Technology transfer industry chain management method and system adopting dynamic matching algorithm

Abstract

The invention provides a technology transfer industry chain management method and system adopting a dynamic matching algorithm, and relates to the technical field of industry chain management, and the method comprises the steps: constructing feature vectors of a technology supplier, a demand side and an intermediary node, and obtaining a node feature vector set; obtaining an initial transfer path based on the node feature vector set in combination with a directed acyclic graph method; carrying out real-time information collection, and constructing a multi-level atlas comprising a plurality of transfer nodes and a cooperative relationship; obtaining a transfer prediction result in combination with the historical transfer data and the node attribute information; and according to the transfer prediction result, combining the upstream and downstream dynamic information of the industrial chain, performing path optimization by using a multi-target dynamic matching algorithm, obtaining a target technology transfer path, and executing technology transfer industrial chain management according to the target technology transfer path. The technical problems of prominent capability bottleneck and low conversion success rate of technology transfer industry chain management in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of industrial chain management, and in particular to a technology transfer industrial chain management method and system using a dynamic matching algorithm. Background Art

[0002] As the core link between technological innovation and industrial application, the efficient management of the technology transfer industry chain is directly related to the efficiency of transforming technological achievements into real productive forces. It is of key significance to optimizing the allocation of innovation resources and improving the overall innovation efficiency of the industry chain.

[0003] However, traditional technology transfer industry chain management mostly adopts a static model, which has problems such as information asymmetry and low matching efficiency between technology suppliers, demanders and intermediary nodes. It also ignores the dynamic changes in the upstream and downstream of the industry chain, such as resource fluctuations, demand adjustments, policy changes, etc., resulting in the technology transfer path being out of touch with the actual scenario, which in turn leads to prominent capacity bottlenecks and low conversion success rates.

[0004] Therefore, there is an urgent need for a management method that can perform dynamic matching to break the limitations of traditional static management. Summary of the Invention

[0005] The present invention aims to solve the technical problems in the prior art of technology transfer industry chain management, such as prominent capacity bottlenecks and low conversion success rates, and provides a technology transfer industry chain management method and system using a dynamic matching algorithm.

[0006] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a technology transfer industry chain management method using a dynamic matching algorithm, comprising: Construct feature vectors of technology suppliers, demanders, and intermediary nodes, and obtain a set of node feature vectors; Based on the node feature vector set, an initial transfer path is obtained in combination with a directed acyclic graph method; Performing real-time information collection according to the initial transfer path, and constructing a multi-level graph including multiple transfer nodes and collaborative relationships based on the real-time information collection results; Combining historical transfer data with node attribute information, traversing the multi-level graph to predict capacity bottlenecks and conversion success rates, and obtaining transfer prediction results; Based on the transfer prediction results, combined with the dynamic information of upstream and downstream of the industrial chain, a multi-objective dynamic matching algorithm is used to optimize the path, obtain the target technology transfer path, and execute technology transfer industry chain management based on the target technology transfer path.

[0007] In a second aspect, the present invention provides a technology transfer industry chain management system using a dynamic matching algorithm, comprising: Vector construction module, used to construct feature vectors of technology suppliers, demanders and intermediary nodes, and obtain node feature vector sets; An initial path acquisition module, configured to acquire an initial transfer path based on the node feature vector set and in combination with a directed acyclic graph method; A graph construction module is used to collect real-time information based on the initial transfer path and construct a multi-level graph including multiple transfer nodes and collaborative relationships based on the real-time information collection results; A transfer prediction module is used to combine historical transfer data with node attribute information, traverse the multi-level graph to predict capacity bottlenecks and conversion success rates, and obtain transfer prediction results; The optimization output module is used to optimize the path based on the transfer prediction results, combined with the dynamic information of the upstream and downstream of the industrial chain, using a multi-objective dynamic matching algorithm to obtain the target technology transfer path, and perform technology transfer industry chain management based on the target technology transfer path.

[0008] The beneficial effects of the present invention are: Compared with the existing technology, this application first constructs the characteristic vectors of technology suppliers, demanders and intermediary nodes, and obtains a set of node characteristic vectors, which provides a unified data foundation for the subsequent path calculation based on directed acyclic graphs and optimization of dynamic matching algorithms, ensuring quantitative analysis and accurate decision-making of the entire process of technology transfer. Secondly, based on the node characteristic vector set, combined with the directed acyclic graph method, the initial transfer path is obtained, the core flow nodes and hierarchical relationships from supply to demand are clarified, and the technology transfer path is transformed from qualitative judgment to quantitative calculation, providing a structured foundation for subsequent more refined management. Thirdly, real-time information collection is carried out according to the initial transfer path, and a multi-level graph containing multiple transfer nodes and collaborative relationships is constructed based on the real-time information collection results. The initial transfer path is refined into a structured network containing specific execution units and collaborative relationships, providing more realistic underlying data support for subsequent accurate prediction and optimization. Furthermore, by combining historical transfer data with node attribute information, the multi-level graph is traversed to predict capability bottlenecks and conversion success rates, obtaining transfer prediction results. This provides accurate capability bottleneck and conversion success rate assessments for each alternative path, laying a data-driven decision-making foundation for subsequent optimization. Finally, based on the transfer prediction results and combined with dynamic information from upstream and downstream of the industry chain, a multi-objective dynamic matching algorithm is used to optimize the path, obtain the target technology transfer path, and implement technology transfer industry chain management based on the target technology transfer path. This allows the technology transfer path to adapt to changes in the industry chain while achieving a multi-objective balance between minimizing capability bottlenecks and maximizing conversion success rates. This avoids the failure of static paths due to environmental changes during execution, ultimately achieving a dual improvement in technology transfer efficiency and stability.

[0009] Through the above technical solutions, this application solves the problem of inefficient matching caused by the fuzziness of subject features by quantifying the multi-dimensional attributes of suppliers, demanders, and intermediary nodes through feature vector quantization technology; by refining the collaborative relationship between nodes with the help of multi-level graphs, it breaks the limitation of unclear node associations under the traditional coarse framework; by combining the transfer prediction model with the multi-target dynamic matching algorithm, it quickly adjusts the path based on the dynamic changes of the upstream and downstream of the industrial chain, effectively avoiding the risk of path disconnection under static management. In this way, the matching accuracy, process efficiency, and conversion success rate of technology transfer industry chain management are improved, and the transformation process of technological achievements into industrial applications is accelerated. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a process for managing a technology transfer industry chain using a dynamic matching algorithm provided by the present invention; Figure 2 This is a structural diagram of a technology transfer industry chain management system using a dynamic matching algorithm provided by the present invention.

[0011] In the accompanying drawings, the components represented by the reference numerals are as follows: Vector construction module 11, initial path acquisition module 12, graph construction module 13, transfer prediction module 14, optimization output module 15. DETAILED DESCRIPTION

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0015] Example 1, as Figure 1 As shown, an embodiment of the present invention provides a technology transfer industry chain management method using a dynamic matching algorithm, including: S10: Construct feature vectors of technology suppliers, demanders, and intermediary nodes, and obtain a set of node feature vectors.

[0016] The technology transfer industry chain involves technology suppliers, demanders and intermediary nodes. Due to information asymmetry and low matching efficiency, traditional methods lead to insufficient accuracy in technology supply and demand matching, delayed transfer path planning, and prone to resource mismatch and industry chain coordination blockage.

[0017] To address the above issues, this application constructs feature vectors of technology suppliers, demanders, and intermediary nodes to obtain a set of node feature vectors.

[0018] Specifically, step S10 in the method includes: The vector dimensions of the feature vector include technical attributes, subject attributes and service attributes; The technical attributes include at least the type of technology, technical maturity, technical indicators, technical innovations, and technical relevance; The subject attributes include at least the subject's size, subject's financial status, subject's credibility, and subject's cooperation history; The service attributes include at least service scope, service success rate, service efficiency, and service resources.

[0019] In the embodiment of the present application, the vector dimensions of the feature vector include technical attributes, subject attributes and service attributes, which can comprehensively characterize the node characteristics and provide objective and comprehensive quantitative support for subsequent path planning and matching calculations.

[0020] Among them, technical attributes reflect the core characteristics of the technology itself, including at least technology type, technology maturity, technical indicators, technological innovations, and technology relevance: Technology type refers to the classification of the field to which the technology belongs, such as artificial intelligence, biomedicine, and new materials, and is used to accurately match the industry direction of the demand side; technology maturity is used to quantify the development stage of the technology, such as the laboratory stage and the commercialization stage; technical indicators include quantitative standards such as core performance parameters and cost thresholds; technological innovations reflect the core advantages of the technology, such as core technology breakthroughs and performance leaps; and technological relevance reflects the degree of compatibility with upstream and downstream technologies. Together, these attributes accurately portray the essential characteristics of the technology and are the core basis for determining the degree of technology matching.

[0021] Among them, the subject attributes reflect the node's own capabilities and reputation level, and include at least the subject's scale, financial status, credibility, and cooperation history. Scale includes the number of employees and institutional qualifications; financial status includes revenue scale and capital reserve capacity; credibility includes historical default rates and partner evaluations; and cooperation history includes the success rate of past technology transfer projects and the duration of cooperation. These attributes comprehensively reflect the node's execution capabilities and cooperation reliability, and are key criteria for assessing the feasibility of cooperation.

[0022] Service attributes measure a node's ability to provide supporting support, including at least service scope, service success rate, service efficiency, and service resources. Service scope refers to the geographic area or technical field covered by the service; service success rate refers to the percentage of successful conversions of historical service projects; service efficiency refers to the speed of service response and completion cycle; and service resources include the available resource pool, such as the number of testing equipment, the size of the expert database, and policy integration channels. These attributes collectively reflect a node's service support capabilities for technology transfer, providing an important reference for ensuring the feasibility of technology transfer implementation.

[0023] Specifically, the “constructing feature vectors of technology suppliers, demanders, and intermediary nodes, and obtaining a node feature vector set” includes: Based on the supply capability data of technology suppliers, the technical attributes, subject attributes and service attributes of technology supply nodes are analyzed and extracted to form the feature vector of technology supply nodes; Based on the demand data of the demand side, the technical attributes, subject attributes and service attributes of the demand nodes are analyzed and extracted to form the demand node feature vector; Clustering the intermediary nodes to obtain an intermediary node category set, and statistically analyzing the intermediary node category set based on big data to extract typical capability parameters of each intermediary node category and generate an intermediary node feature vector; The technology supply node feature vector, the demand node feature vector, and the intermediary node feature vector are aggregated to form the node feature vector set.

[0024] In an embodiment of the present application, the technical attributes, subject attributes, and service attributes of a technology supply node are first analyzed and extracted based on the supply capability data of the technology supplier to form a technology supply node feature vector, wherein the supply capability data includes technical specifications, patent documents, production qualification documents, corporate annual reports, etc. For example, based on the supply capability data of the technology supplier, such as technical specifications, patent documents, production qualification documents, corporate annual reports, etc., the technical attributes, subject attributes, and service attributes of the technology supply node are extracted to form a technology supply node feature vector, for example, {Technical Attributes: [Technology Type = New Energy Battery, TRL = 7, Technical Indicator = Energy Density 350Wh / kg, Technical Innovation = Solid-State Electrolyte, Technical Relevance = Requires Adaptation to BMS System], Subject Attributes: [Subject Scale = Listed Company, Subject Financial Status = AAA, Subject Reputation = 98%, Subject Cooperation History = 120], Service Attributes: [Service Scope = Global Authorization, Service Success Rate = 95%, Service Efficiency = 6-Month Mass Production, Service Resources = 10 OEM Factories]}, which can reflect the technology supply capability and supporting service level of the technology supplier.

[0025] Secondly, based on the demand side's demand data, the technical attributes, subject attributes, and service attributes of the demand node are analyzed and extracted to form a demand node feature vector. The demand data includes a technical requirements list, application scenario description, etc. For example, based on the demand side's demand data such as the technical requirements list and application scenario description, the technical attributes, subject attributes, and service attributes of the demand node are extracted to form a demand node feature vector. For example, {Technical Attributes: [Technology Type = Autonomous Driving Algorithm, TRL Requirement = 6, Technical Indicator = Latency < 50ms, Technological Innovation Requirement = Multi-Sensor Fusion, Subject Attributes: [Subject Size = Medium-Sized Automaker, Subject Reputation = 91%, Subject Cooperation History = 35], Service Attributes: [Service Scope = Localized Deployment, Service Success Rate Requirement > 85%, Service Efficiency = Delivery within 3 Months]} can reflect the demand side's technical requirements standards and cooperation conditions.

[0026] Next, a clustering algorithm is used to cluster intermediary nodes by service scope, generating a set of intermediary node categories. This set of intermediary node categories is then statistically analyzed based on big data to extract typical capability parameters for each intermediary node category, such as average service success rate and resource coverage, and generate intermediary node feature vectors. For example, K-means clustering (k=5) is performed on intermediary nodes by service scope to obtain a set of intermediary node categories, such as {A: testing and certification, B: financing matching, …}. This set of intermediary node categories is then statistically analyzed based on big data to extract typical capability parameters for each intermediary node category. For example, if intermediary node category A has a testing efficiency of 10 days, the resulting feature vector for category A is {Technical Attributes: [Service Technology Field = Electronics / Mechanical, Certification Standard Coverage = 98%], Entity Attributes: [Average Employees = 50, Industry Reputation Rating = AA], Service Attributes: [Scope = Global, Success Rate = 99%, Efficiency = 10 Days]}. This highlights commonalities between categories and facilitates efficient matching of intermediary nodes.

[0027] Finally, the feature vectors of technology supply nodes, demand nodes, and intermediary nodes are aggregated to form a node feature vector set, which provides a quantitative comparison basis for subsequent DAG path planning.

[0028] In summary, compared to existing technologies, this application constructs feature vectors for technology suppliers, demanders, and intermediary nodes, obtaining a set of node feature vectors. This provides a unified data foundation for subsequent directed acyclic graph-based path calculation and optimization of dynamic matching algorithms, ensuring quantitative analysis and accurate decision-making throughout the entire technology transfer process.

[0029] S20: Based on the node feature vector set, an initial transfer path is obtained in combination with a directed acyclic graph method.

[0030] The technology transfer from supply to demand involves multiple flow nodes. Traditional methods lack quantitative analysis of the relationship between nodes and path priority assessment, which often leads to unclear transfer paths, high matching costs and redundant links.

[0031] To address the above problems, the present application obtains the initial transfer path based on the node feature vector set and combined with the directed acyclic graph method.

[0032] Specifically, step S20 in the method includes: According to the node feature vector set, a directed acyclic graph is constructed with the technology supply node as a starting point, the plurality of intermediary nodes as intermediate nodes, and the demand node as an end point, wherein the edges of the directed acyclic graph are unidirectional edges and are directed from the technology supply node to the demand node; In the directed acyclic graph, based on the principle of minimum edge weight, a shortest path algorithm is used to calculate a path from the technology supply node to the demand node through at least one of the intermediary nodes to obtain an initial transfer path; The initial transfer path is used to define the hierarchical path of technology transfer.

[0033] In the embodiment of the present application, a directed acyclic graph is first constructed. Specifically: according to the node feature vector set, a directed acyclic graph is constructed with the technology supply node as the starting point, multiple intermediary nodes as the intermediate nodes, and the demand node as the end point, wherein the edge of the directed acyclic graph is a unidirectional edge and the direction is from the technology supply node to the demand node. Exemplarily, the nodes of the directed acyclic graph are the technology supply node (technology provider), multiple intermediary nodes, and the demand node (technology receiver). The edge of the directed acyclic graph is a unidirectional edge, and the direction strictly follows the logic of technology supply node → intermediary node → demand node, that is, it can only point from upstream to downstream, and reverse or loops are not allowed, which ensures the acyclicity of the graph and avoids logical contradictions in the technology transfer path.

[0034] Secondly, in a directed acyclic graph, the principle of minimum edge weight is used. The shortest path algorithm is used to calculate the path from the technology supply node through at least one intermediary node to the demand node to obtain the initial transfer path, where the initial transfer path is used to define the hierarchical path of technology transfer. For example, the edge weight of a directed acyclic graph reflects the path transfer cost and can be calculated using the following formula: edge weight = 1 / (technology matching degree × node service capability coefficient × historical success rate), where technology matching degree is the cosine similarity of the technical attributes of the technology supply node and the demand node, the service capability coefficient is the weighted value of the intermediary node's service success rate and service efficiency, and the historical success rate is the success rate of past cooperation between the two nodes. The smaller the edge weight, the higher the matching degree, the higher the service capability, and the higher the success rate. Therefore, the principle of minimum edge weight is used in a directed acyclic graph. Exemplarily, in a directed acyclic graph, a shortest path algorithm, such as the Dijkstra algorithm, the Floyd algorithm, etc., is used to calculate the total edge weight of all possible paths from the technology supply node through at least one intermediary node to the demand node, and the path with the smallest total edge weight is selected as the initial transfer path. The initial transfer path is a simplified hierarchical relationship chain, for example, technology supply node (supplier) → intermediary node A → intermediary node B → demand node (demander), which clarifies the core flow nodes, hierarchical relationships and flow order from supply to demand.

[0035] In summary, compared to existing technologies, this application uses the node feature vector set and a directed acyclic graph method to obtain the initial transfer path. By converting node features into a graphical network and calculating the optimal path, the core flow nodes and hierarchical relationships from supply to demand are clarified, achieving a shift from qualitative judgment to quantitative calculation of technology transfer paths, providing a structured foundation for subsequent, more refined management.

[0036] S30: Real-time information collection is performed according to the initial transfer path, and a multi-level graph including multiple transfer nodes and collaborative relationships is constructed according to the real-time information collection results.

[0037] The initial transfer path, as a rough framework of technology flow, only includes the macro-level relationship between suppliers, intermediary nodes and demanders. However, in reality, each intermediary node often contains multiple transfer nodes with specific functions.

[0038] In response to the above problems, the present application performs real-time information collection based on the initial transfer path, and constructs a multi-level graph containing multiple transfer nodes and collaborative relationships based on the real-time information collection results.

[0039] Specifically, step S30 in the method includes: Extracting a plurality of transfer nodes corresponding to each intermediate node based on the initial transfer path and generating a list; Information is called according to the list, and regularized and standardized to obtain entity feature information of the transfer node; According to the entity feature information, the initial transfer path is expanded accordingly to generate a multi-level graph. Each level of the multi-level graph corresponds to the technology supply node, the demand node and multiple intermediary nodes, and each intermediary node is under the jurisdiction of multiple transfer nodes. Each transfer node represents the transfer node capability and collaborative relationship in the form of a graph.

[0040] In an embodiment of the present application, first, multiple transfer nodes corresponding to each intermediary node are extracted based on the initial transfer path to generate a list, wherein the transfer node is a specific execution unit under the intermediary node, the intermediary node and the transfer node are parent-child hierarchical, and the transfer nodes are connected by a collaborative relationship. For example, multiple transfer nodes are extracted from the intermediary node A in the initial path: technology supply node → intermediary node A → demand node, such as transfer node A1, transfer node A2, transfer node A3, etc. If the intermediary node A is a testing agency, then transfer node A1, transfer node A2, and transfer node A3 may be material testing, safety assessment, and certification issuance, respectively. In this way, a transfer node list is generated based on multiple transfer nodes, which clarifies the specific objects for which information needs to be collected, defines the scope for subsequent information acquisition, and avoids the blindness of information collection.

[0041] Secondly, information is retrieved based on the list, and regularized and standardized to obtain the entity feature information of the transfer node. This information can be obtained from internal enterprise systems (such as ERP, CRM, etc.), IoT devices (such as multimodal sensors), etc. For example, the operational data of the transfer nodes in the list, such as equipment status, task queue, and staff size, are retrieved through a real-time API, and the data is regularized and standardized. Regularization unifies the information dimensions of different transfer nodes and eliminates the incomparability caused by dimensional differences. Standardization can perform data cleaning, remove extreme values, normalize, and other processes to reduce noise interference, ensure data stability and consistency, and convert it into structured feature information. The entity feature information of the transfer node can reflect the real-time capabilities (such as efficiency, resource reserves, etc.) and status (such as load) of the transfer node, and is the core data that characterizes the actual operation of the transfer node.

[0042] Finally, based on the entity feature information, the initial transfer path is expanded accordingly to generate a multi-level graph. Each level of the multi-level graph corresponds to a technology supply node, a demand node, and multiple intermediary nodes. Each intermediary node has multiple transfer nodes under its jurisdiction. Each transfer node is represented in a graph form by its capabilities and collaborative relationships. For example, based on the entity feature information, the initial transfer path is expanded into a multi-level graph, with the top layer representing the technology supply node, the bottom layer representing the demand node, and the middle layer representing each intermediary node and its multiple transfer nodes. The attribute graph model accurately describes the node capabilities (such as efficiency) and collaborative relationships (such as sequential dependency or parallel execution) of each transfer node. In this way, the initial transfer path is refined from the rough framework of technology supply node → intermediary node A → demand node to the specific operational chain of technology supply node → intermediary node A {transfer node A1, transfer node A2, transfer node A3} → demand node. This clearly demonstrates the participants, capabilities, and collaborative logic of each micro-link in technology transfer, providing a visual analysis platform for subsequent prediction of path bottlenecks and optimization of collaborative efficiency.

[0043] In summary, compared to existing technologies, this application collects real-time information based on the initial transfer path and constructs a multi-level graph containing multiple transfer nodes and collaborative relationships based on the real-time information collection results. In this way, the initial transfer path is refined into a structured network containing specific execution units and collaborative relationships, providing more realistic underlying data support for subsequent accurate prediction and optimization.

[0044] S40: Combining historical transfer data with node attribute information, traversing the multi-level graph to predict capacity bottlenecks and conversion success rates, and obtaining transfer prediction results.

[0045] Capacity bottlenecks refer to the transfer blockages caused by insufficient resource allocation, poor process integration, or capacity mismatches at various nodes during the technology transfer process, which manifests itself in task delays, link interruptions, or resource waste. The conversion success rate refers to the probability that technology, starting from the supply side and through the collaborative operation of various intermediary nodes, is successfully accepted and applied by the demand side. It comprehensively reflects the collaborative efficiency, technical adaptability, and resource support capabilities of each node. In the management of the technology transfer industry chain, capacity bottlenecks will directly lead to extended transfer cycles, rising costs, and even path interruptions. The conversion success rate determines the quality of the industrialization of technological achievements. A low success rate will cause resource mismatches and investment losses. Both of these are affected by the dynamic state of the nodes and have strong uncertainty. Therefore, it is necessary to make advance judgments through transfer prediction models to provide a quantitative basis for path optimization.

[0046] To address the above issues, this application combines historical transfer data with node attribute information, traverses the multi-level graph to predict capacity bottlenecks and conversion success rates, and obtains transfer prediction results.

[0047] Specifically, step S40 in the method includes: Based on the multi-level graph, traverse multiple levels from top to bottom to perform random selection on multiple transfer nodes to obtain alternative technology transfer paths, and iteratively obtain a set of alternative technology transfer paths; Performing clustering according to the acquired node attribute information of the plurality of transfer nodes, and outputting clustering results as a plurality of node cluster lists; homomorphically partitioning the historical transfer data according to the node cluster list to form a plurality of node historical transfer data clusters; Using multiple node historical transfer data clusters as sample data, construct multiple transfer prediction models and perform supervised training; The entity feature information of multiple transfer nodes is respectively input into multiple transfer prediction models to predict capacity bottlenecks and conversion success rates, and the capacity bottleneck and conversion success rate prediction results are superimposed and fused according to the set of alternative technology transfer paths to obtain the path capacity bottleneck and path conversion success rate of each alternative technology transfer path, and output as the transfer prediction result.

[0048] In an embodiment of the present application, first, based on a multi-level graph, multiple levels are traversed from top to bottom to perform random selection for multiple transfer nodes, that is, starting from the technology supply node, passing through the intermediary nodes of the middle level and the transfer nodes under it, and finally reaching the demand node, different transfer node combinations are randomly selected to obtain alternative technology transfer paths, and then the alternative technology transfer path set is iteratively obtained, wherein the random selection is to avoid falling into local optimality and fully explore the potential feasible paths in the multi-level graph. Exemplarily, from the multi-level graph: technology supply node → intermediary node A {transfer node A1, transfer node A2, transfer node A3} → demand node, multiple levels are traversed from top to bottom to perform random selection of multiple transfer nodes to obtain alternative technology transfer paths, for example, technology supply node → transfer node A1 → demand node, technology supply node → transfer node A2 → demand node, technology supply node → transfer node A3 → demand node. In this way, the above selection process is repeated through multiple iterations to generate a set of alternative technology transfer paths containing multiple different transfer node combinations, ensuring that enough potential paths are covered to avoid missing the optimal solution due to insufficient path enumeration.

[0049] Secondly, clustering is performed based on the acquired node attribute information of the multiple transfer nodes, and the clustering results are output as multiple node cluster lists. For example, based on the acquired node attribute information of the multiple transfer nodes, such as service scope, service success rate, service efficiency, service resources, etc., a clustering algorithm (such as K-means or hierarchical clustering) is used to cluster the multiple transfer nodes into multiple node clusters. For example, material inspection transfer nodes with the same service scope are clustered into one node cluster. Clustering is performed in the same manner to ultimately form multiple node cluster lists, clarifying the transfer nodes contained in each cluster and their common characteristics. In this way, transfer nodes with similar attributes are grouped together, reducing prediction complexity and improving prediction efficiency and accuracy.

[0050] Thirdly, the historical transfer data is homomorphically partitioned according to the node cluster list to form multiple node historical transfer data clusters. Homomorphic partitioning means that the clustering method of the historical transfer data is consistent with the classification logic of the node cluster, that is, the historical transfer data is partitioned according to the node cluster label to ensure that the training data and the prediction target are identically distributed. For example, according to the node cluster list, the nodes involved in the historical transfer data are classified according to the clusters to which they belong. For example, the historical transfer data is homomorphically partitioned according to the material detection node cluster in the node cluster list to form a material detection node historical transfer data cluster. In the same way, homomorphic partitioning is performed to finally form multiple node historical transfer data clusters to ensure the consistency of the training data and the prediction object.

[0051] Furthermore, using multiple node historical transfer data clusters as sample data, multiple transfer prediction models are constructed and supervised training is performed. For example, the transfer prediction model can be constructed using the following technical paths: 1. Data preparation: Historical data is extracted from the node historical transfer data clusters. Attribute features of the nodes, such as the load rate and number of personnel during a particular transfer, are extracted from the historical data as sample input features. Furthermore, the sample input features are manually labeled with historical capacity bottlenecks and historical conversion success rates corresponding to the historical data. The model is then divided into a training set (for model fitting) and a validation set (for parameter adjustment) in a 7:3 ratio. 2. Model construction: A neural network model architecture can be used. The transfer prediction model can adopt a multi-input and dual-output adaptive structure, which is mainly composed of an input layer, a feature processing layer, a feature fusion layer, and an output layer. The input layer receives the entity feature information of the transfer node, which mainly includes numerical features, such as efficiency (day / order), load rate (%), success rate (%) and other directly quantifiable indicators, as well as categorical features, such as service type, coverage area and other attributes that need to be encoded. The input layer performs a preliminary separation of the two types of features to prepare for subsequent processing; the feature processing layer converts discrete categories into low-dimensional dense vectors for categorical features through an embedding layer to capture potential correlations between categories, and eliminates dimensional differences in numerical features through a standardization layer (such as Z-Score normalization) to ensure balanced feature weights. The processed data is integrated into a feature vector of unified dimension through a splicing layer; the feature fusion layer uses a fully connected network for deep feature extraction, which includes a 2-layer fully connected network. The first layer has 32 neurons (ReLU activation function), the second layer has 16 neurons (ReLU activation function), and the Dropout layer (dropout rate=0.2) to suppress overfitting; the output layer uses a dual output head structure, corresponding to two prediction targets: the capacity bottleneck output head uses linear output (regression result), and the conversion success rate output head uses a sigmoid activation function to output the probability of success (between 0 and 1). 3. Model training: The attribute characteristics of the node's historical transfer data are used as input features, and historical capacity bottlenecks and historical conversion success rates are used as supervision labels. A weighted joint loss function is used, with the formula being total loss = 0.6 × bottleneck loss + 0.4 × success rate loss. The weights are set according to business priorities, with bottleneck predictions having a higher weight to reduce risk. The Adam optimizer (learning rate = 0.001, , ), the batch size is set to 32, the iteration round limit is 100, and training is stopped when the total loss of the validation set does not decrease for 10 consecutive rounds to avoid overfitting. During the training process, the validation set indicators are monitored in real time. For classification tasks, the focus is on AUC and F1 score, and for regression tasks, the focus is on R² and MAE. The best performing model is selected and saved as the final transfer prediction model to obtain the trained transfer prediction model.

[0052] Finally, the entity feature information of multiple transfer nodes is fed into multiple transfer prediction models to predict capacity bottlenecks and conversion success rates. These prediction results are then superimposed and fused based on the set of alternative technology transfer paths to obtain the path capacity bottleneck and path conversion success rate for each alternative technology transfer path, which is then output as a transfer prediction result. For example, the entity feature information (such as efficiency, resource reserves, and load) of multiple transfer nodes in a multi-level graph is fed into the transfer prediction model corresponding to their clusters. The prediction output is the capacity bottleneck and conversion success rate for each transfer node. For example, a transfer node may have a potential delay of 2 days and a conversion success rate of 90%. For example, the capacity bottleneck and conversion success rate prediction results are superimposed and fused based on the set of alternative technology transfer paths. For the capacity bottleneck prediction results, the maximum capacity bottleneck of all transfer nodes in the path is taken as the path capacity bottleneck. For the conversion success rate prediction results, the product of the conversion success rates of all serially connected transfer nodes is taken as the path conversion success rate. The final output is the transfer prediction result. This transfer prediction result quantifies the potential risk and predicted success rate of each path and serves as the core basis for subsequent dynamic path optimization.

[0053] In summary, compared to existing technologies, this application combines historical transfer data with node attribute information, traverses the multi-level graph to predict capacity bottlenecks and conversion success rates, and obtains transfer prediction results. In this way, the complex node relationships in the multi-level graph are converted into quantifiable path evaluation indicators. This not only uses historical data to mine node behavior patterns, but also covers potential possibilities by randomly generating paths. Ultimately, it provides accurate capacity bottleneck and conversion success rate assessments for each alternative path, laying a data-driven decision-making foundation for subsequent optimization.

[0054] S50: Based on the transfer prediction results and combined with the dynamic information of the upstream and downstream of the industrial chain, a multi-objective dynamic matching algorithm is used to optimize the path, obtain the target technology transfer path, and perform technology transfer industry chain management based on the target technology transfer path.

[0055] Information in the upstream and downstream of the industrial chain is always changing dynamically, such as resource fluctuations on the supply side, priority adjustments on the demand side, and changes in intermediary service capabilities. Once the traditional static path is determined, it remains fixed and cannot respond to real-time changes in node status and environmental conditions, resulting in the path gradually becoming disconnected from actual demand. It is very easy to have node capability mismatch, reduced transfer efficiency, and even cause path interruption, reducing the success rate of technology conversion and causing resource investment loss.

[0056] In response to the above problems, this application uses a multi-objective dynamic matching algorithm to optimize the path based on the transfer prediction results and combined with the dynamic information of the upstream and downstream of the industrial chain, obtains the target technology transfer path, and performs technology transfer industry chain management based on the target technology transfer path.

[0057] Specifically, step S50 in the method includes: Select the top N optimal candidate technology transfer paths from the transfer prediction results, and obtain dynamic information of the upstream and downstream of the industry chain in real time; Based on the upstream and downstream dynamic information of the industrial chain, predict the capacity bottlenecks and conversion success rates of the multiple transfer nodes corresponding to the N alternative technology transfer paths to obtain a first dynamic prediction result; Based on the upstream and downstream dynamic information of the industrial chain, predict the capacity bottleneck and conversion success rate of the approximate transfer nodes of the plurality of transfer nodes corresponding to the N alternative technology transfer paths to obtain a second dynamic prediction result; Marking an optimal transfer node by combining the first dynamic prediction result and the second dynamic prediction result, and matching and updating the N candidate technology transfer paths according to the optimal transfer node marking result; Iteratively predict the capacity bottlenecks and conversion success rates of the updated N alternative technology transfer paths, and select the optimal path based on the acquired path capacity bottlenecks and path conversion success rates, and output the target technology transfer path.

[0058] In the embodiment of the present application, the top N optimal candidate technology transfer paths from the transfer prediction results are first selected, and corresponding dynamic information from upstream and downstream of the industry chain is updated in real time. For example, the top N optimal candidate technology transfer paths with the best overall performance are selected from the transfer prediction results. For example, paths with the top 20% conversion success rate and the bottom 20% of capability bottlenecks are selected to ensure a high-quality starting point for optimization. Dynamic change data from upstream and downstream of the industry chain is also collected simultaneously, such as resource fluctuations on the technology supply side, priority adjustments on the demand side, resource allocation of intermediary nodes, and changes in cooperative relationships. This dynamic information directly affects the real-time capabilities of the nodes and is a key input for dynamic optimization.

[0059] Secondly, based on the dynamic information of the upstream and downstream of the industrial chain, the capacity bottleneck and conversion success rate of multiple transfer nodes corresponding to the N alternative technology transfer paths are predicted to obtain the first dynamic prediction result. Based on the updated dynamic information of upstream and downstream of the industrial chain, the capacity bottlenecks and conversion success rates of multiple transfer nodes corresponding to the top N alternative technology transfer paths are re-evaluated. For example, if the dynamic information shows that the efficiency of a certain node has dropped by 10% due to personnel resignation, the capacity bottleneck and conversion success rate are re-predicted through the transfer prediction model. The capacity bottleneck is extended from the original 1 day to 2 days, and the conversion success rate is reduced from the original 85% to 70%, ensuring that the evaluation of the original path is synchronized with the real-time status.

[0060] Next, based on the dynamic information from upstream and downstream of the industry chain, the capacity bottleneck and conversion success rate of the approximate transfer nodes corresponding to the multiple transfer nodes of the N alternative technology transfer paths are predicted to obtain a second dynamic prediction result. For example, for the multiple transfer nodes in the alternative technology transfer path, similar nodes with similar functions are found, such as other nodes in the same node cluster. For example, if the original path uses transfer node A1, and transfer node A2 in the same node cluster shows a lower load in the dynamic information, the capacity bottleneck and conversion success rate of transfer node A2 are predicted to obtain a second dynamic prediction result. For example, the capacity bottleneck is 0.5 days and the conversion success rate is 90%. By introducing approximate alternative transfer nodes, the limitations of the original path are broken, providing more possibilities for optimization.

[0061] Furthermore, the optimal transfer node is marked by combining the first and second dynamic prediction results, and the N alternative technology transfer paths are matched and updated based on the optimal transfer node marking results. For example, for each transfer node in each alternative technology transfer path, its first dynamic prediction result is compared with the second dynamic prediction result of the corresponding similar node, and the node with better performance is marked. For example, if the original transfer node A1 has a capacity bottleneck of 2 days and a conversion success rate of 70%, and the similar transfer node A2 has a capacity bottleneck of 0.5 days and a conversion success rate of 90%, then transfer node A2 is marked as the optimal node for that link, and the corresponding node in the original path is replaced with the marked optimal node to generate an updated alternative path.

[0062] Finally, the updated N candidate technology transfer paths are iteratively predicted for their capacity bottlenecks and conversion success rates. Based on the obtained path capacity bottlenecks and path conversion success rates, the optimal path is selected and output as the target technology transfer path. For example, the above process of dynamic information collection → transfer node prediction → transfer node replacement is repeated for the updated N candidate technology transfer paths, and multiple rounds of iterations, such as 3-5 rounds, are performed. Each round of iteration is based on the latest industry chain dynamic information, recalculating the path capacity bottleneck and path conversion success rate to ensure that the path continuously adapts to changes. After the iteration is completed, the final performance of each path is comprehensively evaluated, and the path that simultaneously meets the lowest path capacity bottleneck and the highest path conversion success rate is selected as the target technology transfer path.

[0063] In summary, compared to existing technologies, this application uses a multi-objective dynamic matching algorithm to optimize paths based on the transfer prediction results, combined with dynamic information from upstream and downstream of the industry chain, to obtain a target technology transfer path, and then implements technology transfer industry chain management based on this target technology transfer path. In this way, the technology transfer path adapts to changes in the industry chain while achieving a multi-objective balance between minimizing capacity bottlenecks and maximizing conversion success rates. This avoids the failure of static paths caused by environmental changes during execution, ultimately achieving a dual improvement in technology transfer efficiency and stability.

[0064] In summary, the embodiments of the present application have at least the following technical effects: Compared to existing technologies, this application first constructs feature vectors for technology suppliers, demanders, and intermediary nodes, obtaining a set of node feature vectors. This provides a unified data foundation for subsequent directed acyclic graph-based path calculation and optimization of dynamic matching algorithms, ensuring quantitative analysis and accurate decision-making throughout the entire technology transfer process.

[0065] Secondly, this application uses the node feature vector set and a directed acyclic graph method to obtain the initial transfer path. By converting node features into a graphical network and calculating the optimal path, the core flow nodes and hierarchical relationships from supply to demand are clarified, achieving a shift from qualitative judgment to quantitative calculation of technology transfer paths, providing a structured foundation for subsequent, more refined management.

[0066] Furthermore, this application collects real-time information based on the initial transfer path and constructs a multi-level graph containing multiple transfer nodes and collaborative relationships based on the real-time information collection results. In this way, the initial transfer path is refined into a structured network containing specific execution units and collaborative relationships, providing more realistic underlying data support for subsequent accurate prediction and optimization.

[0067] Furthermore, this application combines historical transfer data with node attribute information to traverse the multi-level graph to predict capacity bottlenecks and conversion success rates, obtaining transfer prediction results. This transforms the complex node relationships in the multi-level graph into quantifiable path evaluation indicators. This not only uses historical data to mine node behavior patterns, but also covers potential possibilities through randomly generated paths. Ultimately, it provides accurate capacity bottleneck and conversion success rate assessments for each alternative path, laying a data-driven decision-making foundation for subsequent optimization.

[0068] Finally, based on the transfer prediction results and combined with dynamic information from upstream and downstream of the industry chain, this application uses a multi-objective dynamic matching algorithm to optimize the path, obtain the target technology transfer path, and implement technology transfer industry chain management based on the target technology transfer path. In this way, the technology transfer path can adapt to changes in the industry chain while achieving a multi-objective balance between minimizing capacity bottlenecks and maximizing conversion success rates. This avoids the failure of static paths caused by environmental changes during execution, ultimately achieving a dual improvement in technology transfer efficiency and stability.

[0069] Through the above technical solutions, this application solves the problem of inefficient matching caused by the fuzziness of subject features by quantifying the multi-dimensional attributes of suppliers, demanders, and intermediary nodes through feature vector quantization technology; by refining the collaborative relationship between nodes with the help of multi-level graphs, it breaks the limitation of unclear node associations under the traditional coarse framework; by combining the transfer prediction model with the multi-target dynamic matching algorithm, it quickly adjusts the path based on the dynamic changes of the upstream and downstream of the industrial chain, effectively avoiding the risk of path disconnection under static management. In this way, the matching accuracy, process efficiency, and conversion success rate of technology transfer industry chain management are improved, and the transformation process of technological achievements into industrial applications is accelerated.

[0070] Example 2, as Figure 2 As shown, based on the same inventive concept as the technology transfer industry chain management method using a dynamic matching algorithm provided in Example 1, an embodiment of the present invention further provides a technology transfer industry chain management system using a dynamic matching algorithm, including: Vector construction module 11, used to construct feature vectors of technology suppliers, demanders and intermediary nodes, and obtain a node feature vector set; An initial path acquisition module 12 is configured to acquire an initial transfer path based on the node feature vector set and in combination with a directed acyclic graph method; A graph construction module 13 is configured to collect real-time information based on the initial transfer path and construct a multi-level graph including multiple transfer nodes and collaborative relationships based on the real-time information collection results; The transfer prediction module 14 is used to combine historical transfer data and node attribute information, traverse the multi-level graph to predict capacity bottlenecks and conversion success rates, and obtain transfer prediction results; The optimization output module 15 is used to optimize the path based on the transfer prediction results and the dynamic information of the upstream and downstream of the industrial chain using a multi-objective dynamic matching algorithm to obtain the target technology transfer path and perform technology transfer industry chain management based on the target technology transfer path.

[0071] The vector construction module 11 is specifically configured to: The vector dimensions of the feature vector include technical attributes, subject attributes and service attributes; The technical attributes include at least the type of technology, technical maturity, technical indicators, technical innovations, and technical relevance; The subject attributes include at least the subject's size, subject's financial status, subject's credibility, and subject's cooperation history; The service attributes include at least service scope, service success rate, service efficiency, and service resources.

[0072] Furthermore, the “constructing feature vectors of technology suppliers, demanders, and intermediary nodes, and obtaining a node feature vector set” includes: Based on the supply capability data of technology suppliers, the technical attributes, subject attributes and service attributes of technology supply nodes are analyzed and extracted to form the feature vector of technology supply nodes; Based on the demand data of the demand side, the technical attributes, subject attributes and service attributes of the demand nodes are analyzed and extracted to form the demand node feature vector; Clustering the intermediary nodes to obtain an intermediary node category set, and statistically analyzing the intermediary node category set based on big data to extract typical capability parameters of each intermediary node category and generate an intermediary node feature vector; The technology supply node feature vector, the demand node feature vector, and the intermediary node feature vector are aggregated to form the node feature vector set.

[0073] The initial path acquisition module 12 is specifically configured to: According to the node feature vector set, a directed acyclic graph is constructed with the technology supply node as a starting point, the plurality of intermediary nodes as intermediate nodes, and the demand node as an end point, wherein the edges of the directed acyclic graph are unidirectional edges and are directed from the technology supply node to the demand node; In the directed acyclic graph, based on the principle of minimum edge weight, a shortest path algorithm is used to calculate a path from the technology supply node to the demand node through at least one of the intermediary nodes to obtain an initial transfer path; The initial transfer path is used to define the hierarchical path of technology transfer.

[0074] The graph construction module 13 is specifically used for: Extracting a plurality of transfer nodes corresponding to each intermediate node based on the initial transfer path and generating a list; Information is called according to the list, and regularized and standardized to obtain entity feature information of the transfer node; According to the entity feature information, the initial transfer path is expanded accordingly to generate a multi-level graph. Each level of the multi-level graph corresponds to the technology supply node, the demand node and multiple intermediary nodes, and each intermediary node is under the jurisdiction of multiple transfer nodes. Each transfer node represents the transfer node capability and collaborative relationship in the form of a graph.

[0075] The transfer prediction module 14 is specifically configured to: Based on the multi-level graph, traverse multiple levels from top to bottom to perform random selection on multiple transfer nodes to obtain alternative technology transfer paths, and iteratively obtain a set of alternative technology transfer paths; Performing clustering according to the acquired node attribute information of the plurality of transfer nodes, and outputting clustering results as a plurality of node cluster lists; homomorphically partitioning the historical transfer data according to the node cluster list to form a plurality of node historical transfer data clusters; Using multiple node historical transfer data clusters as sample data, construct multiple transfer prediction models and perform supervised training; The entity feature information of multiple transfer nodes is respectively input into multiple transfer prediction models to predict capacity bottlenecks and conversion success rates, and the capacity bottleneck and conversion success rate prediction results are superimposed and fused according to the set of alternative technology transfer paths to obtain the path capacity bottleneck and path conversion success rate of each alternative technology transfer path, and output as the transfer prediction result.

[0076] The optimization output module 15 is specifically configured to: Select the top N optimal candidate technology transfer paths from the transfer prediction results, and obtain dynamic information of the upstream and downstream of the industry chain in real time; Based on the upstream and downstream dynamic information of the industrial chain, predict the capacity bottlenecks and conversion success rates of the multiple transfer nodes corresponding to the N alternative technology transfer paths to obtain a first dynamic prediction result; Based on the upstream and downstream dynamic information of the industrial chain, predict the capacity bottleneck and conversion success rate of the approximate transfer nodes of the plurality of transfer nodes corresponding to the N alternative technology transfer paths to obtain a second dynamic prediction result; Marking an optimal transfer node by combining the first dynamic prediction result and the second dynamic prediction result, and matching and updating the N candidate technology transfer paths according to the optimal transfer node marking result; Iteratively predict the capacity bottlenecks and conversion success rates of the updated N alternative technology transfer paths, and select the optimal path based on the acquired path capacity bottlenecks and path conversion success rates, and output the target technology transfer path.

[0077] In summary, the embodiments of the present application have at least the following technical effects: Compared with the existing technology, this application first constructs the feature vectors of technology suppliers, demanders and intermediary nodes through the vector construction module, obtains the node feature vector set, and provides a unified data foundation for the subsequent path calculation based on directed acyclic graphs and the optimization of dynamic matching algorithms, ensuring the quantitative analysis and accurate decision-making of the entire process of technology transfer. Secondly, through the initial path acquisition module, based on the node feature vector set and combined with the directed acyclic graph method, the initial transfer path is obtained, the core flow nodes and hierarchical relationships from supply to demand are clarified, and the technology transfer path is transformed from qualitative judgment to quantitative calculation, providing a structured foundation for subsequent more refined management. Thirdly, through the graph construction module, real-time information collection is carried out according to the initial transfer path, and a multi-level graph containing multiple transfer nodes and collaborative relationships is constructed based on the real-time information collection results. The initial transfer path is refined into a structured network containing specific execution units and collaborative relationships, providing more realistic underlying data support for subsequent accurate prediction and optimization. Furthermore, through the transfer prediction module, combining historical transfer data with node attribute information, the multi-level graph is traversed to predict capability bottlenecks and conversion success rates, obtaining transfer prediction results. This provides accurate capability bottleneck and conversion success rate assessments for each alternative path, laying a data-driven decision-making foundation for subsequent optimization. Finally, through the optimization output module, based on the transfer prediction results and combined with dynamic information from upstream and downstream of the industry chain, a multi-objective dynamic matching algorithm is used to optimize the path, obtain the target technology transfer path, and execute technology transfer industry chain management based on the target technology transfer path. This allows the technology transfer path to adapt to changes in the industry chain while achieving a multi-objective balance between minimizing capability bottlenecks and maximizing conversion success rates. This avoids the failure of static paths due to environmental changes during execution, ultimately achieving a dual improvement in technology transfer efficiency and stability. In this way, the matching accuracy, process efficiency, and conversion success rate of technology transfer industry chain management are improved, accelerating the process of transforming technological achievements into industrial applications.

[0078] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0079] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0081] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0083] Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts become known.

[0084] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A technology transfer industry chain management method using a dynamic matching algorithm, characterized in that: include: Construct feature vectors of technology suppliers, demanders, and intermediary nodes, and obtain a set of node feature vectors; Based on the node feature vector set, an initial transfer path is obtained in combination with a directed acyclic graph method; Performing real-time information collection according to the initial transfer path, and constructing a multi-level graph including multiple transfer nodes and collaborative relationships based on the real-time information collection results; Combining historical transfer data with node attribute information, traversing the multi-level graph to predict capacity bottlenecks and conversion success rates, and obtaining transfer prediction results; Based on the transfer prediction results, combined with the dynamic information of upstream and downstream of the industrial chain, a multi-objective dynamic matching algorithm is used to optimize the path, obtain the target technology transfer path, and execute technology transfer industry chain management based on the target technology transfer path.

2. The technology transfer industry chain management method using a dynamic matching algorithm according to claim 1, characterized in that: The vector dimensions of the feature vector include technical attributes, subject attributes and service attributes; The technical attributes include at least the type of technology, technical maturity, technical indicators, technical innovations, and technical relevance; The subject attributes include at least the subject's size, subject's financial status, subject's credibility, and subject's cooperation history; The service attributes include at least service scope, service success rate, service efficiency, and service resources.

3. The technology transfer industry chain management method using a dynamic matching algorithm according to claim 1, characterized in that: Construct feature vectors of technology suppliers, demanders, and intermediary nodes, and obtain a set of node feature vectors, including: Based on the supply capability data of technology suppliers, the technical attributes, subject attributes and service attributes of technology supply nodes are analyzed and extracted to form the feature vector of technology supply nodes; Based on the demand data of the demand side, the technical attributes, subject attributes and service attributes of the demand nodes are analyzed and extracted to form the demand node feature vector; Clustering the intermediary nodes to obtain an intermediary node category set, and statistically analyzing the intermediary node category set based on big data to extract typical capability parameters of each intermediary node category and generate an intermediary node feature vector; The technology supply node feature vector, the demand node feature vector, and the intermediary node feature vector are aggregated to form the node feature vector set.

4. The technology transfer industry chain management method using a dynamic matching algorithm according to claim 3, characterized in that: Based on the node feature vector set, an initial transfer path is obtained in combination with a directed acyclic graph method, including: According to the node feature vector set, a directed acyclic graph is constructed with the technology supply node as a starting point, the plurality of intermediary nodes as intermediate nodes, and the demand node as an end point, wherein the edges of the directed acyclic graph are unidirectional edges and are directed from the technology supply node to the demand node; In the directed acyclic graph, based on the principle of minimum edge weight, a shortest path algorithm is used to calculate a path from the technology supply node to the demand node through at least one of the intermediary nodes to obtain an initial transfer path; The initial transfer path is used to define the hierarchical path of technology transfer.

5. The technology transfer industry chain management method using a dynamic matching algorithm according to claim 4, characterized in that: Real-time information collection is performed according to the initial transfer path, and a multi-level graph including multiple transfer nodes and collaborative relationships is constructed based on the real-time information collection results, including: Extracting a plurality of transfer nodes corresponding to each intermediate node based on the initial transfer path and generating a list; Information is called according to the list, and regularized and standardized to obtain entity feature information of the transfer node; According to the entity feature information, the initial transfer path is expanded accordingly to generate a multi-level graph. Each level of the multi-level graph corresponds to the technology supply node, the demand node and multiple intermediary nodes, and each intermediary node is under the jurisdiction of multiple transfer nodes. Each transfer node represents the transfer node capability and collaborative relationship in the form of a graph.

6. The technology transfer industry chain management method using a dynamic matching algorithm according to claim 5, characterized in that: Combining historical transfer data with node attribute information, traverse the multi-level graph to predict capacity bottlenecks and conversion success rates, and obtain transfer prediction results, including: Based on the multi-level graph, traverse multiple levels from top to bottom to perform random selection on multiple transfer nodes to obtain alternative technology transfer paths, and iteratively obtain a set of alternative technology transfer paths; Performing clustering according to the acquired node attribute information of the plurality of transfer nodes, and outputting clustering results as a plurality of node cluster lists; homomorphically partitioning the historical transfer data according to the node cluster list to form a plurality of node historical transfer data clusters; Using multiple node historical transfer data clusters as sample data, construct multiple transfer prediction models and perform supervised training; The entity feature information of multiple transfer nodes is respectively input into multiple transfer prediction models to predict capacity bottlenecks and conversion success rates, and the capacity bottleneck and conversion success rate prediction results are superimposed and fused according to the set of alternative technology transfer paths to obtain the path capacity bottleneck and path conversion success rate of each alternative technology transfer path, and output as the transfer prediction result.

7. The technology transfer industry chain management method using a dynamic matching algorithm according to claim 6, characterized in that: Based on the transfer prediction results, combined with the dynamic information of upstream and downstream of the industrial chain, a multi-objective dynamic matching algorithm is used to optimize the path and obtain the target technology transfer path, including: Select the top N optimal candidate technology transfer paths from the transfer prediction results, and obtain dynamic information of the upstream and downstream of the industry chain in real time; Based on the upstream and downstream dynamic information of the industrial chain, predict the capacity bottlenecks and conversion success rates of the multiple transfer nodes corresponding to the N alternative technology transfer paths to obtain a first dynamic prediction result; Based on the upstream and downstream dynamic information of the industrial chain, predict the capacity bottleneck and conversion success rate of the approximate transfer nodes of the plurality of transfer nodes corresponding to the N alternative technology transfer paths to obtain a second dynamic prediction result; Marking an optimal transfer node by combining the first dynamic prediction result and the second dynamic prediction result, and matching and updating the N candidate technology transfer paths according to the optimal transfer node marking result; Iteratively predict the capacity bottlenecks and conversion success rates of the updated N alternative technology transfer paths, and select the optimal path based on the acquired path capacity bottlenecks and path conversion success rates, and output the target technology transfer path.

8. A technology transfer industry chain management system using a dynamic matching algorithm, characterized in that: Used to perform the method according to any one of claims 1 to 7, comprising: Vector construction module, used to construct feature vectors of technology suppliers, demanders and intermediary nodes, and obtain node feature vector sets; An initial path acquisition module, configured to acquire an initial transfer path based on the node feature vector set and in combination with a directed acyclic graph method; A graph construction module is used to collect real-time information based on the initial transfer path and construct a multi-level graph including multiple transfer nodes and collaborative relationships based on the real-time information collection results; A transfer prediction module is used to combine historical transfer data with node attribute information, traverse the multi-level graph to predict capacity bottlenecks and conversion success rates, and obtain transfer prediction results; The optimization output module is used to optimize the path based on the transfer prediction results, combined with the dynamic information of the upstream and downstream of the industrial chain, using a multi-objective dynamic matching algorithm to obtain the target technology transfer path, and perform technology transfer industry chain management based on the target technology transfer path.

Images