CN112489769A - Intelligent traditional Chinese medicine diagnosis and medicine recommendation system for chronic diseases based on deep neural network - Google Patents
Intelligent traditional Chinese medicine diagnosis and medicine recommendation system for chronic diseases based on deep neural network Download PDFInfo
- Publication number
- CN112489769A CN112489769A CN201910776695.5A CN201910776695A CN112489769A CN 112489769 A CN112489769 A CN 112489769A CN 201910776695 A CN201910776695 A CN 201910776695A CN 112489769 A CN112489769 A CN 112489769A
- Authority
- CN
- China
- Prior art keywords
- medicine
- module
- neural network
- information
- deep neural
- 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.)
- Granted
Links
- 239000003814 drug Substances 0.000 title claims abstract description 138
- 238000003745 diagnosis Methods 0.000 title claims abstract description 29
- 208000017667 Chronic Disease Diseases 0.000 title claims abstract description 25
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 18
- 208000024891 symptom Diseases 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000003062 neural network model Methods 0.000 claims abstract description 32
- 201000010099 disease Diseases 0.000 claims abstract description 29
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 29
- 229940079593 drug Drugs 0.000 claims abstract description 23
- 239000013610 patient sample Substances 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 53
- 230000006870 function Effects 0.000 claims description 40
- 238000007781 pre-processing Methods 0.000 claims description 34
- 230000011218 segmentation Effects 0.000 claims description 33
- 238000011176 pooling Methods 0.000 claims description 28
- 239000000523 sample Substances 0.000 claims description 20
- 238000013527 convolutional neural network Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 17
- 230000004913 activation Effects 0.000 claims description 16
- 238000013079 data visualisation Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 11
- 230000000977 initiatory effect Effects 0.000 claims description 7
- 238000013500 data storage Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 238000011282 treatment Methods 0.000 abstract description 17
- 230000036541 health Effects 0.000 abstract description 9
- 238000004092 self-diagnosis Methods 0.000 abstract description 7
- 238000011369 optimal treatment Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 6
- 230000009849 deactivation Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000032683 aging Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001684 chronic effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/90—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to alternative medicines, e.g. homeopathy or oriental medicines
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Alternative & Traditional Medicine (AREA)
- Pharmacology & Pharmacy (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an intelligent chronic disease traditional Chinese medicine diagnosis and medicine recommendation system based on a deep neural network, which comprises a traditional Chinese medicine disease reading module, a diagnosis and medicine recommendation module and a control module, wherein the traditional Chinese medicine disease reading module is used for reading symptom information of a patient sample; the invention constructs a database module for storing symptom information of a patient sample and obtained medicine information; the traditional Chinese medicine disease reading module is used for reading the symptom information of the obtained patient sample, predicting the input information through a deep neural network model and obtaining the classification result of the related medicine to form prediction information; furthermore, medicines are recommended through the medicine recommendation module, intelligent traditional Chinese medicine diagnosis and medicine recommendation of chronic diseases are achieved, doctors are assisted in diagnosis and treatment, particularly, optimal treatment methods are provided for patients by the doctors, and cost is saved; the disease diagnosis accuracy rate can be improved, the death rate can be reduced, the hospital pressure can be relieved, and the like; the system helps patients with chronic diseases to realize self diagnosis and treatment to a certain extent, saves national medical resources and improves the health level of the whole population.
Description
Technical Field
The invention belongs to the technical field of intelligent medical treatment, and particularly relates to an intelligent traditional Chinese medicine diagnosis and medicine recommendation system for chronic diseases based on a deep neural network.
Background
The aging situation of the population in China is severe, the burden of the endowment guarantee is severe, the medical and health expense is increased, the demand of social endowment service is expanded due to the huge aging population, and the social development is deeply influenced. The health problems of the old people are prominent. On the other hand, the condition of the elderly patients with chronic diseases also puts a certain burden on their caregivers. There are studies that indicate that "most caregivers have varying degrees of economic, social, physiological and psychological burden". Therefore, the medical problem of the large and growing number of the elderly chronic disease groups is one of the problems which are not neglected in aging, brings great problems to the medical health service system of China, and is urgent to explore the content and mode of the elderly chronic disease service which meet the needs of China.
The traditional Chinese medicine has unique advantages and rich practical experience for preventing and treating the complications of the chronic diseases, and the concept of holistic concept and dialectical treatment has great significance for treatment and prognosis, prevention and treatment of the complications, improvement of life quality and the like. However, the development of Chinese medicine in China mainly faces three problems: the learning cost of the traditional Chinese medicine is high, and the inheritance difficulty is far higher than that of the western medicine; traditional Chinese medicine lacks a scientific theoretical system like western medicine; the number of the traditional Chinese medical institutions is small, and the resources of doctors are deficient. Artificial intelligence technology creates social value by researching or manufacturing systems or machines with human intelligence to better assist humans in working. With the improvement of computer computing power and the improvement of artificial intelligence scientific theory, the artificial intelligence technology makes great progress, and the medical diagnosis method based on artificial intelligence also becomes a research hotspot of students all over the world. The intelligent diagnosis and treatment can help doctors to improve the accuracy of diagnosis in wide medical professions by quantifying the diagnosis of important clinical indexes, and is beneficial to improving the quality of medical services. More and more students in different fields begin to research the subject with rich and complex knowledge content of the traditional Chinese medicine by using an informatization technical means, so that the traditional Chinese medicine can be better exchanged and popularized among different subjects, a new solution is provided for the intelligent dialectical problem of the traditional Chinese medicine, and the method has great significance for dialectical analysis of traditional Chinese medicine, mining of the association between traditional Chinese medicine and western medicine and construction of an intelligent medical system of the traditional Chinese medicine.
