Infectious disease self-adaptive monitoring system and method based on multi-source heterogeneous data

Abstract

The invention provides an infectious disease self-adaptive monitoring system and method based on multi-source heterogeneous data, and relates to the technical field of infectious disease prevention and control. The data processing device can be triggered to clean the newly added infectious etiology data to obtain the standard infectious etiology data, so that the data storage device can be further triggered to update the detection database according to the standard infectious etiology data and store the standard infectious etiology data to the query statistics device; therefore, mutual cooperation of the data monitoring device, the data processing device, the data storage device and the query statistics device is realized, and full-link connection of automatic data detection, data processing and data storage of newly added infectious etiology data is completed, so that real-time and secure data synchronization is realized; and meanwhile, the data standardization rate and the processing efficiency are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of infectious disease prevention and control, and in particular, to an infectious disease adaptive monitoring system and method based on multi-source heterogeneous data. BACKGROUND

[0002] Currently, in the process of infectious disease monitoring and early warning, the monitoring data mainly depends on the multi-pathogen total monitoring data in the medical institution report and the epidemiological investigation report. However, since the multi-pathogen total monitoring data is in a passive mode of timing batch synchronization (such as once a day), the monitoring data has a lag, which leads to the inability to support early risk identification and rapid response; and since the multi-pathogen total monitoring data has multi-source heterogeneous characteristics and cannot be directly used for statistics and analysis, it needs to rely on manual standardization processing, which is difficult to meet the efficiency of prevention and control. SUMMARY

[0003] Therefore, the purpose of the present application is to provide an infectious disease adaptive monitoring system and method based on multi-source heterogeneous data, to realize data synchronization and real-time and security, and to improve the data standardization rate and processing efficiency.

[0004] In a first aspect, the present application provides an infectious disease adaptive monitoring system based on multi-source heterogeneous data, comprising a data monitoring device, a data processing device, a data storage device and a query statistics device; The data monitoring device is used to monitor the newly added infectious pathogen data in the data warehouse, and send a data acquisition instruction; The data processing device is used to receive the data acquisition instruction, obtain the token corresponding to the data acquisition instruction, and verify the validity of the token; based on the newly added infectious pathogen data in the data acquisition instruction, the data processing model is used to clean and process the newly added infectious pathogen data to obtain standard infectious pathogen data; based on the standard infectious pathogen data, a data storage instruction is sent; The data storage device is used to receive the data storage instruction, update the detection database according to the standard infectious pathogen data in the data storage instruction, and store the standard infectious pathogen data to the query statistics device.

[0005] Optionally, the data processing device is also used to receive the token, verify the identity of the token based on the two-way authentication, and check the validity of the token to determine the validity of the token; based on the validity of the token, the newly added infectious pathogen data in the data acquisition instruction is obtained.

[0006] Optionally, the data processing apparatus is further configured to extract, by the entity recognition sub-model, an age feature in the newly added infectious etiology data; extract, by the multi-level keyword sub-model, a detection name feature in the newly added infectious etiology data; extract, by the rule sub-model, a detection result feature in the newly added infectious etiology data; and determine, based on the age feature, the detection name feature, and the detection result feature, standardized infectious etiology data of the newly added infectious etiology data by using a standardization sub-model.

[0007] Optionally, the data processing apparatus is further configured to extract, by the entity recognition sub-model, a number and a unit in the newly added infectious etiology data; determine an unstructured age corresponding to the number and the unit based on a mapping relationship between the calibrated number and unit and the age; and determine a structured age feature corresponding to the unstructured age based on a standardized age format.

[0008] Optionally, the data processing apparatus is further configured to extract, by the multi-level keyword sub-model, a detection keyword in the newly added infectious etiology data; and determine a detection name corresponding to the detection keyword based on a determined keyword graph.

[0009] Optionally, the data processing apparatus is further configured to process the newly added infectious etiology data by the rule sub-model to obtain a result key feature; determine a negative semantic identifier corresponding to the result key feature based on a negative word library; determine a fuzzy semantic identifier corresponding to the result key feature based on an uncertainty word library; determine key information of the result key feature based on key information extraction; and determine a detection result feature corresponding to the newly added infectious etiology data based on the negative semantic identifier, the fuzzy semantic identifier, and the key information.

[0010] Optionally, the data processing apparatus is further configured to extract actual department information and hospital information in the newly added infectious etiology data; determine standard department information corresponding to the standardized infectious etiology data based on a mapping relationship between calibrated standard department information and the actual department information; and determine a hospital property corresponding to the standardized infectious etiology data based on a mapping relationship between a calibrated standard hospital property and standard hospital information.

