CN115631852B - Certificate type recommendation method and device, electronic equipment and nonvolatile storage medium - Google Patents
Certificate type recommendation method and device, electronic equipment and nonvolatile storage medium Download PDFInfo
- Publication number
- CN115631852B CN115631852B CN202211363166.0A CN202211363166A CN115631852B CN 115631852 B CN115631852 B CN 115631852B CN 202211363166 A CN202211363166 A CN 202211363166A CN 115631852 B CN115631852 B CN 115631852B
- Authority
- CN
- China
- Prior art keywords
- data
- text information
- target
- vector data
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 239000013598 vector Substances 0.000 claims abstract description 202
- 238000012549 training Methods 0.000 claims abstract description 112
- 208000011580 syndromic disease Diseases 0.000 claims abstract description 70
- 238000013528 artificial neural network Methods 0.000 claims abstract description 52
- 239000003814 drug Substances 0.000 claims abstract description 44
- 238000000605 extraction Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000011176 pooling Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 230000004069 differentiation Effects 0.000 abstract description 27
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000003058 natural language processing Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 20
- 208000024891 symptom Diseases 0.000 description 19
- 230000006870 function Effects 0.000 description 16
- 230000008569 process Effects 0.000 description 7
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 230000007812 deficiency Effects 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 210000003734 kidney Anatomy 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 210000004185 liver Anatomy 0.000 description 4
- 230000000873 masking effect Effects 0.000 description 4
- 208000019255 Menstrual disease Diseases 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000012550 audit Methods 0.000 description 2
- 235000019658 bitter taste Nutrition 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000002496 gastric effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000027939 micturition Effects 0.000 description 2
- 230000001717 pathogenic effect Effects 0.000 description 2
- 210000000952 spleen Anatomy 0.000 description 2
- 210000001562 sternum Anatomy 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 206010062717 Increased upper airway secretion Diseases 0.000 description 1
- 238000001467 acupuncture Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 208000022531 anorexia Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 206010061428 decreased appetite Diseases 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 206010013990 dysuria Diseases 0.000 description 1
- 241000411851 herbal medicine Species 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008506 pathogenesis Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 208000026435 phlegm Diseases 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—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
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Probability & Statistics with Applications (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The application discloses a certificate type recommendation method, device, electronic equipment and a nonvolatile storage medium. Wherein the method comprises the following steps: acquiring original text information, wherein the original text information comprises: the inquiry text information and the medical record text information; according to the pre-training model, carrying out vectorization processing on the original text information to obtain target vector data, wherein the target vector data comprises: query vector data and medical record vector data; performing feature extraction on medical record vector data by using a first neural network to obtain first feature data, and performing feature extraction on inquiry vector data by using a second neural network to obtain second feature data; and determining the target certificate according to the first characteristic data and the second characteristic data. The method solves the technical problem of poor accuracy of syndrome type recommendation of the syndrome differentiation system caused by the fact that the existing traditional Chinese medicine syndrome differentiation system mostly does not adopt natural language processing technology.
Description
Technical Field
The application relates to the field of intelligent recommendation, in particular to a certificate type recommendation method, device, electronic equipment and nonvolatile storage medium.
Background
In the field of traditional Chinese medicine, a "syndrome" is a response and generalization of a characteristic (or symptom) at a certain stage in the disease cycle or progression. The differentiation of symptoms is a special research method of traditional Chinese medicine on diseases, is the key of traditional Chinese medicine treatment, and is to use the collected patient symptoms and physical sign information to distinguish the pathogenesis reasons, pathological positions, pathogenic factors and the like of the patient, and finally judge the disease as the symptoms of a certain property.
Along with the rise of artificial intelligence technology, some traditional Chinese medicine dialectical systems for assisting doctors in diagnosing diseases also appear, however, most of the traditional Chinese medicine dialectical systems do not adopt natural language processing technology, so that the reliability of the dialectical systems is low, and the problem of poor accuracy of symptom recommendation often exists.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the application provides a syndrome type recommendation method, a device, electronic equipment and a nonvolatile storage medium, which at least solve the technical problem of poor syndrome type recommendation accuracy of a syndrome type system caused by that the existing traditional Chinese medicine syndrome type system does not adopt a natural language processing technology.
According to an aspect of the embodiments of the present application, there is provided a syndrome recommendation method, including: acquiring original text information, wherein the original text information comprises: the inquiry text information and the medical record text information; according to the pre-training model, carrying out vectorization processing on the original text information to obtain target vector data, wherein the target vector data comprises: the medical record data comprises inquiry vector data and medical record vector data, wherein the inquiry vector data is target vector data obtained by vectorizing inquiry text information, and the medical record vector data is target vector data obtained by vectorizing medical record text information; performing feature extraction on medical record vector data by using a first neural network to obtain first feature data, and performing feature extraction on inquiry vector data by using a second neural network to obtain second feature data; and determining the target certificate according to the first characteristic data and the second characteristic data.
Optionally, according to the pre-training model, vectorizing the original text information to obtain target vector data, including: determining a word vector of each word in the original text information; determining sentence vectors of sentences in which word vectors are located in the original text information; determining a position vector corresponding to the word vector, wherein the position vector is used for representing the position information of the word vector in the sentence; and inputting the word vector, the sentence vector and the position vector into a pre-training model for processing to obtain target vector data.
Optionally, before inputting the word vector, the sentence vector and the position vector into the pre-training model for processing, the method further comprises: the method comprises the steps of obtaining pre-training text information, wherein the pre-training text information is obtained from a traditional Chinese medicine knowledge base, and the traditional Chinese medicine knowledge base stores text information for recording traditional Chinese medicine knowledge; selecting words in the pre-training text information according to the preset probability to cover; and training the initial model according to the covered words and the uncovered words in the pre-training text information to obtain a pre-training model.
Optionally, performing feature extraction on medical record vector data by using a first neural network to obtain first feature data, and performing feature extraction on inquiry vector data by using a second neural network to obtain second feature data includes: convolving the medical record vector data; determining an activation function and a first maximum pooling function corresponding to the first neural network; according to the activation function and the first maximum pooling function, calculating the medical record vector data after convolution processing to obtain first characteristic data; and carrying out feature extraction on the inquiry vector data according to the second neural network to obtain second feature data.
