A prescription intelligent auditing method and system based on multi-dimensional rule matching
By constructing a multi-dimensional rule base for prescription review, the problem of low efficiency in traditional review has been solved, achieving high-precision prescription review, improving review efficiency and accuracy, and ensuring patient medication safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CAPINFO CO LTD
- Filing Date
- 2026-03-05
- Publication Date
- 2026-06-12
AI Technical Summary
Existing technologies cannot meet the needs of multi-dimensional and high-precision prescription review. Traditional review is inefficient, difficult to curb violations, and cannot fully cover compliance with medical insurance policies, rationality of patients' historical medication use, and diagnosis-medication suitability.
A multi-dimensional rule base is constructed, including a drug interaction rule base, a medical insurance policy rule base, a patient's medication history rule base, and a clinical diagnosis rule base. Prescription-related information is reviewed through cross-matching of multi-dimensional rules to generate comprehensive review results.
It significantly improves the comprehensiveness and accuracy of prescription review, effectively identifies violations, reduces unreasonable expenditures of the medical insurance fund, improves review efficiency, and ensures patient medication safety.
Smart Images
Figure CN122201601A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of artificial intelligence technology, and in particular to a prescription intelligent review method and system based on multi-dimensional rule matching. Background Technology
[0002] With the deepening of medical informatization and the continuous improvement of medical insurance policies, medical institutions face increasingly stringent requirements for prescription management. The accuracy and efficiency of prescription review have become crucial links in ensuring medical quality and the security of medical insurance funds. Traditional prescription review relies on manual work, requiring reviewers to manually check prescriptions against treatment guidelines, drug instructions, and medical insurance policies. This is not only inefficient and unable to meet the daily review needs of a massive number of prescriptions, but also suffers from inconsistent review standards and the ease with which violations can be overlooked due to human error. It fails to effectively curb violations such as pre-prescribing, duplicate prescriptions, and excessive medication, resulting in unreasonable expenditures of medical insurance funds.
[0003] In existing technologies, prescription review software mostly relies on locally stored drug interaction databases to perform single-dimensional drug incompatibility screening, resulting in limited functionality. Although some regional medical information platforms have achieved cross-institutional data sharing, they have not built a multi-dimensional rule cross-verification mechanism, which cannot cover key review dimensions such as compliance with medical insurance policies, rationality of patients' historical medication use, and diagnosis-medication suitability, making it difficult to conduct a comprehensive and accurate evaluation of prescriptions.
[0004] Therefore, current technology cannot meet the needs of multi-dimensional and high-precision prescription review. There is an urgent need for an intelligent and comprehensive prescription review method and system to improve review efficiency, ensure patient medication safety, and standardize medical practices. Summary of the Invention
[0005] In view of this, the present invention proposes a prescription intelligent review method and system based on multi-dimensional rule matching, which can realize intelligent review of prescriptions based on multi-dimensional rules.
[0006] To achieve the above objectives, the present invention provides the following technical solution: A prescription intelligent review method based on multi-dimensional rule matching includes: Obtain information related to prescriptions awaiting review; Based on a pre-built multi-dimensional audit rule base, multi-dimensional rule cross-matching audit is performed on the relevant information of the prescription to be audited to obtain a comprehensive audit result. The multi-dimensional audit rule base includes a drug interaction rule base, a medical insurance policy rule base, a patient's historical medication rule base, and a clinical diagnosis rule base. A prescription review report is generated based on the comprehensive review results.
[0007] Based on the above technical solution, the present invention can be further improved as follows: Optionally, the prescription information to be reviewed includes patient basic information, clinical diagnosis information, prescription drug information, and historical prescription information.
[0008] Optionally, the step of performing multi-dimensional rule cross-matching review on the prescription information to be reviewed based on a pre-built multi-dimensional review rule base includes: Based on the drug interaction rule base, the prescription drug information in the prescription information to be reviewed is matched and reviewed for interaction. Based on the aforementioned medical insurance policy rule base, the prescription drug information and clinical diagnosis information in the prescription information to be reviewed are matched and reviewed for medical insurance compliance. Based on the patient's historical medication rule base, the historical prescription information and current prescription drug information in the prescription information to be reviewed are matched and reviewed for medication continuity and rationality. Based on the clinical diagnostic rule base, the clinical diagnostic information and prescription drug information in the prescription information to be reviewed are used to perform diagnostic and medication suitability matching and review.
[0009] Optionally, before performing a multi-dimensional rule cross-matching review step on the prescription information to be reviewed based on a pre-built multi-dimensional review rule base, the method further includes: The multi-dimensional review rule library is updated in real time based on the latest policy requirements and medication rules.
[0010] Optionally, the step of performing multi-dimensional rule cross-matching review on the prescription information to be reviewed based on a pre-built multi-dimensional review rule base includes: Transform the drug interaction rule base, medical insurance policy rule base, patient medication history rule base, and clinical diagnosis rule base into executable rule expressions; Based on the rule expression, multi-dimensional rule cross-matching review is performed on the prescription information to be reviewed.
[0011] Optionally, before obtaining the comprehensive review results, the following steps may also be included: Obtain the individual review results from the drug interaction rule base, medical insurance policy rule base, patient history medication rule base, and clinical diagnosis rule base corresponding to the prescription information to be reviewed; The comprehensive audit result is obtained based on the individual audit results and the preset weight allocation strategy for each individual audit result.
[0012] Optionally, after obtaining the comprehensive review results, the following steps may also be included: The feature vector of the comprehensive review result is extracted, and the feature vector is input into the classification model to obtain the probability of violation and the level of violation of the prescription information to be reviewed. The level includes clear violation, highly suspicious and slightly suspicious.
[0013] A prescription intelligent review system based on multi-dimensional rule matching includes: The information acquisition module is used to acquire information related to prescriptions pending review. The review module is used to perform multi-dimensional rule cross-matching review on the prescription information to be reviewed based on a pre-built multi-dimensional review rule base to obtain a comprehensive review result. The multi-dimensional review rule base includes a drug interaction rule base, a medical insurance policy rule base, a patient's historical medication rule base, and a clinical diagnosis rule base. The report generation module is used to generate a prescription review report based on the comprehensive review results.
[0014] An electronic device includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the method described herein.
[0015] A non-transitory computer-readable storage medium having a computer program stored thereon, the computer program implementing the steps of the method when executed by a processor.
[0016] The present invention has the following advantages: This invention presents a prescription intelligent review method based on multi-dimensional rule matching. By constructing a multi-dimensional review rule library encompassing drug interaction rules, medical insurance policy rules, patient medication history rules, and clinical diagnosis rules, it achieves multi-dimensional rule cross-matching review of prescription information, overcoming the limitations of traditional single-dimensional review and significantly improving the comprehensiveness and accuracy of prescription review. It effectively identifies violations such as pre-prescription and duplicate medication, reducing unreasonable expenditures of the medical insurance fund; it eliminates the need for manual review, significantly improving review efficiency, reducing human error rates, ensuring patient medication safety, and standardizing clinical medical practices, providing intelligent support for prescription management in medical institutions. Attached Figure Description
[0017] For illustrative and not limiting purposes, the present invention will now be described in conjunction with embodiments and accompanying drawings, wherein: Figure 1 This is a flowchart illustrating the intelligent prescription review method based on multi-dimensional rule matching in an embodiment of the present invention. Figure 2 This is a flowchart illustrating the multi-dimensional rule matching process of the intelligent prescription review method based on multi-dimensional rule matching in an embodiment of the present invention. Figure 3 This is a diagram showing the core model relationship of the rule management in the prescription intelligent review method based on multi-dimensional rule matching in the embodiments of the present invention. Figure 4This is a flowchart illustrating the classification of violation levels in the prescription intelligent review method based on multi-dimensional rule matching according to an embodiment of the present invention. Figure 5 This is a schematic diagram of the main components of the prescription intelligent review system based on multi-dimensional rule matching in an embodiment of the present invention; Figure 6 This is an architecture diagram of the prescription intelligent review system based on multi-dimensional rule matching in an embodiment of the present invention; Figure 7 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. Detailed Implementation
[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0019] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0020] It should be noted that, where there is no conflict, the embodiments and features of the present invention can be combined with each other. The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0021] Figure 1 This is a flowchart illustrating the intelligent prescription review method based on multi-dimensional rule matching in an embodiment of the present invention, as shown below. Figure 1 As shown, the prescription intelligent review method based on multi-dimensional rule matching provided in this embodiment of the invention includes the following steps S101 to S103.
