Insurance excess dose identification digital intelligent system based on large model vector knowledge base

Abstract

The invention belongs to the technical field of insurance excess drug quantity identification systems, and particularly relates to an insurance excess drug quantity identification digital intelligent system based on a large model vector knowledge base, which comprises a data collection and preprocessing module, a vector knowledge base construction module, an intelligent analysis module, a risk assessment and early warning module and a report generation and feedback module. The data collecting and preprocessing module is used for collecting insurance claim settlement data and auditing and preprocessing the collected data; according to the invention, the efficiency and accuracy of insurance claim settlement are improved, and the risk of an insurance company is reduced; the supervision efficiency of medical insurance drug use is improved, and the medication safety of patients is ensured; and intelligent analysis is carried out on the medication condition in insurance claim settlement so as to identify whether the excessive medication condition and the abnormal medication condition exist or not.

Description

Technical Field

[0001] The present invention relates to the technical field of insurance overdose identification systems, and in particular to a digital intelligence system for insurance overdose identification based on a large model vector knowledge base. Background Art

[0002] Medical insurance claims refer to the process in which the insurance company provides financial compensation for the medical expenses incurred by the insured in accordance with the terms of the contract when the insured needs treatment due to illness or accidental injury during the insurance period and incurs medical expenses that meet the terms of the insurance contract. Specifically, it is the act of the insurance company reviewing and confirming that the accident falls within the scope of insurance liability after receiving the claim application and relevant supporting materials submitted by the insured, and paying the insurance money to the insured or beneficiary in accordance with the standards and scope agreed in the contract. This process is an important part of insurance services and a key link in protecting the rights and interests of insurance consumers.

[0003] Medical insurance claims include compensation for some of the patient's medication. In order to improve the efficiency and accuracy of insurance claims, reduce the risks of insurance companies, improve the efficiency of supervision of medical insurance drug use, ensure patient medication safety, and conduct intelligent analysis of medication use in insurance claims, it is necessary to develop a digital intelligence system for insurance overdose identification based on a large model vector knowledge base. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] To solve the above technical problems, according to one aspect of the present invention, the present invention provides the following technical solutions:

[0006] A digital intelligence system for identifying excessive drug dosage based on a large model vector knowledge base, comprising:

[0007] It includes data collection and preprocessing module, vector knowledge base construction module, intelligent analysis module, risk assessment and early warning module and report generation and feedback module;

[0008] The data collection and preprocessing module: The data collection and preprocessing module is used to collect insurance claim data and review and preprocess the collected data;

[0009] The data collection and preprocessing module includes the following steps:

[0010] S1: Patient information collection: Establish an electronic claims data collection system to collect patients’ personal information, including name, gender, age, ID number, and contact information;

[0011] S2: Medication record collection: Cooperate with medical institutions to automatically extract patients' medication records through the electronic medical record system, including drug name, dosage, medication time, and medication duration; manually enter medication information through prescriptions and drug purchase records provided by patients;

[0012] The vector knowledge base construction module uses large model technology to construct a vector knowledge base, which includes drug information, medication guides, and medical literature; converts key information such as drug name, dosage, and indication into high-dimensional vectors for fast retrieval and matching;

[0013] The vector knowledge base construction module includes the following steps:

[0014] S1. Drug data collection and processing: Collect a large amount of drug information, medication guidelines, and medical literature data; clean the data, remove irrelevant information, retain key information, including drug name, dosage, indications, side effects, and standardize the data format for subsequent processing;

[0015] S2. Feature extraction: Use natural language processing technology to convert text data into high-dimensional vectors. For drug name entities, named entity recognition technology can be used to accurately extract them. For dosage and indication information, text classification and sequence labeling models can be used to extract them.

[0016] S3. Vector model training: Use a deep learning model, such as Transformer and BERT models, to train the vector representation of text. Input the key information of drug name, dosage, and indication into the model to obtain their respective high-dimensional vector representations.

