CN111739657B - Epidemic infected person prediction method and system based on knowledge graph - Google Patents
Epidemic infected person prediction method and system based on knowledge graph Download PDFInfo
- Publication number
- CN111739657B CN111739657B CN202010695650.8A CN202010695650A CN111739657B CN 111739657 B CN111739657 B CN 111739657B CN 202010695650 A CN202010695650 A CN 202010695650A CN 111739657 B CN111739657 B CN 111739657B
- Authority
- CN
- China
- Prior art keywords
- epidemiological
- person
- epidemiology
- basic information
- word
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000005540 biological transmission Effects 0.000 claims abstract description 47
- 238000004422 calculation algorithm Methods 0.000 claims description 34
- 230000006870 function Effects 0.000 claims description 27
- 230000015654 memory Effects 0.000 claims description 21
- 238000011835 investigation Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000000306 recurrent effect Effects 0.000 claims description 6
- 238000011841 epidemiological investigation Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims 4
- 230000001575 pathological effect Effects 0.000 claims 1
- 201000010099 disease Diseases 0.000 abstract description 12
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 12
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000004891 communication Methods 0.000 description 10
- 238000000605 extraction Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 208000015181 infectious disease Diseases 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 150000007523 nucleic acids Chemical class 0.000 description 2
- 102000039446 nucleic acids Human genes 0.000 description 2
- 108020004707 nucleic acids Proteins 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 206010008631 Cholera Diseases 0.000 description 1
- 208000035473 Communicable disease Diseases 0.000 description 1
- 201000009906 Meningitis Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 206010022000 influenza Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Landscapes
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
One or more embodiments of the present specification provide a method and a system for predicting an epidemiological infector based on a knowledge graph, which construct an epidemiological patient personal knowledge graph and an epidemiological transmission knowledge graph by using a knowledge graph technology, and comprehensively comb the transmission relationship and the path of an epidemiological disease by fusing the epidemiological patient personal knowledge graph and the epidemiological transmission knowledge graph, thereby predicting a suspected patient with pertinence.
Description
Technical Field
One or more embodiments of the present disclosure relate to the field of internet big data technology, and in particular, to a method and a system for predicting an epidemic infected person based on a knowledge graph.
Background
Epidemic disease refers to infectious diseases that can infect numerous populations, such as influenza, meningitis, cholera, and the like. Epidemics can spread widely over a short period of time, either occurring in a certain area or being a global pandemic.
Some epidemic diseases have the ability of people to transmit, can be transmitted by respiratory droplets and close contact, have stronger infectivity, and are generally susceptible to people. After some epidemic diseases, the body of the patient may be damaged to a certain extent, and the disease is critical and even death may occur. Because the epidemic disease has the characteristics of easy infection, high propagation speed and damage to human bodies, the epidemic disease prevention and control work is very important and is not slow.
Early discovery is an important means for controlling epidemic spread and reducing the fatality rate, and the number of accumulated confirmed cases and close contacts is increased along with the development of the epidemic, so that the research on the epidemic spread is the key of epidemic prevention and control work. In epidemic spread research work, data processing work for information on persons who have confirmed infection is important. However, the current data processing for epidemic infected persons only stays in the contact and propagation paths on the surface of the diagnosed infected person, and the hidden propagation relationship cannot be effectively reflected, and meanwhile, the prediction for the susceptible person is not distinguished, so that the existing epidemiological data processing method is not comprehensive and accurate.
Disclosure of Invention
In view of this, one or more embodiments of the present disclosure are directed to a method and a system for predicting an epidemic infected person based on a knowledge graph, so as to solve the problem that the existing epidemic data processing method is not comprehensive and inaccurate.
In view of the above, one or more embodiments of the present specification provide a method for predicting an epidemic infected person based on a knowledge-graph, comprising:
acquiring basic information of a person to be investigated;
extracting entities and relations of the basic information of the inquired person, and constructing an inquired person knowledge graph;
acquiring an epidemiological transmission knowledge map; the epidemiological transmission knowledge map is constructed by utilizing an epidemiological database;
and matching and determining a suspected patient according to the surveyed person knowledge graph and the epidemiological transmission knowledge graph.
Optionally, the method further includes:
constructing a sample set comprising a plurality of samples; wherein the sample comprises: sample data and tag data; the sample data comprises basic information of the respondent; the tag data comprises an epidemiological survey report of the respondent; the epidemiological survey report of the respondents comprises identity information of the respondents, journey tracks of the respondents, contact persons of the respondents and morbidity processes of the respondents;
according to the sample set, an epidemiology investigation report generation model is constructed and trained through a preset machine learning algorithm;
and generating the epidemiological survey report of the inquired person through the epidemiological survey report generation model according to the basic information of the inquired person.
Optionally, the basic information of the person under investigation is in a voice form,
the method further comprises the following steps:
and converting the basic information of the inquired person into a text form.
Optionally, the obtaining of the epidemiological transmission knowledge map; the epidemiological transmission knowledge map is constructed by utilizing an epidemiological database and comprises the following steps:
extracting an epidemiological ternary group dataset from the epidemiological database;
constructing an original knowledge map of the epidemiology by using the three-component data set of the epidemiology;
training the epidemiology original knowledge graph by using a TransE algorithm to obtain an epidemiology entity vector and an epidemiology relationship vector;
evaluating whether an implicit relationship exists between the two epidemiological entities through a pre-constructed evaluation function;
and updating the epidemiology original knowledge graph according to the implicit relationship to obtain the epidemiology propagation knowledge graph.