Therefore, the inventor constructs a deep intelligent machine learning model based on a deep neural network to solve the technical problems of chronic disease diagnosis and drug recommendation, and creatively provides a system for intelligent traditional Chinese medicine diagnosis and drug recommendation for chronic diseases based on the deep neural network.
Disclosure of Invention
The invention aims to: in order to solve the technical problems related to the background technology, an intelligent traditional Chinese medicine diagnosis and medicine recommendation system for chronic diseases based on a deep neural network is provided.
The technical scheme adopted by the invention is as follows:
a chronic disease intelligent traditional Chinese medicine diagnosis and medicine recommendation system based on a deep neural network comprises a traditional Chinese medicine disease reading module, a diagnosis and medicine recommendation module and a control module, wherein the traditional Chinese medicine disease reading module is used for reading symptom information of a patient sample;
the data preprocessing module is used for preprocessing the read symptom information;
the database module is used for storing the symptom information of the patient sample and the obtained medicine information;
the deep neural network model is used for predicting the input information and obtaining the classification result of the related medicine to form prediction information;
the medicine recommending module is used for analyzing and calculating the recommended medicine by combining the prediction information of the deep neural network model, the symptom information of the patient sample stored by the database module and the obtained medicine information;
and the data visualization module is used for visually displaying the recommended drugs.
As a further technical scheme of the invention, the traditional Chinese medicine disease reading module supports various data storage forms.
As a further technical scheme of the invention, the data preprocessing module performs data preprocessing on the read symptom information, the data preprocessing process comprises text word segmentation, word removal and text vectorization, wherein the text word segmentation is performed by a word segmentation tool, and then a dictionary base is added for expansion; forming an item acyclic graph by using all possible word generation conditions, and finding out a maximum segmentation combination based on word frequency by adopting a dynamic programming algorithm when searching for a maximum probability path;
removing stop words, and removing the stop words contained in the word segmentation result by using the library to obtain a result of using the stop word list;
wherein the text vectorization is generated using a trained word2vec trained model.
As a further technical scheme, the database module selects a MySQL database, stores the symptom information and classification information data preprocessed by the data preprocessing module, and stores information of different medicines.
As a further technical scheme, the deep neural network model is a VGGNet convolutional neural network structure model; three inclusion modules are adopted in the VGGNet convolutional neural network to replace convolutional layers for feature extraction, the last pooling layer is changed from original maximum pooling into spatial pyramid pooling, and the number of models is 23; which comprises 10 convolutional layers, 5 pooling layers, 3 initiation modules, 3 full-link layers, 1 input layer and 1 output layer.
As a further technical scheme, the deep neural network model adopts a batch gradient descent algorithm, and the expression of the batch gradient descent algorithm is as follows:
in the formula, the batch represents the size of the batch, the operation is carried out in a matrix mode, and the weight is updated by using the sum of loss functions of one batch size data sample each time;
the input quantity, namely the batch size, is set to be 8 each time, the learning rate learning range of the initial model is 0.001, the model is called to complete one epoch training after completing one training of all images of the training set, 30 epochs are trained in total, the adjustment strategy of the learning rate is multistp, stepvalue is 20 epochs, namely the learning rate is reduced once when the 20 th epochs are completed;
selecting an improved cross entropy loss function by an objective function in the deep neural network model:
J(θ；Is，ys)＝Lc+ω*LR
wherein L iscThe method is implemented by cross entropy as a classification item loss function; l isRThe method is realized by a Dice loss function for the area term loss function; i iss，ysRespectively inputting variables in the training data; x is the number ofvRepresenting the location of the probability feature vector;
representing a probability feature vector output; p is a radical of1Representing a probability of a corresponding output; ω is used to adjust the ratio between the two losses, preferably ω is 3.
A dropout layer is added in the deep neural network model from the second convolution layer, the neural network randomly abandons different parts of neurons with a certain probability in each iteration in the training process, and the dropout rate p is 0.2;
the activation function in the deep neural network model is a sig _ ReLU function, and the activation function combines a sigmoid activation function and a ReLU activation function; the expression is as follows:
as a further technical scheme, the deep neural network model further comprises a training system, the training system performs training through a training set, the recognition accuracy of the model is tested on a verification set after the model training is completed, evaluation is performed through Tanimoto coefficient accuracy of the model, and multiple times of logic judgment and cyclic training meet the accuracy requirement.
As a further technical scheme, the medicine recommending module is a multi-interface module, and the recommended medicines are sent to the data visualization module.
As a further technical solution of the present invention, the data visualization module presents the predicted result as a result of a data table.
As a further technical solution of the present invention, the first row of the data table is a recommended drug name, the first column is a sample name, the number 1 is that the drug is recommended for the sample, and the number 0 is that the sample does not need to correspond to the drug.
The invention discloses an intelligent traditional Chinese medicine recommendation method based on deep learning, which comprises the following steps of:
step 1: pre-processing patient condition data in the data set;
step 2: training a convolutional neural network by using a training sample;
and step 3: and predicting the test sample by using the trained convolutional neural network model to obtain a final prediction result.
Specifically, in step 1, the patient disease data in the data set is preprocessed, the patient disease data in the data set is firstly divided into training samples and testing samples, and then text word segmentation, word deactivation and text vectorization are performed. When the unstructured text is treated, a step of analysis process of the unstructured text needs to be added in the preprocessing process. After the word segmentation of the text is carried out by using a word segmentation tool, a plurality of typical dictionary libraries are added for expansion. And forming an item acyclic graph by using all possible word generation conditions, and finding out a maximum segmentation combination based on word frequency by adopting a dynamic programming algorithm when searching for a maximum probability path. The stop word removing step removes stop words contained in the segmentation result by using the library, and is the result of using the stop word list. Text vectorization is generated using a trained word2vec trained model.
Specifically, in step 2, a convolutional neural network is trained by using training samples, the structure of the convolutional neural network is shown in fig. 4, three inclusion modules are used for extracting features on the basis of VGGNet instead of convolutional layers, the last pooling layer is changed from original maximum pooling into spatial pyramid pooling, and the models are 23 layers in total. Which comprises 10 convolutional layers, 5 pooling layers, 3 initiation modules, 3 full-link layers, 1 input layer and 1 output layer. Training the convolutional neural network by using the training set preprocessed in the step 1, after carrying out convolution, maximum pooling and initiation on the vector of the bottom layer for multiple times by the network, obtaining a feature map containing disease symptoms after pyramid pooling and 3 full-connection layers, wherein each convolutional layer corresponds to a convolutional layer in the coding network, and outputting by using sig _ ReLU as an activation function. And finally, converting the convolution output characteristics into a prediction result by softmax.
After the model training of the first 2 steps is completed, step 3 can be performed to predict the chronic disease patient to be tested. The disease data is preprocessed, then the convolutional neural network is used for prediction, and the whole process is not only fully automatic, but also fast.
The invention provides an intelligent traditional Chinese medicine dialectical and medicine recommendation system for chronic diseases, which mainly comprises: the system comprises a traditional Chinese medicine disease reading module, a data preprocessing module, a deep neural network model, a medicine recommending module, a data visualization module and a database module.
The traditional Chinese medicine disease reading module obtains the symptom information of a patient sample; the data preprocessing module carries out data preprocessing on the read symptom information and comprises the following steps: text word segmentation, word deactivation and text vectorization; the deep neural network model module is used for predicting the input information to obtain a classification result of each medicine so as to obtain a recommended medicine; the three modules are all connected with the database, the database module stores the symptom information of the patient sample and the obtained medicine information, intelligent medicine recommendation can be provided for patients needing diagnosis and treatment through the medicine recommendation module by fusing the symptom information and the medicine information, the patients can be helped to realize self diagnosis and treatment to a certain extent, the general health level of the nation is improved, and the national medical resources are saved.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. the invention provides an intelligent traditional Chinese medicine diagnosis and medicine recommendation system for chronic diseases based on a deep neural network, which comprises a database module, a diagnosis and recommendation module and a recommendation module, wherein the database module is used for storing symptom information of a patient sample and obtained medicine information; the traditional Chinese medicine disease reading module is used for reading the symptom information of the obtained patient sample, predicting the input information through a deep neural network model and obtaining the classification result of the related medicine to form prediction information; the recommended medicine is obtained through analysis and calculation by the medicine recommendation module in combination with the prediction information of the deep neural network model, the symptom information of the patient sample stored in the database module and the obtained medicine information, intelligent traditional Chinese medicine diagnosis and medicine recommendation of the chronic disease are achieved, a doctor is assisted in diagnosis and treatment, particularly, the doctor is assisted in providing an optimal treatment method for the patient, and cost is saved; the disease diagnosis accuracy rate can be improved, the death rate can be reduced, the hospital pressure can be relieved, and the like; the system helps patients with chronic diseases to realize self diagnosis and treatment to a certain extent, saves national medical resources and improves the health level of the whole population.
2. The deep neural network model is comprehensively constructed, the intelligent degree is high, the model processing efficiency is high, and the accuracy of the prediction result is high.
3. The invention further discloses that the data visualization module presents the prediction result as the result of a data table; the first row of the data table is the name of the recommended drug, the first column is the name of the sample, the number 1 is the name of the drug recommended for the sample, and the number 0 is the number of the sample without the corresponding drug, so that the prediction result is visually and clearly displayed.
4. The method further comprises the steps of setting a data preprocessing module, performing data preprocessing on the read symptom information, wherein the data preprocessing process comprises text word segmentation, word removal and text vectorization, and after the text word segmentation is performed by using a word segmentation tool, adding a dictionary base for expansion; forming an item acyclic graph by using all possible word generation conditions, and finding out a maximum segmentation combination based on word frequency by adopting a dynamic programming algorithm when searching for a maximum probability path; removing stop words, and removing the stop words contained in the word segmentation result by using the library to obtain a result of using the stop word list; text vectorization is generated by using a model trained by the trained word2 vec; the pretreatment effect is good, and the subsequent prediction analysis is convenient.
Drawings
FIG. 1 is a block diagram of the system architecture of the present invention;
FIG. 2 is a model design of a training system of the present invention;
FIG. 3 is a graph of sig-ReLU activation function in the present invention;
FIG. 4 is a network structure diagram of a deep neural network model according to the present invention;
FIG. 5 is a data chart of the visual prediction result of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, the intelligent chinese medical dialectical and medicine recommendation system for chronic diseases provided by the present invention mainly includes: the system comprises a traditional Chinese medicine disease reading module, a data preprocessing module, a deep neural network model, a medicine recommending module, a data visualization module and a database module.
The data traditional Chinese medicine disease reading module, the data preprocessing module, the deep neural network model, the medicine recommending module and the data visualization module are sequentially connected, and the data preprocessing module, the deep neural network module and the medicine recommending module are respectively connected with the database module.
The traditional Chinese medicine disease reading module obtains the symptom information of a patient sample; the data preprocessing module carries out data preprocessing on the read symptom information and comprises the following steps: text word segmentation, word deactivation and text vectorization; the deep neural network model module is used for predicting the input information to obtain a classification result of each medicine so as to obtain a recommended medicine; the three modules are all connected with the database, the database module stores the symptom information of the patient sample and the obtained medicine information, intelligent medicine recommendation can be provided for patients needing diagnosis and treatment through the medicine recommendation module by fusing the symptom information and the medicine information, the patients can be helped to realize self diagnosis and treatment to a certain extent, the general health level of the nation is improved, and the national medical resources are saved.
Further, the deep neural network is a neural network model under a TensorFlow framework, the framework has flexible portability, extremely high compiling speed and powerful visual components, a network structure and a training process can be visualized, and the full flow of an application machine can be realized;
further described, the database module is a MySQL database.
The system can assist doctors to provide the optimal treatment method for patients, so that the cost is saved; the disease diagnosis accuracy rate can be improved, the death rate can be reduced, the hospital pressure can be relieved, and the like; the system helps patients to realize self diagnosis and treatment to a certain extent, and improves the national health level.
The invention provides an intelligent traditional Chinese medicine dialectical diagnosis and medicine recommendation platform combined with a deep neural network model aiming at the existing problems, and makes effective auxiliary diagnosis and treatment decisions on the basis of exerting the advantages of the traditional Chinese medicine.
In the system provided by the invention, the traditional Chinese medicine disease reading module supports various data storage forms, and is convenient for a user to operate.
The data preprocessing module is required to preprocess the read patient symptom information. The preprocessing process mainly comprises three steps, namely text word segmentation, word deactivation and text vectorization. When the unstructured text is treated, a step of analysis process of the unstructured text needs to be added in the preprocessing process. After the word segmentation of the text is carried out by using a word segmentation tool, a plurality of typical dictionary libraries are added for expansion. And forming an item acyclic graph by using all possible word generation conditions, and finding out a maximum segmentation combination based on word frequency by adopting a dynamic programming algorithm when searching for a maximum probability path. The stop word removing step removes stop words contained in the segmentation result by using the library, and is the result of using the stop word list. Text vectorization is generated using a trained word2vec trained model.
The deep neural network module mainly comprises a convolution layer, a pooling layer, an inclusion, a full-connection layer and an activation function. The application of the convolutional neural network model in the computer language has great advantages compared with the traditional algorithm. Compared with a shallow artificial neural network, the characteristic data obtained by the deep learning model can represent original data more essentially, the classification and visualization can be conveniently realized, and the problem that the deep neural network is difficult to train to achieve the optimal state can be solved by adopting a layer-by-layer training method, so that the deep neural network model is used for processing. The design of the model is shown in figure 2, and mainly comprises two parts, namely a network layer structure design and a training parameter design, after the design is finished, firstly training a divided training set, testing the identification precision of the model on a verification set after the model training is finished, the evaluation means is mainly the Tanimoto coefficient precision of the model, if the model does not meet the precision requirement, further adjusting the training parameter for retraining, if the model meets the precision requirement, then detecting the model by using the testing set, if the model does not meet the precision requirement, adjusting the network structure for re-circulation training, and if the precision requirement is met, completing the training.
After comparing five convolutional neural networks of AlexNet, GoogleNet, VGGNet, ResNet and DenseNet, VGGNet is selected as a basic model of the invention. To speed up the training process, the present invention uses a batch gradient descent algorithm, whose expression seems to be as follows:
in the formula, the batch represents the size of the batch, the operation is performed in a matrix mode, the weight is updated by using the sum of loss functions of one batch size data sample every time, the iteration times required by network model convergence can be reduced, and the training efficiency is improved while the network identification effect is ensured.
According to the method, the quantity of input in each time, namely the batch size, is set to be 8 during the batch gradient descent algorithm, the learning rate learning range of an initial model is 0.001, the model is called to complete one epoch training after completing one training of all images of a training set, 30 epochs are trained in total, the adjustment strategy of the learning rate is multistp, stepvalue is 20 epochs, and the learning rate is once descended when the 20 th epochs are completed.
The invention selects an improved cross entropy loss function as an objective function:
J(θ；Is，ys)＝Lc+ω*LR
wherein L iscThe method is implemented by cross entropy as a classification item loss function; l isRThe method is realized by a Dice loss function for the area term loss function; i iss，ysRespectively inputting variables in the training data; x is the number ofvRepresenting the location of the probability feature vector;
representing a probability feature vector output; p is a radical of1Representing a probability of a corresponding output; ω is used to adjust the ratio between the two losses, and ω is 3 in the present invention.
In order to further avoid overfitting, a dropout layer is added in each convolution module (except for the first convolution module), and a neural network randomly discards different parts of neurons with a certain probability in each iteration in the training process, so that the diversity of a model sample data set can be enhanced, the sparsity between layers is also enhanced, the disturbance resistance of the model to unknown data is enhanced, the model is more robust, and the adopted dropout rate p is 0.2.
The activation function adopted by the invention is a sig _ ReLU function as shown in fig. 3, and the activation function combines a sigmoid activation function and a ReLU activation function. The expression is as follows:
the improved function is a Sigmoid function in the range of x < 0, so that the condition of gradient explosion or gradient disappearance of the ReLU can be avoided, and the characteristics of quick convergence and sparsity of the ReLU function are kept.
The pooling method adopted by the invention is space pyramid pooling, and the method utilizes multi-scale information of a pooling area, can map feature vectors with different sizes to the same dimension, avoids scaling operation on the original vectors, reduces loss of feature vector information to a certain extent, and improves feature expression capability of network pairs.
Referring to fig. 4, in the present invention, based on VGGNet, three inclusion modules are used to replace convolution layers for feature extraction, and the last pooling layer is changed from the original maximum pooling to spatial pyramid pooling, so that the model has 23 layers in total. Which comprises 10 convolutional layers, 5 pooling layers, 3 initiation modules, 3 full-link layers, 1 input layer and 1 output layer.
The database module uses a MySQL database which is a widely applied relational database system at present, and in the system, the database module stores preprocessed symptom information, classification information and other data and simultaneously stores information of different medicines, thereby providing information for intelligent traditional Chinese medicine dialectics and medicine recommendation of chronic diseases.
The medicine recommending module is a multi-interface module, and after input symptom information is predicted, the recommended medicines are sent to the data visualization module.
The data visualization module presents the prediction result as a result of a data table, as shown in fig. 5, a first row in the data table is a recommended drug name, a first column is a sample name, a number 1 is that the drug is recommended for the sample, and a number 0 is that the sample does not need to correspond to the drug.
Through traditional Chinese medicine disease reading module, data preprocessing module, deep neural network model module, medicine recommending module and data visualization module, a complete chronic disease intelligent traditional Chinese medicine dialectical and medicine recommending system is realized, intelligent traditional Chinese medicine dialectical and medicine recommending are provided for chronic patients, doctors are assisted in diagnosing, the chronic patients are helped to realize self-diagnosis to a certain extent, national medical resources are saved, and the health level of the whole population is improved.
The invention discloses an intelligent traditional Chinese medicine recommendation method based on deep learning, which comprises the following steps of:
step 1: pre-processing patient condition data in the data set;
step 2: training a convolutional neural network by using a training sample;
and step 3: and predicting the test sample by using the trained convolutional neural network model to obtain a final prediction result.
Specifically, in step 1, the patient disease data in the data set is preprocessed, the patient disease data in the data set is firstly divided into training samples and testing samples, and then text word segmentation, word deactivation and text vectorization are performed. When the unstructured text is treated, a step of analysis process of the unstructured text needs to be added in the preprocessing process. After the word segmentation of the text is carried out by using a word segmentation tool, a plurality of typical dictionary libraries are added for expansion. And forming an item acyclic graph by using all possible word generation conditions, and finding out a maximum segmentation combination based on word frequency by adopting a dynamic programming algorithm when searching for a maximum probability path. The stop word removing step removes stop words contained in the segmentation result by using the library, and is the result of using the stop word list. Text vectorization is generated using a trained word2vec trained model.
Specifically, in step 2, a convolutional neural network is trained by using training samples, the structure of the convolutional neural network is shown in fig. 4, three inclusion modules are used for extracting features on the basis of VGGNet instead of convolutional layers, the last pooling layer is changed from original maximum pooling into spatial pyramid pooling, and the models are 23 layers in total. Which comprises 10 convolutional layers, 5 pooling layers, 3 initiation modules, 3 full-link layers, 1 input layer and 1 output layer. Training the convolutional neural network by using the training set preprocessed in the step 1, after carrying out convolution, maximum pooling and initiation on the vector of the bottom layer for multiple times by the network, obtaining a feature map containing disease symptoms after pyramid pooling and 3 full-connection layers, wherein each convolutional layer corresponds to a convolutional layer in the coding network, and outputting by using sig _ ReLU as an activation function. And finally, converting the convolution output characteristics into a prediction result by softmax.
After the model training of the first 2 steps is completed, step 3 can be performed to predict the chronic disease patient to be tested. The disease data is preprocessed, then the convolutional neural network is used for prediction, and the whole process is not only fully automatic, but also fast.
The invention provides an intelligent traditional Chinese medicine dialectical and medicine recommendation system for chronic diseases, which mainly comprises: the system comprises a traditional Chinese medicine disease reading module, a data preprocessing module, a deep neural network model, a medicine recommending module, a data visualization module and a database module.
