A method for intelligent identification and credible verification of carbon footprint identification of bamboo-wood products

Abstract

This invention relates to the field of product carbon footprint certification technology, specifically to a method for intelligent identification and reliable verification of carbon footprint labels for bamboo and wood products. The method acquires the label image and decodes it to obtain the original data string; semantically analyzes and extracts a structured field information set, including key physical parameter field groups; normalizes and constructs a parameter feature vector and performs a hash operation to obtain a parameter fingerprint; retrieves the certification-end parameter data from the certification authority's reliable evidence storage node; performs rapid verification and field-by-field comparison of the parameter fingerprint, specifically verifying the service years of biomass carbon sequestration, and weighted summarization to obtain a comprehensive reliability score; performs a three-level classification judgment based on preset dual thresholds, and generates a structured verification report. This invention fills the technical gap in reliable verification of carbon footprint label data content, effectively preventing the risk of false reporting of carbon footprint parameters.

Description

Technical Field

[0001] This invention relates to the field of product carbon footprint certification technology, specifically to a method for intelligent identification and reliable verification of carbon footprint markings for bamboo and wood products. Background Technology

[0002] Bamboo and wood products, as representative products of natural biomass materials, possess significant carbon sequestration and storage attributes and are in high demand for large-scale export trade, making them a key category of focus in the product carbon footprint certification system. The carbon footprint accounting of bamboo and wood products covers the quantification of greenhouse gas emissions throughout the entire life cycle of raw material acquisition, processing and manufacturing, logistics and transportation, and waste disposal, as well as the conversion of the biomass carbon storage and delayed carbon emission effects of the bamboo and wood materials themselves. Key physical parameters relied upon for the accounting include the carbon content of the bamboo and wood materials, product density, moisture content, amount of adhesive applied, and the number of years of biomass carbon sequestration service. These parameters, along with the carbon emission coefficients at each stage, jointly determine the final carbon footprint declaration value. After the accounting is completed and verified by the certification body, the certification result is affixed to the product in the form of a carbon footprint label, disclosed to consumers and trading partners. Regarding the anti-counterfeiting verification of the carbon footprint label, existing technologies mainly involve embedding micro-anti-counterfeiting features in the label pattern, combined with the re-coding comparison mechanism of the back-end verification system, to identify the physical authenticity of the label carrier. These technologies have been widely applied in consumer goods, food, and other fields.

