CN110289101A - A kind of computer equipment, system and readable storage medium storing program for executing - Google Patents
A kind of computer equipment, system and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN110289101A CN110289101A CN201910587890.3A CN201910587890A CN110289101A CN 110289101 A CN110289101 A CN 110289101A CN 201910587890 A CN201910587890 A CN 201910587890A CN 110289101 A CN110289101 A CN 110289101A
- Authority
- CN
- China
- Prior art keywords
- diabetes
- parameter
- computer equipment
- entity
- processor
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Nutrition Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention discloses a kind of computer equipment, system and readable storage medium storing program for executing.Computer equipment includes memory, processor and stores the computer program that can be run on a memory and on a processor, and processor is realized when executing program: acquisition multi-source heterogeneous data relevant to diabetes;From the relation information extracted in the multi-source heterogeneous data between entity, the entity attributes information and each entity;According to the relation information between entity, the entity attributes information and each entity extracted, Diabetes Mellitus Knowledge map is constructed;The parameter group of one or more parameter compositions related with diabetes is received, and obtains and export diabetes risk corresponding with parameter group based on the Diabetes Mellitus Knowledge map.The present invention carries out risk profile by merging the Diabetes Mellitus Knowledge map of multi-source heterogeneous data building, can accurately provide diabetes risk forecast ratings, and then can provide Health & Fitness Tip with strong points.
Description
Technical field
The present invention relates to field of computer technology.More particularly, to a kind of computer equipment, system and readable storage medium
Matter.
Background technique
Diabetes are a kind of systemic endocrine metabolism diseases relevant to heredity and a variety of environmental factors.Internal pancreas islet
The absolute or relative deficiency of element can cause sugar, protein, fat metabolic disturbance, be mainly characterized by hyperglycemia and glycosuria, can be with
Multiple organ injury causes maimed or even dead.Because diabetes itself without what symptom, are not done blood sugar test and are difficult to
It was found that falling ill.The fearful many complication for being it of diabetes, such as eye retina lesion, neuropathy, nephrosis, high blood
There is acute ketosis stupor, also in pressure and cardio cerebrovascular affection, urinary system infection contamination etc., the patients of many first discovery diabetes
Hypoglycemic coma be all it is extremely hazardous, lethality is very high.There are many cause of disease of the disease, inherent cause, diet, obesity, old age and
Mental wound can lead to the generation of the disease.
Diabetes are as a kind of common disease, and whole world illness rate 1~2%, in 2010, Chinese illness rate was 9.7%,
The Shanghai City chronic disease and its risk factor monitoring and surveying data in November, 2017 show that Shanghai inhabitant 35 years old or more adult
In, diabetes prevalence is up to 17.6%, and more it is not promising that nearly 1/3 diabetic does not know itself illness.If
Reasonably intervened and controlled in this period, the wind of diabetic complication can be reduced glucostasis in a certain concentration
Danger, reduces the disease incidence of diabetes.
Summary of the invention
The purpose of the present invention is to provide a kind of computer equipment and readable storage medium storing program for executing, existing at least to be partially solved
Technology there are the problem of at least one of.
In order to achieve the above objectives, it the present invention provides a kind of computer equipment, including memory, processor and is stored in
On reservoir and the computer program that can run on a processor, the execution when processor is configured to load the computer program
One or more of following step:
Acquire multi-source heterogeneous data relevant to diabetes;
From the relationship letter extracted in the multi-source heterogeneous data between entity, the entity attributes information and each entity
Breath;
According to the relation information between entity, the entity attributes information and each entity extracted, diabetes are constructed
Knowledge mapping;
The parameter group of one or more parameter compositions related with diabetes is received, and is based on the Diabetes Mellitus Knowledge map
Obtain and export diabetes risk corresponding with parameter group.
In some embodiments, the source of the multi-source heterogeneous data includes internet, books, at least two in case history
Person.
In some embodiments, the diabetes risk includes the diabetes risk grade of quantization.
In some embodiments, the execution when processor is configured to load the computer program: according to the glycosuria
Sick knowledge mapping and the diabetes risk export advisory information.
In some embodiments, the advisory information includes: dietary recommendation information, exercise suggestion information, medication recommendation letter
At least one of breath and suggestion from procuratorial organ information.
In some embodiments, the execution when processor is configured to load the computer program: the parameter is stored
Group and diabetes risk corresponding with parameter group.
In some embodiments, the execution when processor is configured to load the computer program: according to the ginseng of storage
Array and corresponding diabetes risk generate simultaneously output parameter group-diabetes risk curve.
In some embodiments, the execution when processor is configured to load the computer program: in response to the ginseng
Lack at least one parameter in array, exports the inquiry message of at least one parameter to lacking in.
In some embodiments, the execution when processor is configured to load the computer program: in response to the ginseng
Lack at least one parameter in array, based on corresponding with the parameter having in the parameter group in the Diabetes Mellitus Knowledge map
Parameter in another parameter group obtain lacking at least one parameter.
In some embodiments, the execution when processor is configured to load the computer program: pass through machine learning
Model is based on the Diabetes Mellitus Knowledge map and obtains and export diabetes risk corresponding with parameter group.
In some embodiments, the machine learning model is SVM-GLM model.
In some embodiments, the execution when processor is configured to load the computer program: pass through sample data
Collection is trained the machine learning model, and it includes multiple groups parameter composition related with diabetes that the sample data, which is concentrated,
The parameter group sample corresponding diabetes risk mark of parameter group sample and parameter related with diabetes composition.
In some embodiments, the execution when processor is configured to load the computer program: different from the multi-source
The data of one of structure data data source construct the problem-answer corpus related with diabetes, include in the corpus
Multiple problem-answers pair;The problem related with diabetes is received, answer corresponding with described problem is obtained based on the corpus
Case.
In some embodiments, the execution when processor is configured to load the computer program: pass through neural network
Neural network obtain in the corpus with it is received the problem of there is the problem of high similarity, and will be asked with the high similarity
Inscribe corresponding answer as it is received the problem of answer.
The present invention also provides a kind of computer systems, computer equipment and terminal device including above-described embodiment, institute
Terminal equipment configuration is stated into the parameter group formed to the one or more parameters related with diabetes of computer equipment input
And receive the diabetes risk of the computer equipment output.
The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the computer
One or more of following step is executed when program is loaded by processor:
Acquire multi-source heterogeneous data relevant to diabetes
From the relationship letter extracted in the multi-source heterogeneous data between entity, the entity attributes information and each entity
Breath;
According to the relation information between entity, the entity attributes information and each entity extracted, diabetes are constructed
Knowledge mapping;
The parameter group of one or more parameter compositions related with diabetes is received, and is based on the Diabetes Mellitus Knowledge map
Obtain and export diabetes risk corresponding with parameter group.
Beneficial effects of the present invention are as follows:
Technical solution of the present invention is pre- by the Diabetes Mellitus Knowledge map progress risk for merging multi-source heterogeneous data building
It surveys, can accurately provide diabetes risk forecast ratings, and then Health & Fitness Tip with strong points can be provided.Specifically, of the invention
Natural language processing, crawler, knowledge fusion, conversational system, risk profile modeling, FAQ inspection is utilized in the overall evaluation of a technical project
The multiple technologies such as rope and knowledge mapping establish a diabetes health control wisdom system, and knowledge base is abundant comprehensively, risk is pre-
It surveys precisely, the glycosuria state of an illness at family can be used to obtain the control management of science.It is this for diabetes needs often examination index with
The disease of corresponding treatment recommendations is obtained, is only capable of carrying out related search queries in webpage manually compared to current user, can not basis
Monitoring index obtains accurate therapeutic scheme, expects that targetedly treatment recommendations are only capable of the mode that hospital is seeked advice from, of the invention
The technical solution combines the risk profile that user needs, treatment recommendations, warning, quick search, health account together, user
The present situation severity that itself can independently be inquired, obtain include the contents such as dietary recommendation, exercise suggestion, medication suggestion recommendation
Scheme and prompting including suggestion from procuratorial organ, and the stage situation of user is recorded in electronic record, is convenient for doctor or user
The progression of the disease that solution fluctuates at any time, conducive to the treatment and science control to the state of an illness.Based on FAQ retrieval technique, user can be with
Oneself relevant FAQs of inquiry diabetes, adequately understands diabetes, carries out user easily targetedly
Self-management reduces the risk of diabetic complication, reduces the disease incidence of diabetes.
Detailed description of the invention
Specific embodiments of the present invention will be described in further detail with reference to the accompanying drawing;
Fig. 1 shows the flow chart of diabetes risk grade prediction technique provided in an embodiment of the present invention.
Fig. 2 shows the schematic diagrames of Diabetes Mellitus Knowledge map.
Fig. 3 shows the structural schematic diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
In order to illustrate more clearly of the present invention, the present invention is done further below with reference to preferred embodiments and drawings
It is bright.Similar component is indicated in attached drawing with identical appended drawing reference.It will be appreciated by those skilled in the art that institute is specific below
The content of description is illustrative and be not restrictive, and should not be limited the scope of the invention with this.
Knowledge mapping is a kind of knowledge base of graph structure, belongs to the scope of knowledge engineering.Different from general knowledge library, knowledge
Map merges all subjects, and the blocks of knowledge of separate sources, different type, different structure is associated to figure by link, is based on
The metadata of each subject provides more range, the knowledge hierarchy of more depth for user and constantly expands.It is substantially to know field
Know data system, relativization, and by Knowledge Visualization in a manner of scheming.In simple terms, knowledge mapping is based on information system
The knowledge hierarchy of foundation, by technologies such as data acquisition, data mining, information processing, knowledge measure and graphic plottings complicated
Ken systematically show, disclose ken active development rule.
As shown in Figure 1, An embodiment provides a kind of prediction technique of diabetes risk, this method by
One or more of the computer program of device load store in memory is managed to execute, include the following steps:
S1, acquisition multi-source heterogeneous data relevant to diabetes, and entity, the entity are extracted from multi-source heterogeneous data
Attribute information and each entity between relation information;
The relation information between entity, the entity attributes information and each entity that S2, basis extract, constructs glycosuria
Sick knowledge mapping;
S3, the parameter group for receiving one or more parameter compositions related with diabetes, and it is based on the Diabetes Mellitus Knowledge
Map obtains and output diabetes risk corresponding with parameter group.
Method provided in this embodiment, it is pre- that the Diabetes Mellitus Knowledge map by merging multi-source heterogeneous data building carries out risk
It surveys, as shown in Fig. 2, diabetes risk forecast ratings can be provided accurately, and then Health & Fitness Tip with strong points, Yong Huke can be provided
Self monitor and scientific management are carried out using diabetic condition of the computer equipment for itself, reduces diabetic complication
Risk reduces the disease incidence of diabetes.Application value with higher.
In some embodiments, the source of the multi-source heterogeneous data includes internet, books, at least two in case history
Person.
For example, the internet can be various medical question and answer websites, these websites are answered by medical professional and are used
The medical problem that family proposes, such as DingXiangYuan, good doctor is online, seeks medical advice and medicine.
For example, books can be the various practice guidelines of hard copy printing or electronization, doctor's desk handbook etc..
For example, case history, which can be hand-written case history, is also possible to electronic health record.
In embodiment of the disclosure, diabetes risk can both be evaluated as non-quantized statement side such as high, medium and low
Formula can also be expressed as the grade form of presentation of the quantizations such as 5,4,3,2,1.It is commented for the ease of user's understanding and doctor etc.
Estimate, in some embodiments, the diabetes risk includes the diabetes risk grade of quantization.
In embodiment of the disclosure, it is readily appreciated that, parameter group is by one or more parameter structures related with diabetes
At combination, the value of these parameters is exported into computer equipment by user so that computer equipment receives the parameter
Group.
In embodiment of the disclosure, the specific implementation of so-called " reception " corresponds to user and uses the computer equipment
Mode.For example, user uses keyboard to computer equipment input data, then computer equipment receives the data that user is inputted;
For example, passing through mouse on application program gui interface of the user by the prediction technique for executing diabetes risk in computer equipment
It clicks, the modes input data such as keyboard operation, then computer equipment captures these operations to receive the data that user is inputted;
For example, user's input data by way of voice, then the method reception user institute that computer equipment turns text by voice is defeated
The data entered;For example, user can also be located at different location with computer equipment, if user uses mobile phone terminal App, and computer
Equipment is located at the server in cloud, then computer equipment can receive user institute by interacting with terminal device used by a user
The data of input.
In some optional implementations of the present embodiment, this method further include: according to the Diabetes Mellitus Knowledge map
With the diabetes risk, advisory information is exported.This implementation can also provide phase while providing diabetes risk prediction
The Health & Fitness Tip answered carries out targetedly self-management convenient for user.
For example, the advisory information includes: that dietary recommendation information, exercise suggestion information, medication advisory information and inspection are built
Discuss at least one of information.This implementation may make user obtain for itself diabetes prediction case dietary recommendation,
The suggested designs of contents such as exercise suggestion, medication suggestion and the prompting including suggestion from procuratorial organ carry out targetedly complete convenient for user
Face self-management.
In some optional implementations of the present embodiment, this method further include: store the parameter group and and parameter
The corresponding diabetes risk of group.This implementation understands the progression of the disease fluctuated at any time convenient for doctor or user, is conducive to disease
The treatment and science control of feelings.
In some optional implementations of the present embodiment, this method further include: according to the parameter group and correspondence of storage
Diabetes risk generate and output parameter group-diabetes risk curve.This implementation can more intuitively be convenient for doctor or use
Family accurately understands the progression of the disease fluctuated at any time, conducive to the treatment and science control to the state of an illness.
Be readily appreciated that, user to the parameter group that computer equipment inputs may be incomplete.In response to this problem, some
In embodiment, in response to lacking at least one parameter in the parameter group, the inquiry of at least one parameter to lacking in is exported
Information.So that user inputs lacked parameter according to the prompt of inquiry message.
In further embodiments, in response to lacking at least one parameter in the parameter group, known based on the diabetes
Know the parameter in map in another parameter group corresponding with the parameter having in the parameter group obtain lacking at least one
Parameter.For example, user input parameter group A should include a1, a2, a3, but lack input parameter a3, retrieval have with parameter a1,
A2 has same or approximation parameters parameter group B, and (including b1, b2, b3, wherein b1, b2 and a1, a2 have same or approximate
Value) in parameter b3 value of the value as a3.The computer equipment is allowed to lack the feelings of part input parameter in user
Auto-complete under condition.
In some embodiments of the present disclosure, obtained by machine learning model based on the Diabetes Mellitus Knowledge map and defeated
Diabetes risk corresponding with parameter group out.
For example, the machine learning model is SVM-GLM model.
It will be understood by those skilled in the art that other machine learning models for executing classification can also be used to execute
The above process, such as Softmax classifier.
In some optional implementations of the present embodiment, this method further include: by sample data set to the machine
Device learning model is trained, and the sample data concentrates the parameter group sample including multiple groups parameter composition related with diabetes
Diabetes risk mark corresponding with the parameter group sample of parameter related with diabetes composition.
For example, sample data concentrate, parameter group may include following parameter: for 24 hours in fasting blood-glucose with postprandial two hours
Blood sugar detection value, glucose tolerance value, glycosylated hemoglobin value, the mean value of urine sugar value, diabetes risk mark is arranged by doctor
Out in electronic medical records patient's severity risk profile tag along sort value (5 be most serious, is analogized in this order, and 1 is slight),
It is trained using SVM-GLM model.
In some optional implementations of the present embodiment, this method further include: from the multi-source heterogeneous data
A kind of data of data source construct the problem-answer corpus related with diabetes, include that multiple problems-are answered in the corpus
Case pair;The problem related with diabetes is received, answer corresponding with described problem is obtained based on the corpus.This implementation
The answer that the FAQs of user's input can quickly and accurately be provided a user, the relevant knowledge of diabetes is obtained convenient for user,
Diabetes are adequately understood.
In some embodiments, due to the medicine question and answer website on internet data structure be ask-answer mode, using come
Derived from internet acquisition and the relevant data of diabetes construct the problem-answer corpus related with diabetes.
In some optional implementations of the present embodiment, this method further include: obtained by neural network neural network
In the corpus with it is received the problem of there is the problem of high similarity, and will high similarity problem be corresponding answers with this
Case as it is received the problem of answer.
For example, neural network used can be twin neural network or pseudo- twin neural network.
The method that the above embodiment of the present invention provides can realize that therefore, the present invention is provided by computer program
A kind of computer equipment, on a memory and the computer that can run on a processor including memory, processor and storage
Program, the processor realize the above method when executing described program.
Wherein, processor can be central processing unit (CPU), Field Programmable Logic Array (FPGA), single-chip microcontroller
(MCU), there is data-handling capacity and/or program to execute energy for digital signal processor (DSP), specific integrated circuit (ASIC) etc.
The logical operation device of power.Memory includes but is not limited to such as volatile memory and/or nonvolatile memory.It is described easy
The property lost memory for example may include random access memory (RAM) and/or cache memory (Cache) etc..It is described non-
Volatile memory for example may include read-only memory (ROM), hard disk, flash memory etc..
Computer equipment provided in this embodiment, the Diabetes Mellitus Knowledge map by merging multi-source heterogeneous data building carry out
Risk profile can provide diabetes risk prediction, and then can provide Health & Fitness Tip with strong points, and user is using the computer
Equipment carries out self monitor and scientific management for the diabetic condition of itself, reduces the risk of diabetic complication, reduces sugar
Urinate the disease incidence of disease.Computer equipment application value with higher.
The present invention also provides a kind of computer systems, computer equipment and terminal device including above-described embodiment, institute
Terminal equipment configuration is stated into the parameter group formed to the one or more parameters related with diabetes of computer equipment input
And receive the diabetes risk of the computer equipment output.
Wherein, the terminal can be mobile phone, tablet computer, laptop, PC etc. with information input energy
The device of power.Terminal can show after the diabetes risk for receiving computer equipment output by screen, voice output etc. just
Formula informs user.
Wherein, terminal can in several ways with computer equipment communication connection.For example, wired side such as cable, optical fiber
The mode of the wireless wide area networks such as the wireless local areas such as formula or Wi-Fi, bluetooth, Zigbee net mode or 3G, 4G, 5G.
It is as follows, this application provides a specific example, the diabetes that computer equipment provided in this embodiment is realized
Risk Forecast Method is realized based on Python, realizes various functions by function call.
The data source for constructing Diabetes Mellitus Knowledge figure includes network data, electronic book data, electronic health record three parts
Data.Wherein, network data can utilize crawler technology, grab long-range data using urllib function in Python and protected
It deposits, Beautiful Soup frame is recycled to extract the content for needing to extract in HTML and XML tag and preservation, wherein
Urllib and Beautiful Soup is two functions that crawler is realized in python, belongs to the realization operation in engineering;For
Editable electronic book data and electronic medical records data, then using two-way shot and long term memory network condition of contact random field
BiLSTM-CRF is named Entity recognition, then carries out Relation extraction using BootStrapping, wherein can pass through operation
BiLSTM-CRF model code carries out Entity recognition to the electronic book data and electronic medical records data not marked and extracts disease
Classification, symptom classification check the information such as classification, drug classification as each entity dictionary, for containing at least two the language of entity
Sentence carries out Relation extraction for example for " the characteristics of type 1 diabetes is general more hurried, mouth of falling ill using BootStrapping
Yearningly, mostly drink, diuresis, more foods and syntexis out of strength ".Based on extracted entity dictionary, entity pair, including " 1 can be identified
Patients with type Ⅰ DM " can set 5 seeds with " hurried, thirsty, more drinks, diuresis, more foods and syntexis out of strength compared with morbidity is general "
It is exactly entity pair, then can extract template " the characteristics of be ", by the entity pair of other sentences of the template extraction, then by newly extracting
Entity is iterated to new template is extracted until extracting the enough relationships of quantity, that is, " disease-shows as-disease to triple
Shape ".Finally, because data source is in network, electronic health record and e-book, so different knowledge bases is established respectively, this
When need to carry out entity alignment, that is, consistent information only retains the high part of source quality, does not have in other knowledge bases
Information is directly added into fusion, this example utilizes three using integration disambiguation is carried out using entity alignment schemes to multi-source heterogeneous data
Tuple saves these knowledge in knowledge base, such as: disease-shows as-symptom, that is, type 1 diabetes-show as-fall ill
It is general more hurried, thirsty, more drinks, diuresis, more foods and syntexis out of strength, to form the unified knowledge base of high quality.
After forming knowledge base, different types of information all in knowledge base are linked together using knowledge mapping and are obtained
One relational network, from the angle analysis problem of " relationship ".Traditional search engines are based on keyword search, and knowledge mapping is available
Preferably to inquire complicated related information, improvement search quality.The efficiency of correlation inquiry is significantly improved than traditional approach.Glycosuria
Relationship in sick knowledge mapping between entity has symptom, inspection, drug, complication, site of pathological change, disease time etc., such as pregnant
Relationship between phase diabetes of being pregnent and macrosomia the two entities is complication.It is constructed using NOSQL graphic data base Neo4j
Diabetes Mellitus Knowledge map is allowed to the logical construction ability for having knowledge reasoning, specifically, form format is previous step
Entity dictionary and triple are imported the graph data using the language Neo4j-import of Neo4j by the database of triple
Library.It can be preferably according to the Diabetes Mellitus Knowledge map of the relation information building between entity, entity attributes information and each entity
Understand semantic coverage domain, promotes the accuracy rate of search.It can be established for human-computer interaction question and answer that may be present in diabetes risk prediction
Fixed basis.
In a specific example, the suggested design including contents such as dietary recommendation, exercise suggestion, medication suggestions is not for
Same diabetes risk forecast ratings, the recommendation based on being customized of relationship of entity in Diabetes Mellitus Knowledge map.For example, drink
Food suggests being reasonable food set meal and natural conditioning product without side-effects that doctor defines, and lists corresponding blood glucose generation and refer to
Several and points for attention;Exercise suggestion can list the aerobic exercise of quantitative timing;Medication suggestion can be the therapeutic regimen that doctor defines.
Also, it is recommended to which scheme may also include the contents such as living habit suggestion, mental health managerial integration.Various suggestions in suggested design
Content can be selected in Diabetes Mellitus Knowledge map corresponding by doctor to solid plate, according to diabetes risk forecast ratings
It is recommended that provide suggested design.User can take the self-management behavior of science according to suggested design, improve sugared body balance,
It repairs insulin secretion, stabilizing blood sugar, reduce complication, to instruct patient's reasonable diet, movement and adjustment medication to provide science
Foundation.Similarly with the suggested design including contents such as dietary recommendation, exercise suggestion, medication suggestions, including suggestion from procuratorial organ
The relationship output also for different diabetes risk forecast ratings, based on entity in Diabetes Mellitus Knowledge map is reminded to customize
It reminds, the project that the needs that suggestion from procuratorial organ can define for doctor check and corresponding time, such as regular timing blood sugar monitoring, simultaneously
Do neurology department's inspection or urine ketone bodies inspection or hepatic and renal function inspection or funduscopy etc..
In a specific example, parameter value (the i.e. diabetes of diabetic in statistics available analysis electronic medical records data
Relevant inspection value), the parameter value of diabetic for example: fasting blood-glucose and postprandial two hours blood sugar detection values in 24 hours,
Glucose tolerance value, glycosylated hemoglobin value, mean value of urine sugar value etc..Using the parameter value of diabetic as training data,
In the electronic medical records that doctor is defined the coincident with severity degree of condition of patient risk profile tag along sort value (for example, 5 be most serious,
And so on, 1 is slight) label as training data using training data training SVM-GLM model utilizes SVM-GLM mould
Type provides the diabetes risk forecast ratings of user corresponding with the parameter value of user's input, for diabetes risk forecast ratings
The case where being 5, can remind user to go to hospital to see a doctor immediately, be that 1 or 2 can voluntarily adjust for diabetes risk forecast ratings
The case where can utilize training data training SVM-GLM mould based on diabetes risk forecast ratings output targetedly suggested design
Type is simultaneously provided for example defeated with the diabetes risk forecast ratings of the corresponding user of parameter value of user's input using SVM-GLM model
The training data entered are as follows: fasting blood-glucose and postprandial two hours blood sugar detection values, glucose tolerance value, HbAle egg in 24 hours
White value, the mean value of urine sugar value export as the diabetes risk forecast ratings of user corresponding with the parameter value that user inputs, can benefit
It is predicted with 4 support vector machines, is then obtained 4 predicted value input generalized linear model GLM models finally respectively
Value reduces error rate.After the completion of SVM-GLM model training, corresponding use can be obtained for the parameter value that user newly inputs
The diabetes risk forecast ratings at family.Wherein, not full-time in the parameter value of user's input, it on the one hand can be used to take turns question and answer more
Dialogic operation guides user's completion parameter value using Slot filling method, for example, user inputs inquiry after blood sugar detection value
Own situation can inquire other parameters value so that user inputs other parameters value;On the other hand, if user can not completion
Parameter value can be provided according to the average value of the other parameters value of the patient in electronic health record with identical blood sugar detection value
(in the case where data volume is sufficiently large, according to Gaussian Profile average value maximum probability), while can also prompt to calculate in the case of this
The parameter value that obtained user does not input is not sufficiently exact.
In a specific example, the interactive mode of question-response is realized using FAQ retrieval technique, data source is in acquisition
Network data relevant to diabetes in a large amount of FAQs and answer, can accordingly be checked by doctor.FAQs
For example with answer: " hello by doctor, I have the pregnancy period 30 weeks, goes inspection blood glucose empty stomach 6.01 today, postprandial two hours 8.68, asks for problem-Q
Ask that this is diabetes, want to beat insulin? " " you are good, this not can determine that diabetes, best periodic review, day for answer-A
It is excessive that normal dietary requirement is careful not to intake energy, prevents the generation of pregnancy period hyperglycemia.Gestational diabetes are to belong to diabetes
Specific type can cause macrosomia, miscarriage, hydramnion etc. if gestational period blood glucose is excessively high, it is proposed that strict glycemic control,
Weighing apparatus nutrition ".The information of such question-response is stored as knowledge, constructs QA corpus.Obtaining user's input
Question information after, answer information based on the output of FAQ retrieval technique is corresponding, such as pass through the problem of extraction (problem puts question to letter
Breath) feature calculation problem similarity, training is using Siamese network model to user's input problem and asking in corpus
Topic successively carries out semantic similarity analysis, answer corresponding to the higher problem of similarity is finally returned to user, wherein mention
Take feature word can be expressed as term vector using TF-IDF using after jieba participle;Then term vector is connected to two sentences
The vector of son indicates, inputs Siamese network model, and output is the similarity degree of two sentences (between 0-1);
After the completion of Siamese network model training, user inputs the sentence putd question to, knowledge base, that is, exportable immediate problem
Answer.This implementation solvable Diabetes Mellitus Knowledge, diabetes coherence check, diabetic diet nutrition treatment, diabetic
Proper exercise, the rational use of medicines, treating diabetes new development etc. the problem of, user can learn diabetes phase with quick search
Close knowledge.
In a specific example, parameter value and diabetes wind of the storage device by storage including users such as blood glucose, blood urines
The data such as dangerous forecast ratings, advisory information are stored in MongoDB database.MongoDB database is deposited based on distributed document
The database of storage has data representation abundant, index, and is similar to relational database, supports query language abundant.Simultaneously
MongoDB database has MapRedurce function, provide data analysis convenient for storage management these similar to JSON format data.
The health account for establishing user is equivalent in storage device, its role is to can comprehensively allow doctor or user understand user with
The progression of the disease of time fluctuation, conducive to the treatment and science control to the state of an illness.
To sum up, the Diabetes Mellitus Knowledge map that computer equipment provided in this embodiment is constructed by merging multi-source heterogeneous data
Risk profile is carried out, can accurately provide diabetes risk forecast ratings, and then Health & Fitness Tip with strong points can be provided, and store
Health account is formed, at the same time it can also which by FAQ retrieval and inquisition FAQs, realizing user can self monitor scientific management
Diabetes it is health management system arranged.Specifically, computer equipment provided in this embodiment is first with natural language processing skill
Art and crawler technology extract the data in multiple sources, and then construct Diabetes Mellitus Knowledge map, pass through simple human-computer interaction question and answer
The state of an illness situation and diabetes risk forecast ratings of user is obtained, recommends that there is targetedly health control side for user later
Case, including dietary therapy, kinesiatrics, drug therapy etc..Meanwhile inspection prompting is carried out according to the state of an illness of user, make user can
Self-monitoring of blood glucose, blood urine in time pay attention to the intervention of hypoglycemia.When the result that is checked every time user, completion parameter value pair
The main suit's information and diabetes risk forecast ratings of words also can be stored in health account, and user can check the essence of blood glucose at any time
Quasi- change procedure, and then can be appreciated that the time of inspection, for example, the user more stable for glycemic control, can measure one in one week
Secondary empty stomach and postprandial 2 hours blood glucose;User biggish for blood glucose fluctuation increases detection frequency according to the state of an illness, checks frequency by curing
Raw given analog value is simultaneously contained in Diabetes Mellitus Knowledge map, and as the one of variable reminded is checked, health account can also
It is referred to doctor's behaviours diagnoses and treatment.It carries out doing FAQ question and answer, some FAQs in addition, user can also input question information
Corresponding answer can be obtained, convenient for understanding the relevant knowledge of diabetes.The present embodiment practical value with higher.
As shown in figure 3, the computer system for being suitable for being used to realize computer equipment provided in this embodiment, including centre
It manages module (CPU), random visit can be loaded into according to the program being stored in read-only memory (ROM) or from storage section
It asks the program in memory (RAM) and executes various movements appropriate and processing.In RAM, it is also stored with computer system behaviour
Various programs and data needed for making.CPU, ROM and RAM are connected by bus by this.Input/input (I/O) interface also connects
It is connected to bus.
I/O interface is connected to lower component: the importation including keyboard, mouse etc.;Including such as liquid crystal display
And the output par, c of loudspeaker etc. (LCD) etc.;Storage section including hard disk etc.;And including such as LAN card, modulation /demodulation
The communications portion of the network interface card of device etc..Communications portion executes communication process via the network of such as internet.Driver
It is connected to I/O interface as needed.Detachable media, such as disk, CD, magneto-optic disk, semiconductor memory etc., according to need
It installs on a drive, in order to be mounted into storage section as needed from the computer program read thereon.
Particularly, according to the present embodiment, the process of flow chart description above may be implemented as computer software programs.Example
Such as, the present embodiment includes a kind of computer program product comprising the computer being tangibly embodied on computer-readable medium
Program, above-mentioned computer program include the program code for method shown in execution flow chart.In such embodiments, should
Computer program can be downloaded and installed from network by communications portion, and/or be mounted from detachable media.
Flow chart and schematic diagram in attached drawing, illustrate the system of the present embodiment, method and computer program product can
The architecture, function and operation being able to achieve.In this regard, each box in flow chart or schematic diagram can represent a mould
A part of block, program segment or code, a part of above-mentioned module, section or code include one or more for realizing rule
The executable instruction of fixed logic function.It should also be noted that in some implementations as replacements, function marked in the box
It can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated can actually be basic
It is performed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that
Each box and signal and/or the combination of the box in flow chart in schematic diagram and/or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Method of the invention can be used as program and be stored in medium, because another aspect of the invention provides a kind of non-
Volatile computer storage medium, which can be in above-described embodiment is wrapped in above-mentioned apparatus
The nonvolatile computer storage media contained, is also possible to individualism, deposits without the non-volatile computer in supplying terminal
Storage media.Above-mentioned nonvolatile computer storage media is stored with one or more program, when said one or multiple journeys
When sequence is executed by an equipment, so that above equipment executes diabetes risk prediction technique disclosed in this invention.
It should be noted that in the description of the present invention, the terms "include", "comprise" or its any other variant are intended to
Cover non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or setting
Standby intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in the process, method, article or apparatus that includes the element.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention for those of ordinary skill in the art on the basis of the above description can be with
It makes other variations or changes in different ways, all embodiments can not be exhaustive here, it is all to belong to the present invention
The obvious changes or variations extended out of technical solution still in the scope of protection of the present invention.
Claims (16)
1. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor executes one in following step when being configured to load the computer program
Or it is multiple:
Acquire multi-source heterogeneous data relevant to diabetes;
From the relation information extracted in the multi-source heterogeneous data between entity, the entity attributes information and each entity;
According to the relation information between entity, the entity attributes information and each entity extracted, Diabetes Mellitus Knowledge is constructed
Map;
The parameter group of one or more parameter compositions related with diabetes is received, and is obtained based on the Diabetes Mellitus Knowledge map
Diabetes risk corresponding with parameter group with output.
2. computer equipment according to claim 1, which is characterized in that the source of the multi-source heterogeneous data includes interconnection
Net, books, in case history both at least.
3. computer equipment according to claim 1, which is characterized in that the diabetes risk includes the diabetes of quantization
Risk class.
4. computer equipment according to claim 1, which is characterized in that the processor is configured to load the computer
It is executed when program: according to the Diabetes Mellitus Knowledge map and the diabetes risk, exporting advisory information.
5. computer equipment according to claim 4, which is characterized in that the advisory information include: dietary recommendation information,
At least one of exercise suggestion information, medication advisory information and suggestion from procuratorial organ information.
6. computer equipment according to claim 1, which is characterized in that the processor is configured to load the computer
It is executed when program: storing the parameter group and diabetes risk corresponding with parameter group.
7. computer equipment according to claim 6, which is characterized in that the processor is configured to load the computer
Execute when program: according to the parameter group of storage and corresponding diabetes risk generates and output parameter group-diabetes risk curve.
8. computer equipment according to claim 1, which is characterized in that the processor is configured to load the computer
It is executed when program: in response to lacking at least one parameter in the parameter group, exporting the inquiry of at least one parameter to lacking in
Ask information.
9. computer equipment according to claim 1, which is characterized in that the processor is configured to load the computer
Executed when program: in response to lacking at least one parameter in the parameter group, based in the Diabetes Mellitus Knowledge map with it is described
Parameter in the corresponding another parameter group of the parameter having in parameter group obtain lacking at least one parameter.
10. computer equipment according to claim 1, which is characterized in that the processor is configured to load the calculating
It is executed when machine program: the Diabetes Mellitus Knowledge map being based on by machine learning model and obtains and export sugar corresponding with parameter group
Urinate sick risk.
11. computer equipment according to claim 10, which is characterized in that the machine learning model is SVM-GLM mould
Type.
12. computer equipment according to claim 10, which is characterized in that the processor is configured to load the calculating
It executes when machine program: the machine learning model being trained by sample data set, it includes more that the sample data, which is concentrated,
The parameter group sample of group parameter composition related with diabetes and the parameter group sample of parameter related with diabetes composition are corresponding
Diabetes risk mark.
13. computer equipment according to claim 1, which is characterized in that the processor is configured to load the calculating
It is executed when machine program: constructing the problem-related with diabetes from the data of one of multi-source heterogeneous data data source and answer
Case corpus includes multiple problem-answers pair in the corpus;The problem related with diabetes is received, the corpus is based on
Library obtains answer corresponding with described problem.
14. computer equipment according to claim 13, which is characterized in that the processor is configured to load the calculating
Executed when machine program: by neural network neural network obtain in the corpus with it is received the problem of with high similarity
The problem of, and using answer corresponding with the high similarity problem as it is received the problem of answer.
15. a kind of computer system, including claim the 1-14 any computer equipment and terminal device, the terminal
Device configuration is at the parameter group and reception formed to the one or more parameters related with diabetes of computer equipment input
The diabetes risk of the computer equipment output.
16. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
One or more of following step is executed when being loaded by processor:
Acquire multi-source heterogeneous data relevant to diabetes
From the relation information extracted in the multi-source heterogeneous data between entity, the entity attributes information and each entity;
According to the relation information between entity, the entity attributes information and each entity extracted, Diabetes Mellitus Knowledge is constructed
Map;
The parameter group of one or more parameter compositions related with diabetes is received, and is obtained based on the Diabetes Mellitus Knowledge map
Diabetes risk corresponding with parameter group with output.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910587890.3A CN110289101A (en) | 2019-07-02 | 2019-07-02 | A kind of computer equipment, system and readable storage medium storing program for executing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910587890.3A CN110289101A (en) | 2019-07-02 | 2019-07-02 | A kind of computer equipment, system and readable storage medium storing program for executing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110289101A true CN110289101A (en) | 2019-09-27 |
Family
ID=68021606
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910587890.3A Pending CN110289101A (en) | 2019-07-02 | 2019-07-02 | A kind of computer equipment, system and readable storage medium storing program for executing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110289101A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111291554A (en) * | 2020-02-27 | 2020-06-16 | 京东方科技集团股份有限公司 | Labeling method, relation extracting method, storage medium, and computing device |
CN111341456A (en) * | 2020-02-21 | 2020-06-26 | 中南大学湘雅医院 | Method and device for generating diabetic foot knowledge map and readable storage medium |
CN111507827A (en) * | 2020-04-20 | 2020-08-07 | 上海商涌网络科技有限公司 | Health risk assessment method, terminal and computer storage medium |
CN111899867A (en) * | 2020-07-28 | 2020-11-06 | 四川大学华西医院 | Operation complication prediction and avoidance aid decision-making system based on deep learning |
CN112017740A (en) * | 2020-07-22 | 2020-12-01 | 厦门快商通科技股份有限公司 | Disease inference method, device, equipment and storage medium based on knowledge graph |
CN112185558A (en) * | 2020-09-22 | 2021-01-05 | 珠海中科先进技术研究院有限公司 | Mental health and rehabilitation evaluation method, device and medium based on deep learning |
CN113836924A (en) * | 2021-09-16 | 2021-12-24 | 东软集团股份有限公司 | Entity relationship extraction method and device, storage medium and electronic equipment |
CN114067940A (en) * | 2020-07-31 | 2022-02-18 | 京东方科技集团股份有限公司 | Health management method and storage medium |
CN114238598A (en) * | 2021-12-07 | 2022-03-25 | 北京妙医佳健康科技集团有限公司 | Question-answering system and labeling, auditing and model training method thereof |
CN114937501A (en) * | 2022-05-23 | 2022-08-23 | 上海迎智正能文化发展有限公司 | Mental health risk grade assessment system and method based on knowledge graph |
CN116860978A (en) * | 2023-08-31 | 2023-10-10 | 南京云创大数据科技股份有限公司 | Primary school Chinese personalized learning system based on knowledge graph and large model |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105892302A (en) * | 2016-05-31 | 2016-08-24 | 北京光年无限科技有限公司 | Intelligent robot-oriented smart home control method and intelligent robot-oriented smart home control system |
US20180082183A1 (en) * | 2011-02-22 | 2018-03-22 | Thomson Reuters Global Resources | Machine learning-based relationship association and related discovery and search engines |
CN108614885A (en) * | 2018-05-03 | 2018-10-02 | 杭州认识科技有限公司 | Knowledge mapping analysis method based on medical information and device |
CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
CN109346169A (en) * | 2018-10-17 | 2019-02-15 | 长沙瀚云信息科技有限公司 | A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium |
CN109543047A (en) * | 2018-11-21 | 2019-03-29 | 焦点科技股份有限公司 | A kind of knowledge mapping construction method based on medical field website |
CN109657918A (en) * | 2018-11-19 | 2019-04-19 | 平安科技(深圳)有限公司 | Method for prewarning risk, device and the computer equipment of association assessment object |
CN109669994A (en) * | 2018-12-21 | 2019-04-23 | 吉林大学 | A kind of construction method and system of health knowledge map |
CN109766445A (en) * | 2018-12-13 | 2019-05-17 | 平安科技(深圳)有限公司 | A kind of knowledge mapping construction method and data processing equipment |
CN109783484A (en) * | 2018-12-29 | 2019-05-21 | 北京航天云路有限公司 | The construction method and system of the data service platform of knowledge based map |
CN109887596A (en) * | 2019-02-18 | 2019-06-14 | 广州天鹏计算机科技有限公司 | Chronic obstructive disease of lung diagnostic method, device and the computer equipment of knowledge based map |
CN109886740A (en) * | 2019-01-31 | 2019-06-14 | 泰康保险集团股份有限公司 | Medical information consultation method, medical information counseling apparatus, storage medium |
CN109933653A (en) * | 2019-01-24 | 2019-06-25 | 平安科技(深圳)有限公司 | Question and answer querying method, system and the computer equipment of question answering system |
CN109949929A (en) * | 2019-03-19 | 2019-06-28 | 挂号网(杭州)科技有限公司 | A kind of assistant diagnosis system based on the extensive case history of deep learning |
-
2019
- 2019-07-02 CN CN201910587890.3A patent/CN110289101A/en active Pending
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180082183A1 (en) * | 2011-02-22 | 2018-03-22 | Thomson Reuters Global Resources | Machine learning-based relationship association and related discovery and search engines |
CN105892302A (en) * | 2016-05-31 | 2016-08-24 | 北京光年无限科技有限公司 | Intelligent robot-oriented smart home control method and intelligent robot-oriented smart home control system |
CN108614885A (en) * | 2018-05-03 | 2018-10-02 | 杭州认识科技有限公司 | Knowledge mapping analysis method based on medical information and device |
CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
CN109346169A (en) * | 2018-10-17 | 2019-02-15 | 长沙瀚云信息科技有限公司 | A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium |
CN109657918A (en) * | 2018-11-19 | 2019-04-19 | 平安科技(深圳)有限公司 | Method for prewarning risk, device and the computer equipment of association assessment object |
CN109543047A (en) * | 2018-11-21 | 2019-03-29 | 焦点科技股份有限公司 | A kind of knowledge mapping construction method based on medical field website |
CN109766445A (en) * | 2018-12-13 | 2019-05-17 | 平安科技(深圳)有限公司 | A kind of knowledge mapping construction method and data processing equipment |
CN109669994A (en) * | 2018-12-21 | 2019-04-23 | 吉林大学 | A kind of construction method and system of health knowledge map |
CN109783484A (en) * | 2018-12-29 | 2019-05-21 | 北京航天云路有限公司 | The construction method and system of the data service platform of knowledge based map |
CN109933653A (en) * | 2019-01-24 | 2019-06-25 | 平安科技(深圳)有限公司 | Question and answer querying method, system and the computer equipment of question answering system |
CN109886740A (en) * | 2019-01-31 | 2019-06-14 | 泰康保险集团股份有限公司 | Medical information consultation method, medical information counseling apparatus, storage medium |
CN109887596A (en) * | 2019-02-18 | 2019-06-14 | 广州天鹏计算机科技有限公司 | Chronic obstructive disease of lung diagnostic method, device and the computer equipment of knowledge based map |
CN109949929A (en) * | 2019-03-19 | 2019-06-28 | 挂号网(杭州)科技有限公司 | A kind of assistant diagnosis system based on the extensive case history of deep learning |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111341456A (en) * | 2020-02-21 | 2020-06-26 | 中南大学湘雅医院 | Method and device for generating diabetic foot knowledge map and readable storage medium |
CN111341456B (en) * | 2020-02-21 | 2024-02-23 | 中南大学湘雅医院 | Method and device for generating diabetic foot knowledge graph and readable storage medium |
CN111291554A (en) * | 2020-02-27 | 2020-06-16 | 京东方科技集团股份有限公司 | Labeling method, relation extracting method, storage medium, and computing device |
CN111291554B (en) * | 2020-02-27 | 2024-01-12 | 京东方科技集团股份有限公司 | Labeling method, relation extracting method, storage medium and arithmetic device |
CN111507827A (en) * | 2020-04-20 | 2020-08-07 | 上海商涌网络科技有限公司 | Health risk assessment method, terminal and computer storage medium |
CN112017740A (en) * | 2020-07-22 | 2020-12-01 | 厦门快商通科技股份有限公司 | Disease inference method, device, equipment and storage medium based on knowledge graph |
CN111899867B (en) * | 2020-07-28 | 2022-08-05 | 四川大学华西医院 | Operation complication prediction and avoidance aid decision-making system based on deep learning |
CN111899867A (en) * | 2020-07-28 | 2020-11-06 | 四川大学华西医院 | Operation complication prediction and avoidance aid decision-making system based on deep learning |
CN114067940A (en) * | 2020-07-31 | 2022-02-18 | 京东方科技集团股份有限公司 | Health management method and storage medium |
CN112185558A (en) * | 2020-09-22 | 2021-01-05 | 珠海中科先进技术研究院有限公司 | Mental health and rehabilitation evaluation method, device and medium based on deep learning |
CN113836924A (en) * | 2021-09-16 | 2021-12-24 | 东软集团股份有限公司 | Entity relationship extraction method and device, storage medium and electronic equipment |
CN114238598A (en) * | 2021-12-07 | 2022-03-25 | 北京妙医佳健康科技集团有限公司 | Question-answering system and labeling, auditing and model training method thereof |
CN114937501A (en) * | 2022-05-23 | 2022-08-23 | 上海迎智正能文化发展有限公司 | Mental health risk grade assessment system and method based on knowledge graph |
CN116860978A (en) * | 2023-08-31 | 2023-10-10 | 南京云创大数据科技股份有限公司 | Primary school Chinese personalized learning system based on knowledge graph and large model |
CN116860978B (en) * | 2023-08-31 | 2023-11-21 | 南京云创大数据科技股份有限公司 | Primary school Chinese personalized learning system based on knowledge graph and large model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110289101A (en) | A kind of computer equipment, system and readable storage medium storing program for executing | |
US11521751B2 (en) | Patient data visualization method and system for assisting decision making in chronic diseases | |
El-Sappagh et al. | A mobile health monitoring-and-treatment system based on integration of the SSN sensor ontology and the HL7 FHIR standard | |
Robertson et al. | Blood Glucose Prediction Using Artificial Neural Networks Trained with the AIDA Diabetes Simulator: A Proof‐of‐Concept Pilot Study | |
US20220198300A1 (en) | Question recommendation method, device and system, electronic device, and readable storage medium | |
Plougmann et al. | DiasNet—a diabetes advisory system for communication and education via the internet | |
Deutsch et al. | UTOPIA: a consultation system for visit-by-visit diabetes management | |
Peral et al. | An ontology-oriented architecture for dealing with heterogeneous data applied to telemedicine systems | |
CN108231146A (en) | A kind of medical records model building method, system and device based on deep learning | |
KR20210052122A (en) | System and method for providing user-customized food information service | |
Javed et al. | Artificial intelligence for cognitive health assessment: state-of-the-art, open challenges and future directions | |
KR102360651B1 (en) | System for providing personalized meal plan service for improving medical test result using medical record | |
RU2752792C1 (en) | System for supporting medical decision-making | |
Dunn et al. | Development of the Likelihood of Low Glucose (LLG) algorithm for evaluating risk of hypoglycemia: a new approach for using continuous glucose data to guide therapeutic decision making | |
Jia et al. | DKDR: An approach of knowledge graph and deep reinforcement learning for disease diagnosis | |
US20230255556A1 (en) | Biosensors and food logger systems for personalized health and self-care | |
Ai | Artificial Intelligence System for College Students’ Physical Fitness and Health Management Based on Physical Measurement Big Data | |
Sun et al. | A general fine-tuned transfer learning model for predicting clinical task acrossing diverse EHRs datasets | |
Zhu et al. | Application of a computerized decision support system to develop care strategies for elderly hemodialysis patients | |
CN117116462A (en) | Method, system and device for predicting glycosylated hemoglobin value | |
Jiang et al. | [Retracted] TCM Physical Health Management Training and Nursing Effect Evaluation Based on Digital Twin | |
Bellamy | What's Missing from Machine Learning for Medicine? New Methods for Causal Effect Estimation and Representation Learning from EHR Data | |
Eghbali-Zarch et al. | Application of machine learning in affordable and accessible insulin management for type 1 and 2 diabetes: A comprehensive review | |
Chauhan | A mobile platform for non-invasive diabetes screening | |
Oliver et al. | Introducing the BlendedICU dataset, the first harmonized, international intensive care dataset |
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 |