Robot industry resource supply and demand docking method and system based on knowledge graph

Abstract

This invention relates to the field of resource management technology, and discloses a method and system for matching supply and demand of resources in the robotics industry based on knowledge graphs. The method includes: parsing resource data to obtain basic supply and demand data; semantically labeling the basic supply and demand data and mapping technical entities and indicator entities to a conceptual system to obtain a set of supply and demand capability features; using entities in the set of supply and demand capability features as resource nodes, writing nodes into a graph database to obtain resource entity nodes; performing link reasoning on the semantic relationships between resource entity nodes to obtain knowledge graph data; receiving matching requests, identifying the intent of the demand description, performing path retrieval in the knowledge graph data, and obtaining a preliminary matching result set; comprehensively sorting the supply entity nodes and encapsulating attribute information and associated paths into a protocol to obtain a matching scheme. This invention can improve the efficiency of supply and demand matching in the robotics industry.

Description

Technical Field

[0001] This invention relates to the field of resource management technology, and in particular to a method and system for matching the supply and demand of resources in the robotics industry based on knowledge graphs. Background Technology

[0002] Existing technologies for supply and demand matching in the robotics industry only perform basic information extraction on industry resource data, lacking specialized field parsing and structuring processing tailored to industry characteristics. This results in a lack of standardized formats and unified content specifications for the acquired supply and demand data, failing to form a systematic foundation of supply and demand data. Consequently, subsequent data applications suffer from information clutter and difficulties in extracting effective content, hindering accurate supply and demand matching operations. Furthermore, existing technologies for processing robotics industry supply and demand data lack an industry-specific ontological concept system and semantic annotation and entity mapping. They cannot uncover the underlying semantic relationships within the data, achieving only simple keyword-based supply and demand matching. They fail to identify the deep technical and indicator matching relationships between supply and demand parties, leading to low accuracy in resource matching during the process.

[0003] Current technologies lack a dedicated knowledge graph for the robotics industry, and are deficient in systematically constructing and semantically linking the entity nodes of industry resources. This prevents the formation of a complete supply and demand network for industry resources, making it difficult to perform global retrieval and matching of industry resources during the supply and demand matching process. This can easily lead to resource omissions and an inability to fully tap into effective supply and demand resources within the industry. Furthermore, in the result screening stage of supply and demand matching in the robotics industry, current technologies rely solely on single-dimensional matching information for result determination, failing to comprehensively evaluate the path association and density characteristics between resource nodes. This makes it difficult to scientifically prioritize supply entity nodes, and the selected matching results often fail to meet the actual needs of the target users, resulting in poor efficiency and implementation effectiveness in supply and demand matching. Summary of the Invention

[0004] This invention provides a knowledge graph-based method and system for matching supply and demand of robotics industry resources to solve the problems mentioned in the background.

[0005] To achieve the above objectives, the present invention provides a knowledge graph-based method for matching supply and demand of robotics industry resources, comprising: S1. Parse the resource data of the robotics industry to obtain the basic supply and demand data of the robotics industry; S2. Based on the preset robot industry ontology library, semantic role labeling is performed on the supply and demand basic data, and the labeled technical entities and indicator entities are mapped to the concept system of the robot industry ontology library to obtain the supply and demand capability feature set of the robot industry. S3. Using the entities in the supply and demand capacity feature set as resource nodes, write nodes into the graph database of the robot industry to obtain the resource entity nodes of the robot industry. S4. Based on the semantic association rules of the robot industry ontology library, perform link reasoning on the semantic relationships between the resource entity nodes to obtain the knowledge graph data of the robot industry; S5. Receive the docking request from the target user, perform intent recognition on the demand description of the docking request, perform path retrieval in the knowledge graph data, and obtain the preliminary matching result set of the robot industry; S6. Based on the path weights and association densities between nodes in the knowledge graph data, the supply entity nodes in the preliminary matching result set are comprehensively sorted, and the attribute information and association paths of the selected optimal supply entity nodes are encapsulated in a protocol to obtain the docking solution for the robotics industry.

[0006] In a preferred embodiment, the step of parsing the resource data of the robotics industry to obtain the basic supply and demand data of the robotics industry includes: The data source type of the resource data in the robotics industry is identified to obtain the source label of the robotics industry; Based on the source tags, the resource data is structurally split to obtain data fragments of the robotics industry; Based on the field mapping rules of the robotics industry, the data fragment is extracted to obtain the field key-value pairs of the robotics industry. The key-value pairs of the fields are normalized and encapsulated to obtain the basic supply and demand data of the robotics industry.

[0007] In a preferred embodiment, based on a pre-defined robot industry ontology library, semantic role labeling is performed on the supply and demand basic data, and the labeled technical entities and indicator entities are mapped to the conceptual system of the robot industry ontology library to obtain the supply and demand capability feature set of the robot industry, including: Based on the semantic role annotation dictionary in the preset robot industry ontology library, semantic roles are assigned to the text fields in the supply and demand basic data to obtain the supply and demand data entries of the robot industry. Based on the conceptual hierarchy of the robot industry ontology library, the role tags in the supply and demand data entries are verified for conceptual attribution to obtain the technical entities and indicator entities of the robot industry. Based on the concept mapping table of the robot industry ontology library, the technical entities and the indicator entities are associated with the ontology concept nodes of the robot industry ontology library to obtain the supply and demand capability feature entries of the robot industry. The ontological concept categories of the supply and demand capability feature items are classified and merged to obtain the supply and demand capability feature set of the robotics industry.

[0008] In a preferred embodiment, the step of using entities in the supply and demand capacity characteristic set as resource nodes and writing nodes into the graph database of the robotics industry to obtain resource entity nodes of the robotics industry includes: Traverse the supply and demand capability feature set, extract entity names and entity attribute lists from the entity entries of the supply and demand data entries in the robotics industry, and obtain the node data details table of the robotics industry; Based on the node data details table, blank nodes are created sequentially in the graphical database of the robotics industry, and node identifiers are assigned to the blank nodes to obtain the identified blank nodes of the robotics industry. The entity attribute list from the node data details table is filled into the attribute field of the blank node to obtain the filled node of the robot industry; Based on the ontology concept categories in the supply and demand capability feature set, the populated nodes are classified and attached to obtain the resource entity nodes of the robotics industry.

[0009] In a preferred embodiment, the step of performing link reasoning on the semantic relationships between the resource entity nodes based on the semantic association rules of the robot industry ontology to obtain the knowledge graph data of the robot industry includes: Extract the upstream and downstream transmission path map of the robot industry from the robot industry body library to obtain the topological skeleton of the robot industry links; The classification tags and attribute information of the resource entity nodes are used to determine the industry segment affiliation, thereby obtaining the segment anchoring entity of the robot industry; Based on the position coordinates of the anchored entity in the industrial chain topology, the upstream and downstream flow direction of the anchored entity is analyzed to obtain a list of candidate flow pairs for the robotics industry. The attribute information of upstream and downstream anchored entities in the candidate flow pair list is matched for supply and demand complementarity. When there is a matching relationship between the supply capacity field of the upstream anchored entity and the demand field of the downstream anchored entity, the supply and demand confirmation pair of the robot industry is obtained. In the graph database, a directed association edge is created for the supply and demand confirmation pair, and the direction of the directed association edge is set from the upstream anchor entity to the downstream anchor entity to obtain the industrial supply and demand chain edge of the robot industry; By performing topological fusion of the anchored entities in the aforementioned links with the edges of the industry supply and demand chain, the knowledge graph data of the robotics industry is obtained.