[0017] S4. Vector knowledge base construction: Store the trained vectors in the database to build a vector knowledge base; add an index to each vector for fast retrieval;

[0018] The intelligent analysis module uses the data collection and preprocessing module to analyze the medication records, compares the medication records through the vector knowledge base construction module, identifies potential abnormal medication situations, and determines whether there is excessive medication;

[0019] The intelligent analysis module includes the following steps:

[0020] S1. Convert the drug name and dosage key information in the medication record into vectors through the vector knowledge base construction module; use the vector knowledge base to compare the drug vectors in the medication record to determine whether there is excessive medication or abnormal medication;

[0021] S2. Label and classify potential excessive medication and abnormal medication:

[0022] The risk assessment and early warning module, based on the analysis results, conducts risk assessment on excessive medication and determines the risk level; issues early warning for high-risk situations, prompting insurance claims personnel to conduct further verification;

[0023] The report generation and feedback module automatically generates an excessive medication identification report, including abnormal medication records and risk assessment results; and provides a feedback mechanism to allow claims personnel to confirm and correct the system identification results.

[0024] As a preferred solution of the digital intelligence system for identifying excessive drug dosage based on a large model vector knowledge base described in the present invention, the data collection and preprocessing module further includes the following steps:

[0025] S3: Disease type collection: Collect disease type and diagnosis information based on the patient's medical records, including disease name, disease code, and diagnosis date; automatically synchronize disease type data through the electronic medical record system and the health information system of the medical institution;

[0026] S4: Data verification and review: Verify and review the collected data to ensure the accuracy and completeness of the data; check the consistency and compliance of the data through manual review and automated tools;

[0027] S5: Data storage and management: Store the collected claims data in a secure database and implement strict data management measures, including: data encryption, access control and regular data backup.

[0028] As a preferred solution of the digital intelligence system for identifying excessive drug dosage based on a large model vector knowledge base described in the present invention, the vector knowledge base construction module further includes the following steps:

[0029] S5. Retrieval and matching: When the user enters a query, the query text is converted into a vector; the vector similarity calculation method is used to retrieve similar vectors in the knowledge base; the drug information with the best match is returned based on the similarity sorting.

[0030] As a preferred solution of the digital intelligence system for identifying excessive medication dosage based on a large model vector knowledge base described in the present invention, the excessive medication and abnormal medication in S2 in the intelligent analysis module include the following situations:

[0031] Overmedication: Identify patients taking medications in doses exceeding the maximum recommended, prescribed dose;

[0032] Irrational use of drugs: Identify drug use that is inconsistent with clinical guidelines and medical common sense, including the use of banned drugs for pregnant women and the use of unapproved drugs for children;

[0033] Repeated medication: It is found that the simultaneous use of drugs of the same class or with similar mechanisms of action may lead to drug interactions and increased side effects;

[0034] Drug allergy: Identifying that a patient is allergic to a specific drug but is still taking that drug;

[0035] Inappropriate drug combinations: It has been found that certain drug combinations may cause adverse reactions and reduce the effectiveness of the drugs.

[0036] As a preferred solution of the digital intelligence system for identifying excessive drug dosage based on a large model vector knowledge base described in the present invention, the intelligent analysis module further includes the following steps:

[0037] S3. Result evaluation and feedback: Evaluate the identified abnormal medication use and verify the accuracy of the algorithm; based on the evaluation results, iteratively optimize the model to improve the recognition effect;

[0038] S4. Deployment and monitoring: Deploy the optimized model to the actual application scenario to monitor the medication records in real time; regularly evaluate and update the model to adapt to the changing medication situation.

[0039] The beneficial effects of the present invention are: the system improves the efficiency and accuracy of insurance claims while reducing the risks of insurance companies; improves the efficiency of supervision of medical insurance drug use and ensures the safety of patient medication; and performs intelligent analysis of medication use in insurance claims to identify whether there is excessive medication or abnormal medication use. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the present invention will be described in detail below in combination with the accompanying drawings and detailed embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0041] Figure 1is a system block diagram of the present invention;

[0042] Figure 2 This is a schematic diagram of the steps of the data collection and preprocessing module of the present invention;

[0043] Figure 3 A schematic diagram of the steps of constructing a vector knowledge base module of the present invention;

[0044] Figure 4 This is a schematic diagram of the steps of the intelligent analysis module of the present invention;

[0045] Figure 5 This is a schematic diagram for marking and classifying potential excessive medication and abnormal medication situations in the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0049] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0050] See also Figure 1-Figure 5 , shows a schematic diagram of the structure of a digital intelligence system implementation method for identifying excessive drug dosage based on a large model vector knowledge base of the present invention, please refer to Figure 1-Figure 5 , a digital intelligence system for identifying insurance overdose based on a large model vector knowledge base is introduced in detail.

