Medical case management system and method based on artificial intelligence large model

Abstract

The invention relates to the technical field of medical case management, and discloses a medical case management system and method based on an artificial intelligence large model, and the system comprises a case receiving module which is used for receiving an electronic medical case of a patient from a hospital or a department, carrying out the data recognition of the received electronic medical case of the patient, and transmitting the data to a server; data using the case management system is directly input, data not using the case management system is marked as to-be-processed data, and the module supports real-time data transmission and batch import so as to guarantee the integrity and timeliness of case data. According to the method, semantic tag extraction and matching are performed on existing database data and to-be-converted data by adopting a natural language processing technology, so that the problem of interoperability caused by non-uniform data codes and formats among different case systems is effectively solved, and intelligent management and standardized processing of the whole process of electronic medical cases of patients are realized; and the data processing efficiency and the information integration accuracy are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical case management, and in particular to a medical case management system and method based on an artificial intelligence large model. Background Art

[0002] A medical case management system is primarily responsible for the comprehensive management of medical cases. Its core goal is to process patients' medical information in a standardized, systematic, and efficient manner, supporting clinical decision-making, medical services, and management. A medical case management system collects and enters case data and manages it through multi-dimensional classifications by disease type, disease category, department, treatment phase, and timeline. It supports the archiving and filing of cases, facilitating subsequent query and tracing. Rapid retrieval and efficient management reduce the paperwork burden on doctors and nurses and facilitate multi-departmental collaboration and information sharing.

[0003] However, currently, common medical case management systems lack effective interoperability. Case data entry standards, formats, and coding systems vary across medical institutions, and even within the same institution, resulting in incompatibility between systems across hospitals and even within different departments within the same hospital. This makes cross-institutional access to medical records difficult. Patients often need to bring paper medical records for referrals and re-enter them into the new department's medical case management system. This information silo phenomenon results in inefficient medical case management entry when transferring between hospitals or departments, impacting the timeliness of medical data and the continuity of diagnosis and treatment. Summary of the Invention

[0004] In response to the problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a medical case management system and method based on an artificial intelligence big model, so that when processing electronic medical cases with inconsistent data standards, the big model natural language processing technology can be used to achieve automatic understanding of case data between different medical institutions and departments, break down information silos, and ensure efficient sharing of case information during referral and follow-up visits.

[0005] In order to achieve the above-mentioned purpose, the present invention provides the following technical solution: a medical case management system based on an artificial intelligence large model, comprising: The case receiving module is used to receive electronic medical records of patients from hospitals or departments, identify the received electronic medical records of patients, directly enter the data that uses this case management system, and mark the data that does not use this case management system as pending data. This module supports real-time data transmission and batch import to ensure the integrity and timeliness of case data; The data comparison module is used to compare the data to be processed with the existing data in the case management system database. The compared data includes patient identification, case information matching, treatment stage time, treatment department information and other data related to the patient case. The data to be processed is divided into usable data and unusable data according to the difference degree of comparison; A data revision module, which is used to perform deep semantic analysis of unavailable data using natural language processing technology, and to standardize the unavailable data based on the existing data in the case management system database, so that the unavailable data is converted into usable data; The case entry module is used to build complete patient electronic medical records using available data, realize automated case entry and update, ensure data security through permission management and log records, and record the entire process of case entry and modification.

[0006] In some embodiments, in the data comparison module, the specific method of dividing the data to be processed into usable data and unusable data includes: obtaining data in the data to be processed that can be interoperable with existing data in the case management system database, classifying the interoperable data as usable data, and classifying the remaining data that cannot be interoperable as unusable data.

[0007] In some embodiments, a specific method of performing standardized conversion on unavailable data based on existing data in the case management system database includes: using natural language processing technology to semantically label the existing data in the case management system database, marking the semantic label as a label template, and using natural language processing technology to extract the semantic label corresponding to the unavailable data, matching the semantic label of the unavailable data with the label template, and performing corresponding standardized conversion on the unavailable data based on the matching results.

[0008] In some embodiments, when there exists a semantic label in the label template that is exactly the same as the semantic label of the unavailable data, the unavailable data is converted into an existing data format with the same semantics as the unavailable data and marked as available data; when there does not exist a semantic label in the label template that is exactly the same as the semantic label of the unavailable data, a semantic matching judgment strategy is executed.

[0009] In some embodiments, the semantic matching judgment strategy includes obtaining all semantic labels corresponding to unavailable data, and comparing all of its semantic labels with the semantic labels in the label template, obtaining the semantic label in the unavailable data with the highest similarity with the label template, marking the semantic label as the most similar semantic, setting a similarity threshold, obtaining the similarity value between the most similar semantic and the label template, comparing the similarity value with the similarity threshold, and making corresponding responses based on the comparison results.

[0010] In some embodiments, when the similarity value is greater than or equal to the similarity threshold, the unavailable data is standardized and converted according to the semantic label in the label template corresponding to the most similar semantics, and the converted data is marked as available data; when the similarity value is less than the similarity threshold, the unavailable data is marked as note data; a note area is created in this case management system, and all unavailable data marked as note data are placed in the note area in their original data format, and the note data can be viewed in the note area of ​​this case management system.

[0011] In some embodiments, a specific method for obtaining the semantic similarity between the unavailable data and the label template includes: converting each semantic label extracted from the unavailable data and each semantic label in the label template into a high-dimensional vector representation through a pre-trained language model, and calculating the cosine similarity between the vector of each semantic label in the unavailable data and the vector of each semantic label in the label template. The numerical range of the calculated result will be between 0 and 1, and the higher the value, the closer the semantics.

[0012] In some embodiments, a data volume threshold is set, and when the data revision module is executed, if the similarity value is less than the similarity threshold and the similarity is greater than 0, the data volume of the currently available data is obtained, and the data volume of the currently available data is compared with the data volume threshold. If the data volume of the currently available data is greater than or equal to the data volume threshold, the unavailable data is still marked as remark data, and no additional operations are performed; if the data volume of the currently available data is less than the data volume threshold, the marking of the unavailable data as remark data is canceled, and the unavailable data is subjected to corresponding standardized conversion according to the semantic label in the label template corresponding to the most similar semantics, and the converted data is marked as available data, and the subsequent case entry module is executed.

[0013] The present invention also provides the following technical solution: a medical case management method based on an artificial intelligence large model, the method comprising the following steps: Receive electronic medical records of patients from hospitals or departments, identify the received electronic medical records of patients, directly enter the data that uses this case management system, and mark the data that does not use this case management system as pending data. This module supports real-time data transmission and batch import to ensure the integrity and timeliness of case data; Compare the data to be processed with the existing data in the case management system database. The compared data include patient identification, case information matching, treatment stage time, treatment department information and other data related to the patient case. The data to be processed is divided into usable data and unusable data according to the difference between the comparisons. Use natural language processing technology to perform deep semantic analysis on unavailable data, and standardize and convert unavailable data based on existing data in the case management system database to convert unavailable data into usable data; Use available data to build complete electronic patient medical records, automate case entry and updates, and ensure data security through permission management and logging, recording the entire process of case entry and modification.

[0014] The present invention further provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the above-mentioned medical case management system based on the artificial intelligence big model.

[0015] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects: First, the present invention uses natural language processing technology to extract and match semantic tags between existing database data and data to be converted, effectively solving the interoperability problem caused by inconsistent data encoding and format between different case systems, and realizing intelligent management and standardized processing of the entire process of patient electronic medical records, greatly improving data processing efficiency and information integration accuracy.

[0016] Secondly, while ensuring the accuracy of automatic conversion, the present invention sets a similarity threshold and a data volume threshold strategy. When the similarity is lower than the threshold but the data volume is insufficient to affect the integrity of the case, remedial measures are actively taken to standardize and convert the data, rather than directly marking it as remark data, to ensure the overall integrity of the case data.

