Liver transplantation postoperative nursing recommendation method and system based on NNN link system

Abstract

The invention relates to a liver transplantation post-operation nursing recommendation method and system based on an NNN link system, and the method comprises the steps: carrying out the construction of a knowledge graph based on the related data of a liver transplantation recipient post-operation NNN link, and constructing a corresponding liver transplantation post-operation nursing knowledge graph; and putting the liver transplantation postoperative nursing knowledge graph into clinical application, predicting an NNN nursing decision scheme matched with liver transplantation symptom information according to the liver transplantation symptom information of a clinical liver transplantation recipient, and executing the NNN nursing decision scheme on a patient. According to the method, an auxiliary decision-making system can be generated, medical staff are helped to reasonably set an outcome target for a liver transplantation recipient and formulate targeted nursing measures, the nursing efficiency is improved, and time and energy consumed by medical care decision making are saved. According to the invention, nurses can be guided to accurately identify and determine existing and potential health problems of liver transplantation recipients. Meanwhile, by introducing an NNN link system, systematized, standardized and intelligent management of postoperative care of liver transplantation recipients is realized.

Description

Technical Field

[0001] The present disclosure relates to the technical field of postoperative care, and in particular to a method, system and electronic device for recommending postoperative care for liver transplantation based on an NNN linking system. Background Art

[0002] The prognosis of liver transplant recipients is closely related to the meticulous care they receive after surgery. As the most direct caregivers of liver transplant recipients after surgery, nurses need to constantly apply scientific thinking to make reasonable decisions in clinical situations when facing changes in patients' conditions. Standardized and accurate nursing records help medical staff evaluate patients' individualized conditions and provide first-hand information for clinical, scientific research, and teaching.

[0003] Standardized nursing terms (SNLs) refer to the use of standardized language to express nursing assessment, nursing diagnosis, nursing intervention, nursing outcomes, etc., which helps nursing staff to form a unified nursing record standard and is one of the foundations and important links in the construction of nursing information standardization. However, since standardized nursing terms originated abroad, their unification and promotion are still important nursing issues that domestic scholars need to solve.

[0004] In addition, domestic clinical nursing, especially the prognosis and postoperative care of liver transplant recipients, mainly relies on some routine clinical nursing methods, and there is almost no clinical nursing plan for standardized nursing. Nurses are unable to provide standardized care for patients according to the liver transplant nursing measures specified in the standardized nursing terminology system, which is easily affected by subjective influences, resulting in uneven nursing work.

[0005] Therefore, the prognosis and postoperative nursing care of liver transplant recipients need to be further strengthened and upgraded to improve the quality of nursing. The internationally accepted "NANDA-I, NOC, NIC" (i.e. nursing diagnosis, nursing outcome, nursing measures) link system (i.e. NNN Alliance, also known as 3M Alliance (or NNN link system, NNN link or NNN standardized nursing terminology system), NNN was established in 2001 by the North American Nursing Diagnosis Association and the Nursing Classification and Clinical Effectiveness Center of the School of Nursing at the University of Iowa. The alliance developed the NNN link, which combines NANDA-I, NIC, and NOC into a whole. When using the NNN link, nurses first need to determine a nursing diagnosis, then select the nursing outcome recommendations for a single patient or patient group in the link table, and finally use the link recommendations to select applicable nursing measures) can achieve the systematic, standardized and intelligent management of nursing knowledge. Therefore, based on this system, combined with the actual nursing needs of liver transplant recipients in my country, recommendations and clinical applications for postoperative nursing care after liver transplantation can be made. Summary of the invention

[0006] In order to solve the above problems, the present application proposes a method, system and electronic device for recommending postoperative care after liver transplantation based on an NNN linking system.

[0007] On the one hand, this application proposes a method for recommending postoperative care for liver transplantation based on the NNN linking system, comprising the following steps:

[0008] S1. Collect the NNN-linked data of several liver transplant recipients after surgery.

[0009] S2. constructing a knowledge graph based on the NNN link-related data of the liver transplant recipient after surgery, and constructing a corresponding knowledge graph for postoperative nursing care after liver transplantation;

[0010] S3, collecting liver transplantation symptom information of liver transplant recipients and importing it into the liver transplantation postoperative nursing knowledge graph, retrieving NNN nursing decision plans matching the liver transplantation symptom information in the liver transplantation postoperative nursing knowledge graph and outputting them to the user interaction module;

[0011] S4. The user interaction module accepts and displays the NNN nursing decision plan, which is confirmed by the administrator and then executed as a reference.

[0012] As an optional implementation scheme of the present application, optionally, the NNN link-related data of the liver transplant recipient after surgery is specifically: an NNN nursing decision plan configured for postoperative care of the liver transplant recipient under the NNN link system, wherein the NNN nursing decision plan includes: core nursing diagnosis, core nursing outcomes and core nursing measures.

[0013] As an optional implementation scheme of the present application, optionally, S1, collecting NNN link-related data of several liver transplant recipients after liver transplantation, including:

[0014] Pre-configuring data collection rules, wherein the data collection rules include: the scope of the sampled population, the data type and format of the NNN link-related data of the liver transplant recipients to be collected, and the encoding rules for encoding the NNN link-related data of the liver transplant recipients after surgery when subsequently creating a knowledge graph;

[0015] Generate corresponding SQL sampling instructions according to the data collection rules, and send them to the backend SQL database to perform data retrieval to obtain the postoperative NNN link related data of several liver transplant recipients;

[0016] The NNN link-related data of the liver transplant recipient after surgery is preprocessed, and after the preprocessing, it is sent to the knowledge graph construction module for knowledge graph construction.

[0017] As an optional implementation scheme of the present application, optionally, S2, constructing a knowledge graph based on the NNN link-related data of the liver transplant recipient after surgery, and constructing a corresponding knowledge graph for postoperative liver transplant care, including:

[0018] Extracting entity content from the NNN link-related data of the liver transplant recipient after surgery, mapping the entity content to a pre-prepared content domain knowledge graph, and obtaining a corresponding entity content knowledge graph;

[0019] Designing retrieval addresses for entity contents in the entity content knowledge graph, generating entity content retrieval addresses for each entity content, and further encoding retrieval address rules for the entity content retrieval addresses to generate corresponding retrieval address rule encoding data;

[0020] Collect the retrieval address rule encoding data of each entity content, and use the retrieval address rule encoding data to adapt the retrieval configuration data of the retrieval engine in the graph database to generate a retrieval adaptation graph database;

[0021] The content domain knowledge graph is stored in the retrieval adaptation graph database to perform intelligent retrieval of the knowledge graph;

[0022] By utilizing natural language processing and knowledge extraction technology, based on the NNN standardized nursing terminology system, entity elements of each entity content stored in the content domain knowledge graph are extracted to obtain liver transplant symptom information of liver transplant recipients at different stages and the corresponding nursing terminology nodes, relationships between nodes and node attributes in the NNN nursing decision plan. Based on the extracted nursing terminology nodes, relationships between nodes and node attributes, the knowledge graph for postoperative nursing after liver transplantation is constructed.

[0023] As an optional implementation scheme of the present application, optionally, in step S2, before extracting the entity content in the NNN link-related data of the liver transplant recipient after surgery and mapping the entity content to a pre-prepared content domain knowledge graph to obtain the corresponding entity content knowledge graph, it also includes:

[0024] Receiving the pre-processed NNN link-related data of the liver transplant recipient after surgery, and performing data normalization processing on the NNN link-related data of the liver transplant recipient after surgery between the management end and the nursing end based on the circular feedback mode of the Delphi method;

[0025] The normalized NNN link-related data of the liver transplant recipient after surgery is stored in a preset graph database.

[0026] As an optional implementation scheme of the present application, optionally, in step S2, after obtaining the corresponding entity content knowledge graph, it also includes:

[0027] collecting first liver transplantation symptom information of clinical liver transplant recipients in real time, and extracting symptom entity content in the first liver transplantation symptom information to obtain first symptom entity content;

[0028] Import the extracted first symptom entity content into the entity content knowledge graph, traverse the first symptom entity content through the entity content knowledge graph, and determine whether the entity content in the entity content knowledge graph can match the first symptom entity content:

[0029] If yes, go to the next step;

[0030] On the contrary, based on the circular feedback model of the Delphi method, the NNN link-related data of the liver transplant recipient after surgery is re-debugged between the management end and the nursing end.

[0031] As an optional implementation scheme of the present application, optionally, in step S2, after constructing the knowledge graph of postoperative care for liver transplantation, it also includes:

[0032] Collecting the second liver transplantation symptom information of clinical liver transplant recipients in real time, and extracting the symptom entity elements in the second liver transplantation symptom information by using natural language processing and knowledge extraction technology;

[0033] The extracted symptom entity elements are imported into the knowledge graph of post-liver transplant nursing, and the symptom entity elements are traversed through the post-liver transplant nursing knowledge graph to determine whether there are nursing term nodes matching the symptom entity elements in the post-liver transplant nursing knowledge graph:

[0034] If it exists, go to the next step;

[0035] Otherwise, entity elements are extracted from each entity content stored in the content domain knowledge graph again to reconstruct the liver transplant postoperative care knowledge graph.

[0036] As an optional implementation scheme of the present application, optionally, S3, collecting liver transplantation symptom information of liver transplantation recipients and importing it into the liver transplantation postoperative nursing knowledge graph, and retrieving NNN nursing decision plans matching the liver transplantation symptom information in the liver transplantation postoperative nursing knowledge graph, including:

[0037] Through the liver transplantation postoperative nursing knowledge graph, the liver transplantation symptom information of the liver transplantation recipient is retrieved and analyzed, and the corresponding nursing diagnosis information is matched;

[0038] Based on the preset similarity information, several nursing outcomes and nursing measures that match and are similar to the nursing diagnosis information are recommended and output, so as to obtain the NNN nursing decision plan for the liver transplant recipient.

[0039] On the other hand, the present application proposes a system for implementing the above-mentioned method for recommending postoperative care for liver transplantation based on the NNN link system, comprising:

[0040] A data management module for collecting postoperative NNN link-related data of several liver transplant recipients;

[0041] A knowledge graph construction module, used to construct a knowledge graph based on the NNN link-related data of the liver transplant recipient after surgery, and to construct a corresponding knowledge graph for postoperative nursing care after liver transplantation;

[0042] A reasoning and decision-making module, for collecting liver transplantation symptom information of liver transplantation recipients and importing it into the liver transplantation postoperative nursing knowledge graph, retrieving NNN nursing decision plans that match the liver transplantation symptom information in the liver transplantation postoperative nursing knowledge graph and outputting it to the user interaction module;

[0043] The user interaction module is used to accept and display the NNN nursing decision plan, which is confirmed by the administrator and then executed as a reference.

[0044] In another aspect, the present application further provides an electronic device, comprising:

[0045] processor;

[0046] a memory for storing processor-executable instructions;

[0047] Wherein, the processor is configured to implement the method for recommending postoperative care for liver transplantation based on the NNN link system when executing the executable instructions.

[0048] Technical effects of the present invention:

[0049] This application constructs a knowledge graph based on the NNN link-related data of liver transplant recipients after surgery, and constructs a corresponding knowledge graph for postoperative nursing care after liver transplantation; the knowledge graph for postoperative nursing care after liver transplantation is put into clinical application and, based on the liver transplantation symptom information of clinical liver transplant recipients, a NNN nursing decision plan that matches the liver transplantation symptom information is predicted, and the NNN nursing decision plan is implemented for the patient. A decision-making support system can be generated to help medical staff reasonably set outcome goals for liver transplant recipients, formulate targeted nursing measures, improve nursing efficiency, and save time and energy spent on medical and nursing decision-making. The intelligent reasoning decision module of the present invention is the core of the system. Through the matching and selection mechanism, the corresponding nursing diagnosis is quickly located in the knowledge graph according to the patient's symptom information, and multiple nursing outcome indicators and nursing measures are recommended based on the preset similarity. This process not only improves the efficiency and accuracy of nursing decisions, but also realizes the personalization and precision of nursing measures.

[0050] Therefore, the present invention helps to guide nurses to accurately identify and determine the existing and potential health problems of liver transplant recipients. At the same time, by introducing the NNN link system, the systematization, standardization and intelligent management of postoperative care for liver transplant recipients can be achieved.

[0051] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0053] Figure 1 It is shown as a schematic diagram of the implementation process of the present invention;

[0054] Figure 2 The technical roadmap of the present invention for constructing a knowledge graph of postoperative nursing care after liver transplantation based on the NNN link system is shown;

[0055] Figure 3 Shown is a schematic diagram of the construction process of the knowledge graph for postoperative nursing after liver transplantation of the present invention;

[0056] Figure 4 Shown is a schematic diagram of clinical application of the knowledge graph of post-liver transplantation nursing care of the present invention;

[0057] Figure 5 Shown is a schematic diagram of the system composition of the present invention;

[0058] Figure 6 It is a schematic diagram showing the application of the electronic device of the present invention. DETAILED DESCRIPTION

[0059] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0060] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0061] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0062] The "NANDA-I, NOC, NIC" (i.e., nursing diagnosis, nursing outcome, nursing measures) linking system has been described in clinical nursing, and its principle is not described in detail in this embodiment. The present invention uses the NNN linking system to achieve intelligent recommendations for postoperative nursing of liver transplant recipients.

[0063] Under the NNN linkage system, nursing big data such as postoperative care plans for liver transplant recipients can be collected clinically by corresponding nursing staff or retrieved through the database on the nursing background.

[0064] Example 1

[0065] like Figure 1 As shown, on the one hand, the present application proposes a method for recommending postoperative care after liver transplantation based on the NNN link system, comprising the following steps:

[0066] S1. Collect the NNN-linked data of several liver transplant recipients after surgery.

[0067] S2. constructing a knowledge graph based on the NNN link-related data of the liver transplant recipient after surgery, and constructing a corresponding knowledge graph for postoperative nursing care after liver transplantation;

[0068] S3, collecting liver transplantation symptom information of liver transplant recipients and importing it into the liver transplantation postoperative nursing knowledge graph, retrieving NNN nursing decision plans matching the liver transplantation symptom information in the liver transplantation postoperative nursing knowledge graph and outputting them to the user interaction module;

[0069] S4. The user interaction module accepts and displays the NNN nursing decision plan, which is confirmed by the administrator and then executed as a reference.

[0070] The present invention aims to establish a knowledge graph of NNN links after liver transplantation, aiming to provide a basis and guarantee for the next step of clinical application. The knowledge graph uses a graphical structure to show the complex relationships in the medical field, integrates a large amount of knowledge data, and can provide a convenient, fast and accurate way to acquire knowledge. The knowledge graph constructed based on the NNN links after liver transplantation and the established decision-making support system can help guide nurses to accurately identify and determine the existing and potential health problems of liver transplantation recipients, reasonably set outcome goals, and formulate targeted nursing measures.

[0071] Specifically, the present invention discloses a liver transplantation post-operative nursing decision-making support system based on a knowledge graph constructed based on a standardized nursing terminology system, which relates to the field of liver transplantation nursing technology. By integrating advanced data management, knowledge graph construction, intelligent reasoning decision-making, and friendly user interaction technology, an efficient and accurate liver transplantation post-operative nursing decision-making support system is created. The system is based on the internationally accepted "NANDA-I, NOC, NIC" (i.e., nursing diagnosis, nursing outcome, nursing measures) link system, combined with the actual nursing needs of liver transplant recipients in my country, to achieve systematic, standardized, and intelligent management of nursing knowledge.

[0072] The steps for building a knowledge graph usually include the following stages:

[0073] 1. Requirements analysis: clarify the purpose and application scenarios of building a knowledge graph, and determine the knowledge areas and scope that need to be covered.

[0074] 2. Data collection: Collect data resources related to the knowledge graph topic, including structured data, semi-structured data and unstructured data.

[0075] 3. Data preprocessing: Perform preprocessing operations such as cleaning, deduplication, and formatting on the collected data to improve data quality.

[0076] 4. Entity Recognition: Identify key entities such as names, places, organizations, etc. from the preprocessed data.

[0077] 5. Relationship extraction: Determine the relationships between entities, such as "belongs to", "is located in", "created by", etc.

[0078] 6. Attribute extraction: Extract relevant attribute information for the entity, such as "date of birth", "date of establishment", "headquarters location", etc.

[0079] 7. Knowledge fusion: Integrate the extracted entities, relations and attributes to solve the ambiguity and conflict problems in entity recognition and relation extraction.

[0080] 8. Knowledge storage: Choose a suitable storage method, such as graph database, relational database, etc., to store the constructed knowledge graph.

[0081] 9. Knowledge update: Regularly update and maintain the knowledge graph to ensure the timeliness and accuracy of knowledge.

[0082] 10. Application development: Develop specific applications based on knowledge graphs, such as intelligent search, recommendation systems, question-answering systems, etc.

[0083] The present invention combines the conventional steps of constructing a knowledge graph to create a knowledge graph for the NNN link-related data of postoperative liver transplant recipients.

[0084] like Figure 2 As shown, it is a technical roadmap for constructing a knowledge graph of postoperative nursing after liver transplantation based on the NNN link system of the present invention. The present invention will construct a knowledge graph of postoperative nursing after liver transplantation in combination with the NNN link system, extract knowledge from the NNN link-related data of the postoperative liver transplant recipient, identify and extract the association relationship between knowledge content and entity elements, and configure each node in the knowledge graph and the graph relationship between nodes, so as to construct an NNN nursing decision plan that can intelligently retrieve and recommend the liver transplant symptom information that matches the liver transplant recipient and output it to the user interaction module, so that nurses can execute the recommended NNN nursing decision plan on patients and realize intelligent decision-making.

[0085] First, through detailed data collection specifications and preprocessing procedures, we ensure that the collected postoperative liver transplant care data are of high quality and in a unified format, laying a solid foundation for subsequent knowledge graph construction and intelligent reasoning.

[0086] As an optional implementation scheme of the present application, optionally, S1, collecting NNN link-related data of several liver transplant recipients after liver transplantation, including:

[0087] Pre-configuring data collection rules, wherein the data collection rules include: the scope of the sampled population, the data type and format of the NNN link-related data of the liver transplant recipients to be collected, and the encoding rules for encoding the NNN link-related data of the liver transplant recipients after surgery when subsequently creating a knowledge graph;

[0088] Generate corresponding SQL sampling instructions according to the data collection rules, and send them to the backend SQL database to perform data retrieval to obtain the postoperative NNN link related data of several liver transplant recipients;

[0089] The NNN link-related data of the liver transplant recipient after surgery is preprocessed, and after the preprocessing, it is sent to the knowledge graph construction module for knowledge graph construction.

[0090] Data on postoperative nursing care for liver transplant recipients based on the NNN link system, i.e., data related to postoperative NNN linking of liver transplant recipients. Specifically, the NNN nursing decision plan configured for postoperative nursing care for liver transplant recipients under the NNN link system, wherein the NNN nursing decision plan includes: core nursing diagnosis, core nursing outcome and core nursing measures.

[0091] In clinical practice, nurses refer to the NNN link system to make various nursing decision plans for postoperative care of liver transplant recipients. Clinical doctors or nurses make corresponding nursing diagnoses and nursing measures, which will not be elaborated in this embodiment.

[0092] Before collecting the postoperative NNN link-related data of these liver transplant recipients, it is first necessary to clarify the sampling population, data type, format, etc., and to configure the encoding rules for subsequent data encoding, etc., which are determined by the administrator.

[0093] Specific data collection and management measures include the following configuration information and preprocessing information:

[0094] (1) Develop detailed data collection specifications, clarify data types, formats, coding rules, etc., to ensure that the collected data meets the requirements for subsequent processing.

[0095] (2) Preprocess non-standardized data, such as terminology mapping and unit unification, to reduce the difficulty of subsequent processing.

[0096] (3) Missing value processing: Perform statistical analysis on missing values ​​to determine the causes and distribution characteristics of missing values.

[0097] (4) Design a reasonable database structure, including table design, field definition, index creation, etc., to support efficient data query and update.

[0098] like Figure 3 As shown, as an optional implementation scheme of the present application, optionally, S2, based on the NNN link-related data of the liver transplant recipient after surgery, a knowledge graph is constructed to construct a corresponding knowledge graph for postoperative liver transplant care, including:

[0099] Extracting entity content from the NNN link-related data of the liver transplant recipient after surgery, mapping the entity content to a pre-prepared content domain knowledge graph, and obtaining a corresponding entity content knowledge graph;

[0100] Designing retrieval addresses for entity contents in the entity content knowledge graph, generating entity content retrieval addresses for each entity content, and further encoding retrieval address rules for the entity content retrieval addresses to generate corresponding retrieval address rule encoding data;

[0101] Collect the retrieval address rule encoding data of each entity content, and use the retrieval address rule encoding data to adapt the retrieval configuration data of the retrieval engine in the graph database to generate a retrieval adaptation graph database;

[0102] The content domain knowledge graph is stored in the retrieval adaptation graph database to perform intelligent retrieval of the knowledge graph;

[0103] By utilizing natural language processing and knowledge extraction technology, based on the NNN standardized nursing terminology system, entity elements of each entity content stored in the content domain knowledge graph are extracted to obtain liver transplant symptom information of liver transplant recipients at different stages and the corresponding nursing terminology nodes, relationships between nodes and node attributes in the NNN nursing decision plan. Based on the extracted nursing terminology nodes, relationships between nodes and node attributes, the knowledge graph for postoperative nursing after liver transplantation is constructed.

[0104] This department uses advanced storage technologies such as graph databases and knowledge extraction based on NLP or deep learning technology to construct a knowledge graph that includes core nursing diagnoses, nursing outcomes, and nursing measures for liver transplant recipients after surgery. This process not only relies on a standardized nursing terminology system, but also uses scientific methods such as the Delphi method (Delphi method: After obtaining the opinions of experts on the issues to be predicted, they are sorted, summarized, and counted, and then anonymously fed back to each expert, and opinions are again solicited, concentrated, and fed back until a consensus is reached. In this part, before the entity content knowledge graph is created in this embodiment, a circular verification will be performed between the nursing end and the management end based on this model to ensure the authority and accuracy of the NNN link-related data of the liver transplant recipient after surgery) to ensure the authority and accuracy of the data. The construction of the knowledge graph will greatly improve the organization and accessibility of nursing knowledge and provide strong support for intelligent reasoning.

[0105] The intelligent reasoning decision module is the core of the system. Through matching and selection mechanisms, it can quickly locate the corresponding nursing diagnosis in the knowledge graph based on the patient's symptom information, and recommend multiple nursing outcome indicators and nursing measures based on the preset similarity. This process not only improves the efficiency and accuracy of nursing decisions, but also realizes the personalization and precision of nursing measures.

[0106] Specifically, the NNN link-related data of liver transplant recipients after surgery usually includes the following data obtained based on the NNN link system: core nursing diagnosis, core nursing outcomes, core nursing measures, and other non-core nursing information of liver transplant recipients after surgery. This department will mainly rely on core nursing diagnosis, core nursing outcomes and core nursing measures to construct the knowledge graph to avoid non-core nursing measures affecting the system decision-making performance.

[0107] First, a standardized nursing terminology system suitable for my country's national conditions was selected, and based on the Delphi method (this place uses the Delphi method's circular feedback model to normalize the data of the NNN link related to the liver transplant recipients after surgery between the management end and the nursing end), the NNN link related data of the liver transplant recipients after surgery was obtained, including the following data obtained under the conditions of the NNN link system: core nursing diagnoses (15 items), core nursing outcomes (42 items), and core nursing measures (106 items) of liver transplant recipients after surgery. These NNN link related data of liver transplant recipients after surgery can be retrieved and provided through the nursing big data in the nursing backend server, and can be screened by the administrator.

[0108] Secondly, use storage technologies such as graph databases (such as Neo4j) and select appropriate storage solutions based on data characteristics and system requirements.

[0109] Furthermore, according to the NNN link-related data of liver transplant recipients after surgery, the content domain knowledge graph is mapped to entity content to generate an entity content knowledge graph; the entity content knowledge graph is designed to perform retrieval address design to generate an entity content retrieval address; the entity content retrieval address is coded by retrieval address rules to generate corresponding retrieval address rule coding data;

[0110] Furthermore, by retrieving address rule encoding data, the graph database is adjusted for retrieval adaptability to generate a retrieval-adapted graph database; the content domain knowledge graph is stored through the retrieval-adapted graph database to perform intelligent retrieval of the knowledge graph.

[0111] Finally, natural language processing and knowledge extraction techniques were used to construct a knowledge graph of postoperative nursing care for liver transplantation based on the NNN standardized nursing terminology system, including nodes (terms), relationships (connections between terms), and attributes (term details).

[0112] When it comes to specific processing, the method of entity content mapping requires identifying key entities such as patient information, surgical details, and postoperative recovery from the NNN link-related data of liver transplant recipients after surgery. Then, these entities are matched and linked with existing concepts or entities in the knowledge graph. Next, the retrieval address is designed based on the entity content domain knowledge graph. This involves creating a unique identifier for each entity or entity combination to facilitate fast retrieval in the knowledge graph. For example, a URL or database query statement can be created for each liver transplant recipient postoperative case. After that, these retrieval addresses need to be rule-encoded to ensure the accuracy and efficiency of the retrieval process. This may include defining query parameters, filtering conditions, and sorting rules. For example, rules can be encoded to specify that the retrieval address should return entities related to postoperative recovery within a specific time range. Finally, the method of entity content mapping includes using natural language processing technology to identify entities in the text and match them with corresponding entities in the knowledge graph. This may involve technologies such as entity recognition, entity disambiguation, and entity linking. Through these methods, the entities in the knowledge graph can be ensured to maintain consistency and accuracy with the information in the actual data source.

[0113] The encoder can be created by the administrator on the background system or the downloaded installation component.

[0114] Based on natural language processing and knowledge extraction technology, it can be understood in combination with NLP technology, which will not be described in detail in this embodiment.

[0115] Here, knowledge graph templates with different forms and format requirements can be created by administrators or the corresponding knowledge graphs can be called from the knowledge graph template library, such as content domain knowledge graphs.

[0116] The graph format and composition of the content domain knowledge graph usually include the following key parts:

[0117] 1. Entities: The basic unit in the graph, representing specific things or concepts in the real world, such as names, places, organizations, events, etc.

[0118] 2. Relations: The connections between entities, describing how entities are related to each other, such as "belongs to", "is located in", "creates", etc.

[0119] 3. Attributes: Characteristics or properties of an entity, used to describe specific information about the entity, such as a person’s age, the coordinates of a location, etc.

[0120] 4. Facts: A combination of entities and relations that constitutes a complete declarative sentence, such as "Einstein is the founder of the theory of relativity."

[0121] 5. Concepts: Abstract categories or themes used to organize and classify entities, such as "scientists", "inventions", etc.

[0122] 6. Ontology: A model that defines concepts and their relationships within a domain. It is the skeleton of the knowledge graph and specifies the types and structures of entities, relationships, and attributes in the graph.

[0123] 7. Graph Schema: The graph schema defines the structure and constraints of entities, relationships, and attributes to ensure the consistency and scalability of the graph.

[0124] 8. Instances: Specific instances of concepts in the ontology, that is, specific entities in the graph.

[0125] 9. Semantic Annotation: The process of associating entities, relationships, and attributes in text with corresponding elements in the knowledge graph.

[0126] 10. Construction Tools: Software tools used to create and maintain knowledge graphs, including data extraction, fusion, storage and query tools.

[0127] The format of the knowledge graph can be RDF (Resource Description Framework), OWL (WebOntology Language), etc. These formats support standardized data exchange and integration. The above knowledge graph can also be created by the administrator according to the graph format and composition.

[0128] Therefore, the knowledge graph of postoperative liver transplantation care constructed by the present invention includes nodes (terms, that is, postoperative care measures, diagnostic information, etc. at the corresponding stage), relationships (connections between terms, such as nursing decision plans or nursing measures at the first or second stage after surgery) and attributes (term detailed information). It can identify the attributes of liver transplant recipients at different stages / nodes and the corresponding associated node care, and recommend other node information associated with the matched node (patient symptom node) (nursing measures / plan nodes associated with symptoms).

[0129] The present invention also sets up a two-level graph verification mechanism in the process of creating the knowledge graph to ensure the construction stability and recognition accuracy of the graph.

[0130] As an optional implementation scheme of the present application, optionally, in step S2, after obtaining the corresponding entity content knowledge graph, it also includes:

[0131] collecting first liver transplantation symptom information of clinical liver transplant recipients in real time, and extracting symptom entity content in the first liver transplantation symptom information to obtain first symptom entity content;

[0132] Import the extracted first symptom entity content into the entity content knowledge graph, traverse the first symptom entity content through the entity content knowledge graph, and determine whether the entity content in the entity content knowledge graph can match the first symptom entity content:

[0133] If yes, go to the next step;

[0134] On the contrary, based on the circular feedback model of the Delphi method, the NNN link-related data of the liver transplant recipient after surgery is re-debugged between the management end and the nursing end.

[0135] As an optional implementation scheme of the present application, optionally, in step S2, after constructing the knowledge graph of postoperative care for liver transplantation, it also includes:

[0136] Collecting the second liver transplantation symptom information of clinical liver transplant recipients in real time, and extracting the symptom entity elements in the second liver transplantation symptom information by using natural language processing and knowledge extraction technology;

[0137] The extracted symptom entity elements are imported into the knowledge graph of post-liver transplant nursing, and the symptom entity elements are traversed through the post-liver transplant nursing knowledge graph to determine whether there are nursing term nodes matching the symptom entity elements in the post-liver transplant nursing knowledge graph:

[0138] If it exists, go to the next step;

[0139] Otherwise, entity elements are extracted from each entity content stored in the content domain knowledge graph again to reconstruct the liver transplant postoperative care knowledge graph.

[0140] When constructing the knowledge graph, the present invention first needs to perform the first stage of entity content extraction. Specifically, it is necessary to extract the entity content of the symptoms of the corresponding liver transplant recipients, such as nursing diagnosis content, nursing strategy content, etc. Therefore, the constructed entity content knowledge graph needs to accurately identify the transplantation symptom information of the liver transplant recipients. This scheme verifies the constructed entity content knowledge breakthrough in combination with the liver transplantation symptom information of clinical recipients to determine whether the entity content knowledge breakthrough can match the liver transplantation symptom information of clinical recipients. If the entity content in the entity content knowledge graph can match the liver transplantation symptom information of the clinical recipients input, it means that the entity content contained in the entity content knowledge graph created in the first stage can identify the symptom content of clinical liver transplant recipients, and a preliminary recognition accuracy verification is carried out before the next stage of liver transplantation postoperative nursing knowledge graph construction is carried out.

[0141] After that, the matching degree of the joint nodes in the knowledge graph of the second stage also needs to be verified. It is necessary to verify whether each node element in the knowledge graph of postoperative liver transplantation care can identify the patient's symptom node and match the node information of each entity content associated with the current node. Collect the symptom information of the clinical recipient and import it into the knowledge graph generated in the second stage. The knowledge graph of postoperative liver transplantation care is used to match the entity elements in the symptom information to determine whether there is a nursing node that matches the symptom entity element of the clinical recipient (and at the same time associates with the nodes where other nursing terms are located (that is, the nodes where nursing decisions are located)). If so, it indicates that the knowledge graph of the second stage can identify the symptom entity elements of clinical patients; otherwise, it is necessary to re-extract the entity and re-configure the information of each node in the knowledge graph.

[0142] As an optional implementation scheme of the present application, optionally, S3, collecting liver transplantation symptom information of liver transplantation recipients and importing it into the liver transplantation postoperative nursing knowledge graph, and retrieving NNN nursing decision plans matching the liver transplantation symptom information in the liver transplantation postoperative nursing knowledge graph, including:

[0143] Through the liver transplantation postoperative nursing knowledge graph, the liver transplantation symptom information of the liver transplantation recipient is retrieved and analyzed, and the corresponding nursing diagnosis information is matched;

[0144] Based on the preset similarity information, several nursing outcomes and nursing measures that match and are similar to the nursing diagnosis information are recommended and output, so as to obtain the NNN nursing decision plan for the liver transplant recipient.

[0145] like Figure 4 Shown is a schematic diagram of the clinical application of the knowledge graph for postoperative care after liver transplantation.

[0146] The knowledge graph of post-liver transplant nursing is deployed in the reasoning decision-making module on the nursing background. The liver transplant symptom information of the liver transplant recipient is subsequently input, and the symptom information is matched in the knowledge graph of post-liver transplant nursing to obtain the corresponding nursing diagnosis information, and the corresponding nursing strategy / plan is output in association. Nurses and other users can log in to the nurse background through the user interaction module, view the nursing strategy / plan recommended by the system, and refer to it for execution.

[0147] When it is implemented:

[0148] 1. Reasoning and decision-making module, including:

[0149] A matching module is connected with the knowledge graph construction module to collect liver transplantation symptom information, and matches the symptom information in the knowledge graph of postoperative nursing after liver transplantation to obtain corresponding nursing diagnosis information;

[0150] The selection module is connected to the matching module to recommend multiple nursing outcome indicators and nursing measures based on the preset similarity. Because the same liver transplant symptom information will have multiple nodes associated with the symptom node, these associated nodes will give corresponding nursing outcome indicators and nursing measures. At this time, it is necessary to sort the multiple nursing outcome indicators and nursing measures recommended by these associations according to the similarity, and recommend the most similar nursing outcome indicators and nursing measures to the user. At this time, the similarity between the nursing outcome indicators and nursing measures of each node and the liver transplant symptoms can be calculated by the similarity algorithm, so that the nursing outcome indicators and nursing measures of the node with the greatest similarity are sent to the user.

[0151] The similarity algorithm is not described in detail in this embodiment and can be calculated by the administrator.

[0152] 2. User interaction module

[0153] Intuitive display: Nursing decision suggestions are intuitively presented to users in the form of charts and graphs, making it easier for users to understand quickly.

[0154] Highlight important information or add special marks to attract users' attention.

[0155] Interactive feedback: When users perform operations (such as viewing decision suggestions), provide clear interactive feedback (such as success prompts, etc.) to improve user experience.

[0156] Allow users to rate, comment or provide feedback on decision suggestions so that the system can be continuously optimized and improved.

[0157] Help Documentation: Provides detailed help documentation and user manuals to introduce how to use the system, precautions, and answers to frequently asked questions.

[0158] The user interaction module can be deployed on an intelligent terminal (such as a PDA) or a PC.

[0159] The nursing end (EDA or PDA) or management end of the present invention may be an APP or PC end, or other intelligent terminals.

[0160] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0161] Example 2

[0162] like Figure 5 As shown, based on the implementation principle of Example 1, on the other hand, the present application proposes a system for implementing the above-mentioned liver transplantation postoperative nursing recommendation method based on the NNN link system, including:

[0163] A data management module for collecting postoperative NNN link-related data of several liver transplant recipients;

[0164] A knowledge graph construction module, used to construct a knowledge graph based on the NNN link-related data of the liver transplant recipient after surgery, and to construct a corresponding knowledge graph for postoperative nursing care after liver transplantation;

[0165] A reasoning and decision-making module, for collecting liver transplantation symptom information of liver transplantation recipients and importing it into the liver transplantation postoperative nursing knowledge graph, retrieving NNN nursing decision plans that match the liver transplantation symptom information in the liver transplantation postoperative nursing knowledge graph and outputting it to the user interaction module;

[0166] The user interaction module is used to accept and display the NNN nursing decision plan, which is confirmed by the administrator and then executed as a reference.

[0167] Please understand the functions and interactions of the above modules in detail in conjunction with Example 1.

[0168] The modules or steps of the present invention described above can be implemented by a general-purpose computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0169] Example 3

[0170] like Figure 6 As shown, further, in another aspect, the present application also proposes an electronic device, including:

[0171] processor;

[0172] a memory for storing processor-executable instructions;

[0173] Wherein, the processor is configured to implement a method for recommending postoperative care for liver transplantation based on an NNN linking system as described in Example 1 when executing the executable instructions.

[0174] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor. The processor is configured to implement the method for recommending postoperative nursing care for liver transplantation based on the NNN linking system described in the above embodiment 1 when executing the executable instructions.

[0175] Here, it should be noted that the number of processors can be one or more. At the same time, the electronic device of the embodiment of the present disclosure may also include an input system and an output system. Among them, the processor, memory, input system and output system may be connected through a bus or in other ways, which are not specifically limited here.

[0176] The memory, as a computer-readable storage medium, can be used to store software programs, computer executable programs and various modules, such as the program or module corresponding to the method for recommending postoperative care for liver transplantation based on the NNN link system in the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0177] The input system can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output system can include display devices such as display screens.

[0178] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for recommending postoperative nursing care for liver transplantation based on the NNN linking system, characterized in that: The steps include: S1. Collect the NNN-linked data of several liver transplant recipients after surgery. S2. constructing a knowledge graph based on the NNN link-related data of the liver transplant recipient after surgery, and constructing a corresponding knowledge graph for postoperative nursing care after liver transplantation; S3, collecting liver transplantation symptom information of liver transplant recipients and importing it into the liver transplantation postoperative nursing knowledge graph, retrieving NNN nursing decision plans matching the liver transplantation symptom information in the liver transplantation postoperative nursing knowledge graph and outputting them to the user interaction module; S4. The user interaction module accepts and displays the NNN nursing decision plan, which is confirmed by the administrator and then executed as a reference.

2. A method for recommending postoperative care for liver transplantation based on the NNN linking system according to claim 1, characterized in that: The NNN link-related data of the liver transplant recipient after surgery specifically include: the NNN nursing decision plan configured for postoperative care of the liver transplant recipient under the NNN link system, wherein the NNN nursing decision plan includes: core nursing diagnosis, core nursing outcome and core nursing measures.

3. The method for recommending postoperative nursing care for liver transplantation based on the NNN linking system according to claim 1, characterized in that: S1. Collect the NNN link-related data of several liver transplant recipients after liver transplantation, including: Pre-configuring data collection rules, wherein the data collection rules include: the scope of the sampled population, the data type and format of the NNN link-related data of the liver transplant recipients to be collected, and the encoding rules for encoding the NNN link-related data of the liver transplant recipients after surgery when subsequently creating a knowledge graph; Generate corresponding SQL sampling instructions according to the data collection rules, and send them to the backend SQL database to perform data retrieval to obtain the postoperative NNN link related data of several liver transplant recipients; The NNN link-related data of the liver transplant recipient after surgery is preprocessed, and after the preprocessing, it is sent to the knowledge graph construction module for knowledge graph construction.

4. A method for recommending postoperative nursing care for liver transplantation based on the NNN linking system according to claim 3, characterized in that: S2. Constructing a knowledge graph based on the NNN link-related data of the liver transplant recipient after surgery, and constructing a corresponding knowledge graph for postoperative liver transplant nursing, including: Extracting entity content from the NNN link-related data of the liver transplant recipient after surgery, mapping the entity content to a pre-prepared content domain knowledge graph, and obtaining a corresponding entity content knowledge graph; Designing retrieval addresses for entity contents in the entity content knowledge graph, generating entity content retrieval addresses for each entity content, and further encoding retrieval address rules for the entity content retrieval addresses to generate corresponding retrieval address rule encoding data; Collect the retrieval address rule encoding data of each entity content, and use the retrieval address rule encoding data to adapt the retrieval configuration data of the retrieval engine in the graph database to generate a retrieval adaptation graph database; The content domain knowledge graph is stored in the retrieval adaptation graph database to perform intelligent retrieval of the knowledge graph; By utilizing natural language processing and knowledge extraction technology, based on the NNN standardized nursing terminology system, entity elements of each entity content stored in the content domain knowledge graph are extracted to obtain liver transplant symptom information of liver transplant recipients at different stages and the corresponding nursing terminology nodes, relationships between nodes and node attributes in the NNN nursing decision plan. Based on the extracted nursing terminology nodes, relationships between nodes and node attributes, the knowledge graph for postoperative nursing after liver transplantation is constructed.

5. A method for recommending postoperative nursing care for liver transplantation based on the NNN linking system according to claim 4, characterized in that: In step S2, before extracting the entity content in the NNN link-related data of the liver transplant recipient after surgery and mapping the entity content to the pre-prepared content domain knowledge graph to obtain the corresponding entity content knowledge graph, it also includes: Receiving the pre-processed NNN link-related data of the liver transplant recipient after surgery, and performing data normalization processing on the NNN link-related data of the liver transplant recipient after surgery between the management end and the nursing end based on the circular feedback mode of the Delphi method; The normalized NNN link-related data of the liver transplant recipient after surgery is stored in a preset graph database.

6. A method for recommending postoperative nursing care for liver transplantation based on the NNN linking system according to claim 4, characterized in that: In step S2, after obtaining the corresponding entity content knowledge graph, it also includes: collecting first liver transplantation symptom information of clinical liver transplantation recipients in real time, and extracting symptom entity content in the first liver transplantation symptom information to obtain first symptom entity content; Import the extracted first symptom entity content into the entity content knowledge graph, traverse the first symptom entity content through the entity content knowledge graph, and determine whether the entity content in the entity content knowledge graph can match the first symptom entity content: If yes, go to the next step; On the contrary, based on the circular feedback model of the Delphi method, the NNN link-related data of the liver transplant recipient after surgery is re-debugged between the management end and the nursing end.

7. The method for recommending postoperative nursing care for liver transplantation based on the NNN linking system according to claim 4, characterized in that: In step S2, after constructing the liver transplantation postoperative care knowledge graph, it also includes: Collecting the second liver transplantation symptom information of clinical liver transplant recipients in real time, and extracting the symptom entity elements in the second liver transplantation symptom information by using natural language processing and knowledge extraction technology; The extracted symptom entity elements are imported into the knowledge graph of post-liver transplant nursing, and the symptom entity elements are traversed through the post-liver transplant nursing knowledge graph to determine whether there are nursing term nodes matching the symptom entity elements in the post-liver transplant nursing knowledge graph: If it exists, go to the next step; Otherwise, entity elements are extracted from each entity content stored in the content domain knowledge graph again to reconstruct the liver transplant postoperative care knowledge graph.

8. The method for recommending postoperative nursing care for liver transplantation based on the NNN linking system according to claim 4, characterized in that: S3, collecting liver transplantation symptom information of liver transplant recipients and importing it into the liver transplantation postoperative nursing knowledge graph, and retrieving NNN nursing decision plans matching the liver transplantation symptom information in the liver transplantation postoperative nursing knowledge graph, including: Through the liver transplantation postoperative nursing knowledge graph, the liver transplantation symptom information of the liver transplantation recipient is retrieved and analyzed, and the corresponding nursing diagnosis information is matched; Based on the preset similarity information, several nursing outcomes and nursing measures that match and are similar to the nursing diagnosis information are recommended and output, so as to obtain the NNN nursing decision plan for the liver transplant recipient.

9. A system for implementing the method for recommending post-liver transplant nursing care based on the NNN linking system as described in any one of claims 1 to 8, characterized in that: include: A data management module for collecting postoperative NNN link-related data of several liver transplant recipients; A knowledge graph construction module, used to construct a knowledge graph based on the NNN link-related data of the liver transplant recipient after surgery, and to construct a corresponding knowledge graph for postoperative nursing care after liver transplantation; A reasoning and decision-making module, for collecting liver transplantation symptom information of liver transplantation recipients and importing it into the liver transplantation postoperative nursing knowledge graph, retrieving NNN nursing decision plans that match the liver transplantation symptom information in the liver transplantation postoperative nursing knowledge graph and outputting it to the user interaction module; The user interaction module is used to accept and display the NNN nursing decision plan, which is confirmed by the administrator and then executed as a reference.

10. An electronic device, characterized in that include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement a method for recommending post-operative care for liver transplantation based on an NNN linking system as described in any one of claims 1-8 when executing the executable instructions.

Images