Optionally, performing feature extraction on the query vector data according to the second neural network, and obtaining second feature data includes: establishing a target relation graph according to the inquiry vector data, wherein the target relation graph is used for representing the relation between word vectors in the inquiry vector data; determining a target adjacent matrix and target training parameters corresponding to the target relation diagram; according to the target adjacency matrix and the target training parameters, calculating influence coefficients of word vectors in the inquiry vector data, wherein the influence coefficients are used for representing influence degrees of the word vectors on other word vectors in the inquiry vector data; and determining second characteristic data according to the influence coefficient and the second maximum pooling function.
Optionally, determining the target credential based on the first feature data and the second feature data includes: calculating the confidence coefficient of each syndrome according to the first characteristic data, the second characteristic data and the target classifier; and determining the pattern with the highest confidence as the target pattern.
Optionally, before calculating the confidence coefficient of each certificate according to the first feature data, the second feature data and the target classifier, the method further includes: obtaining training data, wherein the training data comprises: characteristic data, syndrome type and corresponding relation of characteristic data and syndrome type; determining a target association relationship between the feature data and the syndrome according to the training data; and generating a target classifier according to the target association relation.
According to another aspect of the embodiments of the present application, there is also provided a certificate type recommendation apparatus, including: the data acquisition module is used for acquiring original text information, wherein the original text information comprises: the inquiry text information and the medical record text information; the vectorization module is used for vectorizing the original text information according to the pre-training model to obtain target vector data, wherein the target vector data comprises: the medical record data comprises inquiry vector data and medical record vector data, wherein the inquiry vector data is target vector data obtained by vectorizing inquiry text information, and the medical record vector data is target vector data obtained by vectorizing medical record text information; the feature extraction module is used for carrying out feature extraction on the medical record vector data by adopting a first neural network to obtain first feature data, and carrying out feature extraction on the inquiry vector data by adopting a second neural network to obtain second feature data; and the evidence recommendation module is used for determining the target evidence according to the first characteristic data and the second characteristic data.
According to still another aspect of the embodiments of the present application, there is further provided an electronic device, including a processor, where the processor is configured to execute a program, and the program executes a method for recommending a pattern.
According to still another aspect of the embodiments of the present application, there is further provided a nonvolatile storage medium, where the nonvolatile storage medium includes a stored computer program, and a device in which the nonvolatile storage medium is located executes the certification recommendation method by running the computer program.
In the embodiment of the application, the method comprises the steps of obtaining original text information, wherein the original text information comprises: the inquiry text information and the medical record text information; according to the pre-training model, carrying out vectorization processing on the original text information to obtain target vector data, wherein the target vector data comprises: the medical record data comprises inquiry vector data and medical record vector data, wherein the inquiry vector data is target vector data obtained by vectorizing inquiry text information, and the medical record vector data is target vector data obtained by vectorizing medical record text information; performing feature extraction on medical record vector data by using a first neural network to obtain first feature data, and performing feature extraction on inquiry vector data by using a second neural network to obtain second feature data; according to the first characteristic data and the second characteristic data, the target syndrome type is determined by adding a pre-training model and applying different neural networks to different types of original text data, so that the purposes of ensuring the reliability of a syndrome differentiation system and improving the syndrome differentiation accuracy are achieved, and the technical problem of poor syndrome differentiation recommending accuracy of the syndrome differentiation system caused by the fact that the traditional Chinese medicine syndrome differentiation system does not adopt a natural language processing technology mostly is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a schematic diagram of a method flow of syndrome recommendation provided according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a pre-training model provided according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a process for vectorizing text information in a pre-training model according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a framework structure of a first neural network according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a framework structure of a second neural network provided according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a framework for a certification recommendation provided in accordance with an embodiment of the present application;
fig. 7 is a schematic structural diagram of a dialectical system of traditional Chinese medicine according to an embodiment of the present application;
FIG. 8 is a schematic structural diagram of a certification recommendation apparatus according to an embodiment of the present application;
fig. 9 is a block diagram of a hardware structure of a computer terminal (or electronic device) for implementing a method for certification recommendation according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
For the convenience of those skilled in the art to better understand the embodiments of the present application, some technical terms or nouns related to the embodiments of the present application will now be explained as follows:
syndrome type: the pattern of Chinese medicine is a specific name of Chinese medicine, and is the different disease states of human body caused by different changes of yin-yang qi-blood caused by different etiologies.
Four diagnostic methods: refers to looking, smelling, asking and cutting.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
In accordance with the embodiments of the present application, there is provided a method embodiment of the certification recommendation, it being noted that the steps shown in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order other than that shown or described herein.
Fig. 1 is a schematic diagram of a flow of a method for syndrome recommendation according to an embodiment of the present application, as shown in fig. 1, the method includes the following steps:
step S102, acquiring original text information, wherein the original text information comprises: the inquiry text information and the medical record text information;
in this embodiment, the original text information may be a patient's complaint and a doctor's further inquiry information.
Step S104, carrying out vectorization processing on the original text information according to the pre-training model to obtain target vector data, wherein the target vector data comprises: the medical record data comprises inquiry vector data and medical record vector data, wherein the inquiry vector data is target vector data obtained by vectorizing inquiry text information, and the medical record vector data is target vector data obtained by vectorizing medical record text information;
For the original text information acquired in step S102, the text needs to be represented by text vectorization into a series of vectors capable of expressing text semantics, and then further processing is performed. In different language scenes, the vocabulary is used and the expression difference is large, so that a text vectorization model in a traditional Chinese medicine scene needs to be constructed.
In some embodiments of the present application, vectorizing the original text information according to a pre-training model to obtain target vector data includes the following steps: determining a word vector of each word in the original text information; determining sentence vectors of sentences in which word vectors are located in original text information, wherein the sentence vectors are used for representing semantic information of the sentences in which the word vectors are located; determining a position vector corresponding to the word vector, wherein the position vector is used for representing the position information of the word vector in the sentence; and inputting the word vector, the sentence vector and the position vector into a pre-training model for processing to obtain target vector data.
As an optional implementation manner, when determining the word vector of each word in the original text information, the processing of dividing the words of the original text information may be performed first, and then the vectorization processing of each divided word may be performed to obtain the word vector.
In order to improve accuracy of the syndrome recommendation, before the word vector, the sentence vector and the position vector are input into the pre-training model for processing, the method further comprises the following steps: acquiring pre-training text information, wherein the pre-training text information is text information for recording Chinese medical knowledge; selecting words in the pre-training text information according to the preset probability to cover; and training the initial model according to the covered words and the uncovered words in the pre-training text information to obtain a pre-training model.
In this embodiment, the pre-training text information may be obtained from a knowledge base of traditional Chinese medicine pre-stored in the system, where the pre-training text data includes, but is not limited to: the pre-training model is a pre-training language model, and the pre-training language model is trained by using a large-scale non-labeling corpus to obtain text vector expression containing rich semantic information. Specifically, the training is performed by using text information (i.e., the pre-training text information) such as diagnosis and prescription in the traditional Chinese medicine, and a model for text vectorization based on a pre-training language model is obtained.
Note that, the pre-training language model is not limited to a specific model, and in this embodiment, the pre-training language model may be a BERT model. Specifically, the pre-training model obtains a bi-directional representation of the text through the mask language. In this embodiment, the words in the original text (i.e., the original text information) are randomly selected with a probability of 15%, and the selected words have a probability of 80% using a MASK "[ MASK ] ]"replace (equivalent to masking words as described above), 10% of the probability is replaced with random other words, 10% of the probability is not replaced, FIG. 2 is a schematic diagram of a pre-training model provided according to an embodiment of the present application, as shown in FIG. 2, in which the input is { T } 1 ,T 2 ,…,T m+1 ,[MASK],T m+3 ,T m+4 ++, i.e. T m+2 The word in the position is replaced by a mask, by the remaining uncovered word pairs T m+2 The words in the positions are predicted, so that the unsupervised training of the pre-training model is realized.
For example, the training text is "repeated epigastric and sternal postcausalgia for several years, recurrent menstrual disorder for several months". "performing unsupervised learning on the original text by using a language model with a masking mechanism, namely replacing part of words in the original text by using" [ MASK ] "and finally predicting the original text by using the text with" [ MASK ] ", specifically replacing gastric cavity and menstrual disorder in the original text by using [ MASK ], and finally predicting the original text by using the text with a MASK as follows:
original text: the pain is repeated for several years after the gastric cavity and the sternum, and the menstrual disorder is repeated for several months.
Masked text: repeating [ MASK ] [ MASK ] for several years after joining the sternum, and repeating [ MASK ] [ MASK ] [ MASK ] for several months.
In this embodiment, when the pre-training model performs vectorization processing on text information, three parts need to be determined for processing the original text information, including: fig. 3 is a schematic diagram of a process of vectorizing text information in a pre-training model according to an embodiment of the present application, where the coding refers to a word and a position where the word is located, and the relation between context in text can be better processed, so as to obtain a vector sequence (i.e. the target vector data) corresponding to original text information.
Step S106, performing feature extraction on the medical record vector data by using a first neural network to obtain first feature data, and performing feature extraction on the inquiry vector data by using a second neural network to obtain second feature data;
for the obtained patient medical information (namely the original text information), after vectorization is carried out through a pre-training model, further processing analysis is needed to obtain the result of diagnosis and treatment. For non-natural language text (i.e., the case history text information), such as symptom information in the case history, etc., the convolutional neural network CNN (i.e., the first neural network) may be used to extract information, and for natural language text (i.e., the inquiry text information), such as patient self-description, medical history, four-diagnosis information, etc., the graph neural network GNN (and the second neural network) may be used to extract information; and finally summarizing and classifying.
In some embodiments of the present application, performing feature extraction on medical record vector data using a first neural network to obtain first feature data, and performing feature extraction on interview vector data using a second neural network to obtain second feature data includes: convolving the medical record vector data; determining an activation function and a first maximum pooling function corresponding to the first neural network; according to the activation function and the first maximum pooling function, calculating the medical record vector data after convolution processing to obtain first characteristic data; and carrying out feature extraction on the inquiry vector data according to the second neural network to obtain second feature data.
Specifically, fig. 4 is a schematic diagram of a frame structure of a first neural network according to an embodiment of the present application, as shown in fig. 4, in this embodiment, the first neural network includes three one-dimensional convolution layers, and one-dimensional Max Pooling layer (Max Pooling). The convolution kernel sizes in the three convolution layers are 2, 3 and 4 respectively; the number of output channels per convolution is 2. And splicing the characteristics obtained by different convolution layers to form a final output characteristic.
For the inquiry text information, carrying out feature extraction on the inquiry vector data according to the second neural network to obtain second feature data, wherein the method comprises the following steps of: establishing a target relation graph according to the inquiry vector data, wherein the target relation graph is used for representing the relation between word vectors in the inquiry vector data; determining a target adjacent matrix and target training parameters corresponding to the target relation diagram; according to the target adjacency matrix and the target training parameters, calculating influence coefficients of word vectors in the inquiry vector data, wherein the influence coefficients are used for representing influence degrees of the word vectors on other word vectors in the inquiry vector data; and determining second characteristic data according to the influence coefficient and the second maximum pooling function.
Specifically, fig. 5 is a schematic diagram of a framework structure of a second neural network, as shown in fig. 5, and in this embodiment, when the second neural network processes query vector data, the steps include a graph composition of text, word vector interaction, and feature extraction, which specifically include the following steps:
and 1, constructing a text graph. A graph of text (i.e., the target relationship graph described above) is constructed with word-to-word co-occurrence relationships as edges, denoted g= (V, E), where V represents a word and E represents an edge. For each graph, a corresponding adjacency matrix A (i.e., the target adjacency matrix described above) can be generated using the edge relationships. The co-occurrence relationship of words represents the probability of two words occurring in a fixed sliding window.