[0051] A digital intelligence system for identifying insurance overdose based on a large model vector knowledge base, including a data collection and preprocessing module, a vector knowledge base construction module, an intelligent analysis module, a risk assessment and early warning module, and a report generation and feedback module;

[0052] The data collection and preprocessing module: The data collection and preprocessing module is used to collect insurance claim data and review and preprocess the collected data;

[0053] The data collection and preprocessing module includes the following steps:

[0054] S1: Patient information collection: Establish an electronic claims data collection system to collect patients’ personal information, including name, gender, age, ID number, and contact information;

[0055] When setting up an electronic claims data collection system, the following methods can be used to process and obtain the handwritten information in the prescriptions and drug purchase records provided by patients to ensure that the information is consistent with the data in the electronic medical record system: Use OCR technology to recognize and convert handwritten information. Optical character recognition (OCR) technology refers to the technology of electronically recognizing and extracting text information in paper documents and converting it into editable text data. This technology is widely used in document management, image processing, information entry and other fields, which can effectively improve work efficiency and reduce manual entry errors; verify the recognition results, compare them with the data in the electronic medical record system, manually review and correct the inconsistent information, ensure that the corrected information is accurate, and then update it to the electronic medical record system synchronously.

[0056] S2: Medication record collection: Cooperate with medical institutions to automatically extract patients' medication records through the electronic medical record system, including drug name, dosage, medication time, and medication duration; manually enter medication information through prescriptions and drug purchase records provided by patients;

[0057] S3: Disease type collection: Collect disease type and diagnosis information based on the patient's medical records, including disease name, disease code, and diagnosis date; automatically synchronize disease type data through the electronic medical record system and the health information system of the medical institution;

[0058] S4: Data verification and review: Verify and review the collected data to ensure the accuracy and completeness of the data; check the consistency and compliance of the data through manual review and automated tools;

[0059] S5: Data storage and management: Store the collected claims data in a secure database and implement strict data management measures, including data encryption, access control and regular data backup;

[0060] The vector knowledge base construction module uses large model technology to construct a vector knowledge base, which includes drug information, medication guides, and medical literature; converts key information such as drug name, dosage, and indication into high-dimensional vectors for fast retrieval and matching;

[0061] The vector knowledge base construction module includes the following steps:

[0062] S1. Drug data collection and processing: Collect a large amount of drug information, medication guidelines, and medical literature data; clean the data, remove irrelevant information, retain key information, including drug name, dosage, indications, side effects, and standardize the data format for subsequent processing;

[0063] S2. Feature extraction: Use natural language processing technology to convert text data into high-dimensional vectors. For drug name entities, named entity recognition technology can be used to accurately extract them. For dosage and indication information, text classification and sequence labeling models can be used to extract them.

[0064] S3. Vector model training: Use a deep learning model, such as Transformer and BERT models, to train the vector representation of text. Input the key information of drug name, dosage, and indication into the model to obtain their respective high-dimensional vector representations.

[0065] S4. Vector knowledge base construction: Store the trained vectors in the database to build a vector knowledge base; add an index to each vector for fast retrieval;

[0066] S5, retrieval and matching: when the user enters a query, the query text is converted into a vector; the vector similarity calculation method is used to retrieve similar vectors in the knowledge base; the most matching drug information is returned based on the similarity sorting;

[0067] Here is a simplified pseudocode example that describes this process:

[0068] ```

[0069] Python

[0070] #Pseudocode, does not contain actual model training and data processing code

[0071] #Data preprocessing

[0072] data = collect_data()

[0073] cleaned_data=preprocess_data(data)

[0074] #Feature extraction

[0075] vectors=extract_features(cleaned_data)

[0076] #Vector model training

[0077] train_vectors_model(vectors)

[0078] #Vector knowledge base construction

[0079] vector_database=build_vector_database(vectors)

[0080] #Search and match

[0081] def retrieve_and_match(query):

[0082] query_vector=convert_to_vector(query)

[0083] similar_vectors=search_vector_database(vector_database,query_vector)

[0084] return similar_vectors

[0085] #Function call example

[0086] query="Drugs for treating hypertension"

[0087] matches=retrieve_and_match(query)

[0088] ```

[0089] In order to ensure the timeliness and accuracy of the vector knowledge base, the following methods can be used to update and review it:

[0090] 1. Regular review and update: Establish a regular review mechanism to ensure that the information in the knowledge base is updated in a timely manner. This includes regular checks on existing content and the timely addition of new information.

[0091] 2. Pay attention to authoritative sources: Pay attention to and subscribe to authoritative medical journals, official drug information updates, clinical guideline releases, etc. to obtain the latest medical information.

[0092] 3. Use automated tools: Use automated tools to monitor relevant databases and websites, and automatically remind relevant personnel to update when new drug information or clinical guidelines are released.

[0093] 4. Expert team review: Establish a team of medical experts to review the content in the knowledge base to ensure the accuracy and reliability of the information.

[0094] 5. User feedback mechanism: Establish a user feedback mechanism to encourage users to report errors or outdated information in the knowledge base so that it can be corrected in a timely manner.

[0095] 6. Regular training: Provide regular training to personnel responsible for knowledge base maintenance to ensure that they are aware of the latest medical knowledge and information update procedures.

[0096] The intelligent analysis module uses the data collection and preprocessing module to analyze the medication records, compares the medication records through the vector knowledge base construction module, identifies potential abnormal medication situations, and determines whether there is excessive medication;

[0097] The intelligent analysis module includes the following steps:

[0098] S1. Convert the drug name and dosage key information in the medication record into vectors through the vector knowledge base construction module; use the vector knowledge base to compare the drug vectors in the medication record to determine whether there is excessive medication or abnormal medication;

[0099] S2. Label and classify potential excessive medication and abnormal medication:

[0100] Excessive medication and abnormal medication include the following:

[0101] Overmedication: Identify patients taking medications in doses exceeding the maximum recommended, prescribed dose;

[0102] Irrational use of drugs: Identify drug use that is inconsistent with clinical guidelines and medical common sense, including the use of banned drugs for pregnant women and the use of unapproved drugs for children;

[0103] Repeated medication: It is found that the simultaneous use of drugs of the same class or with similar mechanisms of action may lead to drug interactions and increased side effects;

[0104] Drug allergy: Identifying that a patient is allergic to a specific drug but is still taking that drug;

[0105] Inappropriate drug combinations: It has been found that certain drug combinations may cause adverse reactions and reduce drug effectiveness;

[0106] The following are examples:

[0107] 1. Excessive medication labeling:

[0108] Label type: Overdosage;

[0109] Labeling instructions: The dosage of the drug exceeds the prescribed upper limit;

[0110] Example: Patient A uses a certain antibiotic at a daily dose of 1000 mg, which exceeds the recommended dose by 500 mg; 2. Unreasonable medication labeling:

[0111] Annotation type: irrational use of drugs;

[0112] Note: The use of drugs does not conform to medical common sense and clinical guidelines;

[0113] Example: Patient B, a pregnant woman, was using the banned drug metronidazole;

[0114] 3. Repeated medication labeling:

[0115] Label type: Repeat medication;

[0116] Labeling instructions: drugs of the same class or with similar effects are used simultaneously;

[0117] Example: Patient C is taking two antidepressant medications, both of which belong to the SSRI class;

[0118] 4. Drug allergy labeling:

[0119] Annotation type: drug allergy;

[0120] Labeling: The patient has an allergic reaction to a specific drug but is still using it;

[0121] Example: Patient D is known to be allergic to penicillin, but the prescription contains a penicillin-type drug;

[0122] 5. Labeling of inappropriate drug combinations:

[0123] Annotation type: Inappropriate drug combination;

[0124] Labeling instructions: Drug combinations may cause adverse reactions and reduce efficacy;