The traditional Chinese medicine disease reading module obtains the symptom information of a patient sample; the data preprocessing module carries out data preprocessing on the read symptom information and comprises the following steps: text word segmentation, word deactivation and text vectorization; the deep neural network model module is used for predicting the input information to obtain a classification result of each medicine so as to obtain a recommended medicine; the three modules are all connected with the database, the database module stores the symptom information of the patient sample and the obtained medicine information, intelligent medicine recommendation can be provided for patients needing diagnosis and treatment through the medicine recommendation module by fusing the symptom information and the medicine information, the patients can be helped to realize self diagnosis and treatment to a certain extent, the general health level of the nation is improved, and the national medical resources are saved.
Finally, the above embodiments are only intended to illustrate the technical solution of the present invention and not to limit the same, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention, which should be covered by the claims of the present invention.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A chronic disease intelligent traditional Chinese medicine diagnosis and medicine recommendation system based on a deep neural network is characterized in that:
comprises a traditional Chinese medicine disease reading module used for reading the symptom information of a patient sample;
the data preprocessing module is used for preprocessing the read symptom information;
the database module is used for storing the symptom information of the patient sample and the obtained medicine information;
the deep neural network model is used for predicting the input information and obtaining the classification result of the related medicine to form prediction information;
the medicine recommending module is used for analyzing and calculating the recommended medicine by combining the prediction information of the deep neural network model, the symptom information of the patient sample stored by the database module and the obtained medicine information;
and the data visualization module is used for visually displaying the recommended drugs.
2. The system of claim 1, wherein the system comprises: the traditional Chinese medicine disease reading module supports various data storage forms.
3. The system of claim 1, wherein the system comprises: the data preprocessing module is used for preprocessing the read symptom information, the data preprocessing process comprises text word segmentation, word removal and text vectorization, wherein the text word segmentation is added into a dictionary base for expansion after being segmented by a word segmentation tool; forming an item acyclic graph by using all possible word generation conditions, and finding out a maximum segmentation combination based on word frequency by adopting a dynamic programming algorithm when searching for a maximum probability path;
removing stop words, and removing the stop words contained in the word segmentation result by using the library to obtain a result of using the stop word list;
wherein the text vectorization is generated using a trained word2vec trained model.
4. The system of claim 1, wherein the system comprises: the database module selects a MySQL database, stores the symptom information and classification information data preprocessed by the data preprocessing module, and stores information of different medicines.
5. The system of claim 1, wherein the system comprises: the deep neural network model is a VGGNet convolutional neural network structure model; three inclusion modules are adopted in the VGGNet convolutional neural network to replace convolutional layers for feature extraction, the last pooling layer is changed from original maximum pooling into spatial pyramid pooling, and the number of models is 23; which comprises 10 convolutional layers, 5 pooling layers, 3 initiation modules, 3 full-link layers, 1 input layer and 1 output layer.
6. The system of claim 5, wherein the system comprises: a batch gradient descent algorithm is adopted in the deep neural network model, and the expression is as follows:
in the formula, the batch represents the size of the batch, the operation is carried out in a matrix mode, and the weight is updated by using the sum of loss functions of one batch size data sample each time;
the number of inputs, namely, the batch size, is set to be 8 each time, the learning rate learning range of the initial model is 0.001, the model is called to complete one epoch training after completing the training of all images of the training set once, 30 epochs are trained in total, the adjustment strategy of the learning rate is multistp, stepvalue is 20 epochs, namely, the learning rate is reduced once when the 20 th epochs are completed;
selecting an improved cross entropy loss function by an objective function in the deep neural network model:
J(θ；Is，ys)＝Lc+ω*LR
wherein L iscThe method is implemented by cross entropy as a classification item loss function; l isRThe method is realized by a Dice loss function for the area term loss function; i iss，ysRespectively inputting variables in the training data; x is the number ofvRepresenting the location of the probability feature vector;
representing a probability feature vector output; p is a radical of1Representing a probability of a corresponding output; ω is used to adjust the ratio between the two losses, ω being 3.
A dropout layer is added in the deep neural network model from the second convolution layer, the neural network randomly abandons different parts of neurons with a certain probability in each iteration in the training process, and the dropout rate p is 0.2;
the activation function in the deep neural network model is a sig _ ReLU function, and the activation function combines a sigmoid activation function and a ReLU activation function; the expression is as follows:
7. the system of claim 5, wherein the system comprises: the deep neural network model further comprises a training system, the training system performs training through a training set, the recognition accuracy of the model is tested on a verification set after the model training is completed, evaluation is performed through Tanimoto coefficient accuracy of the model, and multiple times of logic judgment and cyclic training meet accuracy requirements.
8. The system according to any one of claims 1-7, wherein the system comprises: the medicine recommending module is a multi-interface module, and the recommended medicines are sent to the data visualization module.
9. The system of claim 8, wherein the system comprises: the data visualization module presents the predicted results as results of a data table.
10. The system of claim 9, wherein the system comprises: the first row of the data table is the name of the recommended medication, the first column is the name of the sample, the number 1 is the name of the medication recommended for the sample, and the number 0 is the number of the sample that does not need to correspond to the medication.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910776695.5A CN112489769B (en) | 2019-08-22 | 2019-08-22 | Chronic disease intelligent Chinese medicine diagnosis and medicine recommendation system based on deep neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910776695.5A CN112489769B (en) | 2019-08-22 | 2019-08-22 | Chronic disease intelligent Chinese medicine diagnosis and medicine recommendation system based on deep neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112489769A true CN112489769A (en) | 2021-03-12 |
| CN112489769B CN112489769B (en) | 2024-05-17 |
Family
ID=74920206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910776695.5A Active CN112489769B (en) | 2019-08-22 | 2019-08-22 | Chronic disease intelligent Chinese medicine diagnosis and medicine recommendation system based on deep neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489769B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112988953A (en) * | 2021-04-26 | 2021-06-18 | 成都索贝数码科技股份有限公司 | Adaptive broadcast television news keyword standardization method |
| CN113284577A (en) * | 2021-05-24 | 2021-08-20 | 康键信息技术（深圳）有限公司 | Medicine prediction method, device, equipment and storage medium |
| CN113628716A (en) * | 2021-08-05 | 2021-11-09 | 翼健(上海)信息科技有限公司 | Prescription recommendation system |
| CN113782142A (en) * | 2021-08-20 | 2021-12-10 | 中国中医科学院中医药信息研究所 | Traditional Chinese medicine decoction piece formula recommendation system based on integrated neural network |
| CN114969557A (en) * | 2022-07-29 | 2022-08-30 | 之江实验室 | Propaganda and education pushing method and system based on multi-source information fusion |
| CN116092627A (en) * | 2023-04-04 | 2023-05-09 | 南京大经中医药信息技术有限公司 | Intelligent prescription system based on syndrome differentiation of traditional Chinese medicine pathogenesis |
| CN117275660A (en) * | 2023-10-19 | 2023-12-22 | 广州市莲田医药科技有限公司 | Full-link AI auxiliary method for inquiry to prescription |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853325A (en) * | 2009-03-31 | 2010-10-06 | 江启煜 | Computer-aided analysis method for traditional Chinese medicinal clinical information |
| WO2015158017A1 (en) * | 2014-04-16 | 2015-10-22 | 深圳市易特科信息技术有限公司 | Intelligent interaction and psychological comfort robot service system |
| CN106203432A (en) * | 2016-07-14 | 2016-12-07 | 杭州健培科技有限公司 | A kind of localization method of area-of-interest based on convolutional Neural net significance collection of illustrative plates |
| WO2017113232A1 (en) * | 2015-12-30 | 2017-07-06 | 中国科学院深圳先进技术研究院 | Product classification method and apparatus based on deep learning |
| CN106933994A (en) * | 2017-02-27 | 2017-07-07 | 广东省中医院 | A kind of core disease card relation construction method based on knowledge of TCM collection of illustrative plates |
| CN107330876A (en) * | 2017-06-12 | 2017-11-07 | 济南浪潮高新科技投资发展有限公司 | A kind of image automatic diagnosis method based on convolutional neural networks |
| US20180098737A1 (en) * | 2016-10-06 | 2018-04-12 | Fujitsu Limited | Method and apparatus of context-based patient similarity |
| CN108182967A (en) * | 2017-12-14 | 2018-06-19 | 华南理工大学 | A kind of traditional Chinese medical science medicinal material based on deep neural network recommends method |
| CN109344921A (en) * | 2019-01-03 | 2019-02-15 | 湖南极点智能科技有限公司 | A kind of image-recognizing method based on deep neural network model, device and equipment |
| CN110070119A (en) * | 2019-04-11 | 2019-07-30 | 北京工业大学 | A kind of handwritten numeral image recognition classification method based on binaryzation deep neural network |
-
2019
- 2019-08-22 CN CN201910776695.5A patent/CN112489769B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853325A (en) * | 2009-03-31 | 2010-10-06 | 江启煜 | Computer-aided analysis method for traditional Chinese medicinal clinical information |
| WO2015158017A1 (en) * | 2014-04-16 | 2015-10-22 | 深圳市易特科信息技术有限公司 | Intelligent interaction and psychological comfort robot service system |
| WO2017113232A1 (en) * | 2015-12-30 | 2017-07-06 | 中国科学院深圳先进技术研究院 | Product classification method and apparatus based on deep learning |
| CN106203432A (en) * | 2016-07-14 | 2016-12-07 | 杭州健培科技有限公司 | A kind of localization method of area-of-interest based on convolutional Neural net significance collection of illustrative plates |
| US20180098737A1 (en) * | 2016-10-06 | 2018-04-12 | Fujitsu Limited | Method and apparatus of context-based patient similarity |
| CN106933994A (en) * | 2017-02-27 | 2017-07-07 | 广东省中医院 | A kind of core disease card relation construction method based on knowledge of TCM collection of illustrative plates |
| CN107330876A (en) * | 2017-06-12 | 2017-11-07 | 济南浪潮高新科技投资发展有限公司 | A kind of image automatic diagnosis method based on convolutional neural networks |
| CN108182967A (en) * | 2017-12-14 | 2018-06-19 | 华南理工大学 | A kind of traditional Chinese medical science medicinal material based on deep neural network recommends method |
| CN109344921A (en) * | 2019-01-03 | 2019-02-15 | 湖南极点智能科技有限公司 | A kind of image-recognizing method based on deep neural network model, device and equipment |
| CN110070119A (en) * | 2019-04-11 | 2019-07-30 | 北京工业大学 | A kind of handwritten numeral image recognition classification method based on binaryzation deep neural network |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112988953A (en) * | 2021-04-26 | 2021-06-18 | 成都索贝数码科技股份有限公司 | Adaptive broadcast television news keyword standardization method |
| CN112988953B (en) * | 2021-04-26 | 2021-09-03 | 成都索贝数码科技股份有限公司 | Adaptive broadcast television news keyword standardization method |
| CN113284577A (en) * | 2021-05-24 | 2021-08-20 | 康键信息技术（深圳）有限公司 | Medicine prediction method, device, equipment and storage medium |
| CN113284577B (en) * | 2021-05-24 | 2023-08-11 | 康键信息技术（深圳）有限公司 | Medicine prediction method, device, equipment and storage medium |
| CN113628716A (en) * | 2021-08-05 | 2021-11-09 | 翼健(上海)信息科技有限公司 | Prescription recommendation system |
| CN113782142A (en) * | 2021-08-20 | 2021-12-10 | 中国中医科学院中医药信息研究所 | Traditional Chinese medicine decoction piece formula recommendation system based on integrated neural network |
| CN113782142B (en) * | 2021-08-20 | 2024-04-16 | 中国中医科学院中医药信息研究所 | Traditional Chinese medicine decoction piece formula recommendation system based on integrated neural network |
| CN114969557A (en) * | 2022-07-29 | 2022-08-30 | 之江实验室 | Propaganda and education pushing method and system based on multi-source information fusion |
| CN116092627A (en) * | 2023-04-04 | 2023-05-09 | 南京大经中医药信息技术有限公司 | Intelligent prescription system based on syndrome differentiation of traditional Chinese medicine pathogenesis |
| CN116092627B (en) * | 2023-04-04 | 2023-06-27 | 南京大经中医药信息技术有限公司 | Intelligent prescription system based on syndrome differentiation of traditional Chinese medicine pathogenesis |
| CN117275660A (en) * | 2023-10-19 | 2023-12-22 | 广州市莲田医药科技有限公司 | Full-link AI auxiliary method for inquiry to prescription |
| CN117275660B (en) * | 2023-10-19 | 2024-05-07 | 广州市莲田医药科技有限公司 | Full-link AI auxiliary method for inquiry to prescription |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112489769B (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112489769A (en) | Intelligent traditional Chinese medicine diagnosis and medicine recommendation system for chronic diseases based on deep neural network | |
| JP6522161B2 (en) | Medical data analysis method based on deep learning and intelligent analyzer thereof | |
| CN109920501B (en) | Electronic medical record classification method and system based on convolutional neural network and active learning | |
| WO2021120936A1 (en) | Chronic disease prediction system based on multi-task learning model | |
| CN109670179A (en) | Case history text based on iteration expansion convolutional neural networks names entity recognition method | |
| CN106778014A (en) | A kind of risk Forecasting Methodology based on Recognition with Recurrent Neural Network | |
| Manzak et al. | Automated classification of Alzheimer’s disease using deep neural network (DNN) by random forest feature elimination | |
| Bishnoi et al. | Artificial intelligence techniques used in medical sciences: a review | |
| Luo et al. | The prediction of hypertension based on convolution neural network | |
| Suo et al. | Risk factor analysis based on deep learning models | |
| Ullah et al. | A fully connected quantum convolutional neural network for classifying ischemic cardiopathy | |
| WO2023108873A1 (en) | Brain network and brain addiction connection calculation method and apparatus | |
| CN116110597A (en) | Digital twinning-based intelligent analysis method and device for patient disease categories | |
| Ma et al. | Construction and evaluation of intelligent medical diagnosis model based on integrated deep neural network | |
| WO2019132686A1 (en) | Method for generating mathematical models of a patient using artificial intelligence technologies | |
| Maheshwari et al. | Quantum machine learning applied to electronic healthcare records for ischemic heart disease classification | |
| CN114820450A (en) | CT angiography image classification method suitable for Li's artificial liver treatment | |
| EP4149351A1 (en) | System and method for testing for sars-cov-2/covid-19 based on wearable medical sensors and neural networks | |
| Yousif | Classification of mental disorders figures based on soft computing methods | |
| Ambrews et al. | Ensemble based machine learning model for heart disease prediction | |
| Abbas et al. | An Efficient Stacked Ensemble Model for Heart Disease Detection and Classification. | |
| Komalavalli et al. | An Effective Heart Disease Prediction Using Machine Learning | |
| Cao et al. | Alzheimer’s Disease Stage Detection Method Based on Convolutional Neural Network | |
| Jayanthi et al. | Alzheimer’s disease classification using deep learning | |
| Verma et al. | Ontology based personalized modeling for chronic disease risk analysis: An integrated approach |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Building 5, 1st Floor, No. 2 Xiyuanba Road, Xihu District, Hangzhou City, Zhejiang Province, 310030 Applicant after: Zhejiang Yuantu Technology Co.,Ltd. Address before: 310030 west side, 4th floor, building 1, No. 10, xiyuansan Road, Sandun Town, Hangzhou City, Zhejiang Province Applicant before: ZHEJIANG YUANTU INTERCONNECTION TECHNOLOGY CO.,LTD. Country or region before: China |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |