Medical knowledge base real-time updating method and system, medium and equipment

Abstract

The invention provides a medical knowledge base real-time updating method and system, a medium and equipment. The medical knowledge base real-time updating method comprises the steps of obtaining medical literature data in real time; analyzing the medical literature data to obtain first structured data; performing correlation analysis on the first structured data and second structured data in a medical knowledge base to obtain an analysis result; determining whether to update the medical knowledge base according to the analysis result; identifying the difference before and after the medical knowledge base is updated to obtain a difference identification result; distributing a unique version number for each difference in the difference identification result to obtain a version updating record; and based on the version updating record, performing data storage on each difference by adopting an incremental hash table technology. Compared with the prior art, the updating efficiency is higher, the omission risk cannot be generated, the difference data is stored through difference analysis and the incremental hash table technology, the data storage space requirement is remarkably reduced, and meanwhile the data access speed is increased.

Description

Technical Field

[0001] The present invention relates to the technical field of database updating, and in particular to a method, system, medium and device for real-time updating of a medical knowledge base. Background Art

[0002] In the current medical industry, the construction and application of knowledge bases are becoming increasingly important, because the rapid development of medical knowledge and the increasing amount of information require medical institutions to be able to efficiently and accurately manage and use this knowledge. The core purpose of the medical knowledge base is to centrally store and organize medical information, including disease diagnosis, treatment methods, drug information, the latest medical research results, etc., so that doctors and medical professionals can quickly obtain the required information and improve the efficiency and quality of diagnosis and treatment.

[0003] Existing technologies mostly rely on manual retrieval and updating for updating medical knowledge bases, which is inefficient and prone to missing important information. Summary of the invention

[0004] In view of the defects in the prior art, the purpose of the present invention is to provide a method, system, medium and equipment for real-time updating of a medical knowledge base.

[0005] A real-time updating method for a medical knowledge base provided according to the present invention includes: acquiring medical literature data in real time; analyzing the medical literature data to obtain first structured data; performing correlation analysis on the first structured data and second structured data in the medical knowledge base to obtain analysis results; determining whether to update the medical knowledge base based on the analysis results; identifying the differences before and after the medical knowledge base is updated to obtain difference identification results; assigning a unique version number to each difference in the difference identification results to obtain a version update record; based on the version update record, using incremental hash table technology to store data for each difference.

[0006] It is not difficult to understand that this application is to perform structured analysis on medical literature data, calculate the correlation of structured data in the medical knowledge base, and update the medical knowledge base based on the correlation. Compared with manual updates, this application is more efficient and does not incur the risk of omissions. In addition, this application performs a difference analysis on the medical knowledge base before and after the update, and assigns a version number to the updated medical knowledge base based on the difference analysis results, so as to reflect the update status of the medical knowledge base and facilitate understanding of the differences in data between different versions of the medical knowledge base. In addition, this application uses incremental hash table technology to store difference data, which significantly reduces the demand for data storage space and improves data access speed.

[0007] Furthermore, the analysis of the medical literature data to obtain the first structured data includes: performing named entity recognition on the medical literature data to obtain named entities; obtaining candidate entities through named entity screening, and classifying the candidate entities into different concept categories through a clustering algorithm; obtaining semantic relationships between candidate entities based on concept categories to obtain the first structured data.

[0008] Furthermore, the correlation analysis of the first structured data and the second structured data in the medical knowledge base is performed to obtain the analysis results, including: extracting similarity feature dimensions from the first structured data and the second structured data; obtaining weight values ​​corresponding to the similarity feature dimensions; and calculating similarity based on the weight values ​​and the substructured data.

[0009] Furthermore, determining whether to update the medical knowledge base based on the analysis results includes: if the first structured data is correlated with the second structured data in the medical knowledge base, updating the medical literature data to the corresponding position in the medical knowledge base; if the first structured data is not correlated with the second structured data in the medical knowledge base, stopping updating the medical literature data to the medical knowledge base.

[0010] Furthermore, the method for identifying the difference between the medical knowledge base before and after the update includes: generating Merkle trees for the medical knowledge base before and after the update respectively; identifying the changed data items by comparing the Merkle tree hash values ​​before and after the medical database is updated, and generating a difference identification result.

[0011] It is not difficult to understand that this application constructs a Merkle tree, uses the Merkle tree root hash value before and after the medical knowledge base is updated, determines the changed data items based on the difference in hashes, generates difference identification results, and clearly points out the specific differences between data versions. It provides precise difference data for version updates and data storage, effectively improving the accuracy and efficiency of data updates.

[0012] Furthermore, the method of assigning a unique version number to each difference in the difference identification result to obtain a version update record includes: based on the difference identification result, creating a new version node for each difference, recording the parent node information and change details of each version node, managing each version node in a linear update history chain, generating a version update record file, and recording the update history and version change information of each data item.

[0013] It is not difficult to understand that this application assigns a unique version number to each data change, ensuring the consistency and traceability of version control, making data rollback and version comparison operations feasible, and improving the flexibility and security of data management.

[0014] Furthermore, the data storage for each difference using incremental hash table technology based on version update records includes: mapping the difference data of each version into key-value pairs, where the key is the version number of the data item and the value is the difference content of the version relative to the previous version; adjusting the load factor and capacity parameters of the hash table, optimizing data retrieval and update efficiency, and generating differential data with optimized storage.

[0015] It is not difficult to understand that this application generates optimized storage differential data sets for different versions of the medical knowledge base, which only contains the differences between data versions, significantly reducing the data storage space requirements and improving data access speed. The optimized differential data set supports efficient data updates and fast version switching, providing a flexible and efficient data storage solution for the system.

[0016] A medical knowledge base real-time update system provided according to the present invention includes: a data processing and analysis module, which analyzes medical literature data to obtain first structured data; performs correlation analysis on the first structured data and second structured data in the medical knowledge base to obtain analysis results; a knowledge base integration module, which is used to determine whether to update the medical knowledge base based on the analysis results; a version control module, which is used to identify the differences before and after the medical knowledge base is updated to obtain difference identification results; assigns a unique version number to each difference in the difference identification results to obtain a version update record; based on the version update record, uses incremental hash table technology to store data for each difference.

[0017] According to a computer-readable storage medium storing a computer program provided by the present invention, the steps of the medical knowledge base real-time update method are implemented when the computer program is executed by a processor.

[0018] An electronic device provided according to the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the medical knowledge base real-time update method are implemented.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] This application is to perform structured analysis on medical literature data, calculate the correlation of structured data in the medical knowledge base, and update the medical knowledge base based on the correlation. Compared with manual updates, this application is more efficient and does not incur the risk of omissions. In addition, this application performs a difference analysis on the medical knowledge base before and after the update, and assigns a version number to the updated medical knowledge base based on the difference analysis results, so as to reflect the update status of the medical knowledge base and facilitate understanding of the differences in data between different versions of the medical knowledge base. In addition, this application uses incremental hash table technology to store difference data, which significantly reduces the demand for data storage space and improves data access speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0022] Figure 1 This is a flow chart of the real-time updating method of the medical knowledge base in the present invention;

[0023] Figure 2 This is a schematic diagram of the structure of the Merkle tree in the present invention;

[0024] Figure 3 A flowchart for obtaining the first structured data in the present invention;

[0025] Figure 4 It is a deep network model diagram in the present invention;

[0026] Figure 5 is a flow chart of the similarity calculation method in the present invention;

[0027] Figure 6 This is a system architecture diagram for real-time updating of the medical knowledge base in the present invention. DETAILED DESCRIPTION

[0028] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0029] The present invention discloses a real-time updating method for a medical knowledge base, comprising: analyzing medical literature data to obtain first structured data, determining the correlation between the first structured data and second structured data in the medical knowledge base; integrating the first structured data whose correlation meets preset conditions into the medical knowledge base to obtain an updated medical knowledge base; identifying the difference between versions of the medical knowledge base before and after the update to obtain a difference identification result; assigning a unique version number to each difference in the difference identification result to obtain a version update record; based on the version update record, using an incremental hash table technology to store data for each difference.

[0030] It is not difficult to understand that this application is to perform structured analysis on medical literature data, calculate the correlation of structured data in the medical knowledge base, and update the medical knowledge base based on the correlation. Compared with manual updates, this application is more efficient and does not incur the risk of omissions. In addition, this application performs a difference analysis on the medical knowledge base before and after the update, and assigns a version number to the updated medical knowledge base based on the difference analysis results, so as to reflect the update status of the medical knowledge base and facilitate understanding of the differences in data between different versions of the medical knowledge base. In addition, this application uses incremental hash table technology to store difference data, which significantly reduces the demand for data storage space and improves data access speed.

[0031] Reference Figure 1 As shown, a real-time updating method for a medical knowledge base includes:

[0032] Step 1: Obtain medical literature data in real time.

[0033] This application is to monitor and obtain medical data on the Internet in real time through automated scripts, for example, through RSS subscriptions and API calls to monitor various medical data sources in real time, including but not limited to: authoritative medical literature: including medical data, medical guidelines, papers, etc.; clinical databases: including electronic medical records, images, tests and other professional clinical business system data sets; and various Internet information: including medical information, question and answer data, etc. Of course, it can also be other data sources, which are not limited here.

[0034] Step 2: Analyze the medical literature data to obtain the first structured data.

[0035] In some embodiments, analyzing medical literature data to obtain first structured data includes: performing named entity recognition on the medical literature data based on a deep learning model to obtain named entities, classifying the named entities into different concepts through a clustering algorithm based on the obtained named entities, extracting relationships between different concepts to obtain semantic relationships between concepts, and obtaining the first structured data based on the concepts and the semantic relationships between concepts.

[0036] It is not difficult to understand that the present application performs named entity recognition on medical literature data and classifies the obtained named entities through a clustering algorithm, so as to summarize and extract key information from the massive content of medical literature data, thereby facilitating the subsequent comparison of medical literature data with the knowledge base. The present application further strengthens the structural division of medical literature data according to the semantic relationship between concepts by performing relationship extraction on concepts, so as to more clearly understand the logical structure of medical literature data and facilitate the final acquisition of the first structured data.

[0037] Step 3: Perform a correlation analysis on the first structured data and the second structured data in the medical knowledge base to obtain an analysis result.

[0038] In some embodiments, a correlation analysis may be performed on the first structured data and the second structured data in the medical knowledge base according to the similarity between the first structured data and the second structured data in the medical knowledge base to obtain an analysis result. The analysis result includes: the first structured data and the second structured data in the medical knowledge base are correlated, and the first structured data and the second structured data in the medical knowledge base are not correlated.

[0039] For example, the similarity between the first structured data and the second structured data in the medical knowledge base is calculated to obtain a similarity value. If the similarity value is greater than a first preset value, it is determined that the first structured data and the second structured data in the medical knowledge base are relevant; if the similarity value is not greater than the first preset value, it is determined that the first structured data and the second structured data in the medical knowledge base are not relevant. The first preset value can be adjusted according to actual conditions, for example, it can be 70%.

[0040] Step 4: Based on the analysis results, determine whether to update the medical knowledge base.

[0041] As can be seen from step 3, according to the analysis results, if the first structured data is correlated with the second structured data in the medical knowledge base, it is considered that the medical literature data is correlated with the content of the medical knowledge base, and the medical literature data needs to be updated to the corresponding position in the medical knowledge base. If the first structured data is not correlated with the second structured data in the medical knowledge base, it is considered that the medical literature data is not correlated with the content of the medical knowledge base, and it is not necessary to update the medical literature data to the medical knowledge base.

[0042] Step 5: Identify the differences before and after the medical knowledge base is updated and obtain the difference identification results.

[0043] In a specific implementation, identifying the difference before and after the medical knowledge base is updated and obtaining the difference identification result includes: generating Merkle trees for the medical knowledge base before and after the update, respectively, identifying the difference before and after the medical knowledge base is updated by executing the Merkle tree algorithm, including calculating a hash value for each data item, hashing the data block using the SHA-256 algorithm, and identifying the changed data item by comparing the hash value of the current knowledge base data with the hash value of the knowledge base data before the update, thereby generating a difference identification result.

[0044] In the embodiment of the present application, the structure of the Merkle tree is used to further illustrate how to identify differences. Figure 2 As shown in the figure, the Merkle tree is a hierarchical data structure that represents a set of data as an encrypted hash tree. The construction of the Merkle tree is a recursive process, starting from the bottom data block, and continuously calculating the hash value of the parent node upward until the root node is reached. Starting from the bottom, D0, D1, D2, and D3 are the data contained in the leaf nodes, that is, the value of the leaf nodes. Looking up, N0, N1, N2, and N3 are leaf nodes, which are the hash values ​​obtained by hashing the data (that is, D0, D1, D2, and D3); looking up, N4 and N5 are non-leaf nodes, which are the hash values ​​obtained by hashing N0 and N1 and the hash values ​​obtained by hashing N2 and N3. The root node is the hash value obtained by hashing N4 and N5, which is the root hash of this Merkle tree. When identifying the differences before and after the medical knowledge base is updated, the Merkle tree root hash values, the hashes corresponding to the non-leaf nodes, and the hashes corresponding to the leaf nodes are compared in turn before and after the medical knowledge base is updated, so as to quickly identify the nodes with different hash values, and then determine the changed data items, generate difference identification results, and clearly point out the specific differences before and after the medical knowledge base is updated, providing precise difference data for subsequent version updates and data storage, effectively improving the accuracy and efficiency of data updates.

[0045] Step 6: Assign a unique version number to each difference in the difference identification result to obtain a version update record.

[0046] Specifically, based on the difference identification results, a new version node is created for each difference, the parent node information and change details of each node are recorded, and each version node is managed in a linear update history chain manner to generate a version update record file to record the update history and version change information of each data item. For example, when medical literature data is updated to the medical knowledge base, multiple data items may have changed, and each data item needs to be assigned a unique version number.

[0047] Creating a new version node for each difference includes: executing the version control process based on the difference identification results, creating a new version node for each identified difference, recording the change details of the data item and its parent node information, and ensuring the integrity and traceability of the version history. Using a linear update history chain to manage each version node, assigning a unique version number to each data change to ensure the consistency and traceability of version control. Generating a version update record file that records the update history and version change information of each data item makes data rollback and version comparison operations feasible, improving the flexibility and security of data management.

[0048] Step 7: Based on the version update record, use incremental hash table technology to store data for each difference.

[0049] Specifically, the differential data of each version is mapped to a key-value pair, where the key is the version number of the data item and the value is the difference between the version and the previous version; the load factor and capacity parameters of the hash table are adjusted to optimize data retrieval and update efficiency, and generate optimized storage differential data. Based on the version update record, the incremental hash table technology is used for data storage, and the differential data of each version is mapped to a key-value pair, where the key is the version number and the value is the difference content. By adjusting the load factor and capacity parameters of the hash table, the data retrieval and update efficiency are optimized, and the optimized storage differential data is generated.

[0050] Incremental hash table technology is used for data storage based on version update records. Differential data storage uses a key-value pair format, where the key is the version number of the data item and the value is the difference between the version and the previous version. By adjusting the load factor and capacity parameters of the hash table, the storage structure and retrieval efficiency of the data are optimized. An optimized differential data set is generated, which only contains the differences between data versions, significantly reducing the data storage space requirements and improving the data access speed. The optimized differential data set supports efficient data updates and fast version switching, providing a flexible and efficient data storage solution for the system.

[0051] Specifically, refer to Figure 3 As shown, the process of analyzing the medical literature data in step 2 to obtain the first structured data includes:

[0052] Step 201: performing named entity recognition on medical literature data based on a deep learning model to obtain named entities;

[0053] Step 202: According to the obtained named entities, the named entities are classified into different concepts by using a clustering algorithm;

[0054] In a specific implementation, the method of classifying the named entities into different concepts in step 202 is as follows:

[0055] Named entities are classified into corresponding concept categories through clustering algorithms such as K-means. Specifically, the semantic representation features and co-occurrence relationship features of named entities are comprehensively utilized during clustering, and the two features are weighted and fused. Among them, the semantic representation features are obtained by extracting the embedding vector of the named entity through BERT, reflecting the contextual semantic information of the named entity; the co-occurrence relationship features characterize the common occurrence pattern of named entities in the text. For example, named entities appearing in the same sentence or paragraph may belong to similar concepts. For example, the named entities "gastric cancer", "liver cancer" and "lung cancer" are classified into the "cancer" concept category.

[0056] Specifically, the semantic representation features and contribution relationship features are further explained in combination with specific models. The semantic representation features use the pre-trained BERT to map words to vectors in a high-dimensional space. These vectors can capture the semantic similarities and relationships between words. The co-occurrence relationship features are obtained using the term frequency-inverse document frequency (TF-IDF), which measures the importance of a word in a document, that is, the product of the frequency of a word appearing in a document and the general importance of the word in the document collection. The semantic representation features and co-occurrence relationship features are fused to form a comprehensive feature representation. This can be achieved through simple feature concatenation, weighted summation, or more complex feature fusion methods. No limitation is made here.

[0057] Step 203: extract relations between different concepts to obtain semantic relations between concepts, and obtain first structured data based on the concepts and the semantic relations between concepts.

[0058] In a specific implementation, the concept relationship extraction method in step 203 includes:

[0059] The transfer-based dependency analysis performs dependency analysis on concepts to find the core concept; recursively search for all concepts that are parallel to the core concept to form a predicate list; for each predicate, find its subject and object based on the dependency relationship to form an information tuple; for an information tuple without a subject, find a parent tuple that is parallel to its predicate and has a subject. If the parent tuple exists, the subject of the information tuple is set to the subject of the parent tuple. If not found, it is not processed; the processing result is returned to obtain the grammatical relationship between concepts.

[0060] In the process of extracting concept relationships, for isolated concepts that cannot be extracted through the relationship between concept words, semantic relationships with other concepts are established based on their semantic similarity. Finally, the first structured data is obtained based on the obtained concepts and the semantics between the concepts.

[0061] In a specific embodiment, the method for performing named entity recognition on medical literature data based on a deep learning model in step 201 includes: using a deep learning model to determine the probability of different labels corresponding to each character of the medical literature data, determining the label of each character of the medical literature data based on the probability of different labels corresponding to each character of the medical literature data, thereby determining the label sequence of the medical literature data, and determining the named entity of the medical literature data based on the determined label sequence of the medical literature data.

[0062] Taking BIO annotation as an example, different labels corresponding to each character include B, I, and O, where B and I together represent entities, B represents the starting position of a named entity, I represents the position inside the named entity, and O represents a non-entity or non-target category entity. For example, "viruses can cause colds" is marked as:

[0063] sick poison meeting guide To feel Risk Annotation B I 0 B I B I

[0064] Table 1 BIO annotation examples

[0065] like Figure 4 As shown, a specific deep learning model structure is disclosed for performing named entity recognition on medical literature data. Specifically, the deep learning model may include: an embedding layer 101, a neural network layer 102, wherein the neural network layer 102 includes a feature extraction layer 1021 and a fully connected layer 1022.

[0066] The embedding layer 101 is used to convert each character of the medical literature data into a word vector and a word vector to which each character belongs, and concatenate the word vector and the word vector to obtain a concatenated vector.

[0067] Specifically, the embedding layer 101 is used to obtain input medical literature data, and convert each character of the medical literature data into a word vector and a word vector to which each character belongs. The method used may be word embeddings, such as word2vec, glovec, fasttext, etc., which maps each word to a real vector, and these vectors are semantically related.

[0068] The feature extraction layer 1021 is used to determine a splicing feature vector by performing feature extraction on the splicing vector.

[0069] In some embodiments, since medical texts contain a large number of special entities such as professional terms and proper nouns, contextual information is needed to accurately extract these entities. Therefore, the neural network layer 102 of the present application can adopt a bidirectional long short-term memory (BiLSTM) network. The BiLSTM network can fully consider the contextual semantic information of the electronic health record data and avoid the long-distance dependency problem of the medical text, thereby obtaining a concatenated feature vector with richer information, thereby improving the accuracy of the fully connected layer 1022 in determining the probability that each character of the electronic health record data corresponds to a different label.

[0070] The fully connected layer 1022 is used to obtain the probability of different labels corresponding to each character of the electronic health record data according to the concatenated feature vector.

[0071] Specifically, the fully connected layer 1022 maps the concatenated feature vector to a probability distribution corresponding to each label through an activation function, and then normalizes the probability distribution of different labels corresponding to each character to generate the probability of different labels corresponding to each character. According to the combination of the labels with the highest probability for each character, the label sequence corresponding to the electronic health record data can be obtained, and the named entity identified from the electronic health record data can be obtained according to the label sequence.

[0072] In a specific embodiment, referring to Figure 5 As shown, the method for calculating the similarity between the first structured data and the second structured data includes:

[0073] Step S301, extracting similarity feature dimensions from the first structured data and the second structured data. For example: for the literature related to COPD, select "age, gender, BMI, number of acute exacerbations within one year, smoking history, smoking pack-years, recent cough, recent sputum, recent chest tightness, recent wheezing, recent shortness of breath, past shortness of breath, nocturnal paroxysmal dyspnea, bilateral lower limb edema, palpitations, blood eosinophil count, sputum eosinophil count and comorbidities (multiple)" and other dimensions as similarity feature dimensions, and the structured data under these dimensions can be extracted from the first structured data and the second structured data as sub-structured data.