[0010] In a preferred embodiment, the step of performing supply and demand complementarity matching on the attribute information of upstream and downstream anchored entities in the candidate flow pair list, and obtaining the supply and demand confirmation pair for the robotics industry when the supply capacity field of the upstream anchored entity matches the demand field of the downstream anchored entity, includes: Extract the supply capacity field of the upstream anchor entity and the demand field of the downstream anchor entity from the candidate flow pair list; The supply capacity field and the demand field are decomposed into dimensions to obtain the upstream capacity index list and the downstream demand index list of the robot industry. Based on a preset industry technology indicator mapping table, the upstream capability indicator list and the downstream demand indicator list are matched and merged to obtain the indicator matching pair list of the robot industry. The numerical range of the matching pair list of the indicator items is verified. When the nominal range of the upstream capability indicator item can encompass or partially cover the threshold range of the downstream demand indicator item, the set of suitable indicator items for the robot industry is obtained. The matching indicator itemset is merged and statistically analyzed, and the coverage ratio of the matching indicator itemset is calculated based on the downstream demand indicator list to obtain the demand satisfaction coefficient of the robot industry. Based on a preset matching threshold, the demand satisfaction coefficient is checked against the threshold. When the demand satisfaction coefficient reaches or exceeds the matching threshold, a supply and demand confirmation pair for the robotics industry is obtained.

[0011] In a preferred embodiment, the formula for calculating the demand satisfaction coefficient is as follows: ; In the formula, The requirement satisfaction coefficient is the coefficient of the requirement. For the set of adaptation metrics, This is the list of downstream demand indicators. For the set of adaptation index items, the first The importance weight of each indicator item For the set of adaptation index items, the first The coverage depth coefficient of each indicator item, The first in the list of downstream demand indicators The importance weight of each indicator item For the set of adaptation index items, the first The nominal midpoint of the upstream capability indicator for each indicator item. For the set of adaptation index items, the first The median of the threshold range for each downstream demand indicator item. The preset quantity coverage factor, The preset weighted coverage factor, This is the preset range matching factor.

[0012] In a preferred embodiment, the process of receiving a connection request from a target user, performing intent recognition on the demand description of the connection request, and performing path retrieval in the knowledge graph data to obtain a preliminary matching result set for the robotics industry includes: Receive the docking request message from the target user, and extract the requirement description field from the docking request message to obtain the original requirement text of the robot industry; Semantic segmentation is performed on the original demand text to obtain the intent-oriented tags and technical constraints of the robotics industry; Based on the intent pointing tag, the retrieval starting point type is retrieved from the robot industry ontology library, and the matching resource entity node is located in the knowledge graph data according to the retrieval starting point type to obtain the starting retrieval node set of the robot industry. Based on the aforementioned technical constraints, starting from the initial retrieval node set, link tracing is performed along the associated edges in the knowledge graph data to obtain the candidate supply node list and associated path log of the robotics industry. Based on the associated path logs, redundancy is merged in the candidate supply node list to obtain a preliminary matching result set for the robotics industry.

[0013] In a preferred embodiment, the supply entity nodes in the preliminary matching result set are comprehensively sorted based on the path weights and association densities between nodes in the knowledge graph data. The attribute information and association paths of the selected optimal supply entity nodes are then encapsulated using a protocol to obtain the docking solution for the robotics industry, including: Based on the knowledge graph data, a topological traversal is performed on the connection paths between the supply entity nodes and the demand entity nodes of the target user in the preliminary matching result set to obtain the path topology set of the robotics industry. The path depth of the connected paths in the path topology set is analyzed, and the density of the associated edges of the supply entity node and the domain of the demand entity node in the knowledge graph data is aggregated and statistically analyzed to obtain the path depth list and the association density list of the robot industry. Based on the path depth list and the association density list, the supply entity node is evaluated using the minimum path depth value of the supply entity node as the path distance factor and the total number of associated edges aggregated by the supply entity node as the association strength factor, and a multi-factor weighted evaluation is performed to obtain the comprehensive matching index of the robot industry. Based on the comprehensive matching index, the preliminary matching result set is prioritized to obtain the supply node sequence of the robotics industry; Extracting the first and second elements of the supply node sequence yields the target preferred node for the robotics industry. Extract the complete attribute fields of the target preferred node and the shortest path trajectory between the target preferred node and the demand entity node from the knowledge graph data to obtain the preferred node attribute package and associated path trajectory of the robotics industry; The preferred node attribute package and the associated path trajectory are serialized and encapsulated to obtain the docking solution for the robotics industry.

[0014] To address the aforementioned problems, this invention also provides a knowledge graph-based robot industry resource supply and demand matching system, the system comprising: The data field parsing module is used to parse the resource data of the robotics industry to obtain the basic supply and demand data of the robotics industry. The semantic entity annotation module is used to perform semantic role annotation on the supply and demand basic data based on a preset robot industry ontology library, and to map the annotated technical entities and indicator entities to the conceptual system of the robot industry ontology library to obtain the supply and demand capability feature set of the robot industry. The resource node writing module is used to write nodes into the graph database of the robot industry, using entities in the supply and demand capacity feature set as resource nodes, to obtain resource entity nodes of the robot industry. The semantic relationship reasoning module is used to perform link reasoning on the semantic relationship between the resource entity nodes based on the semantic association rules of the robot industry ontology library, so as to obtain the knowledge graph data of the robot industry. The demand intent matching module is used to receive the docking request from the target user, identify the intent of the demand description of the docking request, perform path retrieval in the knowledge graph data, and obtain a preliminary matching result set of the robotics industry. The optimal solution encapsulation module is used to comprehensively sort the supply entity nodes in the preliminary matching result set based on the path weights and association densities between nodes in the knowledge graph data, and encapsulate the attribute information and association paths of the selected optimal supply entity nodes into a protocol to obtain the docking solution for the robotics industry.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention relies on a robotics industry ontology library to complete semantic role labeling and entity mapping of basic supply and demand data. It accurately mines technical and indicator entities within the data and incorporates them into an industry-specific conceptual system, forming a standardized set of supply and demand capability features. This imbues the processing of industry resource data with professional industry attributes and semantic depth, enabling refined and systematic organization of robotics industry resource information. It fully explores the industry-related value behind the data, laying a standardized and high-quality data foundation for supply and demand matching. This technology constructs a knowledge graph data specific to the robotics industry. Through semantic association rules, it completes relationship reasoning and link construction of resource entity nodes. Combined with demand intent recognition, it conducts path retrieval within the knowledge graph. Simultaneously, based on the path weight and association density between nodes, it completes a comprehensive ranking of supply entities, achieving global retrieval and scientific filtering for supply and demand matching. This accurately locates suitable supply resources, significantly improving the accuracy and targeting of supply and demand matching in the robotics industry.

[0016] 2. This invention implements a standardized field parsing process for robotics industry resource data. Through data source calibration, structured decomposition, field extraction, and normalized encapsulation, it forms standardized and consistent supply and demand data, eliminating the clutter of resource data and enabling efficient extraction of effective information in subsequent supply and demand matching data application stages. This improves the processing efficiency and application value of industry resource data. This technology professionally encapsulates the attribute information and association paths of the optimal supply entity nodes using protocols, forming a standardized robotics industry matching solution. It clearly presents the core resource information and association links for supply and demand matching, allowing target users to quickly obtain accurate and complete matching content. This improves the efficiency of implementing robotics industry resource supply and demand matching results, achieving efficient matching and implementation of industry resource supply and demand. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a knowledge graph-based method for matching supply and demand of robotic industry resources, provided in an embodiment of the present invention. Figure 2 A functional module diagram of a knowledge graph-based robot industry resource supply and demand matching system provided in an embodiment of the present invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a knowledge graph-based method for matching the supply and demand of robotics industry resources. The execution entity of this knowledge graph-based method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the knowledge graph-based method for matching the supply and demand of robotics industry resources can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a knowledge graph-based method for matching the supply and demand of robotics industry resources according to an embodiment of the present invention. In this embodiment, the knowledge graph-based method for matching the supply and demand of robotics industry resources includes: S1. Parse the resource data of the robotics industry to obtain the basic supply and demand data of the robotics industry; In this embodiment of the invention, the step of parsing the resource data of the robotics industry to obtain the basic supply and demand data of the robotics industry includes: The data source type of the resource data in the robotics industry is identified to obtain the source label of the robotics industry; Based on the source tags, the resource data is structurally split to obtain data fragments of the robotics industry; Based on the field mapping rules of the robotics industry, the data fragment is extracted to obtain the field key-value pairs of the robotics industry. The key-value pairs of the fields are normalized and encapsulated to obtain the basic supply and demand data of the robotics industry.

[0021] For each piece of resource data in the robotics industry, the data collection channel and data type are identified. According to the preset classification standard for data sources in the robotics industry, each piece of resource data is assigned a unique type identifier. This identifier contains two core contents: the collection channel code and the data type code. This completes the data source type labeling operation for all robotics industry resource data, resulting in the source label of the robotics industry.

[0022] Based on the collection channel code and data type code carried in the source tag, the robot industry resource data splitting rules that match the code are retrieved. The robot industry resource data is split into segments according to the field separator and data segment length specified in the splitting rules. Each segment of data after splitting retains the source tag information corresponding to the original resource data, thus obtaining the data fragment of the robot industry.

[0023] The system retrieves a preset field mapping rule for the robotics industry. This rule includes the core field names, field extraction locations, and field content matching features required for supply and demand matching in the robotics industry. The system locates the corresponding content in the data segment according to the extraction location specified in the rule. Then, it accurately identifies and extracts the located content through the field content matching features. The extracted content is then associated one-to-one with the core field names to obtain the field key-value pairs for the robotics industry.

[0024] The system retrieves a pre-defined normalization standard for key-value pairs in the robotics industry. This standard specifies a unified format for field names, data formats for field values, and a combination structure for key-value pairs. The system then uniformly corrects the field names of all key-value pairs according to this standard, standardizes the format of the field values, and integrates and encapsulates the corrected key-value pairs according to a fixed combination structure. The encapsulated data has a unified storage and retrieval format, thus obtaining the basic supply and demand data for the robotics industry.

[0025] The beneficial effects are that the field parsing operations, including data source type identification, structured decomposition, content extraction, and normalized encapsulation, performed on robotics industry resource data can transform disorganized industry resource data into a standardized data format with clear source identification and a well-organized structure. This effectively extracts the core field information supporting the supply and demand matching of the robotics industry from the resource data. At the same time, through normalized encapsulation, the industry resource data achieves uniformity in format, expression, and structure. The resulting supply and demand basic data has the characteristics of being standardized, complete, and directly callable. This lays a standardized and high-quality data foundation for subsequent semantic analysis, entity mapping, and other operations related to the supply and demand of the robotics industry, improves the overall processing efficiency and application value of robotics industry resource data, and ensures the smooth and accurate implementation of subsequent data processing links related to the supply and demand matching of industry resources.

[0026] S2. Based on the preset robot industry ontology library, semantic role labeling is performed on the supply and demand basic data, and the labeled technical entities and indicator entities are mapped to the concept system of the robot industry ontology library to obtain the supply and demand capability feature set of the robot industry. In this embodiment of the invention, based on a preset robot industry ontology library, semantic role labeling is performed on the supply and demand basic data, and the labeled technical entities and indicator entities are mapped to the conceptual system of the robot industry ontology library to obtain the supply and demand capability feature set of the robot industry, including: Based on the semantic role annotation dictionary in the preset robot industry ontology library, semantic roles are assigned to the text fields in the supply and demand basic data to obtain the supply and demand data entries of the robot industry. Based on the conceptual hierarchy of the robot industry ontology library, the role tags in the supply and demand data entries are verified for conceptual attribution to obtain the technical entities and indicator entities of the robot industry. Based on the concept mapping table of the robot industry ontology library, the technical entities and the indicator entities are associated with the ontology concept nodes of the robot industry ontology library to obtain the supply and demand capability feature entries of the robot industry. The ontological concept categories of the supply and demand capability feature items are classified and merged to obtain the supply and demand capability feature set of the robotics industry.

[0027] The semantic role labeling dictionary built into the preset robot industry ontology library is retrieved. This dictionary contains all preset semantic role labels in the robot industry field and the text feature matching rules corresponding to each label. Text features are extracted from all text fields in the supply and demand basic data one by one. The extracted text features are accurately compared with the feature matching rules in the semantic role labeling dictionary. A unique and matching semantic role label is assigned to each text field. The semantic role assignment operation of the text fields in the supply and demand basic data is completed, and the supply and demand data entries of the robot industry are obtained.

[0028] The system retrieves a pre-defined concept hierarchy from the robot industry ontology library. This structure includes the hierarchical classification standards for all ontology concepts in the robot industry, the feature definition rules for each level of concepts, and the correspondence between role tags and ontology concepts. The semantic role tags in the supply and demand data entries are analyzed one by one. The analyzed role tag features are compared and verified with the feature definition rules in the concept hierarchy. Based on the comparison and verification results, the ontology concept type corresponding to each role tag is determined. Role tags belonging to technical concepts and indicator concepts are selected and converted into corresponding entity forms to obtain the technical entities and indicator entities of the robot industry.

[0029] The system retrieves a pre-defined concept mapping table from the robot industry ontology library. This table contains unique associations between all technical entities and indicator entities in the robot industry and ontology concept nodes in the ontology library. The identified technical entities and indicator entities are matched one by one with the entity information in the concept mapping table. Based on the matching results, each technical entity and indicator entity is associated with the corresponding ontology concept node in the robot industry ontology library, so that each entity forms a unique association mapping with the ontology concept node, thereby obtaining the supply and demand capacity characteristic entries of the robot industry.

[0030] A pre-defined ontology concept category classification standard for the robot industry ontology library is established. This standard divides ontology concept nodes into specific categories such as technology and indicators, and each category has a clear defining identifier. The ontology concept nodes of all supply and demand capability feature items are classified one by one. Based on the identified defining identifiers, supply and demand capability feature items belonging to the same category are centrally integrated. During the integration process, the complete entity information of each feature item and its association with the ontology concept node are preserved. The classification and merging operation of all supply and demand capability feature items is completed, resulting in the supply and demand capability feature set of the robot industry.

[0031] The beneficial effects are as follows: the semantic role labeling and entity mapping operations carried out based on the pre-set robot industry ontology library can accurately mine semantic information in the supply and demand basic data and complete professional role assignment and concept attribution verification. It effectively extracts the technical entities and indicator entities that support the supply and demand docking of the robot industry from the data. Then, through the concept mapping table, the entities are deeply associated with the concept system of the ontology library. Combined with the ontology concept categories, the entities are classified and merged to form a supply and demand capability feature set. This gives the industry supply and demand data standardized semantic attributes and clear concept attribution, fully explores the value of the industry technology and indicator association behind the data, and the resulting supply and demand capability feature set can accurately reflect the supply and demand capability attributes of industry resources. It provides a standardized and systematic entity basis for subsequent resource node construction and semantic relationship reasoning, and gives the subsequent knowledge graph construction stage an accurate entity foundation that fits the characteristics of the industry. This improves the professionalism and accuracy of the overall robot industry resource supply and demand docking data processing.

[0032] S3. Using the entities in the supply and demand capacity feature set as resource nodes, write nodes into the graph database of the robot industry to obtain the resource entity nodes of the robot industry. In this embodiment of the invention, the step of using entities in the supply and demand capacity feature set as resource nodes and writing nodes into the graph database of the robotics industry to obtain resource entity nodes of the robotics industry includes: Traverse the supply and demand capability feature set, extract entity names and entity attribute lists from the entity entries of the supply and demand data entries in the robotics industry, and obtain the node data details table of the robotics industry; Based on the node data details table, blank nodes are created sequentially in the graphical database of the robotics industry, and node identifiers are assigned to the blank nodes to obtain the identified blank nodes of the robotics industry. The entity attribute list from the node data details table is filled into the attribute field of the blank node to obtain the filled node of the robot industry; Based on the ontology concept categories in the supply and demand capability feature set, the populated nodes are classified and attached to obtain the resource entity nodes of the robotics industry.

[0033] Read all data content in the supply and demand capacity feature set line by line according to the preset traversal rules, locate the entity entries of the supply and demand data entries, extract the complete entity name information and the entity attribute list containing all technical attributes and indicator attributes of the entity from each entity entry according to the entity name extraction rules and entity attribute list extraction rules, and organize and integrate all extracted entity names and corresponding entity attribute lists in a unified format to form a detailed table containing all entity-related information, thus obtaining the node data detail table of the robot industry.

[0034] The node creation specifications of the robot industry graph database are retrieved. According to the number of entities in the node data details table, blank nodes with the same number of entities are created sequentially in the preset storage area of ​​the graph database. According to the identifier allocation rules of the graph database, a unique and non-repeating node identifier is assigned to each blank node. The identifier includes the entity category code and the node sequence code. The binding operation between the identifier and the blank node is completed to obtain the identified blank nodes of the robot industry.

[0035] According to the correspondence between entity names and blank nodes in the node data details table, attribute fields are filled for each blank node. The list of entity attributes corresponding to each entity in the node data details table is completely entered into the preset attribute fields of the corresponding blank node. During the filling process, it is ensured that the content of the attribute list matches the category of the attribute field one by one, without omissions or errors. After the attribute filling of all blank nodes is completed, the filled nodes of the robot industry are obtained.

[0036] The system retrieves the pre-defined ontology concept category classification criteria from the supply and demand capacity feature set. This criteria includes the names of all ontology concept categories and their corresponding category feature identifiers. The system identifies the category feature identifiers of the entity attribute list associated with each filled node one by one. Based on the identification results, the system determines the ontology concept category to which each filled node belongs. According to the node mounting rules of the graph database, the filled nodes belonging to the same ontology concept category are mounted to the corresponding category directory in the graph database. This completes the category classification and mounting operations of all filled nodes, resulting in the resource entity nodes of the robot industry.

[0037] The beneficial effects are as follows: the graph database node writing operation based on entities with concentrated supply and demand capacity characteristics can accurately extract the core information of entities from supply and demand data entries and organize it into a standardized node data detail table. Based on the detail table, the graph database completes the standardized creation, identification assignment, and attribute filling of nodes. Then, combined with ontology concept categories, the nodes are accurately mounted and classified. This allows the resource entities of the robotics industry to be systematically stored in the graph database in the form of standardized nodes. Each resource entity node has a unique identifier, complete attributes, and a clear concept category. The formed resource entity nodes can clearly and standardizedly map various resource entities in the robotics industry, providing a structured and standardized node foundation for subsequent semantic relationship linking and reasoning between resource entity nodes. This ensures that the subsequent knowledge graph construction stage can carry out efficient and accurate association analysis based on standardized node information, improving the structured storage level of robotics industry resource data and the efficiency of subsequent data processing.

[0038] S4. Based on the semantic association rules of the robot industry ontology library, perform link reasoning on the semantic relationships between the resource entity nodes to obtain the knowledge graph data of the robot industry; In this embodiment of the invention, the step of performing link reasoning on the semantic relationships between the resource entity nodes based on the semantic association rules of the robot industry ontology to obtain the knowledge graph data of the robot industry includes: Extract the upstream and downstream transmission path map of the robot industry from the robot industry body library to obtain the topological skeleton of the robot industry links; The classification tags and attribute information of the resource entity nodes are used to determine the industry segment affiliation, thereby obtaining the segment anchoring entity of the robot industry; Based on the position coordinates of the anchored entity in the industrial chain topology, the upstream and downstream flow direction of the anchored entity is analyzed to obtain a list of candidate flow pairs for the robotics industry. The attribute information of upstream and downstream anchored entities in the candidate flow pair list is matched for supply and demand complementarity. When there is a matching relationship between the supply capacity field of the upstream anchored entity and the demand field of the downstream anchored entity, the supply and demand confirmation pair of the robot industry is obtained. In the graph database, a directed association edge is created for the supply and demand confirmation pair, and the direction of the directed association edge is set from the upstream anchor entity to the downstream anchor entity to obtain the industrial supply and demand chain edge of the robot industry; By performing topological fusion of the anchored entities in the aforementioned links with the edges of the industry supply and demand chain, the knowledge graph data of the robotics industry is obtained.

[0039] The process of performing supply and demand complementarity matching on the attribute information of upstream and downstream anchored entities in the candidate flow pair list, and obtaining the confirmed supply and demand pair for the robotics industry when the supply capacity field of the upstream anchored entity matches the demand field of the downstream anchored entity, includes: Extract the supply capacity field of the upstream anchor entity and the demand field of the downstream anchor entity from the candidate flow pair list; The supply capacity field and the demand field are decomposed into dimensions to obtain the upstream capacity index list and the downstream demand index list of the robot industry. Based on a preset industry technology indicator mapping table, the upstream capability indicator list and the downstream demand indicator list are matched and merged to obtain the indicator matching pair list of the robot industry. The numerical range of the matching pair list of the indicator items is verified. When the nominal range of the upstream capability indicator item can encompass or partially cover the threshold range of the downstream demand indicator item, the set of suitable indicator items for the robot industry is obtained. The matching indicator itemset is merged and statistically analyzed, and the coverage ratio of the matching indicator itemset is calculated based on the downstream demand indicator list to obtain the demand satisfaction coefficient of the robot industry. Based on a preset matching threshold, the demand satisfaction coefficient is checked against the threshold. When the demand satisfaction coefficient reaches or exceeds the matching threshold, a supply and demand confirmation pair for the robotics industry is obtained.

[0040] The formula for calculating the demand satisfaction coefficient is as follows: ; In the formula, The requirement satisfaction coefficient is the coefficient of the requirement. For the set of adaptation metrics, This is the list of downstream demand indicators. For the set of adaptation index items, the first The importance weight of each indicator item For the set of adaptation index items, the first The coverage depth coefficient of each indicator item, The first in the list of downstream demand indicators The importance weight of each indicator item For the set of adaptation index items, the first The nominal midpoint of the upstream capability indicator for each indicator item. For the set of adaptation index items, the first The median of the threshold range for each downstream demand indicator item. The preset quantity coverage factor, The preset weighted coverage factor, This is the preset range matching factor.

[0041] The system retrieves a pre-defined robot industry ontology library and extracts an upstream and downstream transmission path map containing the hierarchical relationships and inter-link transmission logic of each link in the robot industry according to the extraction rules of the industry map in the ontology library. This map presents the position and correlation of each link in the industry in a topological structure and directly serves as the topological skeleton of the robot industry links.

[0042] The system retrieves the pre-defined industry segment attribution rules from the robot industry ontology library. These rules include the feature definition information of each industry segment, the correspondence between classification tags and industry segments, and the matching standards between entity attribute information and industry segments. The system performs feature parsing on the classification tags of each resource entity node and extracts the attribute information of the resource entity nodes. The parsing results and the extracted content are then compared with the attribution rules to complete the matching and determine the industry segment corresponding to each resource entity node. The resource entity node after the attribution determination is the segment anchoring entity of the robot industry.

[0043] Each industrial link in the industrial link topology is assigned a unique location coordinate, which includes link level code and link sequence code. The upstream and downstream relationships of each coordinate in the topology are clarified. The anchored entity of the link is bound to the location coordinate of the corresponding industrial link. Based on the upstream and downstream relationships of the coordinate, the potential upstream and downstream anchored entities of each anchored entity are sorted out. Each pair of potential upstream and downstream entities is paired and integrated to form a list of candidate pairs for the flow of the robotics industry.

[0044] The system retrieves pre-defined matching rules for the complementary supply and demand of the robotics industry. These rules specify the matching dimensions and criteria for the supply capacity and demand fields. Fields are extracted from each upstream and downstream anchored entity in the candidate flow pair list, obtaining the supply capacity field of the upstream anchored entity and the demand field of the downstream anchored entity. The two fields are then compared one by one according to the matching rules in terms of dimensions and content. When the comparison results meet the matching criteria, it is determined that the supply capacity and demand fields of the upstream and downstream anchored entities in this group have a matching relationship, and this group of entities is considered a confirmed supply and demand pair in the robotics industry.

[0045] The system retrieves the edge creation specifications from the robot industry graph database. Based on these specifications, directed edges are created for each supply and demand pair in the graph database. During creation, the starting end of the directed edge is bound to the upstream anchor entity, and the ending end is bound to the downstream anchor entity. The direction of the directed edge is fixed so that it points from the upstream anchor entity to the corresponding downstream anchor entity. The directed edges after all creation and direction settings are completed are the supply and demand chain edges of the robot industry.

[0046] The system retrieves preset topology fusion rules, which specify the fusion method between anchored entities and industry supply and demand chain edges, as well as the presentation standard of the fused topology structure. All anchored entities are spatially arranged in the graph database according to their position coordinates. Then, the industry supply and demand chain edges are precisely bound to the corresponding upstream and downstream anchored entities, allowing the anchored entities to form a complete topological association through the industry supply and demand chain edges. The overall topology structure after the arrangement and binding is the knowledge graph data of the robotics industry.

[0047] For each pair of upstream and downstream anchored entities in the candidate flow pair list, perform field extraction operations one by one. According to the preset field extraction rules, locate the exclusive field area representing supply capacity in the upstream anchored entity and the exclusive field area representing demand in the downstream anchored entity. Extract the complete field content in the two areas and bind it with the corresponding anchored entity to obtain the supply capacity field of the upstream anchored entity and the demand field of the downstream anchored entity in the robot industry.

[0048] The preset robot industry indicator dimension decomposition rules are retrieved. These rules clarify the decomposition dimensions of the supply capacity field and the demand field, as well as the indicator extraction standards corresponding to each dimension. The extracted supply capacity field and demand field are decomposed into dimensions respectively. All capability indicators are extracted from the supply capacity field according to the decomposition dimensions and organized into a list. All demand indicators are extracted from the demand field and organized into a list, thus obtaining the upstream capability indicator list and the downstream demand indicator list of the robot industry.

[0049] A preset industry technology indicator mapping table is retrieved. This table contains a one-to-one correspondence between all upstream capability indicators and downstream demand indicators in the robotics industry. Each indicator item in the upstream capability indicator list is matched with the upstream indicator in the industry technology indicator mapping table. Then, the corresponding downstream demand indicator item is found according to the mapping table. The successfully matched upstream and downstream indicator items are integrated into pairs to form a standardized indicator item pairing list, thus obtaining the indicator item matching pair list of the robotics industry.

[0050] Each indicator in the list is matched one by one, and the numerical range of each indicator is verified. First, the nominal range numerical range of the upstream capability indicator is extracted and the threshold range numerical range of the downstream demand indicator is extracted. The two numerical ranges are compared. When the minimum nominal range of the upstream capability indicator is less than or equal to the minimum threshold range of the downstream demand indicator and the maximum nominal range of the upstream capability indicator is greater than or equal to the minimum threshold range of the downstream demand indicator, or when the nominal range of the upstream capability indicator completely includes the threshold range of the downstream demand indicator, the indicator is determined to be a suitable indicator. All suitable indicators are integrated to obtain the set of suitable indicators for the robotics industry.

[0051] The number of all indicators in the adaptation indicator set is counted and merged. At the same time, the total number of indicators in the downstream demand indicator list is counted. The number of indicators in the adaptation indicator set is used as the numerator, and the total number of indicators in the downstream demand indicator list is used as the denominator. The coverage ratio of the adaptation indicator set relative to the downstream demand indicator list is obtained by numerical proportion calculation. Combined with the coverage ratio and the preset indicator adaptation evaluation criteria, a comprehensive judgment is made to obtain the demand satisfaction coefficient of the robot industry.

[0052] The preset supply and demand matching threshold for the robotics industry is retrieved. This threshold is a pre-set value for judging the qualification of the demand satisfaction coefficient. The calculated demand satisfaction coefficient is directly compared with the matching threshold for verification. When the value of the demand satisfaction coefficient is equal to or higher than the value of the matching threshold, it is determined that the supply capacity field and demand field of the corresponding upstream and downstream anchored entities have a matching relationship. The upstream and downstream anchored entities are integrated to obtain the supply and demand confirmation pair for the robotics industry.

[0053] Both the matching indicator set and the downstream demand indicator list are extracted and determined from the upstream capability indicator list and the downstream demand indicator list generated during the supply and demand complementarity matching process. The importance weight and coverage depth coefficient of each indicator in the matching indicator set are derived from the pre-set industry technology indicator weight and coefficient configuration table in the robot industry ontology library. Similarly, the importance weight of each indicator in the downstream demand indicator list is extracted from the same configuration table in the robot industry ontology library. The nominal range median of the upstream capability indicator for each indicator in the matching indicator set is calculated from the nominal range value range marked by the corresponding upstream capability indicator, i.e., the midpoint between the maximum and minimum values ​​of the value range. The threshold range median of the downstream demand indicator for each indicator in the matching indicator set is calculated from the threshold range value range marked by the corresponding downstream demand indicator, i.e., the midpoint between the maximum and minimum values ​​of the value range. The quantity coverage factor, weighted coverage factor, and range matching factor are all fixed coefficient values ​​pre-set in the robot industry ontology library for the supply and demand matching process.

[0054] This calculation is used to quantify the degree to which the supply capacity of upstream anchor entities meets the demand of downstream anchor entities. By combining the quantity coverage of matching indicators relative to downstream demand indicators, the weighted coverage with indicator importance, and the range matching of upstream and downstream indicators, three dimensions are assigned fixed coefficient weights for comprehensive calculation to obtain a demand satisfaction coefficient that can accurately reflect the degree of matching between supply and demand. This coefficient serves as the core basis for determining whether upstream and downstream anchor entities can become a supply and demand confirmation pair. By comparing it with the preset matching admission threshold, it can be determined whether there is a matching relationship between the supply capacity field and the demand field of upstream and downstream anchor entities.

[0055] The beneficial effects are as follows: Based on the robot industry ontology database, semantic relationship linking and reasoning of resource entity nodes are conducted. First, the upstream and downstream transmission path map of the industry is extracted to build the topological skeleton of the industry links. Then, the industry link anchoring and upstream and downstream flow analysis of resource entity nodes are completed. Combined with multi-dimensional supply and demand complementarity matching, the supply and demand confirmation pairs are screened. Next, targeted industry supply and demand chain edges are created for the supply and demand confirmation pairs, and the topological fusion of link anchored entities and chain edges is achieved, constructing a robot industry knowledge graph data. The entire process relies on industry-specific semantic association rules to advance layer by layer, allowing the knowledge graph data to accurately map to the industry. The knowledge graph establishes a solid foundation for industry-specific supply and demand relationships across all stages. Through meticulous multi-step processes including field extraction, dimensional decomposition, indicator alignment, and numerical verification, combined with demand satisfaction coefficients and matching thresholds, it accurately determines supply and demand matching. This provides a robust industry-adaptive foundation for the supply and demand relationships within the knowledge graph. The resulting knowledge graph data possesses both a complete industry topology and precise supply and demand relationship logic, offering clear and relevant knowledge support for subsequent supply and demand matching path retrieval, significantly improving the accuracy and professionalism of industry resource supply and demand matching.

[0056] S5. Receive the docking request from the target user, perform intent recognition on the demand description of the docking request, perform path retrieval in the knowledge graph data, and obtain the preliminary matching result set of the robot industry; In this embodiment of the invention, the steps of receiving a connection request from a target user, performing intent recognition on the demand description of the connection request, and performing path retrieval in the knowledge graph data to obtain a preliminary matching result set for the robotics industry include: Receive the docking request message from the target user, and extract the requirement description field from the docking request message to obtain the original requirement text of the robot industry; Semantic segmentation is performed on the original demand text to obtain the intent-oriented tags and technical constraints of the robotics industry; Based on the intent pointing tag, the retrieval starting point type is retrieved from the robot industry ontology library, and the matching resource entity node is located in the knowledge graph data according to the retrieval starting point type to obtain the starting retrieval node set of the robot industry. Based on the aforementioned technical constraints, starting from the initial retrieval node set, link tracing is performed along the associated edges in the knowledge graph data to obtain the candidate supply node list and associated path log of the robotics industry. Based on the associated path logs, redundancy is merged in the candidate supply node list to obtain a preliminary matching result set for the robotics industry.

[0057] The system receives a robot industry resource supply and demand matching request message sent by the target user. According to the preset message field extraction rules, it locates the exclusive demand description field in the message that represents the supply and demand needs. The system extracts the complete text content in the field and retains the original expression information to obtain the original demand text of the robot industry.

[0058] The system retrieves preset semantic segmentation rules for the robotics industry. These rules define the segmentation dimensions of the demand text, the standards for extracting intent tags, and the specifications for defining technical constraints. The system performs segmented semantic analysis and content segmentation on the original demand text, extracts the text content that represents the core direction of the user's connection needs, and transforms it into standardized tags. At the same time, it extracts the text content that represents the user's connection technical requirements and organizes it into standardized constraint clauses, thus obtaining the intent-oriented tags and technical constraints of the robotics industry.

[0059] The extracted intent pointing tags are precisely compared with a pre-defined search starting point type matching table in the robot industry ontology library. This matching table contains unique associations between all standardized intent pointing tags and their corresponding search starting point types. Based on the comparison results, the matching search starting point types are retrieved from the ontology library. Then, a full-domain resource entity node search is performed in the robot industry knowledge graph data according to the type. All resource entity nodes that match the type are located and integrated to obtain the starting search node set of the robot industry.

[0060] The technical constraints are transformed into standardized link tracing screening conditions. Taking each node in the initial retrieval node set as the retrieval starting point, the link tracing is performed node by node along the preset association edge traversal direction in the knowledge graph data. During the tracing process, the screening conditions of each resource entity node are matched and verified. The supply-type resource entity nodes that pass the matching and verification are compiled into a list. At the same time, the complete link path and node association information of each supply entity node from the initial retrieval node are recorded and logs are formed to obtain the candidate supply node list and association path log of the robotics industry.

[0061] The preset rules for determining redundancy in the associated path logs are retrieved. These rules clarify the criteria for determining duplicate supply entity nodes and the merging specifications for path information. The path information in the associated path logs is parsed line by line to identify duplicate supply entity nodes in the candidate supply node list. Redundant information of duplicate nodes is removed, and their optimal associated path information is retained. The list of supply entity nodes after redundancy removal and information merging is standardized and organized to obtain the preliminary matching result set for the robotics industry.

[0062] The beneficial effects are as follows: In the process of receiving and processing user requests, the original request text is obtained by accurately extracting the request description field. Then, through semantic segmentation, standardized intent tags and technical constraints are formed, transforming the user's unstructured requests into structured information that can be directly used for retrieval. Relying on the robot industry ontology library, the system accurately retrieves the type of retrieval starting point and locates the starting retrieval node set, giving the knowledge graph retrieval a precise starting point that matches the user's needs. Based on the technical constraints, link tracing is then carried out along the knowledge graph's related edges, simultaneously forming a candidate supply node list and related path logs, ensuring the traceability of the retrieval process. Finally, the related path logs are used to merge redundancies in the candidate supply node list, eliminating duplicate node information. The resulting preliminary matching result set retains supply node resources that match the user's needs while ensuring the uniqueness and cleanliness of the data. The entire process realizes the transformation of user needs from unstructured to structured, giving path retrieval in the knowledge graph a clear direction and constraints, significantly improving the targeting and efficiency of the retrieval, and laying a precise and high-quality data source foundation for the subsequent comprehensive ranking of supply entity nodes.

[0063] S6. Based on the path weights and association densities between nodes in the knowledge graph data, the supply entity nodes in the preliminary matching result set are comprehensively sorted, and the attribute information and association paths of the selected optimal supply entity nodes are encapsulated in a protocol to obtain the docking solution for the robotics industry.

[0064] In this embodiment of the invention, the supply entity nodes in the preliminary matching result set are comprehensively sorted based on the path weights and association densities between nodes in the knowledge graph data, and the attribute information and association paths of the selected optimal supply entity nodes are encapsulated in a protocol to obtain the docking solution for the robotics industry, including: Based on the knowledge graph data, a topological traversal is performed on the connection paths between the supply entity nodes and the demand entity nodes of the target user in the preliminary matching result set to obtain the path topology set of the robotics industry. The path depth of the connected paths in the path topology set is analyzed, and the density of the associated edges of the supply entity node and the domain of the demand entity node in the knowledge graph data is aggregated and statistically analyzed to obtain the path depth list and the association density list of the robot industry. Based on the path depth list and the association density list, the supply entity node is evaluated using the minimum path depth value of the supply entity node as the path distance factor and the total number of associated edges aggregated by the supply entity node as the association strength factor, and a multi-factor weighted evaluation is performed to obtain the comprehensive matching index of the robot industry. Based on the comprehensive matching index, the preliminary matching result set is prioritized to obtain the supply node sequence of the robotics industry; Extracting the first and second elements of the supply node sequence yields the target preferred node for the robotics industry. Extract the complete attribute fields of the target preferred node and the shortest path trajectory between the target preferred node and the demand entity node from the knowledge graph data to obtain the preferred node attribute package and associated path trajectory of the robotics industry; The preferred node attribute package and the associated path trajectory are serialized and encapsulated to obtain the docking solution for the robotics industry.

[0065] The knowledge graph data of the robotics industry is retrieved, and the demand entity nodes of the target user are used as the core of the search. A full topological traversal is performed on all connected paths between each supply entity node and the demand entity node in the preliminary matching result set. During the traversal, the node composition and associated edge direction of each connected path are fully recorded. All recorded connected paths are classified and integrated according to the supply entity nodes to obtain the path topology set of the robotics industry.

[0066] According to the preset path depth parsing rules, the node level of each connected path in the path topology set is counted, and the minimum number of node jumps from the demand entity node to the corresponding supply entity node is counted as the path depth value. The path depth values ​​of all supply entity nodes are organized into an ordered list. At the same time, the number of all associated edges of each supply entity node in the knowledge graph data that are related to the domain of the demand entity node are counted and aggregated. The counted number of associated edges is organized into an ordered list according to the supply entity node, thus obtaining the path depth list and association density list of the robotics industry.

[0067] The preset multi-factor weighted evaluation rule is retrieved. This rule clarifies the evaluation and assignment standards for the path distance factor and the association strength factor. The minimum path depth value of each supply entity node is extracted from the path depth list and used as the path distance factor. The total number of associated edge aggregations of each supply entity node is extracted from the association density list and used as the association strength factor. The two factors are combined and evaluated according to the evaluation rule, and a unique evaluation result value is assigned to each supply entity node to obtain the comprehensive matching index of the robot industry.

[0068] All supply entity nodes in the initial matching result set are sorted in descending order according to the value of the comprehensive matching index. During the sorting process, each supply entity node is bound to its corresponding attribute information and associated path information. After the sorting is completed, an ordered list of supply entity nodes is formed, resulting in the supply node sequence of the robotics industry.

[0069] According to the preset node truncation rules, the first single node of the supply node sequence is truncated, and the only supply entity node with the highest comprehensive matching index value in the supply node sequence is directly extracted. This node is the optimal supply entity node after comprehensive evaluation, and the target preferred node of the robot industry is obtained.

[0070] Using the target preferred node as the retrieval object, all complete attribute fields of the node are extracted from the knowledge graph data of the robotics industry and integrated into an attribute data package. At the same time, the connected path with the fewest node jumps between the target preferred node and the demand entity node is extracted from the path topology set. The trajectory information formed by the nodes and associated edges of the path is completely recorded, thus obtaining the preferred node attribute package and associated path trajectory of the robotics industry.

[0071] The pre-defined robot industry docking protocol encapsulation specification is retrieved. This specification clarifies the field format, data structure, and content arrangement order of the serialized encapsulation. The attribute information of the preferred node attribute package and the trajectory information of the associated path trajectory are standardized and serialized according to this specification. After processing, a standardized data file with a unified structure, complete content, and direct delivery is formed, thus obtaining the docking solution for the robot industry.

[0072] The beneficial effects are as follows: The comprehensive ranking and matching scheme encapsulation of supply entity nodes based on knowledge graph data accurately obtains the connection paths between supply and demand entity nodes through topological traversal. Combined with path depth analysis and association density statistics, quantitative evaluation criteria are formed. Then, a comprehensive matching index is obtained through multi-factor weighted evaluation using path distance and association strength as core factors. Based on this index, the scientific priority ranking of supply entity nodes is achieved, accurately selecting the optimal target nodes. Simultaneously, complete node attributes and the shortest association path are extracted and standardized serialized to form a matching scheme. The entire process uses the node association characteristics of the knowledge graph as the core to conduct multi-dimensional comprehensive evaluation, ensuring that the selection of supply entity nodes has objective and industry-aligned judgment criteria. The selected optimal nodes can accurately match the actual needs of target users. The resulting matching schemes are structurally standardized, complete in content, and contain clear association paths and node attribute information, directly supporting the implementation of supply and demand matching in the robotics industry. This significantly improves the accuracy and efficiency of supply and demand matching results, enabling standardized and systematic implementation schemes for supply and demand matching in the robotics industry.

[0073] like Figure 2 The diagram shown is a functional block diagram of a knowledge graph-based robot industry resource supply and demand matching system provided in an embodiment of the present invention.

[0074] The knowledge graph-based robot industry resource supply and demand matching system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the knowledge graph-based robot industry resource supply and demand matching system 100 may include a data field parsing module 101, a semantic entity annotation module 102, a resource node writing module 103, a semantic relationship reasoning module 104, a demand intent matching module 105, and an optimal solution encapsulation module 106. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0075] In this embodiment, the functions of each module / unit are as follows: The data field parsing module 101 is used to parse the resource data of the robot industry to obtain the basic supply and demand data of the robot industry. The semantic entity annotation module 102 is used to perform semantic role annotation on the supply and demand basic data based on a preset robot industry ontology library, and to map the annotated technical entities and indicator entities to the concept system of the robot industry ontology library to obtain the supply and demand capability feature set of the robot industry. The resource node writing module 103 is used to write nodes into the graph database of the robot industry, using entities in the supply and demand capacity feature set as resource nodes, to obtain resource entity nodes of the robot industry. The semantic relationship reasoning module 104 is used to perform link reasoning on the semantic relationship between the resource entity nodes based on the semantic association rules of the robot industry ontology library, so as to obtain the knowledge graph data of the robot industry. The demand intent matching module 105 is used to receive the docking request from the target user, perform intent recognition on the demand description of the docking request, perform path retrieval in the knowledge graph data, and obtain a preliminary matching result set for the robotics industry. The optimal solution encapsulation module 106 is used to comprehensively sort the supply entity nodes of the preliminary matching result set based on the path weights and association densities between nodes in the knowledge graph data, and to encapsulate the attribute information and association paths of the selected optimal supply entity nodes into a protocol to obtain the docking solution for the robotics industry.

[0076] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0077] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0079] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0080] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A knowledge graph-based method for matching supply and demand of robotics industry resources, characterized in that, The method includes: S1. Parse the resource data of the robotics industry to obtain the basic supply and demand data of the robotics industry; S2. Based on the preset robot industry ontology library, semantic role labeling is performed on the supply and demand basic data, and the labeled technical entities and indicator entities are mapped to the concept system of the robot industry ontology library to obtain the supply and demand capability feature set of the robot industry. S3. Using the entities in the supply and demand capacity feature set as resource nodes, write nodes into the graph database of the robot industry to obtain the resource entity nodes of the robot industry. S4. Based on the semantic association rules of the robot industry ontology library, perform link reasoning on the semantic relationships between the resource entity nodes to obtain the knowledge graph data of the robot industry; S5. Receive the docking request from the target user, perform intent recognition on the demand description of the docking request, perform path retrieval in the knowledge graph data, and obtain the preliminary matching result set of the robot industry; S6. Based on the path weights and association densities between nodes in the knowledge graph data, the supply entity nodes in the preliminary matching result set are comprehensively sorted, and the attribute information and association paths of the selected optimal supply entity nodes are encapsulated in a protocol to obtain the docking solution for the robotics industry.

2. The knowledge graph-based robotics industry resource supply and demand matching method as described in claim 1, characterized in that, The process of parsing the resource data of the robotics industry yields the basic supply and demand data for the robotics industry, including: The data source type of the resource data in the robotics industry is identified to obtain the source label of the robotics industry; Based on the source tags, the resource data is structurally split to obtain data fragments of the robotics industry; Based on the field mapping rules of the robotics industry, the data fragment is extracted to obtain the field key-value pairs of the robotics industry. The key-value pairs of the fields are normalized and encapsulated to obtain the basic supply and demand data of the robotics industry.

3. The knowledge graph-based robotics industry resource supply and demand matching method as described in claim 1, characterized in that, The aforementioned system, based on a pre-defined robotics industry ontology library, performs semantic role labeling on the supply and demand data, and maps the labeled technical entities and indicator entities to the conceptual system of the robotics industry ontology library, thereby obtaining a feature set of the supply and demand capabilities of the robotics industry, including: Based on the semantic role annotation dictionary in the preset robot industry ontology library, semantic roles are assigned to the text fields in the supply and demand basic data to obtain the supply and demand data entries of the robot industry. Based on the conceptual hierarchy of the robot industry ontology library, the role tags in the supply and demand data entries are verified for conceptual attribution to obtain the technical entities and indicator entities of the robot industry. Based on the concept mapping table of the robot industry ontology library, the technical entities and the indicator entities are associated with the ontology concept nodes of the robot industry ontology library to obtain the supply and demand capability feature entries of the robot industry. The ontological concept categories of the supply and demand capability feature items are classified and merged to obtain the supply and demand capability feature set of the robotics industry.

4. The knowledge graph-based robotics industry resource supply and demand matching method as described in claim 1, characterized in that, The step of using entities from the supply and demand capacity characteristic set as resource nodes and writing nodes into the graph database of the robotics industry to obtain resource entity nodes of the robotics industry includes: Traverse the supply and demand capability feature set, extract entity names and entity attribute lists from the entity entries of the supply and demand data entries in the robotics industry, and obtain the node data details table of the robotics industry; Based on the node data details table, blank nodes are created sequentially in the graphical database of the robotics industry, and node identifiers are assigned to the blank nodes to obtain the identified blank nodes of the robotics industry. The entity attribute list from the node data details table is filled into the attribute field of the blank node to obtain the filled node of the robot industry; Based on the ontology concept categories in the supply and demand capability feature set, the populated nodes are classified and attached to obtain the resource entity nodes of the robotics industry.

5. The knowledge graph-based method for matching supply and demand of robotics industry resources as described in claim 1, characterized in that, The semantic association rules based on the robot industry ontology library are used to perform link reasoning on the semantic relationships between the resource entity nodes to obtain the knowledge graph data of the robot industry, including: Extract the upstream and downstream transmission path map of the robot industry from the robot industry body library to obtain the topological skeleton of the robot industry links; The classification tags and attribute information of the resource entity nodes are used to determine the industry segment affiliation, thereby obtaining the segment anchoring entity of the robot industry; Based on the position coordinates of the anchored entity in the industrial chain topology, the upstream and downstream flow direction of the anchored entity is analyzed to obtain a list of candidate flow pairs for the robotics industry. The attribute information of upstream and downstream anchored entities in the candidate flow pair list is matched for supply and demand complementarity. When there is a matching relationship between the supply capacity field of the upstream anchored entity and the demand field of the downstream anchored entity, the supply and demand confirmation pair of the robot industry is obtained. In the graph database, a directed association edge is created for the supply and demand confirmation pair, and the direction of the directed association edge is set from the upstream anchor entity to the downstream anchor entity to obtain the industrial supply and demand chain edge of the robot industry; By performing topological fusion of the anchored entities in the aforementioned links with the edges of the industry supply and demand chain, the knowledge graph data of the robotics industry is obtained.

6. The knowledge graph-based method for matching supply and demand of robotics industry resources as described in claim 5, characterized in that, The process of performing supply and demand complementarity matching on the attribute information of upstream and downstream anchored entities in the candidate flow pair list, and obtaining the confirmed supply and demand pair for the robotics industry when the supply capacity field of the upstream anchored entity matches the demand field of the downstream anchored entity, includes: Extract the supply capacity field of the upstream anchor entity and the demand field of the downstream anchor entity from the candidate flow pair list; The supply capacity field and the demand field are decomposed into dimensions to obtain the upstream capacity index list and the downstream demand index list of the robot industry. Based on a preset industry technology indicator mapping table, the upstream capability indicator list and the downstream demand indicator list are matched and merged to obtain the indicator matching pair list of the robot industry. The numerical range of the matching pair list of the indicator items is verified. When the nominal range of the upstream capability indicator item can encompass or partially cover the threshold range of the downstream demand indicator item, the set of suitable indicator items for the robot industry is obtained. The matching indicator itemset is merged and statistically analyzed, and the coverage ratio of the matching indicator itemset is calculated based on the downstream demand indicator list to obtain the demand satisfaction coefficient of the robot industry. Based on a preset matching threshold, the demand satisfaction coefficient is checked against the threshold. When the demand satisfaction coefficient reaches or exceeds the matching threshold, a supply and demand confirmation pair for the robotics industry is obtained.

7. The knowledge graph-based method for matching supply and demand of robotics industry resources as described in claim 6, characterized in that, The formula for calculating the demand satisfaction coefficient is as follows: ； In the formula, The requirement satisfaction coefficient is the coefficient of the requirement. For the set of adaptation metrics, This is the list of downstream demand indicators. For the set of adaptation index items, the first The importance weight of each indicator item For the set of adaptation index items, the first The coverage depth coefficient of each indicator item, The first in the list of downstream demand indicators The importance weight of each indicator item For the set of adaptation index items, the first The nominal midpoint of the upstream capability indicator for each indicator item. For the set of adaptation index items, the first The median of the threshold range for each downstream demand indicator item. The preset quantity coverage factor, The preset weighted coverage factor, This is the preset range matching factor.

8. The knowledge graph-based method for matching supply and demand of robotics industry resources as described in claim 1, characterized in that, The process involves receiving a connection request from a target user, performing intent recognition on the request's description, and conducting path retrieval within the knowledge graph data to obtain a preliminary matching result set for the robotics industry, including: Receive the docking request message from the target user, and extract the requirement description field from the docking request message to obtain the original requirement text of the robot industry; Semantic segmentation is performed on the original demand text to obtain the intent-oriented tags and technical constraints of the robotics industry; Based on the intent pointing tag, the retrieval starting point type is retrieved from the robot industry ontology library, and the matching resource entity node is located in the knowledge graph data according to the retrieval starting point type to obtain the starting retrieval node set of the robot industry. Based on the aforementioned technical constraints, starting from the initial retrieval node set, link tracing is performed along the associated edges in the knowledge graph data to obtain the candidate supply node list and associated path log of the robotics industry. Based on the associated path logs, redundancy is merged in the candidate supply node list to obtain a preliminary matching result set for the robotics industry.

9. The knowledge graph-based method for matching supply and demand of robotics industry resources as described in claim 1, characterized in that, The supply entity nodes in the preliminary matching result set are comprehensively sorted based on the path weights and association densities between nodes in the knowledge graph data. The attribute information and association paths of the selected optimal supply entity nodes are then encapsulated using a protocol to obtain the docking solution for the robotics industry, including: Based on the knowledge graph data, a topological traversal is performed on the connection paths between the supply entity nodes and the demand entity nodes of the target user in the preliminary matching result set to obtain the path topology set of the robotics industry. The path depth of the connected paths in the path topology set is analyzed, and the density of the associated edges of the supply entity node and the domain of the demand entity node in the knowledge graph data is aggregated and statistically analyzed to obtain the path depth list and the association density list of the robot industry. Based on the path depth list and the association density list, the supply entity node is evaluated using the minimum path depth value of the supply entity node as the path distance factor and the total number of associated edges aggregated by the supply entity node as the association strength factor, and a multi-factor weighted evaluation is performed to obtain the comprehensive matching index of the robot industry. Based on the comprehensive matching index, the preliminary matching result set is prioritized to obtain the supply node sequence of the robotics industry; Extracting the first and second elements of the supply node sequence yields the target preferred node for the robotics industry. Extract the complete attribute fields of the target preferred node and the shortest path trajectory between the target preferred node and the demand entity node from the knowledge graph data to obtain the preferred node attribute package and associated path trajectory of the robotics industry; The preferred node attribute package and the associated path trajectory are serialized and encapsulated to obtain the docking solution for the robotics industry.

10. A knowledge graph-based robot industry resource supply and demand matching system, characterized in that, The system is used to implement the knowledge graph-based robot industry resource supply and demand matching method as described in claim 1, the system comprising: The data field parsing module is used to parse the resource data of the robotics industry to obtain the basic supply and demand data of the robotics industry. The semantic entity annotation module is used to perform semantic role annotation on the supply and demand basic data based on a preset robot industry ontology library, and to map the annotated technical entities and indicator entities to the conceptual system of the robot industry ontology library to obtain the supply and demand capability feature set of the robot industry. The resource node writing module is used to write nodes into the graph database of the robot industry, using entities in the supply and demand capacity feature set as resource nodes, to obtain resource entity nodes of the robot industry. The semantic relationship reasoning module is used to perform link reasoning on the semantic relationship between the resource entity nodes based on the semantic association rules of the robot industry ontology library, so as to obtain the knowledge graph data of the robot industry. The demand intent matching module is used to receive the docking request from the target user, identify the intent of the demand description of the docking request, perform path retrieval in the knowledge graph data, and obtain a preliminary matching result set of the robotics industry. The optimal solution encapsulation module is used to comprehensively sort the supply entity nodes in the preliminary matching result set based on the path weights and association densities between nodes in the knowledge graph data, and encapsulate the attribute information and association paths of the selected optimal supply entity nodes into a protocol to obtain the docking solution for the robotics industry.

Images