Information sharing method and system based on static therapy system

Abstract

The invention relates to the technical field of static therapy information sharing, in particular to an information sharing method and system based on a static therapy system. The method comprises the following steps: acquiring a multi-disciplinary medical professional term set; performing semantic relationship modeling on the multi-disciplinary medical professional term set to obtain an interdisciplinary semantic mapping ontology model; using the interdisciplinary semantic mapping ontology model to carry out standardized conversion on the multidisciplinary medical professional term set to obtain a standard medical professional term set; performing role classification on the medical personnel based on the standard medical professional term set to obtain a personnel responsibility permission list; and performing information access permission generation on the medical personnel according to the personnel responsibility permission list to obtain a static therapy system permission access control table. According to the invention, medical information can be shared and understood more efficiently, and the efficiency of interdisciplinary team cooperation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of static therapy information sharing, and in particular to an information sharing method and system based on a static therapy system. Background Art

[0002] Static therapy systems involve medical professionals from multiple disciplines, and patient information needs to be shared efficiently and accurately to provide the best treatment. However, existing technologies face some challenges in achieving this goal. First, the diversity and complexity of medical terminology is a significant technical challenge. There are differences in the professional terminology used by medical personnel from different disciplines, which leads to barriers to interdisciplinary communication. Inconsistency in terminology makes information sharing difficult because each professional will have a different understanding of the same term, which can easily lead to misunderstandings and treatment errors. Secondly, the standardization and unification of medical information is a key technical challenge. Due to the lack of a unified standard medical terminology set, medical personnel use different terms and formats when recording and sharing patient information. This inconsistency not only affects the readability and accessibility of information, but also leads to difficulties in data integration and analysis, which in turn affects the continuity and coordination of patient treatment. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide an information sharing method and system based on an intravenous therapy system to solve at least one of the above technical problems.

[0004] To achieve the above purpose, an information sharing method based on a static therapy system includes the following steps:

[0005] Step S1: obtaining a multidisciplinary medical professional terminology set; performing semantic relationship modeling on the multidisciplinary medical professional terminology set to obtain an interdisciplinary semantic mapping ontology model; performing standardized conversion on the multidisciplinary medical professional terminology set using the interdisciplinary semantic mapping ontology model to obtain a standard medical professional terminology set;

[0006] Step S2: Classify the roles of medical personnel based on the standard medical professional terminology set to obtain a list of personnel responsibilities and permissions; generate information access rights for medical personnel based on the list of personnel responsibilities and permissions to obtain an intravenous therapy system permission access control table;

[0007] Step S3: Based on the permission access control table of the intravenous therapy system, real-time data collection is performed on the preset cross-department information channel to obtain the interdisciplinary synchronization data of the intravenous therapy system; based on the preset cross-department information channel, real-time correlation tracking is performed on the interdisciplinary synchronization data of the intravenous therapy system to obtain the medical information correlation traceability chain;

[0008] Step S4: constructing the topology of the communication nodes according to the medical information association traceability chain to obtain an interdisciplinary communication network; constructing a medical information transmission scheme for the static therapy system based on the interdisciplinary communication network to obtain a medical information transmission scheme for the static therapy system;

[0009] Step S5: Acquire patient-related data sets through the intravenous therapy system; dynamically construct a knowledge graph for the patient-related data sets to obtain a patient interdisciplinary information graph; based on the interdisciplinary communication network and according to the medical information transmission plan of the intravenous therapy system, transmit the patient interdisciplinary information graph to the multidisciplinary medical collaboration platform of the intravenous therapy system to realize interdisciplinary medical information sharing.

[0010] The present invention can standardize medical professional terms between different disciplines by constructing an interdisciplinary semantic mapping ontology model, thereby reducing misunderstandings and communication barriers caused by inconsistent terminology. This enables medical professionals to share and understand patient information more efficiently, and improves the efficiency of interdisciplinary team collaboration. By standardizing and converting multidisciplinary medical professional terminology sets, the consistency and accuracy of information when it is transmitted between different departments and professionals can be ensured. This helps to reduce errors caused by differences in terminology understanding. The static therapy system permission access control table generated by role classification and responsibility authority list can ensure that medical personnel access corresponding information according to their roles and responsibilities. Through real-time data collection and association tracking, the real-time update of interdisciplinary synchronous data of the static therapy system and the association tracing of medical information can be achieved. The interdisciplinary communication network constructed based on the medical information association tracing chain provides a structured framework for the transmission of medical information. This not only optimizes the information flow, but also improves the efficiency and reliability of information transmission. By dynamically constructing a knowledge graph for patient-related data sets, a patient interdisciplinary information graph can be generated to integrate the patient's comprehensive medical information. By transmitting the patient's interdisciplinary information graph to a multidisciplinary medical collaboration platform, the sharing of interdisciplinary medical information is achieved.

[0011] Preferably, the present invention further provides an information sharing system based on a static therapy system, which is used to execute the information sharing method based on a static therapy system as described above, and the information sharing system based on a static therapy system comprises:

[0012] A term set acquisition module is used to acquire a multidisciplinary medical term set; to perform semantic relationship modeling on the multidisciplinary medical term set to obtain an interdisciplinary semantic mapping ontology model; to perform standardized conversion on the multidisciplinary medical term set using the interdisciplinary semantic mapping ontology model to obtain a standard medical term set;

[0013] The authority control module is used to classify the roles of medical personnel based on the standard medical professional terminology set to obtain a list of personnel responsibilities and permissions; generate information access rights for medical personnel based on the list of personnel responsibilities and permissions to obtain an access control table for the intravenous therapy system;

[0014] The data tracking module is used to collect real-time data from the preset cross-department information channel based on the permission access control table of the intravenous therapy system to obtain the interdisciplinary synchronous data of the intravenous therapy system; based on the preset cross-department information channel, the interdisciplinary synchronous data of the intravenous therapy system is tracked in real time to obtain the medical information correlation traceability chain;

[0015] The communication network construction module is used to construct the topology of the communication nodes according to the medical information association traceability chain to obtain an interdisciplinary communication network; based on the interdisciplinary communication network, a medical information transmission scheme for the static therapy system is constructed to obtain a medical information transmission scheme for the static therapy system;

[0016] The information sharing module is used to obtain patient-related data sets through the intravenous therapy system; dynamically construct a knowledge graph for the patient-related data sets to obtain the patient's interdisciplinary information graph; based on the interdisciplinary communication network and according to the medical information transmission plan of the intravenous therapy system, the patient's interdisciplinary information graph is transmitted to the multidisciplinary medical collaboration platform of the intravenous therapy system to realize interdisciplinary medical information sharing.

[0017] The present invention realizes the standardized conversion of multidisciplinary medical professional terms through the term set acquisition module and semantic relationship modeling, thereby improving the consistency and standardization level of medical terms and providing a unified language basis for interdisciplinary communication. The authority control module classifies the roles of medical personnel according to the standard medical professional term set and generates information access rights, which enhances information security management, ensures that only authorized personnel can access sensitive medical information, and protects patient privacy. The data tracking module can collect interdisciplinary synchronous data in real time, and conduct real-time correlation tracking to build a medical information correlation traceability chain. This not only improves the timeliness of data processing, but also provides a reliable traceability path. The communication network construction module builds an interdisciplinary communication network according to the medical information correlation traceability chain, and formulates a medical information transmission plan, which optimizes the information flow and improves the efficiency and reliability of information transmission. The patient information map is transmitted to the multidisciplinary medical collaboration platform through the information sharing module, realizing the sharing of interdisciplinary medical information. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present invention will become more apparent from the detailed description made with reference to the following drawings:

[0019] Figure 1 A schematic flow chart of the steps of an information sharing method based on a static therapy system according to an embodiment is shown.

[0020] Figure 2 A detailed flowchart diagram of step S16 of an embodiment is shown.

[0021] Figure 3A detailed flowchart diagram of step S167 of an embodiment is shown. DETAILED DESCRIPTION

[0022] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different network and / or processor methods and / or microcontroller methods.

[0024] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 3 The present invention provides an information sharing method based on a static therapy system, comprising the following steps:

[0026] Step S1: obtaining a multidisciplinary medical professional terminology set; performing semantic relationship modeling on the multidisciplinary medical professional terminology set to obtain an interdisciplinary semantic mapping ontology model; performing standardized conversion on the multidisciplinary medical professional terminology set using the interdisciplinary semantic mapping ontology model to obtain a standard medical professional terminology set;

[0027] Step S2: Classify the roles of medical personnel based on the standard medical professional terminology set to obtain a list of personnel responsibilities and permissions; generate information access rights for medical personnel based on the list of personnel responsibilities and permissions to obtain an intravenous therapy system permission access control table;

[0028] Step S3: Based on the permission access control table of the intravenous therapy system, real-time data collection is performed on the preset cross-department information channel to obtain the interdisciplinary synchronization data of the intravenous therapy system; based on the preset cross-department information channel, real-time correlation tracking is performed on the interdisciplinary synchronization data of the intravenous therapy system to obtain the medical information correlation traceability chain;

[0029] Step S4: constructing the topology of the communication nodes according to the medical information association traceability chain to obtain an interdisciplinary communication network; constructing a medical information transmission scheme for the static therapy system based on the interdisciplinary communication network to obtain a medical information transmission scheme for the static therapy system;

[0030] Step S5: Acquire patient-related data sets through the intravenous therapy system; dynamically construct a knowledge graph for the patient-related data sets to obtain a patient interdisciplinary information graph; based on the interdisciplinary communication network and according to the medical information transmission plan of the intravenous therapy system, transmit the patient interdisciplinary information graph to the multidisciplinary medical collaboration platform of the intravenous therapy system to realize interdisciplinary medical information sharing.

[0031] In this embodiment, first, professional term collection tools such as UMLS (Unified Medical Language System) and MeSH (Medical Subject Thesaurus) are used to obtain multidisciplinary medical professional terminology sets. Ontology modeling tools such as Protégé are used to model the semantic relationships of these terms and create an interdisciplinary semantic mapping ontology model. This model standardizes terms from different sources to form a standard medical professional terminology set. RDF (Resource Description Framework) and OWL (Web Ontology Language) are used to represent and store these terms, and SPARQL query language is used for complex semantic queries. Based on these standard terms, a role classification program is developed that can generate a list of personnel responsibilities and permissions based on the professional fields, titles and skills of medical personnel. LDAP (Lightweight Directory Access Protocol) services are used to manage these permissions and create a permission access control table for the static therapy system. A stream processing platform such as Apache Kafka is deployed, which can handle high-throughput data streams and ensure the reliability of data transmission. Kafka Connect is used to integrate with different data sources and receivers to achieve real-time collection and transmission of interdisciplinary synchronous data in the static therapy system. Neo4j graph database is used to build medical information association traceability chains, which can store and manage complex network structures and quickly query information flow paths. Based on these traceability chains, network analysis tools such as Gephi are used to build interdisciplinary communication networks and plan medical information transmission plans. Finally, patient-related data sets are obtained through the intravenous therapy system, and knowledge graph construction tools such as Apache Jena are used to dynamically build patient interdisciplinary information graphs. Ensure that this graph can reflect the patient's comprehensive medical information, and use RESTful API to transmit these information graphs to the multidisciplinary medical collaboration platform of the intravenous therapy system, such as Microsoft Teams or Slack, to achieve real-time sharing and collaboration of interdisciplinary medical information.

[0032] Preferably, step S1 comprises the following steps:

[0033] Step S11: Acquire a multidisciplinary medical terminology set;

[0034] Specifically, medical terminology can be collected from multiple sources, including medical textbooks, professional medical journals, online medical databases, and standard terminology documents published by medical industry associations. For example, professional terminology in the latest medical research results can be extracted from the Chinese Medical Journal Network, standardized medical terminology can be downloaded from the UMLS (Unified Medical Language System) database of the National Library of Medicine (NLM), and disease-related professional terminology can be obtained from the International Classification of Diseases (ICD) database of the World Health Organization (WHO). These terms will be compiled into a comprehensive multidisciplinary medical terminology set.

[0035] Step S12: performing semantic vectorization of professional terms on a multidisciplinary medical professional terminology set to obtain a medical term semantic feature vector set;

[0036] Specifically, word embedding methods in natural language processing (NLP) technology, such as Word2Vec or GloVe, can be used to convert each professional term in the multidisciplinary medical professional terminology set into a vector in a high-dimensional space. For example, first use a word segmentation tool (such as NLTK or spaCy) to segment the multidisciplinary medical professional terminology set, and then use a pre-trained Word2Vec model (which can be trained on Google News or PubMed corpus) to map each term to a 300-dimensional vector space. In this way, each term corresponds to a vector containing 300 real values, which represent the semantic features of the term. In this way, the semantic information of the term can be encoded into the vector.

[0037] Step S13: performing similarity clustering on the medical term semantic feature vector set to obtain interdisciplinary term association clusters;

[0038] Specifically, the K-means clustering algorithm can be used to identify the similarities between sets of semantic feature vectors of medical terms. The appropriate number of clusters K can be selected, which can be determined by the Elbow Method, that is, by calculating the intra-cluster sum of squares (SSE) under different K values ​​to find the inflection point where the rate of SSE decreases slowly. The K-means algorithm is implemented using the Scikit-learn library in Python. The set of semantic feature vectors of medical terms is input into the algorithm, and the algorithm will output the cluster label to which each term belongs. For example, it was found that the terms "heart disease", "myocardial infarction" and "arrhythmia" were classified into the same cluster by the clustering algorithm, indicating that they are semantically similar, and finally a cluster of interdisciplinary term associations was obtained.

[0039] Step S14: defining the semantic boundaries of the multidisciplinary medical professional terminology set according to the interdisciplinary term association clusters to obtain semantic association boundary mapping data;

[0040] Specifically, the terms in each interdisciplinary term association cluster can be further analyzed to determine the semantic boundaries between them. For example, the hierarchical clustering method is used to refine the clustering results, which can provide a more detailed view of the term relationship. Hierarchical clustering is implemented using the Scipy library in Python, and a cluster tree (Dendrogram) is generated. By analyzing this dendrogram, the semantic boundaries between terms are defined. For example, it is found that although "heart disease" and "cardiac surgery" belong to a large cluster, they have obvious boundaries in semantics, because "heart disease" is more inclined to internal medicine treatment, while "cardiac surgery" involves surgical operations. Based on this analysis, a semantic association boundary mapping data table is created, which records each term and the semantic boundary to which it belongs.

[0041] Step S15: constructing a semantic graph for the multidisciplinary medical professional terminology set based on the semantic association boundary mapping data to obtain a multi-dimensional semantic feature description graph;

[0042] Specifically, a graph database such as Neo4j can be used to store and process semantic association boundary mapping data. Each term is entered into the graph database as a node, and each node contains its corresponding semantic feature vector. According to the semantic boundary mapping data between the terms, edges are created between the nodes to represent the relationship between them. For example, if "heart disease" and "hypertension" appear as related terms in the boundary mapping data, an edge is created between the two nodes and labeled as "related". Use Neo4j's Cypher query language to further enrich the graph. For example, query all terms directly related to "heart disease" and calculate the similarity between them to determine their positions in the multidimensional space. Use a metric such as cosine similarity to calculate the similarity between vectors, and adjust the position of the node in the graph based on these similarity values. In this way, similar terms will be close to each other in the graph, forming a multidimensional semantic feature description graph. Additional dimensions can also be introduced, such as the frequency of use of terms, professional field specificity, etc. These dimensions can be added to the graph as attributes of the nodes. For example, a "field specificity" score is given to terms based on the frequency of their appearance in the literature of a specific medical field, and it is used as an attribute of the node. Through the above processing, a multi-dimensional semantic feature description map can be obtained.

[0043] Step S16: Based on the multi-dimensional semantic feature description graph, the implicit association relationship between professional terms in the multi-disciplinary medical professional terminology set is inferred to obtain a potential term semantic association network, and based on the multi-dimensional semantic feature description graph and the potential term semantic association network, cross-domain semantic ontology modeling is performed to obtain a cross-disciplinary semantic mapping ontology model;

[0044] Specifically, please refer to the sub-steps of step S16 for the detailed implementation process of this embodiment.

[0045] Step S17: using the interdisciplinary semantic mapping ontology model to perform standardized conversion on the multidisciplinary medical professional terminology set to obtain a standard medical professional terminology set.

[0046] Specifically, OWL (Web Ontology Language) can be used as the ontology modeling language, and the Protégé ontology editor can be used to manage and edit the interdisciplinary semantic mapping ontology model. In this ontology model, various terms and their relationships, such as synonyms, hyponyms, and hyponyms, are defined. The Python RDFlib library is used to process RDF (Resource Description Framework) data, which is a commonly used data model for describing terms and relationships in the ontology model. First, the terms and relationships in the ontology model are exported to RDF format, and then a Python script is written to parse these RDF data and find and map each term in the multidisciplinary term set to the standardized term in the ontology model. For example, it is found that "heart failure", "congestive heart failure" and "heart insufficiency" are all associated with a more general term "heart failure" in the ontology model. According to the semantic relationship in the ontology model, the script maps these terms to "heart failure", which is the standard term for this concept. Finally, a standard medical professional term set is obtained, in which each multidisciplinary term is converted into a unified and standardized term.

[0047] The present invention significantly improves the consistency of terminology understanding by semantically vectorizing and clustering multidisciplinary medical professional terms, so that medical professionals from different backgrounds can understand and use these terms in a unified manner. The retrievability and operability of terms are enhanced by converting terms into semantic feature vector sets, so that specific terms can be quickly located and operated in massive medical data. The construction of semantic graphs improves the accuracy of terminology management and reduces ambiguity and misunderstanding in the use of terms. Cross-domain semantic ontology modeling realizes the cross-domain integration of terms and lays the foundation for building a comprehensive medical knowledge base. Ultimately, the implementation of standardized medical professional terminology sets provides a unified terminology foundation for medical information sharing and electronic health records, improves the interoperability of medical data, and enables data to be seamlessly exchanged and integrated between different medical information systems and platforms.

[0048] Preferably, step S16 comprises the following steps:

[0049] Step S161: Encoding the semantic implicit association dimension of the multidisciplinary medical professional terminology set to obtain a term semantic implicit association dimension vector set;

[0050] Specifically, a multidisciplinary medical professional terminology set may contain multiple medical terms, such as {"heart disease", "hypertension", "diabetes"}, and the semantic feature vectors of these terms are obtained through step S12. Now, the implicit associations between these terms are further analyzed, such as their co-occurrence frequencies in different medical documents. The Python programming language and natural language processing libraries, such as Gensim, are used to analyze the co-occurrence of terms in a large number of medical documents. By calculating the number of co-occurrences of each term pair in the document, a weight is assigned to each pair of terms, which can be regarded as a quantitative representation of the strength of the association between them. These weights are used as encodings of the semantic implicit association dimensions of the terms, and they are added to the original semantic feature vectors to form a vector set of the semantic implicit association dimensions of the terms. For example, there is a corpus containing 100 medical documents, and the Python programming language and natural language processing tools (such as spaCy) are used to identify and extract medical terms in these documents. A co-occurrence frequency matrix is ​​constructed, in which rows and columns represent different medical terms, and if two terms appear in the same article, one is added to the corresponding matrix element. For example, if "heart disease" and "hypertension" co-occur in 10 articles, the corresponding element value in the matrix is ​​10. For example, if "heart disease" and "hypertension" co-occur frequently in the literature, this co-occurrence frequency is added as an additional dimension to the semantic feature vectors of the two terms, thereby obtaining an updated set of term semantic implicit association dimension vectors.

[0051] Step S162: Calculate the probabilistic entropy value of the multi-dimensional semantic feature description map according to the term semantic implicit association dimension vector set to obtain the term semantic association entropy value matrix;

[0052] Specifically, the co-occurrence frequencies in the vector set of the implicit semantic association dimensions of the terms can be converted into probability values. For each element in the matrix, the number of co-occurrences is divided by the sum of the number of co-occurrences of all terms in the term pair. For example, if "heart disease" appears a total of 50 times in 100 articles, and "hypertension" appears 60 times, then the co-occurrence probability of "heart disease" and "hypertension" is 10 / (50+60). The entropy calculation formula is used, that is, -∑(p log2 p), where p is the probability of co-occurrence of the term pair. For each pair of terms, its entropy value is calculated. If the co-occurrence probability is 0 (that is, the term pair has never co-occurred), this case is ignored in the calculation, because the result of the logarithm of 0 is undefined. Finally, a term semantic association entropy value matrix is ​​constructed, in which the rows and columns represent different terms, and the elements in the matrix represent the entropy values ​​of the corresponding term pairs. This matrix provides a quantitative view showing the uncertainty of the association between terms. Throughout the process, the NumPy library in Python can be used to efficiently perform matrix operations and mathematical calculations. NumPy provides powerful array operation functions, which can quickly calculate co-occurrence frequency matrices, probability values, and entropy values.

[0053] Step S163: assigning semantic association weights to the multi-dimensional semantic feature description graph according to the term semantic association entropy matrix to obtain a term semantic association dynamic weight graph;

[0054] Specifically, a linear transformation method can be used to map the entropy values ​​in the term semantic association entropy value matrix to a weight range, such as [0,1]. Within this range, lower entropy values ​​(ie, higher certainty) will be mapped to higher weights, while higher entropy values ​​(ie, lower certainty) will be mapped to lower weights. Use the Python programming language and the NumPy library to implement this transformation. First, find the minimum and maximum values ​​in the entropy matrix, and then use these values ​​to normalize all entropy values ​​in the matrix so that they fall within the range of [0,1]. The formula can be expressed as: Finally, a dynamic weight graph of semantic associations of terms can be obtained, in which the edge between each pair of terms is assigned a weight that reflects the strength and certainty of the association between the terms. In this weight graph, edges with higher weights indicate that the association between the terms is closer and more certain, while edges with lower weights indicate that the association is looser and more uncertain.

[0055] Step S164: extracting network topology features from the multi-dimensional semantic feature description graph according to the dynamic weight graph of the term semantic association, and obtaining a term semantic network structure feature set;

[0056] Specifically, the Python library NetworkX can be used to extract network topology features. First, a weighted graph is constructed with terms as nodes and the weights between terms as edge weights. Some key network topology features of this graph are calculated, such as degree centrality, closeness centrality, betweenness centrality, and clustering coefficient. Degree centrality measures the importance of a node, that is, how many other nodes it is connected to. Closeness centrality measures the average distance from a node to all other nodes in the graph. Betweenness centrality measures the number of times a node appears on all shortest paths in the graph. The clustering coefficient measures the closeness of the connection between the neighboring nodes of a node. These features are calculated and used as the network structure feature set of the term. For example, it is found that the term "heart disease" has a high centrality and a high clustering coefficient, which indicates that it is a core node in the term network and has a strong association with its directly related terms. Through these network topology features, it is possible to have a deeper understanding of the structural relationship between terms and identify key terms and subnetwork structures in the multidimensional semantic feature description graph.

[0057] Step S165: performing probabilistic association reasoning on the term semantic network structure feature set to obtain a term semantic association probability set;

[0058] Specifically, machine learning methods, such as the Random Forest algorithm, can be used to model the relationship between features and term association probabilities. Use Python's Scikit-learn library to train a random forest model. The network topology features of the terms are used as input features, and the actual co-occurrence frequency between the terms (or the weights calculated previously) are used as target variables. Through training, the model will learn how to predict the association probability between terms based on network structural features. For example, it is found that the two terms "heart disease" and "hypertension" have a high probability association between them because their centrality and betweenness centrality in the network are both high. After the model training is completed, the network structure features of the terms are input into the model, and the output result is the set of semantic association probabilities of the terms. This set contains the predicted association probability for each pair of terms.

[0059] Step S166: performing cognitive semantic path mining on the multi-dimensional semantic feature description graph according to the term semantic association probability set to obtain an implicit term semantic association path set;

[0060] Specifically, graph mining algorithms, such as the Apriori algorithm or the FP-Growth algorithm, can be used to discover frequent item sets between terms, which can represent implicit association paths between terms. For example, the Apriori algorithm is implemented using Python's MLxtend library. Terms are taken as items in a transaction database, and high association probabilities between terms are taken as item sets in transactions. The algorithm will find all frequent item sets, which represent potential association paths between terms. For example, it is found that the three terms "heart disease", "hypertension" and "diabetes" often appear together, indicating that there is an implicit semantic association path between them. By analyzing these frequent item sets, an implicit term semantic association path set can be constructed, which contains all term association paths. These paths include not only directly associated terms, but also terms that are indirectly associated through other terms.

[0061] Step S167: Perform cross-disciplinary semantic mapping on the implicit term semantic association path set to obtain a latent term semantic association network; and perform cross-domain semantic ontology modeling based on the multi-dimensional semantic feature description graph and the latent term semantic association network to obtain a cross-disciplinary semantic mapping ontology model.

[0062] Specifically, please refer to the sub-steps of step S167 for the detailed implementation process of this embodiment.

[0063] The present invention enhances the depth and accuracy of term association by analyzing multidisciplinary medical professional terminology sets, can capture deeper connections between terms, and form an accurate set of term semantic implicit association dimension vectors. By using the probabilistic entropy value calculation method, the system quantifies the uncertainty in the term semantic association, providing a new perspective for dealing with the complexity and ambiguity of medical terms. The construction of a dynamic weight graph of term semantic association allows the system to dynamically adjust the weight of term association according to the entropy matrix, reflecting the changes in the relative importance of different terms. By extracting the feature set of the term semantic network structure, the network topology structure analysis is optimized, revealing the complex interactive relationship between terms. The accuracy of the term semantic association probability set is improved by the application of probabilistic association reasoning. Cognitive semantic path mining helps to discover implicit associations between terms and enrich the expression of medical knowledge. A comprehensive potential term semantic association network is constructed through interdisciplinary semantic mapping, which promotes interdisciplinary medical cooperation and knowledge integration. Finally, cross-domain semantic ontology modeling integrates terms and concepts from different fields, providing a basis for building a unified medical knowledge framework and achieving interoperability between different medical information systems.

[0064] Preferably, step S167 includes the following steps:

[0065] Step S1671: extracting an explicit semantic association network from the multi-dimensional semantic feature description graph to obtain an explicit semantic association network of terms;

[0066] Specifically, the Python library NetworkX can be used to analyze the multidimensional semantic feature description graph. First, extract the relationships between all the clearly defined terms from the graph. These relationships can be synonyms, hyponyms, causal relationships, etc. For example, we know that "heart failure" is a type of "heart disease", and "heart disease" has a causal relationship with "hypertension". Write a Python script to traverse the graph, identify these explicit semantic associations, and record them. For each term, collect all the terms and association types directly connected to it, and build a term explicit semantic association network. In this network, each node represents a medical term, and each edge represents an explicit semantic association between two terms. For example, extract the "type-instance" relationship between "heart failure" and "heart disease" and the "causal" relationship between "heart disease" and "hypertension" from the graph, and use these relationships as part of the explicit semantic association network.

[0067] Step S1672: performing semantic association fusion on the latent term semantic association network and the term explicit semantic association network to obtain a term comprehensive semantic association network, and performing synaptic plasticity modeling on the term comprehensive semantic association network to obtain a neuromorphic semantic association model;

[0068] Specifically, a graph database such as Neo4j can be used to store and process the data of the latent term semantic association network and the term explicit semantic association network. Import the explicit semantic association network and the latent semantic association network into the Neo4j database. Use the Cypher query language to merge the two networks, ensure that the nodes of the same terms can correspond, and merge the relationships between them. For example, if "heart failure" is associated with "heart disease" in both networks, merge these relationships to form a comprehensive association relationship. Model synaptic plasticity for the term comprehensive semantic association network. Use a neural network model, such as a long short-term memory network (LSTM) or a deep belief network (DBN), to simulate synaptic plasticity in the human brain. Use Python's Keras library to build and train this neural network model. The input of the model is the terms and relationships in the term comprehensive semantic association network, and the output is the strength and type of association between terms. Through training, the model will learn how to dynamically adjust the strength of association between terms according to the relationships in the network, thereby obtaining a neuromorphic semantic association model. This model can simulate the dynamic changes in associations between terms, just like the strengthening and weakening of synapses in the human brain. For example, if the association between "heart failure" and "heart disease" is frequently mentioned in multiple documents, the model will enhance the strength of the association between the two terms, and ultimately obtain a neuromorphic semantic association model that can dynamically reflect the semantic association between the terms.

[0069] Step S1673: Identify information propagation characteristics of the neuromorphic semantic association model based on the multi-dimensional semantic feature description graph to obtain medical term semantic information propagation data;

[0070] Specifically, Python's NetworkX library can be used to identify information propagation characteristics. We import the terms and associations in the neuromorphic semantic association model into NetworkX as nodes and edges of the graph. The PageRank algorithm is applied to calculate the PageRank value of each term, which represents the importance of the term in information propagation. For example, it is found that the PageRank value of the term "heart disease" is very high, indicating that it is a key node for information propagation in the medical term network. The PageRank value of each term and the weight of the edge are recorded, and these data constitute the medical term semantic information propagation data. These data can help understand how information flows in the medical term network and which terms play a core role in the propagation process. For example, it is found that "heart disease" is not only directly associated with terms such as "hypertension" and "diabetes", but also has an indirect strong association with terms such as "cardiac surgery" and "pacemaker" in information propagation.

[0071] Step S1674: verifying the logical consistency of the neuromorphic semantic association model according to the medical terminology semantic information propagation data to obtain a medical terminology semantic mapping logical association chain;

[0072] Specifically, the open source framework Apache Jena can be used for logical consistency verification, and the neuromorphic semantic association model can be exported to RDF format and stored in the RDF repository of Apache Jena. SPARQL queries are written to verify whether a specific semantic association is consistent with the information in the medical knowledge base. For example, query whether "heart disease" is directly associated with "myocardial infarction" and whether this association is supported in the information dissemination data. Through the results of the SPARQL query, a medical term semantic mapping logical association chain is constructed, which contains logically verified term associations. For example, it is found that there is not only a direct semantic association between "heart disease" and "myocardial infarction", but also a strong association is shown in the information dissemination data, which verifies the logical consistency of the neuromorphic semantic association model. Finally, these verified logical association chains are fed back to the neuromorphic semantic association model, and finally a medical term semantic mapping logical association chain with logical consistency verification is obtained, which can accurately reflect the semantic relationship between medical terms.

[0073] Step S1675: The neuromorphic semantic association model is semantically enhanced according to the logical association chain of the medical terminology semantic mapping to obtain an interdisciplinary semantic mapping ontology model.

[0074] Specifically, Python machine learning libraries such as Scikit-learn or TensorFlow can be used to adjust and optimize the neuromorphic semantic association model. The data in the logical association chain is input into the model as additional features or constraints. For example, if the logical association chain shows that there is a direct semantic association between "heart disease" and "heart transplant", this information is added as a feature to the model. Use these new features to retrain or fine-tune the neuromorphic semantic association model. For example, add a supervised learning process in which the model learns how to adjust the weights between terms based on the semantic associations in the logical association chain. In this way, the model is able to learn direct and indirect associations between terms and enhance its ability to predict the semantic associations of terms. During the training process, cross-validation is used to evaluate the performance of the model to ensure that the newly added features or constraints actually improve the accuracy and generalization ability of the model. For example, the improvement in model performance is verified by comparing the performance of the model on the validation set before and after adding the logical association chain. Finally, a cross-disciplinary semantic mapping ontology model enhanced with semantic associations is obtained. This model not only contains explicit and implicit semantic associations extracted from the multi-dimensional semantic feature description graph, but also incorporates logical association chains of logically verified medical term semantic mapping. For example, when querying "heart disease" in the model, the model can not only return directly related terms such as "hypertension" and "diabetes", but also return terms enhanced by logical association chains such as "heart transplantation", thus providing a comprehensive and cross-disciplinary semantic mapping.

[0075] The present invention enhances the clarity of term associations, reduces ambiguity and improves the accuracy of term usage by extracting explicit semantic association networks. By fusing implicit and explicit semantic associations, a comprehensive term comprehensive semantic association network is constructed to fully understand the complex relationships between terms. The neuromorphic semantic association model obtained through synaptic plasticity modeling simulates the way the human brain processes and memorizes information, enhancing the adaptability and learning ability of the model. By identifying the information propagation characteristics in the neuromorphic semantic association model, the flow of knowledge in the term network is optimized. The accuracy and reliability of the model are further improved through logical consistency verification, reducing potential errors and contradictions. The semantic association of the model is enhanced according to the logical association chain, which improves the strength and quality of the association between terms, making the interdisciplinary semantic mapping ontology model more robust and practical.

[0076] Preferably, step S2 comprises the following steps:

[0077] Step S21: collecting professional role attributes of medical personnel to obtain a set of medical personnel role attributes;

[0078] Specifically, an online survey tool, such as SurveyMonkey or Google Forms, can be used to design a questionnaire. This questionnaire will contain a series of questions designed to collect basic information about medical personnel, such as professional fields (such as cardiology, radiology, etc.), years of work, professional titles (such as resident physicians, attending physicians, specialists, etc.), and professional skills (such as surgical skills, diagnostic skills, etc.). The questionnaire will be distributed to the target medical personnel group through email or professional medical forums, and responses will be collected. The collected data will be imported into a database, such as using MySQL or MongoDB. In the database, a record is created for each medical personnel, containing all the attributes of his professional role. For example, there is a record as follows: {"Doctor ID":"D123","Professional Field":"Cardiology","Years of Work":"10 Years","Professional Title":"Attending Physician","Professional Skills":"Cardiac Surgery"}. These records constitute the medical personnel role attribute set.

[0079] Step S22: semantically embedding the medical personnel role attribute set and the standard medical professional terminology set to obtain medical personnel professional semantic association data;

[0080] Specifically, natural language processing (NLP) technology can be used to analyze and embed the semantic association between the medical staff role attribute set and the standard medical professional terminology set. Use Python's NLTK or spaCy library to process text data, and use Word2Vec or GloVe models to convert text into vector form. Convert the medical staff's professional fields, titles, and professional skills into vectors. Convert the terms in the standard medical professional terminology set into vectors. Use metrics such as cosine similarity to calculate the similarity between the medical staff attribute vector and the term vector to find the terms most relevant to each medical staff attribute. For example, it is found that the professional field "cardiology" of the attending physician "D123" has a high vector similarity with the terms "heart failure" and "coronary artery disease". Record this information in the medical staff professional semantic association data, for example: {"doctor ID":"D123","related terms":["heart failure","coronary artery disease"],"similarity":[0.85,0.90]}, and finally obtain the medical staff professional semantic association data.

[0081] Step S23: grade the severity of the standard medical professional terminology set to obtain a graded medical professional terminology set;

[0082] Specifically, a severity rating standard can be defined, which can be based on factors such as the lethality of the disease, the difficulty of treatment, and the impact on the patient's quality of life. Use medical literature, clinical guidelines, and expert opinions to determine these rating standards. Organize a team of multidisciplinary medical experts to evaluate each term based on the predefined rating criteria. Use an online collaboration platform, such as Trello or Asana, to manage this process. Each expert rates the term on the platform, and the system automatically collects all rating results. Use Python to write a script to process the collected rating data. The script stores the terms and corresponding ratings in a database to form a hierarchical medical terminology set. For example, "heart disease" can be rated as "severe", "hypertension" can be rated as "moderate", and "common cold" can be rated as "mild", and finally a hierarchical medical terminology set containing severity information is obtained.

[0083] Step S24: defining the professional authority boundary of medical personnel according to the hierarchical medical professional terminology set and the professional semantic association data of medical personnel to obtain the role authority semantic boundary data;

[0084] Specifically, a permission management software, such as Apache Shiro or Spring Security, can be used to define and enforce these permission boundaries. The scope of the term set that medical personnel should access is determined based on their titles, professional fields, and professional skills, as well as the strength of their semantic association with specific terms. For example, it is stipulated that only cardiologists can access patient information related to terms with a severity level of "severe" such as "heart disease" and "coronary artery disease". These rules are implemented using Python scripts and database queries. The script checks the professional semantic association data of medical personnel to determine which terms the medical personnel are associated with, and determines whether the medical personnel have permission to access these terms based on the hierarchical medical professional term set. For example, if the attending physician "D123" has a professional field of "cardiology" and has a high semantic association with "heart failure" and "coronary artery disease", the script will add these terms to the permission list of "D123", and finally obtain the role permission semantic boundary data, which defines the professional permission boundary of each medical personnel.

[0085] Step S25: assigning role permissions to medical personnel according to the role permission semantic boundary data to obtain a list of personnel responsibilities and permissions;

[0086] Specifically, permissions can be assigned using role-based permission management tools, such as Microsoft Active Directory or a custom permission management system. Different roles are created based on the titles and professional fields of medical personnel in the role permission semantic boundary data, such as "cardiologist", "junior nurse", etc. A series of permissions are defined for each role, which are based on the strength of their semantic association with specific terms and the severity of the hierarchical medical professional terminology set. For example, the "cardiologist" role is assigned permissions to allow access to all terms related to "heart disease" with a severity of "severe" and "moderate". SQL queries are used to update the personnel responsibility permission list in the database to associate each medical personnel with the corresponding role and the corresponding permissions. For example, if doctor "D123" is a "cardiologist", the personnel responsibility permission list will contain the following entries: {"doctor ID":"D123","role":"cardiologist","permission":["heart disease","heart failure","coronary artery disease"]}, and finally a detailed personnel responsibility permission list is obtained, which specifies the scope of information that each medical personnel can access.

[0087] Step S26: Generate information access rights for medical personnel according to the personnel responsibility and authority list to obtain an intravenous therapy system authority access control table.

[0088] Specifically, the list of personnel responsibilities and permissions can be extracted from the database and imported into the permission management module of the intravenous therapy system. For each medical staff, a permission access control entry is created, which details the type of information they can access. For example, for doctor "D123", a control entry is created to allow him to access all patient information and medical records related to "heart disease". These access control rules are programmed using the built-in API or scripting language of the intravenous therapy system. For example, a Python script can be written to set permissions using the API of the intravenous therapy system. The script will traverse the list of personnel responsibilities and permissions and set the corresponding access rights for each medical staff. These permissions are stored in the permission access control table of the intravenous therapy system, for example: {"doctor ID":"D123","accessible information":["heart disease patient information","heart failure treatment records","coronary artery disease surgery records"]}, and finally a complete permission access control table of the intravenous therapy system is obtained.

[0089] The present invention improves the accuracy of role management by collecting the professional role attributes of medical personnel. By semantically associating and embedding the role attributes of medical personnel with the standard medical professional terminology set, the ability of personalized services is enhanced, and a direct connection between medical personnel and the terminology they need to use is established. By grading the severity of the standard medical professional terminology set, hierarchical management of terminology is achieved and resource allocation is optimized. By defining the boundaries of professional authority, the scope of authority of each medical personnel is clarified, and authority abuse and information leakage are avoided. The optimization of role authority allocation ensures that medical personnel obtain authority that matches their responsibilities, thereby improving work efficiency and information security. Reasonable authority allocation and access control help protect patients' privacy and information security and prevent unauthorized information access and data leakage.

[0090] Preferably, step S3 comprises the following steps:

[0091] Step S31: collecting semantic network topology of preset cross-department information channels to obtain information flow path mapping data;

[0092] Specifically, we can assume that there is a hospital information system that needs to share patient information between different departments, such as from the emergency department to the cardiology department. Use network analysis tools, such as Cytoscape, to build and visualize the semantic network of cross-departmental information flow. Define the nodes in the information channel, such as different databases, information systems, and user interfaces. Define the relationship between nodes, such as data transmission protocols and interface calls. Use Python's RDFlib library to process these data and represent them as Resource Description Framework (RDF) triples, which describe entities (nodes) and the relationships between them (edges). For example, there is a set of triples as follows: (Emergency Department Database, Transmission Protocol, Cardiology Department Database), (Cardiology Department Database, Interface Call, Cardiology Department User Interface); Use Cypher query language (if Neo4j is used as the backend storage) to query and analyze these data, so as to build information flow path mapping data. These data record in detail how information flows between different departments, including the starting point, end point, and path of data transmission.

[0093] Step S32: Performing semantic compatibility evaluation on cross-departmental information interfaces based on the information flow path mapping data to obtain information interface semantic compatibility evaluation data;

[0094] Specifically, API management and testing tools, such as Postman or Swagger, can be used to test and evaluate the interface compatibility between different departmental information systems. Define an evaluation standard, including aspects such as data format, data structure, communication protocol, and semantic consistency. Use these tools to send test requests to check whether the interfaces between different departmental information systems can correctly parse and respond to data. For example, it was found that the data transmission protocols between the emergency department database and the cardiology department database were incompatible because the data formats they used were inconsistent. Record these incompatibilities and use Python to write scripts to automate the testing process. The scripts will automatically send requests and record the response results to evaluate the semantic compatibility of the interfaces. Generate information interface semantic compatibility evaluation data based on the test results. These data include the compatibility score of each interface and specific incompatibility issues. For example, the following evaluation data is obtained: Interface compatibility score between the emergency department database and the cardiology department database: low. Incompatibility issue: inconsistent data format.

[0095] Step S33: performing protocol standardization conversion on the preset cross-department information channel according to the information interface semantic compatibility evaluation data to obtain a unified information transmission interface specification;

[0096] Specifically, you can use API management platforms, such as Apigee or AWS API Gateway, to define and implement unified interface specifications. Determine a common data format, such as JSON or XML, and decide to use RESTful API as the communication protocol because it is widely supported and easy to use. Use the tools provided by these platforms to configure and deploy conversion rules. For example, if the data sent by the emergency department database is in XML format, and the cardiology database requires JSON format, configure a conversion rule to automatically convert the XML data to JSON. Ensure that all API calls follow RESTful principles, such as using standard HTTP methods (GET, POST, PUT, DELETE). Use Postman to test these conversion rules to ensure that the data remains complete and accurate during transmission. Through these steps, you can get a unified information transmission interface specification.

[0097] Step S34: real-time data collection is performed on the preset cross-department information channel through the unified information transmission interface specification to obtain cross-disciplinary synchronous data of the static therapy system;

[0098] Specifically, you can first set up the data source and target system, such as collecting data from the emergency department database and synchronizing it to the cardiology department database. Define data mapping and conversion rules to ensure that the data remains consistent and accurate during transmission. For example, map the "Patient ID" field in the emergency department database to the "Patient Number" field in the cardiology department database. Use the scheduling function of these tools to automate the data collection process. For example, set up a data synchronization task that runs every hour to ensure that the patient information in the cardiology department database is up to date. Through these steps, data from cross-departmental information channels can be collected in real time and synchronized to the intravenous therapy system, thereby obtaining cross-disciplinary synchronized data.

[0099] Step S35: Real-time correlation tracking is performed on the preset cross-department information channels according to the interdisciplinary synchronization data of the intravenous therapy system to obtain a medical information correlation traceability chain.

[0100] Specifically, you can use a data tracking and monitoring tool, such as Apache NiFi or Talend Real-time Big Data Platform, to monitor and record data flows. These tools can provide real-time data stream processing and event-driven data processing capabilities. Configure tracking rules to define which data fields need to be tracked, such as the patient information ID, data transmission timestamp, data source and target system, etc. Set up data flows to ensure that all data transmitted across departments will pass through the tracking system and leave detailed flow records. For example, when a medical record about patient "John Doe" is transferred from the emergency department database to the cardiology department database, the tracking system will record the details of this record, including patient ID, transmission time, data content summary, and source and target system information. These records are stored in a centralized log database, such as Elasticsearch, which supports fast data retrieval and analysis. Use visualization tools such as Kibana to view and analyze these tracking data and build a medical information association traceability chain. Through Kibana's dashboard, you can track the flow path of any information from the initial data source to the final target system. For example, if you need to track all medical records of patient "John Doe", enter the patient ID in Kibana, and the system will display all related data flow events, including the time, location, and content of each data update, and finally obtain the medical information association traceability chain.

[0101] The present invention optimizes the information flow path by collecting semantic network topology, significantly improving the efficiency of information circulation and reducing transmission delays and blockages. The compatibility of cross-departmental information interfaces is enhanced through semantic compatibility assessment, ensuring smooth information exchange between different departments. The unification of interface protocols is achieved through protocol standardization conversion, simplifying the integration and data exchange between systems. Real-time data collection further improves the timeliness and accuracy of cross-disciplinary synchronized data in the intravenous therapy system, and enhances the efficiency and reliability of data synchronization. Real-time association tracking strengthens the system's information traceability capabilities, helps monitor information flow, and ensures the integrity and traceability of medical information.

[0102] Preferably, step S4 comprises the following steps:

[0103] Step S41: performing control authority semantic analysis on the intravenous therapy system authority access control table to obtain a control authority semantic feature vector set;

[0104] Specifically, natural language processing (NLP) technology can be used to perform semantic analysis of control permissions. For example, Python's NLTK library is used to segment and tag keywords and concepts in permission descriptions. Word2Vec or GloVe models are used to convert these keywords and concepts into vector form, which can capture the semantic information of permission descriptions. For example, if there is a permission description "Cardiologists can access all records of heart patients", first identify the keywords "cardiologists", "access", "heart patients" and "all records". These keywords are converted into vectors, and each word is mapped to a point in a high-dimensional space, which represents the semantic feature of the word. In this way, a set of control permission semantic feature vectors is finally obtained, in which each permission is represented by a vector, and the vector contains the semantic information of the permission.

[0105] Step S42: topologically deconstruct the medical information associated traceability chain to obtain traceability chain deconstruction data;

[0106] Specifically, graph databases such as Neo4j can be used to store and process data of medical information-related traceability chains. In this database, each node represents an information processing step, and each edge represents the relationship of information flowing from one step to another. Use the Cypher query language to query and analyze these data to deconstruct the topological structure of the traceability chain. For example, query all information flows starting from the "Emergency Department Database" and trace their paths to the "Cardiology Department Database". By analyzing these paths, detailed information about each step can be obtained, including the systems involved, the timestamps of processing, the data format, and the transmission protocol. This information is deconstructed into traceability chain deconstruction data, which describes the network structure of information flow in detail. For example, it is found that patient information first flows from the "Emergency Department Database" to the "Central Patient Information Database", and then flows from the "Central Patient Information Database" to the "Cardiology Department Database". In this process, the information format is converted from XML to JSON.

[0107] Step S43: dynamically hierarchically clustering the communication nodes based on the control authority semantic feature vector set and the traceability chain semantic deconstruction data to obtain an interdisciplinary hierarchical communication node set;

[0108] Specifically, machine learning libraries, such as Scikit-learn, can be used to implement dynamic hierarchical clustering. The control authority semantic feature vector and the traceability chain semantic deconstruction data are merged into a feature set, and each node (for example, a database or information system) is represented by a set of feature vectors. Select a suitable clustering algorithm, such as DBSCAN or hierarchical clustering, to cluster these nodes. These algorithms can automatically determine the number of clusters based on the feature vectors of the nodes and identify similar nodes. For example, it is found that "cardiology database" and "cardiology user interface" are very close in the feature space, so they are classified into the same cluster. This cluster represents the communication nodes of the cardiology department, which share similar access rights and information flow paths. In this way, a set of interdisciplinary hierarchical communication nodes can be obtained, each level corresponds to a different cluster, and each cluster contains communication nodes with similar characteristics.

[0109] Step S44: performing routing planning on the interdisciplinary hierarchical communication node set to obtain a communication node connection path set, and performing topological network connection on the interdisciplinary hierarchical communication node set based on the communication node connection path set to obtain an interdisciplinary communication network;

[0110] Specifically, the interdisciplinary hierarchical communication nodes and the connections between them can be input into the network optimization tool as nodes and edges of the graph. The Dijkstra algorithm is used to calculate the shortest path between each pair of nodes. These algorithms are able to take into account the topology of the network and the weight of the edges (for example, transmission delay or bandwidth limitation). For example, planning a route from the "Emergency Department Database" to the "Cardiology Department Database". The network optimization tool will calculate an optimal path that takes into account the network topology and transmission efficiency. These paths are combined to form a set of communication node connection paths. Use these paths to build an interdisciplinary communication network. Use a network visualization tool, such as Gephi, to visualize this network. In this network, each node represents a communication node, and each edge represents a connection path between nodes. The flow and importance of the path are represented by adjusting the position of the node and the thickness of the edge. For example, it was found that the "Central Patient Information Database" is a common node for many paths, indicating that it is a key hub for information flow. In this way, an interdisciplinary communication network can be obtained.

[0111] Step S45: constructing a medical information transmission scheme for the static therapy system based on the interdisciplinary communication network to obtain a medical information transmission scheme for the static therapy system.

[0112] Specifically, please refer to the sub-steps of step S45 for the detailed implementation process of this embodiment.

[0113] The present invention significantly improves the accuracy and flexibility of authority management through authority management and communication network optimization. The efficiency and accuracy of information tracing are enhanced through topological structure deconstruction, and the flow path of medical information can be quickly analyzed and understood. The management of communication nodes is optimized through dynamic hierarchical clustering methods, and routing planning improves the efficiency of network routing and reduces data transmission delays. The efficient interdisciplinary communication network constructed through topological network connections promotes the rapid flow of information between different disciplines. The precise medical information transmission plan formulated based on this network ensures efficient and accurate information transmission, providing reliable data support for the intravenous therapy system.

[0114] Preferably, step S45 includes the following steps:

[0115] Step S451: performing semantic tracking of historical transmission behaviors on a set of interdisciplinary hierarchical communication nodes to obtain a historical transmission behavior semantic data set;

[0116] Specifically, data warehouse technologies such as Amazon Redshift or Google BigQuery can be used to store and manage these historical transmission records. These records include information such as the timestamp of the transmission, the sending and receiving nodes, the data type and size of the transmission. Use ETL (Extract, Transform, Load) tools such as Talend or Apache NiFi to extract these records and convert them into a structured format. For example, the transmission record is converted into a dataset containing fields such as "sending node", "receiving node", "data type" and "transmission time". Use data analysis and visualization tools such as Tableau or Power BI to track and analyze these data. Through these tools, create dashboards that display information such as the transmission frequency between different nodes, the data type of transmission, and the time distribution of transmission. For example, it is found that the "Emergency Department Database" sends a large amount of electrocardiogram data to the "Cardiology Department Database" between 10 am and 12 pm every day. These analysis results constitute a historical transmission behavior semantic dataset.

[0117] Step S452: Measuring the transmission load of the interdisciplinary hierarchical communication node set based on the historical transmission behavior semantic data set to obtain node transmission load mapping data;

[0118] Specifically, data analysis tools, such as Python's Pandas library, can be used to process the historical transmission behavior semantic dataset and calculate the transmission load of each node. The transmission load can be defined as the total amount of data sent or received by a node during a specific time period. For example, write a Python script to calculate the transmission load of each node per day. The script will read the historical transmission behavior semantic dataset and accumulate the amount of data sent and received for each node. Use Matplotlib or Seaborn libraries to visualize this data and create charts showing the transmission load of each node over time. For example, it was found that the "Central Patient Information Database" has the highest transmission load during a specific time period every day, due to a large number of patient information updates and query operations. These measurement results constitute the node transmission load mapping data.

[0119] Step S453: Track the historical information transmission quality of the interdisciplinary hierarchical communication node set to obtain a node transmission quality evaluation data set;

[0120] Specifically, a database management system, such as PostgreSQL or MongoDB, can be used to store the transmission logs of interdisciplinary hierarchical communication nodes. SQL queries or MongoDB's aggregation framework are used to extract key performance indicators, such as transmission success rate, average delay, and number of errors. Data analysis tools, such as Python's Pandas library, are used to process these log data and calculate the historical transmission quality indicators of each node. For example, the monthly average delay and transmission success rate of each node are calculated. Nodes with frequent transmission errors can also be identified, and the types and causes of errors can be analyzed. For example, it was found that the average transmission delay of the "Radiology Database" in the past three months was 500 milliseconds and the transmission success rate was 98%, while the average transmission delay of the "Cardiology Database" was 300 milliseconds and the transmission success rate was 99%. These analysis results constitute the node transmission quality evaluation dataset.

[0121] Step S454: dynamically allocating data traffic to the interdisciplinary hierarchical communication node set according to the node transmission load mapping data and the node transmission quality assessment data set to obtain a node data volume transmission allocation plan;

[0122] Specifically, network traffic management tools, such as Cisco's Network Assistant or Juniper's Network Director, can be used to configure and adjust network traffic. Analyze the node transmission load mapping data and the node transmission quality assessment data set to determine which nodes have a higher load and better transmission quality, and which nodes have a lower load or poorer transmission quality. For example, it is found that the load of the "Central Patient Information Database" is very high, but the transmission quality is also very good, while the load of the "Emergency Department Database" is low and the transmission quality is average. Based on these analyses, it is decided to increase the data traffic of the "Emergency Department Database" to improve its utilization, while reducing the data traffic of the "Central Patient Information Database" to reduce its load. Use the API or command line interface provided by these tools to adjust the network configuration, such as adjusting the routing weight or QoS (Quality of Service) policy. In this way, a node data volume transmission allocation plan can be obtained, which guides how to dynamically adjust the data traffic according to the node load and transmission quality.

[0123] Step S455: reconstructing the medical information transmission path of the static therapy system based on the node data volume transmission allocation plan to obtain the medical information transmission plan of the static therapy system.

[0124] Specifically, network simulation and optimization tools, such as NS3 or GNS3, can be used to simulate and test different transmission paths. According to the information in the node data volume transmission distribution plan, the network topology and traffic distribution in the simulation environment are configured. These settings reflect the load and transmission quality of the nodes in the actual network. Run the simulation to observe the transmission of data packets in the network. Through simulation, potential bottlenecks and delay points can be identified, and the performance of different paths can be evaluated. For example, it is found that the current path from the "Emergency Department Database" to the "Cardiology Department Database" has a delay, while another path through the "Central Patient Information Database" performs better. Based on the simulation results, network configuration and management tools, such as Cisco's PrimeInfrastructure or Juniper's Network Director, are used to adjust the routing and traffic distribution in the actual network. For example, the metric of the routing protocol is changed to guide the traffic through a path with better performance. The internal configuration of the intravenous therapy system also needs to be updated to ensure that the system can send and receive data according to the new transmission path. This involves modifying the connection string of the database, adjusting the call parameters of the API, or updating the data synchronization script. For example, the static therapy system is updated so that all data about "heart disease" is first sent to the "central patient information database", and then the node forwards the data to the "cardiology database" according to the rules in the traffic distribution plan. In this way, the medical information transmission plan of the static therapy system is finally obtained.

[0125] The present invention improves transmission efficiency, optimizes data traffic distribution, and identifies transmission bottlenecks and overloaded nodes through semantic tracking of historical transmission behaviors and measurement of transmission load. Dynamic data traffic distribution balances network load, reduces network congestion and failures, and thus enhances network stability and reliability. A dynamic resource allocation scheme based on historical transmission data makes resource allocation more reasonable, ensuring that key nodes can obtain the necessary resources to support key tasks. By tracking and evaluating the quality of historical information transmission, transmission quality issues are identified and optimized, thereby improving the quality of information transmission. Path reconstruction ensures that information is transmitted along the optimal path, reducing delays.

[0126] Preferably, step S5 comprises the following steps:

[0127] Step S51: Acquire patient-related data sets through the intravenous therapy system;

[0128] Specifically, you can use the API of the EHR system to access and retrieve patient data. For example, use the HL7 FHIR (Fast Healthcare Interoperability Resources) standard to query the records of a specific patient. Write an application that uses the Python language and the Requests library to send HTTP requests to the API endpoint of the EHR system to obtain data such as the patient's basic information, medical history, drug allergies, and current treatment plans. For example, send a GET request to https: / / api.ehrsystem.com / patients / 12345 to obtain the complete medical record of patient ID 12345. The response data is returned in JSON format, containing the patient's name, gender, date of birth, drug prescriptions, laboratory test results, and doctor's diagnosis instructions, and finally obtains the patient-related data set.

[0129] Step S52: performing semantic relationship reasoning on patient-related data sets to obtain patient semantic association feature data;

[0130] Specifically, NLP libraries such as NLTK or spaCy can be used to perform word segmentation, part-of-speech tagging, and named entity recognition (NER) on patient-related datasets. For example, entities such as disease names, drug names, and treatment procedures in the text are identified. Relation extraction techniques are used to identify the relationship between entities. For example, a well-trained classifier is used to identify the association between "diabetes" and "insulin", or the association between "hypertension" and "diuretics". For example, it is found that the record of patient "John Doe" mentions that he suffers from "hypertension" and is taking "diuretics". Through relationship extraction, the treatment association between "hypertension" and "diuretics" is inferred. These association features are recorded in the patient semantic association feature dataset.

[0131] Step S53: removing irrelevant data from the patient-related data set according to the patient's semantic association feature data to obtain a patient knowledge graph basic data set;

[0132] Specifically, data cleaning and processing tools, such as Python's Pandas library, can be used to process patient-related datasets. Define a set of criteria to identify and remove irrelevant data, for example, exclude news articles that are not related to the patient's disease, non-medical personal notes, etc. For example, if the patient's semantic association feature data indicates that he has "heart disease", all diagnostic reports, treatment plans, and drug records related to heart disease will be retained, while data unrelated to heart disease, such as the patient's eye examination records or irrelevant laboratory test results, will be removed. Write a Python script to automate this process. The script reads the patient's medical records and uses regular expressions and conditional filtering to identify and remove irrelevant data. For example, set a filter condition to exclude all non-heart disease related laboratory test results and only retain relevant data such as electrocardiograms and blood pressure monitoring. Through these steps, the patient knowledge graph basic dataset is finally obtained, which only contains data directly related to the patient's treatment and diagnosis.

[0133] Step S54: dynamically construct a knowledge graph based on the patient knowledge graph basic data set to obtain a patient interdisciplinary information graph;

[0134] Specifically, the entity types and relationship types in the graph can be defined first. Entity types include "patient", "disease", "drug", "treatment procedure", etc., and relationship types include "suffering from", "prescription", "treatment", etc. Use Neo4j's Cypher query language to create nodes and edges, and convert the information in the patient knowledge graph basic data set into a graph structure. For example, if the patient "John Doe" suffers from "heart disease" and is taking "aspirin", a "patient" node, a "disease" node, and a "drug" node will be created in the graph database, and "suffering from" and "prescription" relationships will be created to connect these nodes. Use Neo4j's graphical interface to visualize and explore the patient knowledge graph and identify interdisciplinary associations of patient conditions. For example, it is found that "heart disease" is associated with diseases such as "hypertension" and "diabetes", and is associated with treatment procedures such as "heart surgery" and "drug therapy". Through these steps, a patient interdisciplinary information graph is finally obtained.

[0135] Step S55: Based on the interdisciplinary communication network, the patient's interdisciplinary information map is transmitted to the multidisciplinary medical collaboration platform of the interdisciplinary therapy system according to the medical information transmission plan of the interdisciplinary therapy system.

[0136] Specifically, message queues and real-time data stream processing tools, such as Apache Kafka or RabbitMQ, can be used to implement this transmission process. Configure the message queue service, define the topics and queues for data transmission, and ensure the reliability and persistence of data transmission. Write a data transmission script or application that uses the Python language and the Pika library (for RabbitMQ) or the Kafka-Python library (for Apache Kafka) to serialize the patient graph data into messages in JSON or XML format and publish them to predefined queues or topics. For example, publish the heart disease-related information of the patient "John Doe" to the queue named "Cardiology_Patient_Data". Set up a message consumer on the multidisciplinary medical collaboration platform, which subscribes to the relevant queues or topics and listens to new messages in real time. When the consumer receives the patient graph data, it deserializes the data and updates the database or user interface of the collaboration platform according to the predefined rules and formats. For example, if the ECG data of "John Doe" is updated, consumers of the collaborative platform will receive this data and immediately update the patient information panel on the platform, allowing cardiologists to see the latest ECG results and make diagnosis and treatment decisions accordingly. In this way, real-time transmission and sharing of interdisciplinary patient information graphs are achieved, improving the continuity and coordination of medical services.

[0137] The present invention improves the relevance and practicality of data by acquiring and inferring patient-related data sets, while eliminating irrelevant data, purifying patient data sets, reducing noise and redundant information, and enabling medical professionals to obtain key information more quickly. A comprehensive and structured patient profile is constructed based on the purified data, providing a solid data foundation for interdisciplinary medical collaboration. By dynamically constructing an interdisciplinary information map for patients, key information from different medical fields is integrated to provide patients with a more comprehensive and integrated treatment plan. The optimized information sharing process ensures that patient information is accurately and efficiently transmitted between different medical teams. At the same time, interdisciplinary information sharing strengthens the continuity of patient care and ensures that patients receive consistent and coherent services at different stages of treatment.

[0138] Preferably, the present invention further provides an information sharing system based on a static therapy system, which is used to execute the information sharing method based on a static therapy system as described above, and the information sharing system based on a static therapy system comprises:

[0139] A term set acquisition module is used to acquire a multidisciplinary medical term set; to perform semantic relationship modeling on the multidisciplinary medical term set to obtain an interdisciplinary semantic mapping ontology model; to perform standardized conversion on the multidisciplinary medical term set using the interdisciplinary semantic mapping ontology model to obtain a standard medical term set;

[0140] The authority control module is used to classify the roles of medical personnel based on the standard medical professional terminology set to obtain a list of personnel responsibilities and permissions; generate information access rights for medical personnel based on the list of personnel responsibilities and permissions to obtain an access control table for the intravenous therapy system;

[0141] The data tracking module is used to collect real-time data from the preset cross-department information channel based on the permission access control table of the intravenous therapy system to obtain the interdisciplinary synchronous data of the intravenous therapy system; based on the preset cross-department information channel, the interdisciplinary synchronous data of the intravenous therapy system is tracked in real time to obtain the medical information correlation traceability chain;

[0142] The communication network construction module is used to construct the topology of the communication nodes according to the medical information association traceability chain to obtain an interdisciplinary communication network; based on the interdisciplinary communication network, a medical information transmission scheme for the static therapy system is constructed to obtain a medical information transmission scheme for the static therapy system;

[0143] The information sharing module is used to obtain patient-related data sets through the intravenous therapy system; dynamically construct a knowledge graph for the patient-related data sets to obtain the patient's interdisciplinary information graph; based on the interdisciplinary communication network and according to the medical information transmission plan of the intravenous therapy system, the patient's interdisciplinary information graph is transmitted to the multidisciplinary medical collaboration platform of the intravenous therapy system to realize interdisciplinary medical information sharing.

[0144] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0145] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An information sharing method based on a static therapy system, characterized in that: The following steps are involved: Step S1: obtaining a multidisciplinary medical professional terminology set; performing semantic relationship modeling on the multidisciplinary medical professional terminology set to obtain an interdisciplinary semantic mapping ontology model; performing standardized conversion on the multidisciplinary medical professional terminology set using the interdisciplinary semantic mapping ontology model to obtain a standard medical professional terminology set; Step S2: Classify the roles of medical personnel based on the standard medical professional terminology set to obtain a list of personnel responsibilities and permissions; generate information access rights for medical personnel based on the list of personnel responsibilities and permissions to obtain an intravenous therapy system permission access control table; Step S3: Based on the static therapy system authority access control table, real-time data collection is performed on the preset cross-department information channel to obtain cross-disciplinary synchronous data of the static therapy system; Based on the preset cross-department information channel, the interdisciplinary synchronous data of the static therapy system is tracked in real time to obtain the medical information correlation traceability chain; Step S4: constructing the topology of the communication nodes according to the medical information association traceability chain to obtain an interdisciplinary communication network; constructing a medical information transmission scheme for the static therapy system based on the interdisciplinary communication network to obtain a medical information transmission scheme for the static therapy system; Step S5: Acquire patient-related data sets through the intravenous therapy system; dynamically construct a knowledge graph for the patient-related data sets to obtain a patient interdisciplinary information graph; based on the interdisciplinary communication network and according to the medical information transmission plan of the intravenous therapy system, transmit the patient interdisciplinary information graph to the multidisciplinary medical collaboration platform of the intravenous therapy system to realize interdisciplinary medical information sharing.

2. The information sharing method based on the static therapy system according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire a multidisciplinary medical terminology set; Step S12: performing semantic vectorization of professional terms on a multidisciplinary medical professional terminology set to obtain a medical term semantic feature vector set; Step S13: performing similarity clustering on the medical term semantic feature vector set to obtain interdisciplinary term association clusters; Step S14: defining the semantic boundaries of the multidisciplinary medical professional terminology set according to the interdisciplinary term association clusters to obtain semantic association boundary mapping data; Step S15: constructing a semantic graph for the multidisciplinary medical professional terminology set based on the semantic association boundary mapping data to obtain a multi-dimensional semantic feature description graph; Step S16: Based on the multi-dimensional semantic feature description graph, the implicit association relationship between professional terms in the multi-disciplinary medical professional terminology set is inferred to obtain a potential term semantic association network, and based on the multi-dimensional semantic feature description graph and the potential term semantic association network, cross-domain semantic ontology modeling is performed to obtain a cross-disciplinary semantic mapping ontology model; Step S17: using the interdisciplinary semantic mapping ontology model to perform standardized conversion on the multidisciplinary medical professional terminology set to obtain a standard medical professional terminology set.

3. The information sharing method based on static therapy system according to claim 2 is characterized in that: Step S16 includes the following steps: Step S161: Encoding the semantic implicit association dimension of the multidisciplinary medical professional terminology set to obtain a term semantic implicit association dimension vector set; Step S162: Calculate the probabilistic entropy value of the multi-dimensional semantic feature description map according to the term semantic implicit association dimension vector set to obtain the term semantic association entropy value matrix; Step S163: assigning semantic association weights to the multi-dimensional semantic feature description graph according to the term semantic association entropy matrix to obtain a term semantic association dynamic weight graph; Step S164: extracting network topology features from the multi-dimensional semantic feature description graph according to the dynamic weight graph of the term semantic association, and obtaining a term semantic network structure feature set; Step S165: performing probabilistic association reasoning on the term semantic network structure feature set to obtain a term semantic association probability set; Step S166: performing cognitive semantic path mining on the multi-dimensional semantic feature description graph according to the term semantic association probability set to obtain an implicit term semantic association path set; Step S167: Perform cross-disciplinary semantic mapping on the implicit term semantic association path set to obtain a latent term semantic association network; and perform cross-domain semantic ontology modeling based on the multi-dimensional semantic feature description graph and the latent term semantic association network to obtain a cross-disciplinary semantic mapping ontology model.

4. The information sharing method based on the static therapy system according to claim 3 is characterized in that: Step S167 includes the following steps: Step S1671: extracting an explicit semantic association network from the multi-dimensional semantic feature description graph to obtain an explicit semantic association network of terms; Step S1672: performing semantic association fusion on the latent term semantic association network and the term explicit semantic association network to obtain a term comprehensive semantic association network, and performing synaptic plasticity modeling on the term comprehensive semantic association network to obtain a neuromorphic semantic association model; Step S1673: Identify information propagation characteristics of the neuromorphic semantic association model based on the multi-dimensional semantic feature description graph to obtain medical term semantic information propagation data; Step S1674: verifying the logical consistency of the neuromorphic semantic association model according to the medical terminology semantic information propagation data to obtain a medical terminology semantic mapping logical association chain; Step S1675: The neuromorphic semantic association model is semantically enhanced according to the logical association chain of the medical terminology semantic mapping to obtain an interdisciplinary semantic mapping ontology model.

5. The information sharing method based on static therapy system according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: collecting professional role attributes of medical personnel to obtain a set of medical personnel role attributes; Step S22: semantically embedding the medical personnel role attribute set and the standard medical professional terminology set to obtain medical personnel professional semantic association data; Step S23: grade the severity of the standard medical professional terminology set to obtain a graded medical professional terminology set; Step S24: defining the professional authority boundary of medical personnel according to the hierarchical medical professional terminology set and the professional semantic association data of medical personnel to obtain the role authority semantic boundary data; Step S25: assigning role permissions to medical personnel according to the role permission semantic boundary data to obtain a list of personnel responsibilities and permissions; Step S26: Generate information access rights for medical personnel according to the personnel responsibility and authority list to obtain an intravenous therapy system authority access control table.

6. The information sharing method based on static therapy system according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: collecting semantic network topology of preset cross-department information channels to obtain information flow path mapping data; Step S32: Performing semantic compatibility evaluation on cross-departmental information interfaces based on the information flow path mapping data to obtain information interface semantic compatibility evaluation data; Step S33: performing protocol standardization conversion on the preset cross-department information channel according to the information interface semantic compatibility evaluation data to obtain a unified information transmission interface specification; Step S34: real-time data collection is performed on the preset cross-department information channel through the unified information transmission interface specification to obtain cross-disciplinary synchronous data of the static therapy system; Step S35: Real-time correlation tracking is performed on the preset cross-department information channels according to the interdisciplinary synchronization data of the intravenous therapy system to obtain a medical information correlation traceability chain.

7. The information sharing method based on static therapy system according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing control authority semantic analysis on the intravenous therapy system authority access control table to obtain a control authority semantic feature vector set; Step S42: topologically deconstruct the medical information associated traceability chain to obtain traceability chain deconstruction data; Step S43: dynamically hierarchically clustering the communication nodes based on the control authority semantic feature vector set and the traceability chain semantic deconstruction data to obtain an interdisciplinary hierarchical communication node set; Step S44: performing routing planning on the interdisciplinary hierarchical communication node set to obtain a communication node connection path set, and performing topological network connection on the interdisciplinary hierarchical communication node set based on the communication node connection path set to obtain an interdisciplinary communication network; Step S45: constructing a medical information transmission scheme for the static therapy system based on the interdisciplinary communication network to obtain a medical information transmission scheme for the static therapy system.

8. The information sharing method based on static therapy system according to claim 7 is characterized in that: Step S45 includes the following steps: Step S451: performing semantic tracking of historical transmission behaviors on a set of interdisciplinary hierarchical communication nodes to obtain a historical transmission behavior semantic data set; Step S452: Measuring the transmission load of the interdisciplinary hierarchical communication node set based on the historical transmission behavior semantic data set to obtain node transmission load mapping data; Step S453: Track the historical information transmission quality of the interdisciplinary hierarchical communication node set to obtain a node transmission quality evaluation data set; Step S454: dynamically allocating data traffic to the interdisciplinary hierarchical communication node set according to the node transmission load mapping data and the node transmission quality assessment data set to obtain a node data volume transmission allocation plan; Step S455: reconstructing the medical information transmission path of the static therapy system based on the node data volume transmission allocation plan to obtain the medical information transmission plan of the static therapy system.

9. The information sharing method based on static therapy system according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: Acquire patient-related data sets through the intravenous therapy system; Step S52: performing semantic relationship reasoning on patient-related data sets to obtain patient semantic association feature data; Step S53: removing irrelevant data from the patient-related data set according to the patient's semantic association feature data to obtain a patient knowledge graph basic data set; Step S54: dynamically construct a knowledge graph based on the patient knowledge graph basic data set to obtain a patient interdisciplinary information graph; Step S55: Based on the interdisciplinary communication network, the patient's interdisciplinary information map is transmitted to the multidisciplinary medical collaboration platform of the interdisciplinary therapy system according to the medical information transmission plan of the interdisciplinary therapy system.

10. An information sharing system based on static therapy system, characterized in that: Used to execute the information sharing method based on the static therapy system as claimed in claim 1, the information sharing system based on the static therapy system comprises: A term set acquisition module is used to acquire a multidisciplinary medical term set; to perform semantic relationship modeling on the multidisciplinary medical term set to obtain an interdisciplinary semantic mapping ontology model; to perform standardized conversion on the multidisciplinary medical term set using the interdisciplinary semantic mapping ontology model to obtain a standard medical term set; The authority control module is used to classify the roles of medical personnel based on the standard medical professional terminology set to obtain a list of personnel responsibilities and permissions; generate information access rights for medical personnel based on the list of personnel responsibilities and permissions to obtain an access control table for the intravenous therapy system; The data tracking module is used to collect real-time data from the preset cross-department information channel based on the permission access control table of the intravenous therapy system to obtain the interdisciplinary synchronous data of the intravenous therapy system; based on the preset cross-department information channel, the interdisciplinary synchronous data of the intravenous therapy system is tracked in real time to obtain the medical information correlation traceability chain; The communication network construction module is used to construct the topology of the communication nodes according to the medical information association traceability chain to obtain an interdisciplinary communication network; based on the interdisciplinary communication network, a medical information transmission scheme for the static therapy system is constructed to obtain a medical information transmission scheme for the static therapy system; The information sharing module is used to obtain patient-related data sets through the intravenous therapy system; dynamically construct a knowledge graph for the patient-related data sets to obtain the patient's interdisciplinary information graph; based on the interdisciplinary communication network and according to the medical information transmission plan of the intravenous therapy system, the patient's interdisciplinary information graph is transmitted to the multidisciplinary medical collaboration platform of the intravenous therapy system to realize interdisciplinary medical information sharing.

Images