An epidemic investigation system and method based on scene analysis

Abstract

This application discloses an epidemiological investigation system and method based on scenario analysis. The system includes: a scenario-based rule base construction module for generating rules; a scenario-based data association module for configuring relationships; a synchronization configuration module for lightweight processing of generated rules and synchronizing lightweight rule packages and core collection field configurations; and a scenario-based verification and rule iteration module for verifying data packets and generating verification reports to achieve iterative optimization of rules. The offline collection terminal includes: a synchronization request and preparation module for receiving and loading lightweight rule packages and configuring core collection fields; a scenario-based preliminary judgment engine module for real-time risk assessment of entered epidemiological investigation data and integrating the judgment results with the epidemiological investigation data to form data packets; and a synchronization execution module for matching preset synchronization priority sorting and uploading according to the sorting order. This application can meet the needs of offline analysis, online verification, and rule iteration in epidemiological investigation work.

Description

Technical Field

[0001] This application relates to the field of epidemiological investigation technology, specifically to an epidemiological investigation system and method based on scenario analysis. Background Technology

[0002] In the field of epidemiological investigation, with the increasing awareness of public health and the growing demand for infectious disease prevention and control, the epidemiological investigation system plays a crucial role in epidemic prevention and control. It assists public health departments in quickly and accurately collecting and analyzing relevant information, thereby formulating more effective prevention and control strategies. An efficient and accurate epidemiological investigation system can greatly improve the efficiency of epidemic prevention and control, reduce the scope and speed of disease transmission, and provide strong support for protecting public health.

[0003] In the past, the conventional approach to addressing data collection and analysis in epidemiological investigations was to build epidemiological investigation systems. Existing systems primarily offer basic data collection and simple synchronization capabilities. Regarding risk assessment, these systems lack scenario-based risk assessment rules, uniformly applying fixed judgment logic without considering the differences in transmission risk across different investigation scenarios. In terms of data collection, offline collection terminals can only record data in environments without network connectivity. Regarding data synchronization, the synchronization between offline collection terminals and the management terminal focuses solely on completeness, failing to incorporate scenario-based rules and initial assessment results for targeted transmission. Furthermore, the management terminal does not establish a closed-loop verification process with the scenario rules after receiving the data.

[0004] Existing technologies have significant shortcomings. Due to a lack of scenario adaptability, they employ a fixed judgment logic in risk assessment, ignoring the differences in transmission risks across various epidemiological investigation scenarios. This leads to misjudgments or omissions, resulting in insufficient accuracy. Offline data collection terminals can only record data in environments without network connectivity and cannot identify high-risk clues in real time based on scenario characteristics. They must wait for online processing and rely on the management terminal for batch processing, causing delays in handling high-risk information. Furthermore, the synchronization and verification of offline and management data do not form a scenario-based closed loop, making it difficult to optimize rule adaptability in reverse. This fails to meet the core requirements of epidemiological investigation work—"offline assessability, online verification, and rule iterability"—and restricts the accuracy of epidemiological investigations and the efficiency of prevention and control response. Summary of the Invention

[0005] To meet the needs of offline analysis, online verification, and rule iteration in epidemiological investigation, this application provides an epidemiological investigation system and method based on scenario analysis.

[0006] In a first aspect, this application provides an epidemiological investigation system based on scenario analysis, comprising: a management terminal and an offline collection terminal; the management terminal is configured with a scenario-based rule base construction module, a scenario-based data association module, a synchronization configuration module, and a scenario-based deep verification and rule iteration module; the offline collection terminal is configured with a synchronization request and preparation module, a scenario-based preliminary judgment engine module, and a synchronization execution module; The scenario-based rule base construction module is used to generate risk judgment rules based on the epidemic scenario; the scenario-based data association module is used to configure the association relationship between the data and the collected fields based on the epidemic scenario; the synchronization configuration module is used to perform lightweight processing on the generated rules; receive synchronization requests and read scenario identifiers, and synchronously send the lightweight rule package adapted to the scenario identifier and the core collected fields associated with the scenario identifier to the offline collection terminal. The synchronization request and preparation module is used to provide a scenario selection option interface and read the selected scenario identifier, and send a synchronization request containing the scenario identifier to the management terminal; receive and load lightweight rule packages and configure core collection fields; the scenario-based preliminary judgment engine module is used to perform real-time risk judgment on the entered epidemiological survey data based on the received lightweight rule package, and integrate the judgment results containing the judgment criteria with the epidemiological survey data to form a data package; the synchronization execution module is used to match the scenario identifier and data package with a preset synchronization priority sorting and synchronize the scenario identifier and data package to the management terminal according to the sorting order, and supports breakpoint resume. The scenario-based verification and rule iteration module is used to verify data packets according to scenario identifiers, generate verification reports and mark calibration status, generate confirmation rule matching instructions and core acquisition field supplement instructions based on verification reports and calibration status, and push them to all relevant offline acquisition terminals through the synchronization configuration module to achieve iterative optimization of rules.

[0007] By adopting the above solution, a closed loop of scenario-based configuration, synchronization, preliminary judgment, and online verification between the management end and the offline collection end was achieved, realizing scenario adaptability and real-time performance of risk assessment for epidemiological investigation data, ensuring the integrity and accuracy of high-risk information, and continuously optimizing the judgment capability through rule iteration, providing efficient technical support for epidemiological investigation and prevention work.

[0008] Preferably, the rules in the scenario-based rule base are stored in an associated structure that includes scenario identifiers, risk feature combinations, judgment logic, and supplementary guidance instructions; the risk feature combinations are associated with the feature descriptions of the collected fields, the judgment logic defines the mapping relationship between risk feature combinations and risk levels, and the supplementary guidance instructions include guidance on the core information that needs to be supplemented in preset high-risk scenarios.

[0009] By adopting the above solution, the storage structure of the rule base becomes clearer, making it easier to manage and use. It can accurately identify risks in different scenarios, improve the accuracy of risk assessment, and guide users to supplement key information in high-risk scenarios, thus ensuring the integrity of the data.

[0010] Preferably, the synchronization configuration module is configured with a scenario-based synchronization strategy, and is also used to synchronously send a lightweight rule package adapted to multiple scenario identifiers and the configuration of core collection fields associated with multiple scenario identifiers to the offline collection terminal according to the scenario-based synchronization strategy; the scenario-based synchronization strategy includes a synchronization priority, encrypted transmission protocol and data matching and verification rules preset according to the scenario identifier.

[0011] By adopting the above scheme, based on the scenario identifier, the synchronization priority, encrypted transmission protocol, and data matching and verification rules are set, and the lightweight rule package adapted to multiple scenario identifiers and the configuration of core collection fields are sent synchronously. Furthermore, the matching verification is performed before loading and configuring on the offline collection terminal to avoid mismatch between rules and data, improve the accuracy and security of data synchronization, and ensure the effective transmission and use of epidemiological survey data.

[0012] Preferably, the synchronization configuration module configures a scene-layered synchronization strategy and is further used to pre-divide the generated rules into a static topology graph part and a dynamic parameter value part before performing lightweight processing on the generated rules, and to perform lightweight processing on the corresponding rules of each part respectively; during the process of synchronously pushing the lightweight rule package of the single scene identifier to the offline collection terminal, different frequencies of synchronous push are selected for different parts of the lightweight rule package, so that the synchronous push frequency of the lightweight rule package of the static topology graph part is lower than the synchronous push frequency of the lightweight rule package of the dynamic parameter value part.

[0013] By adopting the above scheme, the rules are processed in layers and synchronized at different frequencies, which can reduce the amount of unnecessary synchronization data, improve synchronization efficiency, and ensure that the offline collection terminal can obtain the update of dynamic parameter values ​​in a timely manner, thereby improving the real-time performance and accuracy of risk assessment.

[0014] Preferably, the management terminal is further configured with a scenario-based rule prediction module; the scenario-based rule base prediction module is used to predict rules based on the verification report and calibration status, generate predicted rules, and supplement the rules in the rule base. The synchronization configuration module is also used to perform lightweight processing on the latest rules and predicted rules after generation or update, and record them as the basic version lightweight rule package and the predicted version lightweight rule package respectively; when synchronously sending the scene identifier-adapted lightweight rule package to the offline collection terminal, it selects to synchronously send the basic version lightweight rule package and the predicted version lightweight rule package. The synchronization request and preparation module is also used to receive and load the basic version of the lightweight rule package and the predicted version of the lightweight rule package, and adaptively match the version of the lightweight rule package to be loaded based on the regional information, time information and traffic information contained in the epidemiological survey data entered by the current user; and pre-set a version loading strategy of the lightweight rule package that is compatible with the combination of regional information, time information and traffic information contained in the entered epidemiological survey data.

[0015] By adopting the above scheme, and supplementing the rule base with the verification report and calibration status prediction rules, lightweight rule packages with basic and predictive versions are provided to the offline collection terminal. This allows the offline collection terminal to adaptively match and load rule package versions according to the region, time and flow information of the epidemiological investigation data, thereby enhancing the forward-looking nature of the epidemiological investigation system rules and their adaptability to different scenarios, and further improving the accuracy of the initial risk assessment of the epidemiological investigation and the efficiency of prevention and control response.

[0016] Preferably, the rules in the scenario-based rule base include rule version information; the synchronization request and preparation module is also used to send a synchronization request containing the rule version information of the current scenario to the management terminal; the synchronization configuration module is also used to push the latest version of the lightweight rule package by comparing the rule version information.

[0017] By adopting the above approach, it is ensured that the offline data collection terminal obtains the latest scenario-based rules from the management terminal, avoiding misjudgments or omissions due to inconsistent rule versions, and improving the accuracy of risk assessment in the epidemiological investigation and tracing system.

[0018] Preferably, the scenario-based preliminary judgment engine module further includes a feature extraction unit and a rule matching unit; the feature extraction unit is used to convert real-time input data into structured risk features; the rule matching unit is used to traverse the rules of the current scenario based on the loaded lightweight rule package for comparison, and generate missing feature prompt information when the feature part is matched.

[0019] By adopting the above scheme, real-time data is converted into structured risk features, making the data easier to analyze and process. When matching features, missing feature prompts are generated to guide users to supplement data, thereby improving the accuracy and completeness of risk assessment.

[0020] Preferably, the scenario preliminary judgment engine module is configured with a supplementary data entry guidance unit. The supplementary data entry guidance unit is used to call the supplementary guidance instruction to generate a structured supplementary data entry interface after the risk level judgment is completed; and to form a complete data package associated with and stored by verifying the integrity of the supplementary information based on the supplementary data entry interface, together with the original epidemiological survey data and the judgment result containing the judgment basis.

[0021] By adopting the above scheme, after the risk level is determined, users can be guided to supplement key information. After integrity verification, a complete data packet is formed and stored in association, which ensures the integrity and accuracy of high-risk information and improves the quality and effectiveness of epidemiological investigation data.

[0022] Preferably, the verification on the management end includes data integrity verification, logical consistency verification, and rule matching verification; the data integrity verification includes verifying whether the epidemiological survey data in the data packet conforms to the scenario-specific core collection field configuration; the logical consistency verification includes determining whether there are data contradictions by comparing the data packets of the same historical scenario; the rule matching verification includes determining whether the rules in the current data packet conform to the latest rules under the same scenario.

[0023] By adopting the above approach, data packets are comprehensively verified from three dimensions: data integrity, logical consistency, and rule matching. This ensures that epidemiological investigation data meets the specific requirements of the scenario, is free of logical contradictions, and matches the latest scenario rules, thereby improving the accuracy of epidemiological investigations and the efficiency of prevention and control response.

[0024] Secondly, this application provides an epidemiological investigation method based on scenario analysis, which, when applied to the aforementioned system, specifically includes: The system receives content selected by the user based on the provided scene selection options and reads the scene identifier. It then sends a synchronization request containing the scene identifier to the management terminal, so that the management terminal receives the synchronization request and reads the scene identifier. The system then configures the system based on the lightweight rule package of the read scene identifier and the core collection fields associated with the scene identifier. Receive the lightweight rule package for scene identifier adaptation and the core collection field configuration associated with the scene identifier sent by the management terminal, load the lightweight rule package, and configure the core collection fields; Based on the received lightweight rule package, the system performs real-time risk assessment on the entered epidemiological survey data and integrates the assessment results, which include the assessment criteria, with the epidemiological survey data to form a data package. The system matches the scene identifier and data packets with a preset synchronization priority and synchronizes the scene identifier and data packets to the management terminal in the sorted order. This allows the management terminal to verify the data packets based on the scene identifier, generate a verification report and mark the calibration status, and generate confirmation rule matching instructions and core acquisition field supplement instructions based on the verification report and calibration status. The system re-receives the lightweight rule package and core collection fields sent by the management terminal, and repeats the process of loading the lightweight rule package, configuring the core collection fields, determining real-time risks, forming and uploading data packets, performing verification and generating a verification report until the verification passes.

[0025] By adopting the above scheme, the scenario adaptability and real-time nature of the initial risk assessment of epidemiological investigation data are achieved, ensuring the integrity and accuracy of high-risk information. At the same time, the judgment capability is continuously optimized through rule iteration, providing efficient technical support for epidemiological investigation and prevention and control work.

[0026] In summary, this application has the following beneficial effects: The management-side scenario-based rule base construction module generates risk assessment rules based on epidemiological scenarios. The scenario-based data association module configures the association between scenarios and collected fields. The synchronization configuration module synchronizes the data to the offline collection terminal, enabling the offline collection terminal to perform real-time risk assessment on the entered epidemiological survey data based on the received lightweight rule package, achieving offline assessability. Furthermore, the management-side scenario-based verification and rule iteration module verifies the data package based on the scenario identifier and updates the rules in the rule base and supplements the core collected fields, pushing the updates to the offline collection terminal. This forms a scenario-based closed loop for offline and management-side data synchronization and verification, solving the problem of rules not being able to be iterated and meeting the requirement for iterative rules in epidemiological investigation work. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of the epidemiological investigation system based on scenario analysis described in a specific embodiment; Figure 2 This is a flowchart of the epidemiological investigation method based on scenario analysis described in a specific embodiment. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0029] like Figure 1 As shown in the figure, this application discloses an epidemiological investigation system based on scenario analysis. Based on a collaborative architecture of system management end and offline data collection end, it follows a data flow logic of scenario-based basic configuration at the management end, synchronous preparation at the offline data collection end, scenario-based initial judgment at the offline data collection end, online synchronization at the offline data collection end, and in-depth verification and rule iteration at the management end. This constructs a full-process scenario-based epidemiological investigation risk initial judgment system, enabling online verification and rule iteration. A detailed description of this system will follow.

[0030] The explanation begins with the design of the basic configuration for scenario-based management on the management side.

[0031] Specifically, the management terminal 1 is configured with a scenario-based rule base construction module 11, a scenario-based data association module 12, a synchronization configuration module 13, and a scenario-based deep verification and rule iteration module 14, etc.

[0032] The scenario-based rule base construction module 11 is used to generate rules for determining epidemic risks based on (extended) epidemic scenario settings, manage the rule building and generation rule base, and automatically generate rule update instructions and complete rule version updates by monitoring changes in epidemic-related policies, and record different rule versions. For example, in the face of an epidemic, corresponding risk rules are generated according to different transmission scenarios, such as medical institutions, schools, shopping malls, etc. As the epidemic develops over time, the characteristics of epidemic transmission under different transmission scenarios will continue to change, and rule update management is carried out, recording versions V1.0, V2.0, ...

[0033] To make the rule base storage structure clearer and easier to manage and use, the rules in the scenario-based rule base are stored in an associated structure that includes scenario identifiers, risk feature combinations, judgment logic, and supplementary guidance instructions. The scenario identifier is bound to the scenario type of the epidemic survey project in the management terminal, such as influenza A survey project and influenza B survey project. The risk feature combination is associated with the feature description of the collected field, such as: contact object type - protective equipment status, etc. The judgment logic defines the mapping relationship between risk feature combinations and risk levels, such as: risk feature combination {a, b, c, d} - high risk. The supplementary guidance instructions contain guidance on the core information that needs to be supplemented under preset high-risk scenarios, such as: core information E that needs to be supplemented related to risk feature e.

[0034] The scenario-based data association module 12 is used to configure the association relationship between epidemic scenarios and collection fields according to the epidemic scenario. For different epidemic scenario types, corresponding epidemic scenario identifiers are assigned, and each scenario identifier is bound to a specific core collection field (e.g., one scenario is bound to fields such as contact duration and protection type, while another scenario is bound to fields such as shared space and personnel density). These core collection fields can be determined by parsing the latest national and local prevention and control policies or historically verified risk event characteristics, and the association relationships of these fields are synchronized to the synchronization configuration module. Similar to the above rules, the association relationship between epidemic scenarios and collection fields will be automatically or manually updated in response to changes in epidemic-related policies.

[0035] The synchronization configuration module 13 is used to perform lightweight processing on the generated rules. This lightweight processing refers to converting the core rules of each scenario in the rule base (removing management metadata, using a simpler rule language or data structure, etc.) into lightweight rule packages adapted to the storage and computing capabilities of the offline collection terminal, ensuring that the offline terminal can load and execute them. To synchronize the scenario-based basic configuration set by the management terminal to the offline collection terminal, the synchronization configuration module 13 is also used to receive synchronization requests and read the current scenario identifier; synchronously send the lightweight rule package adapted to the scenario identifier and the core collection fields associated with the scenario identifier to the offline collection terminal, realizing the scenario-based initial risk assessment basic settings of the offline collection terminal; and to ensure that the synchronized version is the latest version, the synchronization configuration module 13 is also used to compare the rule version information (the latest loaded rule information uploaded by the offline collection terminal and the latest version information in the rule base) and push the latest version of the lightweight rule package. Similar to the above rules, the configuration of the core collection fields can also be compared and updated.

[0036] To further prevent errors in synchronization information during the synchronization process, which could lead to significant errors in the scenario-based risk assessment results of the subsequent offline data collection terminal, the synchronization configuration module 13 is also configured with a scenario-based synchronization strategy. This strategy is used to synchronously send a lightweight rule package for multi-scenario identifier adaptation and the configuration of core collection fields associated with the multi-scenario identifiers to the offline data collection terminal. The scenario-based synchronization strategy includes a pre-defined synchronization priority, an encrypted transmission protocol, and data matching and verification rules based on scenario identifiers. To avoid pushing lightweight rule packages and associated core collection fields tailored to high-risk scenario identifiers under multiple scenario identifiers, a pre-defined synchronization priority is used. For example, scenario identifier 00AX (highly infectious influenza AX) has high priority, while scenario identifier 00A1 (common infectious influenza A1) has low priority. Since some epidemiological investigation projects involve confidential information, an encrypted transmission protocol is pre-defined based on the scenario identifier. The corresponding synchronized lightweight rule packages and core collection fields are encrypted according to this protocol, ensuring that the offline collection terminal decrypts and loads or configures them upon receipt. The data matching and verification rules verify the compatibility between synchronized data and scenario identifiers, ensuring that the synchronized content is fully compatible with the current scenario of the offline collection terminal and avoiding rule-data mismatches.

[0037] This section will continue to elaborate on the preparation for offline data acquisition, the initial scenario-based assessment of offline data acquisition, and the design for online synchronization of offline data acquisition.

[0038] The offline acquisition terminal 2 is configured with a synchronization request and preparation module 21, a scenario-based preliminary judgment engine module 22, a synchronization execution module 23, a synchronization result verification and exception handling module 24, etc.

[0039] The synchronization request and preparation module 21 is used to provide the user with scene selection options (which can be designed through a visual interface) and read the option identifier corresponding to the scene option selected by the user. It then sends a synchronization request to the management terminal containing the scene identifier and rule version information (the latest rule version loaded on the offline collection terminal). The synchronization request may also include core fields of the latest configuration loaded on the offline collection terminal.

[0040] The synchronization request and preparation module 21 is also used to receive and load the synchronized lightweight rule package (to activate the risk judgment logic of the current scenario), configure the core collection fields for synchronization, and ensure that the collection fields are consistent with the scenario rule requirements. After loading and configuration, a scenario ready prompt is generated to confirm that the offline collection state can be entered to receive the epidemiological investigation data (hereinafter referred to as epidemiological investigation data) entered by the user.

[0041] To further ensure the synchronization accuracy of the offline collection terminal, the synchronization result verification and exception handling module 24 in the offline collection terminal is also used to re-verify the matching of the read scene identifier with the currently loaded lightweight rule package and configured core collection fields according to the data matching verification rules issued by the collection terminal before loading the lightweight rule package and configuring the core collection fields; and to perform integrity verification on the received lightweight rule package and core field configuration: if it is found that the lightweight rule package is missing core judgment logic (pre-set) or the core field configuration is incomplete, it automatically re-initiates a synchronization request to the management terminal; if multiple synchronization failures occur, it records the synchronization exception information and prompts the user to check the network to ensure that complete scene-based rules and data configurations have been obtained before offline collection.

[0042] The scenario-based preliminary judgment engine module 22 is used to perform real-time risk assessment on the entered epidemiological survey data based on the received lightweight rule package, and integrate the judgment results containing the judgment criteria with the epidemiological survey data to form a data package. Specifically, feature extraction and rule matching are completed through the feature extraction unit and rule matching unit configured in the scenario-based preliminary judgment engine module. Specifically, the feature extraction unit converts the real-time entered data into structured risk features, including: when the user enters epidemiological survey data, the system monitors the entry behavior of core fields in real time, and automatically triggers the feature extraction process after each core field entry is completed; according to the feature description in the rule package, the entered data is converted into structured risk features (e.g., not wearing protective equipment during contact is converted into a feature of missing protective equipment). The rule matching unit compares the rules of the current scenario based on the loaded lightweight rule package, and generates missing feature prompts when the feature is partially matched; this includes: after feature extraction, the engine traverses the risk judgment rules corresponding to the current scenario, compares whether the extracted features meet the risk feature combination, outputs the corresponding risk level if fully met, and marks the missing feature and prompts the user to supplement the entry if only partially met. After supplementation, feature extraction and rule matching are re-executed.

[0043] In addition, the scenario preliminary judgment engine module 22 is configured with a supplementary data entry guidance unit. This supplementary data entry guidance unit, after completing the risk level determination, calls a supplementary guidance instruction to generate a structured supplementary data entry interface, guiding the user to supplement key information in high-risk scenarios; the information supplemented based on the supplementary data entry interface, after integrity verification, is linked and stored as a complete data package with the original epidemiological survey data and the judgment results containing the judgment criteria.

[0044] The synchronization execution module 23 is used to match the scene identifier and data packet with a preset synchronization priority sorting and synchronize the scene identifier and data packet to the management terminal according to the sorting order, and supports breakpoint resumption. The preset synchronization priority sorting can be based on the combination of risk levels in the judgment results of different scene identifiers and data packets, and the synchronization priority can be sorted in advance for each combination; for example, high-risk, highly infectious epidemic scene type data packets are given priority. During the synchronization process, a breakpoint resumption mechanism is adopted: if the synchronization data packet transmission is interrupted, the transmission will continue from the breakpoint when the network is reconnected, avoiding data duplication or loss; during the synchronization process, the offline collection terminal displays the synchronization progress and the synchronization status corresponding to the scene identifier in real time (e.g., a certain scene data packet is being synchronized, a certain scene data packet is synchronized and completed), and if synchronization fails, the reason for the failure is displayed, guiding the user to troubleshoot and resynchronize.

[0045] The explanation begins with the design of scenario-based validation and rule iteration on the management side.

[0046] The management side is also equipped with a scenario-based verification and rule iteration module 14.

[0047] Specifically, the scenario-based verification and rule iteration module 14 is used to verify the data packet according to the scenario identifier, generate a verification report and mark the calibration status, and generate a confirmation rule matching instruction and a core acquisition field supplement instruction according to the verification report and calibration status.

[0048] The management-side verification includes data integrity verification, logical consistency verification, and rule matching verification. Data integrity verification verifies whether the epidemiological survey data in the data packet conforms to the scenario-specific core collection field configuration. Logical consistency verification compares data packets with historically similar scenarios and their corresponding judgment criteria (adapted rule versions) to determine if there are data contradictions; for example, in historically similar scenarios, the risk assessment criteria (rules) of the corresponding data packets may differ. Rule matching verification determines whether the rules in the current data packet conform to the latest rules in the same scenario, i.e., whether the rules in the judgment criteria of the current data packet are the latest rules in the rule base, preventing errors in judgment results due to outdated rules. The calibration status in the verification report includes: calibration successful; verification failed and data supplementation is required, or rule matching is abnormal.

[0049] The scenario-based verification and rule iteration module 14 is used to generate confirmation rule matching instructions and core collection field supplement instructions based on the verification report and calibration status. That is, when the verification result is verification failure and the verification status is that data needs to be supplemented or the rule matching is abnormal, it is pushed to all relevant offline collection terminals through the synchronization configuration module to realize rule iteration optimization; that is, the management terminal pushes the verification result to the original offline collection terminal through the synchronization configuration module to guide the user to supplement data or confirm the rule matching problem; after receiving the feedback, the offline collection terminal guides the user to supplement data or re-traverse the risk rules of the current scenario through a visual interface to verify the rule matching problem, regenerates the data packet and synchronizes it to the management terminal until the verification is successful.

[0050] The scenario-based verification and rule iteration module 14 is also used to periodically analyze the verification reports of each scenario. If it is found that the rules of a certain scenario have frequent matching anomalies (such as the judgment logic deviating from the actual flow investigation risk), the risk rules of that scenario are adjusted. The updated rules are pushed to all offline collection terminals through the synchronization configuration module to realize the iterative optimization of the rules.

[0051] In addition, the verification on the management end also includes result consistency verification. This result consistency verification involves comparing the latest rule version judgment result adapted by the scenario-based verification and rule iteration module in the management end using the scenario identifier with the judgment result in the data packet to determine if there are any inconsistencies. If inconsistencies exist, there may be rule matching errors or problems in the lightweight rule package generation process. In this case, the verification is deemed to have failed, a rule matching confirmation instruction is generated, and it is sent to the offline collection end through the synchronization configuration module. Simultaneously, a lightweight rule package generation optimization instruction is generated and sent to the synchronization configuration module. The synchronization configuration module 13 is also used to optimize the lightweight rules based on the lightweight rule package generation optimization instruction and regenerate the lightweight rule package.

[0052] In a specific embodiment, to make more rational use of network resources, reduce unnecessary data transmission, improve synchronization efficiency, ensure that the offline acquisition terminal obtains the latest dynamic parameter values ​​in a timely manner, and improve the accuracy of initial risk assessment, the system further includes: The synchronization configuration module is configured with a scene-layered synchronization strategy, including a rule partitioning unit and a synchronization push unit. The rule partitioning unit is used to pre-partition the generated rules into a static topology graph part and a dynamic parameter value part before performing lightweight processing on the generated rules. Its construction feature is that it can accurately identify the static and dynamic parts in the rules.

[0053] The synchronous push unit is used to select different frequencies for synchronous push of different parts of the lightweight rule package during the synchronous push of the lightweight rule package with single scene identifier to the offline collection terminal, so that the synchronous push frequency of the lightweight rule package of static topology map part is lower than the synchronous push frequency of the lightweight rule package of dynamic parameter value part. The rule partitioning unit and the synchronous push unit are connected through a data processing flow. The rule partitioning unit transmits the partitioned rule data to the synchronous push unit, which then performs synchronous push at different frequencies.

[0054] In a specific embodiment, to enhance the rule adaptability and forward-looking nature of the epidemiological investigation system, better address the needs of epidemiological investigations in different scenarios, and further improve the accuracy of epidemiological investigations and the efficiency of prevention and control, a beneficial extension and improvement of existing technologies has been made; the system also includes: The management terminal is also equipped with a scenario-based rule prediction module, including a rule prediction unit and a rule supplementation unit. The rule prediction unit is used to predict rules based on verification reports and calibration status, generating predicted rules. This involves using advanced data analysis and prediction algorithms, such as deep learning algorithms, to predict potentially needed rules based on historical epidemiological survey data and historical verification results. The rule supplementation unit is used to supplement the rule base, accurately adding predicted rules to the rule base. The rule prediction unit and the rule supplementation unit are connected via a data interface; the predicted rule data generated by the rule prediction unit is transmitted to the rule supplementation unit for supplementing the rule base.

[0055] The synchronization configuration module further includes a rule version processing unit and a dual-version synchronization unit. The rule version processing unit performs lightweight processing on the latest generated or updated rules and the predicted rules, respectively, and records them as a basic version lightweight rule package and a predicted version lightweight rule package, accurately processing and storing the different version rule packages. The dual-version synchronization unit is also used to select and simultaneously send both the basic version lightweight rule package and the predicted version lightweight rule package when synchronously sending the scene identifier-adapted lightweight rule package to the offline collection terminal, achieving synchronous sending of the dual-version rule packages. The rule version processing unit and the dual-version synchronization unit are connected through a data processing flow; the two versions of the rule package data processed by the rule version processing unit are transmitted to the dual-version synchronization unit for synchronous sending.

[0056] The synchronization request and preparation module also includes a version matching unit. This unit adaptively matches the version of the lightweight rule package based on the regional, time, and traffic information contained in the currently entered epidemiological survey data. It pre-sets a version loading strategy for the lightweight rule package that matches the combination of regional, time, and traffic information in the entered epidemiological survey data. The synchronization request and preparation module periodically sends user-entered information update prompts to guide users to update their data promptly.

[0057] Specifically, considering that regional information includes the risk level of the corresponding epidemic in the region, and the risk level of the epidemic varies in different regions, for regions with low to medium risk, a corresponding lightweight rule package of the basic version can be pre-set as a version loading strategy to test new rules within a controllable risk range and avoid serious consequences caused by misjudgment of high-risk clues; while for regions with medium risk, a corresponding lightweight rule package of the prediction version can be pre-set as a version loading strategy.

[0058] Based on time and traffic information, the system load within a corresponding time period can be obtained. If the system load exceeds a preset load threshold within the corresponding time period, a corresponding basic version lightweight rule package or a predicted version lightweight rule package can be pre-set as a version loading strategy to achieve basic loading and operation under high load conditions. If the system load is not greater than the preset load threshold within the corresponding time period, the basic version lightweight rule package and the predicted version lightweight rule package are loaded synchronously. The proportion is pre-adapted according to the size of the entered data traffic. The larger the data traffic, the smaller the proportion. The entered data is distributed proportionally to the basic version lightweight rule package and the predicted version lightweight rule package according to the adaptation ratio. This allows subsequent steps to verify the results of the rules based on the judgment results obtained from different versions of the lightweight rule package. If any problems are found, a quick rollback can be performed with a small impact.

[0059] The system combines regional, time, and traffic information to adaptively match and load the version of the lightweight rule package. If there is a conflict in the adaptation results, the time and traffic information adaptation results will be loaded with higher priority, and the regional information adaptation results will be used as a secondary factor.

[0060] like Figure 2 As shown, this application discloses an epidemiological investigation method based on scenario analysis, applying any of the systems described above, with specific steps including: S1. Receive content selected by the user based on the provided scene selection options and read the scene identifier. Send a synchronization request containing the scene identifier to the management terminal so that the management terminal can receive the synchronization request and read the scene identifier. Configure the system based on the lightweight rule package of the read scene identifier and the core collection fields associated with the scene identifier.

[0061] S2. Receive the lightweight rule package for scene identifier adaptation and the core collection field configuration associated with the scene identifier sent by the management terminal, load the lightweight rule package, and configure the core collection fields.

[0062] S3. Based on the received lightweight rule package, perform real-time risk assessment on the entered epidemiological survey data, and integrate the assessment results containing the assessment criteria with the epidemiological survey data to form a data package.

[0063] S4. Match the scene identifier and data packet with the preset synchronization priority sorting and synchronize the scene identifier and data packet to the management terminal according to the sorting order, so that the management terminal can verify the data packet according to the scene identifier, generate a verification report and mark the calibration status, and generate confirmation rule matching instructions and core acquisition field supplement instructions according to the verification report and calibration status.

[0064] S5. Re-receive the lightweight rule package and core collection fields sent by the management terminal, and repeat the process of loading the lightweight rule package, configuring the core collection fields, determining real-time risks, forming and uploading data packets, performing verification and generating a verification report until the verification is successful.

[0065] A computer-readable storage medium is also disclosed.

[0066] Specifically, the computer-readable storage medium stores a computer program that can be loaded by a processor and executed, such as the epidemiological investigation method based on scenario analysis described above. The computer-readable storage medium includes, for example, various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0067] This application also discloses a computer device.

[0068] Specifically, the computer device includes a memory and a processor, with the memory storing computer programs that can be loaded by the processor and executed using the aforementioned scenario-based epidemiological investigation methods.

[0069] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. An epidemiological investigation system based on scenario analysis, characterized in that, include: The system includes a management terminal and an offline collection terminal. The management terminal is configured with a scenario-based rule base construction module, a scenario-based data association module, a synchronization configuration module, and a scenario-based deep verification and rule iteration module. The offline collection terminal is configured with a synchronization request and preparation module, a scenario-based preliminary judgment engine module, and a synchronization execution module. The scenario-based rule base construction module is used to generate risk judgment rules based on the epidemic scenario; the scenario-based data association module is used to configure the association relationship between the data and the collected fields based on the epidemic scenario; the synchronization configuration module is used to perform lightweight processing on the generated rules; receive synchronization requests and read scenario identifiers, and synchronously send the lightweight rule package adapted to the scenario identifier and the core collected fields associated with the scenario identifier to the offline collection terminal. The synchronization request and preparation module is used to provide a scene selection option interface and read the selected scene identifier, send a synchronization request containing the scene identifier to the management terminal, receive and load the lightweight rule package, and configure the core collection fields; The scenario-based preliminary judgment engine module is used to perform real-time risk judgment on the input epidemiological survey data based on the received lightweight rule package, and integrate the judgment results containing the judgment basis with the epidemiological survey data to form a data package. The synchronization execution module is used to match the scene identifier and data packet with a preset synchronization priority sorting and synchronize the scene identifier and data packet to the management terminal according to the sorting order, and supports breakpoint resume. The scenario-based verification and rule iteration module is used to verify data packets according to scenario identifiers, generate verification reports and mark calibration status, generate confirmation rule matching instructions and core collection field supplement instructions based on the verification reports and calibration status, and push them to all relevant offline collection terminals through the synchronization configuration module to achieve iterative optimization of rules. The rules in the scenario-based rule base are stored in an associated structure that includes scenario identifiers, risk feature combinations, judgment logic and supplementary guidance instructions. The risk feature combinations are associated with the feature descriptions of the collection fields, the judgment logic defines the mapping relationship between risk feature combinations and risk levels, and the supplementary guidance instructions contain guidance on the core information that needs to be supplemented in preset high-risk scenarios. The management terminal's verification includes data integrity verification, logical consistency verification, and rule matching verification. The data integrity verification includes verifying whether the epidemiological survey data in the data packet conforms to the scenario-specific core collection field configuration. The logical consistency verification includes determining whether there are data contradictions by comparing the data packets of the same historical scenario. The rule matching verification includes determining whether the rules in the current data packet conform to the latest rules under the same scenario.

2. The epidemiological investigation system based on scenario analysis according to claim 1, characterized in that, The synchronization configuration module is configured with a scenario-based synchronization strategy, and is also used to synchronously send a lightweight rule package adapted to multiple scenario identifiers and the configuration of core collection fields associated with multiple scenario identifiers to the offline collection terminal according to the scenario-based synchronization strategy; the scenario-based synchronization strategy includes a synchronization priority, encrypted transmission protocol and data matching and verification rules preset according to the scenario identifier.

3. The epidemiological investigation system based on scenario analysis according to claim 1, characterized in that, The synchronization configuration module configures a scene-layered synchronization strategy and is also used to pre-divide the generated rules into a static topology graph part and a dynamic parameter value part before performing lightweight processing on the generated rules, and to perform lightweight processing on the corresponding rules of each part respectively; in the process of synchronously pushing the lightweight rule package of a single scene identifier to the offline collection terminal, different frequencies of synchronous push are selected for different parts of the lightweight rule package, so that the synchronous push frequency of the lightweight rule package of the static topology graph part is lower than the synchronous push frequency of the lightweight rule package of the dynamic parameter value part.

4. The epidemiological investigation system based on scenario analysis according to claim 1, characterized in that, The management terminal is also configured with a scenario-based rule prediction module; the scenario-based rule base prediction module is used to predict rules based on the verification report and calibration status, generate predicted rules, and supplement the rules in the rule base. The synchronization configuration module is also used to perform lightweight processing on the latest rules and predicted rules after generation or update, and record them as the basic version lightweight rule package and the predicted version lightweight rule package respectively; when synchronously sending the scene identifier-adapted lightweight rule package to the offline collection terminal, it selects to synchronously send the basic version lightweight rule package and the predicted version lightweight rule package. The synchronization request and preparation module is also used to receive and load the basic version of the lightweight rule package and the predicted version of the lightweight rule package, and adaptively match the version of the lightweight rule package to be loaded based on the regional information, time information and traffic information contained in the epidemiological survey data entered by the current user; and pre-set a version loading strategy of the lightweight rule package that is compatible with the combination of regional information, time information and traffic information contained in the entered epidemiological survey data.

5. The epidemiological investigation system based on scenario analysis according to claim 1, characterized in that, The scenario-based rule base contains rule version information; the synchronization request and preparation module is also used to send a synchronization request containing the rule version information of the current scenario to the management terminal; the synchronization configuration module is also used to push the latest version of the lightweight rule package by comparing the rule version information.

6. The epidemiological investigation system based on scenario analysis according to claim 1, characterized in that, The scenario-based preliminary judgment engine module also includes a feature extraction unit and a rule matching unit; the feature extraction unit is used to convert real-time input data into structured risk features; The rule matching unit is used to traverse the rules of the current scene based on the loaded lightweight rule package, compare them, and generate missing feature prompt information when the feature part is matched.

7. The epidemiological investigation system based on scenario analysis according to claim 1, characterized in that, The scenario initial judgment engine module is equipped with a supplementary data entry guidance unit. After the risk level judgment is completed, the supplementary data entry guidance unit calls the supplementary guidance instruction to generate a structured supplementary data entry interface. The supplementary information based on the supplementary data entry interface is verified for completeness and then linked with the original epidemiological survey data and the judgment results containing the judgment criteria to form a complete data package for storage.

8. A scenario-based epidemiological investigation method using the system described in any one of claims 1 to 7, characterized in that, include: The system receives content selected by the user based on the provided scene selection options and reads the scene identifier. It then sends a synchronization request containing the scene identifier to the management terminal, so that the management terminal receives the synchronization request and reads the scene identifier. The system then configures the system based on the lightweight rule package of the read scene identifier and the core collection fields associated with the scene identifier. Receive the lightweight rule package for scene identifier adaptation and the core collection field configuration associated with the scene identifier sent by the management terminal, load the lightweight rule package, and configure the core collection fields; Based on the received lightweight rule package, the system performs real-time risk assessment on the entered epidemiological survey data and integrates the assessment results, which include the assessment criteria, with the epidemiological survey data to form a data package. The system matches the scene identifier and data packets with a preset synchronization priority and synchronizes the scene identifier and data packets to the management terminal in the sorted order. This allows the management terminal to verify the data packets based on the scene identifier, generate a verification report and mark the calibration status, and generate confirmation rule matching instructions and core acquisition field supplement instructions based on the verification report and calibration status. The system re-receives the lightweight rule package and core collection fields sent by the management terminal, and repeats the process of loading the lightweight rule package, configuring the core collection fields, determining real-time risks, forming and uploading data packets, performing verification and generating a verification report until the verification passes.

Images