CN116304050A - Single disease reporting method, system, terminal and medium - Google Patents
Single disease reporting method, system, terminal and medium Download PDFInfo
- Publication number
- CN116304050A CN116304050A CN202310285938.1A CN202310285938A CN116304050A CN 116304050 A CN116304050 A CN 116304050A CN 202310285938 A CN202310285938 A CN 202310285938A CN 116304050 A CN116304050 A CN 116304050A
- Authority
- CN
- China
- Prior art keywords
- event
- disease
- reporting
- data
- constructing
- 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 166
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 166
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 54
- 238000002372 labelling Methods 0.000 claims abstract description 25
- 238000004590 computer program Methods 0.000 claims description 20
- 230000011218 segmentation Effects 0.000 claims description 17
- 238000010276 construction Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 4
- 206010018852 Haematoma Diseases 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 206010008111 Cerebral haemorrhage Diseases 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 2
- 210000003478 temporal lobe Anatomy 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 210000004720 cerebrum Anatomy 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
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a single disease reporting method, a system, a terminal and a medium, wherein the method comprises the following steps: obtaining disease report standard information, and constructing a disease knowledge frame according to the disease report standard information; constructing an event set according to a disease knowledge frame, and respectively acquiring event problems of various disease events in the event set; determining related texts in sample cases according to event problems, and constructing pre-labeling training data according to the related texts and the event sets; training the event implication model according to pre-labeling training data, and determining to-be-inferred data according to-be-filled medical records; and inputting the data to be inferred into the trained event implication model to conduct event prediction, so as to obtain single disease reporting information. The invention can automatically construct the disease seed knowledge frame representing the key information of the corresponding single disease seed based on the disease seed reporting standard information, so that the event implication model can effectively learn the key information in the pre-labeled training data, and the accuracy of reporting the single disease seed is improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, a system, a terminal, and a medium for reporting single disease seeds.
Background
The reporting of single diseases is to carry out a series of problem reporting on patients admitted to the hospital due to certain diseases according to the requirements of the state and the needs of doctors and according to medical records and various diagnosis records. The reporting of single diseases has great significance for improving the supervision level of medical services and guaranteeing the safety of patients. In the single disease reporting process, key information about data items is required to be extracted from medical record data, so that answer selection is carried out on corresponding questions.
In the existing single disease reporting process, single disease reporting is carried out by adopting a neural network reading and understanding model, and in the existing reading and understanding model training process, medical record data is generally directly input into the reading and understanding model for model training, but because the medical record data content is too tedious and complicated, the reading and understanding model can not learn the problem of key information, inaccurate model prediction is easily caused, and the accuracy of single disease reporting is reduced.
Disclosure of Invention
The embodiment of the invention aims to provide a single disease reporting method, a system, a terminal and a medium, and aims to solve the problem that single disease reporting accuracy is low in the existing single disease reporting process.
The embodiment of the invention is realized in such a way that a single disease species reporting method comprises the following steps:
obtaining disease report standard information, and constructing a disease knowledge frame according to the disease report standard information;
constructing an event set according to the disease knowledge framework, and respectively acquiring event problems of various disease events in the event set;
determining related texts in sample cases according to the event problems, and constructing pre-labeling training data according to the related texts and the event sets;
training the event implication model according to the pre-labeling training data, and determining to-be-inferred data according to-be-reported medical records;
and inputting the data to be inferred into the trained event implication model to conduct event prediction, so as to obtain single disease report information.
Preferably, the constructing a disease knowledge frame according to the disease report standard information includes:
respectively acquiring data item information, event item information and question and answer item information in the disease report standard information;
and combining the data item information, the event item information and the question and answer item information to obtain the disease type knowledge frame.
Preferably, the obtaining the data item information, the event item information and the question and answer item information in the disease report standard information respectively includes:
acquiring disease reporting codes and disease reporting problems in various disease reporting standard information, and constructing the data item information according to the disease reporting codes and the disease reporting problems;
acquiring event occurrence positions and event contents in various disease report standard information, and constructing event item information according to the event occurrence positions and the event contents;
and acquiring the question-answer answers and answer identifications corresponding to the question-answer answers in the reporting standard information of each disease, and constructing the question-answer item information according to the question-answer answers and the answer identifications.
