Drug evaluation method and related equipment

Abstract

The embodiment of the invention provides a medicine evaluation method and related equipment, and belongs to the technical field of information processing. The method comprises the following steps: acquiring medicine input information corresponding to a first medicine; the first medicine is any medicine, and the medicine input information comprises medicine type data; generating a corresponding medicine evaluation template according to medicine type data in the medicine input information; collecting expert evaluation information corresponding to the first drug through the drug evaluation template; the expert evaluation information comprises text data and score data; and performing text analysis on the text data corresponding to the first drug through the drug evaluation model to generate a model evaluation score, and integrating the model evaluation score and the score data to obtain a target evaluation result corresponding to the first drug. According to the embodiment of the invention, the consistency and objectivity of the drug evaluation result can be remarkably improved, so that more comprehensive and intelligent decision support is provided for drug selection of medical institutions.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and in particular to a drug evaluation method and related equipment. Background Technology

[0002] With the rapid development of the pharmaceutical industry and the continuous emergence of new drugs, medical institutions face numerous technical challenges in the drug selection process. The reliance on manual processes and paper documents leads to inefficiency, with evaluation cycles lasting 3-6 weeks. Furthermore, inconsistent expert evaluation standards and a lack of an objective and consistent evaluation framework persist. Simultaneously, traditional methods struggle to effectively process large amounts of unstructured text data, failing to fully extract the value of expert opinions. These problems severely impact the standardization, efficiency, and scientific rigor of drug selection, necessitating the development of intelligent drug evaluation systems to enhance the informatization and precision of the selection process. Summary of the Invention

[0003] Version 1: The main purpose of this application is to propose a drug evaluation method and related equipment, which can significantly improve the consistency and objectivity of drug evaluation results, thereby providing medical institutions with more comprehensive and intelligent decision support for drug selection.

[0004] To achieve the above objectives, one aspect of this application provides a drug evaluation method, the method comprising:

[0005] Obtain the drug entry information corresponding to the first drug; the first drug can be any type of drug, and the drug entry information includes drug type data;

[0006] Generate a corresponding drug evaluation template based on the drug type data in the drug entry information;

[0007] The expert evaluation information corresponding to the first drug is collected using the drug evaluation template; the expert evaluation information includes text data and scoring data.

[0008] The drug evaluation model performs text analysis on the text data corresponding to the first drug to generate a model evaluation score. The model evaluation score and the scoring data are then integrated to obtain the target evaluation result corresponding to the first drug.

[0009] In some embodiments, after obtaining the drug entry information corresponding to the first drug, the method further includes:

[0010] The integrity of the drug entry information corresponding to the first drug is checked. If the drug entry information corresponding to the first drug is found to be incomplete, new drug entry information is obtained and used as the drug entry information corresponding to the first drug.

[0011] In some embodiments, generating a corresponding drug evaluation template based on the drug type data in the drug entry information includes:

[0012] Based on the drug type data in the drug entry information, among the multiple stored initial drug evaluation templates, the initial drug evaluation template with the highest degree of matching with the drug type data is determined as the corresponding drug evaluation template.

[0013] In some embodiments, the step of generating a model evaluation score by performing text analysis on the text data corresponding to the first drug using a drug evaluation model includes:

[0014] The key features of the text are obtained by extracting key points from the text data using the drug evaluation model.

[0015] The sentiment analysis results are obtained by performing sentiment analysis on the text data using the drug evaluation model.

[0016] The model evaluation score is calculated based on the key text features and the sentiment analysis results.

[0017] In some embodiments, integrating the model evaluation score and the scoring data to obtain the target evaluation result corresponding to the first drug includes:

[0018] The target evaluation result corresponding to the first drug is obtained by weighting the model evaluation score with the first weight information corresponding to the model evaluation score, the second weight information corresponding to the scoring data, the model evaluation score, and the scoring data.

[0019] In some embodiments, before performing a weighted calculation based on the first weight information corresponding to the model evaluation score, the second weight information corresponding to the scoring data, the model evaluation score, and the scoring data to obtain the target evaluation result corresponding to the first drug, the method further includes:

[0020] The drug evaluation model is used to score the first drug in multiple dimensions based on expert evaluation information, resulting in multidimensional score data. The multidimensional score data includes basic attribute scores, clinical efficacy scores, safety scores, economic scores, and hospital demand scores.

[0021] An adjustment factor is determined based on the multidimensional scoring data; the magnitude of the adjustment factor is within a preset threshold range.

[0022] The step of weighting the model evaluation score with the first weight information corresponding to the model evaluation score, the second weight information corresponding to the scoring data, the model evaluation score, and the scoring data to obtain the target evaluation result for the first drug includes:

[0023] The model evaluation score, the second weight information corresponding to the scoring data, the model evaluation score, and the scoring data are weighted and calculated. The weighted result is then added to the adjustment factor to obtain the target evaluation result for the first drug.

[0024] In some embodiments, the method further includes:

[0025] Based on the target evaluation results corresponding to the first drug, a multi-dimensional visualization chart is automatically generated; the multi-dimensional visualization chart is used to display the scoring data and the model evaluation score.

[0026] To achieve the above objectives, another aspect of this application provides a drug evaluation device, the device comprising:

[0027] The information acquisition module is used to acquire the drug entry information corresponding to the first drug; the first drug is any kind of drug, and the drug entry information includes drug type data;

[0028] The template generation module is used to generate a corresponding drug evaluation template based on the drug type data in the drug entry information.

[0029] The information collection module is used to collect expert evaluation information corresponding to the first drug through the drug evaluation template; the expert evaluation information includes text data and scoring data.

[0030] The target evaluation module is used to generate a model evaluation score by performing text analysis on the text data corresponding to the first drug through a drug evaluation model, and to integrate the model evaluation score and the scoring data to obtain the target evaluation result corresponding to the first drug.

[0031] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0032] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0033] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method.

[0034] The embodiments of this application include at least the following beneficial effects: This application provides a drug evaluation method and related equipment. The method includes: obtaining drug entry information corresponding to a first drug; the first drug is any type of drug, and the drug entry information includes drug type data; generating a corresponding drug evaluation template based on the drug type data in the drug entry information; collecting expert evaluation information corresponding to the first drug through the drug evaluation template; the expert evaluation information includes text data and scoring data; performing text analysis on the text data corresponding to the first drug through a drug evaluation model to generate a model evaluation score, and integrating the model evaluation score and the scoring data to obtain the target evaluation result corresponding to the first drug. Implementing the embodiments of this application can automatically generate a standardized drug evaluation template matching the drug type information, and perform semantic analysis on the text data contained in the expert evaluation information through a drug evaluation model to obtain a model evaluation score. The model evaluation score is fused with the scoring data directly given by the experts, and the final target evaluation result is formed through multi-source information integration technology. This can significantly improve the consistency and objectivity of drug evaluation results, thereby providing more comprehensive and intelligent decision support for medical institutions to select drugs. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application;

[0036] Figure 2 This is a flowchart of the drug evaluation method provided in the embodiments of this application;

[0037] Figure 3 This is a flowchart provided in this application embodiment, which integrates model evaluation scores and scoring data to obtain the target evaluation result corresponding to the first drug;

[0038] Figure 4 This is a system framework diagram of one embodiment;

[0039] Figure 5 This is a diagram showing the relationship between system functional modules in one embodiment;

[0040] Figure 6 This is a system workflow diagram in one embodiment;

[0041] Figure 7 This is a schematic diagram of the expert evaluation interface and scoring form in one embodiment;

[0042] Figure 8 This is a flowchart of a drug evaluation example;

[0043] Figure 9 This is a diagram illustrating the generation and display of an evaluation report in one embodiment;

[0044] Figure 10 This is a schematic diagram of the structure of the drug evaluation device provided in the embodiments of this application;

[0045] Figure 11 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0047] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0048] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0050] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0051] 1) VBA (Visual Basic for Applications), a programming language that can be used to extend Office applications.

[0052] In related technologies, with the rapid development of the pharmaceutical industry and the continuous emergence of various new drugs, the pharmacy committees of medical institutions face the important task of scientifically evaluating and selecting drugs. Scientific and standardized drug selection helps optimize the drug supply catalog, ensure the safety, effectiveness, and economy of clinical drug use, and promote rational drug use. The "Rapid Guidelines for Drug Evaluation and Selection in Chinese Medical Institutions (Second Edition)" issued by the National Health Commission provides guidance for standardizing drug selection in medical institutions. However, in practice, drug selection and evaluation work still faces many challenges: First, the evaluation process is inefficient. Traditional drug evaluation mainly relies on manual processing and paper documents, resulting in a time-consuming and inefficient process from data collection and expert evaluation to result summarization. According to research, the evaluation cycle for a new drug typically takes 3-6 weeks. Second, evaluation standards are inconsistent. Different experts, due to differences in knowledge background, clinical experience, and focus, have significantly different evaluation results for the same drug, lacking an objective and unified evaluation framework. Third, data processing capabilities are limited. Traditional evaluation methods struggle to effectively process and analyze the large amounts of unstructured text data provided by experts, especially the implicit value information in expert opinions. Fourth, decision support is insufficient. There is a lack of intelligent analytical tools capable of comprehensively considering multi-dimensional factors such as efficacy, safety, cost-effectiveness, and pharmaceutical characteristics. Pharmacy committee decisions often lack comprehensive and objective data support. These problems severely restrict the improvement of the quality and efficiency of drug selection and evaluation, affecting the scientific and standardized nature of drug supply and clinical use. Therefore, there is an urgent need to develop an intelligent drug selection and evaluation system to improve the standardization, precision, and informatization of drug selection.

[0053] Currently, there are some studies on drug selection and evaluation systems both domestically and internationally, but most of them have the following shortcomings: First, the system architecture is complex and the implementation cost is high, making it difficult to promote and apply in primary healthcare institutions; second, the evaluation indicators are not comprehensive or flexible enough, making it difficult to adapt to different drugs and selection needs; third, the integration and utilization of multi-source heterogeneous evidence data is insufficient, making it difficult to form a comprehensive and objective selection basis; and fourth, the level of intelligence is not high, and expert review still requires a lot of manual operation and judgment.

[0054] In view of this, this application provides a drug evaluation method and related equipment, which can significantly improve the consistency and objectivity of drug evaluation results, thereby providing medical institutions with more comprehensive and intelligent decision support for drug selection.

[0055] The drug evaluation method provided in this application relates to the field of information processing technology. The drug evaluation method provided in this application can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the drug evaluation method, but is not limited to the above forms.

[0056] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0057] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0058] like Figure 1 The diagram shown is a schematic representation of an implementation environment provided in an embodiment of this application. (Refer to...) Figure 1The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected via a network, either wirelessly or via a wired connection, to complete data transmission and exchange.

[0059] Server 101 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0060] Additionally, server 101 can also be a node server in a blockchain network. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0061] Terminal 102 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. Terminal 102 and server 101 can be directly or indirectly connected via wired or wireless communication, and this embodiment of the application does not impose any limitations.

[0062] For example, based on Figure 1 The implementation environment shown in this application embodiment provides an image auditing method. The following description uses the application of this image auditing method in server 101 as an example. It can be understood that the image auditing method can also be applied in terminal 102.

[0063] Figure 2 This is an optional flowchart of the drug evaluation method provided in the embodiments of this application. The subject executing the drug evaluation method can be any of the aforementioned electronic devices (including servers or terminals). Figure 2 The method may include, but is not limited to, steps S201 to S204.

[0064] Step S201: Obtain the drug entry information corresponding to the first drug; the first drug can be any type of drug, and the drug entry information includes drug type data.

[0065] In some embodiments, after authentication, the administrator enters the management interface and can configure several core parameters, including the service interface address of the drug evaluation model, a fine-grained user permission system, and a dynamically maintainable evaluation template library. The service interface of the drug evaluation model typically refers to an external artificial intelligence service called via RESTful API or gRPC. This drug evaluation model can be used for data analysis and intelligent reasoning in subsequent stages. The user permission system is implemented based on a role-based access control model, ensuring that users with different roles have corresponding data and function operation permissions. The evaluation template library predefines a structured evaluation indicator framework for different categories of drugs, which can be used to standardize the evaluation process. Optionally, the administrator can initiate an evaluation task and fill in basic information about the drug, such as its generic name, drug category, and indications. After submission, the electronic device can automatically crawl and integrate multi-source heterogeneous data about the drug from internal and external databases or compliant network sources, such as drug instructions, clinical trial reports, and authoritative evidence-based medicine guidelines, forming a complete chain of reference evidence, relying on pre-integrated data interfaces and web crawling technology. This automated data integration process not only significantly reduces the time cost of manual material collection, but also improves the comprehensiveness and reliability of the information required for assessment, thereby providing a consistent and standardized data foundation for subsequent scientific assessment and decision-making.

[0066] As an optional implementation, the drug entry information corresponding to the first drug is obtained. This drug entry information may include basic information manually filled in by the administrator, as well as automatically imported drug-related data, such as drug instructions, clinical trial reports, and authoritative evidence-based medicine guidelines. The drug type data included in the drug entry information can be used to match and generate corresponding drug evaluation templates.

[0067] In some embodiments, the drug entry information corresponding to the first drug is subjected to integrity checks. If incomplete drug entry information is detected, new drug entry information is re-acquired and used as the drug entry information for the first drug. Furthermore, the electronic device can perform automated integrity checks on the drug entry information corresponding to the first drug. This can be achieved through a predefined integrity rule base and structured verification algorithms, systematically checking the existence of required fields, whether the data format conforms to specifications, and whether the information logic is consistent. If incomplete information such as missing information, format errors, or logical conflicts is detected, a data re-collection mechanism will be automatically triggered. This will re-initiate the form filling request or call an external data interface to complete the information, allowing the administrator to re-enter the information for the first drug based on the initiated form. This will obtain updated drug entry information that meets the integrity requirements and serve as the final drug entry information for the first drug. Integrity checks on the drug entry information corresponding to the first drug, based on a rule engine and real-time verification mechanism, not only significantly improve the accuracy and reliability of drug information management but also provide high-quality data input assurance for subsequent drug evaluation and analysis processes.

[0068] Step S202: Generate the corresponding drug evaluation template based on the drug type data in the drug entry information.

[0069] In some embodiments, based on drug type data, such as antibiotics, oncology drugs, or chronic disease treatment drugs, a rule engine and template mapping technology are automatically invoked to generate standardized evaluation templates that meet the requirements of the "Rapid Guidelines for Drug Evaluation and Selection in Chinese Medical Institutions." Through a built-in drug classification knowledge graph and structured parsing of guideline clauses, differentiated automatic configuration of evaluation dimensions, indicator weights, and evidence requirements for different drug categories is achieved, ensuring the standardization and professionalism of the evaluation process. Subsequently, the administrator selects review members from the expert database in the relevant fields. The electronic device can automatically and evenly distribute evaluation tasks based on predefined expert field tags and workload status, using a task allocation algorithm to improve the efficiency and rationality of assignment. After task allocation is completed, an integrated messaging service is triggered, automatically sending evaluation invitations, operation instructions, and related materials to the experts via email or in-site messages through multiple notification mechanisms. Generating corresponding drug evaluation templates based on drug type data in the drug entry information significantly reduces manual intervention, improves the efficiency and accuracy of the evaluation preparation stage, and ensures close integration of the evaluation work with national guidelines and orderly expert collaboration.

[0070] Furthermore, based on the drug type data in the drug entry information, the initial drug evaluation template with the highest degree of matching with the drug type data can be determined from multiple stored initial drug evaluation templates and used as the corresponding drug evaluation template. Based on the drug type data in the entered drug information, a built-in template matching algorithm automatically searches and compares multiple pre-stored initial drug evaluation templates to identify the template with the highest matching degree to the current drug type. The template matching algorithm can be based on rule classification or semantic similarity calculation. According to the predefined drug classification system and template association rules, it can be ensured that the evaluation dimensions and indicators are adapted to the drug characteristics, and the optimal template from the matching results can be automatically selected as the official evaluation template for the drug. This improves the accuracy and efficiency of evaluation template allocation, ensures the standardization and relevance of subsequent drug evaluations, and provides fundamental support for scientific and consistent drug evaluation.

[0071] Step S203: Collect expert evaluation information corresponding to the first drug through the drug evaluation template; the expert evaluation information includes text data and scoring data.

[0072] In some embodiments, after the assessment task is initiated, experts log in to the system through identity authentication and access a customized assessment interface. This interface provides structured electronic forms based on drug assessment templates, supports multi-dimensional quantitative scoring (e.g., using a 1-5 point Likert scale), free discussion of multiple key dimensions of textual evaluation (e.g., efficacy, safety, cost-effectiveness), and the uploading of evidence materials including documents and reports in PDF, Word, and other formats. All submitted assessment data is encrypted using TLS-based end-to-end encryption during transmission to ensure the confidentiality and integrity of assessment information and evidence materials, and is ultimately securely stored in the database. The expert assessment information includes textual data and scoring data. The textual data can be free discussion of multiple key dimensions of textual evaluation (e.g., efficacy, safety, cost-effectiveness) and evidence materials including PDF and Word documents. The scoring data can be the expert's scores for each dimension; for example, the expert can score based on dimensions such as cost-effectiveness and safety, with scores ranging from 1 to 5 points.

[0073] By collecting expert evaluation information corresponding to the first drug through drug evaluation templates, the comprehensiveness and standardization of the evaluation content are ensured through structured data collection. Furthermore, the reliability and compliance of the evaluation process are enhanced through encrypted transmission and centralized storage technologies, providing a high-quality and highly secure data foundation for subsequent intelligent analysis and decision-making.

[0074] Step S204: The drug evaluation model performs text analysis on the text data corresponding to the first drug to generate a model evaluation score, and integrates the model evaluation score and the scoring data to obtain the target evaluation result corresponding to the first drug.

[0075] In some embodiments, automated text analysis is performed on text data related to the first drug using a drug evaluation model. This drug evaluation model is typically based on natural language processing techniques, capable of extracting relevant information from unstructured text data, including expert opinions and drug instructions, using sentiment analysis, keyword extraction, and semantic understanding, and generating a quantified model evaluation score accordingly. Subsequently, through multi-source information fusion techniques, the model evaluation score is weighted and integrated with structured data such as expert evaluation scores, or fused at a decision level, to form the final target evaluation result.

[0076] Furthermore, key points are extracted from the text data using a drug evaluation model to obtain key text features; sentiment analysis is then performed on the text data using the same model to obtain sentiment analysis results; and a model evaluation score is calculated based on the key text features and the sentiment analysis results. The drug evaluation model performs in-depth analysis of the input text data. First, key point extraction techniques from natural language processing are used, based on keyword extraction or entity recognition from a pre-trained language model, to identify and extract core elements closely related to drug evaluation from unstructured text, forming structured key text features. Subsequently, the drug evaluation model uses sentiment analysis algorithms, such as a Transformer-based sentiment classification model, to determine the sentiment tendency of the text, outputting analysis results such as sentiment polarity and intensity. Finally, the key text features and sentiment analysis results are integrated, and a quantitative model evaluation score is generated through a pre-defined weight allocation or neural network calculation method.

[0077] By extracting key points from text data using a drug evaluation model, key text features are obtained. Sentiment analysis of the text data is then performed using the same model to obtain sentiment analysis results. Based on the key text features and sentiment analysis results, a model evaluation score is calculated. This enables automated and refined analysis of textual information such as expert opinions, significantly improving the efficiency, objectivity, and interpretability of drug evaluation decisions.

[0078] In this embodiment, drug entry information corresponding to a first drug is obtained; the first drug can be any type of drug, and the drug entry information includes drug type data; a corresponding drug evaluation template is generated based on the drug type data in the drug entry information; expert evaluation information corresponding to the first drug is collected through the drug evaluation template; the expert evaluation information includes text data and scoring data; a drug evaluation model performs text analysis on the text data corresponding to the first drug to generate a model evaluation score, and integrates the model evaluation score and the scoring data to obtain the target evaluation result corresponding to the first drug. This allows for the automatic generation of a standardized drug evaluation template matching the drug type information, and semantic analysis of the text data contained in the expert evaluation information is performed through the drug evaluation model to obtain a model evaluation score. This model evaluation score is then fused with the scoring data directly given by the experts. Through multi-source information integration technology, the final target evaluation result is formed, which significantly improves the consistency and objectivity of the drug evaluation results, thereby providing more comprehensive and intelligent decision support for medical institutions in drug selection.

[0079] Figure 3 This is a flowchart provided in this application embodiment, which integrates model evaluation scores and scoring data to obtain the target evaluation result corresponding to the first drug. Figure 2 The steps may include, but are not limited to, step S301.

[0080] Step S301: The target evaluation result corresponding to the first drug is obtained by weighting the first weight information corresponding to the model evaluation score, the second weight information corresponding to the scoring data, the model evaluation score, and the scoring data.

[0081] In some embodiments, based on a preset weight configuration, a first weight corresponding to the model evaluation score of the drug evaluation model and a second weight corresponding to the expert evaluation score data are obtained respectively. The two types of scores are then integrated and calculated using a weighted fusion algorithm to finally generate the target evaluation result for the first drug. Further, the first weight can be 30%, and the second weight can be 70%, which can be adjusted by the administrator according to actual needs.

[0082] Based on the stored "Rapid Guidelines for Drug Evaluation and Selection in Chinese Medical Institutions", the electronic device is designed with a tree-structured evaluation form, which consists of the following technical components: an evaluation form interface based on the UserForm control, a dynamically generated scoring scale (1-5 point system or 1-10 point system optional); a text input area that allows experts to freely fill in their evaluation opinions; and support for uploading references and evidence materials.

[0083] The evaluation dimensions are designed as follows: (1) Basic attribute evaluation (weight 10%): completeness of drug registration information, clinical application history, and compliance with the requirements of the hospital preparation committee; (2) Clinical efficacy evaluation (weight 30%): level of evidence-based medicine, comparative advantage with existing treatment regimens, scope of applicability to patient populations, and relevance to treatment endpoints; (3) Safety evaluation (weight 20%): incidence and severity of adverse reactions, safety data for special populations (elderly, children, pregnant women, etc.), drug interaction risks, and drug monitoring requirements; (4) Economic evaluation (weight 20%): cost-effectiveness analysis, budget impact analysis, and price comparison with alternative drugs; (5) Other attributes (weight 10%): national medical insurance, national essential drugs, national centralized procurement drugs, original / reference / consistency evaluation, and status of manufacturers; (6) Hospital actual needs (weight 10%): urgency of patient needs, willingness of departments to use the drug, and consistency with the hospital's drug use direction.

[0084] As an optional implementation method, a drug evaluation model is used to perform multidimensional scoring on the first drug based on expert evaluation information, resulting in multidimensional scoring data. This multidimensional scoring data includes basic attribute scores, clinical efficacy scores, safety scores, economic efficiency scores, and hospital demand scores. An adjustment factor is determined based on the multidimensional scoring data. The magnitude of the adjustment factor is within a preset threshold range. A weighted calculation is performed based on the first weight information corresponding to the model evaluation score, the second weight information corresponding to the scoring data, the model evaluation score, and the scoring data. The weighted calculation result is then added to the adjustment factor to obtain the target evaluation result for the first drug. The drug evaluation model integrates and analyzes the evaluation information provided by experts, automatically generating structured scoring data containing multiple dimensions such as basic attributes, clinical efficacy, safety, economic efficiency, and hospital demand based on a multidimensional quantitative evaluation system. An adjustment factor is dynamically calculated from this multidimensional score according to preset rules and business logic. This adjustment factor is strictly limited to a predefined threshold range, which can be ±0.5, with no specific limitation. Finally, using multi-source information fusion technology, the model evaluation score (by first weight) and the scoring data (by second weight) are weighted and calculated, and the weighted result is added to the adjustment factor to obtain the target evaluation result of the first drug.

[0085] Furthermore, the drug evaluation model can intelligently analyze evaluation data by calling the Open AI API. The HTTP request library uses VBA's WinHttp object to implement API calls, the JSON parsing tool uses custom VBA functions to process JSON data, and preprocesses the expert evaluation text by word segmentation, stop word removal, etc. Finally, the AI ​​analysis results are mapped to the system evaluation index system to obtain the model evaluation score.

[0086] The model evaluation score is weighted according to the first weight information, the second weight information, the model evaluation score, and the scoring data. The weighted result is then added to the adjustment factor to obtain the target evaluation result for the first drug. By introducing a dynamically adaptable adjustment factor, the objectivity and consistency of the evaluation process are maintained, while the system's responsiveness to complex real-world constraints is enhanced. This makes the final result both quantitatively rigorous and business-adaptable, improving the overall scientific nature and decision support value of drug evaluation.

[0087] In some embodiments, a multi-dimensional visualization chart is automatically generated based on the target assessment results corresponding to the first drug. This chart displays scoring data and model evaluation scores. Based on the target assessment results of the first drug, a data visualization engine is automatically invoked to generate an integrated visualization chart that incorporates multi-dimensional information. This chart can clearly present the drug's scoring data in dimensions such as basic attributes, clinical efficacy, safety, and cost-effectiveness through various formats, including integrated radar charts, bar charts, and weighted index curves. Simultaneously, the model evaluation scores are prominently embedded in the same view for comparative display. A weighted algorithm is used to calculate the multi-dimensional scores, and scoring adjustment factors are designed. Quantitative scores are fine-tuned based on AI text analysis results. VBA chart drawing functionality is used to automatically generate multi-dimensional evaluation radar charts, bar charts, etc., and a standardized report containing assessment conclusions and recommendations is automatically generated.

[0088] Based on the target assessment results corresponding to the first drug, the electronic device automatically generates multi-dimensional visualization charts, which can significantly improve the readability and interpretability of the assessment results, and also help decision-makers quickly grasp the overall performance and key characteristics of the drug, thereby supporting efficient and accurate pharmaceutical management and selection decisions.

[0089] Figure 4 A system framework diagram of one embodiment, such as Figure 4 As shown, the system's four-layer core architecture, from bottom to top, consists of: a basic platform layer, a data management layer, an intelligent analysis layer, and a display output layer. The basic platform layer, which can be developed using Excel VBA, includes the user interface and basic functional modules; the data management layer is responsible for storing and retrieving drug information, evaluation data, and user data; the intelligent analysis layer can connect to open AI services via API interfaces to achieve text analysis and decision support; and the display output layer can generate visual charts and standardized reports. Figure 4 The text clearly indicates the core components and data flow relationships at each level, reflecting the interaction logic between modules.

[0090] Figure 5 A system functional module relationship diagram in one embodiment, such as Figure 5 As shown, the Figure 5The system presents the logical relationships and data flow of five core functional modules: User Access Management, Drug Information Management, Expert Evaluation, AI Intelligent Analysis, and Comprehensive Evaluation Report. The User Access Management module handles user registration, login verification, and permission allocation; the Drug Information Management module handles information entry, categorized storage, and retrieval; the Expert Evaluation module handles template generation, quantitative scoring, and evidence uploading; the AI ​​Intelligent Analysis module handles text semantic analysis, opinion extraction, and scoring suggestions; and the Comprehensive Evaluation Report module handles weighted calculations, data visualization, and decision-making suggestion generation. Connecting lines indicates the direction of data flow, clearly defining the system's information processing paths.

[0091] Figure 6 A system workflow diagram in one embodiment, such as Figure 6 As shown, the process begins with initialization and task creation. Users can register and log in to verify their permissions, enabling permission management. Electronic devices manage drug entry information, including data entry, storage, and association. Next, templates are dynamically matched according to drug type data to generate assessment tasks, which are then assigned and communicated. Experts can upload their assessment information via electronic devices or other electronic devices. These devices utilize a drug assessment model to perform textual semantic analysis, opinion extraction, and scoring suggestions on the text data. The scoring data is then integrated and weighted using adjustment factors to obtain the target assessment result, which is then used to generate a visual report.

[0092] Figure 7 This is a schematic diagram of the expert evaluation interface and scoring form in one embodiment, such as... Figure 7 As shown, the diagram is divided into a left-hand drug information area, displaying key information such as drug name, category, and dosage form, and a right-hand evaluation operation area. The scoring form, based on the "Rapid Guidelines for Drug Evaluation and Selection in Chinese Medical Institutions," sets up six evaluation dimensions: basic attributes, clinical efficacy, safety, cost-effectiveness, other attributes, and hospital needs. Each dimension includes a quantitative scoring area where users can input a 1-5 subscale and scoring criteria; a text evaluation area, which can be a text input box for entering text data; and an evidence upload area containing a file attachment function for uploading relevant attachments, as well as marking the weights of each dimension and the data storage mapping relationship.

[0093] Figure 8 This is a flowchart of a drug evaluation example, such as... Figure 8As shown in the diagram, this figure details the technical process of drug evaluation, including the data preprocessing stage, which involves text cleaning, word segmentation, and stop word removal of the text data in the expert evaluation information; API calls that can request the construction of a drug evaluation model, parameter settings, and response processing; and result parsing that involves data analysis, key information extraction, and structured storage of the expert evaluation information, demonstrating the professional technical implementation path.

[0094] Figure 9 This is a screenshot showing the generation and display of an evaluation report in one embodiment, such as... Figure 9 As shown, the system-generated standardized evaluation report format includes: a report header, a comprehensive scoring area, a visualization chart area, an expert opinion area, an AI analysis area, and a decision-making recommendation area. The report header may include the drug name, evaluation date, and number of experts; the comprehensive scoring area may include the total score and scores for each dimension, with color coding; the visualization chart area may include multi-dimensional radar charts and bar charts of the scoring composition; the expert opinion area may include key evaluation points and consistency analysis; the AI ​​analysis area may include drug advantages, risks, and alternative drug recommendations; and the decision-making recommendation area may include introduction recommendations, usage conditions, and monitoring requirements. The logical connection between each part of the report and the underlying data is also clearly indicated.

[0095] In this embodiment, the target evaluation result of the first drug is obtained by weighting the first weight information corresponding to the model evaluation score, the second weight information corresponding to the scoring data, the model evaluation score, and the scoring data. This not only improves the scientificity and comprehensiveness of the evaluation result, but also enhances the system's fault tolerance and interpretability in complex decision-making scenarios, providing a more reliable and consistent quantitative basis for drug selection.

[0096] Please see Figure 10 This application also provides a drug evaluation device that can implement the above-described method. The device includes:

[0097] The information acquisition module 1001 is used to acquire the drug entry information corresponding to the first drug; the first drug can be any drug, and the drug entry information includes drug type data;

[0098] The template generation module 1002 is used to generate a corresponding drug evaluation template based on the drug type data in the drug entry information.

[0099] The information collection module 1003 is used to collect expert evaluation information corresponding to the first drug through the drug evaluation template; the expert evaluation information includes text data and scoring data.

[0100] The target evaluation module 1004 is used to generate a model evaluation score by performing text analysis on the text data corresponding to the first drug through the drug evaluation model, and to integrate the model evaluation score and the scoring data to obtain the target evaluation result corresponding to the first drug.

[0101] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0102] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0103] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0104] Please see Figure 11 , Figure 11 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0105] The processor 1101 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0106] The memory 1102 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 1102 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1102 and is called and executed by the processor 1101 using the methods described in the embodiments of this application.

[0107] Input / output interface 1103 is used to implement information input and output;

[0108] The communication interface 1104 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0109] Bus 1105 transmits information between various components of the device (e.g., processor 1101, memory 1102, input / output interface 1103, and communication interface 1104);

[0110] The processor 1101, memory 1102, input / output interface 1103 and communication interface 1104 are connected to each other within the device via bus 1105.

[0111] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0112] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0113] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0114] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0115] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0116] The drug evaluation methods, devices, electronic devices, storage media, and program products provided in this application can significantly improve the consistency and objectivity of drug evaluation results, thereby providing medical institutions with more comprehensive and intelligent decision support for drug selection.

[0117] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0118] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0119] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0121] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application 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 interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or 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.

[0122] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0124] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0125] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0126] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0127] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method of evaluating a pharmaceutical product, characterized by, The method comprises the following steps: Obtaining drug entry information corresponding to a first drug; the first drug is any drug, and the drug entry information comprises drug type data; Generating a corresponding drug evaluation template according to the drug type data in the drug entry information; Collecting expert evaluation information corresponding to the first drug through the drug evaluation template; the expert evaluation information comprises text data and score data; Performing text analysis on the text data corresponding to the first drug through a drug evaluation model to generate a model evaluation score, and integrating the model evaluation score and the score data to obtain a target evaluation result corresponding to the first drug.

2. The method of claim 1, wherein, After obtaining the drug entry information corresponding to the first drug, the method further comprises: Performing integrity detection on the drug entry information corresponding to the first drug, and if it is detected that the drug entry information corresponding to the first drug is incomplete, obtaining new drug entry information as the drug entry information corresponding to the first drug.

3. The method of claim 1, wherein, The generating of the corresponding drug evaluation template according to the drug type data in the drug entry information comprises: According to the drug type data in the drug entry information, determining an initial drug evaluation template with the highest matching degree with the drug type data from a plurality of stored initial drug evaluation templates as the corresponding drug evaluation template.

4. The method of claim 1, wherein, The generating of the model evaluation score by performing text analysis on the text data corresponding to the first drug through the drug evaluation model comprises: Extracting key points of the text data through the drug evaluation model to obtain text key features; Performing sentiment analysis on the text data through the drug evaluation model to obtain a sentiment analysis result; According to the text key features and the sentiment analysis result, the model evaluation score is calculated.

5. The method of claim 1, wherein, The integration of the model evaluation score and the score data to obtain the target evaluation result corresponding to the first drug comprises: According to the first weight information corresponding to the model evaluation score, the second weight information corresponding to the score data, the model evaluation score and the score data, weighted calculation is performed to obtain the target evaluation result corresponding to the first drug.

6. The method of claim 5, wherein, Before the weighted calculation according to the first weight information corresponding to the model evaluation score, the second weight information corresponding to the score data, the model evaluation score and the score data to obtain the target evaluation result corresponding to the first drug, the method further comprises: According to the expert evaluation information, the drug evaluation model performs multi-dimensional scoring on the first drug to obtain multi-dimensional scoring data; the multi-dimensional scoring data comprises basic attribute score, clinical efficacy score, safety score, economy score and hospital demand score; Determining an adjustment factor according to the multi-dimensional scoring data; the size of the adjustment factor is within a preset threshold range; The weighted calculation according to the first weight information corresponding to the model evaluation score, the second weight information corresponding to the score data, the model evaluation score and the score data to obtain the target evaluation result corresponding to the first drug comprises: The first weight information corresponding to the model evaluation score, the second weight information corresponding to the score data, the model evaluation score and the score data are weighted calculated, and the result of the weighted calculation is added to the adjustment factor to obtain the target evaluation result corresponding to the first drug.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: According to the target evaluation result corresponding to the first drug, a multi-dimensional visualization chart is automatically generated; the multi-dimensional visualization chart is used to display the score data and the model evaluation score.

8. A drug evaluation device, characterized by, The device comprises: An information acquisition module is configured to acquire drug entry information corresponding to a first drug; the first drug is any kind of drug, and the drug entry information includes drug type data; A template generation module is configured to generate a corresponding drug evaluation template according to the drug type data in the drug entry information; An information acquisition module is configured to acquire expert evaluation information corresponding to the first drug through the drug evaluation template; the expert evaluation information includes text data and score data; A target evaluation module is configured to generate a model evaluation score by performing text analysis on the text data corresponding to the first drug through a drug evaluation model, and integrate the model evaluation score and the score data to obtain a target evaluation result corresponding to the first drug.

9. A computer apparatus, comprising: The computer device comprises a memory and a processor, the memory stores a computer program, and the processor realizes the method of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to realize the method of any one of claims 1 to 7.

Images