin models. Based on procurement contracts, design drawings and industry standards, construct standard template files that include basic material information, quality standards, certification documents, appearance parameters and storage requirements, and construct digital twin models that relate to the full life cycle data interfaces of materials based on these template files. S2: Multi-source data collection at the delivery end, collecting basic data, appearance characteristics, physical parameters and delivery environment data of building materials through a multi-dimensional sensing device group; S3: Data preprocessing and format standardization, which performs noise filtering, data completion, and format conversion on the collected multi-source data, converting non-standardized data into standardized data that matches the template file, while quantifying appearance feature parameters; S4: Hierarchical intelligent verification and validation, calling the standard data of the template file and digital twin model, and performing four-level hierarchical verification with the preprocessed actual data, sequentially checking the basic information, physical parameters, appearance and certification documents, environment and full life cycle data; S5: Anomaly identification and hierarchical processing. The AI anomaly identification algorithm analyzes the verification results, marks first-level, second-level, and third-level anomalies, and generates corresponding processing instructions. S6: Verification data archiving and traceability report generation: Archive verification data and anomaly handling records into the blockchain database, generate standardized traceability reports and push them to the corresponding terminals; S7: Dynamic updates and optimizations, based on verification data and engineering feedback, optimize AI algorithm parameters and template files, and synchronously update digital twin model data.
[0005] Compared with the prior art, the beneficial effects of the present invention are: In our work, by setting up a multi-dimensional sensing device group and a hierarchical verification process, we have achieved comprehensive verification of basic information, physical parameters, appearance status, and other dimensions, breaking through the limitations of traditional single-dimensional verification and greatly improving the comprehensiveness of verification. In our work, by integrating AI algorithms with precise measurement technology, we can replace manual operations, control the verification error rate to within 0.8%, improve verification efficiency, and solve the problems of missed detections and false detections in manual verification. In our work, we use blockchain databases to ensure that verification data is archived in an immutable manner, and combine it with digital twin models to link data throughout the entire lifecycle, providing reliable data support for subsequent quality accountability and achieving full traceability. In practice, through dynamic updates of standard template files and self-learning optimization of AI algorithms, it adapts to the verification needs of different projects and different types of building materials, with a wide range of applications and high flexibility. Attached Figure Description
[0006] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.
[0007] In the attached diagram: Fig. 1 This is the overall logic block diagram of the intelligent verification method for the arrival of building materials according to the present invention; Fig. 2 This is a logical block diagram of the data acquisition of the multi-dimensional sensing device group of the present invention; Fig. 3 This is a block diagram of the hierarchical verification and exception handling logic of the present invention; Fig. 4 This is a logic block diagram for data archiving and dynamic optimization in this invention; Detailed Implementation
[0008] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.
[0009] Example 1, by Figs. 1 to 4 The present invention includes the following steps: S1: Construct standard template files and digital twin models. Based on procurement contracts, design drawings and industry standards, construct standard template files that include basic material information, quality standards, certification documents, appearance parameters and storage requirements, and construct digital twin models that relate to the full life cycle data interfaces of materials based on these template files. The standard template files support importing and exporting in multiple formats such as Excel, PDF, and XML. They can achieve real-time data exchange with building engineering management systems and supplier management systems. The quality standard module has a built-in library of the latest industry standards such as GB and ISO, and can automatically match the corresponding verification specifications according to the material type.
[0010] S2: Multi-source data collection at the delivery end, collecting basic data, appearance characteristics, physical parameters and delivery environment data of building materials through a multi-dimensional sensing device group; The multi-dimensional sensing equipment group consists of an RFID reader, a high-definition vision camera, a laser dimension measuring instrument, a quality inspection instrument, and environmental sensors. It adopts a LoRa wireless networking method, supports a combination of mobile and fixed data acquisition, and is adaptable to the complex environment of construction sites. The RFID reader adopts a 13.56MHz high-frequency anti-interference design, with a reading distance of 0-50cm. It can penetrate the packaging of building materials with a thickness of no more than 5cm and accurately obtain basic data such as material production batch, supplier, and specifications. The high-definition vision camera is equipped with an anti-backlight and anti-dust lens, with a pixel count of no less than 20 million and a frame rate of ≥30fps. It can quickly capture images of the material's appearance and extract appearance feature parameters such as surface defects and damage through image segmentation algorithms.
[0011] S3: Data preprocessing and format standardization, which performs noise filtering, data completion, and format conversion on the collected multi-source data, converting non-standardized data into standardized data that matches the template file, while quantifying appearance feature parameters; S4: Hierarchical intelligent verification and validation, calling the standard data of the template file and digital twin model, and performing four-level hierarchical verification with the preprocessed actual data, sequentially checking the basic information, physical parameters, appearance and certification documents, environment and full life cycle data; In the hierarchical intelligent verification process, the response time for Level 1 verification (basic information) is ≤1 second, for Level 2 verification (physical parameters) it is ≤3 seconds, for Level 3 verification (appearance and supporting documents) it is ≤5 seconds, and for Level 4 verification (environment and full lifecycle data) it is ≤8 seconds. The overall verification efficiency is more than 60% higher than that of the traditional manual method.
[0012] S5: Anomaly identification and hierarchical processing. The AI anomaly identification algorithm analyzes the verification results, marks first-level, second-level, and third-level anomalies, and generates corresponding processing instructions. The AI anomaly detection algorithm integrates convolutional neural networks and decision tree algorithms. It has been trained on no less than 100,000 sets of building material verification samples. The accuracy rate of identifying anomalies such as appearance defects and parameter deviations is no less than 99.2%. It also has self-learning capabilities and can continuously optimize the recognition accuracy based on actual verification data.