[0017] Third, the design of the backup notes area designed by the present invention not only retains the original data for subsequent tracking and manual review, but also provides a basis for the system to continuously optimize semantic label templates and matching strategies, thereby gradually improving data conversion accuracy and system adaptability, thereby achieving a balance between data quality and data integrity. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Schematic diagram of the system module of the present invention; Figure 2 Schematic diagram of the method of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the elements may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0021] The present invention provides a medical case management system based on artificial intelligence big model, such as Figure 1 Shown, including: The case receiving module is used to receive electronic medical records of patients from hospitals or departments, identify the received electronic medical records of patients, directly enter the data that uses this case management system, and mark the data that does not use this case management system as pending data. This module supports real-time data transmission and batch import to ensure the integrity and timeliness of case data; The data comparison module is used to compare the data to be processed with the existing data in the case management system database. The compared data includes patient identification, case information matching, treatment stage time, treatment department information and other data related to the patient case. The data to be processed is divided into usable data and unusable data according to the difference degree of comparison; A data revision module, which is used to perform deep semantic analysis of unavailable data using natural language processing technology, and to standardize the unavailable data based on the existing data in the case management system database, so that the unavailable data is converted into usable data; The case entry module is used to build a complete electronic medical record of a patient using available data, automating case entry and updates, and ensuring data security through permission management and logging, recording the entire process of case entry and modification; In the data comparison module, the specific method of dividing the data to be processed into usable data and unusable data includes: obtaining data in the data to be processed that can be interoperable with the existing data in the case management system database, dividing the interoperable data into usable data, and dividing the remaining data that cannot be interoperable into unusable data.

[0022] At the same time, the specific method of standardizing the unavailable data based on the existing data in the case management system database includes: using natural language processing technology to semantically label the existing data in the case management system database, and marking the semantic label as a label template, and using natural language processing technology to extract the semantic label corresponding to the unavailable data, matching the semantic label of the unavailable data with the label template, and performing corresponding standardization conversion on the unavailable data according to the matching results. Specifically, when the label template contains a semantic label that is exactly the same as the semantic label of the unavailable data, it means that after the semantic label of the unavailable data is extracted, existing data with the same semantics as the unavailable data can be found in the database of this case management system, indicating that the reason why the unavailable data cannot be interoperable with the existing data in the database in the data comparison module is that different case systems use different data or encoding formats. The unavailable data is converted into an existing data format with the same semantics as the unavailable data and marked as available data; and when the label template does not contain a semantic label that is exactly the same as the semantic label of the unavailable data, it means that after the semantic label of the unavailable data is extracted, existing data with the same semantics as the unavailable data cannot be found in the database of this case management system, indicating that the reason why the unavailable data cannot be interoperable with the existing data in the database in the data comparison module is that there is no data in the existing database with the same semantics as the unavailable data, and the semantic matching judgment strategy is executed; For example, the corresponding unavailable data is set to be image data, which records the changes in the patient's blood pressure, and computer vision technology is used to convert the image content into a text description (for example, through image annotation and image description generation), obtain text reflecting the image content, and then apply NLP technology to the generated text description to extract the corresponding semantic label, and set the semantic label extracted from the unavailable data to be blood pressure detection. It is set that there is cardiovascular medicine detection data in the existing data in the case management system database. The data uses a textual data format and is labeled with a semantic label of blood pressure detection. Therefore, after matching the semantic label of the unavailable data with the label template, there will be a phenomenon that the label template contains the semantic label of the unavailable data and the same semantic label as the unavailable data. Then, the image content semantics in the image data are converted into a textual data format and marked as available data.

[0023] The semantic matching judgment strategy includes obtaining all semantic labels corresponding to unavailable data, comparing all its semantic labels with the semantic labels in the label template, obtaining the semantic label with the highest similarity between the unavailable data and the label template, marking the semantic label as the most similar semantic, setting a similarity threshold, obtaining a similarity value between the most similar semantic and the label template, comparing the similarity value with the similarity threshold, and making a corresponding response based on the comparison result. Specifically, when the similarity value is greater than or equal to the similarity threshold, it means that although the semantic label of the unavailable data fails to match the exact same label in the label template, there is a label in the label template that is sufficiently close to the most similar semantic. In this case, the unavailable data is subjected to corresponding normalization conversion based on the semantic label in the label template corresponding to the most similar semantic, and the converted data is marked as available data. When the similarity value is less than the similarity threshold, it means that the semantic label of the unavailable data fails to match the exact same label in the label template, and there is no label in the label template that is sufficiently close to the most similar semantic, which means that the patient's electronic medical records received this time contain case data not adopted by this case management system. In this case, the unavailable data is marked as note data. A notes area is created within this case management system. All unavailable data marked as notes is placed in the notes area in its original format. The notes data can be viewed in the notes area within the case management system. The creation and purpose of the notes area primarily enhances the system's management and fault tolerance for abnormal, special, or unsuccessfully standardized data. Unavailable data that fails to meet semantic matching criteria is stored in the notes area in its original format, preventing data from being discarded or lost, thus ensuring the integrity of the case data. Furthermore, the notes data retains its original information, facilitating subsequent tracking and auditing, enabling data traceability and facilitating investigation of the causes of data anomalies. Data in the notes area often represents data that the system was unable to automatically convert using the current template and threshold settings. This data provides valuable reference for medical staff or data managers. After manual review, they can supplement necessary information and continuously optimize and expand label templates and semantic matching strategies, thereby improving the accuracy of future data conversions and the system's adaptability.

[0024] The specific method of obtaining the semantic similarity between unavailable data and the label template includes: each semantic label extracted from the unavailable data and each semantic label in the label template are converted into a high-dimensional vector representation through a pre-trained language model (such as BERT, Sentence-BERT). The converted vector can capture the deep features in the text semantics. The cosine similarity is calculated for the vector of each semantic label in the unavailable data and the vector of each semantic label in the label template. The numerical range of the calculation result will be 0 to 1 (for non-negative similarity measurement). The higher the value, the closer the semantics. Assuming the calculation result is 0.9, it means that the similarity value is 90%. For an unavailable data, all its extracted semantic labels will be calculated in turn for similarity with each label in the label template, and then the one with the highest similarity is selected from these results and marked as the most similar semantics.

[0025] Set the data volume threshold. When executing the data revision module, if the similarity value is less than the similarity threshold and the similarity is greater than 0, obtain the data volume of the currently available data and compare the data volume of the currently available data with the data volume threshold. If the data volume of the currently available data is greater than or equal to the data volume threshold, it indicates that the electronic medical records of the patient received this time have sufficient available data to be entered into this case management system. In this case, the unavailable data will still be marked as remark data and no additional operations will be performed. If the data volume of the currently available data is less than the data volume threshold, it indicates that the electronic medical records of the patient received this time do not have sufficient available data to be entered into this case management system and cannot constitute valid patient medical case data for reference, then the unavailable data will not be marked as remark data. Instead, the unavailable data will be standardized according to the semantic label in the label template corresponding to the most similar semantics, and the converted data will be marked as available data, and the subsequent case entry module will be executed. Through the above operations, when the system receives insufficient available data for direct entry in the patient's electronic medical records, some unavailable data with similarity values ​​below the similarity threshold but with a certain degree of similarity will be forced to undergo standardized conversion, which can ensure that the constructed case data will not be incomplete due to insufficient data volume, thereby improving the reference value of the entire case record and achieving a balance between data quality and data integrity. Under normal circumstances, the system uses a higher similarity threshold to ensure that the automatically converted data has a higher semantic matching accuracy; however, in the case of insufficient case data volume, by setting a data volume threshold to determine in advance that the current available data is insufficient, it allows those data with similarity values ​​that do not meet the highest requirements but still have a certain degree of semantic proximity to be converted into available data, thereby compensating for the problem of incomplete case information review due to excessively high fault tolerance requirements and avoiding the omission of key clinical information.

[0026] In general, the present invention aims to design a medical case management system based on a large artificial intelligence model. When processing electronic medical cases with inconsistent data standards, there is a problem that the inconsistent system standards cause information islands and affect the normal entry and management of cases. The present invention integrates multiple modules such as case reception, data comparison, data revision and case entry to achieve intelligent management and standardized processing of the entire process of patient electronic medical cases, greatly improving data processing efficiency and information integration accuracy. It effectively solves the problem of inconsistent case entry standards, formats and coding systems among various medical institutions and different departments within the same institution, realizes standardized and systematic processing of medical information, breaks the data islands of traditional medical systems, realizes information interconnection across institutions and departments, and improves efficient collaboration in each link of case data collection, entry, archiving, retrieval and tracing. The standardized conversion method of the present invention uses natural language processing technology to extract and match semantic tags of existing database data and data to be converted, effectively solving the interoperability problem caused by inconsistent data coding and format between different case systems. The system can convert data of varying formats and encodings into a unified, standardized format, thereby improving data integration and interoperability. By matching identical semantic labels, it ensures semantic consistency between existing case data and newly input data. By calculating high-dimensional vector cosine similarity between all semantic labels of unavailable data and each label in the label template, it achieves automated and accurate semantic matching. This allows data to be successfully converted to a standard format even if there are differences in format or encoding, as long as the semantics are similar, thereby improving the system's data integration and interoperability. Furthermore, while ensuring automatic conversion accuracy, the system also proactively implements remedial measures to standardize data conversion when the similarity falls below the threshold but the data volume is insufficient, impacting case integrity. This, in turn, helps ensure the overall integrity and clinical reference value of case data. Furthermore, the design of a backup note area preserves the original data for subsequent tracking and manual review while providing the system with a basis for continuous optimization of the semantic label template and matching strategy, thereby gradually improving data conversion accuracy and system adaptability, thereby achieving a balance between data quality and data integrity.

[0027] The present invention provides a medical case management method based on artificial intelligence big model, such as Figure 2 As shown, the method includes the following steps: The first step is to receive electronic medical records of patients from hospitals or departments, identify the data received, directly enter the data that uses this case management system, and mark the data that does not use this case management system as pending data. This module supports real-time data transmission and batch import to ensure the integrity and timeliness of case data; The second step is to compare the data to be processed with the existing data in the case management system database. The compared data includes patient identification, case information matching, treatment stage time, treatment department information and other data related to the patient case. The data to be processed is divided into usable data and unusable data based on the difference between the comparisons. The third step is to use natural language processing technology to perform deep semantic analysis on the unavailable data and standardize the unavailable data based on the existing data in the case management system database to convert the unavailable data into usable data; The fourth step is to use available data to build a complete electronic medical record of the patient, realize automated case entry and update, and ensure data security through permission management and log records, recording the entire process of case entry and modification.

[0028] In the embodiments disclosed herein, the processes described above with reference to the flowcharts can be implemented as computer software programs. The embodiments disclosed herein include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the method illustrated in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component and / or installed from removable media. When the computer program is executed by a central processing unit, the functions defined in the methods of this application are performed. It should be noted that the computer-readable medium referred to herein can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more wire segments, a portable computer disk, a hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Furthermore, in this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, electrical, optical, RF, or any suitable combination thereof.

[0029] The flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0030] Those skilled in the art should understand that the above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered by the scope of protection of the present application.

Claims

1. A medical case management system based on an artificial intelligence large model, characterized in that: include: The case receiving module is used to receive electronic medical records of patients from hospitals or departments, identify the received electronic medical records of patients, directly enter the data that uses this case management system, and mark the data that does not use this case management system as pending data. This module supports real-time data transmission and batch import to ensure the integrity and timeliness of case data; The data comparison module is used to compare the data to be processed with the existing data in the case management system database. The compared data includes patient identification, case information matching, treatment stage time, treatment department information and other data related to the patient case. The data to be processed is divided into usable data and unusable data according to the difference degree of comparison; A data revision module, which is used to perform deep semantic analysis of unavailable data using natural language processing technology, and to standardize the unavailable data based on the existing data in the case management system database, so that the unavailable data is converted into usable data; The case entry module is used to build complete patient electronic medical records using available data, realize automated case entry and update, ensure data security through permission management and log records, and record the entire process of case entry and modification.

2. A medical case management system based on artificial intelligence big model according to claim 1, characterized in that: In the data comparison module, the specific method of dividing the data to be processed into usable data and unusable data includes: obtaining data in the data to be processed that can be interoperable with the existing data in the case management system database, dividing the interoperable data into usable data, and dividing the remaining data that cannot be interoperable into unusable data.

3. A medical case management system based on artificial intelligence big model according to claim 2, characterized in that: The specific method of performing standardized conversion on the unavailable data based on the existing data in the case management system database includes: using natural language processing technology to semantically label the existing data in the case management system database, marking the semantic label as a label template, and using natural language processing technology to extract the semantic label corresponding to the unavailable data, matching the semantic label of the unavailable data with the label template, and performing corresponding standardized conversion on the unavailable data based on the matching results.

4. A medical case management system based on artificial intelligence big model according to claim 3, characterized in that: When there is a semantic label in the label template that is exactly the same as the semantic label of the unavailable data, the unavailable data is converted into an existing data format with the same semantics as it and marked as available data; when there is no semantic label in the label template that is exactly the same as the semantic label of the unavailable data, the semantic matching judgment strategy is executed.

5. The medical case management system based on artificial intelligence big model according to claim 4 is characterized in that: The semantic matching judgment strategy includes obtaining all semantic labels corresponding to unavailable data, and comparing all its semantic labels with the semantic labels in the label template, obtaining the semantic label in the unavailable data with the highest similarity with the label template, marking the semantic label as the most similar semantic, setting a similarity threshold, obtaining the similarity value between the most similar semantic and the label template, comparing the similarity value with the similarity threshold, and making corresponding responses based on the comparison results.

6. The medical case management system based on artificial intelligence big model according to claim 5 is characterized in that: When the similarity value is greater than or equal to the similarity threshold, the unavailable data is standardized and converted according to the semantic label in the label template corresponding to the most similar semantics, and the converted data is marked as available data; When the similarity value is less than the similarity threshold, the unavailable data is marked as remark data; a remark area is created in this case management system, and all unavailable data marked as remark data are placed in the remark area in their original data format, and the remark data can be viewed in the remark area of ​​this case management system.

7. The medical case management system based on artificial intelligence big model according to claim 6 is characterized in that: The specific method of obtaining the semantic similarity between the unavailable data and the label template includes: each semantic label extracted from the unavailable data and each semantic label in the label template are converted into a high-dimensional vector representation through a pre-trained language model, and the cosine similarity of the vector of each semantic label in the unavailable data and the vector of each semantic label in the label template are calculated respectively. The numerical range of the calculated result will be between 0 and 1. The higher the value, the closer the semantics.

8. The medical case management system based on artificial intelligence big model according to claim 7 is characterized in that: Set a data volume threshold. When executing the data revision module, if the similarity value is less than the similarity threshold and the similarity is greater than 0, obtain the data volume of the current available data and compare it with the data volume threshold. If the data volume of the current available data is greater than or equal to the data volume threshold, mark the unavailable data as remark data and do not perform additional operations. If the amount of currently available data is less than the data volume threshold, the unavailable data will not be marked as remark data. Instead, the unavailable data will be standardized and converted according to the semantic label in the label template corresponding to the most similar semantics. The converted data will be marked as available data, and the subsequent case entry module will be executed.

9. A medical case management method based on an artificial intelligence large model, characterized in that: According to any one of claims 1 to 8, the medical case management system based on the artificial intelligence large model comprises the following steps: Receive electronic medical records of patients from hospitals or departments, identify the received electronic medical records of patients, directly enter the data that uses this case management system, and mark the data that does not use this case management system as pending data. This module supports real-time data transmission and batch import to ensure the integrity and timeliness of case data; Compare the data to be processed with the existing data in the case management system database. The compared data include patient identification, case information matching, treatment stage time, treatment department information and other data related to the patient case. The data to be processed is divided into usable data and unusable data according to the difference between the comparisons. Use natural language processing technology to perform deep semantic analysis on unavailable data, and standardize and convert unavailable data based on existing data in the case management system database to convert unavailable data into usable data; Use available data to build complete electronic patient medical records, automate case entry and updates, and ensure data security through permission management and logging, recording the entire process of case entry and modification.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a medical case management system based on an artificial intelligence large model as described in any one of claims 1 to 8.

Images