[0003] However, the existing anti-counterfeiting technologies have a fundamental technical blind spot: they can only verify the physical authenticity of the label carrier, but cannot verify the credibility of the carbon footprint calculation parameters declared in the label. Even after a carbon footprint label passes physical anti-counterfeiting verification, key parameters recorded on the label, such as carbon content, density, and biomass carbon sequestration service years, as well as carbon emission coefficients at each stage, still face risks such as inconsistencies between the entered parameter values ​​and the original verification data from certification bodies, mixed use of parameters from different batches, or selective entry of the best values. Furthermore, existing systems lack an automatic field-by-field comparison mechanism. The declared value of biomass carbon sequestration service years directly affects the delayed carbon emission effect conversion result, and its rationality also lacks an automatic comparison method with the product's physical durability benchmark. These technical deficiencies keep the credibility verification of carbon footprint labels at a superficial level of "whether the label carrier is genuine," failing to answer the deeper question of "whether the label data content is credible." This leaves a systemic loophole for false reporting of carbon footprint data, hindering international mutual trust and trade acceptance of the green attributes of bamboo and wood products. Therefore, a method that can achieve intelligent identification and credible verification at the label data content level is urgently needed. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method for intelligent identification and reliable verification of carbon footprint markings for bamboo and wood products. The technical solution adopted includes: Image data of carbon footprint markers on bamboo and wood products to be verified are acquired through an image acquisition device. The image data is then subjected to noise reduction, perspective correction, and contrast enhancement in sequence. The type of marker carrier is identified, and the carrier content is read and decoded according to the corresponding protocol to obtain the original marker data string. Semantic parsing is performed on the original data string of the identifier to extract the product basic information field group, the key physical parameter field group, and the certification traceability information field group to obtain a structured field information set; the key physical parameter field group includes the carbon content of bamboo and wood materials, product density, moisture content, glue application amount, biomass carbon sequestration service years, and carbon emission coefficients at each life cycle stage; The key physical parameter field group is normalized according to a preset encoding rule to construct a scanning end parameter feature vector. A hash operation is performed on the scanning end parameter feature vector to obtain the scanning end parameter fingerprint. Using the certification batch number in the certification traceability information field group as the search key, a query is initiated to the trusted evidence storage node of the certification authority to obtain the certification end parameter feature vector, certification end parameter fingerprint, set of allowable error thresholds for each parameter field, and benchmark value of reasonable range of biomass carbon sequestration service years; The fingerprint of the scanning end parameter is compared with the fingerprint of the authentication end parameter. If they match, a full confidence score is assigned. If they do not match, the feature vector of the scanning end parameter is compared with the feature vector of the authentication end parameter field by field. Each field score is assigned according to the relationship between the deviation of each field and the allowable error threshold. At the same time, the declared value of the service years of biomass carbon sequestration is compared with the reasonable range benchmark value to determine its reasonableness. The scores of each field are weighted and summarized according to the preset weight to obtain the comprehensive credibility score. Based on the comprehensive credibility score and preset dual thresholds, a three-level classification judgment is performed to obtain the verification conclusion, and a structured verification report is generated that includes a complete list of identification fields, comparison results of each field, comprehensive credibility score, and abnormal field tracing prompts.

[0005] Furthermore, the step of identifying the carrier type and completing the reading and decoding of the carrier content according to the corresponding protocol includes: The preprocessed image is used to locate the marked area and identify the type of the marked carrier, which is a QR code, an NFC chip, a digital printed label, or a combination thereof. For QR code carriers, adaptive threshold binarization is used to improve the decoding success rate. For NFC chip carriers, the chip content is read through the near-field communication protocol. If any necessary field is missing or the field format is abnormal during the decoding process, a field integrity error message is triggered and the name of the missing field is recorded, and the process does not proceed to the subsequent verification process.

[0006] Furthermore, the structured field information set includes: the product basic information field group contains product type, rule type and version number, functional unit or declaration unit and the life cycle stage covered by the system boundary; the key physical parameter field group also contains a set of carbon emission coefficients for each life cycle stage; the certification traceability information field group contains the certification body's unique identifier, certification batch number, verification timestamp and total carbon footprint declaration value; when any certification traceability field is missing, the system refuses to initiate a query on the certification end and outputs a field missing prompt.

[0007] Furthermore, the process of constructing the scanning end parameter feature vector and performing a hash operation to obtain the scanning end parameter fingerprint includes: arranging the parameters in a preset order according to carbon content, product density, moisture content, sizing amount, biomass carbon sequestration service years, and carbon emission coefficients at each stage; performing rounding and normalization on continuous parameters according to a predetermined precision; constructing the scanning end parameter feature vector; performing a SHA-256 hash operation on the scanning end parameter feature vector, and using the hash result as the scanning end parameter fingerprint; the parameter fingerprint serves as the basis for rapid integrity verification in subsequent steps. When the scanning end parameter fingerprint is inconsistent with the authentication end parameter fingerprint, a detailed field-by-field comparison process is directly triggered to improve verification efficiency.

[0008] Furthermore, the step of initiating a query to the trusted evidence storage node of the certification authority to obtain the certification end parameter feature vector and certification end parameter fingerprint includes: the trusted evidence storage node of the certification authority is a blockchain distributed evidence storage node; when the verification is passed, the certification authority synchronously uploads the certification end parameter feature vector and certification end parameter fingerprint to the blockchain for evidence storage, and binds them with the certification batch number and product QR code identifier through a three-party combined hash to ensure that the evidence storage data cannot be tampered with; the query request is initiated through a secure communication protocol, and the query result is accompanied by a digital signature for the verification party to confirm the authenticity of the data source.