[0013] S6: Verification data archiving and traceability report generation: Archive verification data and anomaly handling records into the blockchain database, generate standardized traceability reports and push them to the corresponding terminals; The blockchain database adopts a consortium blockchain architecture, with nodes including engineering parties, suppliers, and regulatory authorities. It links data from the entire process of material production, transportation, verification, and use, ensuring data immutability and full traceability, with data storage latency not exceeding 3 seconds. The traceability report includes verification process details, comparison results of various indicators, anomaly details, handling measures, and risk warnings. It supports online viewing, downloading, and printing, and can be simultaneously pushed to the engineering management platform, supplier terminals, and regulatory authority terminals. S7: Dynamic updates and optimizations, based on verification data and engineering feedback, optimize AI algorithm parameters and template files, and synchronously update digital twin model data.
[0014] During operation, the system first constructs standard template files and digital twin models based on engineering requirements, clarifying the material verification standards and data correlation. After the materials arrive, basic data, appearance features, physical parameters, and environmental data are collected through a multi-dimensional sensing device group. After collection, the data processing unit preprocesses the multi-source data and converts it into a standardized format. Subsequently, the verification control unit calls the standard data for hierarchical comparison and verification, and the AI algorithm module identifies and classifies anomalies. After implementing corresponding handling measures for different levels of anomalies, all data is archived to the blockchain database, a traceability report is generated, and pushed to relevant terminals. Finally, based on the verification data and engineering feedback, the template files and AI algorithms are dynamically optimized to improve the accuracy of subsequent verifications.
[0015] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0016] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A method for intelligent verification and validation of building material deliveries, characterized in that, Includes the following steps: S1: Construct standard template files and digital twin models. Based on procurement contracts, design drawings and industry standards, construct standard template files that include basic material information, quality standards, certification documents, appearance parameters and storage requirements, and construct digital twin models that relate to the full life cycle data interfaces of materials based on these template files. S2: Multi-source data collection at the delivery end, collecting basic data, appearance characteristics, physical parameters and delivery environment data of building materials through a multi-dimensional sensing device group; S3: Data preprocessing and format standardization, which performs noise filtering, data completion, and format conversion on the collected multi-source data, converting non-standardized data into standardized data that matches the template file, while quantifying appearance feature parameters; S4: Hierarchical intelligent verification and validation, calling the standard data of the template file and digital twin model, and performing four-level hierarchical verification with the preprocessed actual data, sequentially checking the basic information, physical parameters, appearance and certification documents, environment and full life cycle data; S5: Anomaly identification and hierarchical processing. The AI anomaly identification algorithm analyzes the verification results, marks first-level, second-level, and third-level anomalies, and generates corresponding processing instructions. S6: Verification data archiving and traceability report generation: Archive verification data and anomaly handling records into the blockchain database, generate standardized traceability reports and push them to the corresponding terminals; S7: Dynamic updates and optimizations, based on verification data and engineering feedback, optimize AI algorithm parameters and template files, and synchronously update digital twin model data.
2. The intelligent verification method for the arrival of building materials according to claim 1, characterized in that: The standard template file supports importing and exporting in multiple formats such as Excel, PDF, and XML. It can achieve real-time data exchange with the construction project management system and supplier management system. Its quality standard module has a built-in GB and ISO industry standard library, which can automatically match and verify specifications according to material type.
3. The intelligent verification method for the arrival of building materials according to claim 1, characterized in that: The multi-dimensional sensing device group consists of an RFID reader, a high-definition vision camera, a laser size measuring instrument, a quality inspection instrument, and an environmental sensor. It adopts a LoRa wireless networking method and supports a combination of mobile and fixed data acquisition.
4. The intelligent verification method for the arrival of building materials according to claim 1, characterized in that: The RFID reader adopts a 13.56MHz high-frequency anti-interference design, with a reading distance of 0-50cm. It can penetrate the packaging of building materials with a thickness of no more than 5cm and accurately obtain basic data such as the production batch, supplier, and specifications of the materials.
5. The intelligent verification method for the arrival of building materials according to claim 1, characterized in that: The high-definition vision camera is equipped with an anti-backlight and anti-dust lens, with a pixel count of no less than 20 million and a frame rate of ≥30fps. It extracts surface defects and damaged appearance feature parameters of materials through image segmentation algorithms.
6. The intelligent verification method for the arrival of building materials according to claim 1, characterized in that: The AI anomaly detection algorithm integrates convolutional neural networks and decision tree algorithms, and has been trained on no less than 100,000 sets of building material verification samples. The anomaly detection accuracy rate is no less than 99.2%, and it has self-learning and optimization capabilities.
7. The intelligent verification method for the arrival of building materials according to claim 1, characterized in that: The blockchain database adopts a consortium blockchain architecture, with nodes including engineering parties, suppliers, and regulatory authorities. It links data from the entire process of material production, transportation, verification, and use, with data storage latency not exceeding 3 seconds.
8. The intelligent verification method for the arrival of building materials according to claim 1, characterized in that: In the hierarchical intelligent verification process, the response time for Level 1 verification is ≤1 second, Level 2 verification is ≤3 seconds, Level 3 verification is ≤5 seconds, and Level 4 verification is ≤8 seconds. The overall verification efficiency is more than 60% higher than that of the traditional manual method.
9. The intelligent verification method for the arrival of building materials according to claim 1, characterized in that: The traceability report includes details of the verification process, indicator comparison results, anomaly details, handling measures, and risk warnings. It supports online viewing, downloading, and printing, and can be simultaneously pushed to the engineering management platform, supplier terminals, and regulatory department terminals.