Preferably, the determining the related text in the sample case according to the event problem includes:
and determining an extraction position according to the problem identification of the event problem, and extracting the text of the sample case according to the extraction position to obtain the related text.
Preferably, the constructing an event set according to the disease kind knowledge framework includes:
and respectively storing the report codes of the disease types, the event occurrence positions, the event contents and the question answer answers corresponding to each knowledge frame to obtain the event set.
Preferably, the constructing pre-labeling training data according to the related text and the event set includes:
respectively acquiring text semantics of the related text, and combining the text semantics with the event set to obtain combined data;
and carrying out data annotation on the combined data to obtain the pre-annotation training data.
Preferably, after determining the relevant text in the sample case according to the event problem, the method further includes:
performing word segmentation on the related text to obtain related word segmentation, and respectively determining the event association degree between the related word segmentation and the event problem;
and screening sentences formed by the related word segmentation according to the event association degree, and determining the sentences as the related text according to the screened sentences.
Another object of an embodiment of the present invention is to provide a single disease seed reporting system, including:
the frame construction module is used for acquiring disease report standard information and constructing a disease knowledge frame according to the disease report standard information;
the problem acquisition module is used for constructing an event set according to the disease knowledge framework and respectively acquiring event problems of various disease events in the event set;
the data construction module is used for determining related texts in sample cases according to the event problems and constructing pre-labeling training data according to the related texts and the event sets;
the model training module is used for training the event implication model according to the pre-labeling training data and determining to-be-inferred data according to the medical record to be filled;
and the event prediction module is used for inputting the data to be inferred into the trained event implication model to perform event prediction so as to obtain single disease report information.
It is a further object of an embodiment of the present invention to provide a terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, which processor implements the steps of the method as described above when executing the computer program.
It is a further object of embodiments of the present invention to provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above method.
According to the embodiment of the invention, the disease type knowledge frame can be automatically constructed based on the disease type reporting standard information, the key information corresponding to single disease type can be effectively represented based on the disease type knowledge frame, so that the event implication model can effectively learn the key information in the pre-marked training data, the accuracy of reporting single disease type is improved, the event collection can be automatically constructed based on the disease type knowledge frame, the accuracy of the event implication model after model training is effectively improved, the reading understanding model is replaced by the event implication model, the matching space of model learning is reduced, the task complexity is reduced, and the training efficiency of the event implication model is effectively improved.
Drawings
FIG. 1 is a flowchart of a single disease reporting method provided by a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of a single disease reporting system according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a single disease reporting system according to a third embodiment of the present invention;
FIG. 4 is a flowchart of a specific implementation of a single disease report system according to a third embodiment of the present invention;
FIG. 5 is a schematic diagram of an event implication model provided by a third embodiment of the present invention;
fig. 6 is a schematic structural diagram of a terminal device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In order to illustrate the technical scheme of the invention, the following description is made by specific examples.
Example 1
Referring to fig. 1, a flowchart of a single disease report method according to a first embodiment of the present invention is shown, where the single disease report method may be applied to any terminal device or system, and the single disease report method includes the steps of:
step S10, obtaining disease report standard information, and constructing a disease knowledge frame according to the disease report standard information;
the disease report standard information is a national standard of single disease report, namely, a knowledge frame of options is established according to the national standard of single disease report, and the disease knowledge frame is obtained;
optionally, in this step, the constructing a disease knowledge frame according to the disease report standard information includes:
respectively acquiring data item information, event item information and question and answer item information in the disease report standard information, wherein the data item information comprises information data corresponding to the data item in the disease report standard information, the event item information comprises information data corresponding to the event item in the disease report standard information, and the question and answer item information comprises information data corresponding to the question and answer item in the disease report standard information;
and combining the data item information, the event item information and the question-answer item information to obtain the disease type knowledge framework, wherein the effect of obtaining key information of various diseases is achieved by combining the data item information, the event item information and the question-answer item information.