Optionally, the pre-configured evaluation function includes:
wherein (A), (B), (C), (D), (C), (h,r,t) Is a positive example triplet;hrepresents the head entity of the epidemiology,trepresents the tail entity of the epidemiology,rrepresenting epidemiological head entitieshAnd epidemiological tail entitiestEpidemiological relationships between;
Tis a set of positive example triples;
(h',r',t') Randomly replacing negative example triples constructed by epidemiological entities and epidemiological relationships;
T'a set of negative example triples;
γa hyperparameter that is the separation distance of the positive and negative example triplet scores;
E(h,r,t) An energy function that is a positive example triplet score;
E(h',r',t') Energy function of negative example triplet scores.
Optionally, the matching and determining the suspected patient according to the surveyed person knowledge graph and the epidemiological transmission knowledge graph includes:
fusing the surveyed person knowledge map and the epidemiological transmission knowledge map to obtain an epidemiological survey knowledge map;
extracting subgraphs from the epidemiological survey knowledge map;
and calculating the correlation between the person in the sub-graph and other persons in contact relationship with the investigated person, and taking the other persons with higher correlation as suspected patients.
Optionally, the calculating the relevance between the person under investigation and other persons in the sub-graph includes:
wherein,w uv representing a person having a contact relationship with the investigated personuAnd other personsvThe correlation of (c);
N(u) Representing persons in the sub-graph having contact relation with the investigated personuA set of (a);
N(v) Representing other persons in the subgraphvA collection of (a).
Based on the same inventive concept, one or more embodiments of the present specification provide a system for predicting an epidemic infected person based on a knowledge-graph, comprising:
an information acquisition module configured to: acquiring basic information of a person to be investigated;
a surveyor knowledge-graph building module configured to: extracting entities and relations of the basic information of the inquired person, and constructing an inquired person knowledge graph;
an epidemiological transmission knowledge map construction module configured to: acquiring an epidemiological transmission knowledge map; the epidemiological transmission knowledge map is constructed by utilizing an epidemiological database;
a suspected patient determination module configured to: and matching and determining a suspected patient according to the surveyed person knowledge graph and the epidemiological transmission knowledge graph.
Based on the same inventive concept, one or more embodiments of the present specification provide an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the above method when executing the program.
Based on the same inventive concept, one or more embodiments of the present specification provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the above-described method.
From the above, it can be seen that one or more embodiments of the present specification provide a method and a system for predicting epidemiological infectors, which construct an epidemiological patient personal knowledge graph and an epidemiological transmission knowledge graph by using a knowledge graph technology, and comprehensively comb the transmission relationship and path of epidemiological diseases by fusing the epidemiological patient personal knowledge graph and the epidemiological transmission knowledge graph, so as to predict suspected patients with pertinence, and at the same time, the method and the system can generate an epidemiological survey report to support epidemiological survey work.
Drawings
In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only one or more embodiments of the present specification, and that other drawings may be obtained by those skilled in the art without inventive effort from these drawings.
FIG. 1 is a schematic flow chart diagram of a method for knowledge-graph-based prediction of pandemic infected persons according to one or more embodiments of the present disclosure;
FIG. 2 is a schematic flow chart for generating an epidemiological survey report provided by one or more embodiments of the present disclosure;
FIG. 3 is a schematic flow chart for constructing an epidemiological spread knowledge graph provided in one or more embodiments of the present disclosure;
FIG. 4 is a schematic flow chart for determining a suspected patient according to one or more embodiments of the present disclosure;
FIG. 5 is a schematic diagram of a system for knowledge-graph based prediction of pandemic infected persons according to one or more embodiments of the present disclosure;
fig. 6 is a schematic diagram of a more specific hardware structure of an electronic device according to one or more embodiments of the present disclosure.
Detailed Description
For the purpose of promoting a better understanding of the objects, aspects and advantages of the present disclosure, reference is made to the following detailed description taken in conjunction with the accompanying drawings.
It is to be noted that unless otherwise defined, technical or scientific terms used in one or more embodiments of the present specification should have the ordinary meaning as understood by those of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," and similar terms in one or more embodiments of the specification is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
To achieve the above objects, one or more embodiments of the present specification provide a method and system for predicting a pandemic ill-infected person based on a knowledge graph, which may be applied to various electronic devices including a memory, a processor, and a computer program stored on the memory and running on the processor, and a non-transitory computer-readable storage medium, which are not specifically limited by the present disclosure.
Fig. 1 is a schematic flow chart of a method for predicting an epidemic infected person based on a knowledge-graph according to one or more embodiments of the present disclosure, wherein the method for predicting an epidemic infected person based on a knowledge-graph includes:
s101, acquiring basic information of the person to be investigated.
In some embodiments, the basic information of the respondent includes identity information of the respondent, a journey track of the respondent, contact persons of the respondent and an attack process of the respondent.
The identity information of the respondents includes names, identification numbers, contact ways, sexes, ages, native places, professional categories and the like. The journey track of the person to be investigated comprises a living address, a working address, a visiting hospital, a vehicle and the like. The respondents included family budders, work budders, and other budders. The onset process of the person to be investigated includes the initial onset date of symptoms, the date of treatment, the date of confirmed diagnosis, the date of rehabilitation and the like.
For example, the basic information acquired for the respondent includes "Zhao a country, flight 5018 to return to the local area from a high-risk area on 1 month and 19 days; after returning to the local place, a certain Zhao country moves for 5 days in the residential quarter, and during the movement, the certain Zhao country carries out close-range conversation with a neighbor Pengzhi sea living in the No. 3 building; 1, 24 days, fever occurs in certain Zhao nations, and the patients go to hospitals to see a diagnosis and confirm the infection; the father of Zhao country Zhao people live with it, during which Zhao people stay on duty normally.
In addition, the basic information of the respondents may also include other epidemiologically related information, such as suspected exposure, suspected contacts, past medical history, infection source classification, relationship with previous cases, input or local cases, and nucleic acid testing history, etc., according to specific needs.
Some information in the basic information of the respondent may be directly obtained from the relevant information base of the respondent, for example, the identity information of the respondent, such as name, identification number, contact way, sex, age, native place, occupation category, etc., may be obtained from the identity database of the relevant department; the journey track of the person to be investigated, such as a living address, a working address, a hospital for seeing a doctor, a vehicle and the like, can be obtained by positioning a mobile phone signal; the past medical history, nucleic acid detection history and the like of the person to be examined can be acquired through information records of hospital departments.
Some of the basic information of the respondents can be obtained by inquiring the respondents, for example, the contact persons of the respondents such as family respondents, work respondents and other respondents can be obtained by inquiring the respondents; the location of some details in the journey trace of the person to be investigated can be obtained by querying the person to be investigated.
In some embodiments, the obtained basic information of the person under investigation is in a voice form.
On one hand, the person to be investigated is generally a confirmed infected person, the epidemic infection is strong, in the investigation visit process for the confirmed infected person, in order to avoid the infection, the person to be investigated, medical staff and other staff generally adopt a stricter protective measure, such as wearing protective clothing, etc., in this case, the activity of the human body is greatly limited, and writing and typing are very inconvenient, so the form of voice recording is adopted.
On one hand, the contents of epidemiological investigation are complex, and especially for the information with high degree of freedom and large individual difference, such as the journey track of the examinee, the contact persons of the examinee and the disease process of the examinee, the written filling mode is difficult to be detailed, which is very insufficient for epidemiological investigation, so that the voice recording mode is adopted, and the medical staff or other staff have conversation access to the examinee, so that more comprehensive information, the details of the information and the consequences of the reasons can be obtained.
Wherein, the basic information of the respondent in the form of voice is converted into the form of text.
The basic information of the person to be investigated contains a large number of expressions of natural language, so that preprocessing is performed on the basic information of the person to be investigated in text form, wherein the preprocessing includes deleting stop words, irrelevant punctuations, repeated information and the like, and details are not described here.
S102, extracting the entities and the relations of the basic information of the inquired person, and constructing the knowledge graph of the inquired person.
In some embodiments, the basic information of the person to be investigated is subjected to entity identification, and the entity and the relationship are extracted.
The entity comprises identity information of the respondent, a journey track of the respondent, contact persons of the respondent, an attack process of the respondent and the like, and specific contents of the entity are determined by basic information of the respondent, for example, if the respondent takes a flight, the corresponding entity comprises the respondent and the flight.
The relationship, for example, a respondent takes a flight.
By extracting the triples in such a way, the more accurate knowledge map of the person to be investigated can be obtained by utilizing the basic information of the person to be investigated, and the knowledge map of the person to be investigated is highly matched with the basic information of the person to be investigated, so that the comprehensiveness and the accuracy of the epidemiological characteristics of the person to be investigated are ensured.
For example, the knowledge-map triplets that can be extracted by the example in S101 include (zhao country, residential address, No. 3 building), (zhao country, other seals, penny sea), (zhao country, family seals, zhao nations), (zhao country, trip track, certain high-risk area) (zhao nations, transportation, flight 5018), (zhao nations, diagnosed date, 1 month 24 days), and the like.
S103, acquiring an epidemiological transmission knowledge map; the epidemiological transmission knowledge map is constructed by utilizing an epidemiological database.
Epidemiological databases contain a large amount of basic information about the person under investigation. The basic information of the person to be investigated includes identity information of the person to be investigated, a journey track of the person to be investigated, contact persons of the person to be investigated, a disease process of the person to be investigated, and the like. And (3) constructing an epidemiological transmission knowledge map based on an epidemiological database according to the epidemiological principle and the epidemiological transmission rule and combing the transmission path of the epidemiological transmission.
And S104, matching and determining the suspected patient according to the surveyed person knowledge graph and the epidemiological transmission knowledge graph.
And establishing a relation between the surveyor knowledge graph and the epidemiological transmission knowledge graph by performing entity matching to obtain an epidemiological transmission path corresponding to the surveyor, and performing reasoning by a path between the two entities to predict the suspected patient. Predicting suspected patients includes predicting specific suspected patient individuals, a population of suspected patients, and a place of aggregation of suspected patients.
The method and the system for predicting epidemiological infectors based on the knowledge graph, which are provided by one or more embodiments of the specification, construct the personal knowledge graph and the epidemiological transmission knowledge graph of the epidemiological patients by using the knowledge graph technology, and comprehensively comb the epidemiological transmission relationship and path by fusing the personal knowledge graph and the epidemiological transmission knowledge graph of the epidemiological patients, so that suspected patients are predicted pertinently.
It should be noted that the method of one or more embodiments of the present disclosure may be performed by a single device, such as a computer or server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the devices may perform only one or more steps of the method of one or more embodiments of the present disclosure, and the devices may interact with each other to complete the method.
Fig. 2 is a schematic flow chart of generating an epidemiological survey report according to one or more embodiments of the present disclosure, the generating of the epidemiological survey report including:
s201, constructing a sample set comprising a plurality of samples; wherein the sample comprises: sample data and tag data; the sample data comprises basic information of the respondent; the tag data comprises an epidemiological survey report of the respondent; the epidemiological survey report of the respondents comprises identity information of the respondents, journey tracks of the respondents, contact persons of the respondents and disease processes of the respondents.
And S202, constructing and training the epidemiological survey report generation model according to the sample set through a preset machine learning algorithm.
Wherein the predetermined machine learning algorithm may be selected from one or more of a naive bayes algorithm, a decision tree algorithm, a support vector machine algorithm, a kNN algorithm, a neural network algorithm, a deep learning algorithm, and a logistic regression algorithm.
And S203, generating an epidemiological survey report of the inquired person through the epidemiological survey report generation model according to the basic information of the inquired person.
In some embodiments, the epidemiological survey report generation model employs an RNN (recurrent neural network) model, including an encoder and a decoder.
The obtained basic information of the inquirer is input into an input layer, specifically, the input layer is a sequentially arranged word sequence obtained by word segmentation of the basic information of the inquirer, and each word can be encoded into a vector form in a one-hot mode. The input layer carries out word embedding processing on the basic information of the inquired person so as to extract the characteristics of each word and obtain the word vector of each word in the basic information of the inquired person. The algorithm used in the Word embedding process may be arbitrarily selected, such as Word2Vec, GloVe, and the like.
And gradually inputting the word vector of each word in the basic information of the inquired person into an encoder, wherein the encoder gradually generates a first hidden state for each word, and the first hidden state is used for representing the comprehensive semantics of the word at the current step and the words at all the previous steps. The first hidden state is a vector whose dimension is equal to the number of neurons included in the hidden layer of the encoder, and whose value in each dimension is the output value of the activation function of each neuron.
For the first step of the decoder, the first hidden state generated by the last step of the encoder is input into the decoder, and because the decoder does not generate the previous step at this time, a start symbol is simultaneously input into the decoder, and the decoder can generate a second hidden state corresponding to the first output word according to the first hidden state and the start symbol generated by the last step of the encoder. For each step after the first step, the decoder can generate a second hidden state of the current step according to the second hidden state generated by the previous step and the output word generated by the previous step.
Specifically, for the output word of the current step, the decoder obtains the second hidden state generated by the current step and each previous step. And the second hidden state is used for representing the comprehensive semantics of the output words of the current step and the output words of all the previous steps. The second hidden state is a vector whose dimension is equal to the number of neurons included in the hidden layer of the decoder, and whose value in each dimension is the output value of the activation function of each neuron.
In this embodiment, the decoder performs normalization (so that the sum of the probability values in the output probability distribution is 1) according to the second hidden state by using a Softmax function, and obtains the output probability distribution that the output word at the current step corresponds to each word in the basic information of the person under investigation. And finally, taking the corresponding word with the maximum probability value as the output word output at the current step. The output words are arranged in sequence to form an epidemiological survey report.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Fig. 3 is a schematic flow chart of the process for constructing the epidemiological transmission knowledge graph provided in one or more embodiments of the present specification, and the process for constructing the epidemiological transmission knowledge graph comprises the following steps:
s301, extracting an epidemiology ternary group data set from the epidemiology database.
And extracting epidemiological knowledge from the epidemiological database, wherein the extracting of the epidemiological knowledge comprises entity extraction and relationship extraction.
The method of entity extraction may be a statistical machine learning-based method and a deep learning-based method. The method based on statistical machine learning mainly comprises the following steps: hidden markov models (hidden markov models HMMs), Maximum Entropy (ME), Support Vector Machines (SVMs), Conditional Random Fields (CRFs), and the like. The deep learning-based method comprises the following steps: recurrent Neural Networks (RNNs), Long Short Term Memory (LSTM), and the like.
The method of relationship extraction may be a method of machine learning, such as supervised learning, semi-supervised learning, and unsupervised learning.
It should be noted that the entity extraction and the relationship extraction may be implemented by different methods, respectively, or simultaneously by using an end-to-end model based on a neural network.
It should be understood that the above extraction method of epidemiological knowledge is illustrative and not intended to limit the implementation of the present invention, and the methods for knowledge extraction in the prior art can be applied to the present embodiment.
S302, constructing an original knowledge map of the epidemiology by using the three-component data set of the epidemiology.
S303, training the epidemiology original knowledge graph by using a TransE algorithm to obtain an epidemiology entity vector and an epidemiology relationship vector.
The TransE algorithm is a distributed vector representation based on entities and relations, and each epidemiological triple (b) is expressed by utilizing the TransE algorithmh, r, t) The head entity and the tail entity of (2) are projected into a relation space, the relation in each epidemiology triple is regarded as the translation from the head entity to the tail entity, and the vector is adjusted to meet the requirementh+r=tAnd (4) obtaining the characteristic entity vector meeting the condition through training.
And finally, calculating a loss function, wherein the closer the entity in geometry is, the greater the correlation is, the higher the relevance of the entity is, and the more possible the relation is.
And S304, evaluating whether an implicit relationship exists between the two epidemiological entities through a pre-constructed evaluation function.
If two entities are directly connected, indicating that there is a relationship between the two entities, then for two entities that are not directly connected, whether there is an implicit relationship between them is considered. The present disclosure evaluates whether there is an implicit relationship between two epidemiological entities through a pre-constructed merit function by iterating over the two entities that are not directly connected.
The pre-constructed merit function includes:
wherein (A), (B), (C), (D), (C), (h,r,t) Is a positive example triplet;hrepresents the head entity of the epidemiology,trepresents the tail entity of the epidemiology,rrepresenting epidemiological head entitieshAnd epidemiological tail entitiestEpidemiological relationships between;
Tis a set of positive example triples;
(h',r',t') Randomly replacing negative example triples constructed by epidemiological entities and epidemiological relationships;
T'a set of negative example triples;
γa hyperparameter that is the separation distance of the positive and negative example triplet scores;
E(h,r,t) An energy function that is a positive example triplet score;
E(h',r',t') Energy function of negative example triplet scores.
In the space where the entities are mapped by using the TransE algorithm, the closer the entity correlation is geometrically, the higher the association degree of the entities is, the more likely the entities have a relationship, so that an implicit relationship is more likely to exist between two entities with higher evaluation function scores.
S305, updating the epidemiology original knowledge graph according to the implicit relationship to obtain the epidemiology propagation knowledge graph.
In the epidemiology original knowledge graph, the implicit relationship calculated in the S304 is complemented, so that the information of the knowledge graph is more comprehensive.
It is to be appreciated that the method can be performed by any apparatus, device, platform, cluster of devices having computing and processing capabilities.
Fig. 4 is a schematic flowchart of a process for determining a suspected patient according to one or more embodiments of the present disclosure, where determining a suspected patient includes:
s401, fusing the surveyed person knowledge map and the epidemiological transmission knowledge map to obtain the epidemiological survey knowledge map.
The information of the knowledge graph of the person to be investigated is limited, and is limited to the range of activity of the person to be investigated and the knowledge of the activity of the person to be investigated, and the traditional way of processing the information of the person to be investigated may only utilize the information, but cannot expand the information. The method fuses the surveyed person knowledge graph and the epidemiology propagation knowledge graph constructed based on the database, expands and supplements the information of the surveyor knowledge graph, and enables the obtained information to be more comprehensive.
S402, extracting subgraphs from the knowledge map of the epidemiological survey.
The information amount of the fused knowledge graph is huge, the size of the knowledge graph can influence the running time and the result of a subsequent algorithm, and in order to be capable of predicting based on specific threads of a person to be investigated in a targeted mode, sub-graphs are extracted from the knowledge graph and serve as the basis of subsequent calculation. It should be understood that larger subgraphs will generally include better features, and the specific subgraph size may be determined by demand and computing power.
And S403, calculating the correlation between the person in the sub-graph and the person in contact relationship with the investigated person and other persons, and taking the other persons with higher correlation as suspected patients.
It should be understood that the conventional method is also used as a suspected patient for a person who has a contact relationship with the person under investigation, but the conventional method is not targeted for a person who has no contact relationship with the person under investigation. On one hand, the more the entities in the knowledge graph are far away from the surveyed person, the more the number of the entities is, on the other hand, the relationships among the entities are different and complicated in structure. Therefore, the present disclosure calculates the correlation between the person in contact relationship with the person under investigation and other persons in the sub-graph, thereby determining the suspected patient with respect to the person under investigation.
And training the subgraph by using a TransE algorithm to obtain an entity vector and a relation vector. The TransE algorithm is a distributed vector representation based on entities and relations, and each epidemiological triple (b) is expressed by utilizing the TransE algorithmh, r, t) The head entity and the tail entity of (a) are projected into a relationship space, and the relationship in each epidemiological triplet is considered as a translation from the head entity to the tail entity.
On the basis of the entity vector and the relationship vector, calculating the correlation between the person in the sub-graph and the person in contact relationship with the person to be investigated and other persons, wherein the correlation comprises the following steps:
wherein,w uv representing a person having a contact relationship with the investigated personuAnd other personsvThe correlation of (c);
N(u) Representing persons in the sub-graph having contact relation with the investigated personuA set of (a);
N(v) Representing other persons in the subgraphvA collection of (a).
And (4) calculating the correlation between the person having contact relationship with the investigated person and other persons, sorting the correlation results, and recommending the persons in the other person set with higher correlation as suspected patients.
Further, by studying suspected patients, it is possible to predict the whole population of suspected patients, the place where the suspected patients are gathered, and the like.
Fig. 5 is a schematic structural diagram of a system for predicting an epidemic infected person based on a knowledge-graph according to one or more embodiments of the present disclosure, wherein the system for predicting an epidemic infected person based on a knowledge-graph includes:
an information acquisition module 501 configured to: and acquiring basic information of the inquired person.
The information obtaining module 501 is specifically configured to: the method comprises the steps of obtaining basic information of a person to be investigated, wherein the basic information of the person to be investigated comprises identity information of the person to be investigated, a journey track of the person to be investigated, contact persons of the person to be investigated, a disease occurrence process of the person to be investigated and the like, converting the obtained basic information of the person to be investigated into a text form when the basic information of the person to be investigated is in a voice form, and carrying out preprocessing such as deleting stop words, irrelevant punctuations, repeated information and the like.
A surveyor's knowledge-graph building module 502 configured to: and extracting the entities and the relations of the basic information of the inquired person, and constructing the knowledge graph of the inquired person.
An epidemiological transmission knowledge map construction module 503 configured to: acquiring an epidemiological transmission knowledge map; the epidemiological transmission knowledge map is constructed by utilizing an epidemiological database.
The epidemiological spread knowledge map construction module 503 is specifically configured to: extracting an epidemiological triple data set from the epidemiological database. And constructing an epidemiological original knowledge map by using the epidemiological ternary group dataset. And training the epidemiological original knowledge graph by using a TransE algorithm to obtain an epidemiological entity vector and an epidemiological relationship vector. Whether an implicit relationship exists between two epidemiological entities is evaluated through a pre-constructed evaluation function. And updating the epidemiology original knowledge graph according to the implicit relationship to obtain the epidemiology propagation knowledge graph.
A suspected patient determination module 504 configured to: and matching and determining a suspected patient according to the surveyed person knowledge graph and the epidemiological transmission knowledge graph.
The suspected patient determining module 504 is specifically configured to: and fusing the surveyed person knowledge map and the epidemiological transmission knowledge map to obtain the epidemiological survey knowledge map. And extracting subgraphs from the knowledge map of the epidemiological survey. And calculating the correlation between the person to be investigated and other persons in the sub-graph, and taking the other persons with higher correlation as suspected patients.
The epidemic infected person prediction system based on the knowledge graph further comprises: an epidemiological survey report generation module configured to: generating an epidemiological survey report of the respondent.
The epidemiological survey report generation module is specifically used for: constructing a sample set comprising a plurality of samples; wherein the sample comprises: sample data and tag data; the sample data comprises basic information of the respondent; the tag data comprises an epidemiological survey report of the respondent; the epidemiological survey report of the respondents comprises identity information of the respondents, journey tracks of the respondents, contact persons of the respondents and disease processes of the respondents.
And according to the sample set, constructing and training by a preset machine learning algorithm to obtain an epidemiological investigation report generation model. Wherein the predetermined machine learning algorithm may be selected from one or more of a naive bayes algorithm, a decision tree algorithm, a support vector machine algorithm, a kNN algorithm, a neural network algorithm, a deep learning algorithm, and a logistic regression algorithm.
And generating the epidemiological survey report of the inquired person through the epidemiological survey report generation model according to the basic information of the inquired person.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the modules may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.
The apparatus of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Fig. 6 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the spirit of the present disclosure, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present description as described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures, for simplicity of illustration and discussion, and so as not to obscure one or more embodiments of the disclosure. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the understanding of one or more embodiments of the present description, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the one or more embodiments of the present description are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the disclosure, it should be apparent to one skilled in the art that one or more embodiments of the disclosure can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
It is intended that the one or more embodiments of the present specification embrace all such alternatives, modifications and variations as fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of one or more embodiments of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (4)
1. A method for predicting epidemic infected persons based on a knowledge graph is characterized by comprising the following steps:
acquiring basic information of a person to be investigated; if the basic information of the inquired person is in a voice form, converting the basic information of the inquired person into a text form;
extracting entities and relations of the basic information of the inquired person, and constructing an inquired person knowledge graph;
acquiring an epidemiological transmission knowledge map; the epidemiological transmission knowledge map is constructed by utilizing an epidemiological database; the method specifically comprises the following steps: extracting an epidemiological ternary group dataset from the epidemiological database; constructing an original knowledge map of the epidemiology by using the three-component data set of the epidemiology; training the epidemiology original knowledge graph by using a TransE algorithm to obtain an epidemiology entity vector and an epidemiology relationship vector; evaluating whether an implicit relationship exists between the two epidemiological entities through a pre-constructed evaluation function; updating the epidemiology original knowledge graph according to the implicit relationship to obtain the epidemiology propagation knowledge graph; wherein the pre-constructed merit function comprises:
(ii) a Wherein (A), (B), (C), (D), (C), (h,r,t) Is a positive example triplet;hrepresents the head entity of the epidemiology,trepresents the tail entity of the epidemiology,rrepresenting epidemiological head entitieshAnd epidemiological tail entitiestEpidemiological relationships between;Tis a set of positive example triples; (h',r',t') Randomly replacing negative example triples constructed by epidemiological entities and epidemiological relationships;T'a set of negative example triples;γa hyperparameter that is the separation distance of the positive and negative example triplet scores;E(h,r,t) An energy function that is a positive example triplet score;E(h',r',t') An energy function that is a negative example triplet score;
matching and determining a suspected patient according to the surveyed person knowledge map and the epidemiological transmission knowledge map; the method specifically comprises the following steps: fusing the surveyed person knowledge map and the epidemiological transmission knowledge map to obtain an epidemiological survey knowledge map; extracting subgraphs from the epidemiological survey knowledge map; calculating the correlation between the person in the sub-graph and the person in contact relationship with the investigated person and other persons, and taking the other persons with higher correlation as suspected patients; wherein the calculating the correlation between the person in the sub-graph and the person in contact relationship with the inquired person comprises the following steps:
(ii) a Wherein,w uv representing a person having a contact relationship with the investigated personuAnd other personsvThe correlation of (c); n (a)u) Representing persons in the sub-graph having contact relation with the investigated personuA set of (a);N(v) Representing other persons in the subgraphvA set of (a);
constructing a sample set comprising a plurality of samples; wherein the sample comprises: sample data and tag data; the sample data comprises basic information of the respondent; the tag data comprises an epidemiological survey report of the respondent; the epidemiological survey report of the respondents comprises identity information of the respondents, journey tracks of the respondents, contact persons of the respondents and morbidity processes of the respondents;
according to the sample set, an epidemiology investigation report generation model is constructed and trained through a preset machine learning algorithm;
generating an epidemiology investigation report of the inquired person through the epidemiology investigation report generation model according to the basic information of the inquired person; the method specifically comprises the following steps: the epidemiological investigation report generation model adopts a recurrent neural network model and comprises an encoder and a decoder; inputting the basic information of the inquired person into an input layer of the recurrent neural network model, and performing word embedding processing on the basic information of the inquired person to extract the characteristics of each word to obtain a word vector of each word in the basic information of the inquired person; gradually inputting the word vector of each word in the basic information of the inquired person into the encoder, wherein the encoder gradually generates a first hidden state for each word; for the first step of the decoder, inputting the first hidden state generated by the last step of the encoder into the decoder to generate a second hidden state corresponding to the first output word; for each step after the first step, the decoder can generate a second hidden state of the current step according to the second hidden state generated by the previous step and the output word generated by the previous step; the decoder is normalized through a Softmax function according to the second hidden state to obtain output probability distribution of the output words of the current step corresponding to all words in the basic information of the inquired person; taking the corresponding word with the maximum probability value as an output word output by the current step; and the output words are arranged in sequence to form the epidemiological survey report.
2. A system for predicting an epidemic infected person based on a knowledge-graph, comprising:
an information acquisition module configured to: acquiring basic information of a person to be investigated; if the basic information of the inquired person is in a voice form, converting the basic information of the inquired person into a text form;
a surveyor knowledge-graph building module configured to: extracting entities and relations of the basic information of the inquired person, and constructing an inquired person knowledge graph;
an epidemiological transmission knowledge map construction module configured to: acquiring an epidemiological transmission knowledge map; the epidemiological transmission knowledge map is constructed by utilizing an epidemiological database; the method specifically comprises the following steps: extracting an epidemiological ternary group dataset from the epidemiological database; constructing an original knowledge map of the epidemiology by using the three-component data set of the epidemiology; training the epidemiology original knowledge graph by using a TransE algorithm to obtain an epidemiology entity vector and an epidemiology relationship vector; evaluating whether an implicit relationship exists between the two epidemiological entities through a pre-constructed evaluation function; updating the epidemiology original knowledge graph according to the implicit relationship to obtain the epidemiology propagation knowledge graph; wherein the pre-constructed merit function comprises:
(ii) a Wherein (A), (B), (C), (D), (C), (h,r,t) Is a positive example triplet;hrepresents the head entity of the epidemiology,trepresents the tail entity of the epidemiology,rrepresenting epidemiological head entitieshAnd epidemiological tail entitiestIn the middle of the periodA pathological relationship;Tis a set of positive example triples; (h',r',t') Randomly replacing negative example triples constructed by epidemiological entities and epidemiological relationships;T'a set of negative example triples;γa hyperparameter that is the separation distance of the positive and negative example triplet scores;E(h,r,t) An energy function that is a positive example triplet score;E(h',r',t') An energy function that is a negative example triplet score;
a suspected patient determination module configured to: matching and determining a suspected patient according to the surveyed person knowledge map and the epidemiological transmission knowledge map; the method specifically comprises the following steps: fusing the surveyed person knowledge map and the epidemiological transmission knowledge map to obtain an epidemiological survey knowledge map; extracting subgraphs from the epidemiological survey knowledge map; calculating the correlation between the person in the sub-graph and the person in contact relationship with the investigated person and other persons, and taking the other persons with higher correlation as suspected patients; wherein the calculating the correlation between the person in the sub-graph and the person in contact relationship with the inquired person comprises the following steps:
(ii) a Wherein,w uv representing a person having a contact relationship with the investigated personuAnd other personsvThe correlation of (c); n (a)u) Representing persons in the sub-graph having contact relation with the investigated personuA set of (a);N(v) Representing other persons in the subgraphvA set of (a);
an epidemiological survey report generation module configured to: constructing a sample set comprising a plurality of samples; wherein the sample comprises: sample data and tag data; the sample data comprises basic information of the respondent; the tag data comprises an epidemiological survey report of the respondent; the epidemiological survey report of the respondents comprises identity information of the respondents, journey tracks of the respondents, contact persons of the respondents and morbidity processes of the respondents;
according to the sample set, an epidemiology investigation report generation model is constructed and trained through a preset machine learning algorithm;
generating an epidemiology investigation report of the inquired person through the epidemiology investigation report generation model according to the basic information of the inquired person; the method specifically comprises the following steps: the epidemiological investigation report generation model adopts a recurrent neural network model and comprises an encoder and a decoder; inputting the basic information of the inquired person into an input layer of the recurrent neural network model, and performing word embedding processing on the basic information of the inquired person to extract the characteristics of each word to obtain a word vector of each word in the basic information of the inquired person; gradually inputting the word vector of each word in the basic information of the inquired person into the encoder, wherein the encoder gradually generates a first hidden state for each word; for the first step of the decoder, inputting the first hidden state generated by the last step of the encoder into the decoder to generate a second hidden state corresponding to the first output word; for each step after the first step, the decoder can generate a second hidden state of the current step according to the second hidden state generated by the previous step and the output word generated by the previous step; the decoder is normalized through a Softmax function according to the second hidden state to obtain output probability distribution of the output words of the current step corresponding to all words in the basic information of the inquired person; taking the corresponding word with the maximum probability value as an output word output by the current step; and the output words are arranged in sequence to form the epidemiological survey report.
3. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of claim 1 when executing the program.
4. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010695650.8A CN111739657B (en) | 2020-07-20 | 2020-07-20 | Epidemic infected person prediction method and system based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010695650.8A CN111739657B (en) | 2020-07-20 | 2020-07-20 | Epidemic infected person prediction method and system based on knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111739657A CN111739657A (en) | 2020-10-02 |
| CN111739657B true CN111739657B (en) | 2020-12-15 |
Family
ID=72654967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010695650.8A Active CN111739657B (en) | 2020-07-20 | 2020-07-20 | Epidemic infected person prediction method and system based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111739657B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112582074B (en) * | 2020-11-02 | 2022-10-18 | 吉林大学 | Bi-LSTM and TF-IDF based new crown epidemic situation prediction and analysis method |
| CN114496284A (en) * | 2020-11-12 | 2022-05-13 | 医渡云（北京）技术有限公司 | Fusion decision method and device, computer readable storage medium and electronic device |
| US11705247B2 (en) * | 2020-11-19 | 2023-07-18 | International Business Machines Corporation | Predictive contact tracing |
| CN112488863B (en) * | 2020-12-01 | 2024-05-28 | 中国人寿保险股份有限公司 | Dangerous seed recommendation method and related equipment in user cold start scene |
| CN112669980B (en) * | 2020-12-28 | 2022-03-11 | 山东大学 | Epidemic propagation network reconstruction method and system based on node similarity |
| CN112599253B (en) * | 2020-12-29 | 2022-04-15 | 医渡云（北京）技术有限公司 | Method, device, equipment and medium for determining epidemic situation propagation path according to close contact map |
| CN112700884B (en) * | 2020-12-31 | 2024-03-29 | 医渡云（北京）技术有限公司 | Epidemic situation prevention and control effectiveness determining method and device, electronic equipment and medium |
| CN113245734B (en) * | 2021-05-11 | 2023-06-16 | 无锡先导智能装备股份有限公司 | Configuration parameter recommendation method, system, instrument and storage medium |
| CN114067935B (en) * | 2021-11-03 | 2022-05-20 | 广西壮族自治区通信产业服务有限公司技术服务分公司 | Epidemic disease investigation method, system, electronic equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130262449A1 (en) * | 2012-04-02 | 2013-10-03 | Playence GmBH | System and method for search refinement using knowledge model |
| CN109325129A (en) * | 2018-06-08 | 2019-02-12 | 浙江捷尚人工智能研究发展有限公司 | A kind of knowledge mapping inference method, electronic equipment, storage medium and system |
| CN111159426B (en) * | 2019-12-30 | 2023-04-18 | 武汉理工大学 | Industrial map fusion method based on graph convolution neural network |
| CN111428045A (en) * | 2020-03-06 | 2020-07-17 | 北京明略软件系统有限公司 | Method and device for constructing knowledge graph, computer storage medium and terminal |
-
2020
- 2020-07-20 CN CN202010695650.8A patent/CN111739657B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111739657A (en) | 2020-10-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111739657B (en) | Epidemic infected person prediction method and system based on knowledge graph | |
| Ahamad et al. | A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients | |
| US11857322B2 (en) | Systems and methods for screening, diagnosing, and stratifying patients | |
| Solayman et al. | Automatic COVID-19 prediction using explainable machine learning techniques | |
| Gupta et al. | PCA-RF: an efficient Parkinson's disease prediction model based on random forest classification | |
| WO2021184792A1 (en) | Dynamic balance assessment method and apparatus, and device and medium | |
| CN112465231B (en) | Method, apparatus and readable storage medium for predicting regional population health status | |
| CN115830718A (en) | Data processing system for predicting rehabilitation training effect based on gait recognition | |
| CN111785372A (en) | Collaborative filtering disease prediction system based on association rule and electronic equipment thereof | |
| CN111161884A (en) | Disease prediction method, device, equipment and medium for unbalanced data | |
| Leng et al. | Bi-level artificial intelligence model for risk classification of acute respiratory diseases based on Chinese clinical data | |
| Stewart et al. | Applications of natural language processing at emergency department triage: A narrative review | |
| Saputra et al. | Implementation of machine learning and deep learning models based on structural MRI for identification autism spectrum disorder | |
| Lutsai et al. | Geolocation predicting of tweets using bert-based models | |
| Yaşar et al. | A novel study to increase the classification parameters on automatic three-class COVID-19 classification from CT images, including cases from Turkey | |
| WO2024065645A1 (en) | Image and text matching model training method and apparatus, and device and storage medium | |
| Samadi et al. | A hybrid modeling framework for generalizable and interpretable predictions of ICU mortality across multiple hospitals | |
| CN116434951A (en) | Disease early warning method, device, electronic equipment, storage medium and program product | |
| CN114429822A (en) | Medical record quality inspection method and device and storage medium | |
| Miranda | HYTEA-HYBRID TREE EVOLUTIONARY ALGORITHM FOR HEARING LOSS DIAGNOSIS | |
| Daniel et al. | [Retracted] Recurrent Neural Networks for Feature Extraction from Dengue Fever | |
| Zhu et al. | Leveraging Prototype Patient Representations with Feature-Missing-Aware Calibration to Mitigate EHR Data Sparsity | |
| Samadi et al. | A hybrid modeling framework for generalizable and interpretable predictions of ICU mortality: leveraging ICD codes in a multi-hospital study of mechanically ventilated influenza patients | |
| Kumar et al. | Assessing the Supervised Machine Learning Algorithms for Human Activity Recognition Using Smartphone | |
| Ayyavaraiah | Computer Aided Covid-19 Mortality Scope Prediction by Supervised Learning. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |