CN114881153A - Disease category analysis method, device, equipment and medium based on multi-task combination - Google Patents
Disease category analysis method, device, equipment and medium based on multi-task combination Download PDFInfo
- Publication number
- CN114881153A CN114881153A CN202210516140.9A CN202210516140A CN114881153A CN 114881153 A CN114881153 A CN 114881153A CN 202210516140 A CN202210516140 A CN 202210516140A CN 114881153 A CN114881153 A CN 114881153A
- Authority
- CN
- China
- Prior art keywords
- inquiry
- disease category
- vector
- calculating
- disease
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 181
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 181
- 238000004458 analytical method Methods 0.000 title claims abstract description 75
- 230000004913 activation Effects 0.000 claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 238000013507 mapping Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 3
- 230000006870 function Effects 0.000 claims description 129
- 230000000306 recurrent effect Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 13
- 210000002569 neuron Anatomy 0.000 claims description 12
- 239000012634 fragment Substances 0.000 claims description 6
- 238000012512 characterization method Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 8
- 208000011580 syndromic disease Diseases 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000001124 body fluid Anatomy 0.000 description 1
- 239000010839 body fluid Substances 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- 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)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the field of intelligent decision, and discloses a disease category analysis method, a device, electronic equipment and a storage medium based on multi-task combination, wherein the method comprises the steps of obtaining inquiry information, mapping the inquiry information to a hidden layer in an input layer of a preset cyclic neural network to obtain an inquiry vector; performing feature extraction on the inquiry vector by using the multilayer perceptron of the hidden layer to obtain inquiry features; constructing an activation function of the inquiry features, calculating a loss value of the activation function through a cross entropy function, optimizing the loss value through a preset optimization algorithm, and outputting the activation function corresponding to the optimized loss value to obtain a target function; and calculating the inquiry characteristics by using the target function to obtain a disease category probability, and determining a disease category corresponding to the inquiry information according to the disease category probability. The invention can improve the accuracy of disease category analysis.
Description
Technical Field
The invention relates to the field of intelligent decision making, in particular to a disease category analysis method and device based on multitask union, electronic equipment and a computer readable storage medium.
Background
The disease category analysis based on the multitask combination refers to that when a patient is subjected to inquiry, the inquiry information of the patient is divided into a plurality of dimensions according to the inquiry information provided by the patient, and each dimension is designed into a plurality of tasks to analyze the disease category of the patient.
At present, when the disease category is analyzed, many subdivision processes are needed to be carried out on the disease, for example, when the disease of a patient is a cold disease, the syndrome of the cold disease obtained by attacking the muscle surface, the channels and collaterals and the internal organs due to wind-dryness evil is a wind-dryness syndrome, the syndrome of the cold disease obtained by attacking the muscle surface, obstructing defensive qi and insufficient body fluid due to wind-dryness evil is a wind-dryness syndrome, and the subdivision characteristics lead to a plurality of types of syndromes, thus leading to very difficult accurate identification and diagnosis of the syndromes. Therefore, the accuracy of disease category analysis is low.
Disclosure of Invention
The invention provides a disease category analysis method and device based on multi-task combination, electronic equipment and a computer readable storage medium, and mainly aims to improve the accuracy of disease category analysis.
In order to achieve the above object, the present invention provides a disease category analysis method based on multitask combination, including:
acquiring inquiry information, and mapping the inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector;
performing feature extraction on the inquiry vector by using the multilayer perceptron of the hidden layer to obtain inquiry features;
constructing an activation function of the inquiry features, calculating a loss value of the activation function through a cross entropy function, optimizing the loss value through a preset optimization algorithm, and outputting the activation function corresponding to the optimized loss value to obtain a target function;
and calculating the inquiry characteristics by using the target function to obtain a disease category probability, and determining a disease category corresponding to the inquiry information according to the disease category probability.
Optionally, the mapping the inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector includes:
decomposing the inquiry information through the neurons of the input layer to obtain information fragments of the inquiry information;
and forming the information fragments into a feature vector, and performing linear combination mapping on the feature vector to a hidden layer to obtain the inquiry vector.
Optionally, the performing feature extraction on the inquiry vector by using the multilayer sensor of the hidden layer to obtain inquiry features includes:
randomly initializing the inquiry vector by using neurons in the multilayer perceptron to obtain an initialization vector;
calculating weight values and bias values of the initialization vector by using neurons in the multilayer perceptron;
and calculating an inquiry feature score of the inquiry vector according to the weight value and the bias value, and taking the inquiry vector with the inquiry feature score larger than a preset score as the inquiry feature.
Optionally, the calculating a feature score of the inquiry vector according to the weight value and the bias value to obtain an inquiry feature of the inquiry vector includes:
calculating a feature score for the interrogation vector by the following formula:
O i ＝<x,w i >+b i
wherein, O i A feature score representing the ith feature of the interrogation vector, x represents the interrogation vector, w i Is a weight value, b i Is an offset value.
Optionally, said calculating a loss value of said activation function by a cross entropy function comprises:
acquiring training data of the activation function, and marking the real disease category of the training data;
calculating an analysis disease category of the training data using the activation function;
calculating the category loss of the real disease category and the analysis disease category through the cross entropy function to obtain a loss value of the activation function.
Optionally, the calculating the class loss of the real disease class and the analysis disease class by the cross entropy function to obtain the loss value of the activation function includes:
calculating a loss value of the activation function by the following formula:
wherein H represents a loss value, y represents an analysis disease class, and y represents ′ Representing the actual disease category.
Optionally, the calculating the inquiry features by using the objective function to obtain the disease category probability includes:
calculating the disease category probability by the following formula:
wherein, y i Representing the probability of a disease class, o i A feature score for the ith feature representing the characterization of the interrogation,
represents the total feature score of the inquiry features, exp refers to an exponential function with a natural constant e as the base.
In order to solve the above problems, the present invention also provides a disease category analysis device based on multitask combination, the device comprising:
the inquiry information mapping module is used for acquiring inquiry information and mapping the inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector;
the data feature extraction module is used for extracting features of the inquiry vector by utilizing the multilayer perceptron of the hidden layer to obtain inquiry features;
the activation function output module is used for constructing an activation function of the inquiry features, calculating a loss value of the activation function through a cross entropy function, optimizing the loss value through a preset optimization algorithm, and outputting the activation function corresponding to the optimized loss value to obtain a target function;
and the disease category determining module is used for calculating the inquiry characteristics by using the target function to obtain a disease category probability, and determining a disease category corresponding to the inquiry information according to the disease category probability.
In order to solve the above problem, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to implement the above-described method for multi-task association based disease category analysis.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the method for analyzing disease category based on multitask union.
It can be seen that, in the embodiments of the present invention, by obtaining inquiry information, which is used as training data of a disease category analysis model, machine learning of the disease category analysis model is facilitated according to the inquiry information, further, in the embodiments of the present invention, the inquiry information is mapped to a hidden layer in an input layer of a recurrent neural network, so as to obtain an inquiry vector, which is used for decomposing the inquiry information and converting the inquiry information into information that can be recognized by a machine, further, in the embodiments of the present invention, a multi-layer sensor of the hidden layer is used for performing feature extraction on the inquiry vector, so as to obtain inquiry features, which are used for capturing data features of the inquiry information, so as to facilitate analysis of disease categories according to the data features, further, in the embodiments of the present invention, by constructing an activation function of the inquiry features, so as to represent scrambled data by probability distribution, the analysis result of the disease category can be intuitively obtained, further, the loss value of the activation function is measured through a cross entropy function to obtain the difference between the analysis result of the disease category and the actual disease category, further, the loss value is optimized through a preset optimization algorithm to improve the accuracy of the disease category analysis model for analyzing the disease category, further, the activation function corresponding to the optimized loss value is output to obtain a target function to obtain the optimal activation function algorithm for analyzing the disease category, the accuracy of the disease category analysis is improved, further, the disease category probability of the inquiry feature is calculated through the target function to calculate the probability of the disease category through a formula, so that the final disease category analysis is obtained according to the probability, further, according to the disease category probability, the disease category corresponding to the inquiry information is generated, so that the disease category with high probability is used as a final result of the disease category analysis, and the disease category is analyzed. Therefore, the disease category analysis method, device, electronic device and computer-readable storage medium based on multi-task association provided by the embodiment of the invention can improve the accuracy of disease category analysis.
Drawings
FIG. 1 is a schematic flow chart of a disease category analysis method based on multitask union according to an embodiment of the present invention;
FIG. 2 is a block diagram of a disease category analysis device based on multitask association according to an embodiment of the present invention;
fig. 3 is a schematic internal structural diagram of an electronic device implementing a disease category analysis method based on multitask union according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention provides a disease category analysis method based on multi-task combination. The execution subject of the disease category analysis method based on multitask union includes but is not limited to at least one of the electronic devices, such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present invention. In other words, the disease category analysis method based on multitask union may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Referring to fig. 1, a flow chart of a disease category analysis method based on multitask union according to an embodiment of the present invention is schematically shown. In an embodiment of the present invention, the disease category analysis method based on multitask combination includes the following steps S1-S4:
s1, obtaining inquiry information, and mapping the inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector.
According to the embodiment of the invention, the inquiry information is obtained and used as the training data of the disease category analysis model, so that the disease category analysis model can conveniently carry out machine learning according to the inquiry information.
The inquiry information includes the name, sex, chief complaint, current medical history, past history and other contents of the patient.
Furthermore, the inquiry information is mapped to a hidden layer in an input layer of a preset cyclic neural network to obtain an inquiry vector, and the inquiry vector is used for decomposing the inquiry information and converting the inquiry information into information which can be recognized by a machine.
The preset recurrent neural network is a recurrent neural network which takes sequence data as input, recurses in the evolution direction of the sequence and all nodes are connected in a chain manner, and the hidden layer is other layers except an input layer and an output layer.
Further, as an embodiment of the present invention, the mapping the inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector includes: decomposing the inquiry information through the neurons of the input layer to obtain information fragments of the inquiry information; and forming the information fragments into a feature vector, and performing linear combination mapping on the feature vector to a hidden layer to obtain the inquiry vector.
And S2, performing feature extraction on the inquiry vector by using the multilayer perceptron of the hidden layer to obtain inquiry features.
According to the embodiment of the invention, the inquiry vector is subjected to feature extraction by utilizing the multilayer perceptron of the hidden layer to obtain the inquiry features, so that the data features of the inquiry information can be captured, and the disease category can be conveniently analyzed according to the data features.
The multi-layer perceptron is a feedforward artificial neural network model, which maps multiple input data sets onto a single output data set.
As an embodiment of the present invention, the performing feature extraction on the inquiry vector by using the multilayer sensor of the hidden layer to obtain an inquiry feature includes: randomly initializing the inquiry vector by using neurons in the multilayer perceptron to obtain an initialization vector; calculating weight values and bias values of the initialization vector by using neurons in the multilayer perceptron; and calculating an inquiry feature score of the inquiry vector according to the weight value and the bias value, and taking the inquiry vector with the inquiry feature score larger than a preset score as the inquiry feature.
Further, as another embodiment of the present invention, the calculating a feature score of the inquiry vector according to the weight value and the bias value to obtain the inquiry feature of the inquiry vector includes: calculating a feature score for the interrogation vector by the following formula:
O i ＝<x,w i >+b i
wherein, O i A feature score representing the ith feature of the interrogation vector, x represents the interrogation vector, w i Is a weight value, b i Is an offset value.
S3, constructing an activation function of the inquiry features, calculating a loss value of the activation function through a cross entropy function, optimizing the loss value through a preset optimization algorithm, and outputting the activation function corresponding to the optimized loss value to obtain a target function.
According to the embodiment of the invention, the activation function of the inquiry characteristic is constructed to express the disordered data through probability distribution, so that the analysis result of the disease category can be intuitively obtained.
Where the activation function is a function added to an artificial neural network intended to help the network learn complex patterns in the data, similar to a neuron-based model in the human brain, the activation function ultimately determines what is to be transmitted to the next neuron.
As an embodiment of the present invention, the constructing an activation function of the inquiry feature includes: constructing an activation function for the interrogation feature by the following formula:
wherein o is i A score representing the ith feature of the interrogation vector,
represents the total score of the inquiry features, exp refers to an exponential function with a natural constant e as the base.
Further, the embodiment of the present invention measures the loss value of the activation function through a cross entropy function, so as to obtain the difference between the disease category analysis result and the actual disease category.
The cross entropy function is used for measuring the similarity between two groups of random variables and is mainly used for measuring the similarity between the probability of the model identification value and the true value.
Further, as an embodiment of the present invention, the calculating the loss value of the activation function by a cross entropy function includes: acquiring training data of the activation function, and marking the real disease category of the training data; calculating an analysis disease category of the training data using the activation function; calculating the category loss of the real disease category and the analysis disease category through the cross entropy function to obtain a loss value of the activation function.
Further, as another embodiment of the present invention, the calculating the class loss of the real disease class and the analysis disease class by the cross entropy function to obtain the loss value of the activation function includes:
calculating a loss value of the activation function by the following formula:
wherein H represents a loss value, y represents an analysis disease class, and y represents ′ Representing the actual disease category.
Further, the loss value is optimized through a preset optimization algorithm so as to improve the accuracy of the disease category analysis model on the disease category analysis.
Illustratively, as an embodiment of the present invention, the loss value is optimized by a preset optimization algorithm and is implemented by a gradient back propagation algorithm, where the gradient back propagation algorithm is a learning algorithm suitable for a multi-layer neuron network, and is established on the basis of a gradient descent method, and it implements a fast training model to improve the efficiency of data analysis.
Further, the embodiment of the invention outputs the activation function corresponding to the optimized loss value to obtain the target function, so as to obtain the optimal activation function algorithm for disease category analysis and improve the accuracy of disease category analysis.
Further, as an embodiment of the present invention, the outputting the activation function corresponding to the optimized loss value to obtain an objective function includes: updating the weight value and the bias value of the activation function according to the optimized loss value to obtain an updated weight value and an updated bias value; and calculating the updating weight value and the bias value to obtain an updating feature score, and replacing the input data of the activation function with the feature score to obtain a target function.
Illustratively, the updating of the weight value and the bias value of the activation function according to the optimized loss value is realized by randomly generating parameters through a neural network, the updating of the weight value and the bias value is calculated to obtain an updated feature score, the input data of the activation function is replaced by the feature score, and the process of obtaining a target function is consistent with the process of calculating the feature score of the inquiry vector according to the weight value and the bias value, which is not repeated herein.
S4, calculating the inquiry characteristics by using the objective function to obtain disease category probability, and determining the disease category corresponding to the inquiry information according to the disease category probability.
According to the embodiment of the invention, the disease category probability of the inquiry characteristics is calculated by utilizing the objective function so as to calculate the probability of occurrence of the disease category through a formula, so that the final disease category analysis is obtained according to the probability.
As an embodiment of the present invention, the calculating the inquiry features by using the objective function to obtain the disease category probability includes:
calculating the disease category probability by the following formula:
wherein, y i Representing the probability of a disease class, o i A feature score for the ith feature representing the characterization of the interrogation,
represents the total feature score of the inquiry features, exp refers to an exponential function with a natural constant e as the base.
Further, according to the disease category probability, the disease category corresponding to the inquiry information is generated, so that the disease category with high probability is used as a final result of the disease category analysis, and the disease category is analyzed.
Further, as an embodiment of the present invention, the generating a disease category corresponding to the inquiry information according to the disease category probability includes: acquiring actual disease types from a disease database, and extracting the maximum probability from the disease type probabilities to obtain a target probability; and identifying an analysis disease category corresponding to the target probability, matching the actual disease category with the analysis disease category, and when the actual disease category is successfully matched with the analysis disease category, taking the analysis disease category as the disease category corresponding to the inquiry information.
It can be seen that, in the embodiments of the present invention, by obtaining inquiry information, which is used as training data of a disease category analysis model, machine learning of the disease category analysis model is facilitated according to the inquiry information, further, in the embodiments of the present invention, the inquiry information is mapped to a hidden layer in an input layer of a recurrent neural network, so as to obtain an inquiry vector, which is used for decomposing the inquiry information and converting the inquiry information into information that can be recognized by a machine, further, in the embodiments of the present invention, a multi-layer sensor of the hidden layer is used for performing feature extraction on the inquiry vector, so as to obtain inquiry features, which are used for capturing data features of the inquiry information, so as to facilitate analysis of disease categories according to the data features, further, in the embodiments of the present invention, by constructing an activation function of the inquiry features, so as to represent scrambled data by probability distribution, the analysis result of the disease category can be intuitively obtained, further, the loss value of the activation function is measured through a cross entropy function to obtain the difference between the analysis result of the disease category and the actual disease category, further, the loss value is optimized through a preset optimization algorithm to improve the accuracy of the disease category analysis model for analyzing the disease category, further, the activation function corresponding to the optimized loss value is output to obtain a target function to obtain the optimal activation function algorithm for analyzing the disease category, the accuracy of the disease category analysis is improved, further, the disease category probability of the inquiry feature is calculated through the target function to calculate the probability of the disease category through a formula, so that the final disease category analysis is obtained according to the probability, further, according to the disease category probability, the disease category corresponding to the inquiry information is generated, so that the disease category with high probability is used as a final result of the disease category analysis, and the disease category is analyzed. Therefore, the disease category analysis method based on the multitask combination provided by the embodiment of the invention can improve the accuracy of the disease category analysis.
FIG. 2 is a functional block diagram of the disease category analyzing apparatus based on multitask combination according to the present invention.
The disease category analysis device 100 based on multitask association according to the present invention may be installed in an electronic device. According to the implemented functions, the disease category analysis device based on multitask combination may include an inquiry information mapping module 101, a data feature extraction module 102, an activation function output module 103, and a disease category determination module 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and can perform a fixed function, and is stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the inquiry information mapping module 101 is configured to obtain inquiry information, and map the inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector;
the data feature extraction module 102 is configured to perform feature extraction on the inquiry vector by using the multilayer perceptron of the hidden layer to obtain inquiry features;
the activation function output module 103 is configured to construct an activation function of the inquiry features, calculate a loss value of the activation function through a cross entropy function, optimize the loss value through a preset optimization algorithm, and output the activation function corresponding to the optimized loss value to obtain a target function;
the disease category determining module 104 is configured to calculate the inquiry features by using the objective function to obtain a disease category probability, and determine a disease category corresponding to the inquiry information according to the disease category probability.
In detail, when the modules in the apparatus 100 for analyzing disease category based on multitask combination according to the embodiment of the present invention are used, the same technical means as the method for analyzing disease category based on multitask combination described in fig. 1 above is adopted, and the same technical effects can be produced, which is not described herein again.
Fig. 3 is a schematic structural diagram of an electronic device 1 for implementing the disease category analysis method based on multitask association according to the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a disease category analysis program based on a multitasking combination, stored in the memory 11 and executable on the processor 10.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device 1, connects various components of the electronic device 1 by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules stored in the memory 11 (for example, executing a disease category analysis program based on multitask union, etc.), and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of a disease category analysis program based on multitask association, but also to temporarily store data that has been output or will be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the electronic device 1 and other devices, and includes a network interface and an employee interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices 1. The employee interface may be a Display (Display), an input unit, such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visual staff interface.
Fig. 3 shows only the electronic device 1 with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the embodiments described are for illustrative purposes only and that the scope of the claimed invention is not limited to this configuration.
The disease category analysis program based on multitasking combination stored in the memory 11 of the electronic device 1 is a combination of a plurality of computer programs, and when running in the processor 10, it can realize:
acquiring inquiry information, and mapping the inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector;
performing feature extraction on the inquiry vector by using the multilayer perceptron of the hidden layer to obtain inquiry features;
constructing an activation function of the inquiry features, calculating a loss value of the activation function through a cross entropy function, optimizing the loss value through a preset optimization algorithm, and outputting the activation function corresponding to the optimized loss value to obtain a target function;
and calculating the inquiry characteristics by using the target function to obtain a disease category probability, and determining a disease category corresponding to the inquiry information according to the disease category probability.
Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer program, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a non-volatile computer-readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device 1, may implement:
acquiring inquiry information, and mapping the inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector;
performing feature extraction on the inquiry vector by using the multilayer perceptron of the hidden layer to obtain inquiry features;
constructing an activation function of the inquiry features, calculating a loss value of the activation function through a cross entropy function, optimizing the loss value through a preset optimization algorithm, and outputting the activation function corresponding to the optimized loss value to obtain a target function;
and calculating the inquiry characteristics by using the target function to obtain a disease category probability, and determining a disease category corresponding to the inquiry information according to the disease category probability.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A method for disease category analysis based on multitask association, the method comprising:
acquiring inquiry information, and mapping the inquiry information to a hidden layer in an input layer of a preset cyclic neural network to obtain an inquiry vector;
performing feature extraction on the inquiry vector by using the multilayer perceptron of the hidden layer to obtain inquiry features;
constructing an activation function of the inquiry features, calculating a loss value of the activation function through a cross entropy function, optimizing the loss value through a preset optimization algorithm, and outputting the activation function corresponding to the optimized loss value to obtain a target function;
and calculating the inquiry characteristics by using the target function to obtain a disease category probability, and determining a disease category corresponding to the inquiry information according to the disease category probability.
2. The method for analyzing disease category based on multitask combination according to claim 1, wherein said mapping said inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector comprises:
decomposing the inquiry information through the neurons of the input layer to obtain information fragments of the inquiry information;
and forming the information fragments into a feature vector, and performing linear combination mapping on the feature vector to a hidden layer to obtain the inquiry vector.
3. The method for analyzing disease category based on multitask combination according to claim 1, wherein the extracting features of the inquiry vector by using the multilayer perceptron of the hidden layer to obtain inquiry features comprises:
randomly initializing the inquiry vector by using neurons in the multilayer perceptron to obtain an initialization vector;
calculating weight values and bias values of the initialization vector by using neurons in the multilayer perceptron;
and calculating an inquiry feature score of the inquiry vector according to the weight value and the bias value, and taking the inquiry vector with the inquiry feature score larger than a preset score as the inquiry feature.
4. The method of claim 3, wherein the calculating a feature score of the inquiry vector according to the weight value and the bias value to obtain the inquiry features of the inquiry vector comprises:
calculating a feature score for the interrogation vector by the following formula:
O i ＝<x,w i >+b i
wherein, O i A feature score representing the ith feature of the interrogation vector, x represents the interrogation vector, w i Is a weight value, b i Is an offset value.
5. The multitask association based disease class analysis method of claim 1 wherein the calculating the loss value of the activation function by a cross entropy function comprises:
acquiring training data of the activation function, and marking the real disease category of the training data;
calculating an analysis disease category of the training data using the activation function;
calculating the category loss of the real disease category and the analysis disease category through the cross entropy function to obtain a loss value of the activation function.
6. The multitask association based disease class analysis method as claimed in claim 5, wherein said calculating class losses for said real disease class and said analyzed disease class by said cross entropy function to obtain a loss value for said activation function comprises:
calculating a loss value of the activation function by the following formula:
where H represents the loss value, y represents the analysis disease class, and y' represents the true disease class.
7. The method for analyzing disease category based on multitasking combination according to claim 1, wherein said calculating said inquiry characteristics by using said objective function to obtain a disease category probability comprises:
calculating the disease category probability by the following formula:
wherein, y i Representing the probability of a disease class, o i A feature score for the ith feature representing the characterization of the interrogation,
represents the total feature score of the inquiry features, exp refers to an exponential function with a natural constant e as the base.
8. A disease category analysis device based on multitasking combination, the device comprising:
the inquiry information mapping module is used for acquiring inquiry information and mapping the inquiry information to a hidden layer in an input layer of a preset recurrent neural network to obtain an inquiry vector;
the data feature extraction module is used for extracting features of the inquiry vector by utilizing the multilayer perceptron of the hidden layer to obtain inquiry features;
the activation function output module is used for constructing an activation function of the inquiry features, calculating a loss value of the activation function through a cross entropy function, optimizing the loss value through a preset optimization algorithm, and outputting the activation function corresponding to the optimized loss value to obtain a target function;
and the disease category determining module is used for calculating the inquiry characteristics by using the target function to obtain a disease category probability, and determining a disease category corresponding to the inquiry information according to the disease category probability.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of multitask based disease category analysis according to any one of claims 1 to 7.
10. A computer-readable storage medium, storing a computer program, wherein the computer program, when executed by a processor, implements the multitask joint based disease category analyzing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210516140.9A CN114881153A (en) | 2022-05-12 | 2022-05-12 | Disease category analysis method, device, equipment and medium based on multi-task combination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210516140.9A CN114881153A (en) | 2022-05-12 | 2022-05-12 | Disease category analysis method, device, equipment and medium based on multi-task combination |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114881153A true CN114881153A (en) | 2022-08-09 |
Family
ID=82675125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210516140.9A Pending CN114881153A (en) | 2022-05-12 | 2022-05-12 | Disease category analysis method, device, equipment and medium based on multi-task combination |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114881153A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118553429A (en) * | 2024-07-29 | 2024-08-27 | 吉林大学 | Intelligent prediction model training and category prediction method for metabolic diseases |
-
2022
- 2022-05-12 CN CN202210516140.9A patent/CN114881153A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118553429A (en) * | 2024-07-29 | 2024-08-27 | 吉林大学 | Intelligent prediction model training and category prediction method for metabolic diseases |
| CN118553429B (en) * | 2024-07-29 | 2024-10-11 | 吉林大学 | Intelligent prediction model training and category prediction method for metabolic diseases |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112446025A (en) | Federal learning defense method and device, electronic equipment and storage medium | |
| CN113283446A (en) | Method and device for identifying target object in image, electronic equipment and storage medium | |
| CN112396005A (en) | Biological characteristic image recognition method and device, electronic equipment and readable storage medium | |
| CN114496264B (en) | Health index analysis method, device, equipment and medium based on multidimensional data | |
| CN112581227A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN111932547A (en) | Method and device for segmenting target object in image, electronic device and storage medium | |
| CN113298159A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN114781832A (en) | Course recommendation method and device, electronic equipment and storage medium | |
| CN114491047A (en) | Multi-label text classification method and device, electronic equipment and storage medium | |
| CN113707337A (en) | Disease early warning method, device, equipment and storage medium based on multi-source data | |
| CN113157739A (en) | Cross-modal retrieval method and device, electronic equipment and storage medium | |
| CN113806434A (en) | Big data processing method, device, equipment and medium | |
| CN114416939A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| CN114187489B (en) | Method and device for detecting abnormal driving risk of vehicle, electronic equipment and storage medium | |
| CN114595321A (en) | Question marking method and device, electronic equipment and storage medium | |
| CN114840684A (en) | Map construction method, device and equipment based on medical entity and storage medium | |
| CN114220536A (en) | Disease analysis method, device, equipment and storage medium based on machine learning | |
| CN114881153A (en) | Disease category analysis method, device, equipment and medium based on multi-task combination | |
| CN114022841A (en) | Personnel monitoring and identifying method and device, electronic equipment and readable storage medium | |
| CN111950707B (en) | Behavior prediction method, device, equipment and medium based on behavior co-occurrence network | |
| CN116741358A (en) | Inquiry registration recommendation method, inquiry registration recommendation device, inquiry registration recommendation equipment and storage medium | |
| CN112052310A (en) | Information acquisition method, device, equipment and storage medium based on big data | |
| CN112232408A (en) | Target recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN114596958B (en) | Pathological data classification method, device, equipment and medium based on cascade classification | |
| CN116340537A (en) | Character relation extraction method and device, electronic equipment and 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 |