[0009] Furthermore, the comparison of the scanning end parameter fingerprint with the authentication end parameter fingerprint, and the assignment of a full confidence score if they match, includes: when the scanning end parameter fingerprint and the authentication end parameter fingerprint are completely identical, it is determined that the overall parameters have not changed, the full confidence score is directly assigned, and the detailed field-by-field comparison step is skipped, proceeding to the three-level hierarchical judgment step; when they are inconsistent, it is determined that at least one parameter field has changed, and the detailed field-by-field comparison process is initiated; through the parameter fingerprint rapid verification mechanism, identifiers with unchanged parameters can quickly pass verification, effectively reducing the computational overhead in large-scale identifier verification scenarios.

[0010] Furthermore, the step of performing numerical comparison and assigning scores to each field includes: assigning a full score to a field when the field value is completely consistent with the corresponding field value at the certification end; linearly reducing the field score based on the ratio of the deviation to the threshold when the field value deviation is within the allowable error threshold preset by the certification body; recording a score of zero and marking it as an abnormal field when the field value deviation exceeds the allowable error threshold or the field is missing; the allowable error threshold is preset by the certification body based on the measurement uncertainty of each parameter to distinguish between reasonable deviations caused by normal measurement errors and abnormal deviations caused by parameter tampering; carbon content and biomass carbon sequestration service years directly affect the calculation results of biomass carbon reserves and should be assigned a first weighting coefficient (the first weighting coefficient is a high weighting coefficient to ensure that the score subsequently enters the verification of the reasonableness of biomass carbon sequestration service years).

[0011] Furthermore, the comparison of the declared service life of biomass carbon sequestration with a reasonable range benchmark value to determine its reasonableness includes: comparing the declared service life of biomass carbon sequestration with a reasonable range benchmark value preset by the certification body based on the durability characteristics of the product type; when the declared value falls within the reasonable range, a special reasonableness verification is passed without imposing an additional penalty coefficient; when the declared value exceeds the upper limit of the reasonable range or falls below the lower limit of the reasonable range, a special anomaly marker is triggered, and a penalty coefficient is applied to the comprehensive credibility score to prevent the risk of artificially lowering the declared carbon footprint value by falsely reporting the service life of biomass carbon sequestration.

[0012] Furthermore, the verification conclusion obtained by performing a three-level classification based on the comprehensive credibility score and preset dual thresholds includes: when the comprehensive credibility score is not lower than the first confidence threshold T1, it is judged as "credible" and a credible verification conclusion is output; when the comprehensive credibility score is between the second confidence threshold T2 and the first confidence threshold T1, it is judged as "doubtful" and a doubtful verification conclusion is output, with all abnormal field names and specific deviation values ​​marked in the report; when the comprehensive credibility score is lower than the second confidence threshold T2, it is judged as "unreliable" and an unreliable verification conclusion is output, with complete difference details recorded; the structured verification report also includes the three-level classification conclusions and the special verification results of the service years of biomass carbon sequestration, which are available for review and use by regulatory agencies, purchasers, or consumers.

[0013] Furthermore, when the verification conclusion is "questionable," the following batch-to-batch comparison steps are performed: using historical certification batch records of similar bamboo and wood products stored in the trusted evidence storage node of the certification body as the data source, the total carbon footprint declaration value and corresponding output value of each historical batch are extracted, and the carbon productivity index of each historical batch is calculated; the carbon productivity index of the current batch to be verified and the carbon productivity data of the historical batch are sorted according to the carbon productivity value, and the ordered samples are clustered using the Fisher optimal segmentation method to identify whether the carbon productivity index of the current batch deviates significantly from the historical normal distribution range; if the deviation exceeds the preset anomaly judgment threshold, the verification conclusion is upgraded to "unreliable," and a batch-to-batch comparison anomaly prompt is added to the structured verification report to assist regulatory agencies in identifying systemic carbon footprint data misreporting issues.

[0014] Compared with existing technologies, this invention fills the technological gap in the reliable verification of carbon footprint labeling data content for the first time. Existing anti-counterfeiting technologies can only identify the physical authenticity of the label carrier, while this invention, by introducing a field-by-field comparison mechanism between parameter feature vectors and certified evidence data, substantially advances the verification dimension from "whether the label carrier is authentic" to "whether the labeling data content is reliable." It can accurately locate abnormal parameter fields such as carbon content, density, and moisture content, providing clear data basis for regulatory accountability. In addition, this invention specifically designs a reasonableness verification mechanism for the biomass carbon sequestration service years parameter unique to the carbon footprint accounting of bamboo and wood products. It automatically compares the declared value of the label with the product type durability benchmark range. When the declared value exceeds the reasonable range, a special anomaly mark is triggered and a penalty coefficient is applied, effectively preventing the risk of artificially lowering the total carbon footprint declared value by falsely reporting the service years, and fundamentally improving the actual credibility of the carbon footprint certification results of bamboo and wood products. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of an embodiment of the present invention. Detailed Implementation

[0017] 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.

[0018] Throughout this specification, references to "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "an embodiment," "an example," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. Moreover, those skilled in the art will understand that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0019] Please see Figure 1 The flowchart illustrates a method for intelligent identification and reliable verification of carbon footprint marking of bamboo and wood products according to an embodiment of the present invention, specifically including: Step S1: Carbon footprint identification image acquisition and preprocessing.

[0020] A bamboo reconstituted flooring manufacturer completed its full lifecycle carbon footprint accounting according to relevant product category rules. The certification body verified the results, which were then affixed to the product packaging as a QR code. Verification personnel used a mobile terminal equipped with a high-resolution camera to photograph the carbon footprint QR code on the product packaging. The system automatically detected the QR code area in the image, performed perspective correction to eliminate shooting angle deviations, and improved the QR code contrast through adaptive threshold binarization to ensure decoding could be completed even with slight wear on the QR code. Successful decoding yielded a JSON-formatted raw data string containing product information, certification batch number, and various parameter fields. If any necessary fields were missing or the format was abnormal during decoding, the system automatically triggered a field integrity error message, recorded the missing field names, and prevented further verification.

[0021] Step S2: Intelligent recognition of structured fields for carbon footprint identification.

[0022] The system performs semantic parsing on the raw data string in JSON format, extracting three types of field groups. The product basic information field group confirms the product type as bamboo and wood products with carbon footprint accounting standards, the functional unit as 1m³ bamboo reconstituted flooring, and the system boundary covering four lifecycle stages: raw material acquisition, processing and manufacturing, logistics and transportation, and waste disposal. The key physical parameter field group reads: bamboo carbon content fC=0.497, product density ρ=1200kg / m³, moisture content w=0.30, adhesive application rate W1=32.70kg / m³, biomass carbon sequestration service life t0=30 years, and carbon emission coefficients for each lifecycle stage. The certification traceability information field group obtains the certification body's unique identifier, certification batch number, verification timestamp, and total carbon footprint declaration value, resulting in a complete set of structured field information.

[0023] Step S3: Construction of key physical parameter feature vectors and generation of parameter fingerprints.

[0024] The system arranges the extracted parameter fields in a predefined order, performs normalization on continuous parameters (e.g., carbon content accurate to three decimal places, density accurate to one unit), and constructs a feature vector V for the scanning end parameters in a preset order of carbon content, product density, moisture content, sizing amount, biomass carbon sequestration service years, and carbon emission coefficients at each stage. scan , for V scan Perform SHA-256 hash operation to generate a 64-bit hexadecimal scan end parameter fingerprint PF. scan This serves as the basis for subsequent rapid verification.

[0025] Step S4: Retrieval and retrieval of the original authentication parameter set.

[0026] The system uses the authentication batch number as the search key and initiates a query request to the blockchain distributed evidence storage node through a secure communication protocol to obtain the authentication end parameter feature vector V. cert and authentication parameters fingerprint PF cert The certification body has already included V during the verification process. cert and PF cert Synchronous on-chain notarization is performed and bound to the certification batch number and product QR code identifier via a three-party combined hash to ensure the immutability of the notarized data. Query results include the certification authority's digital signature for verification purposes, confirming the authenticity of the data source. Simultaneously, a set of preset allowable error thresholds for various parameters from the certification authority is obtained, such as the allowable deviation δ for carbon content. fC =±0.005, Density tolerance δ ρ =±10kg / m³, and the reasonable range of biomass carbon sequestration service years for bamboo reconstituted flooring products [15,50] years.

[0027] Step S5: Field-by-field parameter comparison and overall credibility scoring.

[0028] This step is executed in three levels sequentially. The first level is rapid verification of parameter fingerprints, comparing them with the PF. scan With PF cert If the two are completely consistent, the overall parameters have not changed. When the fingerprint of the scanning end parameter is completely consistent with the fingerprint of the authentication end parameter, it is determined that all parameter fields are completely consistent with the authentication end. The comprehensive credibility score CS is directly assigned a full score (e.g., CS=1.00), which is equivalent to all fields getting full scores and the result being weighted and summarized. There is no need to perform numerical comparisons field by field, and the process directly enters the third-level classification judgment step. If they are inconsistent, the second level is initiated.

[0029] The second level involves a detailed comparison of each field's parameters, specifically for V. scan With V cert The corresponding fields in the table are compared numerically item by item. Taking this example: the carbon content field reading of 0.497 is completely consistent with the certified value of 0.497, so it is awarded full marks; the density field reading of 1205 kg / m³ deviates from the certified value of 1200 kg / m³ by 5 kg / m³, which is within the δ range. ρ Within the allowable range of ±10 kg / m³, scores are linearly reduced proportionally to the deviation. If a field's deviation exceeds the allowable error threshold or the field is missing, its score is zero and it is marked as an abnormal field. The specific calculation formulas for each field's score are as follows: Assuming the full score for field i is 1.00, when the field value deviation |Δi| equals zero, the field score is zero. i =1.00; when 0 < |Δi| ≤ ε i At that time, the field score i =1 |Δi| / ε i That is, it is reduced linearly according to the ratio of deviation to threshold; when |Δi|>ε i When a field is missing, score i =0. Weighted composite score CS weighted =Σ(w i ×score i ), where w i Each field is assigned a pre-defined weight, with the sum of the weights being 1.00. In this embodiment, the weights are: carbon content 0.25, biomass carbon sequestration service years 0.20, product density 0.15, moisture content 0.15, sizing amount 0.10, and total carbon emission coefficients for each stage 0.15. In practical applications, each weight value is pre-set by the certification body based on the contribution of the parameters to the carbon footprint calculation results.

[0030] The third level is a special verification of the reasonableness of the service life of biomass carbon sequestration (this level must be performed regardless of the fingerprint comparison results of the first level). The declared value of t0 (30 years) is compared with the reasonable range benchmark value [15, 50 years]. If 30 years falls within the range, the special verification is passed and no penalty coefficient is applied. If, in a certain scenario, the declared value of t0 is 60 years, exceeding the upper limit of the reasonable range of 50 years, a special anomaly marker is triggered and a penalty coefficient is applied. The overall credibility score will be reduced due to the penalty, and a questionable or unreliable conclusion will be output. When the declared value of t0 falls within the reasonable range, no penalty coefficient is applied, and the final overall credibility score CS = CS. weighted When the declared value of t0 exceeds the reasonable range, a special anomaly flag is triggered, and a penalty coefficient κ is applied. In this embodiment, κ = 0.80, and finally CS = CS. weighted ×0.80. The penalty coefficient is applied only after the weighted aggregation is completed, acting sequentially with the weighting mechanisms of each field, without overlapping. In this embodiment, all fields are consistent or within acceptable limits, and the weighted composite score CS... weighted =0.96, t0 special verification passed, no penalty is imposed, final CS=0.96.

[0031] Step S6: Generate and output the credible verification conclusion.

[0032] The three-level classification is determined based on the comparison between the comprehensive confidence score CS and the preset dual thresholds (first confidence threshold T1=0.90, second confidence threshold T2=0.70). In this embodiment, CS=0.96, which is higher than T1=0.90, so a "credible" verification conclusion is output, and a structured verification report is generated. The report includes an identification list of 8 key physical parameter fields, the comparison results of each field (carbon content is completely consistent, density is reduced within the error range, and other fields are completely consistent), a comprehensive confidence score of 0.96, t0 specific verification passed, and a "credible" level three conclusion. If the verification conclusion is "questionable," the system can further perform a batch-by-batch horizontal comparison step. This involves extracting the total declared carbon footprint and corresponding output value of historical batches of similar bamboo and wood products from the credible evidence storage nodes of the certification body, and calculating the carbon productivity index for each historical batch. The carbon productivity index is defined as the ratio of batch output value to the total declared carbon footprint value of that batch, i.e., CI = Output Value (RMB) / Total Declared Carbon Footprint Value (kgCO2e), with the unit being RMB / kgCO2e. This index measures the economic output corresponding to a unit of carbon emissions; a higher value indicates better carbon emission efficiency. If the current batch's CI value is significantly lower than the historical normal range, it suggests a possible underreporting of carbon footprint data or abnormal output value. The Fisher optimal segmentation method is used to divide all historical batches sorted by CI value into several homogeneous intervals. If the boundary difference between the interval where the current batch falls and the historical main interval (including the continuous interval with the largest number of historical samples) exceeds a preset threshold θ (in this embodiment, θ is taken as 30% of the historical CI mean), then the current batch is determined to have significantly deviated from the historical normal distribution range. The Fisher optimal segmentation method is used to cluster ordered samples to identify whether the carbon productivity of the current batch deviates significantly from the historical normal distribution range. If the deviation exceeds the preset anomaly judgment threshold, the verification conclusion is upgraded to "unreliable", and a batch horizontal comparison anomaly prompt is added to the verification report to help regulatory agencies systematically identify carbon footprint data misreporting issues.

[0033] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments.

[0034] Finally, it should be noted that although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent identification and reliable verification of carbon footprint markings for bamboo and wood products, characterized in that, The method includes the following steps: Image data of carbon footprint markers on bamboo and wood products to be verified are acquired through an image acquisition device. The image data is then subjected to noise reduction, perspective correction, and contrast enhancement in sequence. The type of marker carrier is identified, and the carrier content is read and decoded according to the corresponding protocol to obtain the original marker data string. Semantic parsing is performed on the original data string of the identifier to extract the product basic information field group, the key physical parameter field group, and the certification traceability information field group to obtain a structured field information set; the key physical parameter field group includes the carbon content of bamboo and wood materials, product density, moisture content, glue application amount, biomass carbon sequestration service years, and carbon emission coefficients at each life cycle stage; The key physical parameter field group is normalized according to a preset encoding rule to construct a scanning end parameter feature vector. A hash operation is performed on the scanning end parameter feature vector to obtain the scanning end parameter fingerprint. Using the certification batch number in the certification traceability information field group as the search key, a query is initiated to the trusted evidence storage node of the certification authority to obtain the certification end parameter feature vector, certification end parameter fingerprint, set of allowable error thresholds for each parameter field, and benchmark value of reasonable range of biomass carbon sequestration service years; The fingerprint of the scanning end parameter is compared with the fingerprint of the authentication end parameter. If they match, a full confidence score is assigned. If they do not match, the feature vector of the scanning end parameter is compared with the feature vector of the authentication end parameter field by field. Each field score is assigned according to the relationship between the deviation of each field and the allowable error threshold. At the same time, the declared value of the service years of biomass carbon sequestration is compared with the reasonable range benchmark value to determine its reasonableness. The scores of each field are weighted and summarized according to the preset weight to obtain the comprehensive credibility score. Based on the comprehensive credibility score and preset dual thresholds, a three-level classification judgment is performed to obtain the verification conclusion, and a structured verification report is generated that includes a complete list of identification fields, comparison results of each field, comprehensive credibility score, and abnormal field tracing prompts.

2. The intelligent identification and reliable verification method for carbon footprint identification of bamboo and wood products according to claim 1, characterized in that, The process of identifying the carrier type and reading and decoding the carrier content according to the corresponding protocol includes: The preprocessed image is used to locate the marked area and identify the type of the marked carrier, which is a QR code, an NFC chip, a digital printed label, or a combination thereof. For QR code carriers, adaptive threshold binarization is used to improve the decoding success rate. For NFC chip carriers, the chip content is read through the near-field communication protocol. If any necessary field is missing or the field format is abnormal during the decoding process, a field integrity error message is triggered and the name of the missing field is recorded, and the process does not proceed to the subsequent verification process.

3. The intelligent identification and reliable verification method for carbon footprint identification of bamboo and wood products according to claim 1, characterized in that, The structured field information set includes: The product basic information field group includes product type, rule type and version number, functional unit or declaration unit and life cycle stage covered by the system boundary; the key physical parameter field group also includes a set of carbon emission coefficients for each life cycle stage; the certification traceability information field group includes the certification body's unique identifier, certification batch number, verification timestamp and total carbon footprint declaration value; when any certification traceability field is missing, the system refuses to initiate a certification end query and outputs a field missing prompt.

4. The intelligent identification and reliable verification method for carbon footprint identification of bamboo and wood products according to claim 1, characterized in that, The process of constructing the feature vector of the scanning end parameters and performing a hash operation to obtain the fingerprint of the scanning end parameters includes: The parameters are arranged in a preset order according to carbon content, product density, moisture content, sizing amount, biomass carbon sequestration service years, and carbon emission coefficients at each stage. Continuous parameters are rounded and normalized according to a predetermined precision to construct a feature vector of scanning parameters. The feature vector of scanning parameters is then subjected to a SHA-256 hash operation, and the hash result is used as the fingerprint of scanning parameters. The parameter fingerprint serves as the basis for rapid integrity verification in subsequent steps. When the fingerprint of scanning parameters is inconsistent with the fingerprint of authentication parameters, a detailed field-by-field comparison process is directly triggered.

5. The intelligent identification and reliable verification method for carbon footprint identification of bamboo and wood products according to claim 1, characterized in that, The step of initiating a query to the trusted evidence storage node of the certification authority to obtain the certification end parameter feature vector and certification end parameter fingerprint includes: The trusted evidence storage node of the certification authority is a blockchain distributed evidence storage node. When the verification is passed, the certification authority will simultaneously upload the feature vector of the certification end parameter and the fingerprint of the certification end parameter to the blockchain for evidence storage, and bind them with the certification batch number and product QR code identifier through a three-party combined hash to ensure that the evidence storage data cannot be tampered with. The query request is initiated through a secure communication protocol, and the query result is accompanied by a digital signature so that the verifier can confirm the authenticity of the data source.

6. The intelligent identification and reliable verification method for carbon footprint identification of bamboo and wood products according to claim 1, characterized in that, The step of comparing the fingerprint parameters from the scanning end with the fingerprint parameters from the authentication end, and assigning a full confidence score if they match, includes: When the scanning end parameter fingerprint is completely consistent with the authentication end parameter fingerprint, it is determined that all parameter fields are completely consistent with the authentication end, and the comprehensive credibility score CS is directly assigned a full score of 1.

00. The detailed field-by-field comparison step is skipped, and the process directly enters the biomass carbon sequestration service years rationality verification and three-level classification determination steps. When the two are inconsistent, it is determined that at least one parameter field has changed, and the detailed field-by-field comparison process is initiated. Through the parameter fingerprint rapid verification mechanism, identifiers with unchanged parameters can quickly pass the verification, effectively reducing the computational overhead in large-scale identifier verification scenarios.

7. The intelligent identification and reliable verification method for carbon footprint identification of bamboo and wood products according to claim 1, characterized in that, The step of performing numerical comparison field by field and assigning scores to fields includes: When a field value is completely consistent with the corresponding field value at the certification end, the field is assigned a full score; when the field value deviation is within the allowable error threshold preset by the certification body, the field score is linearly reduced based on the ratio of the deviation to the threshold; when the field value deviation exceeds the allowable error threshold or the field is missing, the field score is recorded as zero and marked as an abnormal field; the allowable error threshold is preset by the certification body based on the measurement uncertainty of each parameter to distinguish between reasonable deviations caused by normal measurement errors and abnormal deviations caused by parameter tampering; carbon content and biomass carbon sequestration service years directly affect the biomass carbon storage calculation results and should be assigned a first weighting coefficient.

8. The intelligent identification and reliable verification method for carbon footprint identification of bamboo and wood products according to claim 1, characterized in that, The comparison of the declared service life of biomass carbon sequestration with a reasonable range benchmark value to determine its reasonableness includes: The declared value of the service life of biomass carbon sequestration is compared with the reasonable range benchmark value preset by the certification body based on the durability characteristics of the product type. When the declared value falls within the reasonable range, it passes the special reasonableness verification without being subject to additional penalty coefficients. When the declared value exceeds the upper limit of the reasonable range or falls below the lower limit of the reasonable range, a special anomaly mark is triggered, and a penalty coefficient is applied to the comprehensive credibility score to prevent the risk of artificially lowering the declared value of carbon footprint by falsely reporting the service life of biomass carbon sequestration.

9. The intelligent identification and reliable verification method for carbon footprint identification of bamboo and wood products according to claim 1, characterized in that, The verification conclusions obtained by performing a three-level classification based on a comprehensive credibility score and preset dual thresholds include: When the overall credibility score is not lower than the first confidence threshold T1, it is judged as "credible" and a credible verification conclusion is output; when the overall credibility score is between the second confidence threshold T2 and the first confidence threshold T1, it is judged as "doubtful" and a doubtful verification conclusion is output, with all abnormal field names and specific deviation values ​​marked in the report; when the overall credibility score is lower than the second confidence threshold T2, it is judged as "unreliable" and an unreliable verification conclusion is output, with complete difference details recorded; the structured verification report also includes the three-level classification conclusion and the special verification results of the service years of biomass carbon sequestration, which can be consulted and used by regulatory agencies, purchasers or consumers.

10. The intelligent identification and reliable verification method for carbon footprint identification of bamboo and wood products according to claim 9, characterized in that, When the verification conclusion is "questionable", the following batch cross-comparison steps are also performed: Using historical certification batch records of similar bamboo and wood products stored in the trusted evidence storage nodes of certification bodies as the data source, the total carbon footprint declaration value and corresponding output value of each historical batch are extracted, and the carbon productivity index of each historical batch is calculated. The carbon productivity index of the current batch to be verified is sorted with the carbon productivity data of the historical batches according to the carbon productivity value. The ordered samples are clustered using the Fisher optimal segmentation method to identify whether the carbon productivity index of the current batch deviates significantly from the historical normal distribution range. If the deviation exceeds the preset anomaly judgment threshold, the verification conclusion is upgraded to "unreliable", and a batch horizontal comparison anomaly prompt is added to the structured verification report to assist regulatory agencies in identifying systemic carbon footprint data false reporting issues.

Images