CN117763140A - Accurate medical information conclusion generation method based on computing feature network - Google Patents
Accurate medical information conclusion generation method based on computing feature network Download PDFInfo
- Publication number
- CN117763140A CN117763140A CN202410196621.5A CN202410196621A CN117763140A CN 117763140 A CN117763140 A CN 117763140A CN 202410196621 A CN202410196621 A CN 202410196621A CN 117763140 A CN117763140 A CN 117763140A
- Authority
- CN
- China
- Prior art keywords
- conclusion
- output
- medical information
- network
- result
- 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
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012549 training Methods 0.000 claims abstract description 58
- 238000012937 correction Methods 0.000 claims abstract description 30
- 238000012795 verification Methods 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims description 27
- 230000015654 memory Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 239000002356 single layer Substances 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 239000010410 layer Substances 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 230000014616 translation Effects 0.000 claims description 6
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000006578 abscission Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Abstract
The invention relates to a method for generating accurate medical information conclusion based on a computing feature network, which comprises the following steps: step S10, acquiring text information of a medical paper; step S20, constructing a training set and a verification set based on the to-be-detected part and the conclusion part; s30, inputting the training set into a computing network to carry out conclusion output model training; and S40, after the conclusion output model which is trained is utilized to carry out conclusion output to obtain an output result, optimizing the conclusion output model based on the correction of the output result by the user. The method and the device can better obtain the corresponding conclusion based on the abstract part of the medical paper, reduce complicated procedures of manual reading, help users obtain the conclusion with tighter logic, clear expression and more intuitionistic, and are beneficial to improving the efficiency.
Description
Technical Field
the invention relates to the technical field of computers, in particular to a method for generating accurate medical information conclusions based on a computing feature network.
Background
medical papers are used as important research result display and information acquisition sources, a large number of medical papers are published almost every day, and the academic results comprise a plurality of latest professional field information, so that the medical papers are effectively and rapidly acquired, and semantic feature representation and learning are particularly important. However, the medical paper data often contains a large number of complex attributes, such as abstracts, keywords, citations and the like of the papers, so that the papers are more closely related, and moreover, a large amount of expertise in the papers covers a wide subject, so that a large amount of expertise is required for extracting the characteristics of the medical papers; the efficient extraction of features of the paper data can provide support for the processing of medical paper data.
in the prior art, the key information in the key information is usually extracted manually one by one, which is time-consuming and labor-consuming.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention aims to provide a precise medical information conclusion generating method based on a computing feature network, which can output the conclusion contents of a medical paper by combining a constructed conclusion output model with the abstract of text information of the medical paper, directly obtain the conclusion of the paper based on the paper abstract, better acquire the conclusion information of the medical paper and reduce labor cost.
in order to achieve the above object, the present invention provides a method for generating accurate medical information conclusions based on a computing feature network, comprising the following steps:
step S10, acquiring text information of a medical paper;
step S20, constructing a training set and a verification set based on the to-be-detected part and the conclusion part;
S30, inputting the training set into a computing network to carry out conclusion output model training;
and S40, after the conclusion output model which is trained is utilized to carry out conclusion output to obtain an output result, optimizing the conclusion output model based on the correction of the output result by the user.
According to one technical scheme of the present invention, in the step S30, the training set is input into a computing network to perform conclusion output model training, which specifically includes:
converting the data of the training set into digital id mapping, mapping through a single-layer network, and converting into vector representation, wherein the steps are as follows:
，
Wherein,For a digital id representation of the data character correspondence of the training set,For the weight matrix of the current single-layer network, T represents the transposed operation of the matrix, b represents the bias matrix of the current single-layer network,A vector representation converted for input data;
，
Wherein A is an adjacent matrix,the result of adding the identity matrix to the adjacency matrix, wherein/>=a+i, I is the identity matrix,/>for input data vector,/>For the weight matrix of the current layer network,/>For/>Degree matrix of/>To activate the function,/>outputting calculation characteristics of the current layer network;
mapping calculation of the size of the word list is carried out, the calculation result is normalized to be 0-1, characters in the word list corresponding to the probability of the maximum result are selected to be used as the output of the model, and the method comprises the following steps:
Wherein,e is a constant in mathematics, is an infinite non-cyclic decimal and is an overrun number.
According to an aspect of the present invention, in the step S40, the method specifically includes:
Step S401, obtaining abstract text information input by a front-end page user, and calling a conclusion output model for completing training to output a conclusion;
Step S402, displaying the output result of the conclusion output model to a user;
step S403, the user corrects the output result by a manual input mode, and stores the abstract text information, the output result and the correction result;
and step S404, optimizing the conclusion output model based on the correction of the output result by the user.
According to an embodiment of the present invention, in the step S20, the method specifically includes:
Completing extraction of the summary portion and the conclusion portion based on extraction logic;
and dividing the data of the abstract part and the conclusion part into a training set and a verification set according to a preset proportion.
according to one embodiment of the present invention, before executing the step S10, the logic for extracting the summary portion and the conclusion portion is constructed, and specifically includes:
The mark of the empty line between the two lines of text as distinguishing different paragraphs;
When any part of the text information meets the condition that the beginning of a paragraph is a 'abstract' or corresponding multiple language translations thereof and the end is followed by a row of blank lines, taking corresponding middle data in the text information as the abstract part;
When any portion of the text information satisfies the condition that the beginning of a paragraph is a "conclusion" or corresponding multiple language translations thereof, and the end is followed by a row of empty lines, then corresponding intermediate data in the text information is taken as the conclusion portion.
According to an aspect of the present invention, before executing the step S40, the method further includes:
and verifying the accuracy of the conclusion output model training by using the verification set.
according to an aspect of the present invention, in the step S404, the method specifically includes:
And determining the correction times of the user on the output result, and storing the stored abstract text information, the output result and the correction result after the correction times reach the preset times to finish the optimization of the conclusion output model.
according to one aspect of the present invention, there is provided a precision medical information conclusion generation system based on a computational feature network, comprising:
The acquisition module is used for acquiring text information of the medical paper;
A building module for building training sets and verification sets based on the desired portion and the conclusion portion;
the model training module is used for inputting the training set into a computing network to carry out conclusion output model training;
And the model optimization module is used for optimizing the conclusion output model based on the correction of the output result by the user after the conclusion output is carried out by using the conclusion output model which is completed with training to obtain the output result.
according to an aspect of the present invention, there is provided an electronic apparatus including: one or more processors, one or more memories, and one or more computer programs; wherein the processor is connected to the memory, the one or more computer programs are stored in the memory, and when the electronic device is running, the processor executes the one or more computer programs stored in the memory, so that the electronic device executes a method for generating an accurate medical information conclusion based on the computing feature network according to any one of the above technical solutions.
according to an aspect of the present invention, there is provided a computer readable storage medium storing computer instructions which, when executed by a processor, implement a method for generating accurate medical information conclusions based on a computational feature network as described in any one of the above technical solutions.
Compared with the prior art, the invention has the following beneficial effects:
The invention provides a method for generating accurate medical information conclusion based on a computing feature network, which comprises the steps of firstly, acquiring text information of a medical paper; secondly, constructing a training set and a verification set based on the to-be-detected part and the conclusion part; thirdly, inputting the training set into a computing network to carry out conclusion output model training; finally, after the conclusion output model which is trained is utilized to output the conclusion to obtain an output result, the conclusion output model is optimized based on the correction of the output result by the user, so that the corresponding conclusion can be better obtained based on the abstract part of the medical paper.
Further, through the abstract part of the medical paper, a corresponding conclusion part is generated, so that complicated procedures of manual reading are reduced, and on the other hand, a user can be helped to obtain a conclusion with tighter logic, clear expression and more intuitionistic, and the efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 schematically shows a structural diagram of a computing feature network-based accurate medical information conclusion generating device of a hardware operation environment according to an embodiment of the present invention;
FIG. 2 schematically illustrates a flow chart of a method for generating accurate medical information conclusions based on a computational feature network in one embodiment of the invention;
FIG. 3 is a flow chart schematically illustrating a method for generating accurate medical information conclusions based on a computational feature network in accordance with another embodiment of the present invention;
FIG. 4 schematically illustrates a specific flow chart of step S40 of FIG. 2 in accordance with one embodiment of the present invention;
FIG. 5 schematically illustrates a block diagram of a precision medical information conclusion generation system based on a computational feature network in one embodiment of the invention.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which 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 those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the 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 the embodiments of the 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.
According to an embodiment of the present application, there is provided a method embodiment of a method for generating accurate medical information conclusions based on a computational feature network, it being noted that the steps shown in the flowchart of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in an order different from that herein.
Fig. 1 is a schematic structural diagram of a device for generating accurate medical information conclusion based on a computing feature network in a hardware operation environment according to an embodiment of the present invention.
As shown in fig. 1, the accurate medical information conclusion generating apparatus based on the computing feature network may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage system separate from the processor 1001 described above.
Those skilled in the art will appreciate that the architecture shown in fig. 1 does not constitute a limitation of an accurate medical information conclusion generation device based on a computational feature network, and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a precise medical information conclusion generation program based on a computing feature network may be included in a memory 1005 as one storage medium.
In the accurate medical information conclusion generating device based on the computing feature network shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the accurate medical information conclusion generating device based on the computing feature network can be arranged in the accurate medical information conclusion generating device based on the computing feature network, the accurate medical information conclusion generating device based on the computing feature network calls the accurate medical information conclusion generating program based on the computing feature network and stored in the memory 1005 through the processor 1001, and the accurate medical information conclusion generating method based on the computing feature network provided by the embodiment of the invention is executed.
fig. 2 and 3 are schematic flow diagrams of the method for generating accurate medical information conclusion based on the computing feature network.
As shown in fig. 2 and 3, the accurate medical information conclusion generating method based on the computing feature network of the present invention includes the following steps:
step S10, acquiring text information of a medical paper;
In the step, firstly, the acquired paper needs to be preprocessed so as to acquire text information of the paper, if the paper cannot be acquired, the paper is directly removed, and when the paper is in the form of an image format, a PDF format and the like, the identification of the text information is completed by processing an image part comprising text content, secondly, the classification of the paper is completed according to self-defined semantic information, the part of the paper which is not the medical paper is removed, a precise medical paper database is constructed, and the precise medical paper database comprises the text information of the medical paper.
the papers may be obtained from literature databases, such as the Web of Science database, the scope database, the PubMed database, and the like.
step S20, constructing a training set and a verification set based on the important part and the conclusion part, which specifically comprises the following steps:
completing extraction of the summary part and the conclusion part based on the extraction logic;
and dividing the data of the abstract part and the conclusion part into a training set and a verification set according to a preset proportion.
Further, the data of the abstract part and the conclusion part are divided into data of different sets such as a training set, a verification set and the like, the structure output model is trained through the training set, the conclusion output model which passes the test is verified through set verification, when the verification is not passed, model parameters are finely adjusted according to the verification result, and after the model verification is passed, the conclusion output model which is completed in training can be output.
for example, the preset ratio of the training set to the verification set may be set to 8:2.
step S30, inputting the training set into a computing network for conclusion output model training, wherein the training set is input into the computing network for conclusion output model training, and the method specifically comprises the following steps:
converting the data of the training set into digital id mapping, mapping through a single-layer network, and converting into vector representation, wherein the steps are as follows:
，
Wherein,For a digital id representation of the data character correspondence of the training set,For the weight matrix of the current single-layer network, T represents the transposed operation of the matrix, b represents the bias matrix of the current single-layer network,A vector representation converted for input data;
，
Wherein A is an adjacent matrix,the result of adding the identity matrix to the adjacency matrix, wherein/>=a+i, I is the identity matrix,/>for input data vector,/>For the weight matrix of the current layer network,/>For/>Degree matrix of/>To activate the function,/>outputting calculation characteristics of the current layer network;
mapping calculation of the size of the word list is carried out, the calculation result is normalized to be 0-1, characters in the word list corresponding to the probability of the maximum result are selected to be used as the output of the model, and the method comprises the following steps:
Wherein,For the calculation feature output of the upper layer network, e is a constant in mathematics, is an infinite non-cyclic decimal, is an overrun number, has a value of about 2.718281828459045, and is the final output result.
and S40, after the training conclusion output model is utilized to output the conclusion to obtain an output result, optimizing the conclusion output model based on the correction of the output result by the user. As shown in fig. 4, the method specifically includes:
Step S401, obtaining abstract text information input by a front-end page user, and calling a conclusion output model for completing training to output a conclusion;
Step S402, displaying the output result of the conclusion output model to a user;
step S403, the user corrects the output result by a manual input mode, and stores the abstract text information, the output result and the correction result;
step S404, optimizing a conclusion output model based on the correction of the output result by the user, specifically comprising:
and determining the correction times of the user on the output result, and storing the correction times based on the stored abstract text information, the output result and the correction result after the correction times reach the preset times to finish the optimization of the conclusion output model.
it will be appreciated that the theoretical output model may also be fine-tuned in real time based on user modification of the output results.
For example, an input module and a display module may be configured at the front end, a user inputs a new thesis abscission question through the input module, then the thesis abscission question inputted by the user is pushed to the web service, a trained conclusion output model is called to conduct prediction answer, an output result of model reply is sent to the display module to be displayed, at this time, the user modifies and audits the output result of the conclusion output model through the input module to obtain a correction result, the correction result is stored, and after the stored correction result reaches 3000, 3000 correction results are utilized to adjust the conclusion output model. Or, training the conclusion output model again by combining 3000 correction results with the original training set.
in one embodiment of the present invention, preferably, before executing step S10, the extracting logic for constructing the summary portion and the conclusion portion specifically includes:
The mark of the empty line between the two lines of text as distinguishing different paragraphs;
When any part of the text information meets the condition that the beginning of a paragraph is a 'abstract' or corresponding multiple language translations, and a row of empty lines is behind the end, taking corresponding middle data in the text information as the abstract part;
When any portion of the text information satisfies the condition that the paragraph starts with a "conclusion" or its corresponding multiple language translations, and the end is followed by a line of empty lines, then the corresponding intermediate data in the text information is taken as the conclusion portion.
As shown in fig. 5, according to an aspect of the present invention, there is provided a precision medical information conclusion generation system based on a computational feature network, including:
an acquisition module 8001 for acquiring text information of a medical paper;
A building block 8002 for building training sets and validation sets based on the desired portion and the conclusion portion;
Model training module 8003 for inputting training set into computing network to make conclusion output model training;
The model optimization module 8004 is configured to optimize the conclusion output model based on the correction of the output result by the user after outputting the conclusion to obtain the output result by using the trained conclusion output model.
In addition, the accurate medical information conclusion generating system based on the computing feature network is also matched with a display module and an input module, wherein the display module can be a smart phone, a smart tablet, a computer display and other devices, and the input module is a mouse keyboard lamp or the display module and the input module are integrated into a touch display screen.
The functions of the modules are the same as the related corresponding steps of the accurate medical information conclusion generation method based on the computing feature network, and the modules can execute the corresponding steps of the accurate medical information conclusion generation method based on the computing feature network to realize the corresponding functions.
according to an aspect of the present invention, there is provided a computer readable storage medium storing computer instructions which, when executed by a processor, implement a method for generating accurate medical information conclusions based on a computational feature network according to any one of the above technical solutions.
Computer-readable storage media may include any medium that can store or transfer information. Examples of a computer readable storage medium include an electronic circuit, a semiconductor memory device, a ROM, a flash memory, an Erasable ROM (EROM), a floppy disk, a CD-ROM, an optical disk, a hard disk, a fiber optic medium, a Radio Frequency (RF) link, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
According to the accurate medical information conclusion generation method based on the computing feature network, firstly, text information of a medical paper is acquired; secondly, constructing a training set and a verification set based on the to-be-detected part and the conclusion part; thirdly, inputting the training set into a computing network to carry out conclusion output model training; finally, after the conclusion output model which is trained is utilized to output the conclusion to obtain an output result, the conclusion output model is optimized based on the correction of the output result by the user, so that the corresponding conclusion can be better obtained based on the abstract part of the medical paper. Further, through the abstract part of the medical paper, a corresponding conclusion part is generated, so that complicated procedures of manual reading are reduced, and on the other hand, a user can be helped to obtain a conclusion with tighter logic, clear expression and more intuitionistic, and the efficiency is improved.
Furthermore, it should be noted that the present invention can be provided as a method, an apparatus, or a computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should also be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
It is finally pointed out that the above description of the preferred embodiments of the invention, it being understood that although preferred embodiments of the invention have been described, it will be obvious to those skilled in the art that, once the basic inventive concepts of the invention are known, several modifications and adaptations can be made without departing from the principles of the invention, and these modifications and adaptations are intended to be within the scope of the invention. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Claims (10)
1. the accurate medical information conclusion generation method based on the computing feature network is characterized by comprising the following steps of:
step S10, acquiring text information of a medical paper;
step S20, constructing a training set and a verification set based on the to-be-detected part and the conclusion part;
S30, inputting the training set into a computing network to carry out conclusion output model training;
and S40, after the conclusion output model which is trained is utilized to carry out conclusion output to obtain an output result, optimizing the conclusion output model based on the correction of the output result by the user.
2. The method for generating accurate medical information conclusions based on the computational feature network according to claim 1, wherein in the step S30, the training set is input into the computational network for training of the conclusion output model, and the method specifically comprises:
converting the data of the training set into digital id mapping, mapping through a single-layer network, and converting into vector representation, wherein the steps are as follows:
，
Wherein,For the digital id representation corresponding to the data character of the training set,/>For the weight matrix of the current single-layer network, T represents transposed operation on the matrix, b represents bias matrix of the current single-layer network,/>A vector representation converted for input data;
，
Wherein A is an adjacent matrix,the result of adding the identity matrix to the adjacency matrix, wherein/>=a+i, I is the identity matrix,/>for input data vector,/>For the weight matrix of the current layer network,/>For/>Degree matrix of/>To activate the function,/>outputting calculation characteristics of the current layer network;
mapping calculation of the size of the word list is carried out, the calculation result is normalized to be 0-1, characters in the word list corresponding to the probability of the maximum result are selected to be used as the output of the model, and the method comprises the following steps:
Wherein/>e is a constant in mathematics, is an infinite non-cyclic decimal and is an overrun number.
3. the method for generating accurate medical information conclusions based on the computational feature network according to claim 1, wherein in the step S40, the method specifically comprises:
Step S401, obtaining abstract text information input by a front-end page user, and calling a conclusion output model for completing training to output a conclusion;
Step S402, displaying the output result of the conclusion output model to a user;
step S403, the user corrects the output result by a manual input mode, and stores the abstract text information, the output result and the correction result;
and step S404, optimizing the conclusion output model based on the correction of the output result by the user.
4. the method for generating accurate medical information conclusions based on the computational feature network according to claim 1, wherein the step S20 specifically comprises:
Completing extraction of the summary portion and the conclusion portion based on extraction logic;
and dividing the data of the abstract part and the conclusion part into a training set and a verification set according to a preset proportion.
5. The method for generating accurate medical information conclusions based on computational feature networks according to claim 4, wherein the step S10 is preceded by constructing extraction logic of the summary part and the conclusion part, comprising:
The mark of the empty line between the two lines of text as distinguishing different paragraphs;
When any part of the text information meets the condition that the beginning of a paragraph is a 'abstract' or corresponding multiple language translations thereof and the end is followed by a row of blank lines, taking corresponding middle data in the text information as the abstract part;
When any portion of the text information satisfies the condition that the beginning of a paragraph is a "conclusion" or corresponding multiple language translations thereof, and the end is followed by a row of empty lines, then corresponding intermediate data in the text information is taken as the conclusion portion.
6. The method for generating accurate medical information conclusions based on computational feature networks according to claim 1, further comprising, before performing the step S40:
and verifying the accuracy of the conclusion output model training by using the verification set.
7. the method for generating accurate medical information conclusions based on the computational feature network according to claim 3, wherein in the step S404, the method specifically comprises:
And determining the correction times of the user on the output result, and storing the stored abstract text information, the output result and the correction result after the correction times reach the preset times to finish the optimization of the conclusion output model.
8. A system for generating accurate medical information conclusions based on a computational feature network, comprising:
an acquisition module (8001) for acquiring text information of a medical paper;
A construction module (8002) for constructing a training set and a validation set based on the desired portion and the conclusion portion;
The model training module (8003) is used for inputting the training set into the computing network to carry out conclusion output model training;
And the model optimization module (8004) is used for optimizing the conclusion output model based on the correction of the output result by the user after the conclusion output is carried out by using the trained conclusion output model to obtain the output result.
9. An electronic device, comprising: one or more processors, one or more memories, and one or more computer programs; wherein the processor is connected to the memory, the one or more computer programs being stored in the memory, which processor, when the electronic device is running, executes the one or more computer programs stored in the memory to cause the electronic device to perform the accurate medical information conclusion generation method based on the computational feature network according to any one of claims 1 to 7.
10. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the method of computing feature network based accurate medical information conclusion generation of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410196621.5A CN117763140A (en) | 2024-02-22 | 2024-02-22 | Accurate medical information conclusion generation method based on computing feature network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410196621.5A CN117763140A (en) | 2024-02-22 | 2024-02-22 | Accurate medical information conclusion generation method based on computing feature network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117763140A true CN117763140A (en) | 2024-03-26 |
Family
ID=90318663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410196621.5A Pending CN117763140A (en) | 2024-02-22 | 2024-02-22 | Accurate medical information conclusion generation method based on computing feature network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117763140A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200364607A1 (en) * | 2019-05-13 | 2020-11-19 | Oracle International Corporation | Systems and methods for unsupervised anomaly detection using non-parametric tolerance intervals over a sliding window of t-digests |
| US20210103703A1 (en) * | 2019-10-02 | 2021-04-08 | Oracle International Corporation | Generating recommendations by using communicative discourse trees of conversations |
| CN114595698A (en) * | 2022-03-16 | 2022-06-07 | 浙江工业大学 | Semantic communication method based on CCSK and deep learning |
| WO2023029462A1 (en) * | 2021-08-31 | 2023-03-09 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Hot event state evaluation method |
| CN115910263A (en) * | 2022-10-28 | 2023-04-04 | 北京邮电大学 | PET/CT image report conclusion auxiliary generation method and device based on knowledge graph |
| CN116884552A (en) * | 2023-07-13 | 2023-10-13 | 中世康恺科技有限公司 | Cloud area radiation information management system |
-
2024
- 2024-02-22 CN CN202410196621.5A patent/CN117763140A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200364607A1 (en) * | 2019-05-13 | 2020-11-19 | Oracle International Corporation | Systems and methods for unsupervised anomaly detection using non-parametric tolerance intervals over a sliding window of t-digests |
| US20210103703A1 (en) * | 2019-10-02 | 2021-04-08 | Oracle International Corporation | Generating recommendations by using communicative discourse trees of conversations |
| WO2023029462A1 (en) * | 2021-08-31 | 2023-03-09 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Hot event state evaluation method |
| CN114595698A (en) * | 2022-03-16 | 2022-06-07 | 浙江工业大学 | Semantic communication method based on CCSK and deep learning |
| CN115910263A (en) * | 2022-10-28 | 2023-04-04 | 北京邮电大学 | PET/CT image report conclusion auxiliary generation method and device based on knowledge graph |
| CN116884552A (en) * | 2023-07-13 | 2023-10-13 | 中世康恺科技有限公司 | Cloud area radiation information management system |
Non-Patent Citations (1)
| Title |
|---|
| 杨丹浩;吴岳辛;范春晓;: "一种基于注意力机制的中文短文本关键词提取模型", 计算机科学, no. 01, 15 January 2020 (2020-01-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109871532B (en) | Text theme extraction method and device and storage medium | |
| CN108388515B (en) | Test data generation method, device, equipment and computer readable storage medium | |
| CN110780873B (en) | Interface color adaptation method, device, computer equipment and storage medium | |
| CN110580308B (en) | Information auditing method and device, electronic equipment and storage medium | |
| CN111460131A (en) | Method, device and equipment for extracting official document abstract and computer readable storage medium | |
| CN112328909B (en) | Information recommendation method and device, computer equipment and medium | |
| CN112286934A (en) | Database table importing method, device, equipment and medium | |
| CN112732898A (en) | Document abstract generation method and device, computer equipment and storage medium | |
| CN113360768A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN110968664A (en) | Document retrieval method, device, equipment and medium | |
| CN110309217B (en) | Data import and export method and device, terminal and computer readable storage medium | |
| CN115357699A (en) | Text extraction method, device, equipment and storage medium | |
| CN110110143B (en) | Video classification method and device | |
| CN111382250A (en) | Question text matching method and device, computer equipment and storage medium | |
| CN114692889A (en) | Meta-feature training model for machine learning algorithm | |
| CN113934834A (en) | Question matching method, device, equipment and storage medium | |
| CN112948526A (en) | User portrait generation method and device, electronic equipment and storage medium | |
| CN111881664A (en) | Information extraction method, device, equipment and medium combining RPA and AI | |
| CN116860747A (en) | Training sample generation method and device, electronic equipment and storage medium | |
| CN114842982B (en) | Knowledge expression method, device and system for medical information system | |
| CN116225956A (en) | Automated testing method, apparatus, computer device and storage medium | |
| CN117763140A (en) | Accurate medical information conclusion generation method based on computing feature network | |
| CN113626468B (en) | SQL sentence generation method, device and equipment based on artificial intelligence and storage medium | |
| CN110780850B (en) | Requirement case auxiliary generation method and device, computer equipment and storage medium | |
| CN113704623A (en) | Data recommendation method, device, 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 |