Self-service registration method and system for entry-exit health certificate

Abstract

This application relates to the field of data processing technology, and discloses a self-service registration method and system for entry-exit health certificates. The method includes: multimodal biometric collection to generate a digital identity package; dynamically generating a form based on the identity package and the health requirements of the destination, obtaining health declaration information to form a health data package; using the health data package to query the physical examination knowledge graph, matching items to generate a physical examination path map; performing quality control on distributed medical device data, and applying a self-correcting model to handle outliers; the physical examination report is reviewed at multiple levels to generate a health certificate decision package; and realizing multi-channel distribution and verification of electronic health certificates. This application realizes the digitization and intelligence of the entire process, improves processing efficiency, reduces manual intervention, ensures data accuracy, and supports cross-system verification of health certificates.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a self-service registration method and system for entry-exit health certificates. Background Art

[0002] As a key component of the infectious disease surveillance system for people entering and leaving the country, entry and exit health certificates have become essential documents for those working, studying abroad, or conducting business across borders. As globalization continues and international mobility becomes increasingly frequent, the need for more convenient health certificates is becoming increasingly prominent. Traditional entry and exit medical examinations, which largely rely on manual processes, present numerous drawbacks. During the registration process, applicants must consult or fill out forms on-site, logging in and entering information. This process is not only time-consuming and labor-intensive, but also prone to errors or omissions. During peak periods, medical examination sites are often overcrowded, forcing applicants to wait in line for extended periods, creating a poor user experience.

[0003] The deficiencies in existing technologies are mainly reflected in the following aspects: the existing self-service registration devices have single functions, most of which only support basic information input, and cannot achieve real-time docking with medical examination data, and cannot meet the differentiated health requirements of different destinations; secondly, the lack of intelligent examination route planning results in applicants having to queue up multiple times during the examination, and the process is cumbersome; thirdly, the data island problem is serious, the information systems between examination centers, entry-exit management departments and health departments are independent of each other, and the data sharing mechanism is imperfect; fourthly, the quality control of examination data relies on manual experience, and lacks automated anomaly detection and correction methods, which affects the accuracy of health certificates; the issuance of health certificates is still mainly based on physical certificates, the promotion and application of electronic health certificates is insufficient, and the verification channels are single. Summary of the Invention

[0004] This application provides a self-service registration method and system for entry and exit health certificates, which is used to realize the digitization and intelligence of the entire process, improve processing efficiency, reduce manual intervention, ensure data accuracy, and support cross-system verification of health certificates.

[0005] In the first aspect, the present application provides a self-service registration method for entry and exit health certificates, which includes: collecting and processing the user's multimodal biometric information to generate a digital identity package; performing dynamic form generation and processing based on the user's basic information and the health requirements data of the destination area in the digital identity package, obtaining health declaration information, and integrating the health declaration information with the digital identity package to generate a health data package; querying and processing the physical examination knowledge graph database based on the health data package, matching the physical examination item set and generating a physical examination path map, and fusing the physical examination path map with the health data package to generate a physical examination execution package; performing real-time quality control processing on the inspection data collected by distributed medical equipment according to the physical examination execution package, using a multi-source heterogeneous data self-correction model to identify outliers in the inspection data, generating a structured physical examination result data set, and generating a physical examination report package; inputting the physical examination report package into a multi-level audit mechanism for compliance analysis and processing, generating audit results and an electronic health certificate, and generating a health certificate decision package; issuing certificates and performing cross-system data synchronization processing based on the health certificate decision package to realize multi-channel distribution and verification of electronic health certificates.

[0006] In a second aspect, the present application provides a self-service registration system for entry-exit health certificates, the self-service registration system for entry-exit health certificates comprising:

[0007] The collection module is used to collect and process the user's multimodal biometric information and generate a digital identity package;

[0008] An integration module is used to generate a dynamic form based on the basic user information and the health requirements data of the destination area in the digital identity package, obtain health declaration information, and integrate the health declaration information with the digital identity package to generate a health data package;

[0009] A query module is used to query the physical examination knowledge graph database based on the health data packet, match the physical examination item set and generate a physical examination path map, and fuse the physical examination path map with the health data packet to generate a physical examination execution package;

[0010] A control module, configured to perform real-time quality control processing on the examination data collected by the distributed medical equipment according to the physical examination execution package, identify outliers on the examination data using a multi-source heterogeneous data self-correction model, generate a structured physical examination result data set, and generate a physical examination report package;

[0011] An analysis module is used to input the medical examination report package into a multi-level audit mechanism for compliance analysis and processing, generate audit results and electronic health certificates, and generate a health certificate decision package;

[0012] The synchronization module is used to issue certificates and synchronize data across systems based on the health certificate decision package, thereby realizing multi-channel distribution and verification of electronic health certificates.

[0013] In a third aspect, a self-service registration device for an entry and exit health certificate is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the self-service registration device for the entry and exit health certificate executes the above-mentioned self-service registration method for the entry and exit health certificate.

[0014] In a fourth aspect, a computer-readable storage medium is provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned self-service registration method for entry and exit health certificates.

[0015] In the technical solution provided by this application, by collecting and processing the user's multimodal biometric information, combining it with a deep neural network model for feature extraction, and generating a unique identifier, high accuracy and security of identity authentication are achieved, effectively preventing identity impersonation; based on the combination of digital identity packages and health requirements data of the destination area, dynamic form generation is performed through a decision tree algorithm, so that the form content accurately matches the differentiated health requirements of different destinations, greatly improving user experience and reporting efficiency; the physical examination knowledge graph database is combined with a knowledge reasoning engine for intelligent matching of physical examination items, and health risk factors are identified through a machine learning algorithm, and a physical examination path map is generated in combination with the shortest path algorithm, effectively solving the problem of time waste caused by repeated examinations and unreasonable paths in traditional physical examinations; especially in terms of medical data quality control, an innovative multi-source heterogeneous data self-correction model is adopted, which can identify outliers in the examination data in real time, and if there are any anomalies, prompt further review. The Bayesian reasoning method is used to carry out targeted processing of different types of outliers, which significantly improves the accuracy and reliability of physical examination data; in the review process, a multi-level review mechanism is adopted in combination with medical knowledge graphs and expert rule bases to realize the intelligence and efficiency of the review process and reduce the subjectivity of manual review; the electronic health certificate is digitally signed through PKI technology, and multi-channel distribution is achieved, which is associated with the blockchain verification service, which not only ensures the authenticity and non-tamperability of the certificate, but also provides a convenient online verification channel to meet the mutual recognition requirements of cross-border health certificates; Overall, the contribution of the application of artificial intelligence algorithms and models in specific functional fields of the present invention is mainly reflected in: deep neural networks improve the accuracy of identity authentication, knowledge graphs cooperate with reasoning engines to realize intelligent physical examination item matching, multi-source heterogeneous data self-correction models solve the problem of medical data quality control, and multi-level machine learning review mechanisms replace traditional manual review. The comprehensive application of these AI technologies has enabled the entire entry and exit health certificate application process to achieve digital transformation and intelligent upgrading, and completely solved the problems of low efficiency of traditional methods, many human errors, data islands and cross-system verification difficulties. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a schematic diagram of an embodiment of a self-service registration method for an entry-exit health certificate in an embodiment of the present application;

[0018] Figure 2This is a schematic diagram of an embodiment of a self-service registration system for entry-exit health certificates in an embodiment of the present application;

[0019] Figure 3 It is a schematic block diagram of the structure of a self-service registration device for entry and exit health certificates in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The embodiments of the present application provide a self-service registration method and system for entry and exit health certificates. The terms first, second, third, fourth, etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate. In addition, the terms include or have and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In one embodiment of the present application, a self-service registration method for an entry-exit health certificate includes:

[0022] Step S101: Collect and process the user's multimodal biometric information to generate a digital identity package;

[0023] Step S102: Dynamically generate a form based on the user's basic information and the destination area's health requirements in the digital identity package to obtain health declaration information, and integrate the health declaration information with the digital identity package to generate a health data package;

[0024] Step S103: query the physical examination knowledge graph database based on the health data packet, match the physical examination item set and generate a physical examination path map, and fuse the physical examination path map with the health data packet to generate a physical examination execution package;

[0025] Step S104: Perform real-time quality control processing on the examination data collected by the distributed medical equipment according to the physical examination execution package, identify outliers in the examination data using a multi-source heterogeneous data self-correction model, generate a structured physical examination result data set, and generate a physical examination report package;

[0026] Step S105: Input the medical examination report package into the multi-level audit mechanism for compliance analysis and processing, generate the audit results and electronic health certificate, and generate a health certificate decision package;

[0027] Step S106: Issue certificates and synchronize data across systems based on the health certificate decision package to achieve multi-channel distribution and verification of electronic health certificates.

