Customs laboratory knowledge co-construction and sharing system and method based on contribution excitation

Abstract

The invention relates to the technical field of data processing systems and commercial methods, and discloses a customs laboratory knowledge co-construction and sharing system and method based on contribution excitation. The system comprises a knowledge input and vectorization module, a dynamic knowledge graph module, a dynamic value and entropy weight calculation module, a guidance and excitation mapping module and a user interaction and visualization module. The method comprises five key steps of knowledge contribution processing, knowledge network construction, dynamic value calculation, contribution excitation mapping and visual interaction. According to the method, a multi-dimensional knowledge evaluation system is constructed, a contribution entropy concept and a value propagation algorithm are introduced, a knowledge value dynamic quantitative evaluation and accurate incentive distribution mechanism is established, and intelligent management of the full life cycle of knowledge is realized; the problem that a traditional knowledge management system is inaccurate in value evaluation, unreasonable in incentive mechanism and lack of dynamic evolution ability is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing systems and business methods, in particular to a customs laboratory knowledge co-construction and sharing system and method based on contribution incentives. BACKGROUND

[0002] The customs laboratory knowledge co-construction and sharing system refers to a digital platform for customs laboratory employees to collaboratively create, organize, manage and utilize professional knowledge using information technology means. The core goal is to integrate the tacit and explicit knowledge such as experience, technical solutions and detection methods scattered among individual experts or specific departments, and to improve the overall technical innovation capability and business processing efficiency of the customs laboratory through systematic aggregation and sharing.

[0003] The existing knowledge management systems in the field of customs laboratories are mostly focused on document storage and retrieval functions. Common technical implementation methods include establishing an electronic document library, using keyword search technology, setting up a user points ranking list, etc. These systems can achieve basic knowledge archiving and sharing, and some systems also use simple collaborative editing tools and version management functions. In terms of incentives, existing technologies mostly use linear point systems based on upload quantity or download count, and encourage users to participate through material rewards or honor recognition.

[0004] However, due to the highly specialized nature of customs laboratory knowledge, rapid iteration and strong implicit value, existing technical solutions have obvious limitations in knowledge value assessment and incentive mechanism design. Traditional quantitative statistical methods cannot accurately measure the intrinsic value and long-term utility of knowledge, which can easily lead to a focus on quantity rather than quality of contribution. At the same time, static knowledge organization methods cannot effectively reflect the dynamic relationships between knowledge units, making the knowledge system lack the ability to evolve. These shortcomings make it difficult for existing systems to motivate users to contribute high-quality knowledge consistently, ultimately resulting in uneven content quality in the knowledge base, low knowledge reuse efficiency, and inability to fully realize the overall benefits of knowledge sharing. SUMMARY

[0005] To address the shortcomings of existing technologies, the present application provides a customs laboratory knowledge co-construction and sharing system and method based on contribution incentives, aiming to solve the problems of inaccurate knowledge value assessment, insufficient rationality of incentive mechanisms and lack of dynamic evolution capability in existing knowledge management systems.

[0006] To achieve the above purpose, the present application realizes the following technical solutions: The customs laboratory knowledge co-construction and sharing system based on contribution incentives comprises: The knowledge input and vectorization module is used to receive knowledge contributions submitted by users and generate an initial contribution vector containing inherent attributes and an initial contribution entropy representing the uncertainty of value for the knowledge contributions. The dynamic knowledge graph module, connected to the knowledge input and vectorization module, is used to instantiate the knowledge contribution into knowledge nodes carrying the initial contribution vector and the initial contribution entropy, and to establish positive and negative relationship edges between the knowledge nodes based on user interaction, so as to construct a knowledge network. The dynamic value and entropy weight calculation module is connected to the dynamic knowledge graph module. Based on the positive relation edges in the knowledge network, it iteratively calculates the dynamic weight of each knowledge node through the value propagation algorithm; and dynamically adjusts the contribution entropy of each knowledge node based on the positive relation edges and negative relation edges. The guidance and incentive mapping module, connected to the dynamic knowledge graph module and the dynamic value and entropy weight calculation module, is used to analyze the knowledge network to identify knowledge gaps and guide users to make knowledge contributions; and based on the dynamic weights of each knowledge node, it summarizes and calculates the user's total contribution as the basis for contribution incentives. The user interaction and visualization module, connected to the aforementioned modules, is used to visually display the knowledge network and the user's total contribution to the user.

[0007] Preferably, the knowledge input and vectorization module includes: A knowledge receiving unit is used to receive the knowledge contribution; An initial vector generation unit, connected to the knowledge receiving unit, is used to generate the initial contribution vector based on the inherent attributes of the knowledge contribution. An initial entropy setting unit, connected to the initial vector generation unit, is used to set the initial contribution entropy based on the initial contribution vector.

[0008] Preferably, the initial vector generation unit is specifically used for: The knowledge contribution is analyzed to obtain multi-dimensional inherent attributes, including at least novelty, criticality, completeness, and universality. The multi-dimensional inherent attributes are quantified to construct the initial contribution vector.

[0009] Preferably, the dynamic knowledge graph module includes: A node instantiation unit is used to receive the knowledge contribution, the initial contribution vector, and the initial contribution entropy, and to instantiate the knowledge contribution into a knowledge node carrying the initial contribution vector and the initial contribution entropy. A relationship edge establishment unit, connected to the node instantiation unit, is used to establish the positive relationship edge and the negative relationship edge between the knowledge nodes generated by the node instantiation unit based on user interaction.

[0010] Preferably, the relationship edge establishment unit is specifically used for: The interactions representing referencing, resolving, applying, or aggregating relationships are established as the positive relationship edges; The interaction representing the falsification relation is established as the negative relation edge.

[0011] Preferably, the dynamic value and entropy weight calculation module includes: A dynamic weight calculation unit is used to acquire the knowledge network and, based on the positive relation edges in the knowledge network, iteratively calculate the dynamic weight of each knowledge node through a value propagation algorithm. The contribution entropy adjustment unit, connected to the dynamic weight calculation unit, is used to dynamically adjust the contribution entropy of each knowledge node based on the positive and negative relation edges in the knowledge network.

[0012] Preferably, the contribution entropy adjustment unit is specifically used for: When a new positive relation edge is detected on the knowledge node, an entropy reduction operation is performed on the contribution entropy of the knowledge node. When a new negative relation edge is detected on the knowledge node, an entropy increase operation is performed on the contribution entropy of the knowledge node.

[0013] Preferably, the guidance and incentive mapping module includes: A knowledge gap identification unit is used to analyze the knowledge network to identify knowledge gaps and guide users to make knowledge contributions. The total contribution calculation unit, connected to the knowledge gap identification unit, is used to calculate the user's total contribution based on the dynamic weights of each knowledge node.

[0014] Preferably, the user interaction and visualization module includes: A knowledge network display unit is used to acquire the knowledge network and visualize it. The total contribution display unit is connected to the knowledge network display unit and is used to obtain the user's total contribution and to visualize the user's total contribution.

[0015] The contribution-incentive-based knowledge co-construction and sharing method for customs laboratories includes the following steps: Knowledge contribution processing: Receive knowledge contributions submitted by users and generate an initial contribution vector containing its inherent attributes, and an initial contribution entropy representing its value uncertainty for the knowledge contribution; Knowledge network construction: The knowledge contribution is instantiated into a knowledge node carrying the initial contribution vector and the initial contribution entropy, and positive and negative relationship edges between the knowledge nodes are established according to user interaction to construct a knowledge network; Dynamic value calculation: Based on the positive relation edges in the knowledge network, the dynamic weight of each knowledge node is iteratively calculated through the value propagation algorithm, and the contribution entropy of each knowledge node is dynamically adjusted based on the positive and negative relation edges; Contribution incentive mapping: The knowledge network is analyzed to identify knowledge gaps, and the total contribution of the user is calculated based on the dynamic weights of each knowledge node. Visual interaction: Present the knowledge network and the user's total contribution to the user in a visual format.

[0016] This invention provides a contribution-incentive-based knowledge co-construction and sharing system and method for customs laboratories. It has the following beneficial effects: 1. This invention achieves standardized value assessment of customs laboratory knowledge by constructing a multi-dimensional knowledge assessment system and introducing the concept of contribution entropy. Compared with traditional single-dimensional knowledge evaluation methods, this system can comprehensively assess the value of knowledge from multiple perspectives such as novelty, criticality, completeness, and universality. Combined with dynamic uncertainty measurement, it provides a more scientific and comprehensive quantitative basis for knowledge co-construction and sharing, which helps to improve the assessment accuracy and reliability of the knowledge management system.

[0017] 2. This invention achieves the self-organizing evolution of the knowledge network by establishing a dynamic knowledge graph and an intelligent relationship recognition mechanism. Compared with the traditional static knowledge base, this system can automatically establish positive and negative relationships between knowledge nodes based on user interaction, forming a dynamic network structure with semantic association. This helps to promote the self-improvement and continuous optimization of the knowledge system and provides a more flexible and intelligent way of organizing knowledge for customs laboratories.

[0018] 3. This invention achieves real-time quantification and updating of knowledge value by designing a value propagation algorithm and a contribution entropy dynamic adjustment mechanism. Compared with the traditional fixed-weight evaluation system, this system can dynamically adjust the value weight according to the correlation between knowledge nodes and user feedback, making knowledge evaluation more objective and fair. It helps to establish a more accurate contribution incentive allocation mechanism and stimulate users' enthusiasm for participating in knowledge co-construction.

[0019] 4. This invention significantly improves user experience and engagement by developing a visual interactive interface and an intelligent guidance system. Compared with traditional text-based knowledge management systems, this system provides an intuitive display of the knowledge network and visualization of multi-dimensional contributions. Combined with intelligent gap identification, it generates personalized guidance suggestions, which helps to lower the user threshold, improve knowledge sharing efficiency, and promote the healthy development of the knowledge ecosystem of the customs laboratory. Attached Figure Description

[0020] Figure 1 This is a diagram of the overall system architecture of the present invention; Figure 2 This is a schematic diagram of the knowledge input and vectorization module unit of the present invention; Figure 3 This is a schematic diagram of the dynamic knowledge graph module unit of the present invention; Figure 4 This is a schematic diagram of the dynamic value and entropy weight calculation module unit of the present invention; Figure 5 This is a schematic diagram of the guidance and excitation mapping module unit of the present invention; Figure 6 This is a schematic diagram of the user interaction and visualization module unit of the present invention; Figure 7 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Please see the appendix Figure 1 - Appendix Figure 6 This invention provides a contribution-incentive-based knowledge co-construction and sharing system for customs laboratories, comprising: The knowledge input and vectorization module is used to receive knowledge contributions submitted by users and generate an initial contribution vector containing inherent attributes, as well as an initial contribution entropy representing the uncertainty of value for the knowledge contribution. Specifically, the knowledge input and vectorization module is usually an application deployed on the system server side, which interacts with the user through the system's front-end interface, such as web-based forms or dedicated client software.

[0023] The implementation of the knowledge input and vectorization module provides a unified, quantitative, and information-rich data foundation for the subsequent construction of dynamic knowledge graphs, the evaluation of the dynamic value of knowledge nodes, and the precise mapping of user contribution incentives. It is a prerequisite for the effective operation of the entire contribution-incentive-based customs laboratory knowledge co-construction and sharing system.

[0024] To achieve the above functions, the knowledge input and vectorization module includes a knowledge receiving unit, an initial vector generation unit, and an initial entropy setting unit in its internal structure. These three units form a sequential data flow processing relationship and work together to complete the transformation from raw knowledge to structured data.

[0025] The knowledge receiving unit's main function is to provide users with a stable and user-friendly knowledge submission channel and to perform necessary preprocessing on the received raw data. The forms of knowledge contributions submitted by users can be very diverse. For example, it could be a text note describing customs inspection techniques, a PDF experimental report on specific chemical testing methods, a troubleshooting flowchart for instrument equipment in image form, or a set of spreadsheet data containing key experimental parameters. To cope with this diversity, the knowledge receiving unit integrates a data format adaptation function, which can parse different types of files.

[0026] Upon receiving the data, the unit immediately performs a series of preprocessing operations. These operations are not limited to basic security measures such as format verification and virus scanning, but also preferably include preliminary cleaning of the text content, such as removing irrelevant format marks, correcting obvious OCR recognition errors, and performing legality checks on the input content, in order to ensure the purity and security of the knowledge sources entering this knowledge co-construction and sharing system.

[0027] After the knowledge receiving unit completes data reception and preprocessing, the standardized knowledge contribution data is transmitted to the initial vector generation unit. This unit is the core of realizing the initial quantification of knowledge value. Its goal is to deeply analyze the intrinsic value attributes of knowledge contribution and objectively and multidimensionally abstract it into an initial contribution vector.

[0028] To achieve the above objectives, the initial vector generation unit is specifically used to analyze knowledge contribution in order to obtain its multi-dimensional inherent attributes. In this embodiment, in order to comprehensively evaluate the initial value of knowledge, the multi-dimensional inherent attributes include at least novelty, criticality, completeness and universality, and can be further extended when necessary.

[0029] Novelty measures whether a knowledge contribution supplements, improves, or entirely creates existing knowledge in the knowledge network. One feasible implementation is for the unit to call a Natural Language Processing (NLP) model (such as BERT or similar deep language models) to convert the submitted knowledge contribution text into semantic vectors and calculate cosine similarity with the semantic vectors of existing knowledge nodes in the knowledge graph. Contributions with similarity scores below a preset threshold are considered to have high novelty and are thus assigned a higher quantification value for this dimension.

[0030] Criticality is designed to measure the importance of the knowledge contribution in solving the core technical difficulties or business challenges of the Customs Laboratory. To conduct this assessment, the unit maintains a critical technical terminology database set by domain experts. When the analysis shows that the content of the knowledge contribution is highly relevant to the entries in the terminology database, or directly provides a targeted solution, its criticality rating will be improved.

[0031] Completeness is used to measure whether the content structure of the knowledge contribution is comprehensive, the argumentation is detailed, and the logic is coherent. The unit has built-in structured templates for different types of knowledge. For example, for an experimental report, it will check whether it contains all the necessary components such as experimental purpose, experimental equipment, operation steps, raw data, result analysis and conclusions. The richness of each part of the content will also be evaluated by indicators such as text length and keyword density.

[0032] Universality is designed to measure the breadth of solutions that can be applied to solve problems provided by the knowledge contribution. This unit assesses universality by identifying words in the text that limit its scope of application (such as specific equipment models, regional names, or time ranges). The fewer limiting words identified, the wider the scope of application of the knowledge, and the higher its universality score.

[0033] After obtaining the aforementioned multi-dimensional inherent attributes, the initial vector generation unit processes each dimension attribute according to preset quantization rules, as follows: For novelty quantification, the text content of the knowledge contribution is input into a pre-trained natural language processing model to generate its semantic vector, and the maximum cosine similarity between this vector and the semantic vectors of all existing knowledge nodes in the knowledge network is calculated. The novelty quantification value is obtained by the following formula: ; In the formula, This is the novelty quantification value. This represents the calculated maximum cosine similarity value.

[0034] For criticality quantification, the text content of knowledge contribution is matched against a pre-defined terminology database containing multiple weighted key technical terms. The criticality quantification value vkvk is obtained by summing and normalizing the weights of all matched key technical terms, as shown in the following formula: ; In the formula, As a key quantification value, The number of key technical terms matched to this knowledge. For the first The weight of each matched key technical term. This represents the total number of all key technical terms in the terminology database. For the terminology database The weight of key technical terms.

[0035] For the quantification of completeness, a pre-defined structured template is matched according to the type of knowledge contribution. This template defines the necessary components that this type of knowledge should include. The completeness quantification value is obtained by calculating the ratio of the actual number of included components to the total number of necessary components defined in the template. The calculation formula is as follows: ; In the formula, For integrity quantification value, The number of the necessary components that actually constitute this knowledge. This represents the total number of necessary components defined in the corresponding template.

[0036] For the quantification of universality, specific words in the knowledge contribution text used to limit its application scope are identified. The universality quantification value is inversely proportional to the number of identified limiting words, and can be calculated using the following formula: ; In the formula, For universally applicable quantification values, The total number of qualifier words identified.

[0037] Finally, the quantized values ​​calculated in the above steps are combined to construct an initial contribution vector, as shown in the following formula: ; In the formula, This is the initial contribution vector. This is the novelty quantification value. As a key quantification value, For integrity quantification value, This is a universally applicable quantified value.

[0038] Subsequently, the initial contribution vector and the original knowledge content are transmitted together to the initial entropy setting unit, and the initial contribution vector... This merely represents the value potential of a knowledge contribution based on its own content at the time of submission. The ultimate value of a piece of knowledge needs to be realized through its subsequent dissemination, application, and verification in the knowledge network. The actual value in the future and the degree of recognition by the community are full of uncertainty in the initial stage. In order to quantify this uncertainty mathematically, this invention introduces the concept of contribution entropy to drive the value discovery process in the subsequent knowledge co-construction and sharing system.

[0039] The initial entropy setting unit's core function is to set an initial contribution entropy for each knowledge contribution based on the initial contribution vector. The initial contribution entropy is a scalar value; a higher value indicates a greater degree of uncertainty in the value of the knowledge contribution. All newly submitted knowledge contributions have their initial contribution entropy set to a relatively high system preset value. This initial value can be fine-tuned based on the initial contribution vector, as shown in the following formula: ; In the formula, As the initial contribution entropy, The system's preset upper limit for entropy. For adjustment coefficients, , , , These are the quantified values ​​of novelty, criticality, completeness, and universality in the initial contribution vector, respectively. , , , Preset weighting coefficients are used to adjust the degree of influence of different inherent attributes on the initial uncertainty for each quantified value.

[0040] Ultimately, this knowledge input and vectorization module combines the original knowledge contribution and the generated initial contribution vector. and the initial contribution entropy set. It is encapsulated as a standardized data object and reliably output to the dynamic knowledge graph module, providing complete input for the subsequent instantiation of knowledge nodes and the dynamic construction of the knowledge network.

[0041] This embodiment extracts and quantifies the inherent attributes of user-submitted knowledge from multiple dimensions, and innovatively introduces initial contribution entropy to measure the uncertainty of its value. This transforms diverse and ambiguous original knowledge contributions into standardized structured data that carries rich value information, laying a solid and reliable data foundation for the subsequent dynamic evaluation and precise incentive of the entire contribution-based incentive-based customs laboratory knowledge co-construction and sharing system.

[0042] The dynamic knowledge graph module, connected to the knowledge input and vectorization module, is used to instantiate knowledge contributions into knowledge nodes carrying initial contribution vectors and initial contribution entropies, and to establish positive and negative relationship edges between knowledge nodes based on user interaction in order to construct a knowledge network. Specifically, the dynamic knowledge graph module is the core data structure and relation engine of the entire system. It receives standardized data objects from the knowledge input and vectorization modules and is responsible for transforming them into a dynamic, computable knowledge network that reflects the complex relationships between knowledge. This knowledge network is not only a carrier of knowledge but also a direct basis for subsequent value assessment and incentive allocation.

[0043] To achieve the above functions, the dynamic knowledge graph module includes a node instantiation unit and a relationship edge establishment unit in its internal structure.

[0044] The node instantiation unit is responsible for receiving the original knowledge contribution, initial contribution vector, and initial contribution entropy from the knowledge input and vectorization module. This unit treats these three as a whole and creates a new and unique knowledge node in the knowledge network. This process is called instantiation, which means that an independent knowledge point is formally established in the system.

[0045] The aforementioned knowledge nodes not only contain the knowledge itself for reference, but more importantly, they store the initial contribution vector and initial contribution entropy as their inherent metadata attributes. These attributes provide a complete picture of the initial state of the knowledge node and serve as the starting point for its subsequent value evolution.

[0046] The relationship edge establishment unit, connected to the node instantiation unit, functions to establish connection edges representing the relationships between various knowledge nodes generated by the node instantiation unit. The establishment of these edges is not automatically preset by the system, but is entirely based on user interaction. This ensures that the evolution of the knowledge network truly reflects the flow and collision of collective wisdom within the Customs Laboratory's knowledge co-construction and sharing system. This unit can establish two completely different types of relationship edges: positive relationship edges and negative relationship edges.

[0047] More specifically, the relation edge building unit parses the semantics of user interactions to build different types of edges: First, interactions representing referencing, resolving, applying, or aggregating relationships are established as positive relationship edges. Positive relationship edges represent supportive, confirmatory, inherited, or heuristic relationships between knowledge, and are the main channels for the positive propagation of knowledge value in the network.

[0048] Reference relationship: When a user submits new knowledge (node ​​B) and explicitly references or cites another existing basic knowledge (node ​​A) in the system, the system will establish a reference relationship edge from node B to node A.

[0049] Relationship resolution: When there is a knowledge node (node ​​C) in the system that describes a specific technical problem, and another user's submitted knowledge (node ​​D) is verified to effectively solve the problem, the system will establish a resolution relationship edge from node D to node C.

[0050] Application Relationship: When a general method or theoretical knowledge (node ​​E) is successfully applied by a user to a specific inspection or testing task and forms a case analysis (node ​​F), the system will establish an application relationship edge from node F to node E.

[0051] Aggregation Relationships: When a user creates a summary or general knowledge node (node ​​G) that systematically organizes and summarizes the content of multiple existing knowledge nodes (nodes H, I, J), the system will establish multiple aggregation relationship edges from node G to nodes H, I, and J respectively.

[0052] Secondly, interactions representing falsification relationships are established as negative relation edges. Negative relation edges represent the opposition, modification, or subversion relationships between knowledge, and are a key mechanism for realizing the self-purification and iterative updating of the knowledge system.

[0053] Falsification relation: When a new research or experimental result (node ​​L) fully proves that a certain existing knowledge or operating procedure in the system (node ​​K) is wrong or outdated, the system will establish a falsification relation edge from node L to node K after the user explicitly points out this opposition relationship through interaction.

[0054] Through the continuous establishment of the two types of relationship edges mentioned above, a dynamic knowledge network composed of knowledge nodes with clear semantics and directions on the edges can be constructed and evolved. This knowledge network not only stores the knowledge itself, but more importantly, it stores the interaction and evaluation relationship between knowledge in a structured way.

[0055] This implementation method outputs the real-time updated knowledge network data, which includes complete node and edge information, to the dynamic value and entropy weight calculation module, providing structured data input for value propagation calculation and dynamic adjustment of contribution entropy.

[0056] The dynamic value and entropy weight calculation module is connected to the dynamic knowledge graph module. Based on the positive relation edges in the knowledge network, it iteratively calculates the dynamic weight of each knowledge node through the value propagation algorithm; and dynamically adjusts the contribution entropy of each knowledge node based on the positive and negative relation edges. Specifically, the dynamic value and entropy weight calculation module is a high-frequency computing engine deployed on the backend of the system server. It synchronizes in real-time with the dynamic knowledge graph module via an internal data bus to acquire complete knowledge network data, including knowledge nodes, initial contribution vectors, initial contribution entropy, and positive and negative relational edges. This module is the core algorithm center for the system to achieve dynamic evaluation of knowledge value and the evolution of uncertainty, providing an objective and calculable basis for the system's precise incentive allocation.

[0057] The dynamic value and entropy weight calculation module includes a dynamic weight calculation unit and a contribution entropy adjustment unit in its internal structure. These two units work together to complete the weight calculation and entropy adjustment functions, respectively.

[0058] The dynamic weight calculation unit is used to acquire the knowledge network and, based on the positive relation edges in the knowledge network, iteratively calculate the dynamic weight of each knowledge node through the value propagation algorithm. This unit performs the following calculation process: ; In the formula, For nodes In the Dynamic weights at the next iteration It is the damping factor and 0 < <1, This represents the total number of nodes in the knowledge network. For all pointing nodes The set of source nodes, For the source node The dynamic weights at the t-th iteration. For nodes Out-degree (i.e., from node) (Number of positive relation edges issued).

[0059] The contribution entropy adjustment unit, connected to the dynamic weight calculation unit, is used to dynamically adjust the contribution entropy of each knowledge node based on the positive and negative relation edges in the knowledge network. This unit specifically performs the following operations: When a new positive relation edge is detected on a knowledge node, the entropy reduction operation is performed on the contribution entropy of that knowledge node using the following formula: ; In the formula, The adjusted contribution entropy, The contribution entropy before adjustment, The pre-defined entropy reduction coefficient for positive relation edges. The upper limit of the entropy value preset for the system.

[0060] When a new negative relation edge is detected on a knowledge node, the entropy increase calculation formula for the contribution entropy of that knowledge node is performed as follows: ; In the formula, The adjusted contribution entropy, The contribution entropy before adjustment, The pre-defined negative relation edge entropy increase coefficient. The upper limit of the entropy value preset for the system.

[0061] This embodiment dynamically calculates node weights through a value propagation algorithm and dynamically adjusts contribution entropy based on positive and negative relational edges, thus fully realizing a continuous, adaptive, and community-driven quantitative assessment of knowledge value, providing core technical support for building a fair, transparent, and efficient knowledge co-construction and sharing ecosystem.

[0062] The guidance and incentive mapping module, connected to the dynamic knowledge graph module and the dynamic value and entropy weight calculation module, is used to analyze the knowledge network to identify knowledge gaps and guide users to make knowledge contributions; and based on the dynamic weight of each knowledge node, it summarizes and calculates the user's total contribution as the basis for contribution incentives. Specifically, the guidance and incentive mapping module is an intelligent analysis and incentive allocation center deployed at the system application layer. It obtains complete knowledge network data from the dynamic knowledge graph module and dynamic weights of each knowledge node from the dynamic value and entropy weight calculation module in real time through the data interface.

[0063] The core function of this module is twofold: on the one hand, it uses intelligent analysis to identify weaknesses in the knowledge system and guides users to contribute knowledge in a targeted manner; on the other hand, it provides a direct basis for fair and transparent incentive allocation by accurately calculating users' cumulative contribution value.

[0064] The functionality of the guidance and incentive mapping module relies on its internal analysis of the knowledge network's topology and precise statistics of user contribution history. It transforms abstract knowledge value into concrete user contribution levels and converts the analysis results into actionable guidance suggestions, serving as a crucial hub for the entire system to achieve a virtuous cycle.

[0065] To achieve the above functions, the guidance and incentive mapping module includes a knowledge gap identification unit and a total contribution calculation unit in its internal structure. These two units are responsible for the core functions of knowledge system improvement and user incentive calculation, respectively.

[0066] The knowledge gap identification unit analyzes knowledge networks to identify knowledge gaps and guide users to contribute knowledge. This unit employs a graph theory-based analysis method, realizing the discovery and guidance of knowledge gaps through the following steps: Structural Hole Identification: This unit identifies sparsely connected knowledge nodes that occupy bridge positions by calculating the network structure constraint index of each node in the network. The lower the network structure constraint index of a node, the more structural holes it occupies. The formula for calculating the network structure constraint index is as follows: ; In the formula, For nodes The network structure constraint index, For nodes Indexes of all directly connected neighboring nodes. For nodes Deploy to neighboring nodes The proportion of network resources in a relation to its total network resources is equal to the node's value. With nodes The edge weight between nodes The sum of the weights of all outgoing edges, For a node Connected to, and also with nodes Connected intermediate nodes, This represents an indirect connection to a node established through the intermediate node qq. With nodes The degree of constraint on the relationship between them.

[0067] Semantic association analysis: This method uses natural language processing techniques to analyze the strength of semantic associations between node content, identifying knowledge node pairs that are semantically highly related but lack direct connections. The semantic association degree is calculated using the following formula: ; In the formula, For nodes With nodes semantic relevance, and They are nodes and nodes semantic vector representation, Let be the cosine similarity.

[0068] Guidance Strategy Generation: Based on the above analysis results, specific knowledge contribution guidance suggestions are generated, including but not limited to: supplementing knowledge nodes in specific fields, establishing connections between key nodes, and improving the content of nodes with low integrity.

[0069] The total contribution calculation unit, connected to the knowledge gap identification unit, is used to calculate the user's total contribution based on the dynamic weights of each knowledge node. This unit performs the following calculation process: ; In the formula, The user's total contribution. The set of all knowledge nodes contributed by this user. For knowledge nodes The dynamic weights, It contributes entropy to its current state. The system's preset upper limit for entropy. For knowledge nodes The timeliness coefficient.

[0070] The timeliness coefficient is calculated using an exponential decay function, with the specific formula as follows: ; In the formula, This is the timeliness coefficient. is the base of the natural logarithm. This is a preset time decay constant used to control the rate of value decay. For the current time, This refers to the creation time of this knowledge node.

[0071] In addition, this unit also calculates the distribution of users' contributions in their professional fields: ; In the formula, For users In the field The percentage of contribution, For belonging to the field The set of all knowledge nodes, For knowledge nodes The contribution value to the total contribution of users.

[0072] Finally, the guidance and incentive mapping module outputs the generated knowledge gap analysis report, user contribution evaluation results, and personalized contribution guidance suggestions, and displays them to users through the user interaction and visualization module. At the same time, the user's total contribution U_k will serve as the core basis for the system to allocate contribution incentives.

[0073] This embodiment, through intelligent identification of knowledge gaps and accurate calculation of user contributions, not only promotes the improvement and development of the knowledge system, but also establishes a fair, transparent, and efficient contribution incentive mechanism, effectively stimulating users' enthusiasm and sustainability in participating in knowledge co-construction and sharing, and providing key support for building a vibrant knowledge ecosystem community.

[0074] The user interaction and visualization module, connected to the aforementioned modules, is used to visually represent the knowledge network and the user's total contribution to the user.

[0075] Specifically, the user interaction and visualization module is the interactive interface and graphics rendering engine deployed on the front end of the system. It interacts with the knowledge input and vectorization module, dynamic knowledge graph module, dynamic value and entropy weight calculation module, and guidance and incentive mapping module through the application programming interface (API) to obtain knowledge network topology, node attribute information, user contribution data, and guidance suggestions in real time.

[0076] The core function of this module is to transform complex knowledge network relationships and abstract value assessment results into intuitive graphical displays, providing users with a user-friendly interactive experience and decision support.

[0077] The functionality of the user interaction and visualization module relies on its integrated graphics rendering engine, interactive event handling mechanism, and multi-dimensional visualization components. By transforming abstract data relationships into concrete visual elements and using scientific visualization coding methods, users can intuitively perceive the structural characteristics and evolutionary patterns of the knowledge network, while clearly understanding their own and others' contributions.

[0078] To achieve the above functions, the user interaction and visualization module includes a knowledge network display unit and a total contribution display unit in its internal structure. These two units are responsible for the core functions of knowledge system visualization and contribution information visualization, respectively.

[0079] The knowledge network display unit is used to acquire and visualize the knowledge network. This unit uses a force-directed graph algorithm for layout optimization and presents the knowledge network through the following visual encoding method: ; In the formula, For knowledge network diagrams, For a set of nodes, Let be the set of edges. For visualization, A collection of node visual elements. It is a collection of visual elements on the edge.

[0080] The node visual attribute encoding rules are as follows: ; In the formula, For nodes Visual size This is the scaling factor. For nodes The dynamic weights.

[0081] ; In the formula, For nodes Color coding, For color gradient functions, This is the lower bound of the entropy value. The upper limit of entropy, For nodes The current contribution entropy.

[0082] The rules for encoding edge visual attributes are as follows: ; In the formula, For the edge Visual weight, This is the edge weight scaling factor. For the edge The strength of the relationship.

[0083] ; In the formula, For the edge Color coding, The color of the positive relationship edge. The color of the edge with a negative relationship. For the set of positive relation edges, It is a set of negative relation edges.

[0084] The Total Contribution Display Unit, connected to the Knowledge Network Display Unit, is used to obtain and visualize a user's total contribution. This unit employs multi-dimensional information visualization technology to present user contribution information in the following ways: Radial graph showing total user contribution: ; In the formula, For users Radial plot of contribution For users Total contribution For users In various fields The percentage of contribution.

[0085] Contribution trend time series chart: ; In the formula, For users Contribution trend chart For time User contribution It is a time series.

[0086] The formula for visualizing the leaderboard comparison is as follows: ; In the formula, A user contribution ranking list The sum of contributions from all users. For the display of the front User name.

[0087] This module also provides a wealth of interactive features, including but not limited to: viewing knowledge node details, zooming and rotating the network topology, sliding the timeline to view historical status, multi-dimensional data filtering, and saving personalized view configurations. All visualizations support real-time updates, and the visualization will automatically update when the underlying data changes.

[0088] Ultimately, this user interaction and visualization module provides users with an immersive knowledge exploration environment and contribution query services through various forms such as web front-end interfaces, mobile applications, or large-screen display systems.

[0089] This embodiment transforms complex knowledge network relationships and contribution evaluation results into intuitive and easy-to-understand visual expressions through advanced visualization technology and user-friendly interactive design. This significantly reduces the cognitive load on users in understanding and using the system, effectively enhances users' experience and sense of gain in participating in knowledge co-construction and sharing, and provides an important experience guarantee for the promotion, popularization and continued activity of the system.

[0090] Please see the appendix Figure 7 This invention provides a method for knowledge co-construction and sharing in customs laboratories based on contribution incentives, comprising the following steps: Knowledge contribution processing: Receive knowledge contributions submitted by users and generate an initial contribution vector containing its inherent attributes, as well as an initial contribution entropy representing the uncertainty of its value; Knowledge network construction: Instantiate knowledge contributions into knowledge nodes carrying initial contribution vectors and initial contribution entropy, and establish positive and negative relationship edges between knowledge nodes based on user interactions to construct a knowledge network; Dynamic value calculation: Based on the positive relation edges in the knowledge network, the dynamic weight of each knowledge node is iteratively calculated through the value propagation algorithm, and the contribution entropy of each knowledge node is dynamically adjusted based on the positive and negative relation edges. Contribution incentive mapping: Analyze the knowledge network to identify knowledge gaps, and calculate the user's total contribution based on the dynamic weights of each knowledge node; Visual interaction: Presenting the knowledge network and the user's total contribution to the user in a visual format.

Claims

1. A contribution-incentive-based knowledge co-construction and sharing system for customs laboratories, characterized in that: include: The knowledge input and vectorization module is used to receive knowledge contributions submitted by users and generate an initial contribution vector containing inherent attributes and an initial contribution entropy representing the uncertainty of value for the knowledge contributions. The dynamic knowledge graph module, connected to the knowledge input and vectorization module, is used to instantiate the knowledge contribution into knowledge nodes carrying the initial contribution vector and the initial contribution entropy, and to establish positive and negative relationship edges between the knowledge nodes based on user interaction, so as to construct a knowledge network. The dynamic value and entropy weight calculation module is connected to the dynamic knowledge graph module. Based on the positive relation edges in the knowledge network, it iteratively calculates the dynamic weight of each knowledge node through the value propagation algorithm; and dynamically adjusts the contribution entropy of each knowledge node based on the positive relation edges and negative relation edges. The guidance and incentive mapping module is connected to the dynamic knowledge graph module and the dynamic value and entropy weight calculation module, and is used to analyze the knowledge network to identify knowledge gaps and guide users to make knowledge contributions. Based on the dynamic weights of each knowledge node, the user's total contribution is calculated and used as the basis for contribution incentives. The user interaction and visualization module, connected to the aforementioned modules, is used to visually display the knowledge network and the user's total contribution to the user.

2. The customs laboratory knowledge co-construction and sharing system based on contribution incentives according to claim 1, characterized in that, The knowledge input and vectorization module includes: A knowledge receiving unit is used to receive the knowledge contribution; An initial vector generation unit, connected to the knowledge receiving unit, is used to generate the initial contribution vector based on the inherent attributes of the knowledge contribution. An initial entropy setting unit, connected to the initial vector generation unit, is used to set the initial contribution entropy based on the initial contribution vector.

3. The customs laboratory knowledge co-construction and sharing system based on contribution incentives according to claim 2, characterized in that, The initial vector generation unit is specifically used for: The knowledge contribution is analyzed to obtain multi-dimensional inherent attributes, including at least novelty, criticality, completeness, and universality. The multi-dimensional inherent attributes are quantified to construct the initial contribution vector.

4. The customs laboratory knowledge co-construction and sharing system based on contribution incentives according to claim 1, characterized in that, The dynamic knowledge graph module includes: A node instantiation unit is used to receive the knowledge contribution, the initial contribution vector, and the initial contribution entropy, and to instantiate the knowledge contribution into a knowledge node carrying the initial contribution vector and the initial contribution entropy. A relationship edge establishment unit, connected to the node instantiation unit, is used to establish the positive relationship edge and the negative relationship edge between the knowledge nodes generated by the node instantiation unit based on user interaction.

5. The customs laboratory knowledge co-construction and sharing system based on contribution incentives according to claim 4, characterized in that, The relation edge establishment unit is specifically used for: The interactions representing referencing, resolving, applying, or aggregating relationships are established as the positive relationship edges; The interaction representing the falsification relation is established as the negative relation edge.

6. The customs laboratory knowledge co-construction and sharing system based on contribution incentives according to claim 1, characterized in that, The dynamic value and entropy weight calculation module includes: A dynamic weight calculation unit is used to acquire the knowledge network and, based on the positive relation edges in the knowledge network, iteratively calculate the dynamic weight of each knowledge node through a value propagation algorithm. The contribution entropy adjustment unit, connected to the dynamic weight calculation unit, is used to dynamically adjust the contribution entropy of each knowledge node based on the positive and negative relation edges in the knowledge network.

7. The customs laboratory knowledge co-construction and sharing system based on contribution incentives according to claim 6, characterized in that, The contribution entropy adjustment unit is specifically used for: When a new positive relation edge is detected on the knowledge node, an entropy reduction operation is performed on the contribution entropy of the knowledge node. When a new negative relation edge is detected on the knowledge node, an entropy increase operation is performed on the contribution entropy of the knowledge node.

8. The customs laboratory knowledge co-construction and sharing system based on contribution incentives according to claim 1, characterized in that, The guidance and incentive mapping module includes: A knowledge gap identification unit is used to analyze the knowledge network to identify knowledge gaps and guide users to make knowledge contributions. The total contribution calculation unit, connected to the knowledge gap identification unit, is used to calculate the user's total contribution based on the dynamic weights of each knowledge node.

9. The customs laboratory knowledge co-construction and sharing system based on contribution incentives according to claim 1, characterized in that, The user interaction and visualization module includes: A knowledge network display unit is used to acquire the knowledge network and visualize it. The total contribution display unit is connected to the knowledge network display unit and is used to obtain the user's total contribution and to visualize the user's total contribution.

10. A method for co-constructing and sharing customs laboratory knowledge based on contribution incentives, using the customs laboratory knowledge co-construction and sharing system based on contribution incentives as described in any one of claims 1-9, characterized in that, Includes the following steps: Knowledge contribution processing: Receive knowledge contributions submitted by users and generate an initial contribution vector containing its inherent attributes, and an initial contribution entropy representing its value uncertainty for the knowledge contribution; Knowledge network construction: The knowledge contribution is instantiated into a knowledge node carrying the initial contribution vector and the initial contribution entropy, and positive and negative relationship edges between the knowledge nodes are established according to user interaction to construct a knowledge network; Dynamic value calculation: Based on the positive relation edges in the knowledge network, the dynamic weight of each knowledge node is iteratively calculated through the value propagation algorithm, and the contribution entropy of each knowledge node is dynamically adjusted based on the positive and negative relation edges; Contribution incentive mapping: The knowledge network is analyzed to identify knowledge gaps, and the total contribution of the user is calculated based on the dynamic weights of each knowledge node. Visual interaction: Present the knowledge network and the user's total contribution to the user in a visual format.

Images