Public health emergency command information management method and system

Abstract

The application discloses a public health emergency command information management method and system, relates to the field of public health emergency management, and comprises the following steps: receiving a self-description information package; when an abnormal characteristic information of a preset type is collected by a field information collection device, generating characteristic description information corresponding to the abnormal characteristic information, and encapsulating the abnormal characteristic information and the characteristic description information to form a data package; dynamically adjusting a data storage structure according to the characteristic description information in the self-description information package to store the abnormal characteristic information; extracting auxiliary information related to the abnormal characteristic information from the self-description information package, and calibrating the collection time and / or the geographic position of the abnormal characteristic information according to the auxiliary information; associating the calibrated abnormal characteristic information with related flow adjustment data and detection results, and providing a unified event situation information view to assist in making emergency command decisions. The application can ensure the efficiency and accuracy of public health emergency command.

Description

Technical Field

[0001] This application relates to the field of public health emergency management, and in particular to an information management method and system for public health emergency command. Background Technology

[0002] In the field of public health emergency management, rapid and accurate information processing is crucial. While traditional management systems can handle routine data, their reliance on pre-defined data formats and fixed communication rules often proves inadequate when dealing with emergencies such as novel pathogens. When unprecedented information (such as descriptions of novel symptoms, non-standard images, or audio) appears on-site, the system, lacking corresponding fields, can only rely on unstructured fields such as "remarks" or "attachments" for temporary storage, resulting in critical information being unrecognizable and unretrieval by subsequent systems. Furthermore, non-standard labeling of samples used on-site to differentiate priorities (such as adding special suffixes) can lead to sample association failures and timestamp recording errors due to incompatibility with the strict format rules of Laboratory Information Management Systems (LIMS).

[0003] The command center was unable to accurately match the unique symptoms or environmental exposure characteristics of novel pathogens discovered during on-site epidemiological investigations with the timelines of laboratory-confirmed cases. This resulted in some crucial clues for tracing the source of infection, such as the correlation between exposure at a specific location and the onset time of subsequent cases, becoming unclear due to inaccurate time information. Simultaneously, the inability to effectively utilize the characteristics of novel pathogens in unstructured data made it difficult for the command center to promptly identify potential hidden transmission chains within a region or to accurately assess the impact of specific interventions on the spread of the epidemic. This disconnect in data sharing and process coordination severely impacted the efficiency and accuracy of public health emergency command. Summary of the Invention

[0004] Therefore, this application proposes an information management method and system for public health emergency command, aiming to solve the technical problems of existing public health emergency management systems when processing new abnormal characteristic information that exceeds the preset type. These problems include rigid data formats, limited parsing logic, and inaccurate information association, which lead to the disconnect in data sharing and process connection, seriously affecting the efficiency and accuracy of public health emergency command.

[0005] Firstly, this application provides an information management method for public health emergency command, comprising the following steps: Receive a self-describing information packet, wherein the self-describing information packet is a data packet formed by the field information acquisition device generating feature description information corresponding to the abnormal feature information when it acquires abnormal feature information that exceeds the preset type, and encapsulating the abnormal feature information and the feature description information. The data storage structure is dynamically adjusted based on the feature description information in the self-describing information package to store the abnormal feature information; Extract auxiliary information related to the abnormal feature information from the self-describing information package, and calibrate the collection time and / or geographical location of the abnormal feature information based on the auxiliary information; The calibrated abnormal feature information is correlated with associated epidemiological investigation data and detection results, and a unified view of the event situation information is provided to assist in the formulation of emergency command decisions.

[0006] According to some embodiments of this application, the encapsulation step of the self-describing information packet includes: When abnormal feature information exceeding the preset type is collected on the on-site information collection equipment, one or more standardized descriptive tags are retrieved and recommended based on the type and content of the abnormal feature information. Select recommended standardized description tags or obtain custom description tags from external input, and associate them with the abnormal feature information to generate feature description information corresponding to the abnormal feature information; The abnormal feature information and feature description information are encapsulated into a self-describing information package.

[0007] According to some embodiments of this application, the step of retrieving and recommending one or more standardized descriptive tags based on the type and content of the abnormal feature information when abnormal feature information exceeding a preset type is collected on the on-site information collection device includes: On the on-site information acquisition equipment, when abnormal feature information exceeding the preset type is acquired, the features of the abnormal feature information are extracted. Calculate the semantic similarity between the features of the abnormal feature information and the features of each preset tag in the preset semantic tag library of the on-site information acquisition device; Determine whether there is a value in the semantic similarity that is higher than a preset similarity threshold; If there is a value in the semantic similarity that is higher than the preset similarity threshold, then the preset tags in the preset semantic tag library with similarity higher than the preset similarity threshold will be recommended as standardized description tags for on-site personnel to select. If there is no value in the semantic similarity that is higher than the preset similarity threshold, then the tag expansion process is triggered, which includes: Retrieve candidate terms related to the features of the abnormal feature information from external knowledge sources, and use them as candidate extended tags after processing; The candidate extended tags are recommended as standardized descriptive tags for on-site personnel to select.

[0008] According to some embodiments of this application, the steps for standardizing description label recommendation output include: The standardized description tags are sorted according to the semantic similarity between each standardized description tag and the abnormal feature information; The sorted standardized description labels are then recommended and output as a list.

[0009] According to some embodiments of this application, the preset similarity threshold is dynamically adjusted according to the stage or level of the current public health event.

[0010] According to some embodiments of this application, the step of retrieving candidate terms related to the features of the abnormal feature information from external knowledge sources and processing them as candidate extended tags includes: Obtain scientific literature or report texts related to the characteristics of the abnormal features from a pre-set authoritative medical database or epidemiological knowledge base; Language processing is performed on the scientific literature or report texts to extract core terms describing clinical symptoms, pathogen characteristics, or exposure factors; The core terms are deduplicated and normalized to form the candidate extended tags.

[0011] According to some embodiments of this application, the step of dynamically adjusting the data storage structure based on the feature description information in the self-describing information package to store the abnormal feature information includes: Parse the self-describing information packet to obtain its feature description information; Determine whether the feature description information is appearing for the first time; If this is the first occurrence, then in the database management system, a data table structure is dynamically created or expanded for the data type corresponding to the feature description information to store the abnormal feature information.

[0012] According to some embodiments of this application, the step of extracting auxiliary information related to the abnormal feature information from the self-describing information package and calibrating the collection time and / or geographical location of the abnormal feature information based on the auxiliary information includes: When the abnormal feature information includes a multimedia file, the creation timestamp and / or geographic coordinates in the metadata of the multimedia file are parsed and extracted, and the creation timestamp and / or geographic coordinates are used as auxiliary information. The auxiliary information is compared with the collection timestamp and / or geographical location encapsulated in the self-describing information package; Based on the comparison results, the deviation between the auxiliary information and the timestamp and / or geographic coordinates encapsulated in the self-describing information package is determined; if the deviation exceeds a preset threshold, calibration is performed using the timestamp and / or geographic coordinates in the auxiliary information.

[0013] According to some embodiments of this application, the step of associating the calibrated abnormal feature information with relevant epidemiological investigation data and detection results, and providing a unified view of event situation information to assist in making emergency command decisions, includes: The stored abnormal feature information is then uniformly correlated with routine epidemiological investigation data and laboratory test results to obtain the correlation results; Based on the aforementioned correlation results, a unified event situation information view is constructed and provided to assist in the formulation of emergency command decisions; wherein, the event situation information view supports information query and integrated display by case identifier, time range, or geographical region.

[0014] Secondly, this application also provides a public health emergency command and information management system, including: The information receiving module is used to receive a self-describing information packet. The self-describing information packet is a data packet formed by the field information acquisition device generating feature description information corresponding to the abnormal feature information when it acquires abnormal feature information that exceeds the preset type, and encapsulating the abnormal feature information and the feature description information. The data storage module is used to dynamically adjust the data storage structure according to the feature description information in the self-describing information package in order to store the abnormal feature information; The information calibration module is used to extract auxiliary information related to the abnormal feature information from the self-describing information package, and to calibrate the collection time and / or geographical location of the abnormal feature information based on the auxiliary information. The information association module is used to associate the calibrated abnormal feature information with related epidemiological investigation data and detection results, and to provide a unified view of event situation information to assist in making emergency command decisions.

[0015] The technical solution according to the embodiments of this application has at least the following beneficial effects: The public health emergency command information management method proposed in this application effectively solves the problems of rigid data format, limited parsing logic, and inaccurate information association in traditional systems when processing unknown or abnormal public health event information through innovative mechanisms such as self-describing information packages, dynamic data storage and adjustment, auxiliary information calibration, and unified event situation information view. It eliminates the gaps in data sharing and process connection, and ensures the efficiency and accuracy of public health emergency command.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0018] Figure 1 This is a flowchart illustrating a public health emergency command information management method provided in an embodiment of this application.

[0019] Figure 2 This is a schematic diagram of the architecture of a public health emergency command and information management system provided in an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical methods, 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.

[0021] It should be noted that if the terms "first" or "second" are used, they are only for the purpose of distinguishing technical features and should not be interpreted as indicating or implying relative importance, or implicitly indicating the number of technical features indicated, or implicitly indicating the order of the technical features indicated.

[0022] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, or the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0023] In the field of public health emergency management, traditional information management systems perform well when processing routine data. However, when faced with sudden public health emergencies, especially the emergence of novel pathogens or unknown abnormal characteristics, their pre-set data formats and communication rules often prove rigid and inadequate. This limitation makes it difficult to effectively identify, store, and process critical unstructured data, thereby affecting the timeliness and accuracy of emergency command and decision-making. For example, abnormal characteristic information such as descriptions of novel rashes, environmental photo metadata, or transcripts of voice recordings collected on-site, lacking corresponding structured fields, is often simply categorized as "remarks" or "attachments," preventing its crucial information from entering the core analysis process. Simultaneously, non-standardized sample numbers may prevent the automatic correlation between laboratory test results and sample information, or even result in timestamp errors, severely hindering accurate assessment of the epidemic situation and precise tracing of the source of infection.

[0024] For this, please refer to Figure 1This application proposes an information management method for public health emergency command, comprising the following steps: S110, Receive a self-describing information packet, wherein the self-describing information packet is a data packet formed by the field information acquisition device generating feature description information corresponding to the abnormal feature information when it acquires abnormal feature information that exceeds the preset type, and encapsulating the abnormal feature information and the feature description information. S120, dynamically adjust the data storage structure according to the feature description information in the self-describing information package to store the abnormal feature information; S130, extract auxiliary information related to the abnormal feature information from the self-describing information package, and calibrate the collection time and / or geographical location of the abnormal feature information based on the auxiliary information; S140, the calibrated abnormal feature information is associated with the relevant epidemiological investigation data and detection results, and a unified view of the event situation information is provided to assist in the formulation of emergency command decisions.

[0025] To better understand the information management method for public health emergency command proposed in this application, some key terms involved will be explained first.

[0026] A "self-describing information packet" is a special data encapsulation format that not only contains anomalous feature information collected by field information acquisition equipment, but also "feature description information" describing these anomalous feature information. The unique feature of this information packet is its "self-describing" capability, that is, it can carry its own data structure and semantic information, allowing the receiver to understand and process the content without the need for preset parsing rules.

[0027] "Abnormal characteristic information" refers to potentially important information collected by on-site information collection equipment during public health emergencies that exceeds the preset data types or formats of the current system. Examples include descriptions of unknown symptoms caused by novel pathogens, photos of atypical environmental exposures, or unstructured voice recordings.

[0028] "Feature description information" refers to metadata that semantically describes anomalous feature information. It can clearly explain the type, content, and source of anomalous feature information, enabling the system to understand the meaning of this unstructured or semi-structured data. For example, for a photo of a novel rash, the feature description information might include tags such as "novel rash photo," "dermatologist's diagnosis," and "suspected viral infection."

[0029] "Auxiliary information" refers to supplementary data encapsulated together with the anomalous feature information in a self-describing information package, or that can be extracted from the anomalous feature information itself (such as the metadata of a multimedia file), used to verify or calibrate the time or geographical location of the anomalous feature information collection. For example, the shooting timestamp and GPS coordinates included in the EXIF ​​information of a photograph.

[0030] "Epidemiological investigation data" refers to various information related to cases collected during the epidemiological investigation process, including but not limited to basic information of the case, onset time, contact history, activity trajectory, clinical manifestations, etc.

[0031] "Test results" refers to the results obtained by the laboratory after testing the sample, such as the results of pathogen nucleic acid testing and antibody testing.

[0032] The "Event Situation Information View" is a comprehensive information display interface that integrates processed and correlated abnormal feature information, epidemiological investigation data, test results, etc., to present the overall situation of the epidemic in an intuitive and visual way, assisting decision-makers in making judgments and directing operations.

[0033] The core of the public health emergency command information management method proposed in this application lies in its ability to flexibly handle unknown or abnormal information. Specifically, the method includes the following main steps: The first step is to receive the self-describing information package. In practical applications, on-site information acquisition devices, such as smartphones, tablets, or dedicated medical monitoring devices, generate feature description information corresponding to the abnormal feature information when they collect abnormal feature information that exceeds the preset type. For example, when on-site personnel use a smartphone to take a photo of a previously unseen rash, the device can prompt the on-site personnel to input or select tags describing the rash characteristics, such as "novel viral rash" or "fever with rash of unknown cause," etc. These tags are the feature description information. Subsequently, the abnormal feature information (i.e., the rash photo) and the feature description information (i.e., the description tags) are encapsulated into a self-describing information package.

[0034] The second step is to dynamically adjust the data storage structure based on the feature description information in the self-describing information packet to store the abnormal feature information. When the system receives the self-describing information packet, it parses the feature description information within it. For example, if the feature description information indicates that the packet contains data on "novel viral rash," and the current database does not have a dedicated table structure for storing such data, the system will dynamically create or expand the corresponding data table structure based on this description information. Specifically, the system can automatically generate new fields or tables based on keywords in the feature description information to adapt to the storage needs of different types of abnormal feature information. For example, a new data table can be created for "novel viral rash," containing fields such as "rash location," "rash morphology," and "accompanying symptoms." This dynamic adjustment mechanism ensures that the system can flexibly store and manage various unknown or novel abnormal feature information, avoiding information loss or processing difficulties caused by data structure mismatches.

[0035] The third step is to extract auxiliary information related to the anomalous feature information from the self-describing information package and calibrate the collection time and / or geographical location of the anomalous feature information based on the auxiliary information. For example, when the anomalous feature information contains multimedia files (such as photos or videos), the system can parse and extract the metadata of these multimedia files, such as the creation timestamp and GPS geographic coordinates in the EXIF ​​information. This metadata can then serve as auxiliary information. Subsequently, the system compares this auxiliary information with the collection timestamp and / or geographical location encapsulated in the self-describing information package. If a significant discrepancy is found between the two (e.g., the creation time of the multimedia file differs from the collection time recorded in the information package by several hours), the system will calibrate based on the timestamp and / or geographical coordinates in the auxiliary information. As another implementation, if the self-describing information package contains auxiliary information manually entered by on-site personnel, such as a textual description of the collection time or location, the system can also use natural language processing technology to extract this information and cross-validate it with the automatically recorded timestamp and geographical location to improve the accuracy of the data.

[0036] The fourth step involves associating the calibrated abnormal feature information with relevant epidemiological investigation data and test results, and providing a unified view of the event situation to assist in emergency command decisions. After the abnormal feature information is calibrated, the system will uniformly associate it with existing epidemiological investigation data (such as the case's contact history and activity trajectory) and laboratory test results (such as positive results for pathogen nucleic acid testing). For example, if the calibrated abnormal feature information (such as a photo of a novel rash) is associated with the epidemiological investigation data of a case (such as the case's recent activity trajectory) and its test results (such as a positive result for novel coronavirus nucleic acid) in terms of time, location, or case identification, the system will integrate this information. Based on these association results, the system will construct and provide a unified view of the event situation. This view can be displayed in various forms such as maps, timelines, and charts. For example, the map can mark the geographical distribution of novel rash cases and use color depth to represent the number of cases; the timeline can display the onset time of cases, the reporting time of test results, and the collection time of abnormal feature information, thus clearly presenting the overall situation of the epidemic. This view supports information retrieval and integrated display by case identifier, time range, or geographical region, thereby assisting decision-makers in fully understanding the development of the epidemic and making scientific emergency command decisions.

[0037] This application has the following advantages: First, this application utilizes self-describing information packets to enable anomalous feature information to carry its own semantic description, thereby allowing the system to dynamically understand and process these novel data, avoiding information loss and processing delays. For example, in existing systems, a photo of a novel rash might only be considered an attachment, and its inherent epidemiological significance is difficult to automatically identify. In this application, however, the photo is accompanied by feature description information such as "novel viral rash," enabling the system to identify its type and perform targeted processing.

[0038] Secondly, this application can dynamically adjust the data storage structure based on the feature description information in the self-describing information package, such as automatically creating new data tables or expanding existing fields, thereby achieving seamless storage and management of unknown data types. This significantly reduces system maintenance costs and improves the system's response speed to unexpected events.

[0039] Furthermore, this application effectively improves the accuracy and reliability of data by extracting auxiliary information (such as metadata of multimedia files) from the self-describing information package and calibrating the collection time and / or geographical location of anomalous feature information based on this auxiliary information. This is crucial for accurately tracing the source of infection and assessing the transmission path of the epidemic.

[0040] Finally, in terms of decision support, this application unifies the association between calibrated abnormal characteristic information and epidemiological investigation data and test results, and provides a unified view of event situation information. This view supports multi-dimensional querying and integrated display, which can assist decision-makers in gaining a more comprehensive and accurate understanding of the epidemic situation, thereby enabling them to formulate more scientific and timely emergency command decisions. For example, by integrating the geographical distribution of the novel rash, the activity trajectory of cases, and laboratory test results, the command center can more quickly identify potential transmission chains and high-risk areas.

[0041] In summary, the public health emergency command information management method proposed in this application effectively solves the problems of rigid data formats, limited parsing logic, and inaccurate information correlation in traditional systems when processing information on unknown or abnormal public health events through innovative mechanisms such as self-describing information packages, dynamic data storage and adjustment, auxiliary information calibration, and unified event situation information view. It also eliminates the gaps in data sharing and process connection, ensuring the efficiency and accuracy of public health emergency command.

[0042] In some embodiments of this application, the encapsulation step of the self-describing information packet preferably includes: When abnormal feature information exceeding the preset type is collected on the on-site information collection equipment, one or more standardized descriptive tags are retrieved and recommended based on the type and content of the abnormal feature information. Select recommended standardized description tags or obtain custom description tags from external input, and associate them with the abnormal feature information to generate feature description information corresponding to the abnormal feature information; The abnormal feature information and feature description information are encapsulated into a self-describing information package.

[0043] Among them, on-site information collection equipment refers to hardware or software systems used to collect various types of data at the scene of public health events, such as smartphones, wearable sensors, IoT devices, or specialized medical testing equipment. When on-site information collection equipment collects abnormal characteristic information beyond the preset types, such as discovering new pathogen symptoms, unknown environmental pollution indicators, or abnormal crowd gathering patterns, the system needs to effectively describe it. Specifically, based on the type and content of the abnormal characteristic information, the system will retrieve and recommend one or more standardized descriptive tags from a preset tag library. These standardized descriptive tags aim to provide a unified and standardized semantic description, ensuring that abnormal information from different sources can be consistently understood and processed.

[0044] Furthermore, on-site personnel can choose from the system-recommended standardized description tags or input custom description tags based on the actual situation. The selected or input tags will be associated with the anomaly feature information, thereby generating feature description information corresponding to that anomaly feature information. This feature description information is crucial for semantically annotating the anomaly feature information, enabling the raw, unstructured anomaly data to possess understandable and processable metadata. Finally, the anomaly feature information and the generated feature description information are encapsulated into a self-describing information package. This self-describing information package is a complete data unit containing the raw anomaly data and descriptive information that semantically interprets it, allowing the recipient to understand and process the content without prior knowledge of the data structure.

[0045] This application's solution addresses the problem of rapid identification, classification, and storage of abnormal information in traditional systems by performing real-time and flexible semantic annotation and encapsulation of abnormal feature information at the on-site information acquisition device. By introducing standardized and custom descriptive tags, a mechanism ensures that abnormal feature information possesses a clear semantic context before transmission and processing. This preprocessing mechanism enables subsequent data storage structure adjustments, information calibration, and correlation analysis to be performed more efficiently and accurately.

[0046] In a preferred embodiment, when abnormal feature information exceeding a preset type is collected on the field information acquisition device, the step of retrieving and recommending one or more standardized descriptive tags based on the type and content of the abnormal feature information can be further refined into the following process.

[0047] On the on-site information acquisition equipment, when abnormal feature information exceeding the preset type is acquired, the features of the abnormal feature information are extracted. Calculate the semantic similarity between the features of the abnormal feature information and the features of each preset tag in the preset semantic tag library of the on-site information acquisition device; Determine whether there is a value in the semantic similarity that is higher than a preset similarity threshold; If there is a value in the semantic similarity that is higher than the preset similarity threshold, then the preset tags in the preset semantic tag library with similarity higher than the preset similarity threshold will be recommended as standardized description tags for on-site personnel to select. If there is no value in the semantic similarity that is higher than the preset similarity threshold, then the tag expansion process is triggered, which includes: Retrieve candidate terms related to the features of the abnormal feature information from external knowledge sources, and use them as candidate extended tags after processing; The candidate extended tags are recommended as standardized descriptive tags for on-site personnel to select.

[0048] Specifically, when the on-site information acquisition equipment collects abnormal feature information that exceeds the preset type, feature extraction is first required for this abnormal feature information. Feature extraction can be performed based on the specific type of abnormal feature information. For example, if the abnormal feature information is text data, natural language processing (NLP) technology can be used to extract keywords, entities, or topics; if it is image or video data, image recognition or video analysis technology can be used to extract visual features, such as lesion morphology and color changes; if it is sensor data, its temporal pattern or abnormal fluctuation characteristics can be extracted. The extracted features aim to comprehensively and accurately characterize the core content of the abnormal feature information.

[0049] Subsequently, semantic similarity is calculated between the features of the anomalous feature information and the features of each preset tag in the preset semantic tag library built into the on-site information acquisition device. The preset semantic tag library may contain a series of known, standardized public health event-related terms or classification tags, such as International Classification of Diseases (ICD) codes, Medical Subject Headings (MeSH), or tags from specific epidemiological classification systems. Semantic similarity can be calculated using various methods, such as cosine similarity based on word vector models, path similarity based on ontology knowledge, or Jaccard similarity based on text matching. Through calculation, the degree of association between the anomalous feature information and existing standardized descriptive tags can be quantified.

[0050] After obtaining semantic similarity, the system will determine whether there are any values ​​higher than a preset similarity threshold. The preset similarity threshold is a configurable parameter used to define the degree of matching between abnormal feature information and preset tags. If there are values ​​higher than the preset similarity threshold, it indicates that the abnormal feature information has a high degree of matching with certain tags in the preset semantic tag library. In this case, these preset tags with similarity higher than the threshold will be recommended as standardized descriptive tags for on-site personnel to select or directly apply.

[0051] However, in certain situations, particularly when novel diseases, rare symptoms, or unknown pathogens emerge, the features of the anomalous characteristic information may not achieve a similarity threshold with any tag in the preset semantic tag library. In such cases, to ensure accurate description of novel or unknown anomalous characteristic information, the system will trigger a tag expansion process. This tag expansion process aims to find potential descriptive tags from a broader range of knowledge sources. Specifically, this process includes retrieving candidate terms related to the features of the anomalous characteristic information from external knowledge sources. These external knowledge sources may include authoritative medical databases (such as PubMed and Medline), epidemiological knowledge bases, scientific literature databases, or public health reports. By performing information retrieval and processing on these external knowledge sources, such as text mining, entity recognition, and term extraction, a series of candidate terms related to the anomalous characteristic information can be obtained. After deduplication and normalization, these candidate terms form candidate expanded tags. Finally, these candidate expanded tags will also be output as standardized descriptive tags for on-site personnel to choose from, thereby supplementing the deficiencies of the preset tag library.

[0052] In a further embodiment of this application, the step of standardizing the description label recommendation output preferably includes: The standardized description tags are sorted according to the semantic similarity between each standardized description tag and the abnormal feature information; The sorted standardized description labels are then recommended and output as a list.

[0053] Specifically, when recommending standardized descriptive tags, the system first utilizes the semantic similarity between each standardized descriptive tag and the anomaly feature information, calculated previously. This semantic similarity reflects the degree of semantic association or matching between the tag and the anomaly feature information. Based on these similarity values, the standardized descriptive tags are sorted from high to low (or from low to high, usually from high to low to highlight the most relevant items) according to their similarity. This sorting process can employ various known sorting algorithms. Furthermore, the sorted standardized descriptive tags are presented to on-site personnel in a list format. This list format can be a drop-down menu in a graphical user interface, a checkbox list, or any other clear and intuitive list display format designed to facilitate user browsing and selection.

[0054] This application's solution effectively addresses the difficulty faced by on-site personnel in selecting from multiple recommended tags by sorting the recommended standardized descriptive tags and outputting them in a list format. Because the sorting is based on semantic similarity, the most relevant tags are placed prominently in the list, enabling on-site personnel to quickly locate and assess the applicability of these tags. Simultaneously, the list format provides a structured and easy-to-read interface, avoiding information overload and simplifying the user's selection process.

[0055] In a further embodiment of this application, the preset similarity threshold is dynamically adjusted according to the stage or level of the current public health event.

[0056] Specifically, the stages or levels of a public health event can be understood as an assessment of the current state and severity of the event. For example, the stages of a public health event can include the warning period, outbreak period, spread period, control period, and recovery period; the levels of a public health event can be divided into different levels according to national or local emergency response mechanisms, such as Level I, Level II, Level III, and Level IV responses. In practical applications, dynamic adjustment refers to modifying and updating the preset similarity threshold in real time or periodically according to changes in the stage or level of the public health event. For example, in the early warning stage of a public health event, a lower similarity threshold may be needed to capture any potential, even weak, abnormal signals; while after the event enters a stable control stage, a higher similarity threshold may be needed to focus on key, clearly defined abnormal features.

[0057] The proposed solution links and dynamically adjusts a preset similarity threshold to the stage or level of a public health event, enabling the label recommendation mechanism to better adapt to the complexity and dynamism of public health events.

[0058] The following is a specific example to illustrate this.

[0059] Suppose a novel infectious disease outbreak occurs in a certain area. In the early warning stage, due to incomplete understanding of the pathogen and symptoms, the system sets a low preset similarity threshold (e.g., 0.6) to ensure that on-site data collection equipment can capture any abnormal features that show some similarity to known disease symptoms or pathogen characteristics. Even if the similarity is low, appropriate descriptive labels can still be recommended, thus expanding the monitoring scope and avoiding the omission of early signals. As the outbreak progresses and a clearer understanding of the pathogen and main clinical symptoms is achieved, the system appropriately increases the preset similarity threshold (e.g., 0.75) to focus on abnormal information highly correlated with known outbreak characteristics, reducing interference from non-critical information and improving the accuracy of label recommendations, thereby more effectively identifying and tracing cases. When the outbreak enters the control or recovery phase, the system can further increase the preset similarity threshold (e.g., 0.85) to ensure that only labels highly matching specific and clear outbreak characteristics are recommended for monitoring the eventual decline of the outbreak or identifying potential variants, thus supporting precise prevention and control and routine management. Through this dynamic adjustment mechanism, the system can flexibly adjust the label recommendation strategy according to the actual needs of public health events, thereby providing the most appropriate information support at different stages.

[0060] In some embodiments of this application, the step of retrieving candidate terms related to the features of the anomalous feature information from external knowledge sources and processing them as candidate extended tags preferably includes: Obtain scientific literature or report texts related to the characteristics of the abnormal features from a pre-set authoritative medical database or epidemiological knowledge base; Language processing is performed on the scientific literature or report texts to extract core terms describing clinical symptoms, pathogen characteristics, or exposure factors; The core terms are deduplicated and normalized to form the candidate extended tags.

[0061] Specifically, when it is necessary to retrieve candidate terms from external knowledge sources, the system will first access pre-defined authoritative medical databases or epidemiological knowledge bases. These knowledge bases may include, but are not limited to, PubMed, WHO databases, CDC reports, and guidelines issued by the National Center for Disease Control and Prevention, and are characterized by containing a large amount of expert-verified professional information related to public health events. By querying these databases, scientific literature or report texts that are highly relevant to the characteristics of the anomalous information can be obtained.

[0062] Furthermore, the acquired scientific literature or report texts are sent to the language processing module for analysis. This language processing process can employ Natural Language Processing (NLP) techniques, such as text segmentation, part-of-speech tagging, named entity recognition, and keyword extraction, aiming to accurately identify and extract core terms describing clinical symptoms (such as fever, cough, and fatigue), pathogen characteristics (such as virus type, bacterial species, and transmission route), or exposure factors (such as contact history, travel history, and occupational exposure) from massive amounts of text information. These core terms form the basis for standardized descriptive labels.

[0063] Subsequently, the extracted core terms undergo deduplication and normalization. Deduplication aims to eliminate duplicate terms, ensuring the uniqueness of candidate extended labels. Normalization includes, but is not limited to, mapping synonyms or near-synonyms to a unified expression, correcting spelling errors, and aligning terms with predefined medical ontologies or terminology sets (such as SNOMED CT, ICD codes) to ensure the consistency and standardization of the resulting candidate extended labels. Thus, the processed set of terms forms the candidate extended labels, available for selection by on-site personnel.

[0064] The proposed solution, through the aforementioned steps, ensures that, even when a pre-defined semantic tag library cannot provide suitable tags, candidate terms highly relevant to anomalous feature information can be systematically and accurately obtained from authoritative and professional external knowledge sources. First, obtaining scientific literature and reports from authoritative databases guarantees the reliability and professionalism of the information sources. Second, language processing technology efficiently and accurately extracts key core terms from complex text, avoiding the inefficiency and subjectivity of manual screening. Finally, deduplication and standardization of core terms further improve the quality and usability of candidate expanded tags, making them more aligned with the standardized requirements of public health emergency command. It is precisely the synergistic effect of these steps that enables the tag expansion process to provide high-quality, selectable, standardized descriptive tags.

[0065] In some embodiments of this application, the step of dynamically adjusting the data storage structure based on the feature description information in the self-describing information packet to store abnormal feature information preferably includes: Parse the self-describing information packet to obtain its feature description information; Determine whether the feature description information is appearing for the first time; If this is the first occurrence, then in the database management system, a data table structure is dynamically created or expanded for the data type corresponding to the feature description information to store the abnormal feature information.

[0066] The purpose of parsing the self-describing information packet is to accurately identify and extract metadata about abnormal characteristics from the received data packet, namely, feature description information. This feature description information usually exists in a structured or semi-structured form, such as JSON, XML, or other predefined data formats, and its content describes in detail the type, attributes, data format, etc. of the abnormal characteristics.

[0067] Furthermore, determining whether a feature description is appearing for the first time involves the system comparing new feature descriptions with known or registered feature descriptions. This can be done by querying a metadata registry, data dictionary, or existing database schema definition. If the feature description has never been recorded or processed in the system before, it is considered to be appearing for the first time.

[0068] Specifically, if the feature description information is determined to be appearing for the first time, the database management system will automatically create a new data table or expand an existing data table based on the data type and structure defined by the feature description information. For example, if the feature description information indicates the gene sequence data of a completely new viral variant, the system can dynamically create a data table specifically for storing the gene sequence of that variant and define the corresponding fields and data types; or, if the feature description information indicates a new symptom of an existing disease, the system can add new fields to the existing symptom data table to record the specific attributes of the new symptom. This process aims to ensure that all received abnormal feature information, regardless of whether its type is preset, can be properly stored and managed.

[0069] The proposed solution first parses the self-describing information packet to accurately obtain the feature description information it contains. Then, by determining whether this feature description information is encountered for the first time by the system, it achieves the identification of novel anomalous feature information. Once new feature description information is identified, the system can dynamically create or expand the corresponding data table structure in the database management system based on the data type it describes. This mechanism allows the system to adaptively adjust to the actual data content received, without needing to predefine the data structure for all possible anomalous feature information. Therefore, it ensures that even in the face of unknown or constantly evolving public health events, the system can flexibly store and manage various types of anomalous feature information.

[0070] In a further embodiment of this application, the step of extracting auxiliary information related to the abnormal feature information from the self-describing information package and calibrating the collection time and / or geographical location of the abnormal feature information based on the auxiliary information includes: When the abnormal feature information includes a multimedia file, the creation timestamp and / or geographic coordinates in the metadata of the multimedia file are parsed and extracted, and the creation timestamp and / or geographic coordinates are used as auxiliary information. The auxiliary information is compared with the collection timestamp and / or geographical location encapsulated in the self-describing information package; Based on the comparison results, the deviation between the auxiliary information and the timestamp and / or geographic coordinates encapsulated in the self-describing information package is determined; if the deviation exceeds a preset threshold, calibration is performed using the timestamp and / or geographic coordinates in the auxiliary information.

[0071] Specifically, when the abnormal feature information is a multimedia file such as an image, video, or audio file, these files typically contain metadata. The metadata refers to data describing the multimedia file; for example, the EXIF ​​information of an image file may contain the shooting time, GPS coordinates, etc.; a video file may contain the recording time, geolocation tags, etc. This application obtains the creation timestamp and / or geographic coordinates recorded in the multimedia file by parsing and extracting its metadata. This metadata is usually automatically generated by the acquisition device and has high objectivity and reliability, thus serving as a more credible auxiliary information.

[0072] The creation timestamp and / or geographic coordinates are used as auxiliary information to provide a reference base independent of the time and location information encapsulated in the self-describing information package. This auxiliary information is then compared with the acquisition timestamp and / or geographic location encapsulated in the self-describing information package to assess their consistency. The comparison result is used to determine the deviation between the two. This deviation can be understood as the difference between two timestamps or the distance between two geographic coordinate points.

[0073] In practical applications, the preset threshold can be set according to actual needs and the requirements for data accuracy. For example, for time deviation, it can be set to 5 seconds, 10 seconds, or longer; for geographical location deviation, it can be set to 5 meters, 10 meters, or further. If the deviation exceeds the preset threshold, it indicates that there may be a large error in the timestamp and / or geographical location encapsulated in the self-description information packet. In this case, calibration is performed using the timestamp and / or geographical coordinates in the auxiliary information, that is, the original collection time and / or geographical location is replaced or corrected with more reliable time and location information extracted from multimedia metadata.

[0074] This application's solution provides an independent and generally more reliable source of time and location information by utilizing the metadata inherent in multimedia files. When on-site information acquisition equipment generates self-describing information packets, the timestamps and / or geographic locations encapsulated within them may be affected by various factors, resulting in errors. By introducing the creation timestamps and / or geographic coordinates from the multimedia metadata as auxiliary information and comparing them with the information in the self-describing information packet, potential deviations can be effectively detected. Once a deviation exceeds a preset threshold, it is considered that the information in the self-describing information packet may be inaccurate. At this point, the more objective and tamper-resistant time and location information from the multimedia metadata is used for calibration, thereby improving the accuracy and reliability of the time and location data for abnormal feature information. This mechanism ensures the accuracy of subsequent data correlation and event situation information views, providing a more solid data foundation for emergency command and decision-making.

[0075] Specifically, the preferred steps for associating the calibrated abnormal feature information with relevant epidemiological investigation data and detection results, and providing a unified view of the event situation to assist in making emergency command decisions, include: The stored abnormal feature information is then uniformly correlated with routine epidemiological investigation data and laboratory test results to obtain the correlation results; Based on the aforementioned correlation results, a unified event situation information view is constructed and provided to assist in the formulation of emergency command decisions; wherein, the event situation information view supports information query and integrated display by case identifier, time range, or geographical region.

[0076] The unified association of stored abnormal feature information with routine epidemiological investigation data and laboratory test results refers to integrating calibrated and stored abnormal feature information with routine epidemiological investigation data and laboratory test results from different sources through preset association rules or algorithms. Specifically, routine epidemiological investigation data may include basic patient information, contact history, travel history, symptom onset time, etc., while laboratory test results may cover pathogen detection, antibody detection, and other data. These data are linked together through unified identifiers, such as case identifiers, event IDs, timestamps, or geographic location information, thereby forming a comprehensive and multi-dimensional association result.

[0077] Furthermore, based on the aforementioned correlation results, constructing and providing a unified event situation information view means using the integrated correlation results and data visualization technology to generate an intuitive and easy-to-understand event situation information display interface. This view aims to provide emergency command personnel with a macro-level and detailed overall picture of the event, enabling them to quickly grasp the event's progress and impact. Specifically, the event situation information view supports information querying and integrated display by case identifier, time range, or geographical region. This means that users can track individual situations based on specific case IDs, set time periods to observe the dynamic changes of the event, or define geographical regions to analyze the spatial distribution of the epidemic, thereby achieving flexible information retrieval and multi-dimensional presentation.

[0078] This application's solution breaks down information barriers between different data sources by uniformly linking calibrated anomaly information with traditional epidemiological investigation data and laboratory test results. Specifically, by uniformly linking stored anomaly information with routine epidemiological investigation data and laboratory test results, a comprehensive and multi-dimensional correlation result can be formed. Based on this correlation result, the system can construct and provide a unified view of the event's situation. This view supports multiple query and integrated display methods, such as case identification, time range, or geographical region, enabling emergency command personnel to examine the overall situation of the event from different dimensions, thereby gaining a more comprehensive and accurate understanding of the evolution and impact of public health events.

[0079] Please refer to Figure 2 The specific implementation of this application also discloses a public health emergency command information management system 200, including: Information receiving module 210 is used to receive self-describing information packets. The self-describing information packets are data packets generated by the field information acquisition device when it acquires abnormal feature information that exceeds the preset type, and the abnormal feature information and the feature description information are encapsulated together. The data storage module 220 is used to dynamically adjust the data storage structure according to the feature description information in the self-describing information package in order to store the abnormal feature information; The information calibration module 230 is used to extract auxiliary information related to the abnormal feature information from the self-describing information package, and to calibrate the collection time and / or geographical location of the abnormal feature information based on the auxiliary information; The information association module 240 is used to associate the calibrated abnormal feature information with the associated epidemiological investigation data and detection results, and to provide a unified view of the event situation information to assist in making emergency command decisions.

[0080] To better understand the public health emergency command information management system proposed in this application, the following provides a detailed description of each module involved.

[0081] The information receiving module is used to receive self-describing information packets. These self-describing information packets are data packets generated by the field information acquisition device when it collects abnormal feature information exceeding a preset type, along with corresponding feature description information. It should be noted that the information receiving module can be implemented using hardware circuitry, software programs, firmware, or a combination thereof. For example, the information receiving module can be configured as a network interface card and corresponding driver to monitor and receive network data streams from the field information acquisition device and perform preliminary parsing of the received data packets. Alternatively, the information receiving module can also be a service process deployed on a server, receiving uploaded self-describing information packets through a specific application programming interface (API).

[0082] The data storage module dynamically adjusts the data storage structure based on the feature description information in the self-describing information package to store the abnormal feature information. It should be noted that the data storage module can consist of a database management system and its associated storage engine and data definition language parser. For example, the data storage module can be configured to automatically execute Structured Query Language (SQL) statements to create new data tables or add new fields to existing data tables upon receiving new feature description information. As a preferred implementation, the data storage module can also be a NoSQL-based storage system that inherently supports flexible or dynamic schemas, thus more naturally adapting to different types of abnormal feature information storage needs.

[0083] The information calibration module is used to extract auxiliary information related to the anomalous feature information from the self-describing information package, and to calibrate the collection time and / or geographical location of the anomalous feature information based on the auxiliary information. It should be noted that the information calibration module can consist of a data parser, a metadata extractor, and a calibration logic processor. For example, the information calibration module can be configured as an image processing library or multimedia parsing tool to extract the creation timestamp and Global Positioning System (GPS) coordinates from the Exchangeable Image File Format (EXIF) information of multimedia files. Alternatively, the information calibration module can also include a natural language processing unit to extract time or location information from the text description and compare and calibrate it with the metadata recorded by the system.

[0084] The information association module is used to link the calibrated abnormal feature information with relevant epidemiological investigation data and test results, and to provide a unified view of the event situation to assist in emergency command decisions. It should be noted that the information association module can consist of a data integration engine, a relationship matching algorithm, and a visualization interface generator. For example, the information association module can be configured to establish associations between different databases (such as an abnormal feature information database, an epidemiological investigation database, and a laboratory test result database) using case identifiers, timestamps, and geographic location information. As a preferred implementation, the information association module can also integrate geographic information systems and time series analysis tools to construct an interactive view of the event situation, supporting multi-dimensional data queries and visualization.

[0085] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0086] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A public health emergency command and information management method, characterized in that, Includes the following steps: Receive a self-describing information packet, wherein the self-describing information packet is a data packet formed by the field information acquisition device generating feature description information corresponding to the abnormal feature information when it acquires abnormal feature information that exceeds the preset type, and encapsulating the abnormal feature information and the feature description information. The data storage structure is dynamically adjusted based on the feature description information in the self-describing information package to store the abnormal feature information; Extract auxiliary information related to the abnormal feature information from the self-describing information package, and calibrate the collection time and / or geographical location of the abnormal feature information based on the auxiliary information; The calibrated abnormal feature information is correlated with the associated epidemiological investigation data and detection results, and a unified view of the event situation information is provided to assist in the formulation of emergency command decisions. The step of extracting auxiliary information related to the abnormal feature information from the self-describing information package, and calibrating the collection time and / or geographical location of the abnormal feature information based on the auxiliary information, includes: When the abnormal feature information includes a multimedia file, the creation timestamp and / or geographic coordinates in the metadata of the multimedia file are parsed and extracted, and the creation timestamp and / or geographic coordinates are used as auxiliary information. The auxiliary information is compared with the collection timestamp and / or geographical location encapsulated in the self-describing information package; Based on the comparison results, the deviation between the auxiliary information and the timestamp and / or geographic coordinates encapsulated in the self-describing information package is determined; if the deviation exceeds a preset threshold, calibration is performed using the timestamp and / or geographic coordinates in the auxiliary information. The encapsulation steps of the self-describing information packet include: When abnormal feature information exceeding the preset type is collected on the on-site information collection equipment, one or more standardized descriptive tags are retrieved and recommended based on the type and content of the abnormal feature information. Select recommended standardized description tags or obtain custom description tags from external input, and associate them with the abnormal feature information to generate feature description information corresponding to the abnormal feature information; The abnormal feature information and feature description information are encapsulated into a self-describing information package; When abnormal feature information exceeding a preset type is collected on the on-site information collection device, the step of retrieving and recommending one or more standardized descriptive tags based on the type and content of the abnormal feature information includes: On the on-site information acquisition equipment, when abnormal feature information exceeding the preset type is acquired, the features of the abnormal feature information are extracted. Calculate the semantic similarity between the features of the abnormal feature information and the features of each preset tag in the preset semantic tag library of the on-site information acquisition device; Determine whether there is a value in the semantic similarity that is higher than a preset similarity threshold; If there is a value in the semantic similarity that is higher than the preset similarity threshold, then the preset tags in the preset semantic tag library with similarity higher than the preset similarity threshold will be recommended as standardized description tags for output. If there is no value in the semantic similarity that is higher than the preset similarity threshold, then the tag expansion process is triggered, which includes: Candidate terms related to the features of the abnormal feature information are retrieved from external knowledge sources, processed, and used as candidate extended tags for selection by on-site personnel. The candidate extended tags are recommended as standardized descriptive tags for on-site personnel to select from. The preset similarity threshold is dynamically adjusted according to the stage or level of the current public health event; The step of retrieving candidate terms related to the features of the abnormal feature information from external knowledge sources and processing them as candidate extended tags includes: Obtain scientific literature or report texts related to the characteristics of the abnormal features from a pre-set authoritative medical database or epidemiological knowledge base; Language processing is performed on the scientific literature or report texts to extract core terms describing clinical symptoms, pathogen characteristics, or exposure factors; The core terms are deduplicated and normalized to form the candidate extended tags.

2. The public health emergency command information management method according to claim 1, characterized in that, The steps for standardizing description label recommendation output include: The standardized description tags are sorted according to the semantic similarity between each standardized description tag and the abnormal feature information; The sorted standardized description labels are then recommended and output as a list.

3. The information management method for public health emergency command according to claim 1, characterized in that, The step of dynamically adjusting the data storage structure based on the feature description information in the self-describing information package to store the abnormal feature information includes: Parse the self-describing information packet to obtain its feature description information; Determine whether the feature description information is appearing for the first time; If this is the first occurrence, then in the database management system, a data table structure is dynamically created or expanded for the data type corresponding to the feature description information to store the abnormal feature information.

4. The public health emergency command information management method according to claim 1, characterized in that, The steps of associating the calibrated abnormal feature information with relevant epidemiological investigation data and detection results, and providing a unified view of the event situation to assist in making emergency command decisions, include: The stored abnormal feature information is then uniformly correlated with routine epidemiological investigation data and laboratory test results to obtain the correlation results; Based on the aforementioned correlation results, a unified event situation information view is constructed and provided to assist in making emergency command decisions; The event situation information view supports information querying and integrated display by case identifier, time range, or geographical region.

5. A public health emergency command and information management system, characterized in that, include: The information receiving module is used to receive a self-describing information packet. The self-describing information packet is a data packet formed by the field information acquisition device generating feature description information corresponding to the abnormal feature information when it acquires abnormal feature information that exceeds the preset type, and encapsulating the abnormal feature information and the feature description information. The encapsulation of the self-describing information packet includes: When abnormal feature information exceeding the preset type is collected on the on-site information collection equipment, one or more standardized descriptive tags are retrieved and recommended based on the type and content of the abnormal feature information. Select recommended standardized description tags or obtain custom description tags from external input, and associate them with the abnormal feature information to generate feature description information corresponding to the abnormal feature information; The abnormal feature information and feature description information are encapsulated into a self-describing information package; When abnormal feature information exceeding a preset type is collected on the on-site information acquisition device, one or more standardized descriptive tags are retrieved and recommended based on the type and content of the abnormal feature information, including: On the on-site information acquisition equipment, when abnormal feature information exceeding the preset type is acquired, the features of the abnormal feature information are extracted. Calculate the semantic similarity between the features of the abnormal feature information and the features of each preset tag in the preset semantic tag library of the on-site information acquisition device; Determine whether there is a value in the semantic similarity that is higher than a preset similarity threshold; If there is a value in the semantic similarity that is higher than the preset similarity threshold, then the preset tags in the preset semantic tag library with similarity higher than the preset similarity threshold will be recommended as standardized description tags for output. If there is no value in the semantic similarity that is higher than the preset similarity threshold, then the tag expansion process is triggered, which includes: Candidate terms related to the features of the abnormal feature information are retrieved from external knowledge sources, processed, and used as candidate extended tags for selection by on-site personnel. The candidate extended tags are recommended as standardized descriptive tags for on-site personnel to select from. The preset similarity threshold is dynamically adjusted according to the stage or level of the current public health event; The step of retrieving candidate terms related to the features of the abnormal feature information from external knowledge sources, and then processing them as candidate extended tags, includes: Obtain scientific literature or report texts related to the characteristics of the abnormal features from a pre-set authoritative medical database or epidemiological knowledge base; Language processing is performed on the scientific literature or report texts to extract core terms describing clinical symptoms, pathogen characteristics, or exposure factors; The core terms are deduplicated and standardized to form the candidate extended tags; The data storage module is used to dynamically adjust the data storage structure according to the feature description information in the self-describing information package in order to store the abnormal feature information; The information calibration module is used to extract auxiliary information related to the abnormal feature information from the self-describing information package, and to calibrate the collection time and / or geographical location of the abnormal feature information based on the auxiliary information. The step of extracting auxiliary information related to the abnormal feature information from the self-describing information package, and calibrating the collection time and / or geographical location of the abnormal feature information based on the auxiliary information, includes: When the abnormal feature information includes a multimedia file, the creation timestamp and / or geographic coordinates in the metadata of the multimedia file are parsed and extracted, and the creation timestamp and / or geographic coordinates are used as auxiliary information. The auxiliary information is compared with the collection timestamp and / or geographical location encapsulated in the self-describing information package; Based on the comparison results, the deviation between the auxiliary information and the timestamp and / or geographic coordinates encapsulated in the self-describing information package is determined; if the deviation exceeds a preset threshold, calibration is performed using the timestamp and / or geographic coordinates in the auxiliary information. The information association module is used to associate the calibrated abnormal feature information with related epidemiological investigation data and detection results, and to provide a unified view of event situation information to assist in making emergency command decisions.

Images