[0125] Example: Patient E uses the anticoagulant drug warfarin and certain antibiotics simultaneously, which may reduce the effectiveness of warfarin;

[0126] In this way, medical professionals can quickly identify and review abnormal medication use and take appropriate measures to ensure patient medication safety;

[0127] S3. Result evaluation and feedback: Evaluate the identified abnormal medication use and verify the accuracy of the algorithm; based on the evaluation results, iteratively optimize the model to improve the recognition effect;

[0128] S4. Deployment and monitoring: Deploy the optimized model to actual application scenarios to monitor medication records in real time; regularly evaluate and update the model to adapt to the changing medication situation;

[0129] Among them, in order to effectively identify abnormal medication, it is necessary to set a reasonable threshold first; the setting of this threshold is based on the statistical distribution of medication records, in order to distinguish normal medication from abnormal medication; usually, the mean plus or minus standard deviation method is used to determine this threshold; for example, the threshold can be set as the mean plus or minus twice the standard deviation, which can cover most normal medication situations; however, in practical applications, there are always some edge cases, which may not be directly classified by threshold judgment; in order to deal with these edge cases, cluster analysis is used for further classification; cluster analysis can help classify similar medication records into the same category, making it easier to identify abnormal behavior; in addition, in order to ensure the accuracy of classification, expert knowledge is also combined for manual review; experts can further verify and correct the results of cluster analysis with their rich experience and professional knowledge to ensure that the final classification results are both scientific and reliable; through this comprehensive method, abnormal medication behavior can be more accurately identified, thereby improving the quality and practicality of the vector knowledge base;

[0130] The risk assessment and early warning module, based on the analysis results, conducts risk assessment on excessive medication and determines the risk level; issues early warning for high-risk situations, prompting insurance claims personnel to conduct further verification;

[0131] Among them, the risk assessment method for excessive medication is as follows:

[0132] 1. Medication frequency and dosage: Analyze whether the patient's medication frequency and dosage are beyond the normal range;

[0133] 2. Drug interactions: assess whether there are interactions between multiple drugs used by the patient at the same time, which may lead to adverse reactions;

[0134] 3. Drug indications: Check whether the patient's medication is targeted at their specific condition to avoid using inappropriate drugs;

[0135] 4. Individual differences among patients: Consider factors such as the patient's age, gender, weight, liver and kidney function, and evaluate the metabolism and excretion of the drug in the body;

[0136] 5. Medication history: Analyze the patient’s medication history to identify possible drug abuse or over-dependence issues.

[0137] The specific standards for risk assessment are as follows:

[0138] Risk quantification criteria:

[0139] Low risk: The patient is taking 1-4 medications and the dosages are within the recommended range.

[0140] Medium risk: Patients are taking 4-5 drugs or the drug dosage exceeds the recommended dose by 20%-50%.

[0141] High risk: The patient is taking more than 5 drugs or the drug dosage exceeds the recommended dose by 50%.

[0142] Very high risk: Patients are taking more than 7 drugs or the drug dosage exceeds the recommended dose by 100%.

[0143] The report generation and feedback module automatically generates an excessive medication identification report, including abnormal medication records and risk assessment results; and provides a feedback mechanism to allow claims personnel to confirm and correct the system identification results.

[0144] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced by equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed in the present invention may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A digital intelligence system for identifying excessive drug dosage based on a large model vector knowledge base, characterized in that: It includes data collection and preprocessing module, vector knowledge base construction module, intelligent analysis module, risk assessment and early warning module and report generation and feedback module; The data collection and preprocessing module: The data collection and preprocessing module is used to collect insurance claim data and review and preprocess the collected data; The data collection and preprocessing module includes the following steps: S1: Patient information collection: Establish an electronic claims data collection system to collect patients’ personal information, including name, gender, age, ID number, and contact information; S2: Medication record collection: Cooperate with medical institutions to automatically extract patients' medication records through the electronic medical record system, including drug name, dosage, medication time, and medication duration; manually enter medication information through prescriptions and drug purchase records provided by patients; The vector knowledge base construction module uses large model technology to construct a vector knowledge base, which includes drug information, medication guides, and medical literature; converts key information such as drug name, dosage, and indication into high-dimensional vectors for fast retrieval and matching; The vector knowledge base construction module includes the following steps: S1. Drug data collection and processing: Collect a large amount of drug information, medication guidelines, and medical literature data; clean the data, remove irrelevant information, retain key information, including drug name, dosage, indications, side effects, and standardize the data format for subsequent processing; S2. Feature extraction: Use natural language processing technology to convert text data into high-dimensional vectors. For drug name entities, named entity recognition technology can be used to accurately extract them. For dosage and indication information, text classification and sequence labeling models can be used to extract them. S3. Vector model training: Use a deep learning model, such as Transformer and BERT models, to train the vector representation of text. Input the key information of drug name, dosage, and indication into the model to obtain their respective high-dimensional vector representations. S4. Vector knowledge base construction: Store the trained vectors in the database to build a vector knowledge base; add an index to each vector for fast retrieval; The intelligent analysis module uses the data collection and preprocessing module to analyze the medication records, compares the medication records through the vector knowledge base construction module, identifies potential abnormal medication situations, and determines whether there is excessive medication; The intelligent analysis module includes the following steps: S1. Convert the drug name and dosage key information in the medication record into vectors through the vector knowledge base construction module; use the vector knowledge base to compare the drug vectors in the medication record to determine whether there is excessive medication or abnormal medication; S2. Label and classify potential excessive medication and abnormal medication: The risk assessment and early warning module, based on the analysis results, conducts risk assessment on excessive medication and determines the risk level; issues early warning for high-risk situations, prompting insurance claims personnel to conduct further verification; The report generation and feedback module automatically generates an excessive medication identification report, including abnormal medication records and risk assessment results; and provides a feedback mechanism to allow claims personnel to confirm and correct the system identification results.

2. According to claim 1, a digital intelligence system for identifying excessive drug dosage based on a large model vector knowledge base is characterized by: The data collection and preprocessing module also includes the following steps: S3: Disease type collection: Collect disease type and diagnosis information based on the patient's medical records, including disease name, disease code, and diagnosis date; automatically synchronize disease type data through the electronic medical record system and the health information system of the medical institution; S4: Data verification and review: Verify and review the collected data to ensure the accuracy and completeness of the data; check the consistency and compliance of the data through manual review and automated tools; S5: Data storage and management: Store the collected claims data in a secure database and implement strict data management measures, including: data encryption, access control and regular data backup.

3. According to claim 1, a digital intelligence system for identifying excessive drug dosage based on a large model vector knowledge base is characterized by: The vector knowledge base construction module also includes the following steps: S5. Retrieval and matching: When the user enters a query, the query text is converted into a vector; the vector similarity calculation method is used to retrieve similar vectors in the knowledge base; the drug information with the best match is returned based on the similarity sorting.

4. According to claim 1, a digital intelligence system for identifying excessive drug dosage based on a large model vector knowledge base is characterized by: The excessive medication and abnormal medication in S2 of the intelligent analysis module include the following situations: Overmedication: Identify patients taking medications in doses exceeding the maximum recommended, prescribed dose; Irrational use of drugs: Identify drug use that is inconsistent with clinical guidelines and medical common sense, including the use of banned drugs for pregnant women and the use of unapproved drugs for children; Repeated medication: It is found that the simultaneous use of drugs of the same class or with similar mechanisms of action may lead to drug interactions and increased side effects; Drug allergy: Identifying that a patient is allergic to a specific drug but is still taking that drug; Inappropriate drug combinations: It has been found that certain drug combinations may cause adverse reactions and reduce the effectiveness of the drugs.

5. The digital intelligence system for identifying excessive drug dosage based on a large model vector knowledge base according to claim 1 is characterized by: The intelligent analysis module also includes the following steps: S3. Result evaluation and feedback: Evaluate the identified abnormal medication use and verify the accuracy of the algorithm; based on the evaluation results, iteratively optimize the model to improve the recognition effect; S4. Deployment and monitoring: Deploy the optimized model to the actual application scenario to monitor the medication records in real time; regularly evaluate and update the model to adapt to the changing medication situation.

Images