[0074] Step S302, obtaining the weight value corresponding to the similarity feature dimension.

[0075] The determined similarity feature dimensions are used as similarity comparison nodes. The number of similarity feature dimensions is generally multiple. In this step, a corresponding weight value can be assigned to each node according to the influence of each similarity feature dimension on the similarity.

[0076] Step S303, calculating similarity based on weight values ​​and substructured data. In this step, similarity can be calculated according to weight values ​​assigned to each similarity feature dimension and substructured data under each similarity feature dimension, for example, similarity can be calculated by weighted summing of each substructured data. It can also be: obtaining the intersection value and union value of the substructured data of the first structure data and the second structured data; then after obtaining the weight values ​​assigned to each similarity feature dimension, using the intersection value of each substructured data and the corresponding weight value to perform weighted calculation to obtain a weighted intersection value, using the union value of each substructured data and the weight value to perform weighted calculation to obtain a weighted union value, and finally taking the ratio of the weighted intersection value to the weighted union value as the similarity.

[0077] The following uses a specific case to further illustrate how to use the ratio of the weighted intersection value to the weighted union value as the similarity. Assume that each substructured data of the first structured data is represented as set A, and each substructured data of the second structured data is represented as set B. Then, we can first find the intersection of set A and set B, perform weighted summation on each item in the intersection to obtain the weighted intersection value, then find the union of set A and set B, perform weighted summation on each item in the union to obtain the weighted union value, and finally divide the weighted intersection value by the weighted union value to obtain the similarity between the first structured data and the second structured data, which can be expressed by the following formula:

[0078]

[0079] Wherein, S represents similarity, wi represents the product of the i-th data item in the intersection of set A and set B and the corresponding weight value, and wj represents the product of the j-th data item in the union of set A and set B and the corresponding weight value. This embodiment can accurately calculate the similarity of the structured data of each electronic medical record through the weighted intersection value and weighted union value of each substructured data of each electronic medical record, providing a data basis for accurately calculating the similarity between electronic medical records.

[0080] Reference Figure 6 As shown, a real-time updating system of a medical knowledge base is used to execute the above-mentioned electronic health record structured processing method. The system includes:

[0081] A data processing and analysis module, used to analyze the medical literature data to obtain the first structured data and the correlation between the first structured data and the second structured data in the medical knowledge base;

[0082] A knowledge base integration module, used to integrate the first structured data whose relevance meets the preset conditions into the medical knowledge base to obtain a new version of the medical knowledge base;

[0083] The version control module is used to identify the difference between the versions of the medical knowledge base before and after the update to obtain the difference identification results; assign a unique version number to each difference in the difference identification results to obtain a version update record; based on the version update record, use incremental hash table technology to store data for each difference.

[0084] In other embodiments, the medical knowledge base real-time update system also includes a user interface module, a version control system, a user feedback and quality control module, a system integration and coordination module, and a deployment and maintenance module.

[0085] The user interface module is used to provide a user interface for users to view the update history, differences and knowledge base status. The version control system is used to track the change history of the knowledge base and record the detailed differences of each update. It implements differential storage and version comparison algorithms and provides historical version recovery functions. The version information and change records are transmitted to the user interface module for users to query. The user feedback and learning module is used to collect user feedback, perform quality control, ensure the accuracy and reliability of knowledge base information, implement user feedback mechanism, and verify and correct errors or omissions reported by users. The system integration and testing module is used to ensure that the various modules of the system work together and conduct system testing and performance evaluation. Through the interface standardization and data synchronization mechanism between modules, integration testing and stress testing are carried out. At the same time, the system integration and test results are fed back to each module to guide system optimization and upgrade. The deployment and maintenance module is responsible for the deployment, monitoring and maintenance of the system to ensure the stable operation of the system. Through the integrated monitoring system, the system performance indicators are tracked in real time to implement the automatic deployment and rollback mechanism. At the same time, the system operation data and maintenance logs are collected for continuous improvement of the system.

[0086] It should be understood that the embodiments of the present invention can be implemented in hardware, software or a combination thereof. Software can be stored in a volatile or non-volatile storage device (regardless of whether the data is deletable or rewritable) like a ROM, in a memory like a RAM, a memory chip, a device or an integrated circuit, or in a storage medium on which data can be optically or magnetically recorded and from which data can be read by a machine (e.g., a computer), such as a compact disc (CD), a digital versatile disc (DVD), a disk, or a tape. Moreover, the embodiments of the present invention can be implemented in a computer or portable terminal having a controller and a memory, and the memory is an example of a non-temporary computer-readable storage medium suitable for storing one or more programs including commands for implementing the embodiments of the present invention. Therefore, the present invention includes a program having a code for implementing the device or method defined by the claims, and a machine-readable non-temporary storage medium storing the program. The program can be transferred electrically by a medium such as a communication signal transmitted via a wired or wireless connection, and the program and its equivalent are included in the present invention.

[0087] The device may receive a program from a program providing device connected via a cable or wirelessly and store the program. The program providing device may include a program containing commands for implementing the embodiments of the present invention, a memory for storing information required by the embodiments of the present invention, a communication module for communicating with the mobile device via a cable or wirelessly, and a controller for transmitting the program to the device automatically or upon request of the device.

[0088] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0089] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A real-time updating method for a medical knowledge base, characterized in that: include: Real-time access to medical literature data; Analyze the medical literature data to obtain the first structured data; Performing correlation analysis on the first structured data and the second structured data in the medical knowledge base to obtain an analysis result; Determine whether to update the medical knowledge base based on the analysis results; Identify the differences before and after the medical knowledge base is updated and obtain the difference identification results; Assign a unique version number to each difference in the difference identification result to obtain a version update record; Based on the version update record, the incremental hash table technology is used to store the data of each difference.

2. The real-time updating method of medical knowledge base according to claim 1, characterized in that: The analyzing of the medical literature data to obtain the first structured data includes: Perform named entity recognition on medical literature data to obtain named entities; Candidate entities are obtained through named entity screening, and the candidate entities are classified into different concept categories through clustering algorithms; The semantic relationship between the candidate entities based on the concept category is obtained to obtain the first structured data.

3. The real-time updating method of medical knowledge base according to claim 1, characterized in that: The correlation analysis of the first structured data and the second structured data in the medical knowledge base is performed to obtain the analysis results including: extracting similarity feature dimensions from the first structured data and the second structured data; Obtaining weight values ​​corresponding to similarity feature dimensions; Calculate similarity based on weight values ​​and substructured data.

4. The real-time updating method of medical knowledge base according to claim 3, characterized in that: Determining whether to update the medical knowledge base according to the analysis result includes: If the first structured data is relevant to the second structured data in the medical knowledge base, the medical literature data is updated to the corresponding position in the medical knowledge base; if the first structured data is not relevant to the second structured data in the medical knowledge base, the updating of the medical literature data to the medical knowledge base is stopped.

5. The real-time updating method of medical knowledge base according to claim 1, characterized in that: The method for identifying the difference between the medical knowledge base before and after updating includes: Generate Merkle trees for the medical knowledge base before and after the update; By comparing the Merkle tree hash values ​​before and after the medical database is updated, the changed data items are identified and the difference identification results are generated.

6. The real-time updating method of medical knowledge base according to claim 1, characterized in that: The step of assigning a unique version number to each difference in the difference identification result to obtain a version update record includes: Based on the difference identification results, a new version node is created for each difference, the parent node information and change details of each version node are recorded, and each version node is managed in a linear update history chain manner. A version update record file is generated to record the update history and version change information of each data item.

7. The real-time updating method of medical knowledge base according to claim 1, characterized in that: The method of storing data for each difference using an incremental hash table technology based on the version update record includes: Map the difference data of each version into key-value pairs, where the key is the version number of the data item and the value is the difference between the version and the previous version; Adjust the load factor and capacity parameters of the hash table to optimize data retrieval and update efficiency and generate differential data for optimized storage.

8. A medical knowledge base real-time update system, characterized in that: include: A data processing and analysis module analyzes the medical literature data to obtain the first structured data; Performing correlation analysis on the first structured data and the second structured data in the medical knowledge base to obtain an analysis result; A knowledge base integration module is used to determine whether to update the medical knowledge base based on the analysis results; A version control module is used to identify the differences before and after the medical knowledge base is updated and obtain difference identification results; A unique version number is assigned to each difference in the difference identification result to obtain a version update record; based on the version update record, an incremental hash table technology is used to store data for each difference.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the real-time updating method of the medical knowledge base according to any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by a processor, the steps of the real-time updating method of the medical knowledge base according to any one of claims 1 to 7 are implemented.

Images