[0011] In a second aspect, the present application provides a self-adaptive monitoring method for infectious diseases based on multi-source heterogeneous data, which is applicable to the data processing apparatus of the self-adaptive monitoring system for infectious diseases based on multi-source heterogeneous data, and the method comprises the following steps: Upon receiving the data acquisition instruction, a token corresponding to the data acquisition instruction is acquired, and the validity of the token is verified; Based on the validity of the token, the newly added infectious etiology data in the data acquisition instruction is acquired; Based on the newly added infectious etiology data in the data acquisition instruction, the data processing model is used to clean the newly added infectious etiology data to obtain standard infectious etiology data. Based on the standard infectious etiology data, a data storage instruction is sent.

[0012] In a third aspect, the present application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to realize the adaptive monitoring method of infectious diseases based on multi-source heterogeneous data as described in the foregoing embodiments.

[0013] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are executed by a processor to realize the adaptive monitoring method of infectious diseases based on multi-source heterogeneous data as described in the foregoing embodiments.

[0014] The adaptive monitoring system and method of infectious diseases based on multi-source heterogeneous data provided by the embodiments of the present application can send a data acquisition instruction after the data monitoring device monitors the newly added infectious etiology data in the data warehouse, which can trigger the data processing device to clean the newly added infectious etiology data to obtain standard infectious etiology data, so as to further trigger the data storage device to update the detection database according to the standard infectious etiology data and store the standard infectious etiology data to the query statistical device, and thus the data monitoring device, the data processing device, the data storage device and the query statistical device are mutually coordinated, the full-link connection of the automatic data detection, data processing and data storage of the newly added infectious etiology data is completed, the data synchronization real-time and security are realized, and the data standardization rate and processing efficiency are improved.

[0015] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0017] Figure 1 Fig. 1 shows a structural schematic diagram of an adaptive monitoring system of infectious diseases based on multi-source heterogeneous data provided by an embodiment of the present application; Figure 2A flow chart of an infectious disease adaptive monitoring method based on multi-source heterogeneous data is shown. Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in connection with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0019] The embodiments of the present application provide an infectious disease adaptive monitoring system based on multi-source heterogeneous data, referring to Figure 1 The infectious disease adaptive monitoring system based on multi-source heterogeneous data provided by the embodiments of the present application includes a data monitoring device 110, a data processing device 120, a data storage device 130 and a query statistics device 140. The data monitoring device 110 is configured to send a data acquisition instruction when new infectious pathogen data is monitored into the data warehouse. The data processing device 120 is configured to receive the data acquisition instruction, acquire a token corresponding to the data acquisition instruction and verify the validity of the token, clean the new infectious pathogen data based on the new infectious pathogen data in the data acquisition instruction by using a data processing model to obtain standardized infectious pathogen data, and send a data storage instruction based on the standardized infectious pathogen data. The data storage device 130 is configured to receive the data storage instruction, update the detection database according to the standardized infectious pathogen data in the data storage instruction, and store the standardized infectious pathogen data to the query statistics device 140.

[0020] In the embodiments of the present application, the data monitoring device 110 can call a lightweight agent module deployed in the intranet environment of the medical institution or regional data warehouse of infectious etiology data to monitor the newly added infectious etiology data in the data warehouse. For example, when the data warehouse generates infectious etiology related data operations (such as medical institutions entering new patient pathogen detection results, updating sampling time and supplementing monitoring project information, etc.), corresponding operation logs or data change events (such as database INSERT, UPDATE, etc. Operation records) are generated; the agent module listens to the logs and / or events in real time, and analyzes the logs and / or events in real time through the trigger analysis technology in the agent module, identifies that the logs and / or events belong to the newly added infectious etiology data based on the preset data type filtering rules; based on the identified newly added infectious etiology data, a data acquisition instruction is generated, and the data acquisition instruction is sent to the data processing device 120; wherein the data acquisition instruction includes but is not limited to data source identification, data addition timestamp, core field identification of data to be acquired and other key information, so as to automatically capture the daily newly added infectious etiology data in the data warehouse, without manual triggering to complete incremental data extraction, ensure the real-time nature (such as second-level or millisecond-level response) of data addition detection, avoid the lag problem caused by traditional timing batch detection and avoid repeated extraction of historical full data, thereby reducing the waste of bandwidth resources, also ensuring that the extracted data is truly valuable new monitoring information, providing efficient input for subsequent cleaning and analysis links.

[0021] In specific implementation, the data processing device 120 is further configured to, when the token is received, verify the identity of the token based on the bidirectional authentication and check the validity of the token to determine the validity of the token; based on the validity of the token, acquire the newly added infectious etiology data in the data acquisition instruction.

[0022] In the embodiments of the present application, after the data processing apparatus 120 receives the data acquisition instruction, the newly added infectious etiology data is acquired through a double-channel model, wherein the double-channel model includes an instruction channel (API Gateway) module and a data channel (Message Queue) module. When acquiring the newly added infectious etiology data, the instruction channel module first calls the API gateway of the central platform through an HTTPS API, applies for a token for this transmission with timeliness (such as 5 minutes), and verifies the identity of the data processing apparatus and the central platform API gateway issuing the token using a two-way TLS (Transport Layer Security) certificate. That is, the API gateway receives the client digital certificate sent by the data processing apparatus through the instruction channel and verifies the legality of the client data certificate, and at the same time, the data processing apparatus receives the server digital certificate sent by the API gateway through the instruction channel and verifies its legality. Then, the validity of the token is checked in multiple dimensions, such as checking the timeliness, authority and / or integrity of the token, so as to ensure the security of data synchronization. Finally, the encrypted newly added infectious etiology data is acquired through the data channel, and the encrypted newly added infectious etiology data is decrypted and stored in a temporary storage area. The data acquisition module acquires the message header containing the above token in the central platform message queue through the data channel to acquire the encrypted newly added infectious etiology data.

[0023] It should be noted that the central platform is the data transmission hub between the data warehouse and the infectious disease adaptive monitoring system. The data warehouse sends the newly added infectious etiology data to the central platform after encryption, and the infectious disease adaptive monitoring system acquires the encrypted newly added infectious etiology data in the central platform through the double-channel model.

[0024] In specific implementation, the data processing apparatus 120 is further configured to extract an age feature in the newly added infectious etiology data through an entity recognition sub-model; extract a detection name feature in the newly added infectious etiology data through a multi-level keyword sub-model; extract a detection result feature in the newly added infectious etiology data through a rule sub-model; and determine standardized infectious etiology data of the newly added infectious etiology data based on the age feature, the detection name feature and the detection result feature using a standardization sub-model.

[0025] In this embodiment, the data processing model includes an entity recognition sub-model, a multi-level keyword sub-model, a rule sub-model, and a standardization sub-model. The entity recognition sub-model, the multi-level keyword sub-model, and the rule sub-model are connected to the standardization sub-model. Newly added infectious pathogen data is used as input data for the data processing model, and standardized infectious pathogen data is used as output data. The entity recognition sub-model, the multi-level keyword sub-model, and the rule sub-model in the data processing model extract features from the newly added infectious pathogen data and input the extracted features into the standardization sub-model. The standardization sub-model obtains standardized infectious pathogen data based on each feature, thereby improving the accuracy and standardization of the data.

[0026] In specific implementation, the data processing device 120 is also used to extract numbers and units from newly added infectious pathogen data through entity recognition sub-model; determine the unstructured age corresponding to the data and units based on the calibrated mapping relationship between numbers and units and age; and determine the structured age features corresponding to the unstructured age based on the standardized age format.

[0027] In this embodiment, the entity recognition sub-model can extract numbers and units from newly added infectious pathogen data in the following ways: extracting numbers (2, 1, or 3) and units (month, age, and week) from newly added infectious pathogen data based on standard formats (\d+age?, Y, M, etc.) matching with regular rules; and extracting numbers and units from complex expressions (such as "about 1.5 years old") in newly added infectious pathogen data through a natural language processing (NLP) model. To determine the unstructured age corresponding to data and units, keyword mapping and calculation rules can be used to identify the unstructured age (i.e., age without a standardized format) in newly added infectious pathogen data. For example, for newborns, the mapping is 0 years old; for numbers and units (i.e., months), the numbers and units are identified, and based on the units, the conversion units corresponding to the data and units are determined to determine the age. For example, for 2 months, the number 2 divided by the unit month 12 equals 0.17 years old. Furthermore, when determining unstructured age through keyword mapping and calculation rules, the original values ​​related to data and units are recorded for subsequent traceability. Based on standardized age formats, the structured age features corresponding to unstructured ages can be determined in the following ways: For unstructured age data with ambiguous formats (such as whether "10 / 05 / 2000" is MM / DD or DD / MM), the default rules of the business scenario should be followed first, that is, "month last" should be "DD / MM / YYYY". Secondly, a validity check should be added (such as "13 / 05 / 2000" where "13" is not a month, so "DD / MM / YYYY" should be determined). Then, the data should be unified by fixing the number of decimal places (that is, retaining 2 decimal places).

[0028] Further, for invalid date or format recognition failure data is uniformly marked as unknown, based on the set failure threshold triggers manual review, that is, when the unknown rate is greater than the failure threshold, the manual review instruction is triggered; when receiving the special format corrected by manual, the historical failure cases are constructed, and the regular rule set, NLP model and keyword mapping and calculation rule are optimized based on the historical failure cases.

[0029] In the embodiments of the present application, by combining deep learning classification recognition, adaptive calculation logic, dynamic legality verification and scene association judgment, accurate analysis and standard calculation of multi-format age data are realized, and the accuracy of age data is greatly improved through artificial review feedback optimization model.

[0030] In specific implementation, the data processing apparatus is further configured to extract a detection keyword in the newly added infectious etiology data through a multi-level keyword sub-model; and determine a detection name corresponding to the detection keyword based on the determined keyword graph.

[0031] In the embodiments of the present application, the multi-level keyword sub-model can extract the detection keyword (such as influenza) in the newly added infectious etiology data through the NLP word segmentation algorithm, based on the detection keyword and the keyword graph, the fusion edit distance algorithm (i.e. calculating character similarity) and the cosine similarity algorithm (i.e. calculating semantic similarity) are used to calculate the matching degree of the detection keyword and each category keyword in the keyword graph, to determine the detection name of the newly added infectious etiology data, and mark the detection method corresponding to the detection name; further, the keyword graph structure includes 4 pathogen categories, 85 keywords, 1200+ detection items and 7 detection methods (such as respiratory pathogen containing keyword "influenza", containing 135 different detection items such as influenza virus A antigen, influenza virus B antigen, influenza virus A, influenza virus B, influenza virus A antigen determination, influenza virus A IGM, influenza virus A IgM antibody, influenza virus B antibody-IgM, etc.). Further, the detection keyword also includes the inspection department, according to the determination of the inspection department in the newly added infectious etiology data, the detection name of the newly added infectious etiology data is further determined (such as "Vibrio cholerae" matching the intestinal clinic).

[0032] Further, determining the detection name of the newly added infectious etiology data also includes a hierarchical matching relationship based on the constructed hospital-specific rules, global default rules and association verification, constructing a detection name mapping rule library according to the medical institution dimension, and preferentially calling the medical institution specific rules (such as "human rhinovirus RNA" of hospital A corresponding to the keyword "rhinovirus", and the detection method is "culture").

[0033] The application embodiment establishes the hierarchical matching system of "hospital-specific rules-global default rules-association verification" through the above, and uses the fusion algorithm of edit distance and cosine similarity to calculate the matching degree globally, accurately associates the standard keywords and detection methods, and synchronously combines the association field verification of the submission department (i.e. the detection department), so as to improve the matching confidence and the standardization rate of detection information, and realize the standardization of detection information.

[0034] In specific implementation, the data processing apparatus is further configured to process the newly added infectious etiology data through the rule sub-model to obtain a result key feature; determine a negative semantic identifier corresponding to the result key feature based on a negative word library; determine a fuzzy semantic identifier corresponding to the result key feature based on an uncertainty word library; determine key information of the result key feature based on key information extraction; and determine a detection result feature corresponding to the newly added infectious etiology data based on the negative semantic identifier, the fuzzy semantic identifier and the key information.

[0035] In the application embodiment, the newly added infectious etiology data is processed through the rule sub-model to obtain a result key feature. The result key feature can be a plurality of words or a phrase sequence. For example, the newly added infectious etiology data is "pneumonia mycoplasma antibody IgM [MP-IgM] detection result is positive". The result key feature obtained by processing the newly added infectious etiology data through the rule sub-model is ["pneumonia mycoplasma", "antibody", "IgM", "[MP-IgM]", "detection", "result", "is", "positive"]. Further, the negative words, uncertainty and key information in the result key feature are determined, and the detection result is determined in the following manner: based on the negative word library, the negative words or negative patterns in the result key feature are determined through a regular expression, and when the negative words or negative patterns match the negative word library, the result key feature is marked with a negative semantic identifier; based on the uncertainty word library, the uncertainty words or uncertainty patterns in the result key feature are determined through a regular expression, and when the uncertainty words or uncertainty patterns match the negative word library, the result key feature is marked with a fuzzy semantic identifier, and according to the uncertainty type and weight, an uncertainty score corresponding to the result key feature is determined, for example:

[0036] The key information of the result key feature is determined through regular expression extraction (i.e. key information extraction). The key information includes numerical value, unit and target, for example, the numerical value and unit can be extracted from the result key feature using a regular expression to extract patterns such as <500, 1:160, etc., and the corresponding units copies / mL, titer are identified; the detection target is extracted in combination with the detection name keyword atlas described above, and the pathogen and detection method (such as "pneumonia mycoplasma" and "IGM detection") in the result key feature are identified. Further, based on the negative semantic identifier, the ambiguous semantic identifier and the key information, determining the detection result feature corresponding to the newly added infectious etiology data can be achieved by the following way: determining the detection result feature corresponding to the newly added infectious etiology data based on the negative semantic identifier, the ambiguous semantic identifier and the key information priority rules, wherein the priority rules are: the negative semantic identifier is greater than the ambiguous semantic identifier, which is greater than the positive / negative key information. For example: rule 1 (negative priority): if an effective negative word is detected (and its modification range contains the detection target), it is preliminarily determined as "negative"; rule 2 (uncertainty correction): based on rule 1, if an uncertainty word is also detected, the final result is not simply "negative", but "negative (suspected)", with an uncertainty label; rule 3 (positive determination): if no negative word is detected, but positive key words such as "positive" and "+" are detected, it is preliminarily determined as "positive"; rule 4 (uncertainty correction): based on rule 3, if a weak positive word is detected, the final result is "positive (weak positive)"; if a suspicious word is detected, the result is "positive (suspected)"; rule 5 (numerical determination): if a numerical value and a comparison symbol (such as <500) are extracted, it is determined as "negative (below the detection limit)" or a quantitative result is generated according to the pre-defined detection limit standard. In order to solve the multi-target problem, the data processing module associates the negative word / uncertainty word with the nearest detection target. For example, through syntax analysis or simple distance judgment, it is determined whether "not detected" modifies "influenza A" or "influenza B".

[0037] Further, if the newly added infectious etiology data is "EV-71 IgM detection result: suspicious, not detected", the newly added infectious etiology data is processed by the rule sub-model to obtain the result key features ["EV-71", "IgM", "detection", "result", "suspicious", "not", "detected"]; based on the negative word library, the negative semantic identifier corresponding to the result key features is determined (the "not detected" is found, and the polarity is marked as "negative"); based on the uncertainty word library, the ambiguous semantic identifier corresponding to the result key features is determined (the "suspicious" is found, which is classified as "suspicious type", and the weight is 0.5); based on the key information extraction, the key information of the result key features is determined (target extraction: "EV-71" is identified); based on the negative semantic identifier, the ambiguous semantic identifier and the key information, the detection result feature corresponding to the newly added infectious etiology data is determined (the logical judgment process includes applying rule 1: there is a negative word "not detected", which is preliminarily determined as "negative"; applying rule 2: there is an uncertainty word "suspicious" at the same time, which modifies the result; the detection result feature is the core determination-negative; the modifier is suspicious; the confidence is 0.95).

[0038] It should be noted that when there is no negation and / or uncertainty in the result key features, the detection result features corresponding to the newly added infectious etiology data are determined by judging the result key features, wherein the judgment of the result key features includes abnormal flag judgment, detection result judgment, reference value judgment and / or bacterial result judgment; the abnormal flag judgment is 1-normal-negative, 3-abnormal high-positive and 4-abnormal low-negative; the detection result judgment is that the actual detection result value is determined to be within the detection data range by extracting the detection data range corresponding to each interval by regular rules, then the detection result is determined; the reference value judgment is that for the standard reference range (0.00-20.00, <1.00, >20.00, 20.00), the detection result is obtained by comparing the result of the reference value with the reference range; for special reference range (<24.00 negative; 24.00≤suspect<36.00; ≥36.00 positive), the negative reference value is screened out, if the reference value is within the negative range, the result is negative, otherwise it is positive; the bacterial result judgment is that if the bacterial result is not found, the detection index result is negative; if the bacterial result is found, and the bacterial name contains “none”, “not detected”, the bacterial result is negative, and the detection index result is negative; if the bacterial result is found, and the colony count and detection result contain “+”, “positive”, “bacteria”, the bacterial result is positive (the original value is retained), and the detection index result is positive; if the bacterial result is found, and the colony count and detection result contain “not found”, “negative”, “sterile”, the bacterial result is negative, and the detection index result is negative; if the colony count and detection result are both empty, the bacterial result is positive, and the detection index result is positive.

[0039] In the embodiments of the present application, by regular extraction, machine learning classification and clinical significance, various reference ranges are intelligently analyzed and standard detection results are determined, the problem of non-standard reference range determination is solved, reliable basis is provided for infectious disease screening, and important guarantee for subsequent monitoring and early warning is provided.

[0040] In specific implementation, the data processing apparatus is further configured to extract the institution attribute information in the newly added infectious etiology data; based on the mapping relationship between the standard institution information and the institution attribute information, the standard institution information corresponding to the standardized infectious etiology data is determined.

[0041] In the embodiments of the present application, by obtaining the department information (i.e. institution attribute information) defined by different hospitals, the mapping relationship between the standard institution information and the institution attribute information is established, based on the mapping relationship between the standard institution information and the institution attribute information, the institution attribute information in the newly added infectious etiology data is converted into standard institution information, and key attributes such as hospital property (such as whether it is a pilot hospital) are marked, so as to realize institution information planning.

[0042] In specific embodiments, the data processing device sends the standardized infectious etiology data to a monitoring database and a query statistics device, respectively. The query statistics device is provided with a three-level intelligent query architecture of "local cache + distributed cache + ES + real-time computing engine". The three-level intelligent query architecture can process query requirements in layers according to request frequency, realize intelligent monitoring and early warning in combination with a real-time computing engine, greatly improve data query efficiency and infectious disease risk response speed, and ensure problem positioning and solution through a whole-process monitorable traceability system.

[0043] Further, the local cache in the three-level intelligent query architecture of "local cache + distributed cache + ES + real-time computing engine" is a memory-level cache (such as Redis LocalCache, Caffeine, etc.) deployed locally on an application server. The standardized infectious etiology data is directly stored in the memory of the application process and can be read without network request. The distributed cache is a cache system (such as Redis Cluster, Memcached) deployed in a cluster composed of multiple servers. The standardized infectious etiology data is stored in the cluster nodes and can be shared across application servers, supporting horizontal expansion to cope with massive data. The ES (Elasticsearch) is a distributed full-text search engine based on Lucene, which is good at real-time retrieval and aggregation analysis of massive unstructured / semi-structured data, supports multi-dimensional condition filtering and complex statistics, and the real-time computing engine is a framework (such as Flink, Spark Streaming) supporting real-time processing and incremental calculation of stream data, which can perform low-latency calculation on newly added data (such as real-time synchronized infectious etiology data) and output dynamic results.

[0044] The embodiment of the present application provides an infectious disease adaptive monitoring method based on multi-source heterogeneous data. Referring to FIG. 1, the embodiment of the present application provides an infectious disease adaptive monitoring method based on multi-source heterogeneous data, which is applicable to a data processing module in an infectious disease adaptive monitoring system based on multi-source heterogeneous data. The general process of the method is as follows: Figure 2 Step 210, when receiving the data acquisition instruction, acquiring a token corresponding to the data acquisition instruction and verifying the validity of the token; Step 220, based on the validity of the token, acquiring the newly added infectious etiology data in the data acquisition instruction; Step 230, based on the newly added infectious etiology data in the data acquisition instruction, using a data processing model to clean and process the newly added infectious etiology data to obtain standardized infectious etiology data; Step 240, based on the standardized infectious etiology data, sending a data storage instruction.

[0045] ​In an optional embodiment, the method further comprises: upon receiving the token, verifying the identity of the token and checking the validity of the token based on the mutual authentication, determining the validity of the token; based on the validity of the token, obtaining the newly added infectious etiology data in the data acquisition instruction; In an optional embodiment, the method further comprises: extracting the age feature in the newly added infectious etiology data through the entity recognition sub-model; extracting the detection name feature in the newly added infectious etiology data through the multi-level keyword sub-model; extracting the detection result feature in the newly added infectious etiology data through the rule sub-model; based on the age feature, the detection name feature and the detection result feature, determining the standardized infectious etiology data of the newly added infectious etiology data by using the standardization sub-model; In an optional embodiment, the method further comprises: extracting the number and unit in the newly added infectious etiology data through the entity recognition sub-model; based on the mapping relationship between the calibrated number and unit and the age, determining the unstructured age corresponding to the data and the unit; based on the standardized age format, determining the structured age feature corresponding to the unstructured age.

[0046] In an optional embodiment, the method further comprises: extracting the detection keyword in the newly added infectious etiology data through the multi-level keyword sub-model; based on the determined keyword graph, determining the detection name corresponding to the detection keyword.

[0047] In an optional embodiment, the method further comprises: processing the newly added infectious etiology data through the rule sub-model to obtain the result key feature; based on the negation word library, determining the negation semantic identifier corresponding to the result key feature; based on the uncertainty word library, determining the fuzzy semantic identifier corresponding to the result key feature; based on the key information extraction, determining the key information of the result key feature; based on the negation semantic identifier, the fuzzy semantic identifier and the key information, determining the detection result feature corresponding to the newly added infectious etiology data.

[0048] In an optional embodiment, the method further comprises: extracting the actual department information and the hospital information in the newly added infectious etiology data; based on the mapping relationship between the calibrated standard department information and the actual department information, determining the standard department information corresponding to the standardized infectious etiology data; based on the mapping relationship between the calibrated standard hospital property and the standard hospital information, determining the hospital property corresponding to the standardized infectious etiology data.

[0049] It should be noted that the principle of solving the technical problem of the method for adaptively monitoring infectious diseases based on multi-source heterogeneous data provided in the embodiments of the present application is similar to the method for adaptively monitoring infectious diseases based on multi-source heterogeneous data provided in the embodiments of the present application. Therefore, the implementation of the method for adaptively monitoring infectious diseases based on multi-source heterogeneous data provided in the embodiments of the present application can refer to the implementation of the method for adaptively monitoring infectious diseases based on multi-source heterogeneous data provided in the embodiments of the present application, and the repeated parts will not be described here.

[0050] After introducing the method for adaptively monitoring infectious diseases based on multi-source heterogeneous data provided in the embodiments of the present application, next, the electronic device provided in the embodiments of the present application is briefly introduced.

[0051] Referring to Figure 3 The electronic device 500 provided in the embodiments of the present application at least includes a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501, and the processor 501 implements the method for adaptively monitoring infectious diseases based on multi-source heterogeneous data provided in the embodiments of the present application when executing the computer program.

[0052] The electronic device 500 provided in the embodiments of the present application can also include a bus 503 connected to different components (including the processor 501 and the memory 502). Among them, the bus 503 represents one or more of several types of bus structures, including a memory bus, a peripheral bus, a local bus, etc.

[0053] The memory 502 can include a readable storage medium in the form of a volatile memory, such as a random access memory (RAM) 5021 and / or a cache memory 5022, and can further include a read-only memory (ROM) 5023. The memory 502 can also include a program tool 5025 having a set of (at least one) program modules 5024, including but not limited to an operating subsystem, one or more application programs, other program modules, and program data, each of these examples or some combination thereof can include the implementation of a network environment.

[0054] The processor 501 can be one processing element or a collective term for multiple processing elements. For example, the processor 501 can be a central processing unit (CPU), or one or more integrated circuits configured to implement the method of adaptive monitoring of infectious diseases based on multi-source heterogeneous data provided by the embodiments of the present application. Specifically, the processor 501 can be a general-purpose processor, including but not limited to a CPU, an application specific integrated circuit (ASIC), a ready-to-program gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0055] The electronic device 500 can communicate with one or more external devices 504 (such as a keyboard, a remote controller, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 500 (such as a mobile phone, a computer, etc.), and / or communicate with a device that enables the electronic device 500 to communicate with one or more other electronic devices 500 (such as a router, a modem, etc.). Such communication can be carried out through an input / output (I / O) interface 505. In addition, the electronic device 500 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) through a network adapter 506. As shown, the network adapter 506 communicates with other modules of the electronic device 500 through the bus 503. It should be understood that although Figure 3 not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 500, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, redundant arrays of independent disks (RAID) subsystems, tape drives, and data backup storage subsystems, etc. Figure 3 It should be understood that although

[0056] It should be noted that Figure 3 The electronic device 500 shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0057] The computer readable storage medium provided by the embodiments of the present application is described below. The computer readable storage medium provided by the embodiments of the present application stores computer instructions, and the computer instructions are executed by a processor to implement the adaptive monitoring method for infectious diseases based on multi-source heterogeneous data provided by the embodiments of the present application. Specifically, the computer instructions can be built-in or installed in the processor, so that the processor can implement the adaptive monitoring method for infectious diseases based on multi-source heterogeneous data provided by the embodiments of the present application by executing the built-in or installed computer instructions.

[0058] In addition, the adaptive monitoring method for infectious diseases based on multi-source heterogeneous data provided by the embodiments of the present application can also be implemented as a computer program product, which includes program codes. When the program codes are run on a processor, the adaptive monitoring method for infectious diseases based on multi-source heterogeneous data provided by the embodiments of the present application is implemented.

[0059] The computer program product provided by the embodiments of the present application can adopt one or more computer readable storage media. Specifically, the computer readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any appropriate combination of the above. More specifically, the computer readable storage medium includes, but is not limited to, an electrical connection with one or more wires, a portable disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination of the above.

[0060] The computer program product provided by the embodiments of the present application can adopt a CD-ROM and include program codes, and can also run on an electronic device such as a computer. However, the computer program product provided by the embodiments of the present application is not limited to this. In the embodiments of the present application, the computer readable storage medium can be any tangible medium containing or storing program codes, which can be used or combined with an instruction execution system, device or apparatus.

[0061] It should be noted that although several units or sub-units of the apparatus are mentioned in the above detailed description, such division is only exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into units embodied by multiple units.

[0062] Furthermore, although the operations of the method(s) herein can be described in a particular, sequential order, this order is not meant to be a limitation and one or more of the operations described can be performed in parallel, or in a different order, including simultaneous execution of one or more operations, unless otherwise specified herein. In addition, the description sometimes uses terms like "operate" or "execute" to describe the operation of certain steps, which should not be construed to refer to a specific computer or memory location. Rather, such terms are used to generally describe the operation of the steps.

[0063] While the preferred embodiments of the application have been described above, it will be recognized and understood that various modifications and changes can be made to the embodiments of the application without departing from the spirit and scope of the application. It is intended that the appended claims be construed to include all such modifications and changes insofar as they fall within the scope of the present application.

[0064] It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application cover the modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. An adaptive monitoring system for infectious diseases based on multi-source heterogeneous data, characterized in that, This includes data monitoring devices, data processing devices, data storage devices, and query and statistics devices; The data monitoring device is used to send a data acquisition command when new infectious pathogen data is detected in the data warehouse; The data processing device is configured to, upon receiving the data acquisition instruction, acquire the token corresponding to the data acquisition instruction and verify the validity of the token; Based on the newly added infectious pathogen data in the data acquisition instruction, the newly added infectious pathogen data is cleaned using a data processing model to obtain standard infectious pathogen data. Based on the aforementioned standard infectious pathogen data, a data storage instruction is sent; The data storage device is used to, upon receiving the data storage instruction, update the detection database and store the standard infectious pathogen data in the query and statistics device according to the standard infectious pathogen data in the data storage instruction.

2. The adaptive monitoring system for infectious diseases based on multi-source heterogeneous data according to claim 1, characterized in that, The data processing device is further configured to, upon receiving the token, verify the identity of the token based on two-way authentication and check the validity of the token to determine the validity of the token; Based on the validity of the token, the newly added infectious pathogen data in the data acquisition instruction is obtained.

3. The adaptive monitoring system for infectious diseases based on multi-source heterogeneous data according to claim 1, characterized in that, The data processing device is further configured to extract age features from the newly added infectious pathogen data through an entity recognition sub-model; and to extract detection name features from the newly added infectious pathogen data through a multi-level keyword sub-model. The detection result features in the newly added infectious pathogen data are extracted using a rule-based sub-model. Based on the age characteristics, the detection name characteristics, and the detection result characteristics, a standardized sub-model is used to determine the standardized infectious pathogen data of the newly added infectious pathogen data.

4. The adaptive monitoring system for infectious diseases based on multi-source heterogeneous data according to claim 3, characterized in that, The data processing device is further configured to extract numbers and units from the newly added infectious pathogen data through the entity recognition sub-model; and determine the unstructured age corresponding to the data and the unit based on the calibrated mapping relationship between the numbers and units and age. Based on the standardized age format, the structured age features corresponding to the unstructured age are determined.

5. The adaptive monitoring system for infectious diseases based on multi-source heterogeneous data according to claim 3, characterized in that, The data processing device is further configured to extract detection keywords from the newly added infectious pathogen data through the multi-level keyword sub-model; and determine the detection name corresponding to the detection keywords based on the determined keyword map.

6. The adaptive monitoring system for infectious diseases based on multi-source heterogeneous data according to claim 3, characterized in that, The data processing device is further configured to process the newly added infectious pathogen data through the rule sub-model to obtain key features of the results; and to determine the negative semantic identifier corresponding to the key features of the results based on the negative word library. Based on an uncertainty lexicon, the fuzzy semantic identifiers corresponding to the key features of the results are determined; based on key information extraction, the key information of the key features of the results is determined. Based on the negative semantic identifier, the fuzzy semantic identifier, and the key information, the detection result features corresponding to the newly added infectious pathogen data are determined.

7. The adaptive monitoring system for infectious diseases based on multi-source heterogeneous data according to claim 3, characterized in that, The data processing device is further configured to extract actual department information and hospital information from the newly added infectious pathogen data; determine the standard department information corresponding to the standardized infectious pathogen data based on the mapping relationship between the calibrated standard department information and the actual department information; and determine the hospital nature corresponding to the standardized infectious pathogen data based on the mapping relationship between the calibrated standard hospital nature and the standard hospital information.

8. An adaptive monitoring method for infectious diseases based on multi-source heterogeneous data, characterized in that, The data processing apparatus applicable to the adaptive surveillance system for infectious diseases based on multi-source heterogeneous data as described in any one of claims 1 to 7, the method comprising: Upon receiving the data acquisition instruction, obtain the token corresponding to the data acquisition instruction and verify the validity of the token; Based on the validity of the token, the newly added infectious pathogen data in the data acquisition instruction is obtained; Based on the newly added infectious pathogen data in the data acquisition instruction, the newly added infectious pathogen data is cleaned using a data processing model to obtain standard infectious pathogen data. Based on the aforementioned standard infectious pathogen data, a data storage instruction is sent.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the adaptive monitoring method for infectious diseases based on multi-source heterogeneous data as described in claim 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the adaptive monitoring method for infectious diseases based on multi-source heterogeneous data as described in claim 8.

Images