[0022] S101, Obtain relevant information about the prescription to be reviewed.
[0023] The information related to the prescriptions to be reviewed includes the patient's basic information, clinical diagnosis information, prescription drug information, and historical prescription information.
[0024] Collect patient basic information, clinical diagnosis information, and prescription drug information from the Hospital Information System (HIS).
[0025] Retrieve historical prescription information from the data storage module.
[0026] S102, based on the pre-built multi-dimensional audit rule base, performs multi-dimensional rule cross-matching audit on the relevant information of the prescription to be audited, and obtains a comprehensive audit result.
[0027] The multi-dimensional review rule base includes a drug interaction rule base, a medical insurance policy rule base, a patient's historical medication rule base, and a clinical diagnosis rule base.
[0028] The drug interaction rule base contains drug-drug interactions: The medical insurance policy and rule database includes restrictions on drug indications, usage and dosage restrictions, and reimbursement ratios; The patient's historical medication rule database implements a medication anomaly detection mechanism to identify abnormal situations such as duplicate medication, premature medication, and excessive medication.
[0029] The clinical diagnostic rule base is designed to create a diagnostic-medication matching algorithm to detect whether the prescribed medication meets the disease treatment needs.
[0030] Based on the drug interaction rule base, the prescription drug information in the prescription information to be reviewed is matched and reviewed for interaction. Based on the aforementioned medical insurance policy rule base, the prescription drug information and clinical diagnosis information in the prescription information to be reviewed are matched and reviewed for medical insurance compliance. Based on the patient's historical medication rule base, the historical prescription information and current prescription drug information in the prescription information to be reviewed are matched and reviewed for medication continuity and rationality. Based on the clinical diagnostic rule base, the clinical diagnostic information and prescription drug information in the prescription information to be reviewed are used to perform diagnostic and medication suitability matching and review.
[0031] Figure 2 This is a flowchart illustrating the multi-dimensional rule matching process of the intelligent prescription review method based on multi-dimensional rule matching in an embodiment of the present invention. Figure 2 As shown, the process starts from "Start," first executing "Obtain Prescription Information" to retrieve prescription data to be reviewed (including patient, medication, diagnosis, etc.). Through "Multi-dimensional Parallel Rule Matching," two types of detection branches are initiated simultaneously: Branch 1: First, perform "Drug Interaction Detection," then analyze "Patient's Historical Medication Use" (identifying duplicate / overdosing, etc.); Branch 2: First, perform "Medical Insurance Policy Compliance Detection," then perform "Clinical Diagnosis Matching Analysis" (verifying whether medication and diagnosis are compatible).
[0032] The detection results from the two branches are summarized in "Result Summary Analysis", followed by "Violation Level Assessment" (classifying violations as clear violations or highly suspicious, etc.), and finally the audit conclusion is presented through "Result Display", thus ending the process.
[0033] This process achieves multi-dimensional and comprehensive coverage of prescription review, ensuring both medication safety and compliance with medical insurance.
[0034] Transform the drug interaction rule base, medical insurance policy rule base, patient medication history rule base, and clinical diagnosis rule base into executable rule expressions; Based on the rule expression, multi-dimensional rule cross-matching review is performed on the prescription information to be reviewed.
[0035] A rule-based matching mechanism is employed, transforming various rules into executable rule expressions and achieving efficient multi-dimensional matching through rule priority management. The rule expressions use SQL-like syntax, making them easy for hospital administrators to understand and maintain, for example: IF (Drug Name = 'Metformin Hydrochloride Extended-Release Tablets') AND; (Diagnose NOT LIKE '%diabetes%') AND; (Age <18 OR Age >70) THEN; It was marked as 'mildly suspicious' because 'the indication is not suitable; this drug is mainly used for diabetic patients'.
[0036] Figure 3 This is a diagram illustrating the core model relationship of the rule management in the prescription intelligent review method based on multi-dimensional rule matching in this invention. Figure 3 As shown, the indicator layer: the "indicator model" contains multiple "indicators" through a "combination" relationship, that is, the indicator model is a collection carrier of indicators.
[0037] Rule layer: "Rules" are mapped to "indicators" through "associations" (rules take effect based on indicator data); "rule groups" contain multiple "rules" through "aggregation" relationships, that is, a rule group is a collection of rules; "rules" depend on "rule engines" (rule engines are the technical support for executing rules).
[0038] Action layer: "Rules" trigger corresponding "actions" through "associations" (the result of rule matching will drive specific operations).
[0039] In addition, the "rule group" also relies on the "rule engine" to ensure that the rule group can be executed by the engine.
[0040] Simply put, this is a logical architecture where "indicators support rules, rules are aggregated into groups, and the engine executes the rules and triggers actions."
[0041] Before performing a multi-dimensional rule cross-matching review step on the prescription information to be reviewed based on a pre-built multi-dimensional review rule base, the following steps are also included: The multi-dimensional review rule library is updated in real time based on the latest policy requirements and medication rules.
[0042] Before obtaining the comprehensive review results, the following steps are also included: Obtain the individual review results from the drug interaction rule base, medical insurance policy rule base, patient history medication rule base, and clinical diagnosis rule base corresponding to the prescription information to be reviewed; The comprehensive audit result is obtained based on the individual audit results and the preset weight allocation strategy for each individual audit result.
[0043] After obtaining the comprehensive review results, the following steps are also included: The feature vector of the comprehensive review result is extracted, and the feature vector is input into the classification model to obtain the probability of violation and the level of violation of the prescription information to be reviewed. The level includes clear violation, highly suspicious and slightly suspicious.
[0044] Clear violations: Actions that clearly violate medical insurance policies or clinical drug use guidelines, such as: The drug's indications are completely inconsistent with the patient's diagnosis; The dosage of the medicine far exceeded the prescribed range; The patient has clearly restricted access to medications covered by medical insurance and has no eligible diagnosis.
[0045] Highly suspicious: There is a high probability of violations of medical insurance policies or clinical drug use guidelines, such as: The correlation between the drug's indications and the patient's diagnosis is weak; The dosage of the drug is close to the upper limit of the prescribed range; There is a potential for serious drug interactions.
[0046] Mildly suspicious: There is a possibility of violating medical insurance policies or clinical drug use guidelines, such as: The usage of this medicine differs slightly from the instructions in the package insert. Mild drug interactions exist; The patient's age or gender does not completely match the recommended population for drug use.
[0047] Figure 4 This is a flowchart illustrating the violation level classification of the prescription intelligent review method based on multi-dimensional rule matching in an embodiment of the present invention, as shown below. Figure 4 As shown, the process starts and data input is triggered by "Start". First, "Get Review Results" (i.e., the basic data after the initial review of the prescription) is obtained.
[0048] Feature processing and model invocation: Extract feature vectors from the audit results (convert the data into a format that the model can recognize), and then invoke the classification model for intelligent analysis.
[0049] Parallel analysis and result integration: The classification model performs two tasks simultaneously: "calculating the probability of violation" (quantifying the likelihood of violation) and "determining the level of violation" (classifying levels such as clear violation / highly suspicious); then the results of these two tasks are combined to "generate a detailed report".
[0050] Suggested output and display: Based on the report, "generate processing suggestions" (such as prescription modification, manual review, etc.), and finally "display the results". The process ends with "end".
[0051] This process involves a second intelligent processing of the prescription review results, making the review conclusions more accurate and actionable.
[0052] S103, Generate a prescription review report based on the comprehensive review results.
[0053] Generate a prescription review report that includes review conclusions, explanations of violations, risk warnings, and handling suggestions, and push the report to the doctor's workstation for review and further processing.
[0054] This invention integrates review rules across four dimensions: drug interactions, medical insurance policies, patient medication history, and clinical diagnosis. It achieves an organic combination of medical order information sharing and prior reminders from the National Medical Products Administration, providing a comprehensive perspective on prescription review. Through cross-validation of multi-dimensional information, it significantly improves the detection rate and accuracy of violations.
[0055] This invention establishes a full lifecycle management mechanism for rules, supporting the creation, testing, release, and optimization of rules. It enables automatic updates and version management of the rule base, ensuring that the review criteria are consistent with the latest policies. It also introduces machine learning technology to continuously optimize the accuracy and efficiency of rule matching through actual review cases.
[0056] This invention innovatively divides the review results into three levels: clear violation, highly suspicious, and slightly suspicious. Each level corresponds to a different processing procedure and display method, which helps doctors quickly identify and deal with high-risk issues, provides detailed explanations of the reasons for violations and relevant evidence, and enhances the interpretability and credibility of the review results.
[0057] Through the above technological innovations, this invention can effectively improve the quality of medical care, ensure patient medication safety, standardize medical practices, and reduce unreasonable expenditures of medical insurance funds, thus possessing significant practical value and promotional significance.
[0058] Figure 5 This is a schematic diagram illustrating the main components of the prescription intelligent review system based on multi-dimensional rule matching in an embodiment of the present invention. Figure 5 As shown, the prescription intelligent review system 1 based on multi-dimensional rule matching provided in this embodiment of the invention includes an information acquisition module 10, a review module 20, and a report generation module 30.
[0059] Information acquisition module 10 is used to acquire information related to the prescription to be reviewed; The review module 20 is used to perform multi-dimensional rule cross-matching review on the prescription information to be reviewed based on a pre-built multi-dimensional review rule base to obtain a comprehensive review result. The multi-dimensional review rule base includes a drug interaction rule base, a medical insurance policy rule base, a patient's historical medication rule base, and a clinical diagnosis rule base. The report generation module 30 is used to generate a prescription review report based on the comprehensive review results.
[0060] Figure 6 This is an architecture diagram of the prescription intelligent review system based on multi-dimensional rule matching in an embodiment of the present invention, as shown below. Figure 6 As shown, the data input layer uses the Hospital Information System (HIS) as the data source to transmit the medical order information (including patient, drug, diagnosis, etc.) corresponding to the prescription to the system.
[0061] Core Audit Layer (M01): The "Medical Order API Service" receives and standardizes medical order information, and at the same time, the "Rule Engine Service" retrieves the audit rules in the "Rule Cache" to match and verify the medical orders. The verification results are synchronized to the "Violation Judgment Record Database" for storage, thus completing the compliance determination of the prescription.
[0062] Rule Management Layer (M02): The "Rule Management Service (AI Recognition)" connects to the "Medical Insurance Catalog Database" to obtain the latest medical insurance data, generates / updates review rules for drugs, medical insurance, etc., and stores them in the "Rule Database". The rules will be synchronized to the "rule cache" of M01 to ensure the timeliness of the review rules.
[0063] Results Transfer Layer (M03): The "Medical Insurance Feedback Service" pushes the review results of M01 to the "Medical Insurance Interface" and simultaneously sends them back to the "Violation Judgment Record Database," achieving synchronization of the review results with medical insurance and archiving within the hospital.
[0064] This architecture enables fully automated review of prescriptions from "data acquisition - rule verification - result reporting," connecting with both hospital systems and linking with medical insurance data to ensure prescription compliance.
[0065] Figure 7 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 7As shown, the electronic device 40 includes: a processor 401, a memory 402, and a bus 403; The processor 401 and the memory 402 communicate with each other via the bus 403. The processor 401 is used to call program instructions in the memory 402 to execute the methods provided in the above-described method embodiments, and to execute the methods provided in the embodiments of the present invention.
[0066] This embodiment provides a non-transitory computer-readable storage medium that stores computer instructions, which cause a computer to execute the method provided in this embodiment of the invention.
[0067] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various storage media capable of storing program code, such as ROM, RAM, magnetic disk, or optical disk.
[0068] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A prescription intelligent review method based on multi-dimensional rule matching, characterized in that, include: Obtain information related to prescriptions awaiting review; Based on a pre-built multi-dimensional audit rule base, multi-dimensional rule cross-matching audit is performed on the relevant information of the prescription to be audited to obtain a comprehensive audit result. The multi-dimensional audit rule base includes a drug interaction rule base, a medical insurance policy rule base, a patient's historical medication rule base, and a clinical diagnosis rule base. A prescription review report is generated based on the comprehensive review results.
2. The prescription intelligent review method based on multi-dimensional rule matching according to claim 1, characterized in that, The information related to the prescriptions to be reviewed includes the patient's basic information, clinical diagnosis information, prescription drug information, and historical prescription information.
3. The prescription intelligent review method based on multi-dimensional rule matching according to claim 2, characterized in that, The multi-dimensional rule cross-matching review of the prescription information to be reviewed, based on a pre-built multi-dimensional review rule base, includes: Based on the drug interaction rule base, the prescription drug information in the prescription information to be reviewed is matched and reviewed for interaction. Based on the aforementioned medical insurance policy rule base, the prescription drug information and clinical diagnosis information in the prescription information to be reviewed are matched and reviewed for medical insurance compliance. Based on the patient's historical medication rule base, the historical prescription information and current prescription drug information in the prescription information to be reviewed are matched and reviewed for medication continuity and rationality. Based on the clinical diagnostic rule base, the clinical diagnostic information and prescription drug information in the prescription information to be reviewed are used to perform diagnostic and medication suitability matching and review.
4. The prescription intelligent review method based on multi-dimensional rule matching according to claim 1, characterized in that, Before performing a multi-dimensional rule cross-matching review step on the prescription information to be reviewed based on a pre-built multi-dimensional review rule base, the following steps are also included: The multi-dimensional review rule library is updated in real time based on the latest policy requirements and medication rules.
5. The prescription intelligent review method based on multi-dimensional rule matching according to claim 1, characterized in that, The multi-dimensional rule cross-matching review of the prescription information to be reviewed, based on a pre-built multi-dimensional review rule base, includes: Transform the drug interaction rule base, medical insurance policy rule base, patient medication history rule base, and clinical diagnosis rule base into executable rule expressions; Based on the rule expression, multi-dimensional rule cross-matching review is performed on the prescription information to be reviewed.
6. The prescription intelligent review method based on multi-dimensional rule matching according to claim 1, characterized in that, Before obtaining the comprehensive review results, the following steps are also included: Obtain the individual review results from the drug interaction rule base, medical insurance policy rule base, patient history medication rule base, and clinical diagnosis rule base corresponding to the prescription information to be reviewed; The comprehensive audit result is obtained based on the individual audit results and the preset weight allocation strategy for each individual audit result.
7. The prescription intelligent review method based on multi-dimensional rule matching according to claim 1, characterized in that, After obtaining the comprehensive review results, the following steps are also included: The feature vector of the comprehensive review result is extracted, and the feature vector is input into the classification model to obtain the probability of violation and the level of violation of the prescription information to be reviewed. The level includes clear violation, highly suspicious and slightly suspicious.
8. A system for intelligent prescription review based on multi-dimensional rule matching, characterized in that, include: The information acquisition module is used to acquire information related to prescriptions pending review. The review module is used to perform multi-dimensional rule cross-matching review on the prescription information to be reviewed based on a pre-built multi-dimensional review rule base to obtain a comprehensive review result. The multi-dimensional review rule base includes a drug interaction rule base, a medical insurance policy rule base, a patient's historical medication rule base, and a clinical diagnosis rule base. The report generation module is used to generate a prescription review report based on the comprehensive review results.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.
10. A non-transitory computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.