Value contribution real-time evaluation method and system based on behavior chain fingerprints

Abstract

The invention discloses a value contribution real-time evaluation method based on behavior chain fingerprints, and belongs to the technical field of value evaluation. Enhancing the multi-source behavior data of the user; secondly, feature coding is carried out on the user behavior chain fingerprints to obtain user behavior chain fingerprints, the user behavior chain fingerprints are multi-dimensional binary codes, and then user value contribution values are calculated in real time; and finally, carrying out encryption uplink on the user behavior chain fingerprint and the user value contribution value. According to the method, the multi-source behavior data of the user is acquired, and the data enhancement processing is performed through context injection, so that the user chain fingerprint carries more-dimensional and richer user behavior information, and the value contribution evaluation of the user is more comprehensive and accurate; meanwhile, the user behavior chain fingerprints are used for uplink encryption storage to help to form fingerprint authenticity verification, false contribution is prevented from entering evaluation, and the fairness of user value contribution evaluation is maintained.

Description

Technical Field

[0001] This invention belongs to the field of value assessment technology, specifically relating to a real-time value contribution assessment method and system based on behavioral chain fingerprints. Background Technology

[0002] In the current wave of the digital economy sweeping the globe, individuals and organizations rely on digital platforms to conduct various activities, creating immeasurable value for their platforms, communities, and even the entire social ecosystem through continuous behavioral output. However, with the diversification of value creation scenarios and the dynamic development of value-contributing behaviors, how to accurately measure these dispersed and constantly changing value contributions has become a key bottleneck restricting the healthy development of the digital economy. Currently, mainstream value contribution assessment technologies suffer from two major flaws:

[0003] From an evaluation perspective, existing technical solutions generally employ modeling methods based on historical data backtracking or fixed-period statistics, resulting in overly simplistic evaluation model construction logic. These methods can only capture static results of value contribution, failing to track the dynamic fluctuations in behavioral value in real time. For example, in knowledge-sharing communities, a user's answer to a question may have a lasting impact over time, but traditional evaluation systems can only record the initial response, unable to quantify the cascading value triggered by that answer in subsequent discussions. More seriously, existing systems suffer from fundamental flaws in dimensional integration, often treating contributions from different dimensions such as resource consumption, social interaction, and content creation in a fragmented manner, leading to fragmented evaluation results. This evaluation approach fails to reflect the depth of user contributions (such as the systematic output of professional knowledge), struggles to measure their breadth (such as the diffusion of cross-domain influence), and fails to identify innovative breakthroughs, ultimately resulting in a misallocation of incentive resources and inhibiting users' continuous innovation motivation.

[0004] At the evaluation mechanism level, existing technological systems lack effective anti-fraud protection mechanisms, making it difficult to accurately identify fraudulent contributions. Some users artificially create fake contribution data through methods such as machine scripts to inflate numbers, content plagiarism and patchwork, and malicious peer review. Traditional evaluation systems often rely on simple frequency statistics or surface feature analysis, making it difficult to penetrate the data surface and identify the essence. For example, in the user review system of e-commerce platforms, paid reviewers can easily manipulate product ratings by mass-posting templated positive reviews. Existing evaluation models, lacking the ability to verify authenticity, often confuse such fraudulent contributions with genuine user contributions. This evaluation distortion not only prevents high-quality contributors from receiving due rewards but also seriously undermines the fairness of the platform ecosystem, even creating a vicious cycle.

[0005] As mentioned above, how to provide a real-time value contribution assessment method and system based on behavioral chain fingerprints that can improve the comprehensiveness, accuracy and fairness of value contribution assessment has become an urgent problem to be solved. Summary of the Invention

[0006] The purpose of this invention is to provide a real-time evaluation method for value contribution based on behavioral chain fingerprints, in order to solve the above-mentioned problems existing in the prior art.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a method for real-time evaluation of value contribution based on behavioral chain fingerprints, including:

[0009] Acquire user multi-source behavioral data;

[0010] Context awareness is performed on the user multi-source behavior data to obtain user multi-source behavior context data. The user multi-source behavior context data is then injected into the user multi-source behavior data to generate enhanced user multi-source behavior data. The user multi-source behavior context data includes time series context data, social relationship context data, and task goal context data.

[0011] The enhanced user multi-source behavior data is feature-encoded to obtain a user behavior chain fingerprint, wherein the user behavior chain fingerprint is a multi-dimensional binary code;

[0012] The user behavior value weight value is obtained, and the user behavior multidimensional index is obtained by parsing the user behavior chain fingerprint. Based on the user behavior multidimensional index and the user behavior value weight value, the user value contribution value is calculated in real time. The user behavior multidimensional index is a dynamic feature code with at least 12 dimensions.

[0013] The user behavior chain fingerprint and the user value contribution value are encrypted, uploaded to the blockchain, and integrated for visualization.

[0014] In one possible design, the user multi-source behavioral data includes resource usage behavior data, innovative original behavior data, community interaction behavior data, collaborative participation behavior data, geolocation behavior data, device interaction behavior data, user identification data, action type data, operation object data, operation time data, and / or environmental parameter data.

[0015] Accordingly, acquiring multi-source user behavior data includes:

[0016] Obtain raw, multi-source user behavior data from the enterprise platform database;

[0017] Invalid behavior data is filtered out from the original user multi-source behavior data, and the missing original user multi-source behavior data is filled with data mean to generate user multi-source behavior data.

[0018] In one possible design, context-aware processing is performed on the user multi-source behavior data to obtain user multi-source behavior context data. This user multi-source behavior context data is then injected into the user multi-source behavior data to generate enhanced user multi-source behavior data, including:

[0019] The user multi-source behavior data is input into a long short-term memory network model for feature encoding to form the temporal probability value of the user multi-source behavior data, so as to obtain the user multi-source behavior temporal context data.

[0020] The user multi-source behavior data is input into the GNN graph neural network model to construct a user behavior association graph, and the user multi-source behavior data of adjacent nodes in the user behavior association graph are connected to obtain user multi-source behavior social context data.

[0021] Obtain a preset task template and match the user's multi-source behavior data with the preset task template to obtain user multi-source behavior task context data;

[0022] The user multi-source behavior time context data, the user multi-source behavior social context data, and the user multi-source behavior task context data are integrated to generate user multi-source behavior context data;

[0023] By utilizing an attention mechanism, the user multi-source behavioral context data and the user multi-source behavioral data are concatenated to form enhanced user multi-source behavioral data. The enhanced user multi-source behavioral data includes user industry affiliation information, user value contribution information, user behavior stability information, and user innovation capability information.

[0024] In one possible design, the enhanced user multi-source behavior data is feature-encoded to obtain a user behavior chain fingerprint, including:

[0025] Obtain user behavior association rules, and construct a user behavior graph structure based on the enhanced user multi-source behavior data based on the user behavior association rules;

[0026] The enhanced user multi-source behavior data is subjected to hash sharding to generate user multi-source behavior sequences;

[0027] The user behavior graph structure is input into a GNN graph neural network model to obtain graph structure features. The user multi-source behavior sequence is input into a Transformer attention mechanism model to obtain behavior sequence features. The graph structure features and the behavior sequence features are fused to generate a high-dimensional semantic vector.

[0028] The high-dimensional semantic vector is subjected to local sensitive hashing dimensionality reduction processing to generate a multi-bit binary hash value, and the multi-bit binary hash value is used as the fingerprint of the user behavior chain.

[0029] In one possible design, user behavior value weights are obtained, and multi-dimensional user behavior indicators are derived through user behavior chain fingerprint parsing. Based on these multi-dimensional indicators and the user behavior value weights, the user value contribution value is calculated in real time, including:

[0030] Obtain predefined feature dimensions and preset feature code order, and perform feature label mapping on the user behavior chain fingerprint according to the predefined feature dimensions to obtain user industry affiliation label, user value contribution label, user behavior stability label and user innovation capability label;

[0031] According to the preset feature code order, the user industry affiliation tag, the user value contribution tag, the user behavior stability tag, and the user innovation ability tag are combined into a dynamic feature code with at least 12 dimensions, so as to use this dynamic feature code as a multi-dimensional indicator of user behavior.

[0032] The user behavior multidimensional indicators are analyzed to obtain the user resource utilization value R, user trust value T, user stability value E, and user innovation capability value I, and to obtain the external adjustment factor M.

[0033] User identification data is identified from the user's multi-source behavior data, and user role types are defined through the user identification data, wherein the user role type is production type, innovation type, coordination type or comprehensive type;

[0034] Obtain a preset behavior value weight table, and assign user value weights to users according to the user role type to obtain user behavior value weight values. The preset behavior value weight table is periodically updated according to the user's multi-source behavior data. The user behavior value weight values ​​include resource utilization value weight α, trust value weight β, stability value weight γ, innovation ability value weight δ, and external adjustment factor weight ε.

[0035] Based on the multidimensional indicators of user behavior and the weighted values ​​of user behavior, the following formula is used:

[0036] V = αR + βT + γE + δI + εM (1)

[0037] Calculate the user value contribution value V.

[0038] In one possible design, the user behavior chain fingerprint and the user value contribution value are encrypted and uploaded to the blockchain, including:

[0039] The user behavior chain fingerprint and the user value contribution value are encrypted using a quantum-resistant cryptographic algorithm to obtain an encrypted user fingerprint data packet;

[0040] The encrypted user fingerprint data packet is written into the blockchain node, and a storage record containing timestamp, user ID and block height is generated;

[0041] Correspondingly, integrating the user behavior chain fingerprint and the user value contribution value for visual display includes:

[0042] Obtain the visualization particle generation rules, and use the visualization particle generation rules to generate user value visualization particles based on the user value contribution value;

[0043] The user value visualization particles are rendered based on the user behavior chain fingerprint, and the rendered user value visualization particles are then visualized.

[0044] The user value contribution value is binary encoded and a user value heatmap is generated. The user value heatmap is divided into heat regions, and the user behavior chain fingerprint is linked to the corresponding heat regions to complete the visualization display.

[0045] In one possible design, after encrypting the user behavior chain fingerprint and the user value contribution value and uploading them to the blockchain, the following steps are also included:

[0046] By using the consortium blockchain cross-chain protocol between related blocks, the newly added blockchain fingerprint is compared with the user behavior chain fingerprint in real time to obtain the fingerprint similarity.

[0047] Obtain the fingerprint similarity threshold and the contribution value difference threshold, and determine whether the fingerprint similarity exceeds the fingerprint similarity threshold;

[0048] If the fingerprint similarity is determined to be less than the fingerprint similarity threshold, then the newly added fingerprint does not need to be verified for fingerprint authenticity. If the fingerprint similarity is determined to be greater than the fingerprint similarity threshold, then the new user value contribution value corresponding to the newly added fingerprint is obtained, and it is determined whether the difference between the new user value contribution value and the user value contribution value exceeds the contribution value difference threshold.

[0049] If it is determined that the difference between the new user value contribution value and the user value contribution value does not exceed the contribution value difference threshold, then it is considered that the new on-chain fingerprint does not need to be verified for fingerprint authenticity. If it is determined that the difference between the new user value contribution value and the user value contribution value exceeds the contribution value difference threshold, then the on-chain smart contract is invoked to verify the fingerprint authenticity of the new on-chain fingerprint using the blockchain, and a fingerprint authenticity verification result is generated.

[0050] The fingerprint authenticity verification result is encrypted and stored in all associated blockchain nodes, and the cross-platform cheater blacklist is updated according to the fingerprint authenticity verification result. The cross-platform cheater blacklist is a shared list among all associated blocks.

[0051] Secondly, the present invention provides a real-time value contribution evaluation system based on behavioral chain fingerprints, characterized in that it includes:

[0052] Distributed data acquisition units are used to acquire multi-source user behavior data;

[0053] The data augmentation unit is used to perform context awareness on the user multi-source behavior data to obtain user multi-source behavior context data, and inject the user multi-source behavior context data into the user multi-source behavior data to generate augmented user multi-source behavior data. The user multi-source behavior context data includes time series context data, social relationship context data and task goal context data.

[0054] A binary encoding unit is used to perform feature encoding on the enhanced user multi-source behavior data to obtain a user behavior chain fingerprint, wherein the user behavior chain fingerprint is a multi-dimensional binary code;

[0055] The data processing and computing unit is used to obtain the user behavior value weight value, and to obtain the user behavior multidimensional index according to the user behavior chain fingerprint parsing. Based on the user behavior multidimensional index and the user behavior value weight value, the user value contribution value is calculated in real time. The user behavior multidimensional index is a dynamic feature code with at least 12 dimensions.

[0056] The data encryption and on-chain unit is used to encrypt the user behavior chain fingerprint and the user value contribution value, upload them to the blockchain, and integrate the user behavior chain fingerprint and the user value contribution value for visualization.

[0057] Thirdly, the present invention provides an electronic device comprising a memory, a processor, and a transceiver connected in sequence and communication, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the real-time value contribution evaluation method based on behavioral chain fingerprints as described in the first aspect or any possible design of the first aspect.

[0058] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the real-time value contribution evaluation method based on behavioral chain fingerprints as described in the first aspect or any possible design of the first aspect.

[0059] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform a real-time value contribution evaluation method based on behavioral chain fingerprints as described in the first aspect or any possible design of the first aspect.

[0060] Beneficial Effects: This invention provides a real-time value contribution evaluation method based on behavioral chain fingerprints, comprising: first, acquiring multi-source user behavior data; second, performing context awareness on the multi-source user behavior data to obtain multi-source user behavior context data, and injecting the multi-source user behavior context data into the multi-source user behavior data to generate enhanced multi-source user behavior data, wherein the multi-source user behavior context data includes time series context data, social relationship context data, and task goal context data; then, performing feature encoding on the enhanced multi-source user behavior data to obtain a user behavior chain fingerprint, wherein the user behavior chain fingerprint is a multi-dimensional binary code; further, acquiring user behavior value weight values, and parsing user behavior multi-dimensional indicators based on the user behavior chain fingerprint, and calculating user value contribution values ​​in real time based on the user behavior multi-dimensional indicators and the user behavior value weight values, wherein the user behavior multi-dimensional indicators are dynamic feature codes with at least 12 dimensions; finally, encrypting the user behavior chain fingerprint and the user value contribution values, uploading them to the blockchain, and integrating the user behavior chain fingerprint and the user value contribution values ​​for visualization. By acquiring multi-source user behavior data and performing data augmentation through context injection, the user chain fingerprint carries more multi-dimensional and richer user behavior information, making the assessment of user value contribution more comprehensive and accurate. At the same time, the user behavior chain fingerprint is encrypted and stored on the chain to help verify the authenticity of the fingerprint, prevent false contributions from entering the assessment, and maintain the fairness of the assessment of user value contribution. Attached Figure Description

[0061] Figure 1A flowchart illustrating the real-time value contribution evaluation method based on behavioral chain fingerprinting provided in this embodiment of the invention;

[0062] Figure 2 A functional structure diagram of the real-time value contribution evaluation system based on behavioral chain fingerprinting provided in an embodiment of the present invention;

[0063] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0064] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is 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. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0065] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0066] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0067] Example:

[0068] like Figure 1 As shown, the first aspect of this embodiment provides a method for real-time evaluation of value contribution based on behavioral chain fingerprints, including:

[0069] S1. Obtain multi-source user behavior data;

[0070] S2. Perform context awareness on the user multi-source behavior data to obtain user multi-source behavior context data, and inject the user multi-source behavior context data into the user multi-source behavior data to generate enhanced user multi-source behavior data, wherein the user multi-source behavior context data includes time series context data, social relationship context data and task goal context data;

[0071] S3. Perform feature encoding on the enhanced user multi-source behavior data to obtain a user behavior chain fingerprint, wherein the user behavior chain fingerprint is a multi-dimensional binary code;

[0072] S4. Obtain the user behavior value weight value, and obtain the user behavior multidimensional indicator based on the user behavior chain fingerprint parsing. Based on the user behavior multidimensional indicator and the user behavior value weight value, calculate the user value contribution value in real time. The user behavior multidimensional indicator is a dynamic feature code with at least 12 dimensions.

[0073] S5. Encrypt the user behavior chain fingerprint and the user value contribution value, upload them to the blockchain, and integrate the user behavior chain fingerprint and the user value contribution value for visualization.

[0074] In one possible implementation, the user multi-source behavioral data includes resource usage behavior data, innovative original behavior data, community interaction behavior data, collaborative participation behavior data, geolocation behavior data, device interaction behavior data, user identification data, action type data, operation object data, operation time data, and / or environmental parameter data.

[0075] Accordingly, in step S1, obtaining user multi-source behavior data can be broken down into, but is not limited to, the following steps S11-S12, including:

[0076] S11. Obtain raw user multi-source behavior data from the enterprise platform database;

[0077] S12. Filter out invalid behavior data from the original user multi-source behavior data, and fill the missing original user multi-source behavior data with the data mean to generate user multi-source behavior data.

[0078] It should be noted that, in actual implementation, the aforementioned multi-source user behavior data is achieved through a distributed data acquisition module, including a distributed acquisition layer and a central information acquisition layer. The distributed acquisition layer is deployed on each user's terminal device to collect community interaction behavior data, geolocation behavior data, device interaction behavior data, user identification data, action type data, operation object data, operation time data, and / or environmental parameter data. The central information acquisition layer is located on a central server and is used to collect resource usage behavior data, innovative original behavior data, and collaborative participation behavior data. This multi-dimensional information acquisition mechanism makes the obtained multi-source user behavior data richer and more comprehensive, forming the basis for subsequent value contribution assessment.

[0079] Invalid behavior data (e.g., user heartbeat monitoring data) is filtered out from the original multi-source user behavior data. The invalid behavior data should be judged according to the preset valid contribution behavior table and / or valid contribution behavior judgment model to screen out user behavior data that is invalid for value contribution and ensure the accuracy of multi-source user behavior data.

[0080] In one possible implementation, step S2 involves performing context awareness on the user multi-source behavior data to obtain user multi-source behavior context data, and then injecting the user multi-source behavior context data into the user multi-source behavior data to generate enhanced user multi-source behavior data. This step can be broken down into, but is not limited to, the following steps S21-S25, including:

[0081] S21. Input the user multi-source behavior data into a long short-term memory network model for feature encoding to form the temporal probability value of the user multi-source behavior data, so as to obtain the user multi-source behavior temporal context data.

[0082] S22. Input the user multi-source behavior data into a graph neural network (GNN) model to construct a user behavior association graph, and connect the user multi-source behavior data of adjacent nodes in the user behavior association graph to obtain user multi-source behavior social context data.

[0083] S23. Obtain a preset task template, and match the user multi-source behavior data with the preset task template to obtain user multi-source behavior task context data;

[0084] S24. Integrate the user multi-source behavior time context data, the user multi-source behavior social context data, and the user multi-source behavior task context data to generate user multi-source behavior context data;

[0085] S25. Using an attention mechanism, the user multi-source behavior context data and the user multi-source behavior data are concatenated to form enhanced user multi-source behavior data, wherein the enhanced user multi-source behavior data includes user industry affiliation information, user value contribution information, user behavior stability information, and user innovation capability information.

[0086] It should be noted that user multi-source behavior data is actually isolated data collected from the platform in real time. However, by perceiving and injecting contextual data, isolated user multi-source behavior data can be placed in the context of time series, social relationships and task goals for understanding, so as to generate richer and more enhanced user multi-source behavior data. This effectively improves the distinguishability and information content of the subsequently generated user behavior chain fingerprint, so as to help to complete a more accurate and comprehensive value contribution assessment.

[0087] In one possible implementation, step S3, which involves feature encoding of the enhanced user multi-source behavior data to obtain a user behavior chain fingerprint, can be decomposed, but is not limited to, the following steps S31-S34, including:

[0088] S31. Obtain user behavior association rules, and construct a user behavior graph structure based on the enhanced user multi-source behavior data based on the user behavior association rules;

[0089] S32. Perform hash sharding on the enhanced user multi-source behavior data to generate user multi-source behavior sequences;

[0090] S33. Input the user behavior graph structure into a GNN graph neural network model to obtain graph structure features, input the user multi-source behavior sequence into a Transformer attention mechanism model to obtain behavior sequence features, and fuse the graph structure features and the behavior sequence features to generate a high-dimensional semantic vector;

[0091] S34. Perform local sensitive hashing dimensionality reduction processing on the high-dimensional semantic vector to generate a multi-bit binary hash value, and use the multi-bit binary hash value as the user behavior chain fingerprint.

[0092] It should be noted that the parallel processing mode of graph structure features and behavioral sequence features is adopted here. This not only extracts the basic features of the enhanced user multi-source behavioral data, but also enables a deeper understanding of the semantic meaning and topological relationship of the enhanced user multi-source behavioral data in specific scenarios.

[0093] In one possible implementation, the graph structure features and the behavioral sequence features can be fused using a fully connected network to generate a 128-dimensional high-dimensional semantic vector. This high-dimensional semantic vector is then processed using the MinHash algorithm family as the LSH (Locality Sensitive Hash) function, constructing 64 hash functions. The output of each hash function is binarized, and all the resulting binary numbers are concatenated to complete the LSH dimensionality reduction process, yielding a 64-bit binary code (multi-bit binary hash value), which is the user behavior chain fingerprint. By generating unique user behavior chain fingerprints for each user, fraudulent activities such as fake production and fake reviews are prevented, significantly improving the fairness of value contribution assessment.

[0094] In one possible implementation, step S4 involves obtaining a user behavior value weight value and parsing the user behavior chain fingerprint to obtain a multi-dimensional user behavior indicator. Based on the multi-dimensional user behavior indicator and the user behavior value weight value, the user value contribution value is calculated in real time. This step can be, but is not limited to, decomposed into the following steps S41-S46, including:

[0095] S41. Obtain predefined feature dimensions and preset feature code order, and perform feature label mapping on the user behavior chain fingerprint according to the predefined feature dimensions to obtain user industry affiliation label, user value contribution label, user behavior stability label and user innovation capability label;

[0096] S42. According to the preset feature code order, combine the user industry affiliation tag, the user value contribution tag, the user behavior stability tag and the user innovation ability tag into a dynamic feature code with at least 12 dimensions, so as to use this dynamic feature code as a multi-dimensional indicator of user behavior.

[0097] S43. Analyze the multidimensional indicators of user behavior to obtain the user resource utilization value R, user trust value T, user stability value E, and user innovation capability value I, and obtain the external adjustment factor M;

[0098] S44. Identify user identification data from the user multi-source behavior data, and define user role types through the user identification data, wherein the user role type is production type, innovation type, coordination type or comprehensive type;

[0099] S45. Obtain a preset behavior value weight table, and assign user value weights to users according to the user role type to obtain user behavior value weight values. The preset behavior value weight table is periodically updated according to the user's multi-source behavior data. The user behavior value weight values ​​include resource utilization value weight α, trust value weight β, stability value weight γ, innovation ability value weight δ, and external adjustment factor weight ε.

[0100] S46. Based on the multidimensional indicators of user behavior and the weighted values ​​of user behavior, the following formula is used:

[0101] V = αR + βT + γE + δI + εM (1)

[0102] Calculate the user value contribution value V.

[0103] It should be noted that the preset behavioral value weight table is updated periodically based on the multi-source behavioral data of each user. For example, if the production efficiency and production volume of production users increase in the previous period, the user resource utilization value R and user trust value T of production users will be increased. If the conflict resolution rate of coordination users increases in the previous period, the trust value weight β and stability value weight γ of coordination users will be increased. If the original behavior and innovative products of innovative users increase in the previous period, the resource utilization value weight α, trust value weight β, and innovation capability value weight δ of innovative users will be increased.

[0104] In practice, the external adjustment factor M is obtained by summarizing and quantifying real-time information published by authoritative information databases and making quantitative predictions. Correspondingly, the weight ε of the external adjustment factor can also be updated in real time according to the external adjustment factor M, thus constituting external regulation of the user value contribution value V, so that the calculated user value contribution value V fully conforms to the actual situation of the user.

[0105] Furthermore, the innovation capability value weight δ is quantified based on the user's innovation capability tag. The innovation capability value weight δ makes the user's innovation value contribution explicit, incorporates the innovation value contribution as an innovation image into the value contribution assessment calculation, and focuses on the user's innovation capability to obtain more accurate and comprehensive assessment results.

[0106] In one possible implementation, step S5, which involves encrypting the user behavior chain fingerprint and the user value contribution value and uploading them to the blockchain, can be broken down into, but is not limited to, the following steps S51-S52, including:

[0107] S51. The user behavior chain fingerprint and the user value contribution value are encrypted using a quantum-resistant cryptographic algorithm to obtain an encrypted user fingerprint data packet;

[0108] S52. Write the encrypted user fingerprint data packet into the blockchain node and generate a storage record containing a timestamp, user ID, and block height;

[0109] Accordingly, in step S5, integrating the user behavior chain fingerprint and the user value contribution value for visualization can be broken down into, but is not limited to, the following steps S53-S55, including:

[0110] S53. Obtain the visualization particle generation rules, and use the visualization particle generation rules to generate user value visualization particles for the user value contribution value;

[0111] S54. Render the user value visualization particles according to the user behavior chain fingerprint, and visualize the rendered user value visualization particles.

[0112] S55. The user value contribution value is binary encoded and a user value heat map is generated. The user value heat map is divided into heat regions, and the user behavior chain fingerprint is linked with the corresponding heat region to complete the visualization display.

[0113] In one possible implementation, after encrypting the user behavior chain fingerprint and the user value contribution value in step S5 and uploading them to the blockchain, step S6 may also be included, but is not limited to. Step S6 may be decomposed into steps S61-S65 as follows:

[0114] S61. Through the consortium blockchain cross-chain protocol between related blocks, the newly added blockchain fingerprint is compared with the user behavior chain fingerprint in real time to obtain the fingerprint similarity.

[0115] S62. Obtain the fingerprint similarity threshold and the contribution value difference threshold, and determine whether the fingerprint similarity exceeds the fingerprint similarity threshold;

[0116] S63. If it is determined that the fingerprint similarity does not exceed the fingerprint similarity threshold, it is considered that the newly added fingerprint does not need to be verified for fingerprint authenticity. If it is determined that the fingerprint similarity exceeds the fingerprint similarity threshold, the new user value contribution value corresponding to the newly added fingerprint is obtained, and it is determined whether the difference between the new user value contribution value and the user value contribution value exceeds the contribution value difference threshold.

[0117] S64. If it is determined that the difference between the new user value contribution value and the user value contribution value does not exceed the contribution value difference threshold, then it is considered that the new on-chain fingerprint does not need to be verified for fingerprint authenticity. If it is determined that the difference between the new user value contribution value and the user value contribution value exceeds the contribution value difference threshold, then the on-chain smart contract is called to verify the fingerprint authenticity of the new on-chain fingerprint using the blockchain and generate a fingerprint authenticity verification result.

[0118] S65. The fingerprint authenticity verification result is encrypted and stored in all associated blockchain nodes, and the cross-platform cheater blacklist is updated according to the fingerprint authenticity verification result, wherein the cross-platform cheater blacklist is a shared list among all associated blocks.

[0119] It should be noted that when verifying the authenticity of newly added fingerprints on the blockchain, multi-dimensional characteristics of the users can be collected from the blockchain, including but not limited to: device hardware information (CPU / GPU model and memory size), operating system version, network configuration, geographical location, battery fluctuation mode, gyroscope and accelerometer noise characteristics, application installation list, font and font rendering method, screen resolution, time zone setting, language setting, browser plugins, and user behavior interaction mode (click, swipe, and input latency). Auditing is performed through the blockchain's smart contract to obtain the audit results (fingerprint authenticity verification results).

[0120] Based on the fingerprint authenticity verification results, it is determined whether the newly added fingerprint user is a cheater. If so, the cheater's user behavior chain fingerprint is written into the consortium chain between related blocks to form a cheater blacklist, realizing cross-platform sharing and querying of the cheater blacklist.

[0121] Furthermore, once a cheater is detected, their various behavioral data are flagged, their existing value contribution-related data is cleared, and their permissions for asset trading and resource acquisition are frozen. By constructing this cross-chain anti-cheating mechanism, the fairness of value contribution assessment can be effectively guaranteed, maintaining market fairness.

[0122] like Figure 2 As shown, the second aspect of this embodiment provides a hardware system for implementing the real-time value contribution evaluation method based on behavioral chain fingerprints described in the first aspect of the embodiment, including:

[0123] Distributed data acquisition units are used to acquire multi-source user behavior data;

[0124] The data augmentation unit is used to perform context awareness on the user multi-source behavior data to obtain user multi-source behavior context data, and inject the user multi-source behavior context data into the user multi-source behavior data to generate augmented user multi-source behavior data. The user multi-source behavior context data includes time series context data, social relationship context data and task goal context data.

[0125] A binary encoding unit is used to perform feature encoding on the enhanced user multi-source behavior data to obtain a user behavior chain fingerprint, wherein the user behavior chain fingerprint is a multi-dimensional binary code;

[0126] The data processing and computing unit is used to obtain the user behavior value weight value, and to obtain the user behavior multidimensional index according to the user behavior chain fingerprint parsing. Based on the user behavior multidimensional index and the user behavior value weight value, the user value contribution value is calculated in real time. The user behavior multidimensional index is a dynamic feature code with at least 12 dimensions.

[0127] The data encryption and on-chain unit is used to encrypt the user behavior chain fingerprint and the user value contribution value, upload them to the blockchain, and integrate the user behavior chain fingerprint and the user value contribution value for visualization.

[0128] It should be noted that, in one possible implementation, a cheating verification unit is also included. The cheating verification unit is used to perform fingerprint similarity and contribution value difference fingerprint calculation on the newly added fingerprint to complete the fingerprint authenticity verification, and to encrypt and store the generated fingerprint authenticity verification result to all associated blockchain nodes, and to update the cross-platform cheater blacklist according to the fingerprint authenticity verification result.

[0129] The working process, working details and technical effects of the system provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0130] like Figure 3 As shown, the third aspect of this embodiment provides an electronic device, including: a memory, a processor, and a transceiver that are sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the real-time value contribution evaluation method based on behavioral chain fingerprints as described in the first aspect of the embodiment.

[0131] For specific examples, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor, also known as the CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0132] In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. For example, the processor may not be limited to microprocessors of the STM32F105 series, reduced instruction set computer (RISC) microprocessors, x86 architecture processors, or processors with integrated neural network processing units (NPUs). The transceiver may be, but is not limited to, a Wi-Fi transceiver, a Bluetooth transceiver, a General Packet Radio Service (GPRS) transceiver, a ZigBee (a low-power LAN protocol based on the IEEE 802.15.4 standard) transceiver, a 3G transceiver, a 4G transceiver, and / or a 5G transceiver. Furthermore, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0133] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0134] The fourth aspect of this embodiment provides a storage medium that stores instructions containing the real-time value contribution evaluation method based on behavioral chain fingerprints as described in the first aspect of the embodiment. That is, the storage medium stores instructions that, when executed on a computer, perform the real-time value contribution evaluation method based on behavioral chain fingerprints as described in the first aspect of the embodiment.

[0135] The storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or memory sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0136] The working process, working details and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0137] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the real-time value contribution evaluation method based on behavioral chain fingerprints as described in the first aspect of this embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0138] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A real-time value contribution evaluation method based on behavioral chain fingerprints, characterized in that, include: Acquire user multi-source behavioral data; Context awareness is performed on the user multi-source behavior data to obtain user multi-source behavior context data. The user multi-source behavior context data is then injected into the user multi-source behavior data to generate enhanced user multi-source behavior data. The user multi-source behavior context data includes time series context data, social relationship context data, and task goal context data. The enhanced user multi-source behavior data is feature-encoded to obtain a user behavior chain fingerprint, wherein the user behavior chain fingerprint is a multi-dimensional binary code; The user behavior value weight value is obtained, and the user behavior multidimensional index is obtained by parsing the user behavior chain fingerprint. Based on the user behavior multidimensional index and the user behavior value weight value, the user value contribution value is calculated in real time. The user behavior multidimensional index is a dynamic feature code with at least 12 dimensions. The user behavior chain fingerprint and the user value contribution value are encrypted, uploaded to the blockchain, and integrated for visualization.

2. The real-time value contribution evaluation method based on behavioral chain fingerprints according to claim 1, characterized in that, The user multi-source behavioral data includes resource usage behavior data, innovation and originality behavior data, community interaction behavior data, collaborative participation behavior data, geolocation behavior data, device interaction behavior data, user identification data, action type data, operation object data, operation time data, and / or environmental parameter data. Accordingly, acquiring multi-source user behavior data includes: Obtain raw, multi-source user behavior data from the enterprise platform database; Invalid behavior data is filtered out from the original user multi-source behavior data, and the missing original user multi-source behavior data is filled with data mean to generate user multi-source behavior data.

3. The real-time value contribution evaluation method based on behavioral chain fingerprints according to claim 1, characterized in that, Context awareness is applied to the user multi-source behavior data to obtain user multi-source behavior context data. This user multi-source behavior context data is then injected into the user multi-source behavior data to generate enhanced user multi-source behavior data, including: The user multi-source behavior data is input into a long short-term memory network model for feature encoding to form the temporal probability value of the user multi-source behavior data, so as to obtain the user multi-source behavior temporal context data. The user multi-source behavior data is input into the GNN graph neural network model to construct a user behavior association graph, and the user multi-source behavior data of adjacent nodes in the user behavior association graph are connected to obtain user multi-source behavior social context data. Obtain a preset task template and match the user's multi-source behavior data with the preset task template to obtain user multi-source behavior task context data; The user multi-source behavior time context data, the user multi-source behavior social context data, and the user multi-source behavior task context data are integrated to generate user multi-source behavior context data; By utilizing an attention mechanism, the user multi-source behavioral context data and the user multi-source behavioral data are concatenated to form enhanced user multi-source behavioral data. The enhanced user multi-source behavioral data includes user industry affiliation information, user value contribution information, user behavior stability information, and user innovation capability information.

4. The real-time value contribution evaluation method based on behavioral chain fingerprints according to claim 1, characterized in that, The enhanced user multi-source behavior data is feature-encoded to obtain a user behavior chain fingerprint, including: Obtain user behavior association rules, and construct a user behavior graph structure based on the enhanced user multi-source behavior data based on the user behavior association rules; The enhanced user multi-source behavior data is subjected to hash sharding to generate user multi-source behavior sequences; The user behavior graph structure is input into a GNN graph neural network model to obtain graph structure features. The user multi-source behavior sequence is input into a Transformer attention mechanism model to obtain behavior sequence features. The graph structure features and the behavior sequence features are fused to generate a high-dimensional semantic vector. The high-dimensional semantic vector is subjected to local sensitive hashing dimensionality reduction processing to generate a multi-bit binary hash value, and the multi-bit binary hash value is used as the fingerprint of the user behavior chain.

5. The real-time value contribution evaluation method based on behavioral chain fingerprints according to claim 1, characterized in that, Obtain user behavior value weights, and derive multi-dimensional user behavior indicators based on the user behavior chain fingerprint. Based on these multi-dimensional indicators and the user behavior value weights, calculate the user value contribution value in real time, including: Obtain predefined feature dimensions and preset feature code order, and perform feature label mapping on the user behavior chain fingerprint according to the predefined feature dimensions to obtain user industry affiliation label, user value contribution label, user behavior stability label and user innovation capability label; According to the preset feature code order, the user industry affiliation tag, the user value contribution tag, the user behavior stability tag, and the user innovation ability tag are combined into a dynamic feature code with at least 12 dimensions, so as to use this dynamic feature code as a multi-dimensional indicator of user behavior. The user behavior multidimensional indicators are analyzed to obtain the user resource utilization value R, user trust value T, user stability value E, and user innovation capability value I, and to obtain the external adjustment factor M. User identification data is identified from the user's multi-source behavior data, and user role types are defined through the user identification data, wherein the user role type is production type, innovation type, coordination type or comprehensive type; Obtain a preset behavior value weight table, and assign user value weights to users according to the user role type to obtain user behavior value weight values. The preset behavior value weight table is periodically updated according to the user's multi-source behavior data. The user behavior value weight values ​​include resource utilization value weight α, trust value weight β, stability value weight γ, innovation ability value weight δ, and external adjustment factor weight ε. Based on the multidimensional indicators of user behavior and the weighted values ​​of user behavior, the following formula is used: V = αR + βT + γE + δI + εM (1) Calculate the user value contribution value V.

6. The real-time value contribution evaluation method based on behavioral chain fingerprints according to claim 1, characterized in that, The user behavior chain fingerprint and the user value contribution value are encrypted and uploaded to the blockchain, including: The user behavior chain fingerprint and the user value contribution value are encrypted using a quantum-resistant cryptographic algorithm to obtain an encrypted user fingerprint data packet; The encrypted user fingerprint data packet is written into the blockchain node, and a storage record containing timestamp, user ID and block height is generated; Correspondingly, integrating the user behavior chain fingerprint and the user value contribution value for visual display includes: Obtain the visualization particle generation rules, and use the visualization particle generation rules to generate user value visualization particles based on the user value contribution value; The user value visualization particles are rendered based on the user behavior chain fingerprint, and the rendered user value visualization particles are then visualized. The user value contribution value is binary encoded and a user value heatmap is generated. The user value heatmap is divided into heat regions, and the user behavior chain fingerprint is linked to the corresponding heat regions to complete the visualization display.

7. The real-time value contribution evaluation method based on behavioral chain fingerprints according to claim 1, characterized in that, After encrypting the user behavior chain fingerprint and the user value contribution value and uploading them to the blockchain, the process also includes: By using the consortium blockchain cross-chain protocol between related blocks, the newly added blockchain fingerprint is compared with the user behavior chain fingerprint in real time to obtain the fingerprint similarity. Obtain the fingerprint similarity threshold and the contribution value difference threshold, and determine whether the fingerprint similarity exceeds the fingerprint similarity threshold; If the fingerprint similarity is determined to be less than the fingerprint similarity threshold, then the newly added fingerprint does not need to be verified for fingerprint authenticity. If the fingerprint similarity is determined to be greater than the fingerprint similarity threshold, then the new user value contribution value corresponding to the newly added fingerprint is obtained, and it is determined whether the difference between the new user value contribution value and the user value contribution value exceeds the contribution value difference threshold. If it is determined that the difference between the new user value contribution value and the user value contribution value does not exceed the contribution value difference threshold, then it is considered that the new on-chain fingerprint does not need to be verified for fingerprint authenticity. If it is determined that the difference between the new user value contribution value and the user value contribution value exceeds the contribution value difference threshold, then the on-chain smart contract is invoked to verify the fingerprint authenticity of the new on-chain fingerprint using the blockchain, and a fingerprint authenticity verification result is generated. The fingerprint authenticity verification result is encrypted and stored in all associated blockchain nodes, and the cross-platform cheater blacklist is updated according to the fingerprint authenticity verification result. The cross-platform cheater blacklist is a shared list among all associated blocks.

8. A real-time value contribution evaluation system based on behavioral chain fingerprints, characterized in that, include: Distributed data acquisition units are used to acquire multi-source user behavior data; The data augmentation unit is used to perform context awareness on the user multi-source behavior data to obtain user multi-source behavior context data, and inject the user multi-source behavior context data into the user multi-source behavior data to generate augmented user multi-source behavior data. The user multi-source behavior context data includes time series context data, social relationship context data and task goal context data. A binary encoding unit is used to perform feature encoding on the enhanced user multi-source behavior data to obtain a user behavior chain fingerprint, wherein the user behavior chain fingerprint is a multi-dimensional binary code; The data processing and computing unit is used to obtain the user behavior value weight value, and to obtain the user behavior multidimensional index according to the user behavior chain fingerprint parsing. Based on the user behavior multidimensional index and the user behavior value weight value, the user value contribution value is calculated in real time. The user behavior multidimensional index is a dynamic feature code with at least 12 dimensions. The data encryption and on-chain unit is used to encrypt the user behavior chain fingerprint and the user value contribution value, upload them to the blockchain, and integrate the user behavior chain fingerprint and the user value contribution value for visualization.

9. An electronic device, characterized in that, The device includes a memory, a processor, and a transceiver that are sequentially and communicatively connected. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the real-time value contribution evaluation method based on behavioral chain fingerprints as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the real-time value contribution evaluation method based on behavioral chain fingerprints as described in any one of claims 1 to 7.

Images