Further, the respectively obtaining the data item information, the event item information and the question and answer item information in the disease report standard information includes:
acquiring disease reporting codes and disease reporting problems in various disease reporting standard information, and constructing the data item information according to the disease reporting codes and the disease reporting problems;
acquiring event occurrence positions and event contents in various disease report standard information, and constructing event item information according to the event occurrence positions and the event contents;
acquiring question-answer answers and answer identifiers corresponding to the question-answer answers in the reporting standard information of each disease, and constructing question-answer item information according to the question-answer answers and the answer identifiers;
for example, ICH-1-3-5 hematomas break the ventricles: y-is, n-is, the following disease knowledge framework is established:
the data item information comprises 'itemId', 'ICH-1-3-5' -data item code (disease report code) and 'query', 'whether hematoma breaks into ventricle', 'data item content (disease report problem');
event item information includes "event_id": 0-event id, "event_loc": "ventricle" -event occurrence location, "event_core": hematoma break "-event content and" event_time ":" PRESENT "-event occurrence event;
the question and answer item information comprises 'opt_name', 'y' -option name ',' opt_content 'and' option_content 'which are' -option content;
"opt_rules": "happend: 0= happend", "connection: 0= connection", "notify: 0= notify" -this option is conditional;
wherein, the occurrence of the happend indicates a collision, the non indicates not mentioned, and 0 is an event_id in opt_events;
"opt_name": "n", "opt_content": "no", "opt_files": [ ], "opt_events": [ ]
"item_rule": "y: y= happend", "n: y-! =happend "-when y= =happend, select y-yes, otherwise select n-no;
the definition principle of the event opt_events comprises the following steps: the event is as principle as possible and can not be subdivided, the event semantics in the options are not covered with each other, and the event names are as consistent as possible with the spoken habit of doctors.
Step S20, an event set is constructed according to the disease knowledge frame, and event problems of various disease events in the event set are respectively acquired;
the method can effectively represent key information of a single disease based on a disease knowledge framework, for example, an event set corresponding to ICH-1-3-5 is 'y ventricle_hematoma broken-in_present', and the event set can be automatically constructed based on the disease knowledge framework, so that event data items of various diseases are mutually independent, and the accuracy of an event implication model after model training is effectively improved.
Optionally, in this step, the constructing an event set according to the disease knowledge framework includes:
and respectively storing the report codes of the disease types, the event occurrence positions, the event contents and the question answer answers corresponding to each knowledge frame to obtain the event set.
Step S30, determining relevant texts in sample cases according to the event problems, and constructing pre-labeling training data according to the relevant texts and the event sets;
the method comprises the steps of respectively inquiring medical record positions of event problems in medical record texts, extracting texts of the medical record positions to obtain relevant texts, and effectively constructing pre-labeling training data based on the extracted relevant texts and event sets;
optionally, in this step, the determining related text in the sample case according to the event question includes:
determining an extraction position according to the problem identification of the event problem, and extracting the text of the sample case according to the extraction position to obtain the related text; wherein the problem identification may be stored in an alphanumeric or coded manner.
Further, in this step, the constructing pre-labeled training data according to the related text and the event set includes:
respectively acquiring text semantics of the related text, combining the text semantics with the event set to obtain combined data, and performing data annotation on the combined data to obtain the pre-annotation training data, wherein the pre-annotation training data comprises: bilateral temporal lobe hooked back shifts down ventricle_hematoma break-in_present N, right brain hemisphere cerebral hemorrhage break-in ventricle_hematoma break-in_present H.
Step S40, training the event implication model according to the pre-labeling training data, and determining to-be-inferred data according to the to-be-filled medical record;
the method comprises the steps of controlling an event implication model to perform unsupervised learning on pre-labeling training data by adopting a BERT learning method, enabling the event implication model to automatically learn various information in the pre-labeling training data, controlling the event implication model to perform linear prediction on the pre-labeling training data, determining model loss of the event implication model according to a linear prediction result, and performing parameter updating on the event implication model according to the model loss until the event implication model converges;
s50, inputting the data to be inferred into the trained event implication model to conduct event prediction, and obtaining single disease report information;
and inputting the data to be inferred into the trained event implication model to conduct event prediction so as to output the option answers of all the questions in the medical record to be filled.
In this embodiment, a disease type knowledge frame can be automatically constructed based on disease type reporting standard information, key information corresponding to single disease types can be effectively represented based on the disease type knowledge frame, so that an event implication model can effectively learn key information in pre-labeled training data, accuracy of single disease type reporting is improved, event sets can be automatically constructed based on the disease type knowledge frame, accuracy of the event implication model after model training is effectively improved, reading understanding of the model is replaced by the event implication model, matching space of model learning is reduced, task complexity is reduced, and training efficiency of the event implication model is effectively improved.
Example two
Referring to fig. 2, a flowchart of a secret embedding sharing method according to a second embodiment of the present invention is provided, and the method is used for further refining steps after step S50 in the first embodiment, and includes the steps of:
step S60, word segmentation is carried out on the related text to obtain related word segmentation, and the event association degree between the related word segmentation and the event problem is respectively determined;
the method comprises the steps of carrying out word segmentation on related texts based on the number of preset characters or a preset vocabulary, wherein the number of the preset characters and the preset vocabulary can be set according to requirements;
step S70, screening sentences formed by the related word segmentation according to the event association degree, and determining the sentences as the related text according to the screened sentences;
and respectively calculating the sum of the event association degrees among related segmented words in each sentence to obtain a total association value, deleting the sentence corresponding to the association threshold if the total association value corresponding to any sentence is smaller than the association threshold, and determining the filtered sentence as a related text.
According to the method, the related text is segmented, so that the determination of the degree of event relevance between each related segmented word and the event problem is effectively guaranteed, sentences formed by the related segmented words are screened through the degree of event relevance, sentences with smaller relevance to the event problem in the related text can be effectively deleted, and the accuracy of the related text is improved.
In the embodiment, modeling is performed on a certain knowledge point of whether the text contains options, an event implication model is used for replacing a reading understanding model, matching space of model learning is reduced, task complexity is reduced, modeling is performed only on the inside of each problem data item in single disease report, and each disease data item is independent of each other, so that the accuracy of the model is improved.
Example III
Referring to fig. 3, a schematic structural diagram of a single disease reporting system 100 according to a third embodiment of the present invention includes: a framework construction module 10, a problem acquisition module 11, a data construction module 12, a model training module 13, and an event prediction module 14, wherein:
and the frame construction module 10 is used for acquiring disease report standard information and constructing a disease knowledge frame according to the disease report standard information.
Optionally, the frame construction module 10 is further configured to: respectively acquiring data item information, event item information and question and answer item information in the disease report standard information;
and combining the data item information, the event item information and the question and answer item information to obtain the disease type knowledge frame.
Further, the frame construction module 10 is also for: acquiring disease reporting codes and disease reporting problems in various disease reporting standard information, and constructing the data item information according to the disease reporting codes and the disease reporting problems;
acquiring event occurrence positions and event contents in various disease report standard information, and constructing event item information according to the event occurrence positions and the event contents;
and acquiring the question-answer answers and answer identifications corresponding to the question-answer answers in the reporting standard information of each disease, and constructing the question-answer item information according to the question-answer answers and the answer identifications.
The problem obtaining module 11 is configured to construct an event set according to the disease knowledge frame, and obtain event problems of various disease events in the event set respectively.
Optionally, the problem obtaining module 11 is further configured to: and respectively storing the report codes of the disease types, the event occurrence positions, the event contents and the question answer answers corresponding to each knowledge frame to obtain the event set.
The data construction module 12 is configured to determine relevant text in a sample case according to the event problem, and construct pre-labeling training data according to the relevant text and the event set.
Optionally, the data construction module 12 is further configured to: and determining an extraction position according to the problem identification of the event problem, and extracting the text of the sample case according to the extraction position to obtain the related text.
Further, the data construction module 12 is further configured to: respectively acquiring text semantics of the related text, and combining the text semantics with the event set to obtain combined data;
and carrying out data annotation on the combined data to obtain the pre-annotation training data.
Still further, the data construction module 12 is further configured to: performing word segmentation on the related text to obtain related word segmentation, and respectively determining the event association degree between the related word segmentation and the event problem;
and screening sentences formed by the related word segmentation according to the event association degree, and determining the sentences as the related text according to the screened sentences.
And the model training module 13 is used for training the event implication model according to the pre-labeling training data and determining to-be-inferred data according to the medical record to be filled.
The event prediction module 14 is configured to input the data to be inferred into the trained event implication model to perform event prediction, so as to obtain single disease report information.
Specifically, please refer to fig. 4, which is a schematic diagram illustrating steps of the single disease report system 100 according to the present embodiment:
(1) Establishing a knowledge framework of options according to the national standard reported by single disease seeds;
for example, ICH-1-3-5 hematomas break the ventricles: y-is, n-is, the following disease knowledge framework is established:
the data item information comprises 'itemId', 'ICH-1-3-5' -data item code (disease report code) and 'query', 'whether hematoma breaks into ventricle', 'data item content (disease report problem');
event item information includes "event_id": 0-event id, "event_loc": "ventricle" -event occurrence location, "event_core": hematoma break "-event content and" event_time ":" PRESENT "-event occurrence event;
the question and answer item information comprises 'opt_name', 'y' -option name ',' opt_content 'and' option_content 'which are' -option content;
"opt_rules": "happend: 0= happend", "connection: 0= connection", "notify: 0= notify" -this option is conditional;
wherein, the occurrence of the happend indicates a collision, the non indicates not mentioned, and 0 is an event_id in opt_events;
"opt_name": "n", "opt_content": "no", "opt_files": [ ], "opt_events": [ ]
"item_rule": "y: y= happend", "n: y-! =happend "-when y= =happend, select y-yes, otherwise select n-no;
the definition principle of the event opt_events comprises the following steps: the event is as principle as possible and can not be subdivided, the event semantics in the options are not covered with each other, and the event names are as consistent as possible with the spoken habit of doctors.
(2) Generating event sets from the knowledge framework defined in (1)
For example, the set of events corresponding to ICH-1-3-5 is "yventricular_hematoma break-in_present";
(3) Extracting relevant text according to the medical record position of the data item problem, and generating corresponding pre-labeling training data by using the event set generated in the step (2), wherein the generated pre-labeling training data (N corresponds to NOTREF, H corresponds to HAPPEND, and C corresponds to CONFLICT) is generated according to the 'inspection report' content in the medical record corresponding to ICH-1-3-5:
bilateral temporal lobe hook back downward shift of ventricle_hematoma break-in_present N
Right cerebral hemisphere cerebral hemorrhage into ventricle and ventricle-hematoma breaking-in_present H
Pre-labeling training data is formed after manual rechecking;
(4) Training was performed using an event implication model, the model structure being as in fig. 5:
the method comprises the steps of controlling an event implication model to conduct unsupervised learning on pre-labeling training data by adopting a BERT learning method, enabling the event implication model to automatically learn various information in the pre-labeling training data, controlling the event implication model to conduct linear prediction on the pre-labeling training data, determining model loss of the event implication model according to a linear prediction result, and conducting parameter updating on the event implication model according to the model loss until the event implication model converges.
(5) In the reasoning stage, generating data to be inferred according to the steps (2) and (3), and giving answer options according to a knowledge framework 'item_rule' defined in the step (1); specifically, the data to be inferred is input into the trained event implication model to conduct event prediction, and single disease report information is obtained.
In the embodiment, modeling is performed on a certain knowledge point of whether the text contains options, an event implication model is used for replacing a reading understanding model, matching space of model learning is reduced, task complexity is reduced, modeling is performed only on the inside of each problem data item in single disease report, and each disease data item is independent of each other, so that the accuracy of the model is improved.
Example IV
Fig. 6 is a block diagram of a terminal device 2 according to a fourth embodiment of the present application. As shown in fig. 6, the terminal device 2 of this embodiment includes: a processor 20, a memory 21 and a computer program 22 stored in said memory 21 and executable on said processor 20, for example a program for a single illness report method. The steps of the various embodiments of the single disease reporting methods described above are implemented by the processor 20 when executing the computer program 22.
Illustratively, the computer program 22 may be partitioned into one or more modules that are stored in the memory 21 and executed by the processor 20 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program 22 in the terminal device 2. The terminal device may include, but is not limited to, a processor 20, a memory 21.
The processor 20 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 21 may be an internal storage unit of the terminal device 2, such as a hard disk or a memory of the terminal device 2. The memory 21 may be an external storage device of the terminal device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal device 2. Further, the memory 21 may also include both an internal storage unit and an external storage device of the terminal device 2. The memory 21 is used for storing the computer program as well as other programs and data required by the terminal device. The memory 21 may also be used for temporarily storing data that has been output or is to be output.
