Food-borne disease event epidemiological investigation and disposal management system and method

Abstract

The invention provides a food-borne disease event epidemiology investigation and disposal management system and method, and belongs to the technical field of epidemiology investigation and disposal, and the food-borne disease event epidemiology investigation and disposal management system comprises a cloud server and a plurality of field investigation personnel nodes. Wherein the cloud server comprises a case analysis module, a similar case classification module, a communication scheduling module and an investigation conclusion generation module, and through the function modules, the cloud server can receive multiple pieces of first disease information sent by the site investigation personnel node; after analysis and processing, a plurality of pieces of first disease information and a plurality of pieces of first pathogenesis information can be obtained, and a plurality of first investigation conclusion forms are generated and issued to corresponding field investigation personnel nodes. Through the technical scheme of the invention, the investigation progress of the food-borne disease event is more convenient and faster, and the investigation conclusion is more accurate.

Description

Technical Field

[0001] The present invention belongs to the technical field of epidemiological investigation and processing, and in particular relates to a management system and method for epidemiological investigation and processing of foodborne disease events. Background Art

[0002] Foodborne disease incidents occur from time to time, seriously endangering public health. The causes of the incidents should be investigated in a timely manner and the results of the investigation should be announced to the public. In order to prevent similar accidents from happening again, it is required to record the disease incidents that have occurred and make full preparations for future sudden disease incidents. The existing technology mainly relies on the emergency personnel's cognition of public health emergencies and their familiarity with emergency preparedness. The above investigation methods have the following problems: investigators need to rely on memory or flip through the questionnaire to conduct the investigation, the generation of the investigation conclusion is too subjective, and there is a lack of scientific analysis process. Summary of the invention

[0003] The purpose of the present invention is to provide a foodborne disease incident epidemiological investigation and disposal management system and method to solve the technical problem that the prior art cannot generate foodborne disease incident epidemiological investigation conclusions scientifically and efficiently.

[0004] The present application proposes a foodborne disease incident epidemiological investigation and disposal management system, including a cloud server and multiple field investigator nodes, characterized in that the cloud server includes: A case analysis module analyzes the multiple first case information uploaded by each of the on-site investigator nodes one by one, classifies and integrates the extracted first symptom information and first cause of disease information, and updates the case database in real time; A similar case classification module is used to classify case information within a specific geographical area according to the geographical location information of the plurality of first case information, so as to extract a first symptom label and a first cause label for characterizing the main symptom of the foodborne disease incident; A communication scheduling module communicates with each of the on-site investigator nodes to obtain the first symptom information in real time; The investigation conclusion generating module generates an epidemiological investigation conclusion of a foodborne disease event according to the first symptom label and the first cause label.

[0005] Preferably, the working steps of the case analysis module include: S11: receiving a plurality of first case information sent by the on-site investigator node; S12: extracting first text information and first multimedia information from each of the first case information; S13: for each of the first case information, inputting the first multimedia information into a first case analysis model to output first risk information; S14: Inputting the first text information and the first risk information into a second case analysis model to output first symptom information and first cause of disease information.

[0006] Preferably, the working steps of the case analysis module also include: S15: Update the first case information database using the first text information, the first risk information, the first symptom information and the first cause of disease information.

[0007] Preferably, the working steps of the similar case classification module mainly include: S21: Acquire first time information and first location information of a plurality of first case information; S22: generating a plurality of first time-space two-dimensional vectors for a plurality of first case information according to the first time information and the first position information; S23: clustering the plurality of the first spatiotemporal two-dimensional vectors to obtain a plurality of first case sets; S24: Acquire multiple pieces of second case information contained in each of the first case sets, and generate a first case description vector for each piece of the second case information; S25: clustering the plurality of first case description vectors to obtain a plurality of second case sets; S26: For each of the second case sets, generate a first symptom label and a first cause label.

[0008] Preferably, the main working steps of the communication scheduling module are as follows: S31: The plurality of on-site investigator nodes upload the collected foodborne disease event information to the cloud server; S32: The cloud server analyzes the foodborne disease event information and updates the first case information database.

[0009] Preferably, the main working steps of the survey conclusion generation module are as follows: S41: generating a plurality of first investigation conclusion forms according to a plurality of the first symptom labels and a plurality of the first cause of disease labels; S42: Distribute the plurality of first investigation conclusion forms to corresponding on-site investigator nodes through the communication scheduling module.

[0010] The present application also proposes a foodborne disease incident epidemiological investigation and disposal management method, which is based on the above-mentioned foodborne disease incident epidemiological investigation and disposal management system for execution, and includes the following steps: S51: receiving a plurality of first case information sent by the on-site investigator node; S52: generating corresponding first symptom information and first cause information according to the first case information; S53: clustering the plurality of first symptom information and the plurality of first cause of disease information to generate a plurality of first symptom labels and a plurality of first cause of disease labels; S54: generating a plurality of first investigation conclusion forms according to the plurality of the first symptom labels and the plurality of the first cause labels; S55: Distribute the plurality of first investigation conclusion forms to corresponding on-site investigator nodes.

[0011] The foodborne disease incident epidemiological investigation and disposal management system and method proposed in this application belong to the field of epidemiological investigation and disposal technology. The foodborne disease incident epidemiological investigation and disposal management system includes a cloud server and multiple on-site investigator nodes, wherein the cloud server includes a case analysis module, a similar case classification module, a communication scheduling module, and an investigation conclusion generation module. Through the above functional modules, the cloud server can receive multiple first symptom information sent by the on-site investigator node, and after analysis and processing, multiple first symptom information and multiple first cause of disease information can be obtained, and then multiple first investigation conclusion forms are generated and issued to the corresponding on-site investigator nodes. The technical solution of this application can make the investigation progress of foodborne disease incidents more convenient and faster, and the investigation conclusions are more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0013] Figure 1 It is a structural diagram of the foodborne disease incident epidemiological investigation and disposal management system of the present invention.

[0014] Figure 2 It is a flow chart of the epidemiological investigation, disposal and management method of foodborne disease events of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0017] The foodborne disease incident epidemiological investigation and disposal management system and method of the present invention are described in detail below.

[0018] This embodiment proposes a foodborne disease incident epidemiological investigation and disposal management system, the system structure is as follows: Figure 1 As shown, it specifically includes a cloud server and multiple field investigator nodes. The functions of each system module are as follows: The cloud server is mainly used to provide computing services for the foodborne disease incident epidemiological investigation and disposal management system. The cloud server mainly includes a case analysis module, a similar case classification module, a communication scheduling module and an investigation conclusion generation module.

[0019] Among them, the case analysis module is mainly used to analyze the case information uploaded by each of the on-site investigator nodes one by one, extract symptoms and causes from all case information and classify and integrate them, and use the newly acquired case information to timely update the case database; the similar case classification module is mainly used to classify case information within a specific geographical area according to geographic location information, so as to analyze and summarize the main causes; the communication scheduling module is mainly used to communicate with each of the on-site investigator nodes to obtain the latest symptom information in a timely manner; the investigation conclusion generation module is mainly used to generate epidemiological investigation conclusions of foodborne disease events based on the information of the case analysis module and the similar case classification module.

[0020] From the above analysis, it can be seen that the main analysis and calculation operations of this application are all performed by the cloud server, so the following mainly introduces the working steps of the functional modules included in the cloud server: The working steps of the case analysis module include: S11: receiving a plurality of first case information sent by the on-site investigator node.

[0021] The field investigator node refers to a smart mobile terminal used by field investigators responsible for investigating foodborne disease incidents. During the investigation, the field investigators can send information in the form of text, video, audio, etc. obtained to the case analysis module of the cloud server through the field investigator node, so that the case analysis module can process the information data.

[0022] S12: Extracting first text information and first multimedia information from each of the first case information.

[0023] Each of the first case information includes textual description information such as the gender, age, main symptoms, etc. of the person under investigation, and includes multimedia information related to describing the symptoms of the person under investigation, the dining environment, and the meal preparation environment.

[0024] S13: For each of the first case information, input the first multimedia information into a first case analysis model to output first risk information.

[0025] The first case analysis model is used to analyze the first multimedia information to extract risk information that may cause foodborne diseases.

[0026] The first case analysis model is obtained by deep convolutional neural network training, and the training process is as follows: First, first foodborne disease sample data is obtained. The case samples are obtained from historical foodborne disease cases stored in the first case information database, including multimedia information corresponding to each of the historical foodborne disease cases, and the risk information of the foodborne disease that is finally confirmed. For example, if the food preparation environment is poor in the multimedia information, bacteria can be used as risk information that may cause foodborne diseases.

[0027] Secondly, the first foodborne disease sample data is used to train a convolutional neural network model to obtain the first case analysis model. During the training process, the multimedia information in the sample data is used as input data, and the corresponding risk information is used as output data to complete the training process.

[0028] S14: Inputting the first text information and the first risk information into a second case analysis model to output first symptom information and first cause of disease information.

[0029] The first text information may include first basic information and first test information. The first basic information includes text description information such as gender, age, and main symptoms of the first case information, and the first test information refers to text description information obtained after meal sampling and testing based on the dining history in the first case information.

[0030] The second case analysis model is obtained based on deep convolutional neural network training, and the training process is as follows: First, obtain the second foodborne disease sample data. Each piece of the second foodborne disease sample data is obtained from the first case information database, and includes risk information extracted from the food preparation environment, basic information and detection information corresponding to each piece of the first case information, and also includes symptom information and cause information corresponding to each piece of the second foodborne disease sample data.

[0031] Secondly, the second case analysis model is trained using the second foodborne disease sample data. During the training process, the text information consisting of basic information and detection information in the sample data, and the risk information extracted from the food preparation environment are used as input data, and the symptom information and cause information corresponding to each piece of the second foodborne disease sample data are used as output data to train a deep convolutional neural network model to obtain the second case analysis model.

[0032] S15: Update the first case information database using the first text information, the first risk information, the first symptom information and the first cause of disease information.

[0033] After completing the case information extraction and analysis operations, the analysis results need to be uploaded or updated to the first case information database to make subsequent case information analysis operations more accurate.

[0034] Among them, if the first symptom information and the first cause information appear for the first time, the case information can be uploaded to the first case information database. If part or all of the first symptom information and the first cause information already exist in the first case information database, the designated database items in the first case information database can be updated according to the first text information, the first risk information, the first symptom information and the first cause information in the case information.

[0035] The working steps of the similar case classification module mainly include: S21: Obtain the first time information and the first location information of the plurality of the first case information.

[0036] The similar case classification model is mainly used to classify cases with high similarity in time and space, so as to discover group foodborne disease events.

[0037] S22: Generate multiple first time-space two-dimensional vectors for multiple first case information.

[0038] In this step, a first time-space two-dimensional vector is generated according to the first time information and the first location information of each first case information. The first time-space two-dimensional vector is used to represent the time and location of the occurrence of the first case information.

[0039] S23: Clustering the plurality of the first time-space two-dimensional vectors to obtain a plurality of first case sets.

[0040] In this step, the K-MEANS clustering algorithm is used to cluster the multiple first spatiotemporal two-dimensional vectors, so that the multiple first spatiotemporal two-dimensional vectors can be divided into multiple first case sets. Among them, the multiple first spatiotemporal two-dimensional vectors in each first case set have a high similarity, that is, the multiple first case information in each first case set has a high probability of being caused by the same cause.

[0041] S24: Acquire multiple pieces of second case information contained in each of the first case sets, and generate a first case description vector for each piece of the second case information.

[0042] The first case description vector is a four-dimensional vector, which is composed of first text information, first risk information, first symptom information and first cause information corresponding to a first case information. The first case description vector can be used to characterize the details of the corresponding first case information.

[0043] S25: Clustering the plurality of first case description vectors to obtain a plurality of second case sets.

[0044] In this step, the K-MEANS algorithm is used to cluster the plurality of second case information corresponding to the plurality of first case description vectors, thereby obtaining a plurality of second case sets, wherein each of the second case sets contains a plurality of case information with a high degree of similarity in etiology.

[0045] S26: For each of the second case sets, generate a first symptom label and a first cause label.

[0046] Since each case in the second case set is caused by a similar cause and the symptoms are also relatively similar, the causes and symptoms in the second case set can be merged and deduplicated to obtain the first symptom label and the first cause label for characterizing the second case set.

[0047] The main working steps of the communication scheduling module are as follows: S31: The plurality of on-site investigator nodes upload the collected foodborne disease event information to the cloud server.

[0048] In this step, the on-site investigator node collects basic information, causes and symptoms of the individual patients according to the incidence of foodborne diseases, collects multimedia information of the on-site outbreak, generates a foodborne disease incident reporting work order, and sends it to the cloud server.

[0049] S32: The cloud server analyzes the foodborne disease event information and updates the first case information database.

[0050] The cloud server updates the causes and symptoms of foodborne disease events in the first case information database based on the foodborne disease event information obtained in real time to facilitate knowledge query by the epidemiological survey administrator.

[0051] Preferably, the communication scheduling module is also used for: When the epidemiological investigation administrator performs on-site investigation work, if relevant knowledge query is required, he can log in to the first case information database located in the cloud server through the communication scheduling module to query.

[0052] The main working steps of the survey conclusion generation module are as follows: S41: Generate a plurality of first investigation conclusion forms according to a plurality of the first symptom labels and a plurality of the first cause of disease labels.

[0053] In this step, according to the plurality of second case sets generated by the similar case classification module, the first symptom label and the first cause label corresponding to each second case set are respectively obtained, and then a plurality of first investigation conclusion forms corresponding to the plurality of second case sets are generated.

[0054] S42: Distribute the plurality of first investigation conclusion forms to corresponding on-site investigator nodes through the communication scheduling module.

[0055] In this step, after distributing a plurality of the first investigation conclusion forms to the corresponding field investigator nodes, a reference can be provided to the field investigator nodes, thereby obtaining a more accurate investigation conclusion of the foodborne disease incident.

[0056] This application also proposes a foodborne disease incident epidemiological investigation and disposal management method, which is implemented based on the above-mentioned foodborne disease incident epidemiological investigation and disposal management system, such as Figure 2 As shown, the specific execution process is as follows: S51: Receive multiple first case information sent by the field investigator node.

[0057] S52: Generate corresponding multiple first symptom information and multiple first cause of disease information according to the multiple first case information.

[0058] S53: Clustering is performed according to the plurality of first symptom information and the plurality of first cause of disease information to generate a plurality of first symptom labels and a plurality of first cause of disease labels.

[0059] S54: Generate a plurality of first investigation conclusion forms according to the plurality of the first symptom labels and the plurality of the first cause of disease labels.

[0060] S55: Distribute the plurality of first investigation conclusion forms to corresponding on-site investigator nodes.

[0061] The foodborne disease incident epidemiological investigation and disposal management system and method proposed in this application belong to the field of epidemiological investigation and disposal technology. The foodborne disease incident epidemiological investigation and disposal management system includes a cloud server, a field investigator node and multiple field investigator nodes, wherein the cloud server includes a case analysis module, a similar case classification module, a communication scheduling module and an investigation conclusion generation module. Through the above functional modules, the cloud server can receive multiple first symptom information sent by the field investigator node, and after analysis and processing, multiple first symptom information and multiple first cause of disease information can be obtained, and then multiple first investigation conclusion forms are generated and issued to the corresponding field investigator nodes. The technical solution of this application can make the investigation progress of foodborne disease incidents more convenient and faster, and the investigation conclusions are more accurate.

[0062] The above description is only a preferred embodiment of the present invention, so all equivalent changes or modifications made according to the structure, characteristics and principles described in the scope of the patent application of the present invention are included in the scope of the patent application of the present invention.

Claims

1. Foodborne disease incident epidemiological investigation and disposal management system, including a cloud server and multiple field investigator nodes, characterized in that: The cloud server comprises: A case analysis module analyzes the multiple first case information uploaded by each of the on-site investigator nodes one by one, classifies and integrates the extracted first symptom information and first cause of disease information, and updates the case database in real time; A similar case classification module is used to classify case information within a specific geographical area according to the geographical location information of the plurality of first case information, so as to extract a first symptom label and a first cause label for characterizing the main symptom of the foodborne disease incident; A communication scheduling module communicates with each of the on-site investigator nodes to obtain the first symptom information in real time; The investigation conclusion generating module generates an epidemiological investigation conclusion of a foodborne disease event according to the first symptom label and the first cause label.

2. The foodborne disease incident epidemiological investigation and disposal management system according to claim 1, characterized in that: The working steps of the case analysis module include: S11: receiving a plurality of first case information sent by the on-site investigator node; S12: extracting first text information and first multimedia information from each of the first case information; S13: for each of the first case information, inputting the first multimedia information into a first case analysis model to output first risk information; S14: Inputting the first text information and the first risk information into a second case analysis model to output first symptom information and first cause of disease information.

3. The foodborne disease incident epidemiological investigation and disposal management system according to claim 2, characterized in that: The working steps of the case analysis module also include: S15: Update the first case information database using the first text information, the first risk information, the first symptom information and the first cause of disease information.

4. The foodborne disease incident epidemiological investigation and disposal management system according to claim 3, characterized in that: The working steps of the similar case classification module mainly include: S21: Acquire first time information and first location information of a plurality of first case information; S22: generating a plurality of first time-space two-dimensional vectors for a plurality of first case information according to the first time information and the first position information; S23: clustering the plurality of the first spatiotemporal two-dimensional vectors to obtain a plurality of first case sets; S24: Acquire multiple pieces of second case information contained in each of the first case sets, and generate a first case description vector for each piece of the second case information; S25: clustering the plurality of first case description vectors to obtain a plurality of second case sets; S26: For each of the second case sets, generate a first symptom label and a first cause label.

5. The foodborne disease incident epidemiological investigation and disposal management system according to claim 4, characterized in that: The main working steps of the communication scheduling module are as follows: S31: The plurality of on-site investigator nodes upload the collected foodborne disease event information to the cloud server; S32: The cloud server analyzes the foodborne disease event information and updates the first case information database.

6. The foodborne disease incident epidemiological investigation and disposal management system according to claim 5, characterized in that: The main working steps of the survey conclusion generation module are as follows: S41: generating a plurality of first investigation conclusion forms according to a plurality of the first symptom labels and a plurality of the first cause of disease labels; S42: Distribute the plurality of first investigation conclusion forms to corresponding on-site investigator nodes through the communication scheduling module.

7. A method for managing the epidemiological investigation and disposal of foodborne disease incidents, which is executed based on the epidemiological investigation and disposal management system of foodborne disease incidents in claims 1 to 6, and is characterized in that: The steps include: S51: receiving a plurality of first case information sent by the on-site investigator node; S52: generating corresponding first symptom information and first cause information according to the first case information; S53: clustering the plurality of first symptom information and the plurality of first cause of disease information to generate a plurality of first symptom labels and a plurality of first cause of disease labels; S54: generating a plurality of first investigation conclusion forms according to the plurality of first symptom labels and the plurality of first cause labels; S55: Distribute the plurality of first investigation conclusion forms to corresponding on-site investigator nodes.

Images