Digital asset right confirmation method and system based on continuous education process data

Abstract

The invention discloses a digital asset right confirmation method and system based on continuous education process data, and relates to the technical field of digital asset right confirmation, and the method comprises the steps: collecting the fine-grained behavior data of a learner in an education platform, carrying out the data cleaning and abnormal behavior recognition, and obtaining a continuous education process data sequence; based on a continuous education process data sequence, constructing and dynamically updating a time evolution sequence of a multi-dimensional ability vector, and reflecting a growth trajectory of a learner in the aspects of knowledge mastering, thinking development, collaborative participation and practical innovation; carrying out weighted integration on the time evolution sequence of the multi-dimensional capability vector, generating a capability evolution track reflecting the dynamic characteristics of the learning process, and generating a capability evolution fingerprint abstract according to the capability evolution track; and combining the capability evolution fingerprint abstract, analyzing the causal relationship between the learning behavior event and the capability change, identifying the influence of the key learning activity on the capability improvement, and generating a capability improvement attribution label containing the causal strength.

Description

Technical Field

[0001] This invention relates to the field of digital asset ownership confirmation technology, and in particular to a method and system for digital asset ownership confirmation based on continuous education process data. Background Technology

[0002] Digital asset ownership verification technology refers to a technical system that uses technological means to uniquely identify, determine ownership of, record the status of, and verify the authenticity of digital assets (such as learning outcomes, skill certificates, and creative content). Its core objective is to address the questions of who owns what, when, and whether the asset is genuine and valid. Therefore, how to utilize advanced technologies to improve the intelligence and security of digital asset ownership verification has become one of the most pressing issues to be addressed.

[0003] In the field of digital asset ownership confirmation, traditional digital certificates are mostly stored in static PDF or image form, lacking a strong binding relationship with the underlying data, making them easy to copy, tamper with, or forge. Existing blockchain evidence storage mostly adopts the result-on-chain mode, without incorporating process data and causal explanations into the ownership confirmation system, resulting in the inability to verify the authenticity of the content during verification. Furthermore, data is fragmented between different educational platforms, and learning records are distributed in a fragmented manner, making it impossible to form a coherent learning path. Existing technologies lack modeling of learning version evolution and knowledge dependencies, resulting in the inability to achieve cross-institutional and cross-stage integration and traceability of learning outcomes. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a digital asset ownership confirmation method based on continuous educational process data. This addresses the problems of traditional digital certificates being stored mostly in static PDF or image format, lacking a strong binding relationship with the underlying data, making them easy to copy, tamper with, or forge. Existing blockchain evidence storage mostly adopts the result-on-chain mode, failing to incorporate process data and causal explanations into the ownership confirmation system, resulting in the inability to verify the authenticity of the content during verification. Furthermore, data is fragmented between different educational platforms, and learning records are distributed in a fragmented manner, making it impossible to form a coherent learning path. Existing technologies lack modeling of learning version evolution and knowledge dependencies, resulting in the inability to achieve cross-institutional and cross-stage integration and traceability of learning outcomes.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for confirming ownership of digital assets based on continuous education process data, which includes: Collect fine-grained behavioral data of learners on the education platform, perform data cleaning and abnormal behavior identification, and obtain a continuous educational process data sequence; Based on the continuous educational process data sequence, a time evolution sequence of multidimensional ability vectors is constructed and dynamically updated to reflect learners’ growth trajectory in knowledge acquisition, thinking development, collaborative participation and practical innovation. The time evolution sequence of multidimensional capability vectors is weighted and integrated to generate capability evolution trajectories that reflect the dynamic characteristics of the learning process, and capability evolution fingerprint summaries are generated accordingly. By combining capability evolution fingerprint summaries, we analyze the causal relationship between learning behavior events and capability changes, identify the impact of key learning activities on capability improvement, and generate capability improvement attribution labels containing causal strength. The capability evolution fingerprint summary and capability enhancement attribution label are encapsulated into composite ownership data and written into a phylogenetic directed acyclic graph maintained by the education alliance nodes. Certificate nodes containing version inheritance and path dependency relationships are established to form anchor records. Digital certificates containing visual charts and invisible watermarks are generated based on anchored records. When a verification request is received, the watermark information in the certificate image is extracted and compared with the original data in the phylogenetic directed acyclic graph to complete the certificate authenticity verification.

[0007] As a preferred embodiment of the digital asset ownership confirmation method based on continuous education process data described in this invention, the specific steps of collecting fine-grained behavioral data of learners on the education platform, performing data cleaning and abnormal behavior identification to obtain a continuous education process data sequence are as follows: Obtain learners' video viewing logs, chapter access records, quiz answer data, assignment submission information, discussion forum posts, and project completion status generated in the online education system to form a raw behavioral dataset; Timestamp alignment is performed on each record in the original behavior dataset; Behavioral data is collected according to learner identifiers and arranged in chronological order to form a raw behavioral sequence with time as the axis. For the original behavior sequence, analyze the distribution of time intervals between adjacent behaviors to identify data segments whose time intervals deviate from the normal learning rhythm; Calculate the operation frequency of each behavioral event. When the number of operations per unit time exceeds the reasonable threshold set by the system, it is marked as a suspected anomaly. By combining the logical coherence of the behavioral sequence, we can determine whether there are operational patterns that violate the learning pattern, such as completing a test without watching a video or submitting assignments in batches within a short period of time. Isolate the behavioral data that is marked as abnormal, and retain the rest of the data; The processed behavioral data is re-sorted by time to generate an educational process data sequence.

[0008] As a preferred embodiment of the digital asset ownership confirmation method based on continuous educational process data described in this invention, the step of constructing and dynamically updating a time evolution sequence of a multi-dimensional ability vector based on a continuous educational process data sequence, reflecting the learner's growth trajectory in knowledge acquisition, thinking development, collaborative participation, and practical innovation, specifically includes the following steps: The behavioral types in the continuous educational process data sequence are mapped to the corresponding ability dimensions, where the knowledge point test score is the input variable for the knowledge mastery dimension, the depth of question posing and the length of the reasoning chain are the input variables for the thinking development dimension, the number of group task participations and the quality of peer evaluation are the input variables for the collaborative participation dimension, and the project result evaluation level is the input variable for the practical innovation dimension. The historical observations of each capability dimension are used to construct a time series, and an exponential smoothing model is used to model them. set up For the first A score for a specific ability dimension at any given time. The observed value at the current moment, The smoothed value from the previous time step is expressed as: ; smoothness coefficient It is adaptively adjusted based on data volatility to control the weight of the impact of new observations on the current score; Perform the above update process on each of the four capability dimensions to generate a multidimensional capability vector sequence that evolves over time. Each component corresponds to a dynamic score for a capability dimension.

[0009] As a preferred embodiment of the digital asset ownership confirmation method based on continuous education process data described in this invention, the specific steps of weighted integration of the time evolution sequence of multi-dimensional ability vectors to generate an ability evolution trajectory reflecting the dynamic characteristics of the learning process, and generating an ability evolution fingerprint summary accordingly, are as follows: Extract a length of [length] from the multidimensional capability vector sequence. All vectors within the sliding time window ,in This represents a point in time within the window, with a value range of [tw,t]. For each moment within the window Weights are assigned to the capability vector The weights decay exponentially over time, as expressed by: ; Where the attenuation parameter Pre-set by the system to reflect the greater influence of recent performance on overall competence assessment; Calculate the weighted capability trajectory vector Its components are approximations of the weighted integrals of each capability dimension within the window, expressed as: ; For the weighted capability trajectory vector Normalization is performed to eliminate the dimensional differences between different capability dimensions, resulting in a normalized vector. ; Will The learner's anonymous identifier is concatenated with the learner's anonymous identifier and then input into a cryptographic hash function to generate a capability evolution fingerprint digest, which is used to uniquely represent the learning process characteristics within that time period.

[0010] As a preferred embodiment of the digital asset ownership confirmation method based on continuous education process data described in this invention, the steps of combining ability evolution fingerprint summaries to analyze the causal relationship between learning behavior events and ability changes, identifying the impact of key learning activities on ability improvement, and generating ability improvement attribution labels containing causal strength are as follows: Selecting a time series of a certain capability dimension As the dependent variable, a sequence of learning behavior events that may influence this ability was selected. As an independent variable; Constructing lagged variables and ,in The maximum lag order is used to capture the delayed effect of behavior on ability; Establish a vector autoregression model and test it. Lagged term prediction Changes; If the null hypothesis of no Granger causality is rejected, then the behavior is considered... Regarding ability There is a statistically significant causal effect; Calculating the causality strength index It is defined as the absolute value of the standardized regression coefficient of the behavioral variable in the prediction model, and its expression is: ; in, The coefficients of behavioral variables in regression analysis, after standardization, can be used to compare the relative impact of different behaviors; Generate capability enhancement attribution tags, wherein the tags include the behavior name, the affected capability dimension, and the corresponding causal strength. This is used to explain the driving factors of changes in ability.

[0011] As a preferred embodiment of the digital asset ownership confirmation method based on continuous education process data described in this invention, the steps of encapsulating the capability evolution fingerprint summary and capability enhancement attribution tag into composite ownership confirmation data, writing it into a phylogenetic directed acyclic graph maintained by the education alliance nodes, establishing certificate nodes containing version inheritance and path dependency relationships, and forming anchor records are as follows: The capability evolution fingerprint summary is combined with one or more capability enhancement attribution tags in a structured manner to form a composite authority data package; The composite rights confirmation data packet is written as a new node into the phylogenetic directed acyclic graph. The phylogenetic directed acyclic graph is jointly maintained by multiple educational institutions as consensus nodes, and a Byzantine fault-tolerant consensus mechanism with educational contribution weighting is adopted. Query whether there are any prior competency certificate nodes for the same learner in the graph. ; If it exists, then in and Establish directed edges between them Marked as version inheritance relationship, and Write the node identifier The parent node field; Check if there are any prerequisite knowledge certificate nodes in the graph that the current learning content depends on. ; If it exists, then in and Establish directed edges between them and mark them as knowledge dependencies; After completing the node writing and edge relationship establishment, an immutable anchor record is generated; The anchor record includes node data, edge relationships, and consensus confirmation information.

[0012] As a preferred embodiment of the digital asset ownership confirmation method based on continuous education process data described in this invention, the following steps are taken: The digital certificate generated based on anchored records, containing a visual chart and an invisible watermark, is verified upon receiving a verification request by extracting the watermark information from the certificate image and comparing it with the original data in a phylogenetic directed acyclic graph. The specific steps are as follows: Capability evolution trajectory data are extracted from the anchored records, and a two-dimensional curve is plotted with time on the horizontal axis and capability scores on the vertical axis to show the learner's growth process in each capability dimension. Using the aforementioned graph as a background, superimpose display capability enhancement attribution tags, certificate numbers, and genealogical link information to generate a digital certificate image; An invisible watermark is embedded in a predetermined area of ​​the image. The watermark content includes a capability evolution fingerprint summary. The first few characters of the certificate and the unique ID are embedded using an image processing algorithm based on discrete cosine transform. When a verification request is received, obtain the certificate image file to be verified; The embedded watermark information is recovered from the image using a preset watermark extraction algorithm. ; By querying the phylogenetic directed acyclic graph based on the certificate number, the original capability evolution fingerprint summary stored in the node corresponding to the certificate can be obtained. ; extract The first few characters constitute the reference watermark ; Compare and If they match, output a verification passed result; otherwise, output a verification failed result.

[0013] Secondly, this invention provides a digital asset ownership confirmation system based on continuous education process data, comprising: The module includes a data acquisition module, a capability modeling module, a fingerprint generation module, an attribution analysis module, a genealogy anchoring module, and a verification module. The data acquisition module is used to collect learners' behavioral data on the education platform, clean and identify anomalies, and output a continuous education process data sequence. The ability modeling module is used to construct and dynamically update the time evolution sequence of multidimensional ability vectors based on the continuous educational process data sequence, reflecting the learner's growth trajectory in knowledge acquisition, thinking development, collaborative participation and practical innovation. The fingerprint generation module is used to weight and integrate the time evolution sequence of the multidimensional capability vector to generate a capability evolution trajectory that reflects the dynamic characteristics of the learning process, and generate a capability evolution fingerprint summary accordingly. The attribution analysis module is used to analyze the causal relationship between learning behavior events and ability changes, identify the impact of key learning activities on ability improvement, and generate ability improvement attribution tags containing causal strength. The genealogical anchoring module is used to encapsulate the capability evolution fingerprint summary and capability enhancement attribution label into composite rights confirmation data, write it into the genealogical directed acyclic graph maintained by the education alliance, establish version inheritance and knowledge dependency relationship, and form anchoring records. The verification module is used to generate a digital certificate with an invisible watermark based on the anchored record, and extract the image watermark information during verification, compare it with the original data in the genealogy chart, and complete the authenticity verification.

[0014] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the digital asset ownership confirmation method based on continuous education process data as described in the first aspect of the present invention.

[0015] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the digital asset ownership confirmation method based on continuous education process data as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By collecting and cleaning learners' continuous educational process data, a dynamically updated multidimensional ability evolution model is constructed. A time-weighted integral is used to generate an ability evolution fingerprint summary that reflects the characteristics of the learning process. Causal analysis is introduced to identify the impact of key behaviors on ability improvement, forming composite ownership data that includes process and outcome explanations. A credible anchoring of learning outcomes across platforms and cycles is achieved through a phylogenetic directed acyclic graph. Version inheritance and knowledge dependency relationship expression are supported. A visual digital certificate with embedded invisible watermark is generated, realizing closed-loop management of the entire process from learning process modeling to certificate authenticity verification. This improves the ownership accuracy, interpretability, and anti-counterfeiting capabilities of educational digital assets. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the digital asset ownership confirmation method based on continuous education process data in Example 1.

[0019] Figure 2 This is a schematic diagram of the digital asset ownership confirmation system based on continuous education process data in Example 1. Detailed Implementation

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example, refer to Figure 1 and Figure 2 This embodiment of the invention provides a method for confirming digital asset ownership based on continuous education process data, comprising the following steps: S1. Collect fine-grained behavioral data of learners on the education platform, perform data cleaning and abnormal behavior identification, and obtain a continuous educational process data sequence; Furthermore, we can obtain learners' video viewing logs, chapter access records, quiz answer data, assignment submission information, discussion forum posts, and project completion status generated in the online education system to form a raw behavioral dataset. Timestamp alignment is performed on each record in the original behavior dataset; Behavioral data is collected according to learner identifiers and arranged in chronological order to form a raw behavioral sequence with time as the axis. For the original behavior sequence, analyze the distribution of time intervals between adjacent behaviors to identify data segments whose time intervals deviate from the normal learning rhythm; Calculate the operation frequency of each behavioral event. When the number of operations per unit time exceeds the reasonable threshold set by the system, it is marked as a suspected anomaly. By combining the logical coherence of the behavioral sequence, we can determine whether there are operational patterns that violate the learning pattern, such as completing a test without watching a video or submitting assignments in batches within a short period of time. Isolate the behavioral data that is marked as abnormal, and retain the rest of the data; The processed behavioral data is re-sorted by time to generate an educational process data sequence; It should be noted that by aggregating and standardizing multi-source behavioral data, the integrity and temporal consistency of educational process data are ensured. The anomaly identification mechanism, built based on time intervals, operation frequency, and logical coherence, can effectively filter out non-genuine learning behaviors such as machine-generated lessons and proxy learning, ensuring the data reliability of subsequent ability modeling. The generated continuous educational process data sequence serves as the basic input for the entire rights confirmation process and has the characteristics of traceability and tamper-proof.

[0024] S2. Based on the continuous educational process data sequence, construct and dynamically update the time evolution sequence of multidimensional ability vectors to reflect learners’ growth trajectory in knowledge acquisition, thinking development, collaborative participation and practical innovation. Furthermore, behavioral types in the continuous educational process data sequence are mapped to corresponding ability dimensions, where knowledge point test scores are input variables for the knowledge mastery dimension, question posing depth and reasoning chain length are input variables for the thinking development dimension, group task participation frequency and peer evaluation quality are input variables for the collaborative participation dimension, and project outcome evaluation level is input variable for the practical innovation dimension. The historical observations of each capability dimension are used to construct a time series, and an exponential smoothing model is used to model them. set up For the first A score for a specific ability dimension at any given time. The observed value at the current moment, The smoothed value from the previous time step is expressed as: ; smoothness coefficient It is adaptively adjusted based on data volatility to control the weight of the impact of new observations on the current score; Perform the above update process on each of the four capability dimensions to generate a multidimensional capability vector sequence that evolves over time. Each component corresponds to a dynamic score for a capability dimension; It should be noted that by transforming discrete behaviors into continuous ability development signals and using an exponential smoothing model to dynamically update ability scores, the oversensitivity or delayed response of traditional static scoring to process fluctuations is avoided. The construction of each ability dimension is based on the principles of educational measurement, with clear and interpretable mapping relationships. The generated multidimensional ability vector sequence truly reflects the learner's growth trajectory at different cognitive and practical levels, providing structured input for subsequent dynamic fingerprint generation.

[0025] S3. Weighted integration of the time evolution sequence of multidimensional capability vectors to generate capability evolution trajectory that reflects the dynamic characteristics of the learning process, and generate capability evolution fingerprint summary accordingly. Furthermore, extract a length of [length missing] from the multidimensional capability vector sequence. All vectors within the sliding time window ,in This represents a point in time within the window, with a value range of [tw,t]. For each moment within the window Weights are assigned to the capability vector The weights decay exponentially over time, as expressed by: ; Where the attenuation parameter Pre-set by the system to reflect the greater influence of recent performance on overall competence assessment; Calculate the weighted capability trajectory vector Its components are approximations of the weighted integrals of each capability dimension within the window, expressed as: ; For weighted capability trajectory vectors Normalization is performed to eliminate the dimensional differences between different capability dimensions, resulting in a normalized vector. ; Will After being concatenated with the learner's anonymous identifier, the fingerprint digest is input into a cryptographic hash function to generate a capability evolution fingerprint digest, which is used to uniquely represent the learning process characteristics within that time period. It should be noted that the introduction of a time-weighted integral mechanism highlights the impact of recent learning performance on overall ability assessment, making the generated ability evolution trajectory time-sensitive and dynamic in representation. Normalization eliminates the differences in dimensionality between dimensions, ensuring the stability and comparability of fingerprint summaries. The fingerprint summaries generated by combining anonymized identifiers not only have uniqueness but also embed learning process pattern characteristics, realizing a leap from data evidence storage to growth pattern ownership confirmation.

[0026] S4. Combining the ability evolution fingerprint summary, analyze the causal relationship between learning behavior events and ability changes, identify the impact of key learning activities on ability improvement, and generate ability improvement attribution labels containing causal strength. Furthermore, select a time series of a specific capability dimension. As the dependent variable, a sequence of learning behavior events that may influence this ability was selected. As an independent variable; Constructing lagged variables and ,in The maximum lag order is used to capture the delayed effect of behavior on ability; Establish a vector autoregression model and test it. Lagged term prediction Changes; If the null hypothesis of no Granger causality is rejected, then the behavior is considered... Regarding ability There is a statistically significant causal effect; Calculating the causality strength index It is defined as the absolute value of the standardized regression coefficient of the behavioral variable in the prediction model, and its expression is: ; in, The coefficients of behavioral variables in regression analysis, after standardization, can be used to compare the relative impact of different behaviors; Generate capability enhancement attribution tags, which include the behavior name, the affected capability dimension, and the corresponding causal strength. This is used to explain the driving factors of changes in ability; It should be noted that by establishing a statistical causal relationship between behavior and ability changes through Granger causality tests, the limitations of correlation analysis are overcome. This approach can identify key learning events that truly drive ability improvement, and the causal strength index quantifies the contribution of different behaviors. This makes the attribution labels for ability improvement comparable and verifiable, enhances the educational value and credibility of digital certificates, and provides a deeper basis for talent evaluation.

[0027] S5. Encapsulate the capability evolution fingerprint summary and capability enhancement attribution tag into composite ownership data, write it into the phylogenetic directed acyclic graph maintained by the education alliance nodes, establish certificate nodes containing version inheritance and path dependency relationships, and form anchor records. Furthermore, the capability evolution fingerprint summary is structurally combined with one or more capability enhancement attribution tags to form a composite ownership data package; The composite rights confirmation data packet is written as a new node into the phylogenetic directed acyclic graph. The phylogenetic directed acyclic graph is jointly maintained by multiple educational institutions as consensus nodes, and a Byzantine fault-tolerant consensus mechanism with educational contribution weighting is adopted. Query whether there are any prior competency certificate nodes for the same learner in the graph. ; If it exists, then in and Establish directed edges between them Marked as version inheritance relationship, and Write the node identifier The parent node field; Check if there are any prerequisite knowledge certificate nodes in the graph that the current learning content depends on. ; If it exists, then in and Establish directed edges between them and mark them as knowledge dependencies; After completing the node writing and edge relationship establishment, an immutable anchor record is generated; Anchor records contain node data, edge relationships, and consensus confirmation information; It should be noted that the phylogenetic directed acyclic graph constructed in this step is free from dependence on public blockchains. It adopts an education alliance consensus mechanism to ensure privacy and operational efficiency. Through version inheritance and the establishment of knowledge dependency edges, it fully records the evolutionary logic of the learning path, supports the integration of learning outcomes across institutions and stages, and the anchored records cannot be tampered with once written, forming a trusted ownership chain with semantic association and topological structure.

[0028] S6. Generate a digital certificate containing a visual chart and an invisible watermark based on the anchored record. When a verification request is received, the watermark information in the certificate image is extracted and compared with the original data in the phylogenetic directed acyclic graph to complete the certificate authenticity verification. Furthermore, we extracted ability evolution trajectory data from the anchored records and plotted a two-dimensional curve graph with time on the horizontal axis and ability scores on the vertical axis to show the learner's growth process in each ability dimension. Using a graph as a background, overlay attribution tags, certificate numbers, and genealogical link information to generate a digital certificate image; An invisible watermark is embedded in a preset area of ​​the image. The watermark content contains a capability evolution fingerprint summary. The first few characters of the certificate and the unique ID are embedded using an image processing algorithm based on discrete cosine transform. When a verification request is received, obtain the certificate image file to be verified; The embedded watermark information is recovered from the image using a preset watermark extraction algorithm. ; By querying the phylogenetic directed acyclic graph based on the certificate number, the original capability evolution fingerprint summary stored in the node corresponding to the certificate can be obtained. ; extract The first few characters constitute the reference watermark ; Compare and If they match, output a verification passed result; otherwise, output a verification failed result. It should be noted that visual charts are used to intuitively present the capability development process, improving the readability and expressiveness of digital certificates. The invisible watermark embedding and extraction mechanism achieves consistent binding between the certificate image content and on-chain data, effectively preventing image forgery and tampering. The verification process does not rely on third-party platforms and can complete the authenticity verification through local comparison, ensuring the autonomy, controllability and high efficiency of the rights confirmation system.

[0029] This embodiment also provides a digital asset ownership confirmation system based on continuous education process data, including: The module includes a data acquisition module, a capability modeling module, a fingerprint generation module, an attribution analysis module, a genealogy anchoring module, and a verification module. The data acquisition module is used to collect learners' behavioral data on the education platform, clean and identify anomalies, and output a continuous educational process data sequence. The competency modeling module is used to construct and dynamically update the time evolution sequence of multidimensional competency vectors based on the continuous educational process data sequence, reflecting the learner's growth trajectory in knowledge acquisition, thinking development, collaborative participation, and practical innovation. The fingerprint generation module is used to weight and integrate the temporal evolution sequence of multidimensional capability vectors to generate capability evolution trajectories that reflect the dynamic characteristics of the learning process, and generate capability evolution fingerprint summaries accordingly. The attribution analysis module is used to analyze the causal relationship between learning behavior events and ability changes, identify the impact of key learning activities on ability improvement, and generate ability improvement attribution tags containing causal strength. The genealogical anchoring module is used to encapsulate the capability evolution fingerprint summary and capability enhancement attribution label into composite ownership data, write it into the genealogical directed acyclic graph maintained by the education alliance, establish version inheritance and knowledge dependency relationships, and form anchoring records. The verification module is used to generate digital certificates with hidden watermarks based on anchor records, and extract image watermark information during verification, compare it with the original data in the genealogy chart, and complete the authenticity verification.

[0030] This embodiment also provides a computer device applicable to the digital asset ownership confirmation method based on continuous education process data, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the digital asset ownership confirmation method based on continuous education process data as proposed in the above embodiment.

[0031] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0032] This embodiment also provides a storage medium on which a computer program is stored. When executed by a processor, the program implements the digital asset ownership confirmation method based on continuous education process data as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0033] In summary, this invention collects and cleans learners' continuous educational process data, constructs a dynamically updated multidimensional ability evolution model, generates an ability evolution fingerprint summary reflecting the characteristics of the learning process by combining time-weighted integrals, and introduces causal analysis to identify the impact of key behaviors on ability improvement, forming composite ownership data that includes process and outcome explanations. It achieves reliable anchoring of learning outcomes across platforms and cycles through a phylogenetic directed acyclic graph, supports version inheritance and knowledge dependency expression, and generates a visual digital certificate with embedded invisible watermarks. This realizes closed-loop management of the entire process from learning process modeling to certificate authenticity verification, improving the ownership accuracy, interpretability, and anti-counterfeiting capabilities of educational digital assets.

[0034] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for confirming ownership of digital assets based on continuous education process data, characterized in that: include: Collect fine-grained behavioral data of learners on the education platform, perform data cleaning and abnormal behavior identification, and obtain a continuous educational process data sequence; Based on the continuous educational process data sequence, a time evolution sequence of multidimensional ability vectors is constructed and dynamically updated to reflect learners’ growth trajectory in knowledge acquisition, thinking development, collaborative participation and practical innovation. The time evolution sequence of multidimensional capability vectors is weighted and integrated to generate capability evolution trajectories that reflect the dynamic characteristics of the learning process, and capability evolution fingerprint summaries are generated accordingly. By combining capability evolution fingerprint summaries, we analyze the causal relationship between learning behavior events and capability changes, identify the impact of key learning activities on capability improvement, and generate capability improvement attribution labels containing causal strength. The capability evolution fingerprint summary and capability enhancement attribution label are encapsulated into composite ownership data and written into a phylogenetic directed acyclic graph maintained by the education alliance nodes. Certificate nodes containing version inheritance and path dependency relationships are established to form anchor records. Digital certificates containing visual charts and invisible watermarks are generated based on anchored records. When a verification request is received, the watermark information in the certificate image is extracted and compared with the original data in the phylogenetic directed acyclic graph to complete the certificate authenticity verification.

2. The method for confirming ownership of digital assets based on continuous education process data as described in claim 1, characterized in that: The process involves collecting fine-grained behavioral data of learners on the education platform, cleaning the data, identifying abnormal behaviors, and obtaining a continuous educational process data sequence. The specific steps are as follows: Obtain learners' video viewing logs, chapter access records, quiz answer data, assignment submission information, discussion forum posts, and project completion status generated in the online education system to form a raw behavioral dataset; Timestamp alignment is performed on each record in the original behavior dataset; Behavioral data is collected according to learner identifiers and arranged in chronological order to form a raw behavioral sequence with time as the axis. For the original behavior sequence, analyze the distribution of time intervals between adjacent behaviors to identify data segments whose time intervals deviate from the normal learning rhythm; Calculate the operation frequency of each behavioral event. When the number of operations per unit time exceeds the reasonable threshold set by the system, it is marked as a suspected anomaly. By combining the logical coherence of the behavioral sequence, we can determine whether there are operational patterns that violate the learning pattern, such as completing a test without watching a video or submitting assignments in batches within a short period of time. Isolate the behavioral data that is marked as abnormal, and retain the rest of the data; The processed behavioral data is re-sorted by time to generate an educational process data sequence.

3. The method for confirming digital asset ownership based on continuous education process data as described in claim 2, characterized in that: The process of constructing and dynamically updating a time evolution sequence of multidimensional ability vectors based on continuous educational process data sequences, reflecting learners' growth trajectory in knowledge acquisition, thinking development, collaborative participation, and practical innovation, involves the following steps: The behavioral types in the continuous educational process data sequence are mapped to the corresponding ability dimensions, where the knowledge point test score is the input variable for the knowledge mastery dimension, the depth of question posing and the length of the reasoning chain are the input variables for the thinking development dimension, the number of group task participations and the quality of peer evaluation are the input variables for the collaborative participation dimension, and the project result evaluation level is the input variable for the practical innovation dimension. The historical observations of each capability dimension are used to construct a time series, and an exponential smoothing model is used to model them. set up For the first A score for a specific ability dimension at any given time. The observed value at the current moment, The smoothed value from the previous time step is expressed as: ; smoothness coefficient It is adaptively adjusted based on data volatility to control the weight of the impact of new observations on the current score; Perform the above update process on each of the four capability dimensions to generate a multidimensional capability vector sequence that evolves over time. Each component corresponds to a dynamic score for a capability dimension.

4. The method for confirming digital asset ownership based on continuous education process data as described in claim 3, characterized in that: The process involves weighted integration of the temporal evolution sequence of the multidimensional capability vectors to generate capability evolution trajectories that reflect the dynamic characteristics of the learning process, and based on this, a capability evolution fingerprint summary is generated. The specific steps are as follows: Extract a length of [length] from the multidimensional capability vector sequence. All vectors within the sliding time window ,in This represents a point in time within the window, with a value range of [tw,t]. For each moment within the window Weights are assigned to the capability vector The weights decay exponentially over time, as expressed by: ； in Attenuation parameter Pre-set by the system to reflect the greater influence of recent performance on overall competence assessment; Calculate the weighted capability trajectory vector Its components are approximations of the weighted integrals of each capability dimension within the window, expressed as: ； For the weighted capability trajectory vector Normalization is performed to eliminate the dimensional differences between different capability dimensions, resulting in a normalized vector. ; Will The learner's anonymous identifier is concatenated with the learner's anonymous identifier and then input into a cryptographic hash function to generate a capability evolution fingerprint digest, which is used to uniquely represent the learning process characteristics within that time period.

5. The method for confirming digital asset ownership based on continuous education process data as described in claim 4, characterized in that: The method of combining ability evolution fingerprint summaries to analyze the causal relationship between learning behavior events and ability changes, identify the impact of key learning activities on ability improvement, and generate ability improvement attribution labels containing causal strength, specifically as follows: Selecting a time series of a certain capability dimension As the dependent variable, a sequence of learning behavior events that may influence this ability was selected. As an independent variable; Constructing lagged variables and ,in The maximum lag order is used to capture the delayed effect of behavior on ability; Establish a vector autoregression model and test it. Lagged term prediction Changes; If the null hypothesis of no Granger causality is rejected, then the behavior is considered... Regarding ability There is a statistically significant causal effect; Calculating the causality strength index It is defined as the absolute value of the standardized regression coefficient of the behavioral variable in the prediction model, and its expression is: ； in, The coefficients of behavioral variables in regression analysis, after standardization, can be used to compare the relative impact of different behaviors; Generate capability enhancement attribution tags, wherein the tags include the behavior name, the affected capability dimension, and the corresponding causal strength. This is used to explain the driving factors of changes in ability.

6. The method for confirming digital asset ownership based on continuous education process data as described in claim 5, characterized in that: The process of encapsulating capability evolution fingerprint summaries and capability enhancement attribution tags into composite ownership data, writing it into a phylogenetic directed acyclic graph maintained by the education alliance nodes, establishing certificate nodes containing version inheritance and path dependency relationships, and forming anchor records involves the following steps: The capability evolution fingerprint summary is combined with one or more capability enhancement attribution tags in a structured manner to form a composite authority data package; The composite rights confirmation data packet is written as a new node into the phylogenetic directed acyclic graph. The phylogenetic directed acyclic graph is jointly maintained by multiple educational institutions as consensus nodes, and a Byzantine fault-tolerant consensus mechanism with educational contribution weighting is adopted. Query whether there are any prior competency certificate nodes for the same learner in the graph. ; If it exists, then in and Establish directed edges between them Marked as version inheritance relationship, and Write the node identifier The parent node field; Check if there are any prerequisite knowledge certificate nodes in the graph that the current learning content depends on. ; If it exists, then in and Establish directed edges between them and mark them as knowledge dependencies; After completing the node writing and edge relationship establishment, an immutable anchor record is generated; The anchor record includes node data, edge relationships, and consensus confirmation information.

7. The method for confirming ownership of digital assets based on continuous education process data as described in claim 6, characterized in that: The digital certificate generated based on anchored records, which includes a visual chart and an invisible watermark, verifies the authenticity of the certificate by extracting the watermark information from the certificate image and comparing it with the original data in the phylogenetic directed acyclic graph upon receiving a verification request. The specific steps are as follows: Capability evolution trajectory data are extracted from the anchored records, and a two-dimensional curve is plotted with time on the horizontal axis and capability scores on the vertical axis to show the learner's growth process in each capability dimension. Using the aforementioned graph as a background, superimpose display capability enhancement attribution tags, certificate numbers, and genealogical link information to generate a digital certificate image; An invisible watermark is embedded in a predetermined area of ​​the image. The watermark content includes a capability evolution fingerprint summary. The first few characters of the certificate and the unique ID are embedded using an image processing algorithm based on discrete cosine transform. When a verification request is received, obtain the certificate image file to be verified; The embedded watermark information is recovered from the image using a preset watermark extraction algorithm. ; By querying the phylogenetic directed acyclic graph based on the certificate number, the original capability evolution fingerprint summary stored in the node corresponding to the certificate can be obtained. ; extract The first few characters constitute the reference watermark ; Compare and If they match, output a verification passed result; otherwise, output a verification failed result.

8. A digital asset ownership confirmation system based on continuous education process data, and a digital asset ownership confirmation method based on continuous education process data as described in any one of claims 1 to 7, characterized in that: include: The module includes a data acquisition module, a capability modeling module, a fingerprint generation module, an attribution analysis module, a genealogy anchoring module, and a verification module. The data acquisition module is used to collect learners' behavioral data on the education platform, clean and identify anomalies, and output a continuous educational process data sequence. The ability modeling module is used to construct and dynamically update the time evolution sequence of multidimensional ability vectors based on the continuous educational process data sequence, reflecting the learner's growth trajectory in knowledge acquisition, thinking development, collaborative participation and practical innovation. The fingerprint generation module is used to weight and integrate the time evolution sequence of the multidimensional capability vector to generate a capability evolution trajectory that reflects the dynamic characteristics of the learning process, and generate a capability evolution fingerprint summary accordingly. The attribution analysis module is used to analyze the causal relationship between learning behavior events and ability changes, identify the impact of key learning activities on ability improvement, and generate ability improvement attribution tags containing causal strength. The genealogical anchoring module is used to encapsulate the capability evolution fingerprint summary and capability enhancement attribution label into composite rights confirmation data, write it into the genealogical directed acyclic graph maintained by the education alliance, establish version inheritance and knowledge dependency relationship, and form anchoring records. The verification module is used to generate a digital certificate with an invisible watermark based on the anchored record, and extract the image watermark information during verification, compare it with the original data in the genealogy chart, and complete the authenticity verification.

9. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the digital asset ownership confirmation method based on continuous education process data as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the digital asset ownership confirmation method based on continuous education process data as described in any one of claims 1 to 7.

Images