CN109065100A - A kind of personalized questionnaire intelligence of Chinese medicine health based on block chain generates and encryption system - Google Patents
A kind of personalized questionnaire intelligence of Chinese medicine health based on block chain generates and encryption system Download PDFInfo
- Publication number
- CN109065100A CN109065100A CN201810946386.3A CN201810946386A CN109065100A CN 109065100 A CN109065100 A CN 109065100A CN 201810946386 A CN201810946386 A CN 201810946386A CN 109065100 A CN109065100 A CN 109065100A
- Authority
- CN
- China
- Prior art keywords
- questionnaire
- user
- constitution
- topic
- matter
- 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
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Nutrition Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention discloses a kind of personalized questionnaire of Chinese medicine health based on block chain and intelligently generates and encryption system, belongs to Computer Science and Technology field.Present invention seek to address that computer automatically generates questionnaire and according to user option fast convergence to a certain constitutive character result, and health data of the user on multi-platform is attached using block chain, to obtaining the data the closest with user, more targetedly suggested design is provided for user according to these data.By healthy semantic knowledge map, entity and affective state relationship under each constitution of Attention-lstm model learning utilize VAE generation technique, and intelligence generates questionnaire image.After category generation questionnaire is filled in user, by establishing the random exam pool abstracting method sampled based on Gibbs, allows result to converge in stable constitution deduction state, carry out classification judgement to result is filled in.
Description
Technical field
The present invention relates to questionnaire survey fields, are a kind of personalized questionnaires of Chinese medicine health based on block chain specifically
Intelligence generates and encryption system.
Background technique
Prior art has Traditional Chinese Medicine Constitution Classification and decision table and doctor's clinical diagnosis.Substantially sentence although they can make
Disconnected, still, Traditional Chinese Medicine Constitution Classification and decision table main problem are that (1) questionnaire problem total amount is more, organize questionnaire time and effort consuming.(2)
All more than 5 topics, answer people is easy to make similar answer the topic of every kind of constitution.Doctor's clinical diagnosis then expends more hospital's money
Source is not suitable for a wide range of promote.By constructing healthy semantic knowledge map, the connection between topic is excavated, then generate by VAE
Model, automatically generates questionnaire content, and user by establishing Gibbs sampling rapidly converges to a certain stable constitution to result after answering
Judgement, to solve the above problems.
Knowledge mapping was defined as a kind of visualization image early in 1991.Researcher is using specific software to a large amount of
The reflection structure of knowledge and the data of development grain are automatically processed, and visual knowledge mapping is generated.By merging polynary number
According to being understood to inquiry content and integrate related data.
For middle acute hearing after proposition bit coin concept in 2009, the block chain technology of behind obtains extensive concern.Block chain
There is decentralization, be not necessarily to the features such as Fiduciary, is each provided with new technical side in every field such as finance, production, industry
Case.Using block chain, data sharing can be allowed to utilize and provide new thinking with effective protection privacy of user, progress product traceability.
Using block chain, health data of the user in different platform is carried out shared analysis, system can be allowed preferably to hold user
State provides the service more refined.
Summary of the invention
Object of the present invention is to be intended to provide a kind of personalized questionnaire of Chinese medicine health based on block chain intelligently generate and plus
Close system, by healthy semantic knowledge map, entity and affective state under each constitution of Attention-lstm model learning are closed
System, using VAE generation technique, intelligence generates questionnaire image.After category generation questionnaire is filled in user, it is based on by establishing
The random exam pool abstracting method of Gibbs sampling, allows result to converge in stable constitution deduction state, divides result is filled in
Class judgement, using block chain, links the data of each platform, equipment, is combined, and the health control clothes more refined are provided
Business.
To realize the above-mentioned technical purpose, The technical solution adopted by the invention is as follows:
A kind of personalized questionnaire of Chinese medicine health intelligently generation and encryption system, including server and clothes based on block chain
Questionnaire is sent to client by the client for device communication connection of being engaged in, server, and questionnaire answer is sent back to server by client, institute
Stating server includes,
Questionnaire Auto-Generation Tool is automatically generated according to exam pool data using topic model and healthy semantic knowledge map
The multi-modal questionnaire content that both pictures and texts are excellent；
User's classification of TCM constitution tool converges on stable constitution using the random exam pool abstracting method sampled based on gibbs
In deduction state, when receiving questionnaire answer, quickly classify to user's constitution using based on supporting vector machine model calculating；
Information pushing tool provides relevant information push according to user's constitution.
Further, further include the multi-platform data connection encrypting module of block chain, be used for each health equipment, platform
Data link together, a block is arranged in each equipment, platform, common to record user's diet, movement, work and rest, medical treatment note
The health data of the different dimensions such as record, encrypts user identity, and protection privacy of user simultaneously again can be strong using these people
Health data are analyzed.After data link each platform, to quickly extract the number with user-association in mass data
According to being analyzed and processed.
Further, the questionnaire Auto-Generation Tool pre-processes topic exam pool, is labeled to exam pool topic,
Utilize Attention-lstm model learning entity emotion relationship.Specifically include following two step:
Step1. the relationship (relation) of topic entity (entity) and emotion (sentiment) are marked；
Step2. corresponding entity emotion relationship under the various classification of TCM constitution of Attention-lstm model learning is utilized.
Further, questionnaire Auto-Generation Tool is based on Chinese medicine health and interest in diet, constructs healthy semantic knowledge figure
Spectrum is based on VAE generation technique, and intelligence generates questionnaire content and iamge description, process include:
Step1. data (recipe, food pharmacological property, effect, the constitution effects such as tcm health preserving health and interest in diet are collected
Deng)；
Step2. picture concerned, receipe data are arranged, generate model training data using picture materials as VAE,
Pass through neural metwork training encoder (Encoder)；
Step3. the average vector (mean vector) of initial data (entity picture) is calculated by the encoder of Step2
And standard deviation vector (standard deviation vector)；
Step4. latent variable (simple latent vector) is calculated on the basis of Step3, and passes through another mind
Through network training decoder (decoder)；
Step5. chain of entities is carried out to data such as the questionnaire datas and picture for completing tag along sort to refer to, excavate text and figure
Corresponding relationship between piece constructs information extraction system, obtains being associated between topic and topic；
Step6. according to the relationship of knowledge mapping, the VAE decoder that is obtained using Step4 according to the item content of selection from
It is dynamic to generate the multi-modal questionnaire content that both pictures and texts are excellent.
Further, it after user obtains questionnaire, fills in after returning to option, establishes the random exam pool sampled based on Gibbs and take out
Method is taken, quickly converges on result in stable constitution deduction state.Specific questionnaire topic generating process is as follows:
Step1. a kind of tcm constitution H is randomly choosed；
Step2. according to the entity of the somatotypes of selection and generation --- emotional relationship model accordingly selects the constitution class
An entity (entity) under not, and corresponding state emotion (sentiment) option X is generated, it is generated using VAE decoder
Corresponding entity state picture after user fills in rear questionnaire, calculates the posterior probability P (H | X) that the user belongs to the setting constitution
~Pt.
If posterior probability reaches a threshold value, benefit generates the different topics of same constitution with the aforedescribed process again, and again
Secondary calculating its posteriority probability P t+1, when | Pt+1-Pt | when < δ is sufficiently small, corresponding classification of TCM constitution, which is set, gives a biggish weight.
If posterior probability differs larger with threshold value, chooses other constitutions and re-execute above-mentioned process.When, answer amount is more than
Volume threshold value or prediction probability are more than probability threshold value, and stopping answers and provides final analysis as a result, the highest constitution of weighting weight
Classification results automatically generate an analysis result using double LSTM and diagnose as a result by combining user identity.
Further, the client sends URLConnect request, clothes to server by calling network to access kernel
Questionnaire is sent to user client by business device, and user's questionnaire answer is sent to server again by client.Questionnaire is sent to client
End loads the questionnaire page, obtains corresponding user option.
Further, user's constitution is divided into gentle matter, deficiency of vital energy matter, deficiency of yang matter, deficiency of Yin matter, phlegm by user's classification of TCM constitution tool
Wet matter, damp and hot matter, extravasated blood matter, obstruction of the circulation of vital energy matter, special official report matter, wherein gentle matter and other eight kinds of constitutions are mutual exclusion constitution.
Further, (1) each user need to take turns in client answer at least one, and wherein first round topic includes eight, remove
Each outer constitution of gentle matter has one of topic；
(2) result of last round of answer is inscribed identifier according to additional pumping to judge whether that pumping is needed to inscribe, needs which is extracted
The topic of constitution is inscribed if necessary to pumping, by each topic of the topic for extracting corresponding constitution, composition the second wheel topic；
(3) according to pre-set volume threshold value and probability threshold value, judge whether to terminate answer, if not reaching volume threshold
Value and probability threshold value, then continue to repeat the operation progress answer in (2) terminates if reaching volume threshold value and probability threshold value
Answer.
It can be seen from the above, system simulation normal users request, learns the connection between questionnaire data simultaneously by topic model
Knowledge mapping is constructed, essence material is trained to obtain the encoder and decoder parameters of VAE generation model, utilizes decoder root
Questionnaire graph-text content is automatically generated according to demand, questionnaire data is sent to server under the premise of guaranteeing reliability, benefit
With the Gibbs methods of sampling, classification results is allowed to rapidly converge to a certain constitution.System provides a set of based on user experience design
Front end interface system.This system automatically generates questionnaire topic according to user's speciality on the basis of based on humanized user experience,
And according to the user's choice, quickly judge user's classification of TCM constitution, it is flat from difference by the data link encryption technology of block chain
Platform, equipment obtain effectively believable health data, by the encryption technology of block chain, shield the direct pass of user and concrete behavior
Connection, and be that user recommends personalized recipe scheme using knowledge mapping, finer health data management service is provided.By
It has been linked together by block chain in user behavior, therefore, can quickly have been looked for from mass data by the record of block chain
To data associated with the user, to improve the effective use of data.
Detailed description of the invention
The present invention can be further illustrated by the nonlimiting examples that attached drawing provides；
Fig. 1 is the structural diagram of the present invention；
Fig. 2 is to automatically generate questionnaire illustraton of model；
Fig. 3 is the multi-platform data link structural schematic diagram of block chain；
Fig. 4 is the logic chart that the present invention judges answer person's somatotypes；
Specific embodiment
In order to make those skilled in the art that the present invention may be better understood, with reference to the accompanying drawings and examples to this hair
Bright technical solution further illustrates.
As shown in Figure 1-3, a kind of personalized questionnaire of Chinese medicine health based on block chain intelligently generates and encryption system, including
Questionnaire is sent to client by server, the client with server communication connection, server, and client sends back to questionnaire answer
To server, the server includes,
Questionnaire Auto-Generation Tool is automatically generated according to exam pool data using topic model and healthy semantic knowledge map
The multi-modal questionnaire content that both pictures and texts are excellent；
User's classification of TCM constitution tool converges on stable constitution using the random exam pool abstracting method sampled based on gibbs
In deduction state, when receiving questionnaire answer, quickly classify to user's constitution using based on supporting vector machine model calculating；
Information pushing tool provides relevant information push according to user's constitution.
Further, further include the multi-platform data connection encrypting module of block chain, be used for each health equipment, platform
Data link together, a block is arranged in each equipment, platform, common to record user's diet, movement, work and rest, medical treatment note
The health data of the different dimensions such as record, encrypts user identity, and protection privacy of user simultaneously again can be strong using these people
Health data are analyzed.After data link each platform, to quickly extract the number with user-association in mass data
According to being analyzed and processed.
Further, the questionnaire Auto-Generation Tool pre-processes topic exam pool, is labeled to exam pool topic,
Utilize Attention-lstm model learning entity emotion relationship.Specifically include following two step:
Step1. the relationship (relation) of topic entity (entity) and emotion (sentiment) are marked；
Step2. corresponding entity emotion relationship under the various classification of TCM constitution of Attention-lstm model learning is utilized.
Further, questionnaire Auto-Generation Tool is based on Chinese medicine health and interest in diet, constructs healthy semantic knowledge figure
Spectrum is based on VAE generation technique, and intelligence generates questionnaire content and iamge description, process include:
Step1. data (recipe, food pharmacological property, effect, the constitution effects such as tcm health preserving health and interest in diet are collected
Deng)；
Step2. picture concerned, receipe data are arranged, generate model training data using picture materials as VAE,
Pass through neural metwork training encoder (Encoder)；
Step3. the average vector (mean vector) of initial data (entity picture) is calculated by the encoder of Step2
And standard deviation vector (standard deviation vector)；
Step4. latent variable (simple latent vector) is calculated on the basis of Step3, and passes through another mind
Through network training decoder (decoder)；
Step5. chain of entities is carried out to data such as the questionnaire datas and picture for completing tag along sort to refer to, excavate text and figure
Corresponding relationship between piece constructs information extraction system, obtains being associated between topic and topic；
Step6. according to the relationship of knowledge mapping, the VAE decoder that is obtained using Step4 according to the item content of selection from
It is dynamic to generate the multi-modal questionnaire content that both pictures and texts are excellent.
Further, it after user obtains questionnaire, fills in after returning to option, establishes the random exam pool sampled based on Gibbs and take out
Method is taken, quickly converges on result in stable constitution deduction state.Specific questionnaire topic generating process is as follows:
Step1. a kind of tcm constitution H is randomly choosed；
Step2. according to the entity of the somatotypes of selection and generation --- emotional relationship model accordingly selects the constitution class
An entity (entity) under not, and corresponding state emotion (sentiment) option X is generated, it is generated using VAE decoder
Corresponding entity state picture after user fills in rear questionnaire, calculates the posterior probability P (H | X) that the user belongs to the setting constitution
~Pt.
If posterior probability reaches a threshold value, benefit generates the different topics of same constitution with the aforedescribed process again, and again
Secondary calculating its posteriority probability P t+1, when | Pt+1-Pt | when < δ is sufficiently small, corresponding classification of TCM constitution, which is set, gives a biggish weight.
If posterior probability differs larger with threshold value, chooses other constitutions and re-execute above-mentioned process.When, answer amount is more than
Volume threshold value or prediction probability are more than probability threshold value, and stopping answers and provides final analysis as a result, the highest constitution of weighting weight
Classification results automatically generate an analysis result using double LSTM and diagnose as a result by combining user identity.
Further, the client sends URLConnect request, clothes to server by calling network to access kernel
Questionnaire is sent to user client by business device, and user's questionnaire answer is sent to server again by client.Questionnaire is sent to client
End loads the questionnaire page, obtains corresponding user option.
Further, user's constitution is divided into gentle matter, deficiency of vital energy matter, deficiency of yang matter, deficiency of Yin matter, phlegm by user's classification of TCM constitution tool
Wet matter, damp and hot matter, extravasated blood matter, obstruction of the circulation of vital energy matter, special official report matter, wherein gentle matter and other eight kinds of constitutions are mutual exclusion constitution.
Further, (1) each user need to take turns in client answer at least one, and wherein first round topic includes eight, remove
Each outer constitution of gentle matter has one of topic；
(2) result of last round of answer is inscribed identifier according to additional pumping to judge whether that pumping is needed to inscribe, needs which is extracted
The topic of constitution is inscribed if necessary to pumping, by each topic of the topic for extracting corresponding constitution, composition the second wheel topic；
(3) according to pre-set volume threshold value and probability threshold value, judge whether to terminate answer, if not reaching volume threshold
Value and probability threshold value, then continue to repeat the operation progress answer in (2) terminates if reaching volume threshold value and probability threshold value
Answer.
In the intelligent questionnaire of tcm constitution, answer person need according to the topic minute wheels time of eight kinds of constitutions (except gentle matter) into
Row answer.Wherein, eight kinds of constitutions of the meaning of the topic of gentle matter and other in this questionnaire on the contrary, do not set a question individually.Then root
It is analyzed according to the answer result of this wheel, to start the answer of next round.The volume of one wheel is between one to eight.
As shown in figure 4, specific practice is:
(1) questionnaire problem data library is formed from 66 problems for surveying table by " Traditional Chinese Medicine Constitution Classification and judgement ", passes through theme mould
Type and knowledge mapping excavate the connection between topic.
(2) it when questionnaire generates, automatically generates all types of topics and is tested to user, form eight problems of the first round.By answering
Topic person answers.Exam pool removes eight problems answered.
(3) according to the topic of the first round as a result, the somatotypes of the logic prediction answer person according to Fig. 2.And prediction is tied
Fruit updates to somatotypes count of predictions device, i.e. table one.
(4) in exam pool, the topic of topic composition the second wheel answer is respectively extracted according to the somatotypes of prediction.
(5) the answer result of the wheel of answer person second is obtained.According to the somatotypes of Fig. 2 prediction user, and update table one
Data.
(6) according to pre-set volume threshold value and probability threshold value, judge whether to terminate answer.If not terminating answer by
Start the answer of a new round according to the 3rd, 4,5 step.Wherein, the condition for terminating answer is that answer amount is more than volume threshold value, and prediction is general
Rate is more than probability threshold value.Note that there are mutex relations for gentle matter and other eight kinds of constitutions, prediction knot can't be appeared in together
Fruit, the adjustment for the result that need to give a forecast.
Table one
| Gentle matter | Deficiency of vital energy matter | Deficiency of yang matter | Deficiency of Yin matter | Phlegm wet matter | Damp and hot matter | Hemostasis matter | Obstruction of the circulation of vital energy matter | Spy reports matter | |
| It is | |||||||||
| Tendency is |
Answer person's somatotypes is predicted in Fig. 2 method particularly includes:
By each four options of topic following settings, each option is respectively 1,2,3,4 point, and answer person is according to oneself feelings
Condition judges that the topic oneself reaches rather, and more similar score is higher.
In first round answer, if answer result has greater than 3, the quantity of "Yes" adds in the counter of corresponding constitution
One, gentle matter identifier is False, and additionally pumping topic identifier is True to epicycle, and is 3 answer result in this answer,
The quantity of " tendency is " adds one in the counter of corresponding somatotypes；If fruit answer result is all less than 3, gentle matter mark
Symbol is True, and additionally pumping topic identifier is False to epicycle；Remaining situation, then additionally pumping topic identifier is True to epicycle.
Then identifier is inscribed according to additional pumping and judges whether to pumping topic, when identifier is False, terminated answer, obtain
Gentle matter conclusion out；When identifier is True, additional pumping topic is carried out, the somatotypes of additional pumping topic is upper wheel answer answer knot
Fruit is the somatotypes except 3, judges whether the somatotypes quantity of additional pumping topic is 0.
If being equal to 0, the quantity of "Yes" adds one in counter, and the identifier of " gentle matter " is True, terminates answer.Such as
Fruit is not equal to 0, carries out additional pumping topic, and judges that the somatotypes quantity of additional pumping topic is less than 8 and is also equal to 8, if it is less than
8, if being all 3 in the epicycle topic answer that additionally pumping is inscribed, the quantity of " tendency is " adds one in " gentle matter " counter, " gentle
The identifier of matter " is True；If being equal to 8, the maximum value of the classification processing answer that additionally pumping is inscribed, when less than 3, " gentle matter " is counted
The quantity of "Yes" adds one in number device, and the identifier of " gentle matter " is True；Equal to 3, in " gentle matter " counter " tendency is "
Quantity adds one, and the identifier of " gentle matter " is True；The quantity of "Yes" adds in the counter of somatotypes of the answer result greater than 3
One, and the somatotypes is added in the queue of next pumping topic, it is False the identifier of " gentle matter ".
A kind of personalized questionnaire intelligence of Chinese medicine health based on block chain provided by the invention is generated above and is with encryption
System is described in detail.The explanation of specific embodiment is merely used to help understand method and its core concept of the invention.It answers
It, for those skilled in the art, without departing from the principle of the present invention, can also be to this when pointing out
Some improvement and modification can also be carried out for invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.
Claims (7)
1. a kind of personalized questionnaire of Chinese medicine health based on block chain intelligently generates and encryption system, it is characterised in that: including clothes
Questionnaire is sent to client by the client for device and the server communication connection of being engaged in, server, and questionnaire answer is sent back to by client
Server, the server include,
Questionnaire Auto-Generation Tool automatically generates picture and text using topic model and healthy semantic knowledge map according to exam pool data
And the multi-modal questionnaire content of cyclopentadienyl；
User's classification of TCM constitution tool is converged on stable constitution and inferred using the random exam pool abstracting method sampled based on gibbs
In state, when receiving questionnaire answer, quickly classify to user's constitution using based on supporting vector machine model calculating；
Information pushing tool provides relevant information push according to user's constitution.
2. a kind of personalized questionnaire of Chinese medicine health based on block chain according to claim 1 is intelligently generated is with encryption
System, it is characterised in that: further include the multi-platform data connection encrypting module of block chain, for by each health equipment, platform
Together, a block, the common health data for recording different dimensions is arranged in each equipment, platform to data link.
3. a kind of personalized questionnaire of Chinese medicine health based on block chain according to claim 1 is intelligently generated is with encryption
System, it is characterised in that: the questionnaire Auto-Generation Tool pre-processes topic exam pool, is labeled to exam pool topic, benefit
With Attention-lstm model learning entity emotion relationship.
4. a kind of personalized questionnaire of Chinese medicine health based on block chain according to claim 3 is intelligently generated is with encryption
System, it is characterised in that: questionnaire Auto-Generation Tool is based on Chinese medicine health and interest in diet, constructs healthy semantic knowledge map,
Based on VAE generation technique, intelligence generates questionnaire content and iamge description, process include:
(1) tcm health preserving health and interest in diet data are collected；
(2) picture concerned, receipe data are arranged, generates model training data using picture materials as VAE, passes through nerve
Network training encoder；
(3) average vector and standard deviation vector of initial data are calculated by the encoder in (2).
(4) latent variable is calculated on the basis of (3), and passes through another neural metwork training decoder；
(5) chain of entities is carried out to data such as the questionnaire datas and picture for completing tag along sort to refer to, excavate between text and picture
Corresponding relationship, construct information extraction system, obtain being associated between topic and topic；
(6) according to the relationship of knowledge mapping, the VAE decoder for utilizing (4) to obtain automatically generates figure according to the item content of selection
The multi-modal questionnaire content of Wen Bingmao.
5. a kind of personalized questionnaire of Chinese medicine health based on block chain according to claim 1 is intelligently generated is with encryption
System, it is characterised in that: the client sends URLConnect request, server to server by calling network to access kernel
Questionnaire is sent to user client, user's questionnaire answer is sent to server again by client.
6. a kind of personalized questionnaire of Chinese medicine health based on block chain according to claim 1 is intelligently generated is with encryption
System, it is characterised in that: user's constitution is divided into gentle matter, deficiency of vital energy matter, deficiency of yang matter, deficiency of Yin matter, phlegm wet by user's classification of TCM constitution tool
Matter, damp and hot matter, extravasated blood matter, obstruction of the circulation of vital energy matter, special official report matter, wherein gentle matter and other eight kinds of constitutions are mutual exclusion constitution.
7. a kind of personalized questionnaire of Chinese medicine health based on block chain according to claim 4 is intelligently generated is with encryption
System, it is characterised in that: (1) each user need to take turns in client answer at least one, and wherein first round topic includes eight, except gentle
Each outer constitution of matter has one of topic；
(2) result of last round of answer is inscribed into identifier according to additional pumping and judges whether that pumping is needed to inscribe which constitution needed to extract
Topic, if necessary to pumping inscribe, by the topic for extracting corresponding constitution it is each one topic, composition second wheel topic；
(3) according to pre-set volume threshold value and probability threshold value, judge whether to terminate answer, if do not reach volume threshold value and
Probability threshold value, then continuing to repeat the operation progress answer in (2) terminates answer if reaching volume threshold value and probability threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810946386.3A CN109065100A (en) | 2018-08-20 | 2018-08-20 | A kind of personalized questionnaire intelligence of Chinese medicine health based on block chain generates and encryption system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810946386.3A CN109065100A (en) | 2018-08-20 | 2018-08-20 | A kind of personalized questionnaire intelligence of Chinese medicine health based on block chain generates and encryption system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109065100A true CN109065100A (en) | 2018-12-21 |
Family
ID=64686523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810946386.3A Pending CN109065100A (en) | 2018-08-20 | 2018-08-20 | A kind of personalized questionnaire intelligence of Chinese medicine health based on block chain generates and encryption system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109065100A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919196A (en) * | 2019-02-01 | 2019-06-21 | 华南理工大学 | A kind of constitution recognition methods based on feature selecting and disaggregated model |
| CN110503202A (en) * | 2019-08-22 | 2019-11-26 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN110782308A (en) * | 2019-09-20 | 2020-02-11 | 北京三快在线科技有限公司 | Pushing method and device for recommended package, electronic equipment and readable storage medium |
| CN111354469A (en) * | 2020-03-31 | 2020-06-30 | 浙江禾连网络科技有限公司 | User health condition comprehensive evaluation method and system |
| CN111753021A (en) * | 2020-06-17 | 2020-10-09 | 第四范式（北京）技术有限公司 | Method, device and equipment for constructing knowledge graph and readable storage medium |
| CN111797100A (en) * | 2020-07-03 | 2020-10-20 | 上海华客信息科技有限公司 | Model training method and device, questionnaire pushing method and device, equipment and medium |
| CN112019486A (en) * | 2019-05-31 | 2020-12-01 | 中国移动通信集团浙江有限公司 | Data association method and device based on block chain and computing equipment |
| CN112530598A (en) * | 2020-12-11 | 2021-03-19 | 万达信息股份有限公司 | Health risk self-measurement table recommendation method and system based on health data |
| CN112992295A (en) * | 2019-12-13 | 2021-06-18 | 韩美营销集团 | Method and device for providing personalized information for diabetic pregnant women |
| WO2021185041A1 (en) * | 2020-03-19 | 2021-09-23 | 深圳数字生命研究院 | Method and apparatus for processing questionnaire information, storage medium, and electronic apparatus |
| CN115828285A (en) * | 2022-12-20 | 2023-03-21 | 人民卫生电子音像出版社有限公司 | Encryption and decryption tool system based on medical examination questions |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014150214A2 (en) * | 2013-03-15 | 2014-09-25 | Google Inc. | Questions answering to populate knowledge base |
| CN104217038A (en) * | 2014-09-30 | 2014-12-17 | 中国科学技术大学 | Knowledge network building method for financial news |
| CN106776711A (en) * | 2016-11-14 | 2017-05-31 | 浙江大学 | A kind of Chinese medical knowledge mapping construction method based on deep learning |
| CN107748757A (en) * | 2017-09-21 | 2018-03-02 | 北京航空航天大学 | A kind of answering method of knowledge based collection of illustrative plates |
-
2018
- 2018-08-20 CN CN201810946386.3A patent/CN109065100A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014150214A2 (en) * | 2013-03-15 | 2014-09-25 | Google Inc. | Questions answering to populate knowledge base |
| CN104217038A (en) * | 2014-09-30 | 2014-12-17 | 中国科学技术大学 | Knowledge network building method for financial news |
| CN106776711A (en) * | 2016-11-14 | 2017-05-31 | 浙江大学 | A kind of Chinese medical knowledge mapping construction method based on deep learning |
| CN107748757A (en) * | 2017-09-21 | 2018-03-02 | 北京航空航天大学 | A kind of answering method of knowledge based collection of illustrative plates |
Non-Patent Citations (2)
| Title |
|---|
| 陈恒: "基于知识图谱的问卷辅助生成系统", 《中国优秀硕士学位论文全文数据库》 * |
| 黄永刚: "基于区块链技术的电子健康档案安全建设", 《中华医学图书情报杂志》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919196B (en) * | 2019-02-01 | 2023-12-08 | 华南理工大学 | Physique identification method based on feature selection and classification model |
| CN109919196A (en) * | 2019-02-01 | 2019-06-21 | 华南理工大学 | A kind of constitution recognition methods based on feature selecting and disaggregated model |
| CN112019486B (en) * | 2019-05-31 | 2022-09-16 | 中国移动通信集团浙江有限公司 | Data association method and device based on block chain and computing equipment |
| CN112019486A (en) * | 2019-05-31 | 2020-12-01 | 中国移动通信集团浙江有限公司 | Data association method and device based on block chain and computing equipment |
| CN110503202A (en) * | 2019-08-22 | 2019-11-26 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN110782308A (en) * | 2019-09-20 | 2020-02-11 | 北京三快在线科技有限公司 | Pushing method and device for recommended package, electronic equipment and readable storage medium |
| CN112992295A (en) * | 2019-12-13 | 2021-06-18 | 韩美营销集团 | Method and device for providing personalized information for diabetic pregnant women |
| WO2021185041A1 (en) * | 2020-03-19 | 2021-09-23 | 深圳数字生命研究院 | Method and apparatus for processing questionnaire information, storage medium, and electronic apparatus |
| CN111354469A (en) * | 2020-03-31 | 2020-06-30 | 浙江禾连网络科技有限公司 | User health condition comprehensive evaluation method and system |
| CN111753021A (en) * | 2020-06-17 | 2020-10-09 | 第四范式（北京）技术有限公司 | Method, device and equipment for constructing knowledge graph and readable storage medium |
| CN111797100A (en) * | 2020-07-03 | 2020-10-20 | 上海华客信息科技有限公司 | Model training method and device, questionnaire pushing method and device, equipment and medium |
| CN112530598A (en) * | 2020-12-11 | 2021-03-19 | 万达信息股份有限公司 | Health risk self-measurement table recommendation method and system based on health data |
| CN112530598B (en) * | 2020-12-11 | 2023-07-25 | 万达信息股份有限公司 | Health risk self-measuring table recommendation method based on health data |
| CN115828285A (en) * | 2022-12-20 | 2023-03-21 | 人民卫生电子音像出版社有限公司 | Encryption and decryption tool system based on medical examination questions |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109065100A (en) | A kind of personalized questionnaire intelligence of Chinese medicine health based on block chain generates and encryption system | |
| DeYoung et al. | Ms2: Multi-document summarization of medical studies | |
| Liikkanen et al. | Inspiring design idea generation: insights from a memory-search perspective | |
| Alvarez et al. | Spatial ensemble statistics are efficient codes that can be represented with reduced attention | |
| Wardle et al. | Illusory faces are more likely to be perceived as male than female | |
| TW201939400A (en) | Method and device for determining group of target users | |
| Lin et al. | An integer programming approach and visual analysis for detecting hierarchical community structures in social networks | |
| Pillutla et al. | Iterative generation of insight from text collections through mutually reinforcing visualizations and fuzzy cognitive maps | |
| Huber et al. | Competition and moral behavior: A meta-analysis of forty-five crowd-sourced experimental designs | |
| Margolin et al. | The emotional antecedents of solidarity in social media crowds | |
| Brüns et al. | Show me that you are advertising: Visual salience of products attenuates detrimental effects of persuasion knowledge activation in influencer advertising | |
| Andy | Studying how individuals who express the feeling of loneliness in an online loneliness forum communicate in a nonloneliness forum: observational study | |
| Vivas et al. | Describing the structure of concepts through different feature levels | |
| Liu et al. | A reliable cross-site user generated content modeling method based on topic model | |
| Huang et al. | Social group modeling with probabilistic soft logic | |
| Liu et al. | The evolution of structural balance in time-varying signed networks | |
| Tian et al. | Exploring public attitudes toward live-streaming fitness in China: A sentiment and content analysis of China's social media Weibo | |
| Zhang et al. | Federated Markov Logic Network for indoor activity recognition in Internet of Things | |
| Pareek et al. | Modelling and Analysis of Prey-Predator Interaction on Spatio-temporal Dynamics: A Systematic | |
| Young et al. | Happy and unhappy adolescent bullies: Evidence for theoretically meaningful subgroups | |
| Wester et al. | Exploring People’s Perceptions of LLM-generated Advice | |
| Bhuiyan et al. | PRIIME: A generic framework for interactive personalized interesting pattern discovery | |
| Mitrović et al. | Patterns of emotional blogging and emergence of communities: Agent-based model on bipartite networks | |
| Chen et al. | A perceptual image prediction model of professional dress style based on PSO-BP neural network | |
| Wijeratne et al. | Emoji Understanding and applications in social media: lay of the land and special issue introduction |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |
|
| RJ01 | Rejection of invention patent application after publication |