[0028] It is understandable that the execution subject of this application can be a self-service registration system for entry and exit health certificates, or a terminal or server, which is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0029] Specifically, a biometric acquisition device captures the user's facial, iris, and fingerprint information to generate multimodal biometric data. This data is then fed into a deep neural network model for feature extraction. This model, comprised of multiple convolutional and fully connected layers, is capable of extracting key points and texture information from various biometric features. A feature fusion algorithm integrates the feature vectors from different modalities to generate a unique identifier. When the user authenticates, the system compares this unique identifier with a pre-stored biometric template to generate an authentication result. After successful authentication, basic user information is obtained by matching the corresponding issued document. The provided document undergoes optical character recognition (OCR) processing to extract textual information, which is then cross-validated against database information. The verified personal information and unique identifier are encrypted using the national encryption algorithm SM4 to form a digital identity package. The user's basic information and unique application identification code are extracted from the digital identity package. The latest health entry requirements for the user's country of destination are then retrieved through a search. This basic user information and the destination country's requirements are then analyzed using a decision tree algorithm. This algorithm constructs a decision path based on the degree of match between the user's nationality, age, occupation, and other attributes and the destination country's requirements, generating a personalized form structure. The system applies semantic analysis technology to the form structure, translating abstract health requirements into specific form fields. Some fields are pre-populated based on previous health records, reducing the user's burden. Information entered into the interactive health form is subject to real-time data validation rules to ensure the appropriateness of the data format and content. Validated health declaration data undergoes structured processing and integration with the digital identity package to generate a digitally signed health data package.

[0030] The system extracts user information, destination country requirements, and health declaration information from the health data package to form a set of medical examination requirements. This set of requirements is then queried against the medical examination knowledge graph database. The knowledge inference engine analyzes the correlation between medical examination requirements and disease examination indicators in various countries around the world to generate an initial set of medical examination items. A machine learning algorithm analyzes the user's historical medical examination data, identifies health risk factors, and adds targeted examinations for risky items to form a risk-weighted set of medical examination items. The system compares this set with the user's electronic health record, eliminating recently validated examination items to obtain a set of medical examination items. This set is then fed into a shortest path algorithm, which takes into account the logical order of items and the layout of medical institutions to generate a medical examination path map. The system generates a QR code identifier for this path map, which contains the user identification code and medical examination item codes. The path map, item set, and QR code identifier are then integrated with the health data package to generate a medical examination execution package. The medical examination execution package extracts user information, a medical examination checklist, and a path. Identity verification is performed by scanning the QR code, and a secure connection is established with the distributed medical device. As the device collects blood analysis, imaging, and physiological indicator data, the system performs multimodal data fusion to verify data integrity and trigger re-collection instructions for missing data. Heterogeneous raw examination data is fed into a multi-source heterogeneous data self-correction model, which consists of a four-layer network structure: feature extraction, anomaly detection, data correction, and validation. After feature mapping, the system performs a data consistency check, calculates the covariance matrix and deviation threshold, and flags outliers. Bayesian inference methods combine historical examination data to calculate conditional probability distributions, determine the type of anomaly, and perform appropriate corrections to produce corrected data. This data is converted into a standard medical format, and the entire process is recorded via blockchain, forming a structured examination result dataset that is linked to the user's information to form a medical report package.

[0031] Medical examination data and application information are extracted from the medical examination report package and input into a multi-level review mechanism for analysis. This mechanism compares the completeness and indicator range of each medical examination item at the basic rule review level. Subsequently, at the comprehensive analysis review level, machine learning algorithms are used to integrate multiple examination results to identify health risks. Finally, at the destination country-specific requirements review level, verification is performed based on the destination country's conditions. The system analyzes the review results at each level for anomalies and their types. For anomalies, the system generates an electronic health certificate with an electronic signature and anti-counterfeiting mark. Applications requiring review generate an anomaly analysis report. For rejections, a non-compliance statement is generated. All review records, classification results, and processing documents are integrated into a health certificate decision package. Based on the review results of the health certificate decision package, an electronic health certificate is generated. This certificate is digitally signed using PKI technology and generates a verification QR code. Based on the user's selected delivery method, the system implements multi-channel distribution. The electronic certificate is encrypted and sent to an email or app account, while the physical certificate is sent with printing instructions to a self-service terminal. The system also performs cross-system data synchronization, pushes health information of different granularities to relevant government systems, establishes certificate lifecycle management, provides blockchain verification services, and records all operation logs to form a complete traceability chain.

[0032] In the embodiment of the present application, by collecting and processing the user's multimodal biometric information, combining it with a deep neural network model for feature extraction, and generating a unique identifier, high accuracy and security of identity authentication are achieved, effectively preventing identity fraud; based on the combination of the digital identity package and the health requirements data of the destination area, dynamic form generation is performed through a decision tree algorithm, so that the form content accurately matches the differentiated health requirements of different destinations, greatly improving the user experience and reporting efficiency; the physical examination knowledge graph database is combined with the knowledge reasoning engine to intelligently match physical examination items, and health risk factors are identified through a machine learning algorithm, and a physical examination path map is generated in combination with the shortest path algorithm, which effectively solves the problem of time waste caused by repeated examinations and unreasonable paths in traditional physical examinations; especially in terms of medical data quality control, an innovative multi-source heterogeneous data self-correction model is adopted, which can identify outliers in the examination data in real time. If anomalies exist, further review is prompted. The Bayesian reasoning method is used to carry out targeted processing of different types of outliers, which significantly improves the accuracy and reliability of physical examination data; in the review process, a multi-level review mechanism is adopted in combination with medical knowledge graphs and expert rule bases to realize the intelligence and efficiency of the review process and reduce the subjectivity of manual review; the electronic health certificate is digitally signed through PKI technology, and multi-channel distribution is achieved, which is associated with the blockchain verification service, which not only ensures the authenticity and non-tamperability of the certificate, but also provides a convenient online verification channel to meet the mutual recognition requirements of cross-border health certificates; Overall, the contribution of the application of artificial intelligence algorithms and models in specific functional fields of the present invention is mainly reflected in: deep neural networks improve the accuracy of identity authentication, knowledge graphs cooperate with reasoning engines to realize intelligent physical examination item matching, multi-source heterogeneous data self-correction models solve the problem of medical data quality control, and multi-level machine learning review mechanisms replace traditional manual review. The comprehensive application of these AI technologies has enabled the entire entry and exit health certificate application process to achieve digital transformation and intelligent upgrading, and completely solved the problems of low efficiency of traditional methods, many human errors, data islands and cross-system verification difficulties.

[0033] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0034] Collect the user's facial information, iris features and fingerprint information to obtain multimodal biometric data;

[0035] Input multimodal biometric data into a deep neural network model for feature extraction and processing to generate a unique user identifier;

[0036] Compare and verify the biometric template stored in the security database based on the unique identifier to generate an authentication result;

[0037] Based on the identity verification results, a dedicated interface is called to connect to the pre-set entry and exit management database and health database to extract basic user information;

[0038] Scan the passport or ID card provided by the user, extract the text information of the ID card through the improved OCR algorithm, cross-verify it with the user's basic information, and generate verified personal information;

[0039] The verified personal information and unique identifier are encrypted using the national encryption algorithm SM4 to generate a digital identity package containing the user's basic information and a unique application identification code.

[0040] Specifically, high-resolution biometric data collection equipment captures the user's facial, iris, and fingerprint information. Facial data is collected using a dual-mode infrared and visible light camera to capture three-dimensional facial structure and texture features. Iris data is collected by illuminating the iris with a near-infrared light source to record the unique texture pattern. Fingerprint data is captured using a capacitive sensor to determine the positional relationship between fingerprint ridges and valleys. These three types of biometric information are digitized to form a multimodal biometric dataset consisting of a pixel matrix, texture features, and a ridge distribution map. This collected multimodal biometric data is then fed into a deep neural network model for feature extraction. This deep neural network model comprises convolutional, pooling, and fully connected layers. The convolutional layers extract feature maps, the pooling layers perform feature dimensionality reduction, and the fully connected layers convert features into feature vectors. For facial data, the model extracts facial key points and texture features; for iris features, it extracts circular texture codes; and for fingerprints, it extracts minutiae position and orientation information. The features from each modality are fused in a feature fusion layer to generate a fixed-length feature code, which is then transformed into a unique user identifier using a hash function.

[0041] Based on the generated unique identifier, the biometric template stored in the secure database is compared and verified. The verification process uses a feature distance calculation method to calculate the Euclidean distance or cosine similarity between the current feature and the database template. If the distance value is less than a preset threshold or the similarity value is greater than a preset threshold, the identity is determined to be the same person and verification is successful; otherwise, verification fails. The verification result includes the verification status (pass or fail) and the similarity score. After verification, a dedicated interface is called based on the identity verification result to connect to the pre-configured entry-exit management database and health database. This interface call uses an encrypted communication protocol and sends a query request containing the unique identifier. The entry-exit management database returns basic identity information such as the user's name, gender, date of birth, nationality, and passport or ID number; the health database returns health data such as the user's previous physical examination records, vaccination status, and chronic disease history. This information is standardized in JSON format to form the user's basic information dataset. Scanning the user's passport or ID card is a key step in supplementing and cross-verifying this information. Document scanning uses a high-resolution image capture device to capture images of both the front and back of the document. Using an improved OCR algorithm, which includes four steps: image preprocessing, text region detection, text recognition, and post-processing, the text on the ID card is extracted. The improved OCR algorithm is optimized for the special characters and layouts found on ID cards from different countries, improving the accuracy of special character recognition. The extracted ID card text is cross-validated against basic user information obtained from the database at the field level, comparing key fields such as name, ID number, and date of birth to verify consistency. Once verified, the information from each source is merged to generate a complete, verified personal profile. The verified personal profile and unique identifier are encrypted using the SM4 national encryption algorithm. SM4 is a commercial Chinese encryption algorithm that uses a 128-bit key and a symmetric block cipher. The encryption process includes key expansion and round function transformations. The encryption process first serializes the personal profile and unique identifier into a data stream and encrypts them in 128-bit blocks to generate ciphertext. This ciphertext is then encapsulated with encryption metadata (such as encryption timestamp and encryption parameter identifiers) to form a digital identity package. This digital identity package contains the encrypted basic user information and a unique application identification code derived from the unique identifier, which serves as the user's identity verification credential in subsequent processes.

[0042] For example, a user named Mr. Wang needs to apply for a health certificate. He approaches the self-service terminal and positions his face toward the camera assembly, which captures a frontal facial image and depth information. He then gazes at the iris scanning area for a few seconds, which captures an iris texture image. Finally, he places his right index finger on the fingerprint sensor, which captures a fingerprint image. These three sets of biometric data are fed into a deep neural network, which extracts a 128-dimensional facial feature vector, a 256-dimensional iris feature vector, and a 96-dimensional fingerprint feature vector. Feature fusion generates a 256-bit feature code, which is then used with the SHA-256 algorithm to generate a unique identifier. The system compares the identifier with a database and calculates a similarity of 92%, exceeding the 85% verification threshold, thus passing verification. The system then calls an interface to retrieve Mr. Wang's basic information and scans his passport. The OCR recognizes that the passport number matches the database record. The system encrypts the data using the SM4 algorithm, generating a tamper-resistant digital identity package.

[0043] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0044] Extract user basic information and unique application identification code from the digital identity package to generate user basic information;

[0045] Obtain health entry requirements data for the destination area according to the user's planned destination;

[0046] Input user basic information and destination area health entry requirements data into the decision tree algorithm for analysis and processing to generate a personalized form structure;

[0047] Apply semantic analysis to the personalized form structure, convert health requirements into structured form fields, and pre-fill them based on the user's previous health records to generate an interactive health form;

[0048] The information entered by the user in the interactive health form is verified in real time through data validity verification rules to obtain formatted health declaration data;

[0049] The formatted health declaration data is structured and integrated with the digital identity package, and a health data package is generated through digital signature technology.

[0050] Specifically, the user's basic information and unique application identification code are extracted from the digital identity package. This extraction process utilizes decryption and deserialization technology. Specifically, the digital identity package is decrypted using the SM4 decryption algorithm to obtain the plaintext data corresponding to the ciphertext. This plaintext data is then deserialized using a JSON parser to extract basic user information, including fields such as name, gender, age, nationality, and previous health records, as well as the unique application identification code used for identification. This extracted information is organized into structured basic user information, which serves as the data foundation for subsequent form generation.

[0051] Based on the user's planned destination, data on health entry requirements for that destination is obtained. A decision tree algorithm constructs a multi-level tree structure, making judgments based on specific attributes at each internal node. Based on the judgment results, different branches are selected, and conclusions are drawn at leaf nodes. In this method, the decision tree algorithm uses the user's nationality as the root node and selects different entry policy branches based on nationality. The user's occupation is then used as a second-level judgment node to further refine the specific requirements of different occupational groups. Through this multi-level judgment process, a set of form fields required for each specific user is generated, forming a personalized form structure. Semantic analysis techniques are applied to this personalized form structure to transform abstract health requirements into specific form fields. Semantic analysis techniques segment and tag the health requirement text, identifying key entities and relationships within it. Semantic matching then matches the identified entities to predefined form field templates, generating specific form field definitions, including field name, data type, value range, and mandatory / required attributes. Furthermore, pre-filling is performed based on the user's previous health records. The system compares form fields with fields in the user's health records and automatically populates historical data for matching fields, reducing the user's filling burden. Through this processing, an interactive health form with pre-filled data is generated.

[0052] Real-time validation of the information entered by users in interactive health forms through data validation rules is an important step in ensuring data quality. Data validation rules include four types: format validation, range validation, logic validation, and consistency validation. Format validation checks whether the data conforms to predefined format patterns, such as date format, email format, etc.; range validation checks whether the numerical data is within the logical range, such as height value, weight value, etc.; logic validation checks whether the logical relationship between multiple fields is reasonable, such as whether the medical history and gender match; consistency validation checks whether there is a conflict between the information filled in by the user and the existing information in the system. The verification process uses a real-time trigger mechanism. When the user completes a field, verification is performed immediately. Input that does not comply with the rules will be prompted immediately and required to be corrected. Through this rigorous verification process, formatted health declaration data with correct format and reasonable content is obtained.

[0053] The final step is to structure the formatted health declaration data, integrate it with the digital identity package, and generate a health data package using digital signature technology. Structuring organizes all types of completed health declaration data according to a standardized data model, maps discrete form fields to predefined health data standards, and forms a data set with a unified structure. This structured data is then integrated with the previous digital identity package to construct the user's health application data body. Digital signature technology is used to sign the integrated data, specifically using an asymmetric encryption algorithm, encrypting the data summary with a private key, generating a digital signature, and encapsulating the original data together with the digital signature to form a tamper-proof health data package.

[0054] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0055] Extracting user identity information, destination area requirements, and health declaration information from the health data packet to obtain a physical examination requirement set, and determining an initial physical examination item set based on the physical examination requirement set;

[0056] Based on the initial set of physical examination items, machine learning algorithms are used to analyze the user's historical physical examination data, identify health risk factors, and generate a risk-weighted physical examination item set;

[0057] Compare and analyze the risk-weighted physical examination item set with the user's electronic health record, eliminate the examination items that have been completed recently and have valid results, and obtain the physical examination item set;

[0058] Input the physical examination item set into the shortest path algorithm, consider the logical order between the examination items and the spatial layout of the medical institutions, and generate a physical examination path map;

[0059] A QR code identifier containing the user's unique application identification code and the physical examination item code is generated for the physical examination path map, and the physical examination path map, physical examination item set, QR code identifier and health data package are integrated to generate a physical examination execution package.

[0060] Specifically, user identity information, destination region requirements, and health declaration information are extracted from the health data package. This extraction process utilizes data parsing and structured extraction techniques. Using a JSON or XML parser, the health data package is deconstructed to extract the user's basic identity information (including name, gender, age, and occupation), the destination region's specific health requirements (including entry-export infectious disease screening requirements and occupational health requirements), and the user's completed health declaration information (including medical history, allergies, and medication history). This extracted information is organized into a set of medical examination requirements according to a predefined data model. Each requirement item includes attributes such as requirement type, source, and priority. Furthermore, the initial set of medical examination items is determined based on the medical examination requirements set.

[0061] Based on the initial set of physical examination items, the user's historical physical examination data is analyzed using a machine learning algorithm in order to identify potential health risks. This process uses a supervised learning model, which learns the association pattern between historical physical examination data and health risks, and can predict potential risks based on the current user's historical physical examination results. The specific process extracts the user's historical physical examination data as a feature vector, including the historical values ​​of various test indicators and their changing trends; then the feature vector is input into a pre-trained risk prediction model, which uses a random forest or gradient boosting tree algorithm to calculate the probability scores of various health risks; finally, based on the risk probability score, the initial physical examination items are weighted, and the weights of examination items associated with high risks are increased to form a risk-weighted physical examination item set to ensure that the focus is on the user's health risk areas.

[0062] Comparing and analyzing the risk-weighted health checkup item set with the user's electronic health record is designed to optimize the health checkup process. This process extracts recently completed health checkup items and their results from the user's electronic health record, including the item name, time, result, and expiration date. Each risk-weighted health checkup item is then matched against the item in the health record to identify any potential duplicates. For successfully matched items, the expiration date is determined by calculating the difference between the examination time and the current time and comparing it with the item's preset expiration date. Finally, any items with normal results within their expiration date are removed from the risk-weighted set to create the health checkup item set, thus avoiding unnecessary duplicate examinations.

[0063] Inputting a collection of medical examination items into a shortest path algorithm and generating a medical examination path map is key to optimizing the user's medical examination process. The shortest path algorithm considers two main factors: the logical order between examination items and the spatial layout of the medical institution. Logical order means that certain examinations must be performed before or after others. The algorithm constructs a weighted directed graph, with nodes representing examination items and edges representing the sequential relationship and spatial distance between items. The edge weights take into account both the travel distance and the strength of the logical constraints. An improved Dijkstra algorithm is then applied to calculate the shortest path that satisfies all constraints, generating a medical examination path map that both conforms to the medical examination logic and minimizes the distance users travel within the medical institution.

[0064] Generating a QR code identifier for the physical examination roadmap and integrating relevant data to generate a physical examination execution package is the last step in preparing the physical examination process. The QR code generation process organizes the user's unique application identification code and physical examination item code into a string according to a predetermined format; then uses the QR code encoding algorithm to encode the string into a two-dimensional matrix; finally, renders the matrix into an image to generate a scannable QR code identifier. The generation of the physical examination execution package is to fuse the physical examination roadmap, physical examination item set, QR code identifier and the original health data package into a structured data package, encapsulate it in JSON or XML format, and add a digital signature to ensure data integrity. This physical examination execution package contains all the information the user needs to complete the physical examination.

[0065] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0066] Extract user identity information, a list of physical examination items, and a physical examination path from the physical examination execution package, perform identity verification by scanning the user's QR code, establish a secure connection channel with the distributed medical device when the verification is successful, and trigger a secondary biometric verification process when the verification fails, compare and analyze the user's iris features, generate a secondary verification result, and determine the authenticity of the identity based on the secondary verification result;

[0067] Performing multimodal data fusion on the blood analysis data, imaging data, and physiological indicator data collected by the distributed medical equipment to generate a heterogeneous original examination data set;

[0068] Inputting the heterogeneous original inspection data set into the multi-source heterogeneous data anomaly detection model, the multi-source heterogeneous data anomaly detection model is a four-layer neural network structure consisting of a feature extraction layer, an anomaly detection layer, an anomaly marking layer, and a verification layer. Feature mapping is performed on the inspection data. When the feature dimension exceeds a preset threshold, a dimensionality reduction operation is performed. When the dimension is below the threshold, the original dimension is maintained to obtain a feature vector set;

[0069] Performing data consistency check based on the feature vector set to generate an anomaly labeled data set;

[0070] Applying the Bayesian inference method to the abnormality labeling dataset to perform abnormality identification analysis, combining historical physical examination data to calculate the conditional probability distribution, determine the abnormal type of the examination result, generate a data abnormality prompt label when the data is outlier, generate an indicator abnormality prompt label when the detection indicator is abnormal, and retain the original value without adding an abnormal label when it is a normal physiological fluctuation. All original examination data are retained and corresponding prompt labels are added to abnormal items to obtain the original examination data with abnormal prompts;

[0071] The original examination data with abnormal prompts is converted into a standard medical data format, the timestamp of the entire collection process and the operator information are recorded, the abnormal prompt items are counted and the data integrity score is calculated. When the integrity score is higher than the high integrity threshold, a structured physical examination result data set is directly generated. When the integrity score is lower than the high integrity threshold, a manual review process is triggered, and a structured physical examination result data set is integrated and generated, and it is associated with the user identity information to generate a physical examination report package.

[0072] Specifically, the user's identity information, list of physical examination items, and physical examination path are extracted from the physical examination execution package. This extraction process uses data parsing technology to deserialize the physical examination execution package, separating the identity data block containing the user's basic information, a list of all physical examination items that need to be completed, and the physical examination path information sorted by the optimal path. Identity verification is then performed by scanning the user's QR code. The QR code decoder reads the QR code content, extracts the user's unique application identification code and physical examination item code, and compares them with the identity information in the physical examination execution package. If the comparison results are consistent, the verification is successful, and a secure connection channel with the distributed medical device is immediately established. The TLS protocol is used for encrypted communication to ensure data transmission security. If the comparison results are inconsistent, the verification fails, and the secondary biometric verification process is automatically triggered. The iris scanning device is called to collect the user's current iris image, extract the iris texture features, compare and analyze with the pre-stored iris template, calculate the similarity score, generate a secondary verification result, and determine the authenticity of the user's identity based on this result.

[0073] After identity verification is passed, the inspection data collected by distributed medical devices begins to be processed. Distributed medical devices include blood analyzers, imaging devices, and physiological indicator monitoring devices, each of which collects different types of physical examination data. Blood analysis data includes numerical data such as blood cell counts and biochemical indicators; imaging data includes image data such as X-rays and ultrasounds; and physiological indicator data includes measurement data such as blood pressure and heart rate. These data from different sources and formats are integrated and processed using multimodal data fusion technology. Multimodal data fusion performs standardized preprocessing on various data types, converting the raw data output by different devices into a unified data format. The data is then classified and organized according to the inspection item code, and relationships between the data are established. Finally, all collected data is organized into a structured, heterogeneous raw inspection dataset.

[0074] Inputting heterogeneous raw inspection datasets into a multi-source heterogeneous data anomaly detection model is a core step in inspection data quality control. This model is a deep learning model specifically designed for medical data quality monitoring and consists of a four-layer neural network structure: a feature extraction layer, anomaly detection layer, anomaly labeling layer, and a verification layer. The feature extraction layer applies various feature extraction algorithms to the input inspection data, such as statistical feature extraction for numerical data, convolutional feature extraction for image data, and time-frequency feature extraction for time series data, to form a feature representation. The extracted features are then evaluated for dimensionality. When the feature dimension exceeds a preset threshold, dimensionality reduction operations such as principal component analysis are performed to retain the key feature information. When the dimension falls below the threshold, the original dimension is retained without dimensionality reduction.

[0075] Performing data consistency checks based on feature vector sets is a crucial step in identifying abnormal data. This consistency check calculates the correlations between data sources to determine whether the logical relationships between the data are reasonable. It then calculates the statistical distribution of each indicator and compares it to the normal reference range to identify values ​​outside of the normal range. It then calculates the continuity of the time series data to detect data jumps. Finally, based on these check results, each data point is scored. Data points that exceed the threshold are marked as abnormal, generating a dataset containing the anomaly type, severity, and location information.

[0076] Applying Bayesian inference to anomaly identification and analysis on anomaly-labeled datasets is a critical step in ensuring data quality. Bayesian inference combines the user's historical medical examination data with the statistical distribution of similar populations to calculate a conditional probability distribution—the probability distribution of the current observation given the historical data. The type of outlier is then determined based on the conditional probability distribution and the anomaly label. When data is identified as an outlier (e.g., a metric significantly differs from the user's historical value and does not conform to physiological variations), a data anomaly warning label is generated, and the original data is annotated with "Data Anomaly - Suspected Measurement Error." When a test metric is identified as abnormal (e.g., key indicators like blood pressure and blood sugar are outside the normal range, or a positive HIV or hepatitis B surface antigen test result), a warning label is generated, and the original data is annotated with "Indicator Abnormal - Medical Evaluation Required." When normal physiological fluctuations are identified (e.g., fluctuations in test values ​​due to changes in the user's physiological state, such as medication or food intake), the original value is retained without adding an anomaly label. All original examination data is retained intact, with only the corresponding warning label added to the abnormal item, resulting in the original examination data with an abnormality warning.

[0077] The final step in data integration is converting raw examination data with abnormality indications into a standard medical data format. This standardized conversion utilizes common data exchange standards in the medical field, such as HL7 and DICOM, to ensure data interoperability. Blockchain technology is embedded in the conversion process to record the entire data collection process, including metadata such as the timestamp of each examination item, operator authentication information, and device identification, forming a data traceability chain. Data integrity assessment calculates an integrity score based on pre-set evaluation indicators, including data item coverage, key data missing rate, and the proportion of items with abnormality indications. When the integrity score exceeds the high integrity threshold, a structured medical examination result dataset is directly generated. When the integrity score falls below the high integrity threshold, a manual review process is triggered, marking data items requiring manual review and guiding medical professionals to conduct a review. All raw data with abnormality indications is integrated and linked to user identity information to generate a formal medical examination report package.

[0078] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0079] Extract the user's physical examination data and application information from the physical examination report package to generate an audit input data set;

[0080] The audit input data set is input into the first basic rule audit layer of the multi-level audit mechanism composed of the medical knowledge graph and the expert rule base, and the completeness of the physical examination items and the indicator range are compared and analyzed item by item to generate the basic audit results;

[0081] The basic audit results are input into the second-tier comprehensive analysis and audit layer of the multi-level audit mechanism. Based on machine learning algorithms, multiple inspection results are integrated to identify health risks, conduct potential correlation analysis, and obtain risk assessment results.

[0082] Input the risk assessment results and audit input data set into the third level of the destination region specific requirements audit of the multi-level audit mechanism, conduct targeted verification based on the destination region's sanitary entry conditions, and generate the destination region compliance results;

[0083] The credibility of the basic audit results, risk assessment results, and compliance results for the destination region is calculated. When the credibility of an audit result is lower than the credibility threshold, it is marked as a manual review item and an audit classification result is generated. The audit classification result classifies the application into three categories: approved, requiring review, and rejected.

[0084] Based on the audit classification results, corresponding processing files are generated. When the classification is passed, an electronic health certificate containing an electronic signature and encrypted anti-counterfeiting mark is generated. When the classification is required for review, an abnormality analysis report is generated. When the classification is rejected, a non-compliance explanation is generated. The audit classification results, processing files and complete audit records are integrated to generate a health certificate decision package.

[0085] Specifically, the user's medical examination data and application information are extracted from the medical examination report package. This extraction process utilizes data parsing technology to perform a structured reading of the medical examination report package, extracting the medical examination data including the individual examination results and the user's basic application information. The extracted data undergoes format conversion and standardization, organizing it into a standardized data structure to form the audit input dataset, which serves as input for the multi-level audit mechanism. The basic rule audit layer is composed of a medical knowledge graph and an expert rule library. The medical knowledge graph stores the logical relationships and medical reference ranges between medical examination items, while the expert rule library contains a large number of audit rules defined by medical experts. The audit process verifies the completeness of the medical examination items, verifying their completion against the list of mandatory examination items required by the destination region. Each medical examination indicator is then compared to the medical reference range, with outliers flagged. Consistency between examination items is then checked, identifying logically inconsistent results. The results of these checks are organized into structured basic audit results, including information such as item completion status, indicator anomaly flags, and consistency assessment.

[0086] The comprehensive analysis and review layer, based on machine learning algorithms, integrates multiple examination results for in-depth analysis. This layer employs ensemble learning methods, combining multiple classifiers and regression models, to comprehensively evaluate the user's physical examination data. The processing involves feature engineering each examination indicator, extracting derived features such as correlations and changing trends between indicators. These features are then fed into a pre-trained health risk prediction model, which has been trained on a large amount of historical physical examination data and is capable of identifying potential health risk patterns. Anomaly pattern detection is then performed to identify combinations of indicators that match typical disease characteristics. Finally, the predictions from each model are summarized to generate a risk assessment that includes risk type, risk level, and confidence level.

[0087] The Destination Region Specific Requirements Review layer contains a database of entry health requirements for countries and regions worldwide, storing the specific health requirements for individuals of different occupations and nationalities in different regions. The review process queries the specific health requirements corresponding to the user's destination region and occupational category. These requirements are then converted into structured validation rules. Next, the validation rules are applied against the risk assessment results and the original medical examination data, checking whether each requirement of the destination region is met. Finally, the validation results are summarized to generate a detailed destination region compliance report, clearly indicating which specific requirements are met and which are not.

[0088] Credibility calculations employ evidence theory, treating each level of audit results as an independent source of evidence and assessing the reliability of each conclusion. The calculation process assigns a basic credibility weight to each audit result, reflecting the importance of different audit levels in decision-making. Initial credibility is then adjusted based on data quality factors, such as the stability of test values ​​and the calibration status of equipment. The internal consistency of the audit results is then analyzed, lowering credibility when conflicting conclusions arise between different levels. Finally, a comprehensive credibility score is calculated. When the credibility of a particular audit result falls below a preset credibility threshold, it is marked as requiring manual review. Based on the comprehensive audit results and credibility assessment, an audit classification result is generated, classifying applications into three categories: approved, requiring review, and rejected.

[0089] Generating the corresponding processing files based on the audit classification results is the final step in achieving the output of the audit results. For applications classified as approved, an electronic health certificate is generated. This certificate contains the user's basic information, a summary of the physical examination results, the validity period, and the certificate number, and adds an electronic signature and an encrypted anti-counterfeiting mark to ensure the authenticity and non-tamperability of the certificate; for applications classified as requiring review, a detailed abnormality analysis report is generated, clearly indicating the specific items that need to be reviewed, the reasons for the abnormality, and the review suggestions, to guide medical professionals to conduct targeted reviews; for applications classified as rejected, a non-conformity explanation document is generated, detailing the non-conformity items and reasons, and providing improvement suggestions. The audit classification results, corresponding processing files, and audit records are integrated together to form a health certificate decision package.

[0090] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0091] According to the review results in the health certificate decision package, the electronic health certificate information is identified, including user identity information, physical examination result summary, validity period and unique certificate identification code, to obtain the target data package;

[0092] Apply PKI technology to digitally sign the target data packet and generate a verification QR code containing the core information of the certificate;

[0093] Execute multi-channel distribution processing based on the user's pre-selected certificate receiving method. For users who choose electronic certificates, the encrypted certificate will be sent to the email and mobile application account. For users who choose physical certificates, the printing instruction will be sent to the self-service terminal device.

[0094] Implement cross-system data synchronization based on the core certificate information in the electronic health certificate, push health information of different granularities to the management system through a secure API interface to form a synchronized data set;

[0095] Set up a lifecycle management mechanism for electronic health certificates, establish a validity monitoring database, record certificate status information, and generate expiration reminder tasks;

[0096] The electronic health certificate is linked to the blockchain verification service, providing an online verification channel through certificate QR code scanning or certificate number input, logging all certificate operations, and generating a certificate traceability chain.

[0097] Specifically, in the self-registration method for entry-exit health certificates, multi-channel health certificate issuance and cross-system data synchronization are key steps in ensuring the effective circulation of health certificates. Electronic health certificates are identified based on the review results in the health certificate decision package. Using templated certificate generation technology, the package extracts the user's identity information (including name, gender, date of birth, nationality, and ID number), a summary of the physical examination results (including key health indicators and their determinations), the validity period (typically 12 months), and a unique certificate identification code automatically generated by the system (using specific encoding rules to ensure global uniqueness). This information is organized according to international electronic certificate specifications to generate a standardized target data package. The target data package uses XML or JSON format.

[0098] Applying PKI technology to digitally sign the target data packet is an important step in ensuring the authenticity and integrity of the certificate. PKI (Public Key Infrastructure) technology is a security framework based on asymmetric encryption, used to implement digital signatures and encrypted communications. The digital signature process calculates the hash value of the electronic health certificate and uses a secure hash algorithm such as SHA-256 to convert the certificate content into a fixed-length digest. This digest is then encrypted using the issuing authority's private key to generate a digital signature. Finally, the original certificate content is encapsulated together with the digital signature to form a signed electronic health certificate. At the same time, a verification QR code is generated based on the core information of the certificate (such as the certificate identification code, user identity information, validity period, etc.). This QR code adopts the QR code standard with a high error correction level to ensure fault tolerance during printing and scanning, facilitating offline verification of the certificate's authenticity.

[0099] Executing multi-channel distribution processing based on the user's pre-selected certificate receiving method is an important step in achieving user-friendliness. The receiving method pre-selected by the user during the application process is recorded in the user's preferences, and the distribution system reads this setting to execute the corresponding distribution strategy. For users who choose electronic certificates, the system will encrypt the signed certificate and encrypt the certificate content using a symmetric encryption algorithm (such as AES-256). The key is sent through a secure channel reserved by the user (such as a mobile phone text message); the encrypted certificate file is then sent to the user's email address via a secure email protocol, and pushed to the user's personal account on the relevant mobile application to form a double backup. For users who choose physical certificates, the system assembles the certificate data and printing parameters (such as the anti-counterfeiting watermark position, holographic label layout, etc.) into a printing instruction, sends it to the designated self-service terminal device, triggers the printing process, and generates a physical certificate with physical anti-counterfeiting features.

[0100] Implementing a cross-system data synchronization mechanism based on the core certificate information in the electronic health certificate is a key step in achieving information interoperability. The data synchronization mechanism formulates differentiated data push strategies based on the authority levels and data requirements of different receiving systems, and determines the granularity of data provided to each system; then, through a pre-configured secure API interface, it uses the REST or SOAP protocol to send data packets to the relevant government management system. The pushed content includes basic user identity information, certificate identification code, physical examination summary information (provided with different levels of detail depending on the authority level), validity period and certificate status, etc. The scope of receiving systems includes entry and exit management systems, customs quarantine systems, international health information exchange platforms, etc. All pushed data is transmitted through a secure channel, and data verification is performed at the receiving end. After confirming the integrity, it is written into the database of each system to form a synchronized data set.

[0101] Establishing a lifecycle management mechanism for electronic health certificates is a necessary measure to ensure their timeliness. Lifecycle management establishes a dedicated validity monitoring database to record each certificate's issuance time, validity period, and current status (valid, expiring, expired, revoked, etc.). A regular scanning task is then set up to scan the database daily to identify certificates that are about to expire (e.g., expiring within 15 days). Expiration reminder tasks are then generated, corresponding to different reminder time points (e.g., 15 days, 7 days, 3 days before expiration). Finally, the reminder task is executed, sending a reminder message through the user's pre-selected notification channel (SMS, email, app push, etc.), informing the user of the impending certificate expiration and renewal procedures. Furthermore, for certificates that need to be revoked under special circumstances, the system immediately updates their status and synchronizes it with all relevant systems.

[0102] Linking electronic health certificates with blockchain-based verification services is an innovative approach to building a trusted verification system. Based on distributed ledger technology, blockchain-based verification services provide an immutable chain of records for certificate verification. This process involves writing key certificate information (such as the certificate identification code, issuance date, validity period, and digital signature) to the blockchain, creating a certificate record on the blockchain. Multiple verification methods are then provided, including scanning the QR code on the certificate or entering the certificate number through the official website. Verification requests then trigger the execution of a smart contract, which queries the certificate record on the blockchain and cross-verifies it with a central database. Finally, verification results are returned, including the certificate's authenticity, current status, and basic information. Furthermore, all certificate operations (such as issuance, verification, and revocation) are automatically logged in detail, including the time, type, operator, and content of the operation. These logs are also written to the blockchain, forming a traceability chain for the certificate, ensuring transparency and auditability throughout the certificate lifecycle.

[0103] The above describes the self-service registration method for the entry-exit health certificate in the embodiment of the present application. The following describes the self-service registration system for the entry-exit health certificate in the embodiment of the present application. Figure 2 In one embodiment of the present application, a self-service registration system for entry-exit health certificates includes:

[0104] The collection module 201 is used to collect and process the user's multimodal biometric information and generate a digital identity package;

[0105] Integration module 202, for performing dynamic form generation processing based on the user basic information and destination area health requirement data in the digital identity package, obtaining health declaration information, and integrating the health declaration information with the digital identity package to generate a health data package;

[0106] A query module 203 is configured to query a physical examination knowledge graph database based on the health data packet, match a physical examination item set and generate a physical examination path map, and fuse the physical examination path map with the health data packet to generate a physical examination execution package;

[0107] The control module 204 is configured to perform real-time quality control processing on the examination data collected by the distributed medical devices according to the physical examination execution package, identify outliers in the examination data using a multi-source heterogeneous data self-correction model, generate a structured physical examination result data set, and generate a physical examination report package;

[0108] The analysis module 205 is used to input the medical examination report package into the multi-level audit mechanism for compliance analysis and processing, generate audit results and electronic health certificates, and generate a health certificate decision package;

[0109] The synchronization module 206 is used to issue certificates and synchronize data across systems based on the health certificate decision package, thereby realizing multi-channel distribution and verification of electronic health certificates.

[0110] Through the collaborative cooperation of the above-mentioned components, by collecting and processing the user's multimodal biometric information, combining it with a deep neural network model for feature extraction, and generating a unique identifier, high accuracy and security of identity authentication are achieved, effectively preventing identity fraud; based on the combination of digital identity packages and health requirements data of the destination area, dynamic form generation is performed through a decision tree algorithm, so that the form content accurately matches the differentiated health requirements of different destinations, greatly improving user experience and reporting efficiency; the physical examination knowledge graph database is combined with a knowledge reasoning engine for intelligent matching of physical examination items, and health risk factors are identified through machine learning algorithms, combined with the shortest path algorithm to generate a physical examination path map, effectively solving the problem of time waste caused by repeated examinations and unreasonable paths in traditional physical examinations; especially in terms of medical data quality control, an innovative multi-source heterogeneous data self-correction model is adopted, which can identify outliers in examination data in real time. If anomalies exist, further review will be prompted. The Bayesian reasoning method is used to carry out targeted processing of different types of outliers, which significantly improves the accuracy and reliability of physical examination data; in the review process, a multi-level review mechanism is adopted in combination with medical knowledge graphs and expert rule bases to realize the intelligence and efficiency of the review process and reduce the subjectivity of manual review; the electronic health certificate is digitally signed through PKI technology, and multi-channel distribution is achieved, which is associated with the blockchain verification service, which not only ensures the authenticity and non-tamperability of the certificate, but also provides a convenient online verification channel to meet the mutual recognition requirements of cross-border health certificates; Overall, the contribution of the application of artificial intelligence algorithms and models in specific functional fields of the present invention is mainly reflected in: deep neural networks improve the accuracy of identity authentication, knowledge graphs cooperate with reasoning engines to realize intelligent physical examination item matching, multi-source heterogeneous data self-correction models solve the problem of medical data quality control, and multi-level machine learning review mechanisms replace traditional manual review. The comprehensive application of these AI technologies has enabled the entire entry and exit health certificate application process to achieve digital transformation and intelligent upgrading, and completely solved the problems of low efficiency of traditional methods, many human errors, data islands and cross-system verification difficulties.

[0111] above Figure 2 The self-service registration system for entry and exit health certificates in an embodiment of the present invention is described in detail from the perspective of modular functional entities. The self-service registration device for entry and exit health certificates in an embodiment of the present invention is described in detail from the perspective of hardware processing.

[0112] Figure 3This is a schematic diagram of the structure of a self-service registration device for entry-exit health certificates, provided in an embodiment of the present invention. The self-service registration device 300 for entry-exit health certificates may vary significantly depending on configuration or performance. It may include one or more central processing units (CPUs) 310 (e.g., one or more processors), memory 320, and one or more storage media 330 (e.g., one or more high-volume storage devices) storing applications 333 or data 332. The memory 320 and storage medium 330 may be either transient or persistent storage. The program stored in the storage medium 330 may include one or more modules (not shown), each of which may include a series of instructions for operating on the self-service registration device 300 for entry-exit health certificates. Furthermore, the processor 310 may be configured to communicate with the storage medium 330, executing the series of instructions stored in the storage medium 330 on the self-service registration device 300 for entry-exit health certificates, thereby implementing the steps of the self-service registration method for entry-exit health certificates described above.

[0113] The self-service registration device 300 for entry and exit health certificates may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input and output interfaces 360, and / or one or more operating systems 331, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be understood by those skilled in the art that Figure 3 The structure of the self-service registration device for entry and exit health certificates shown does not constitute a limitation on the self-service registration device for entry and exit health certificates provided by the present invention, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0114] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the self-service registration method for entry and exit health certificates.

[0115] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0116] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion 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 several instructions for causing a self-service registration device for entry and exit health certificates (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A self-service registration method for entry-exit health certificates, characterized in that: The method comprises: Collect and process the user's multimodal biometric information to generate a digital identity package; Perform dynamic form generation processing based on the user basic information and destination area health requirement data in the digital identity package, obtain health declaration information, and integrate the health declaration information with the digital identity package to generate a health data package; Based on the health data packet, query the physical examination knowledge graph database, match the physical examination item set and generate a physical examination path map, and fuse the physical examination path map with the health data packet to generate a physical examination execution package; The query processing of the physical examination knowledge graph database based on the health data packet, matching the physical examination item set and generating a physical examination path map, and fusing the physical examination path map with the health data packet to generate a physical examination execution package includes: Extract user identity information, destination area requirements and health declaration information from the health data packet to obtain a physical examination requirement set, and determine an initial physical examination item set based on the physical examination requirement set; based on the initial physical examination item set, apply a machine learning algorithm to analyze the user's historical physical examination data, identify health risk factors, and generate a risk-weighted physical examination item set; compare and analyze the risk-weighted physical examination item set with the user's electronic health record, eliminate the examination items that have been completed recently and have valid results, and obtain a physical examination item set; input the physical examination item set into the shortest path algorithm, consider the logical order between the examination items and the spatial layout of the medical institution, and generate a physical examination path map; generate a QR code identifier for the physical examination path map containing the user's unique application identification code and the physical examination item code, and merge the physical examination path map, the physical examination item set, the QR code identifier and the health data packet to generate a physical examination execution package; Performing real-time quality control processing on the inspection data collected by the distributed medical equipment according to the physical examination execution package, identifying outliers in the inspection data using a multi-source heterogeneous data self-correction model, generating a structured physical examination result data set, and generating a physical examination report package; Input the medical examination report package into the multi-level audit mechanism for compliance analysis and processing, generate audit results and electronic health certificates, and generate a health certificate decision package; Based on the health certificate decision package, certificate issuance and cross-system data synchronization processing are carried out to realize multi-channel distribution and verification of electronic health certificates.

2. The self-service registration method for entry-exit health certificate according to claim 1 is characterized in that: The collecting and processing of the user's multimodal biometric information to generate a digital identity package includes: Collect the user's facial information, iris features and fingerprint information to obtain multimodal biometric data; Inputting the multimodal biometric data into a deep neural network model for feature extraction processing to generate a unique user identifier; Comparing and verifying the biometric template stored in the security database based on the unique identifier to generate an identity verification result; Based on the identity verification result, a dedicated interface is called to connect to the preset entry-exit management database and health database to extract basic user information; Scan the passport or ID card provided by the user, extract the text information of the ID card through the improved OCR algorithm, cross-verify it with the basic information of the user, and generate verified personal information; The verified personal information and the unique identifier are encrypted using the national encryption algorithm SM4 to generate a digital identity package containing basic user information and a unique application identification code.

3. The self-service registration method for entry-exit health certificate according to claim 1, characterized in that: The process of generating a dynamic form based on the basic user information and the health requirements data of the destination area in the digital identity package, obtaining health declaration information, and integrating the health declaration information with the digital identity package to generate a health data package includes: Extracting user basic information and a unique application identification code from the digital identity package to generate user basic information; Obtain health entry requirements data for the destination area according to the user's planned destination; Input the user basic information and the destination area health entry requirement data into the decision tree algorithm for analysis and processing to generate a personalized form structure; Applying semantic analysis to the personalized form structure, converting health requirements into structured form fields, and pre-filling them based on the user's previous health records to generate an interactive health form; The information entered by the user in the interactive health form is verified in real time through data validity verification rules to obtain formatted health declaration data; The formatted health declaration data is structured and integrated with the digital identity package, and a health data package is generated through digital signature technology.

4. The self-service registration method for entry-exit health certificate according to claim 1, characterized in that: The physical examination execution package performs real-time quality control processing on the inspection data collected by the distributed medical equipment, uses a multi-source heterogeneous data self-correction model to identify outliers in the inspection data, generates a structured physical examination result data set, and generates a physical examination report package, including: Extract user identity information, a list of physical examination items, and a physical examination path from the physical examination execution package, perform identity verification by scanning the user's QR code, establish a secure connection channel with the distributed medical device when the verification is successful, and trigger a secondary biometric verification process when the verification fails, compare and analyze the user's iris features, generate a secondary verification result, and determine the authenticity of the identity based on the secondary verification result; Performing multimodal data fusion on the blood analysis data, imaging data, and physiological indicator data collected by the distributed medical equipment to generate a heterogeneous original examination data set; Inputting the heterogeneous original inspection data set into the multi-source heterogeneous data self-correction model, the multi-source heterogeneous data self-correction model is a four-layer neural network structure consisting of a feature extraction layer, anomaly detection layer, anomaly marking layer and a verification layer, performing feature mapping processing on the inspection data, performing a dimensionality reduction operation when the feature dimension exceeds a preset threshold, and maintaining the original dimension when the dimension is below the threshold to obtain a feature vector set; Performing data consistency check based on the feature vector set to generate an anomaly labeled data set; Applying the Bayesian inference method to the abnormality labeling dataset to perform abnormality identification analysis, combining historical physical examination data to calculate the conditional probability distribution, determine the abnormal type of the examination result, generate a data abnormality prompt label when the data is outlier, generate an indicator abnormality prompt label when the detection indicator is abnormal, and retain the original value without adding an abnormal label when it is a normal physiological fluctuation. All original examination data are retained and corresponding prompt labels are added to abnormal items to obtain the original examination data with abnormal prompts; The original examination data with abnormal prompts is converted into a standard medical data format, the timestamp of the entire collection process and the operator information are recorded, the abnormal prompt items are counted and the data integrity score is calculated. When the integrity score is higher than the high integrity threshold, a structured physical examination result data set is directly generated. When the integrity score is lower than the high integrity threshold, a manual review process is triggered, and a structured physical examination result data set is integrated and generated, and it is associated with the user identity information to generate a physical examination report package.

5. The self-service registration method for entry-exit health certificate according to claim 1 is characterized in that: The medical examination report package is input into the multi-level audit mechanism for compliance analysis and processing, and the audit results and electronic health certificate are generated, and the health certificate decision package is generated, including: Extracting the user's physical examination data and application information from the physical examination report package to generate an audit input data set; Input the audit input data set into the first basic rule audit layer of the multi-level audit mechanism composed of the medical knowledge graph and the expert rule base, perform item-by-item comparison and analysis on the completeness of the physical examination items and the indicator range, and generate basic audit results; The basic audit results are input into the second comprehensive analysis audit layer of the multi-level audit mechanism, and multiple inspection results are integrated based on a machine learning algorithm to identify health risks, perform potential correlation analysis, and obtain risk assessment results; Inputting the risk assessment results and the audit input data set into the third-tier destination region specific requirements audit layer of the multi-tier audit mechanism, performing targeted verification based on the destination region sanitary entry conditions, and generating a destination region compliance result; Calculate the credibility of the basic audit results, the risk assessment results, and the compliance results of the destination region. When the credibility of a certain audit result is lower than the credibility threshold, it is marked as a manual review item and an audit classification result is generated. The audit classification result classifies the application into three categories: approved, requiring review, and rejected; Based on the audit classification results, corresponding processing files are generated. When the classification is passed, an electronic health certificate containing an electronic signature and an encrypted anti-counterfeiting mark is generated. When the classification is required for review, an abnormality analysis report is generated. When the classification is rejected, a non-compliance explanation is generated. The audit classification results, processing files and complete audit records are integrated to generate a health certificate decision package.

6. The self-service registration method for entry-exit health certificate according to claim 1, characterized in that: The certificate issuance and cross-system data synchronization based on the health certificate decision package realizes multi-channel distribution and verification of electronic health certificates, including: According to the review results in the health certificate decision package, the electronic health certificate information is identified, including user identity information, physical examination result summary, validity period and unique certificate identification code, to obtain a target data packet; Apply PKI technology to digitally sign the target data packet and generate a verification QR code containing the core information of the certificate; Execute multi-channel distribution processing based on the user's pre-selected certificate receiving method. For users who choose electronic certificates, the encrypted certificate will be sent to the email and mobile application account. For users who choose physical certificates, the printing instruction will be sent to the self-service terminal device. Based on the core certificate information of the electronic health certificate, a cross-system data synchronization mechanism is implemented, and health information of different granularities is pushed to the management system through a secure API interface to form a synchronized data set; Setting up a lifecycle management mechanism for the electronic health certificate, establishing a validity monitoring database, recording certificate status information, and generating expiration reminder tasks; The electronic health certificate is associated with the blockchain verification service, and an online verification channel is provided by scanning the certificate QR code or entering the certificate number. All certificate operations are logged and a certificate traceability chain is generated.

7. A self-service registration system for entry and exit health certificates, characterized in that: For implementing the self-service registration method for entry-exit health certificates according to any one of claims 1 to 6, the self-service registration system for entry-exit health certificates comprises: The collection module is used to collect and process the user's multimodal biometric information and generate a digital identity package; An integration module is used to generate a dynamic form based on the basic user information and the health requirements data of the destination area in the digital identity package, obtain health declaration information, and integrate the health declaration information with the digital identity package to generate a health data package; A query module is used to query the physical examination knowledge graph database based on the health data packet, match the physical examination item set and generate a physical examination path map, and fuse the physical examination path map with the health data packet to generate a physical examination execution package; The query module is specifically used to: extract user identity information, destination area requirements and health declaration information from the health data packet to obtain a physical examination requirement set, and determine an initial physical examination item set based on the physical examination requirement set; based on the initial physical examination item set, apply a machine learning algorithm to analyze the user's historical physical examination data, identify health risk factors, and generate a risk-weighted physical examination item set; compare and analyze the risk-weighted physical examination item set with the user's electronic health record, eliminate the examination items that have been completed recently and have valid results, and obtain a physical examination item set; input the physical examination item set into the shortest path algorithm, consider the logical order between the examination items and the spatial layout of the medical institution, and generate a physical examination path map; generate a QR code identifier for the physical examination path map containing the user's unique application identification code and the physical examination item code, and merge the physical examination path map, the physical examination item set, the QR code identifier and the health data packet to generate a physical examination execution package; A control module, configured to perform real-time quality control processing on the examination data collected by the distributed medical equipment according to the physical examination execution package, identify outliers on the examination data using a multi-source heterogeneous data self-correction model, generate a structured physical examination result data set, and generate a physical examination report package; An analysis module is used to input the medical examination report package into a multi-level audit mechanism for compliance analysis and processing, generate audit results and electronic health certificates, and generate a health certificate decision package; The synchronization module is used to issue certificates and synchronize data across systems based on the health certificate decision package, thereby realizing multi-channel distribution and verification of electronic health certificates.

8. A self-service registration device for entry and exit health certificates, characterized in that: It includes a memory and a processor, the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the self-service registration method for entry and exit health certificates described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor executes the self-service registration method for entry-exit health certificates as claimed in any one of claims 1 to 6.

Images