Copyright authentication precision optimization method and system based on block chain

Abstract

The invention is suitable for the technical field of block chain copyright authentication, and provides a copyright authentication precision optimization method and system based on a block chain, and the method comprises the steps: obtaining target test question data which is submitted by a user and is registered to a block chain platform, and obtaining initial ownership credibility determined for the target test question data, and meanwhile, obtaining a historical interaction record of the user in the block chain platform. According to the method, the first adjustment factor based on the user behavior trend and the second adjustment factor based on semantic similarity analysis are introduced, a calculation mechanism for dynamically correcting the ownership credibility of the test question data is constructed, and upgrading of copyright authentication from static claim to behavior-content two-way evaluation is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of blockchain copyright authentication, and in particular relates to a copyright authentication accuracy optimization method and system based on blockchain. Background Art

[0002] With the rapid development of educational digital content, test data, as a core teaching resource, is frequently created, edited, and distributed on various online platforms. To protect the rights and interests of content creators and regulate the order of content circulation, more and more teaching platforms are introducing blockchain-based copyright confirmation mechanisms, which store and identify test data submitted by users through on-chain registration. However, existing technologies often use static rules to judge the credibility of test claims, mainly relying on objective indicators such as submission time, content fingerprint matching, or basic information integrity. They ignore the actual behavioral characteristics of users on the platform and the stability of content claims. It is difficult to effectively identify unstable behaviors such as repeated claims, pseudo-originality, or inertial withdrawal, resulting in the risk of misjudgment of credibility in copyright certification.

[0003] Furthermore, existing technologies lack the ability to semantically analyze the correlation between current test data and a user's previously unstable test questions, making it impossible to assess the legitimacy of claims based on content similarity. This results in some easily confusing content not being properly handled during copyright verification. Therefore, a dynamic evaluation mechanism that combines historical user behavior trends with content semantic features is urgently needed to improve the accuracy and fairness of test question copyright verification. Summary of the Invention

[0004] The purpose of the present invention is to provide a copyright authentication accuracy optimization method and system based on blockchain, aiming to solve the problems raised in the background technology.

[0005] The present invention is implemented as follows: a blockchain-based copyright authentication accuracy optimization method, the method comprising:

[0006] Obtain target test question data submitted by the user and registered on the blockchain platform, obtain the initial ownership credibility determined for the target test question data, and obtain the user's historical interaction records on the blockchain platform;

[0007] Parse historical interaction records, extract historical test question data with consistent attributes with the target test question data, calculate the withdrawal and modification ratio of the target test question data and each copy of the historical test question data, and construct a withdrawal ratio curve in chronological order;

[0008] Determine whether the withdrawal and modification ratio of the target test question data is within the fitting interval of the withdrawal ratio curve; if so, determine a first adjustment factor according to a change trend of the withdrawal ratio curve;

[0009] Screening a number of representative test question data with a withdrawal modification ratio higher than a preset threshold, extracting semantic vectors of the modified segments in the target test question data and each representative test question data based on semantic analysis, calculating semantic similarity in turn, and determining a second adjustment factor based on the similarity results;

[0010] The initial ownership credibility is corrected by combining the first adjustment factor and the second adjustment factor to generate a corrected ownership credibility.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the steps of parsing historical interaction records, extracting historical test question data having consistent attributes with the target test question data, calculating the withdrawal and modification ratio of the target test question data to each piece of historical test question data, and constructing a withdrawal ratio curve in chronological order include:

[0012] Parse historical interaction records and filter out historical test question data that has consistent attributes with the target test question data. The consistent attributes include question type category, knowledge point label, and test question purpose type.

[0013] Obtain the number of revisions, withdrawals, and total submissions of the target test question data and each set of historical test question data, and calculate the ratio of the number of revisions to the total submissions and the ratio of the number of withdrawals to the total submissions, respectively, as the first ratio and the second ratio, and perform linear weighting on the first ratio and the second ratio to obtain the corresponding withdrawal-revision ratio;

[0014] A withdrawal ratio curve is constructed with the time sequence as the horizontal axis and the withdrawal modification ratio as the vertical axis.

[0015] As a further limitation of the technical solution of the embodiment of the present invention, the step of determining whether the withdrawal modification ratio of the target test question data is within the fitting interval of the withdrawal ratio curve, and if so, determining the first adjustment factor according to the change trend of the withdrawal ratio curve includes:

[0016] Substitute the withdrawal and modification ratio corresponding to the target test question data into the withdrawal ratio curve to determine whether its deviation within the fitting interval is less than a preset threshold;

[0017] If the offset amplitude is smaller than the preset threshold, the average slope of the withdrawal ratio curve is calculated and used as the first adjustment factor.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the steps of screening a plurality of representative test question data having a withdrawal modification ratio higher than a preset threshold, extracting semantic vectors of the modified segments in the target test question data and each representative test question data based on semantic analysis, and sequentially calculating semantic similarity, and determining the second adjustment factor based on the similarity results include:

[0019] Screening a preset number of representative test question data with a withdrawal and revision ratio higher than a preset threshold from historical test question data;

[0020] Based on semantic analysis, the semantic vectors of the modified segments in the target test data and each representative test data are extracted, and the semantic similarity between the target test data and each representative test data is calculated using cosine similarity;

[0021] An average value of a preset number of semantic similarities is calculated, and the average value is used as the second adjustment factor.

[0022] As a further limitation of the technical solution of the embodiment of the present invention, after the first adjustment factor and the second adjustment factor are determined, based on a preset ownership credibility correction formula, the first adjustment factor and the second adjustment factor are combined with the initial ownership credibility to generate a corrected ownership credibility;

[0023] The ownership credibility correction formula is: Where C refers to, C0 refers to the corrected ownership credibility, S refers to the first adjustment factor, that is, the average slope of the withdrawal rate curve, K1 refers to the adjustment coefficient corresponding to the first adjustment factor, n refers to the preset number, sim i Refers to the semantic similarity of the i-th representative test data, It refers to the second adjustment factor, that is, the average value of a preset number of semantic similarities, and K2 refers to the adjustment coefficient corresponding to the second adjustment factor.

[0024] A blockchain-based copyright authentication accuracy optimization system includes: a data acquisition module, a data screening module, a first adjustment factor determination module, a second adjustment factor determination module, and an ownership credibility correction module, wherein:

[0025] A data acquisition module is used to obtain target test question data submitted by the user and registered on the blockchain platform, obtain the initial ownership credibility determined for the target test question data, and obtain the user's historical interaction records on the blockchain platform;

[0026] The data screening module is used to parse historical interaction records, extract historical test question data with consistent attributes with the target test question data, calculate the withdrawal and modification ratio of the target test question data and each copy of the historical test question data, and construct a withdrawal ratio curve in chronological order;

[0027] A first adjustment factor determination module is used to determine whether the withdrawal and modification ratio of the target test question data is within the fitting interval of the withdrawal ratio curve, and if so, determine the first adjustment factor according to the change trend of the withdrawal ratio curve;

[0028] A second adjustment factor determination module is configured to screen a number of representative test question data having a withdrawal modification ratio higher than a preset threshold, extract semantic vectors of the modified segments in the target test question data and each representative test question data based on semantic analysis, calculate semantic similarity in sequence, and determine a second adjustment factor based on the similarity results;

[0029] The ownership credibility correction module is used to correct the initial ownership credibility by combining the first adjustment factor and the second adjustment factor to generate a corrected ownership credibility.

[0030] As a further limitation of the technical solution of the embodiment of the present invention, the data screening module specifically includes:

[0031] A data screening unit is used to parse historical interaction records and screen out historical test question data that has consistent attributes with the target test question data. The consistent attributes include question type category, knowledge point label, and test question purpose type;

[0032] a ratio calculation unit, configured to obtain the number of revisions, withdrawals, and total submissions of the target test question data and each copy of the historical test question data, and respectively calculate the ratio of the number of revisions to the total submissions, and the ratio of the number of withdrawals to the total submissions, as a first ratio and a second ratio, respectively, and linearly weight the first ratio and the second ratio to obtain a corresponding withdrawal-revision ratio;

[0033] The curve construction unit is used to construct a withdrawal ratio curve with the time sequence as the horizontal axis and the withdrawal modification ratio as the vertical axis.

[0034] As a further limitation of the technical solution of the embodiment of the present invention, the first adjustment factor determination module specifically includes:

[0035] a ratio matching judgment unit, configured to substitute the withdrawal modification ratio corresponding to the target test question data into the withdrawal ratio curve, and judge whether the deviation amplitude thereof within the fitting interval is less than a preset threshold;

[0036] The average slope calculation unit is configured to calculate an average slope of the withdrawal ratio curve if the offset amplitude is less than a preset threshold, and use the average slope as a first adjustment factor.

[0037] As a further limitation of the technical solution of the embodiment of the present invention, the second adjustment factor determination module specifically includes:

[0038] a representative data extraction unit, configured to screen a preset number of representative test question data having a withdrawal and modification ratio higher than a preset threshold value from the historical test question data;

[0039] a semantic similarity calculation unit, configured to extract semantic vectors of the modified segments in the target test question data and each representative test question data based on semantic analysis, and calculate semantic similarity between the target test question data and each representative test question data using cosine similarity;

[0040] The average value calculation unit is used to calculate an average value of a preset number of semantic similarities and use the average value as a second adjustment factor.

[0041] As a further limitation of the technical solution of the embodiment of the present invention, after the first adjustment factor and the second adjustment factor are determined, based on a preset ownership credibility correction formula, the first adjustment factor and the second adjustment factor are combined with the initial ownership credibility to generate a corrected ownership credibility;

[0042] The ownership credibility correction formula is: Where C refers to, C0 refers to the corrected ownership credibility, S refers to the first adjustment factor, that is, the average slope of the withdrawal rate curve, K1 refers to the adjustment coefficient corresponding to the first adjustment factor, n refers to the preset number, sim i Refers to the semantic similarity of the i-th representative test data, It refers to the second adjustment factor, that is, the average value of a preset number of semantic similarities, and K2 refers to the adjustment coefficient corresponding to the second adjustment factor.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention constructs a computational mechanism for dynamically correcting the credibility of test data ownership by introducing a first adjustment factor based on user behavior trends and a second adjustment factor based on semantic similarity analysis, thereby achieving an upgrade in copyright authentication from static assertions to behavior-content two-way evaluation. Compared with existing technologies that rely solely on timestamps or content fingerprints for authentication, the present invention can identify the stability of users' assertions and the risk of repeated behavior in specific content categories, improves the ability to handle complex situations such as pseudo-originality and repeated submissions, and enhances the objectivity and credibility of authentication evaluations. On the basis of ensuring the interpretability of the system, the present invention has good adaptability and foresight, which helps to improve the overall accuracy and robustness of copyright authentication on blockchain platforms. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of a method provided by an embodiment of the present invention;

[0046] Figure 2 A flow chart of constructing a withdrawal ratio curve in the method provided in an embodiment of the present invention;

[0047] Figure 3A flowchart of determining a first adjustment factor in the method provided in an embodiment of the present invention;

[0048] Figure 4 A flowchart of determining a second adjustment factor in the method provided in an embodiment of the present invention;

[0049] Figure 5 An application architecture diagram of the system provided by an embodiment of the present invention;

[0050] Figure 6 A structural block diagram of a data screening module in a system provided by an embodiment of the present invention;

[0051] Figure 7 A structural block diagram of a first adjustment factor determination module in a system provided by an embodiment of the present invention;

[0052] Figure 8 This is a structural block diagram of a second adjustment factor determination module in a system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0055] Specifically, a copyright authentication accuracy optimization method based on blockchain includes the following steps:

[0056] Step S100: Obtain target test question data submitted by the user and registered on the blockchain platform, obtain the initial ownership credibility determined for the target test question data, and simultaneously obtain the user's historical interaction records on the blockchain platform.

[0057] In embodiments of the present invention, the present invention is applicable to blockchain platform scenarios related to the confirmation of ownership of educational content, and is particularly applicable to teaching resource platforms, online examination platforms, and teaching content creation and distribution platforms centered around a question bank system. On these platforms, users typically submit structured teaching resources such as test questions as content creators and hope to obtain credible copyright claim records to avoid plagiarism, controversial claims, or duplicate publication by others. By constructing a behavior-driven dynamic adjustment mechanism, the present invention enables copyright authentication to not only rely on static information, but also comprehensively considers the historical behavior patterns of users on the platform, thereby improving the scientific nature and pertinence of the judgment of the credibility of ownership confirmation.

[0058] Target test question data submitted and registered on the blockchain platform by users refers to teaching resource data created or uploaded by users to the platform for copyright verification. This data is then verified, timestamped, and stored through the blockchain platform's on-chain registration process. This target test question data can be a single question, a test book consisting of multiple questions, or a structured document containing a set of questions. It typically includes fields such as the question stem, options, answer, explanation, question type, applicable grade level, and knowledge point labels. The platform can hash these core fields or summary information to ensure that the content is tamper-proof and traceable.

[0059] The initial ownership credibility determined for the target test data can be obtained through existing technical means. Typically, during the initial stages of ownership confirmation, existing platforms generate preliminary credibility scores for users based on objective static characteristics, such as the chronological order of submission, content completeness, fingerprint duplication with existing resources on the platform, the submitter's identity verification level, and whether it is the first publication. These methods are primarily implemented through content fingerprint comparison, metadata analysis, and account-level information filtering. They are used to generate basic ownership judgment results, which serve as input parameters for subsequent dynamic adjustment mechanisms.

[0060] The historical interaction records of users in the blockchain platform can be continuously recorded and synchronized with the chain by the platform, usually obtained by combining the operation behavior log with the hash of the chain record. The interaction record includes at least the user's test question uploading behavior, modification operation, withdrawal operation, copyright claim time point, failed confirmation record, dispute history, authorization behavior and the historically uploaded test question data itself. The historically uploaded test question data includes the test question content submitted by the user and its metadata information, which may specifically include structured fields such as question stem, options, answers, analysis, question type classification, knowledge point tags, and the corresponding confirmation status, modification record and version number of the test question data. The above-mentioned interaction records can be extracted after cross-validation with the platform database through the data structure on the blockchain side (such as the timestamp event sequence in the block, contract execution log, etc.) to form a time-series behavior data set as the basis for subsequent behavior evaluation and factor generation.

[0061] Furthermore, the blockchain-based copyright authentication accuracy optimization method further includes the following steps:

[0062] Step S200 , parsing historical interaction records, extracting historical test question data having consistent attributes with the target test question data, calculating the withdrawal and modification ratio of the target test question data to each copy of the historical test question data, and constructing a withdrawal ratio curve in chronological order.

[0063] Specifically, Figure 2 A flow chart for constructing a withdrawal ratio curve is shown.

[0064] The steps of parsing historical interaction records, extracting historical test question data with consistent attributes with the target test question data, calculating the withdrawal and modification ratio of the target test question data to each copy of the historical test question data, and constructing a withdrawal ratio curve in chronological order include the following:

[0065] Step S201: parsing historical interaction records to filter out historical test question data that have consistent attributes with the target test question data, where the consistent attributes include question type category, knowledge point label, and test question purpose type;

[0066] Step S202: Obtain the number of revisions, withdrawals, and total submissions for the target test question data and each set of historical test question data, and calculate the ratio of the number of revisions to the total submissions, and the ratio of the number of withdrawals to the total submissions, respectively, as a first ratio and a second ratio. Linearly weight the first ratio and the second ratio to obtain a corresponding withdrawal-revision ratio.

[0067] In step S203 , a withdrawal ratio curve is constructed with the time sequence as the horizontal axis and the withdrawal modification ratio as the vertical axis.

[0068] In this embodiment of the present invention, consistent attributes can be not only attributes that are completely consistent with the target test question data, but also attribute combinations that share similarities in question type, knowledge point label, or test question usage type. By introducing a fuzzy matching or label nesting relationship judgment mechanism, a certain degree of semantic extensibility is allowed, making the selected historical test question data more contextually relevant, thereby enhancing the reference value of subsequent behavior analysis and the stability of the correction results.

[0069] After obtaining the number of revisions, withdrawals, and total submissions for the target question data and each set of historical question data, the ratios of revisions to submissions and withdrawals to submissions are calculated as the first and second ratios, respectively. This step can be accomplished by retrieving the user's historical records for the corresponding question identifier from the platform's behavior log. The total submission count is the cumulative number of submissions completed for a question throughout its lifecycle, while the revision and withdrawal counts are calculated based on the user's history of actions, such as editing or deleting the question. The first and second ratios are then linearly weighted, using a weighting function such as: Withdrawal / Revision Ratio = α × First Ratio + β × Second Ratio, where α and β are pre-set weighting coefficients. This weighted calculation step serves to quantitatively model the stability of users' claims regarding a particular type of content, providing a unified standard metric for subsequent trend analysis and credibility correction. Compared to analyzing only revisions or withdrawals, using a combined ratio provides a more comprehensive reflection of users' behavioral tendencies and content control.

[0070] When constructing the withdrawal ratio curve, the time sequence is used as the horizontal axis and the withdrawal modification ratio is used as the vertical axis. Existing data visualization and time series modeling technologies can be used to achieve this. Specifically, by reading the withdrawal modification ratio values ​​of target users for the same attribute test questions at different time points, a time series data point set can be constructed, and then the data point sequence is smoothed using interpolation, spline fitting, or regression fitting methods to form a trend curve. The curve construction process can call existing time series analysis tools (such as Python's pandas, matplotlib, regression models in the scikit-learn library, or built-in functions in the database). Through this step, the user's behavioral evolution pattern in a specific content category can be more clearly revealed, providing dynamic quantitative support for behavioral credibility.

[0071] Furthermore, the blockchain-based copyright authentication accuracy optimization method further includes the following steps:

[0072] Step S300 , determining whether the withdrawal modification ratio of the target test question data is within the fitting interval of the withdrawal ratio curve; if so, determining a first adjustment factor according to the variation trend of the withdrawal ratio curve.

[0073] Specifically, Figure 3 A flow chart for determining a first adjustment factor is shown.

[0074] The step of determining whether the withdrawal and modification ratio of the target test question data is within the fitting interval of the withdrawal ratio curve, and if so, determining the first adjustment factor according to the change trend of the withdrawal ratio curve specifically includes the following steps:

[0075] Step S301: Substitute the withdrawal and modification ratio corresponding to the target test question data into the withdrawal ratio curve to determine whether the deviation within the fitting interval is less than a preset threshold;

[0076] Step S302 : If the offset amplitude is smaller than the preset threshold, the average slope of the withdrawal ratio curve is calculated and used as the first adjustment factor.

[0077] In an embodiment of the present invention, the withdrawal modification ratio corresponding to the target test question data is substituted into the withdrawal ratio curve, and the offset amplitude within the fitting interval is determined to be less than a preset threshold. This is to determine whether the behavioral performance of the test question data is consistent with the user's historical behavioral trend on similar test questions. This judgment operation can effectively filter out abnormal or non-representative data points, avoiding unreasonable interference with the credibility assessment results due to isolated fluctuations or occasional behaviors. When the offset amplitude is small, it means that the behavioral characteristics of the test question data are highly consistent with the user's past performance on this type of test question, are statistically representative, and provide a basis for further slope trend analysis.

[0078] After determining that the conditions are met, this can be achieved by calculating the average slope of the withdrawal ratio curve, using derivative estimation methods based on time series data. Common techniques include using first-order differences, local linear regression, and least squares fitting within a preset time window to approximate the slope of multiple data points of the ratio curve.

[0079] The main significance of using the average slope as the first adjustment factor is to introduce the ability to dynamically correct the initial ownership credibility by the evolution trend of user behavior. The average slope reflects whether the user's withdrawal and modification behavior on this type of test data is on a downward trend (behavior tends to be stable) or an upward trend (behavior fluctuations intensify). If the average slope is negative, it means that the stability of the user's claim for this type of content has increased, and its credibility should be adjusted upward; if it is positive, it means that the claim behavior is still unstable, and the credibility should be conservatively corrected or lowered. Therefore, this factor has the dual functions of quantifying behavioral trends and guiding the direction of correction, which can effectively enhance the rationality and timeliness of the calculation results of the title confirmation credibility.

[0080] Furthermore, the blockchain-based copyright authentication accuracy optimization method further includes the following steps:

[0081] Step S400, screen several representative test question data with a withdrawal modification ratio higher than a preset threshold, extract the semantic vectors of the target test question data and the modified segments in each representative test question data based on semantic analysis, calculate the semantic similarity in turn, and determine the second adjustment factor based on the similarity result.

[0082] Specifically, Figure 4 A flow chart for determining the second adjustment factor is shown.

[0083] The steps of screening a number of representative test question data with a withdrawal modification ratio higher than a preset threshold, extracting semantic vectors of the modified segments in the target test question data and each representative test question data based on semantic analysis, and calculating semantic similarity in sequence, and determining the second adjustment factor based on the similarity results specifically include the following steps:

[0084] Step S401, screening a preset number of representative test question data with a withdrawal and modification ratio higher than a preset threshold from historical test question data;

[0085] Step S402: extracting semantic vectors of the modified segments in the target test data and each representative test data based on semantic analysis, and calculating the semantic similarity between the target test data and each representative test data using cosine similarity;

[0086] Step S403 : Calculate an average value of a preset number of semantic similarities, and use the average value as a second adjustment factor.

[0087] In embodiments of the present invention, the preset threshold can be adjusted based on the platform's statistical results of user behavior stability classification. Typically, a threshold is selected based on a significant fluctuation in a specific behavior. For example, after statistically analyzing the historical distribution of withdrawal and modification rates across all users, the top 25% or top 10% is used as the threshold. This threshold is intended to filter out sample data that exhibits relatively unstable withdrawal and modification behavior within the context of this type of test question attributes, thereby identifying content that users have been prone to repetitively asserting or lacking confidence in, serving as a reference for determining current test question behavior patterns.

[0088] We screen a preset number of representative test questions from historical test data, each with a withdrawal and modification rate exceeding a preset threshold. This is done to ensure the quality of representative behavioral data samples while controlling computing resources and similarity calculation complexity. This preset number can be set based on system resources and assessment accuracy requirements, such as 5, 10, or 20 questions. Generally, we recommend a limit of 10 to avoid sample dilution, which can lead to overly smoothed semantic similarity means and reduced discrimination.

[0089] During the semantic analysis implementation process, the first step is to extract the modified segments between the target test data and the representative test data. This typically includes differences in core fields such as the question stem, option content, and parsing statements. After extraction, the text is segmented and encoded, and existing semantic vector modeling methods such as BERT, Sentence-BERT, and SimCSE are used to map the text content into a fixed-dimensional semantic vector. Cosine similarity is then used to calculate the degree of similarity between the angles between the target test data and the vectors of each representative test data. This method has been widely used for semantic similarity calculation in the field of natural language processing. It is mature, easy to deploy, and supports implementation based on mainstream frameworks such as TensorFlow and PyTorch.

[0090] The significance of calculating the average value of the preset number of semantic similarities and using the average value as the second adjustment factor is to quantify the strength of the semantic association between the current test question and the historical high-volatility test questions. When the average value of semantic similarity is high, it means that the current test question is highly similar in content expression or structure to the test questions that the user has frequently modified or withdrawn in the past. It may be repeated in the unstable area of ​​the claim, and its credibility should be conservatively adjusted; when the average value of similarity is low, it means that the current test question has a certain degree of independence and does not belong to the "inertial content" repeatedly claimed by users. Its claim has a more credible basis. This indicator can assist the system in identifying potential duplication, rewriting or pseudo-original behavior from a semantic level, and enhance the content pertinence and behavior explanatory power of the overall adjustment logic.

[0091] Furthermore, the blockchain-based copyright authentication accuracy optimization method further includes the following steps:

[0092] Step S500: After the first adjustment factor and the second adjustment factor are determined, the first adjustment factor and the second adjustment factor are combined with the initial ownership credibility based on a preset ownership credibility correction formula to generate a corrected ownership credibility.

[0093] The ownership credibility correction formula is: Where C refers to, C0 refers to the corrected ownership credibility, S refers to the first adjustment factor, that is, the average slope of the withdrawal rate curve, K1 refers to the adjustment coefficient corresponding to the first adjustment factor, n refers to the preset number, sim i Refers to the semantic similarity of the i-th representative test data, It refers to the second adjustment factor, that is, the average value of a preset number of semantic similarities, and K2 refers to the adjustment coefficient corresponding to the second adjustment factor.

[0094] In this embodiment of the present invention, by combining the first and second adjustment factors to jointly modify the initial ownership credibility, a more comprehensive reflection of the user's assertion behavior characteristics on the target test question data can be achieved. The first adjustment factor, based on the changing trend of the withdrawal and modification rate curve, depicts the evolution of user assertion behavior over time, with strong time sensitivity and the ability to express behavioral trends. The second adjustment factor, through semantic similarity calculation, introduces the semantic correlation between the current content and previously unstable content, enhancing the ability to identify potential duplicate assertions, pseudo-originality, or templated creation behavior.

[0095] The combination of the two not only shifts the credibility correction process from a single dimension to a multi-dimensional behavior-content fusion, but also makes the system's understanding of user claims more contextually continuous and insightful. This structure offers the added advantage of learning users' "habitual behavior patterns" and proactively identifying content implied by risk factors without explicitly marking untrustworthy content, thereby enabling a more forward-looking logic for determining claim credibility. Compared to traditional rule-based or static indicator-based judgment methods, this approach demonstrates greater adaptability and stronger anomaly recognition capabilities in actual deployments, providing structural support for improving the accuracy and anti-circumvention capabilities of the platform's title confirmation system.

[0096] Further, Figure 5 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0097] In another preferred embodiment of the present invention, a copyright authentication accuracy optimization system based on blockchain includes:

[0098] The data acquisition module 100 is used to obtain the target test question data submitted by the user and registered on the blockchain platform, obtain the initial ownership credibility determined for the target test question data, and obtain the user's historical interaction records in the blockchain platform.

[0099] Furthermore, the copyright authentication accuracy optimization system based on blockchain also includes:

[0100] The data screening module 200 is used to parse historical interaction records, extract historical test question data with consistent attributes with the target test question data, calculate the withdrawal and modification ratio of the target test question data and each historical test question data, and construct a withdrawal ratio curve in chronological order.

[0101] Specifically, Figure 6 FIG. 2 shows a structural block diagram of a data screening module 200 in a system provided by an embodiment of the present invention.

[0102] In a preferred embodiment of the present invention, the data screening module 200 specifically includes:

[0103] The data screening unit 201 is used to parse the historical interaction records and screen out the historical test question data having the same attributes as the target test question data, wherein the same attributes include question type category, knowledge point label and test question purpose type;

[0104] The ratio calculation unit 202 is used to obtain the number of revisions, withdrawals, and total submissions of the target test question data and each piece of historical test question data, and respectively calculate the ratio of the number of revisions to the total submissions and the ratio of the number of withdrawals to the total submissions as a first ratio and a second ratio, respectively, and linearly weight the first ratio and the second ratio to obtain a corresponding withdrawal-revision ratio;

[0105] The curve construction unit 203 is used to construct a withdrawal ratio curve with the time sequence as the horizontal axis and the withdrawal modification ratio as the vertical axis.

[0106] Furthermore, the copyright authentication accuracy optimization system based on blockchain also includes:

[0107] The first adjustment factor determination module 300 is used to determine whether the withdrawal modification ratio of the target test question data is within the fitting interval of the withdrawal ratio curve. If so, the first adjustment factor is determined according to the change trend of the withdrawal ratio curve.

[0108] Specifically, Figure 7 FIG. 4 shows a structural block diagram of the first adjustment factor determination module 300 in the system provided by an embodiment of the present invention.

[0109] In a preferred embodiment of the present invention, the first adjustment factor determination module 300 specifically includes:

[0110] The ratio matching judgment unit 301 is used to substitute the withdrawal modification ratio corresponding to the target test question data into the withdrawal ratio curve and judge whether the deviation amplitude within the fitting interval is less than a preset threshold;

[0111] The average slope calculation unit 302 is configured to calculate an average slope of the withdrawal ratio curve if the offset amplitude is less than a preset threshold, and use the average slope as a first adjustment factor.

[0112] Furthermore, the copyright authentication accuracy optimization system based on blockchain also includes:

[0113] The second adjustment factor determination module 400 is used to screen several representative test question data with a withdrawal modification ratio higher than a preset threshold, extract the semantic vectors of the modified fragments in the target test question data and each representative test question data based on semantic analysis, calculate the semantic similarity in turn, and determine the second adjustment factor based on the similarity result.

[0114] Specifically, Figure 8 FIG. 4 is a structural block diagram of a second adjustment factor determination module 400 in a system provided by an embodiment of the present invention.

[0115] In a preferred embodiment of the present invention, the second adjustment factor determination module 400 specifically includes:

[0116] The representative data extraction unit 401 is used to select a preset number of representative test question data with a withdrawal and modification ratio higher than a preset threshold from the historical test question data;

[0117] A semantic similarity calculation unit 402 is configured to extract semantic vectors of the modified segments of the target test question data and each representative test question data based on semantic analysis, and calculate semantic similarity between the target test question data and each representative test question data using cosine similarity;

[0118] The average value calculation unit 403 is configured to calculate an average value of a preset number of semantic similarities and use the average value as a second adjustment factor.

[0119] Furthermore, the copyright authentication accuracy optimization system based on blockchain also includes:

[0120] The ownership credibility correction module 500 is used to correct the initial ownership credibility by combining the first adjustment factor and the second adjustment factor to generate a corrected ownership credibility.

[0121] After the first adjustment factor and the second adjustment factor are determined, based on a preset ownership credibility correction formula, the first adjustment factor and the second adjustment factor are combined with the initial ownership credibility to generate a corrected ownership credibility;

[0122] The ownership credibility correction formula is: Where C refers to, C0 refers to the corrected ownership credibility, S refers to the first adjustment factor, that is, the average slope of the withdrawal rate curve, K1 refers to the adjustment coefficient corresponding to the first adjustment factor, n refers to the preset number, sim i Refers to the semantic similarity of the i-th representative test data, It refers to the second adjustment factor, that is, the average value of a preset number of semantic similarities, and K2 refers to the adjustment coefficient corresponding to the second adjustment factor.

[0123] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0124] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0125] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0126] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0127] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A copyright authentication accuracy optimization method based on blockchain, characterized in that: The method comprises: Obtain target test question data submitted by the user and registered on the blockchain platform, obtain the initial ownership credibility determined for the target test question data, and obtain the user's historical interaction records on the blockchain platform; Parse historical interaction records, extract historical test question data with consistent attributes with the target test question data, calculate the withdrawal and modification ratio of the target test question data and each copy of the historical test question data, and construct a withdrawal ratio curve in chronological order; Determine whether the withdrawal and modification ratio of the target test question data is within the fitting interval of the withdrawal ratio curve; if so, determine a first adjustment factor according to a change trend of the withdrawal ratio curve; Screening a number of representative test question data with a withdrawal modification ratio higher than a preset threshold, extracting semantic vectors of the modified segments in the target test question data and each representative test question data based on semantic analysis, calculating semantic similarity in turn, and determining a second adjustment factor based on the similarity results; The initial ownership credibility is corrected by combining the first adjustment factor and the second adjustment factor to generate a corrected ownership credibility.

2. The copyright authentication accuracy optimization method based on blockchain according to claim 1 is characterized in that: The steps of parsing historical interaction records, extracting historical test question data having consistent attributes with the target test question data, calculating the withdrawal and modification ratio of the target test question data and each piece of historical test question data, and constructing a withdrawal ratio curve in chronological order include: Parse historical interaction records and filter out historical test question data that has consistent attributes with the target test question data. The consistent attributes include question type category, knowledge point label, and test question purpose type. Obtain the number of revisions, withdrawals, and total submissions of the target test question data and each set of historical test question data, and calculate the ratio of the number of revisions to the total submissions and the ratio of the number of withdrawals to the total submissions, respectively, as the first ratio and the second ratio, and perform linear weighting on the first ratio and the second ratio to obtain the corresponding withdrawal-revision ratio; A withdrawal ratio curve is constructed with the time sequence as the horizontal axis and the withdrawal modification ratio as the vertical axis.

3. The copyright authentication accuracy optimization method based on blockchain according to claim 2 is characterized in that: The step of determining whether the withdrawal and modification ratio of the target test question data is within the fitting interval of the withdrawal ratio curve, and if so, determining the first adjustment factor according to the change trend of the withdrawal ratio curve includes: Substitute the withdrawal and modification ratio corresponding to the target test question data into the withdrawal ratio curve to determine whether its deviation within the fitting interval is less than a preset threshold; If the offset amplitude is smaller than the preset threshold, the average slope of the withdrawal ratio curve is calculated and used as the first adjustment factor.

4. The copyright authentication accuracy optimization method based on blockchain according to claim 3 is characterized in that: The steps of screening a number of representative test question data having a withdrawal modification ratio higher than a preset threshold, extracting semantic vectors of the modified segments in the target test question data and each representative test question data based on semantic analysis, and sequentially calculating semantic similarity, and determining the second adjustment factor based on the similarity results include: Screening a preset number of representative test question data with a withdrawal and revision ratio higher than a preset threshold from historical test question data; Based on semantic analysis, the semantic vectors of the modified segments in the target test data and each representative test data are extracted, and the semantic similarity between the target test data and each representative test data is calculated using cosine similarity; An average value of a preset number of semantic similarities is calculated, and the average value is used as the second adjustment factor.

5. The copyright authentication accuracy optimization method based on blockchain according to claim 4 is characterized in that: After the first adjustment factor and the second adjustment factor are determined, based on a preset ownership credibility correction formula, the first adjustment factor and the second adjustment factor are combined with the initial ownership credibility to generate a corrected ownership credibility; The ownership credibility correction formula is: Where C refers to, C0 refers to the corrected ownership credibility, S refers to the first adjustment factor, that is, the average slope of the withdrawal rate curve, K1 refers to the adjustment coefficient corresponding to the first adjustment factor, n refers to the preset number, sim i Refers to the semantic similarity of the i-th representative test data, It refers to the second adjustment factor, that is, the average value of a preset number of semantic similarities, and K2 refers to the adjustment coefficient corresponding to the second adjustment factor.

6. A copyright authentication precision optimization system based on blockchain, characterized in that: The system includes: a data acquisition module, a data screening module, a first adjustment factor determination module, a second adjustment factor determination module, and an ownership credibility correction module, wherein: A data acquisition module is used to obtain target test question data submitted by the user and registered on the blockchain platform, obtain the initial ownership credibility determined for the target test question data, and obtain the user's historical interaction records on the blockchain platform; The data screening module is used to parse historical interaction records, extract historical test question data with consistent attributes with the target test question data, calculate the withdrawal and modification ratio of the target test question data and each copy of the historical test question data, and construct a withdrawal ratio curve in chronological order; A first adjustment factor determination module is used to determine whether the withdrawal and modification ratio of the target test question data is within the fitting interval of the withdrawal ratio curve, and if so, determine the first adjustment factor according to the change trend of the withdrawal ratio curve; A second adjustment factor determination module is configured to screen a number of representative test question data having a withdrawal modification ratio higher than a preset threshold, extract semantic vectors of the modified segments in the target test question data and each representative test question data based on semantic analysis, calculate semantic similarity in sequence, and determine a second adjustment factor based on the similarity results; The ownership credibility correction module is used to correct the initial ownership credibility by combining the first adjustment factor and the second adjustment factor to generate a corrected ownership credibility.

7. The copyright authentication precision optimization system based on blockchain according to claim 6 is characterized in that: The data screening module specifically includes: A data screening unit is used to parse historical interaction records and screen out historical test question data that has consistent attributes with the target test question data. The consistent attributes include question type category, knowledge point label, and test question purpose type; a ratio calculation unit, configured to obtain the number of revisions, withdrawals, and total submissions of the target test question data and each copy of the historical test question data, and respectively calculate the ratio of the number of revisions to the total submissions, and the ratio of the number of withdrawals to the total submissions, as a first ratio and a second ratio, respectively, and linearly weight the first ratio and the second ratio to obtain a corresponding withdrawal-revision ratio; The curve construction unit is used to construct a withdrawal ratio curve with the time sequence as the horizontal axis and the withdrawal modification ratio as the vertical axis.

8. The copyright authentication precision optimization system based on blockchain according to claim 7 is characterized in that: The first adjustment factor determination module specifically includes: a ratio matching judgment unit, configured to substitute the withdrawal modification ratio corresponding to the target test question data into the withdrawal ratio curve, and judge whether the deviation amplitude thereof within the fitting interval is less than a preset threshold; The average slope calculation unit is configured to calculate an average slope of the withdrawal ratio curve if the offset amplitude is less than a preset threshold, and use the average slope as a first adjustment factor.

9. The blockchain-based copyright authentication accuracy optimization system according to claim 8 is characterized in that: The second adjustment factor determination module specifically includes: a representative data extraction unit, configured to screen a preset number of representative test question data having a withdrawal and modification ratio higher than a preset threshold value from the historical test question data; a semantic similarity calculation unit, configured to extract semantic vectors of the modified segments in the target test question data and each representative test question data based on semantic analysis, and calculate semantic similarity between the target test question data and each representative test question data using cosine similarity; The average value calculation unit is used to calculate an average value of a preset number of semantic similarities and use the average value as a second adjustment factor.

10. The copyright authentication precision optimization system based on blockchain according to claim 9 is characterized in that: After the first adjustment factor and the second adjustment factor are determined, based on a preset ownership credibility correction formula, the first adjustment factor and the second adjustment factor are combined with the initial ownership credibility to generate a corrected ownership credibility; The ownership credibility correction formula is: Where C refers to, C0 refers to the corrected ownership credibility, S refers to the first adjustment factor, that is, the average slope of the withdrawal rate curve, K1 refers to the adjustment coefficient corresponding to the first adjustment factor, n refers to the preset number, sim i Refers to the semantic similarity of the i-th representative test data, It refers to the second adjustment factor, that is, the average value of a preset number of semantic similarities, and K2 refers to the adjustment coefficient corresponding to the second adjustment factor.

Images