And 2, word vector interaction based on the graph. The deep relation between words (equivalent to determining the influence coefficient of each word vector) is learned by using the second neural network, and one word node can receive information a from the adjacent word nodes and then combine with the own vector code h to update. The updating process is as follows:
a t ＝Ah t-1 W a
z t ＝σ(W z a t +U z h t-1 +b z )
r t ＝σ(W r a t +U r h t-1 +b r )
wherein A represents an adjacency matrix, sigma represents an activation function sigmoid, W z ,U z ,b z ,W r ,U r ,b r ,W h ,U h ,b h Are all trainable parameters, z t And r t An update gate and a reset gate, respectively, for determining the influence degree (i.e. the influence coefficient) h of the neighboring node on the current node t Vector encoding of word vector for current node, h t-1 Vector encoding of word vectors for neighbor nodes, a t Messages representing interactions between nodes, for updating vector coding of word nodes, W a Is required to trainIs used for the weight matrix of the (c),is the vector code after word vector interaction and is used for updating the word vector.
And 3, reading the characteristics. After vocabulary interaction, the code h of each word node contains context information, and the final characteristic information h is obtained by summarizing the information of all word nodes G . The specific process is as follows:
wherein f 1 ,f 2 For two multi-layer perceptrons, and finally using Max Pooling (i.e., the second Max Pooling function described above) to extract keywords in text, h v Representing the final vector encoding of the v-th node,representing vector coding of the V-th node in the t-th turn of GNN, wherein V represents the number of nodes and h 1 ,h 2 ,…,h V Representing the final vector encoding of all nodes, i.e. h as described above v 。
Step S108, determining the target certificate according to the first characteristic data and the second characteristic data.
In some embodiments of the present application, determining the target credential from the first feature data and the second feature data comprises: calculating the confidence coefficient of each syndrome according to the first characteristic data, the second characteristic data and the target classifier; and determining the pattern with the highest confidence as the target pattern.
In this embodiment, the syndromes include, but are not limited to: deficiency of both spleen and kidney, deficiency of liver and kidney yin, stagnation of phlegm-qi, deficiency of liver and kidney, upward disturbance of wind-heat, pathogenic wind attacking the lung and obstruction of lung-qi.
In some embodiments of the present application, before calculating the confidence of each syndrome according to the first feature data, the second feature data, and the target classifier, the method further includes: obtaining training data, wherein the training data comprises: characteristic data, syndrome type and corresponding relation of characteristic data and syndrome type; determining a target association relationship between the feature data and the syndrome according to the training data; and generating a target classifier according to the target association relation.
In this embodiment, the training data may be obtained from old and ancient medical records data in a knowledge base of traditional Chinese medicine.
The technology that the dialectical system used in the prior art is comparatively backward, the prediction accuracy is low, and the traditional Chinese medicine knowledge base is not fused, the dialectical experience of the old traditional Chinese medicine in the old and current medical records is not fully excavated, and the scheme in the application greatly improves the reliability of the dialectical system by introducing the old traditional Chinese medicine old and current medical record data of the traditional Chinese medicine knowledge base.
Specifically, training data of the theoretical model is extracted from the knowledge base, as an alternative implementation manner, symptoms are taken as input, a syndrome is taken as output, a parameter value of the pre-training model is taken as an initialization parameter, targeted training is performed, and the training data can be symptoms and a syndrome corresponding to the symptoms, for example, the symptoms: frequent urination, painful urination, dark red tongue, dark tongue fur and wiry pulse; syndrome type: deficiency of both spleen and kidney;
as an alternative implementation manner, the input information of the treatment model can be medical record text information and inquiry text information, for example, the medical record text information can include complaint information of a patient, such as 'urgent and uncomfortable urination after holding urine, repeated five months and two days', the inquiry text information is four-diagnosis information, such as tongue, pulse and other related symptom descriptions, and in addition, the medical record text information can also include basic information descriptions of the patient, such as gender, age and the like.
Fig. 6 is a schematic diagram of a frame structure of a syndrome recommendation according to an embodiment of the present application, as shown in fig. 6, in the syndrome recommendation method in the present application, a pre-training language model is used to perform word vectorization, a first neural network CNN is used to perform feature extraction on medical record text information, a second neural network GNN is used to perform feature extraction on features of inquiry text information, and finally a target classifier Softmax is used to classify the characteristics to obtain a target syndrome, so that reliability of a syndrome differentiation system is improved, and accuracy of syndrome differentiation results is higher.
For example, collecting self-description of the patient and four-diagnosis information of doctors, and processing; for example, the patient's self-description is: dull pain in liver area, bitter taste; the supplementary information of doctors is: weak food, debilitation, dark tongue with white coating and wiry and slippery pulse; the symptoms finally obtained after treatment are as follows: bitter taste, anorexia, debilitation, hypochondriac pain, dark tongue, white tongue fur, wiry and slippery pulse, and the recommended symptoms obtained according to the obtained symptoms are: deficiency of liver and kidney.
Through the steps, the pre-training model is generated, and different neural networks are applied to different types of original text data, so that the purposes of ensuring the reliability of the dialectical system and improving the dialectical accuracy are achieved, and the technical problem of poor dialectical recommendation accuracy of the dialectical system caused by the fact that the traditional Chinese medicine dialectical system does not adopt a natural language processing technology mostly is solved.
Example 2
According to the embodiment of the application, an embodiment of a traditional Chinese medicine syndrome differentiation system is also provided. Fig. 7 is a schematic structural diagram of a dialectical system of traditional Chinese medicine, as shown in fig. 7, where the dialectical system of traditional Chinese medicine may be used to execute the dialectical recommendation method in the present application, and each module in the dialectical system of traditional Chinese medicine may execute the following steps:
Step 1, collecting pre-training data through a data acquisition module;
in this embodiment, various Chinese medicine texts including descriptive information of diseases, prescriptions, acupuncture, medical cases, chinese herbal medicines, chinese patent medicines, etc. can be collected from the knowledge base of the traditional Chinese medicine;
step 2, model pre-training is carried out through a dialectical model pre-training module;
specifically, using the collected pre-training data, performing unsupervised learning by using a language model with a masking mechanism, masking part of words in the text, and training the model by predicting the masked words by using the rest of words;
step 3, collecting training data through a data acquisition module,
in this embodiment, the training data is data of "medical record/inquiry-evidence" collected from medical records in the knowledge base of traditional Chinese medicine;
step 4, performing dialectical model training through a dialectical model training module;
specifically, the trained pre-training model in the step 2 and the medical record/inquiry-evidence data collected in the step 3 are used, symptoms are taken as input, and the evidence is taken as output to further train the model; obtaining a model which can obtain a evidence by inputting symptoms;
step 5, collecting patient information through a patient information collecting module;
In this embodiment, the information collected from the patient includes patient complaints and further interrogation information from the doctor;
step 6, data processing, namely, carrying out data standardization and data cleaning on the information of the patient in the step 5 by utilizing a traditional Chinese medicine knowledge base;
as an alternative embodiment, the normalization of the data and the data cleansing comprises the following steps: detecting whether nonstandard words exist in the collected information according to a preset dictionary, wherein the preset dictionary comprises a plurality of groups of standard words and nonstandard words, and the standard words and the nonstandard words in the same group are synonymous; under the condition that the nonstandard words exist in the collected information, replacing the nonstandard words with standard words according to a preset dictionary, wherein the replaced standard words and the nonstandard words before replacement are synonymous.
Step 7, intelligent syndrome differentiation is carried out through a syndrome differentiation module;
specifically, using the trained dialectical model in the step 4, inputting the data after data standardization and data cleaning to obtain the target dialectical model recommended by the system;
step 8, auditing the result through a result auditing module;
in this embodiment, after the recommended target syndrome is obtained, an audit and verification result of the doctor for the recommended target syndrome may be obtained, and if the audit and verification result is that the patient information is not further obtained by returning to step 5;
Step 9, storing results through a storage module, and storing the target syndrome and all symptoms into a traditional Chinese medicine knowledge base and prompting whether to continue training the model if the auditing and checking results are passed; if the model continues to be trained, steps 3 through 4 will be performed.
It should be noted that, the syndrome differentiation model in the traditional Chinese medicine syndrome differentiation system in fig. 7 may be divided into two parts, namely model training and model use, specifically, the knowledge base, the data acquisition module, the data processing module, the syndrome differentiation model pre-training module and the syndrome differentiation model training module in fig. 7 together form a model training part, the patient information acquisition module, the data processing module, the syndrome differentiation module, the result auditing module and the storage module together form a model use part, and the model training part and the model use part can be independently operated and selectively operated according to actual requirements, and under the condition that the syndrome differentiation model has completed training, the model can be directly used for syndrome recommendation without training, and operations such as training and strengthening can also be independently performed on the model.
The syndrome differentiation system of the traditional Chinese medicine in the embodiment of the application adopts the syndrome differentiation method, and combines a traditional Chinese medicine knowledge base, trains a syndrome differentiation model based on traditional Chinese medicine description by utilizing the medical case data of the old traditional Chinese medicine, and ensures the reliability of the syndrome differentiation system; by utilizing an online learning technology, continuously training a syndrome differentiation model by continuously collecting data, and continuously improving the prediction accuracy of the syndrome differentiation model; meanwhile, a result checking module is provided to prevent syndrome differentiation errors caused by inaccurate symptom description or excessively complex symptoms, and further improve syndrome differentiation accuracy.
Example 3
According to the embodiment of the application, an embodiment of a certificate type recommendation device is also provided. Fig. 8 is a schematic structural diagram of a certificate-type recommendation device according to an embodiment of the present application. As shown in fig. 8, the apparatus includes:
the data acquisition module 80 is configured to acquire original text information, where the original text information includes: the inquiry text information and the medical record text information;
the vectorization module 82 is configured to perform vectorization processing on the original text information according to the pre-training model to obtain target vector data, where the target vector data includes: the medical record data comprises inquiry vector data and medical record vector data, wherein the inquiry vector data is target vector data obtained by vectorizing inquiry text information, and the medical record vector data is target vector data obtained by vectorizing medical record text information;
the feature extraction module 84 is configured to perform feature extraction on the medical record vector data by using a first neural network to obtain first feature data, and perform feature extraction on the inquiry vector data by using a second neural network to obtain second feature data;
the certificate recommendation module 86 is configured to determine a target certificate according to the first feature data and the second feature data.
Note that each module in the above-described certification recommendation apparatus may be a program module (for example, a set of program instructions for implementing a specific function), or may be a hardware module, and for the latter, it may be represented by the following form, but is not limited thereto: the expression forms of the modules are all a processor, or the functions of the modules are realized by one processor.
It should be noted that, the certification recommending apparatus provided in the present embodiment may be used to execute the certification recommending method shown in fig. 1, so that the explanation of the certification recommending method is also applicable to the embodiment of the present application, and is not repeated here.
Example 4
According to an embodiment of the present application, there is also provided an embodiment of a computer terminal for implementing the method of syndrome recommendation. Fig. 9 is a block diagram of a hardware architecture of a computer terminal (or electronic device) for implementing a method of certification recommendation according to an embodiment of the present application. As shown in fig. 9, the computer terminal 90 (or electronic device 90) may include one or more (shown in the figures as 902a, 902b, … …,902 n) processors (which may include, but are not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA), a memory 904 for storing data, and a transmission module 906 for communication functions. In addition, the method may further include: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power supply, and/or a camera. It will be appreciated by those skilled in the art that the configuration shown in fig. 9 is merely illustrative and is not intended to limit the configuration of the electronic device. For example, the computer terminal 90 may also include more or fewer components than shown in FIG. 9, or have a different configuration than shown in FIG. 9.
It should be noted that the one or more processors and/or other data processing circuits described above may be referred to herein generally as "data processing circuits. The data processing circuit may be embodied in whole or in part in software, hardware, firmware, or any other combination. Furthermore, the data processing circuitry may be a single stand-alone processing module, or incorporated, in whole or in part, into any of the other elements in the computer terminal 90 (or electronic device). As referred to in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of the path of the variable resistor termination to interface).
The memory 904 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the method of syndrome recommendation in the embodiments of the present application, and the processor executes the software programs and modules stored in the memory 904, thereby performing various functional applications and data processing, that is, implementing the method of syndrome recommendation described above. The memory 904 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 904 may further include memory located remotely from the processor, which may be connected to the computer terminal 90 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission module 906 is used to receive or transmit data via a network. The specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 90. In one example, the transmission means 906 comprises a network adapter (Network Interface Controller, NIC) that can be connected to other network devices via a base station to communicate with the internet. In one example, the transmission device 906 may be a Radio Frequency (RF) module for communicating with the internet wirelessly.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 90 (or electronic device).
It should be noted here that, in some alternative embodiments, the computer device (or the electronic device) shown in fig. 9 may include hardware elements (including circuits), software elements (including computer code stored on a computer readable medium), or a combination of both hardware elements and software elements. It should be noted that fig. 9 is only one example of a specific example, and is intended to illustrate the types of components that may be present in the above-described computer device (or electronic device).
It should be noted that, the electronic device for the syndrome recommendation shown in fig. 9 is used to execute the method for the syndrome recommendation shown in fig. 1, so the explanation of the method for the syndrome recommendation is also applicable to the electronic device for the syndrome recommendation, which is not described herein.
Example 5
According to still another aspect of the embodiments of the present application, there is further provided a nonvolatile storage medium, the nonvolatile storage medium including a stored computer program, wherein a device in which the nonvolatile storage medium is located executes the following certification recommendation method by running the computer program: acquiring original text information, wherein the original text information comprises: the inquiry text information and the medical record text information; according to the pre-training model, carrying out vectorization processing on the original text information to obtain target vector data, wherein the target vector data comprises: the medical record data comprises inquiry vector data and medical record vector data, wherein the inquiry vector data is target vector data obtained by vectorizing inquiry text information, and the medical record vector data is target vector data obtained by vectorizing medical record text information; performing feature extraction on medical record vector data by using a first neural network to obtain first feature data, and performing feature extraction on inquiry vector data by using a second neural network to obtain second feature data; and determining the target certificate according to the first characteristic data and the second characteristic data.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, for example, may be a logic function division, and may be implemented in another manner, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.
Claims (7)
1. A certification recommendation method, comprising:
obtaining original text information, wherein the original text information comprises: the inquiry text information and the medical record text information;
performing vectorization processing on the original text information according to a pre-training model to obtain target vector data, wherein the target vector data comprises: the medical record training system comprises inquiry vector data and medical record vector data, wherein the inquiry vector data is target vector data obtained after vectorizing the inquiry text information, the medical record vector data is target vector data obtained after vectorizing the medical record text information, and the pre-training model is obtained through training of the following steps: acquiring pre-training text information, wherein the pre-training text information is acquired from a traditional Chinese medicine knowledge base, and the traditional Chinese medicine knowledge base stores text information for recording traditional Chinese medicine knowledge; selecting words in the pre-training text information according to a preset probability to cover; training an initial model according to covered words and uncovered words in the pre-training text information to obtain the pre-training model;
Performing feature extraction on the medical record vector data by using a first neural network to obtain first feature data, and performing feature extraction on the inquiry vector data by using a second neural network to obtain second feature data, wherein the feature extraction comprises the following steps: convolving the medical record vector data; determining an activation function and a first maximum pooling function corresponding to the first neural network; according to the activation function and the first maximum pooling function, calculating the medical record vector data subjected to convolution processing to obtain the first characteristic data; performing feature extraction on the query vector data according to the second neural network to obtain second feature data, including: establishing a target relation graph according to the inquiry vector data, wherein the target relation graph is used for representing the relation between word vectors in the inquiry vector data; determining a target adjacent matrix and target training parameters corresponding to the target relation graph; calculating influence coefficients of word vectors in the inquiry vector data according to the target adjacent matrix and the target training parameters, wherein the influence coefficients are used for representing influence degrees of the word vectors on other word vectors in the inquiry vector data; determining the second characteristic data according to the influence coefficient and a second maximum pooling function, wherein the first neural network is a convolutional neural network and the second neural network is a graph neural network;
And determining the target certificate according to the first characteristic data and the second characteristic data.
2. The method of claim 1, wherein vectorizing the original text information according to a pre-training model to obtain target vector data comprises:
determining a word vector of each word in the original text information;
determining sentence vectors of sentences in which the word vectors are located in the original text information;
determining a position vector corresponding to the word vector, wherein the position vector is used for representing the position information of the word vector in the sentence;
and inputting the word vector, the sentence vector and the position vector into the pre-training model for processing to obtain the target vector data.
3. The method of claim 1, wherein determining a target pattern based on the first and second characteristic data comprises:
calculating the confidence coefficient of each syndrome according to the first characteristic data, the second characteristic data and the target classifier;
and determining the pattern with the highest confidence as the target pattern.
4. The method of claim 3, further comprising, prior to calculating the confidence level for each syndrome based on the first feature data, the second feature data, and the target classifier:
Obtaining training data, wherein the training data comprises: characteristic data, a syndrome type and a corresponding relation between the characteristic data and the syndrome type;
determining a target association relationship between the feature data and the syndrome according to the training data;
and generating the target classifier according to the target association relation.
5. A certification recommendation apparatus, comprising:
the data acquisition module is used for acquiring original text information, wherein the original text information comprises: the inquiry text information and the medical record text information;
the vectorization module is used for vectorizing the original text information according to a pre-training model to obtain target vector data, wherein the target vector data comprises: the medical record training system comprises inquiry vector data and medical record vector data, wherein the inquiry vector data is target vector data obtained after vectorizing the inquiry text information, the medical record vector data is target vector data obtained after vectorizing the medical record text information, and the pre-training model is obtained through training of the following steps: acquiring pre-training text information, wherein the pre-training text information is acquired from a traditional Chinese medicine knowledge base, and the traditional Chinese medicine knowledge base stores text information for recording traditional Chinese medicine knowledge; selecting words in the pre-training text information according to a preset probability to cover; training an initial model according to covered words and uncovered words in the pre-training text information to obtain the pre-training model;
The feature extraction module is configured to perform feature extraction on the medical record vector data by using a first neural network to obtain first feature data, and perform feature extraction on the inquiry vector data by using a second neural network to obtain second feature data, and includes: convolving the medical record vector data; determining an activation function and a first maximum pooling function corresponding to the first neural network; according to the activation function and the first maximum pooling function, calculating the medical record vector data subjected to convolution processing to obtain the first characteristic data; performing feature extraction on the query vector data according to the second neural network to obtain second feature data, including: establishing a target relation graph according to the inquiry vector data, wherein the target relation graph is used for representing the relation between word vectors in the inquiry vector data; determining a target adjacent matrix and target training parameters corresponding to the target relation graph; calculating influence coefficients of word vectors in the inquiry vector data according to the target adjacent matrix and the target training parameters, wherein the influence coefficients are used for representing influence degrees of the word vectors on other word vectors in the inquiry vector data; determining the second characteristic data according to the influence coefficient and a second maximum pooling function, wherein the first neural network is a convolutional neural network and the second neural network is a graph neural network;
And the pattern recommending module is used for determining a target pattern according to the first characteristic data and the second characteristic data.
6. An electronic device comprising a processor, wherein the processor is configured to run a program, wherein the program is configured to perform the certification recommendation method of any one of claims 1 to 4 when run.
7. A non-volatile storage medium, characterized in that the non-volatile storage medium comprises a stored computer program, wherein the device in which the non-volatile storage medium is located performs the method for recommending a certificate according to any of claims 1 to 4 by running the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211363166.0A CN115631852B (en) | 2022-11-02 | 2022-11-02 | Certificate type recommendation method and device, electronic equipment and nonvolatile storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211363166.0A CN115631852B (en) | 2022-11-02 | 2022-11-02 | Certificate type recommendation method and device, electronic equipment and nonvolatile storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115631852A CN115631852A (en) | 2023-01-20 |
| CN115631852B true CN115631852B (en) | 2024-04-09 |
Family
ID=84907930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211363166.0A Active CN115631852B (en) | 2022-11-02 | 2022-11-02 | Certificate type recommendation method and device, electronic equipment and nonvolatile storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115631852B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117995347A (en) * | 2024-04-07 | 2024-05-07 | 北京惠每云科技有限公司 | Medical record content quality control method and device, electronic equipment and storage medium |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223749A (en) * | 2019-06-14 | 2019-09-10 | 电子科技大学 | Chinese medical discrimination aid decision-making method based on PCNN network and attention mechanism |
| CN110600123A (en) * | 2019-08-29 | 2019-12-20 | 成都信息工程大学 | Clinical auxiliary diagnosis method for traditional Chinese medicine |
| CN110706768A (en) * | 2019-09-09 | 2020-01-17 | 安徽中医药大学 | Method for summarizing traditional Chinese medicine insomnia diagnosis information and medication rule |
| CN111276258A (en) * | 2020-01-15 | 2020-06-12 | 大连理工大学 | Medicine pathogenic relation extraction method based on domain knowledge |
| CN111554371A (en) * | 2020-03-30 | 2020-08-18 | 平安医疗健康管理股份有限公司 | Internet data processing method and device, computer equipment and storage medium |
| CN112561165A (en) * | 2020-12-16 | 2021-03-26 | 南京航空航天大学 | Multidimensional time series data prediction method based on combined model |
| CN113223735A (en) * | 2021-04-30 | 2021-08-06 | 平安科技（深圳）有限公司 | Triage method, device and equipment based on session representation and storage medium |
| CN113345574A (en) * | 2021-05-26 | 2021-09-03 | 复旦大学 | Traditional Chinese medicine stomachache health preserving scheme obtaining device based on BERT language model and CNN model |
| CN113724882A (en) * | 2021-08-30 | 2021-11-30 | 康键信息技术（深圳）有限公司 | Method, apparatus, device and medium for constructing user portrait based on inquiry session |
| CN113808693A (en) * | 2021-09-10 | 2021-12-17 | 浙江科技学院 | Medicine recommendation method based on graph neural network and attention mechanism |
| CN113868374A (en) * | 2021-09-15 | 2021-12-31 | 西安交通大学 | Graph convolution network biomedical information extraction method based on multi-head attention mechanism |
| WO2022041727A1 (en) * | 2020-08-28 | 2022-03-03 | 康键信息技术（深圳）有限公司 | Question and answer management method, apparatus, and device for medical inquiry system, and storage medium |
| CN114154514A (en) * | 2022-02-07 | 2022-03-08 | 北京三子健康科技有限公司 | Traditional Chinese medicine syndrome type identification method and system |
| CN114428860A (en) * | 2022-01-26 | 2022-05-03 | 河北工程大学 | Pre-hospital emergency case text recognition method and device, terminal and storage medium |
| CN114512228A (en) * | 2022-02-08 | 2022-05-17 | 吾征智能技术(北京)有限公司 | Traditional Chinese medicine disease auxiliary diagnosis system, equipment and storage medium |
| CN114520053A (en) * | 2022-02-22 | 2022-05-20 | 平安科技（深圳）有限公司 | Medical information processing method, system, terminal and storage medium |
| CN114579723A (en) * | 2022-03-02 | 2022-06-03 | 平安科技（深圳）有限公司 | Interrogation method and apparatus, electronic device, and storage medium |
| CN114783618A (en) * | 2022-05-17 | 2022-07-22 | 平安科技（深圳）有限公司 | Traditional Chinese medicine model training method and device based on knowledge structure and four-diagnosis character |
| CN114970508A (en) * | 2022-05-17 | 2022-08-30 | 国网浙江省电力有限公司电力科学研究院 | Power text knowledge discovery method and device based on data multi-source fusion |
| CN115083628A (en) * | 2022-08-19 | 2022-09-20 | 成都中医药大学 | Medical education cooperative system based on traditional Chinese medicine inspection objectivity |
-
2022
- 2022-11-02 CN CN202211363166.0A patent/CN115631852B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223749A (en) * | 2019-06-14 | 2019-09-10 | 电子科技大学 | Chinese medical discrimination aid decision-making method based on PCNN network and attention mechanism |
| CN110600123A (en) * | 2019-08-29 | 2019-12-20 | 成都信息工程大学 | Clinical auxiliary diagnosis method for traditional Chinese medicine |
| CN110706768A (en) * | 2019-09-09 | 2020-01-17 | 安徽中医药大学 | Method for summarizing traditional Chinese medicine insomnia diagnosis information and medication rule |
| CN111276258A (en) * | 2020-01-15 | 2020-06-12 | 大连理工大学 | Medicine pathogenic relation extraction method based on domain knowledge |
| CN111554371A (en) * | 2020-03-30 | 2020-08-18 | 平安医疗健康管理股份有限公司 | Internet data processing method and device, computer equipment and storage medium |
| WO2022041727A1 (en) * | 2020-08-28 | 2022-03-03 | 康键信息技术（深圳）有限公司 | Question and answer management method, apparatus, and device for medical inquiry system, and storage medium |
| CN112561165A (en) * | 2020-12-16 | 2021-03-26 | 南京航空航天大学 | Multidimensional time series data prediction method based on combined model |
| CN113223735A (en) * | 2021-04-30 | 2021-08-06 | 平安科技（深圳）有限公司 | Triage method, device and equipment based on session representation and storage medium |
| CN113345574A (en) * | 2021-05-26 | 2021-09-03 | 复旦大学 | Traditional Chinese medicine stomachache health preserving scheme obtaining device based on BERT language model and CNN model |
| CN113724882A (en) * | 2021-08-30 | 2021-11-30 | 康键信息技术（深圳）有限公司 | Method, apparatus, device and medium for constructing user portrait based on inquiry session |
| CN113808693A (en) * | 2021-09-10 | 2021-12-17 | 浙江科技学院 | Medicine recommendation method based on graph neural network and attention mechanism |
| CN113868374A (en) * | 2021-09-15 | 2021-12-31 | 西安交通大学 | Graph convolution network biomedical information extraction method based on multi-head attention mechanism |
| CN114428860A (en) * | 2022-01-26 | 2022-05-03 | 河北工程大学 | Pre-hospital emergency case text recognition method and device, terminal and storage medium |
| CN114154514A (en) * | 2022-02-07 | 2022-03-08 | 北京三子健康科技有限公司 | Traditional Chinese medicine syndrome type identification method and system |
| CN114512228A (en) * | 2022-02-08 | 2022-05-17 | 吾征智能技术(北京)有限公司 | Traditional Chinese medicine disease auxiliary diagnosis system, equipment and storage medium |
| CN114520053A (en) * | 2022-02-22 | 2022-05-20 | 平安科技（深圳）有限公司 | Medical information processing method, system, terminal and storage medium |
| CN114579723A (en) * | 2022-03-02 | 2022-06-03 | 平安科技（深圳）有限公司 | Interrogation method and apparatus, electronic device, and storage medium |
| CN114783618A (en) * | 2022-05-17 | 2022-07-22 | 平安科技（深圳）有限公司 | Traditional Chinese medicine model training method and device based on knowledge structure and four-diagnosis character |
| CN114970508A (en) * | 2022-05-17 | 2022-08-30 | 国网浙江省电力有限公司电力科学研究院 | Power text knowledge discovery method and device based on data multi-source fusion |
| CN115083628A (en) * | 2022-08-19 | 2022-09-20 | 成都中医药大学 | Medical education cooperative system based on traditional Chinese medicine inspection objectivity |
Non-Patent Citations (2)
| Title |
|---|
| 曹彬 ; 王峰 ; 李诗语 ; .面向中医领域的智能聊天机器人系统设计.电脑知识与技术.2019,(12),全文. * |
| 许朝霞 ; 王忆勤 ; 颜建军 ; 郭睿 ; 刘国萍 ; 燕海霞 ; 李福凤 ; 徐琎 ; 郝一鸣 ; 钱鹏 ; .基于支持向量机和人工神经网络的心血管疾病中医证候分类识别研究.北京中医药大学学报.2011,(08),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115631852A (en) | 2023-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109669994B (en) | Construction method and system of health knowledge map | |
| CN110490251B (en) | Artificial intelligence-based prediction classification model obtaining method and device and storage medium | |
| CN107016438B (en) | System based on traditional Chinese medicine syndrome differentiation artificial neural network algorithm model | |
| CN109637669B (en) | Deep learning-based treatment scheme generation method, device and storage medium | |
| CN110297908A (en) | Diagnosis and treatment program prediction method and device | |
| CN110516161A (en) | A kind of recommended method and device | |
| CN109670179A (en) | Case history text based on iteration expansion convolutional neural networks names entity recognition method | |
| CN111316281A (en) | Semantic classification of numerical data in natural language context based on machine learning | |
| CN106874643A (en) | Build the method and system that knowledge base realizes assisting in diagnosis and treatment automatically based on term vector | |
| CN116682553B (en) | Diagnosis recommendation system integrating knowledge and patient representation | |
| CN112100406B (en) | Data processing method, device, equipment and medium | |
| CN112182168B (en) | Medical record text analysis method and device, electronic equipment and storage medium | |
| CN110277167A (en) | The Chronic Non-Communicable Diseases Risk Forecast System of knowledge based map | |
| WO2023029502A1 (en) | Method and apparatus for constructing user portrait on the basis of inquiry session, device, and medium | |
| CN113035362A (en) | Medical prediction method and system based on semantic graph network | |
| CN115631852B (en) | Certificate type recommendation method and device, electronic equipment and nonvolatile storage medium | |
| CN112420191A (en) | Traditional Chinese medicine auxiliary decision making system and method | |
| CN115858886B (en) | Data processing method, device, equipment and readable storage medium | |
| CN117077786A (en) | Knowledge graph-based data knowledge dual-drive intelligent medical dialogue system and method | |
| CN116364299A (en) | Disease diagnosis and treatment path clustering method and system based on heterogeneous information network | |
| CN112447270A (en) | Medication recommendation method, device, equipment and storage medium | |
| CN114420279A (en) | Medical resource recommendation method, device, equipment and storage medium | |
| CN115631851A (en) | Prescription recommendation method and device, electronic equipment and nonvolatile storage medium | |
| CN112435745B (en) | Method and device for recommending treatment strategy, electronic equipment and storage medium | |
| CN115565636A (en) | Drug recommendation model construction method, device, equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |