Unified architecture method, device and equipment of medical knowledge and database using redundancy strategy and storage medium

Abstract

The application discloses a unified architecture method of medical knowledge and database by adopting a redundancy strategy, and comprises the following steps: value range classification is performed on a preset standard dictionary knowledge base; a clinical event is acquired, and the clinical event is compared with a standard guide to confirm a belonging state of the clinical event according to event content of the clinical event; a mapping relationship is constructed by judging and combining according to a standard dictionary value range attribute of the event content and the belonging state of the clinical event; and knowledge graph is constructed by adopting different redundancy strategies based on different mapping relationships. The application avoids selection during selection of the regular expression and NLP on the matter extraction, adopts different redundancy strategies for all different mapping relationships to construct the knowledge graph, and can realize unification of the medical knowledge structure and the database structure.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a unified architecture method, apparatus, device, and storage medium for medical knowledge and databases employing a redundancy strategy. Background Technology

[0002] The difficulty of unifying medical knowledge structure and database structure: The development of medical disciplines, from traditional medicine to evidence-based medicine, has always been based on the summarization and induction of numerous clinical cases. Medical decisions are usually based on objective research results as much as possible, with the ultimate goal of curing diseases and saving lives, rather than doing things perfectly according to a set of logic. Therefore, medical knowledge structures currently exist in an unstructured form, making it largely impossible to establish a good mathematical model.

[0003] Data structure refers to the structure of a related, structured collection of data rationally stored on a computer's storage device. The purpose of a database is to store and retrieve large amounts of data, and it includes databases, tables, fields, filters, etc. Database construction is often accompanied by the definition of a set of data structures or layouts using terminology. Computer languages ​​describe how the data will be organized and connected; that is, events are represented through tables, views, fields, relationships, packages, indexes, types, etc. Databases are designed entirely according to a set of optimal logic. Therefore, databases used by big data programs exist in a standardized and structured form. A small portion of data that does not require explicit exploration of logical relationships can be stored in an unstructured form. Unstructured storage is generally only used for retrieval and display, not for logical calculations. Even if calculations are required, they are first performed using regular expressions or NLP (Natural Language Processing) to extract keywords and store them in a structured logical framework for computation. In summary, achieving a unified medical knowledge structure and database structure is extremely difficult.

[0004] Current status of the adaptation between medical knowledge structure and database structure: Currently, the adaptation between medical knowledge structure and database structure in hospitals has two levels and is fragmented.

[0005] The first aspect is the teaching level of the knowledge base: Knowledge bases are used for teaching and searching, often indexed by keywords embedded in HTML pages to meet application-level needs. Typically, users search for a specific keyword, and when encountering unfamiliar keywords while reading related information, they navigate to new keywords. Even when using knowledge graphs, connections are established by pre-defined relationships between symptoms, diseases, surgeries, tests, examinations, pathology, etc. The knowledge graph exists as a directory, allowing users to search for knowledge within HTML pages.

[0006] The second aspect is the clinical diagnosis and treatment level: In clinical practice, knowledge graphs are often iterated through feature engineering and AI technology, including but not limited to anchoring data test sets, annotating electronic medical records, and extracting keywords using NLP, such as creating knowledge graphs for symptoms, diseases, drugs, tests, and examinations. After the knowledge graph is created, it is applied clinically. Doctors input symptoms, and the system calculates disease datasets, drug datasets, and other datasets in the knowledge graph, as well as the probability of each element in the corresponding dataset, as a basis for auxiliary diagnosis and treatment.

[0007] The disconnect between these two levels, as revealed by the technical approaches used at each level, reveals that knowledge graph construction often falls into two extremes: one is an academic approach that closely adheres to textbooks, and the other is a practice-oriented approach that closely adheres to clinical practice. Because textbook knowledge often lags behind clinical practice and tends to focus more on high-probability diseases, while clinical knowledge is more realistic and unique to each case, the constructed knowledge graph is often not comprehensive and is constrained by the disease distribution of patients in the hospital. This leads to drawbacks at the application level and makes it impossible to unify the two types of knowledge graphs. Summary of the Invention

[0008] The main objective of this invention is to provide a unified architecture method, apparatus, device, and storage medium for medical knowledge and databases employing a redundancy strategy, thereby addressing the aforementioned technical problems.

[0009] To achieve the above objectives, the present invention provides a unified architecture method for medical knowledge and databases that employs a redundancy strategy.

[0010] The unified architecture approach for medical knowledge and databases employing a redundancy strategy includes the following steps: Classify value ranges from a pre-defined standard dictionary knowledge base; Acquire clinical events and compare them with standard guidelines to determine the status of the clinical events based on their content; The mapping relationship is constructed by judging and combining the standard dictionary value range attributes of the event content and the status of the clinical event; Knowledge graphs are constructed using different redundancy strategies based on different mapping relationships.

[0011] Preferably, the standard dictionary knowledge base includes national standard dictionaries, provincial standard dictionaries, municipal standard dictionaries, and institute-level standard dictionaries.

[0012] Preferably, the state of the clinical event includes a stable state, a slow iteration state, and a fast iteration state.

[0013] Preferably, the step of judging and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct a mapping relationship includes: If the standard dictionary value range attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a stable state or a slow iteration state; Then, the current standard dictionary value range attribute and the state of the clinical event are constructed as the first mapping relationship.

[0014] Preferably, the step of judging and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct the mapping relationship further includes: If the standard dictionary value range attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a fast iteration state; Then, a second mapping relationship is constructed between the current standard dictionary value domain attributes and the state to which the clinical event belongs.

[0015] Preferably, the step of judging and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct the mapping relationship further includes: If the standard dictionary value range attribute of the event content is the hospital-level standard dictionary, and the state of the clinical event is a stable state or a slow iteration state; Then, a third mapping relationship is constructed between the current standard dictionary value range attributes and the state to which the clinical event belongs.

[0016] Preferably, the step of judging and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct the mapping relationship further includes: If the standard dictionary value range attribute of the event content is the hospital-level standard dictionary, and the state of the clinical event is the fast iteration state; Then, the current standard dictionary value range attribute and the state of the clinical event are constructed as the fourth mapping relationship.

[0017] Furthermore, to achieve the above objectives, the present invention also provides a unified architecture device for medical knowledge and database employing a redundancy strategy, the unified architecture device for medical knowledge and database employing a redundancy strategy comprising: The classification module is used to classify value ranges from a pre-defined standard dictionary knowledge base; The comparison module is used to acquire clinical events and compare them with standard guidelines to determine the status of the clinical events based on their event content. The judgment module is used to judge and combine the standard dictionary value range attributes of the event content and the state of the clinical event to build a mapping relationship; The building module is used to construct knowledge graphs by adopting different redundancy strategies based on different mapping relationships.

[0018] Furthermore, to achieve the above objectives, the present invention also provides a unified architecture device for medical knowledge and database employing a redundancy strategy. The unified architecture device for medical knowledge and database employing a redundancy strategy includes: a memory, a processor, and a unified architecture program for medical knowledge and database stored in the memory and executable on the processor. When the unified architecture program for medical knowledge and database is executed by the processor, it implements the steps of the data calculation method described above.

[0019] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a unified architecture program for medical knowledge and database, wherein the unified architecture program for medical knowledge and database, when executed by a processor, implements the steps of the data storage method described above.

[0020] The beneficial effects of this invention are as follows: The unified architecture method for medical knowledge and databases using a redundancy strategy proposed in this invention can determine and combine data based on the standard dictionary value domain attributes of event content and the state of clinical events to construct mapping relationships, and then construct medical knowledge graphs based on different mapping relationships. This addresses and compensates for the variability of medical knowledge structures, where different classifications and mappings exist in different applications. It avoids the selection methods used by regular expressions and NLP when extracting items, instead employing different redundancy strategies to construct knowledge graphs for all different mapping relationships, thus achieving a unification of medical knowledge structure and database structure. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the hardware operating environment of the device involved in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the first embodiment of the unified architecture method for medical knowledge and databases employing a redundancy strategy according to the present invention. Figure 3 This is a flowchart illustrating the second embodiment of the unified architecture method for medical knowledge and databases employing a redundancy strategy according to the present invention. Figure 4 This is a flowchart illustrating the third embodiment of the unified architecture method for medical knowledge and databases employing a redundancy strategy according to the present invention. Figure 5 This is a flowchart illustrating the fourth embodiment of the unified architecture method for medical knowledge and databases employing a redundancy strategy according to the present invention. Figure 6 This is a flowchart illustrating the fifth embodiment of the unified architecture method for medical knowledge and databases employing a redundancy strategy according to the present invention.

[0022] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Implementation

[0023] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0024] The main solution of this invention is: Classify value ranges from a pre-defined standard dictionary knowledge base; Acquire clinical events and compare them with standard guidelines to determine the status of the clinical events based on their content; The mapping relationship is constructed by judging and combining the standard dictionary value range attributes of the event content and the status of the clinical event; Knowledge graphs are constructed using different redundancy strategies based on different mapping relationships.

[0025] Because existing knowledge graphs are often not comprehensive and are limited by the disease distribution of hospital patients, they have drawbacks at the application level and also prevent the unification of two knowledge graphs. This invention provides a solution that addresses and compensates for the diverse nature of medical knowledge structures, which exhibit different classifications and mappings in different applications. It enables the unification of medical knowledge structures and database structures. like Figure 1 As shown, Figure 1 This is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiments of the present invention.

[0026] The terminal in this invention embodiment can be a PC, or a smartphone, tablet computer, e-book reader, MP3 (Moving Picture Experts Group Audio Layer III) player, MP4 (Moving Picture Experts Group Audio Layer IV) player, portable computer, or other portable terminal devices with display functions.

[0027] like Figure 1As shown, the terminal may include: a processor 1001, such as a CPU; a communication bus 1002; a user interface 1003; a network interface 1004; and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0028] Optionally, the terminal may also include a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, and so on. Sensors may include light sensors, motion sensors, and other sensors. Specifically, light sensors may include ambient light sensors and proximity sensors. The ambient light sensor can adjust the display brightness according to the ambient light level, while the proximity sensor can turn off the display and / or backlight when the mobile terminal is moved to the ear. As a type of motion sensor, a gravity accelerometer can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity, and can be used for applications that identify the mobile terminal's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition functions (such as pedometers, taps), etc. Of course, the mobile terminal may also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which will not be elaborated here.

[0029] Those skilled in the art will understand that Figure 1 The terminal structure shown does not constitute a limitation on the terminal and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0030] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a unified architecture program for medical knowledge and databases.

[0031] exist Figure 1In the terminal shown, network interface 1004 is mainly used to connect to the backend server and communicate data with it; user interface 1003 is mainly used to connect to the client (user terminal) and communicate data with it; while processor 1001 can be used to call the unified architecture program of medical knowledge and database stored in memory 1005 and perform the following operations: Classify value ranges from a pre-defined standard dictionary knowledge base; Acquire clinical events and compare them with standard guidelines to determine the status of the clinical events based on their content; The mapping relationship is constructed by judging and combining the standard dictionary value range attributes of the event content and the status of the clinical event; Knowledge graphs are constructed using different redundancy strategies based on different mapping relationships.

[0032] Furthermore, the processor 1001 can call the unified architecture program of medical knowledge and database stored in memory 1005, and also perform the following operations: If the standard dictionary value range attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a stable state or a slow iteration state; Then, the current standard dictionary value range attribute and the state of the clinical event are constructed as the first mapping relationship.

[0033] Furthermore, the processor 1001 can call the unified architecture program of medical knowledge and database stored in the memory 1005, and also perform real-time calculations on the real-time data in the first data group to generate real-time data processing results. If the standard dictionary value range attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a fast iteration state; Then, a second mapping relationship is constructed between the current standard dictionary value domain attributes and the state to which the clinical event belongs.

[0034] Furthermore, the processor 1001 can call the unified architecture program of medical knowledge and database stored in memory 1005, and also perform the following operations: If the standard dictionary value range attribute of the event content is the hospital-level standard dictionary, and the state of the clinical event is a stable state or a slow iteration state; Then, a third mapping relationship is constructed between the current standard dictionary value range attributes and the state to which the clinical event belongs.

[0035] Furthermore, the processor 1001 can call the unified architecture program of medical knowledge and database stored in memory 1005, and also perform the following operations: If the standard dictionary value range attribute of the event content is the hospital-level standard dictionary, and the state of the clinical event is the fast iteration state; Then, a fourth mapping relationship is constructed between the current standard dictionary value range attributes and the state to which the clinical event belongs. The specific embodiments of the data storage device used in this invention are basically the same as the embodiments of the data storage method described below, and will not be repeated here.

[0036] Reference Figure 2 The first embodiment of the present invention provides a unified architecture method for medical knowledge and databases employing a redundancy strategy. The unified architecture method for medical knowledge and databases employing a redundancy strategy includes: Step S10: Classify the value range from the preset standard dictionary knowledge base; Step S20: Obtain clinical events and compare them with standard guidelines to determine the status of the clinical events based on their event content; Step S30: Based on the standard dictionary value range attributes of the event content and the state of the clinical event, a judgment and combination are made to construct a mapping relationship; Step S40: Construct a knowledge graph by adopting different redundancy strategies based on different mapping relationships.

[0037] In this embodiment, judgments and combinations can be made based on the standard dictionary value range attributes of event content and the state of clinical events to construct mapping relationships, and medical knowledge graphs can be built based on different mapping relationships. This addresses and compensates for the variability of medical knowledge structures, where different classifications and mappings exist in different applications. It avoids the selection methods used by regular expressions and NLP when extracting items, instead employing different redundancy strategies to construct knowledge graphs for all different mapping relationships, thus achieving a unification of medical knowledge structures and database structures.

[0038] The standard dictionary knowledge base includes national standard dictionaries (such as gender, ICD10, ICD11, etc.), provincial standard dictionaries (such as medical insurance fee catalogs, etc.), municipal standard dictionaries (such as municipal government procurement catalogs, etc.), and hospital-level standard dictionaries (such as in-hospital Western medicine diagnoses, in-hospital departments, etc.). The states of the clinical events include stable states, slow iteration states, and fast iteration states.

[0039] Specifically, the three states are explained as follows: The stable state is when the medical knowledge has remained unchanged for many years, and related peripheral knowledge points are also mostly stable, such as smallpox and the smallpox vaccine; in principle, there will be no future changes. The slow iterative state is when the medical knowledge changes, but the speed and direction of the change are directional and predictable, such as certain ultrasound, CT, and MRI examination methods. In principle, these examination methods will not change, but with the improvement of technology, certain attributes may advance, such as ultrasound evolving from black and white ultrasound to color ultrasound. The rapid iterative state is when the medical knowledge is a new understanding in the field or an innovative treatment method, and it is only clinically practiced on a small scale, such as a certain innovative surgical procedure.

[0040] Furthermore, refer to Figure 3 The second embodiment of the present invention provides a unified architecture method for medical knowledge and databases employing a redundancy strategy, based on the above. Figure 2 In the illustrated embodiment, the step of determining and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct a mapping relationship includes: Step S31: If the standard dictionary value domain attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a stable state or a slow iteration state, then the current standard dictionary value domain attribute and the state of the clinical event are constructed as a first mapping relationship.

[0041] In this embodiment, if the event content consists of "value range events corresponding to national, provincial, and municipal standard dictionaries" and "stable states and slow iteration states," the value ranges for such events are often quantifiable and clearly defined. At the medical level, hospitals can generally reach a consensus on these ranges, so the workload is controllable and limited, and the reusability is extremely high. We will adopt a simple exhaustive approach, mapping the content in medical books to the data in hospital information systems to ensure data accuracy. Furthermore, the mapping at the clinical level will be the primary focus of the graph.

[0042] Furthermore, refer to Figure 4 The third embodiment of the present invention provides a unified architecture method for medical knowledge and databases employing a redundancy strategy, based on the above. Figure 2 In the illustrated embodiment, the step of determining and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct a mapping relationship further includes: Step S32: If the standard dictionary value domain attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a fast iteration state, then the current standard dictionary value domain attribute and the state of the clinical event are constructed as a second mapping relationship.

[0043] In this embodiment, if the event content consists of "value domain events corresponding to the national standard dictionary, provincial standard dictionary, and municipal standard dictionary" and "rapid iteration status", such matters are often clearly defined. From the medical and clinical perspectives, all hospitals must reach a consensus before the work can be carried out. Therefore, although the degree of reuse of the work is almost non-existent and it does not exist in the books themselves, the importance of the event to the clinical practice is very high. We will also adopt the form of tracking and iteration, and directly use the value domains in the hospital information system for display.

[0044] Furthermore, refer to Figure 5 The fourth embodiment of the present invention provides a unified architecture method for medical knowledge and databases employing a redundancy strategy, based on the above. Figure 2 In the illustrated embodiment, the step of determining and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct a mapping relationship further includes: Step S33: If the standard dictionary value domain attribute of the event content is a hospital-level standard dictionary, and the state of the clinical event is a stable state or a slow iteration state, then a third mapping relationship is constructed between the current standard dictionary value domain attribute and the state of the clinical event.

[0045] In this embodiment, if the event content consists of "hospital-level standard dictionary" and "stable state, slow iteration state," such matters are often unrelated to clinical practice and are attributes influenced by administrative decisions of the hospital. Departmental setup is a typical example of this type of matter. Some of these matters are closely related to clinical practice, such as departments and medical disciplines. In this case, we will still adopt a simple exhaustive approach, mapping the content in medical books to the data in the hospital information system to ensure data accuracy. However, in the graph, we will retain both clinical and teaching aspects for display. There is another type of matter that has no clinical relevance. We will adopt a tracking and iterative approach, directly using the value range from the hospital information system for display.

[0046] Furthermore, refer to Figure 6 The fifth embodiment of the present invention provides a unified architecture method for medical knowledge and databases employing a redundancy strategy, based on the above. Figure 2 In the illustrated embodiment, the step of determining and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct a mapping relationship further includes: Step S34: If the standard dictionary value domain attribute of the event content is a hospital-level standard dictionary, and the state of the clinical event is a fast iteration state, then construct a fourth mapping relationship between the current standard dictionary value domain attribute and the state of the clinical event.

[0047] In this embodiment, if the event content consists of "hospital-level standard dictionary" and "rapid iteration status," such matters often belong to the cutting-edge field of medicine. Previous textbooks may only provide general descriptions, while clinical guidelines may be in stable iteration. At the medical level, hospitals are basically still in the research and academic exchange stage and have not yet reached a clear consensus, such as new drugs and treatments in clinical trials. For such matters, we will adopt the basic strategy of not extracting them.

[0048] In the above embodiments, different redundancy strategies can be used to construct knowledge graphs.

[0049] Redundancy Strategy 1 Step 1: Import the above categories of "National Standard Dictionary, Provincial Standard Dictionary, Municipal Standard Dictionary, and Institute Standard Dictionary" and "Stable State, Slow Iteration State" and "Stable State, Slow Iteration State, and Fast Iteration State" into the knowledge graph database in the form of node category Type.

[0050] Step 2: Import the above items into the knowledge graph database in the form of Nodes according to the above Type. If a Node has multiple Type categories, the node needs to be imported into all attributes repeatedly.

[0051] Redundancy Strategy 2 Step 1: Import the above information into the knowledge graph database in the form of Nodes.

[0052] Step 2: Import the above categories of content, using node attributes as part of the Node, into the knowledge graph database.

[0053] Redundancy Strategy 3 Step 1: Import the above items and their corresponding categories into the knowledge graph database as nodes.

[0054] Step 2: Categorize the above items and their corresponding categories, and connect them using Relationships to form a knowledge graph network.

[0055] Regarding the association of redundant strategy content, items with the same content in the above three types of redundancy strategies can be linked using the Relationship attribute. This Relationship attribute is defined as "same" and hardcoded into the database.

[0056] In addition, the content of items in the hospital information system and the content of items in the knowledge graph are data-connected and marked. The same items are marked as the same, and the mapped items are marked as mapped, thus creating a connection.

[0057] Data from the hospital information system is captured according to three categories of operational behaviors: patient-centered, doctor-centered, and disease-centered. The captured information is stored in the form of time series.

[0058] The above time series are combined and calculated according to the number of visits to determine the weights and related attributes of the time series.

[0059] The aforementioned time series is written back into the knowledge graph in the form of relationships. The knowledge graph is then iterated, and the weights calculated by merging are stored as attributes of the relationships.

[0060] This will enable the knowledge graph to be used in conjunction with the hospital information system, forming a stable interconnected model of medical knowledge structure and database structure.

[0061] After using the aforementioned "stable medical knowledge structure and database structure interoperability model" for a period of time, the accuracy of the knowledge graph iteration was manually verified. At this point, we can observe the directional iteration of the knowledge graph (i.e., the fitting effect of the time series weight superposition). For Nodes and Relationships with relatively high weights, we can directly enter the automation mode, meaning that manual processing is no longer required.

[0062] For Nodes and Relationships with relatively low weights, we enter manual verification mode, where two scenarios may occur: Scenario 1: If the data reflects the real medical scenario, that is, if the weight is small, then we can directly enter the automation mode, that is, no more manual processing.

[0063] Scenario 2: If the data fails to reflect the real medical scenario, i.e. the weight is small due to reasons such as hospital informatization, for example, the information systems in some departments are not connected to the hospital information system, then we should make a manual judgment and set up a periodic batch processing mode to supplement the application of automation.

[0064] The technical solution provided in this application addresses and compensates for the variability of medical knowledge structures, which involve different classifications and mappings in different applications. It avoids the selection methods used by regular expressions and NLP when extracting items, instead employing different redundancy strategies to construct the knowledge graph for all different mapping relationships, thus achieving a unification of medical knowledge structures and database structures.

[0065] Unlike traditional knowledge graph construction methods that require doctors to participate in feature engineering, this method uses a time-series extraction approach for medical events within the hospital system. This avoids the predicament of clinicians not understanding the medical knowledge structure and the compatibility with the database structure, as well as the ineffective participation of data annotation without understanding the technical institutions. It adopts a method of applying and judging medical knowledge directly based on the results generated by the technology, reducing the investment of doctors in information system construction, while also improving the usability of the system.

[0066] Furthermore, embodiments of the present invention also propose a unified architecture device for medical knowledge and databases employing a redundancy strategy, the unified architecture device for medical knowledge and databases employing a redundancy strategy comprising: The classification module is used to classify value ranges from a pre-defined standard dictionary knowledge base; The comparison module is used to acquire clinical events and compare them with standard guidelines to determine the status of the clinical events based on their event content. The judgment module is used to judge and combine the standard dictionary value range attributes of the event content and the state of the clinical event to build a mapping relationship; The building module is used to construct knowledge graphs by adopting different redundancy strategies based on different mapping relationships.

[0067] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the above-described apparatus and modules can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0068] Furthermore, embodiments of the present invention also propose a computer-readable storage medium storing a unified architecture program for medical knowledge and a database. When executed by a processor, the unified architecture program for medical knowledge and a database performs the following operations: Classify value ranges from a pre-defined standard dictionary knowledge base; Acquire clinical events and compare them with standard guidelines to determine the status of the clinical events based on their content; The mapping relationship is constructed by judging and combining the standard dictionary value range attributes of the event content and the status of the clinical event; Knowledge graphs are constructed using different redundancy strategies based on different mapping relationships.

[0069] Furthermore, when the unified architecture program for the medical knowledge and database is executed by the processor, it also performs the following operations: If the standard dictionary value range attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a stable state or a slow iteration state; Then, the current standard dictionary value range attribute and the state of the clinical event are constructed as the first mapping relationship.

[0070] Furthermore, when the unified architecture program for the medical knowledge and database is executed by the processor, it also performs the following operations: If the standard dictionary value range attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a fast iteration state; Then, a second mapping relationship is constructed between the current standard dictionary value domain attributes and the state to which the clinical event belongs.

[0071] Furthermore, when the unified architecture program for the medical knowledge and database is executed by the processor, it also performs the following operations: If the standard dictionary value range attribute of the event content is the hospital-level standard dictionary, and the state of the clinical event is a stable state or a slow iteration state; Then, a third mapping relationship is constructed between the current standard dictionary value range attributes and the state to which the clinical event belongs.

[0072] Furthermore, when the unified architecture program for the medical knowledge and database is executed by the processor, it also performs the following operations: If the standard dictionary value range attribute of the event content is the hospital-level standard dictionary, and the state of the clinical event is the fast iteration state; Then, the current standard dictionary value range attribute and the state of the clinical event are constructed as the fourth mapping relationship.

[0073] The specific embodiments of the computer-readable storage medium of the present invention are basically the same as the embodiments of the application software security vulnerability detection method described above, and will not be repeated here.

[0074] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0075] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0076] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0077] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A unified architecture method for medical knowledge and databases employing a redundancy strategy, characterized in that, The unified architecture approach for medical knowledge and databases employing a redundancy strategy includes the following steps: Classify value ranges from a pre-defined standard dictionary knowledge base; Acquire clinical events and compare them with standard guidelines to determine the status of the clinical events based on their content; The mapping relationship is constructed by judging and combining the standard dictionary value range attributes of the event content and the status of the clinical event; Knowledge graphs are constructed using different redundancy strategies based on different mapping relationships; The redundancy strategy includes: The event content and its corresponding classification are fully imported into the knowledge graph as nodes, and the event content and its corresponding classification are connected by relationships to form a knowledge graph network. Data connection tags are created by linking and marking the event content in the hospital information system and the event content in the knowledge graph. Identical tags are marked as identical, and mapped tags are marked as mapped, thus establishing a connection.

2. The unified architecture method for medical knowledge and databases employing a redundancy strategy as described in claim 1, characterized in that, The standard dictionary knowledge base includes national standard dictionaries, provincial standard dictionaries, municipal standard dictionaries, and institute-level standard dictionaries.

3. The unified architecture method for medical knowledge and databases employing a redundancy strategy as described in claim 2, characterized in that, The clinical events are classified into three states: stable state, slow iteration state, and fast iteration state.

4. The unified architecture method for medical knowledge and databases employing a redundancy strategy according to claim 3, characterized in that, The step of determining and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct a mapping relationship includes: If the standard dictionary value range attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a stable state or a slow iteration state; Then, the current standard dictionary value range attribute and the state of the clinical event are constructed as the first mapping relationship.

5. The unified architecture method for medical knowledge and databases employing a redundancy strategy according to claim 4, characterized in that, The step of determining and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct a mapping relationship further includes: If the standard dictionary value range attribute of the event content is a national standard dictionary, a provincial standard dictionary, or a municipal standard dictionary, and the state of the clinical event is a fast iteration state; Then, a second mapping relationship is constructed between the current standard dictionary value domain attributes and the state to which the clinical event belongs.

6. The unified architecture method for medical knowledge and databases employing a redundancy strategy according to claim 5, characterized in that, The step of determining and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct a mapping relationship further includes: If the standard dictionary value range attribute of the event content is the hospital-level standard dictionary, and the state of the clinical event is a stable state or a slow iteration state; Then, a third mapping relationship is constructed between the current standard dictionary value range attributes and the state to which the clinical event belongs.

7. The unified architecture method for medical knowledge and databases employing a redundancy strategy according to claim 6, characterized in that, The step of determining and combining the value range attributes of the event content standard dictionary and the state of the clinical event to construct a mapping relationship further includes: If the standard dictionary value range attribute of the event content is the hospital-level standard dictionary, and the state of the clinical event is the fast iteration state; Then, the current standard dictionary value range attribute and the state of the clinical event are constructed as the fourth mapping relationship.

8. A unified architecture device for medical knowledge and databases employing a redundancy strategy, characterized in that, The unified architecture device for medical knowledge and databases employing a redundancy strategy includes: The classification module is used to classify value ranges from a pre-defined standard dictionary knowledge base; The comparison module is used to acquire clinical events and compare them with standard guidelines to determine the status of the clinical events based on their event content. The judgment module is used to judge and combine the standard dictionary value range attributes of the event content and the state of the clinical event to build a mapping relationship; The building module is used to construct knowledge graphs by adopting different redundancy strategies based on different mapping relationships; The construction module is also used to completely import the event content and the corresponding event content classification into the knowledge graph in the form of nodes, and connect the event content and the corresponding event classification with relationships to form a knowledge graph network. Data connection tags are created by linking and marking the event content in the hospital information system and the event content in the knowledge graph. Identical tags are marked as identical, and mapped tags are marked as mapped, thus establishing a connection.

9. A unified architecture device for medical knowledge and databases employing a redundancy strategy, characterized in that, The unified architecture device for medical knowledge and database employing a redundancy strategy includes: a memory, a processor, and a unified architecture program for medical knowledge and database stored on the memory and executable on the processor. When the unified architecture program for medical knowledge and database is executed by the processor, it implements the steps of the unified architecture method for medical knowledge and database employing a redundancy strategy as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a unified architecture program for medical knowledge and databases, which, when executed by a processor, implements the steps of the unified architecture method for medical knowledge and databases employing a redundancy strategy as described in any one of claims 1 to 7.

Images