In addition, each functional module in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Wherein the computer readable storage medium may be nonvolatile or volatile. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each method embodiment described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable storage medium may include: any entity or device capable of carrying computer program code, a recording medium, a USB flash disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a Read-only memory (ROM), a random access memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable storage medium may be appropriately scaled according to the requirements of jurisdictions in which such computer readable storage medium does not include electrical carrier signals and telecommunication signals, for example, according to jurisdictions and patent practices.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. A method for reporting a single disease species, the method comprising:
obtaining disease report standard information, and constructing a disease knowledge frame according to the disease report standard information;
constructing an event set according to the disease knowledge framework, and respectively acquiring event problems of various disease events in the event set;
determining related texts in sample cases according to the event problems, and constructing pre-labeling training data according to the related texts and the event sets;
training the event implication model according to the pre-labeling training data, and determining to-be-inferred data according to-be-reported medical records;
and inputting the data to be inferred into the trained event implication model to conduct event prediction, so as to obtain single disease report information.
2. The method for reporting single disease seeds of claim 1, wherein the constructing a disease seed knowledge frame according to the disease seed reporting standard information comprises:
respectively acquiring data item information, event item information and question and answer item information in the disease report standard information;
and combining the data item information, the event item information and the question and answer item information to obtain the disease type knowledge frame.
3. The method for reporting a single disease seed according to claim 2, wherein the step of obtaining the data item information, the event item information, and the question-answer item information in the disease seed reporting standard information, respectively, includes:
acquiring disease reporting codes and disease reporting problems in various disease reporting standard information, and constructing the data item information according to the disease reporting codes and the disease reporting problems;
acquiring event occurrence positions and event contents in various disease report standard information, and constructing event item information according to the event occurrence positions and the event contents;
and acquiring the question-answer answers and answer identifications corresponding to the question-answer answers in the reporting standard information of each disease, and constructing the question-answer item information according to the question-answer answers and the answer identifications.
4. The single illness report method of claim 1, wherein the determining the relevant text in the sample case according to the event question includes:
and determining an extraction position according to the problem identification of the event problem, and extracting the text of the sample case according to the extraction position to obtain the related text.
5. The method for reporting single disease seeds of claim 3, wherein the constructing an event set according to the disease seed knowledge framework comprises:
and respectively storing the report codes of the disease types, the event occurrence positions, the event contents and the question answer answers corresponding to each knowledge frame to obtain the event set.
6. The method of claim 1, wherein said constructing pre-labeled training data from said related text and said set of events comprises:
respectively acquiring text semantics of the related text, and combining the text semantics with the event set to obtain combined data;
and carrying out data annotation on the combined data to obtain the pre-annotation training data.
7. The method for reporting single diseases according to any one of claims 1 to 6, wherein after determining the relevant text in the sample case according to the event question, the method further comprises:
performing word segmentation on the related text to obtain related word segmentation, and respectively determining the event association degree between the related word segmentation and the event problem;
and screening sentences formed by the related word segmentation according to the event association degree, and determining the sentences as the related text according to the screened sentences.
8. A single disease seed reporting system, the system comprising:
the frame construction module is used for acquiring disease report standard information and constructing a disease knowledge frame according to the disease report standard information;
the problem acquisition module is used for constructing an event set according to the disease knowledge framework and respectively acquiring event problems of various disease events in the event set;
the data construction module is used for determining related texts in sample cases according to the event problems and constructing pre-labeling training data according to the related texts and the event sets;
the model training module is used for training the event implication model according to the pre-labeling training data and determining to-be-inferred data according to the medical record to be filled;
and the event prediction module is used for inputting the data to be inferred into the trained event implication model to perform event prediction so as to obtain single disease report information.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310285938.1A CN116304050A (en) | 2023-03-22 | 2023-03-22 | Single disease reporting method, system, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310285938.1A CN116304050A (en) | 2023-03-22 | 2023-03-22 | Single disease reporting method, system, terminal and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116304050A true CN116304050A (en) | 2023-06-23 |
Family
ID=86792286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310285938.1A Pending CN116304050A (en) | 2023-03-22 | 2023-03-22 | Single disease reporting method, system, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116304050A (en) |
-
2023
- 2023-03-22 CN CN202310285938.1A patent/CN116304050A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112256828B (en) | Medical entity relation extraction method, device, computer equipment and readable storage medium | |
| CN114912887B (en) | Clinical data input method and device based on electronic medical record | |
| CN112614559A (en) | Medical record text processing method and device, computer equipment and storage medium | |
| CN113626591A (en) | Electronic medical record data quality evaluation method based on text classification | |
| CN114218370A (en) | Method, device, equipment and storage medium for determining answers to questions reported by single disease | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| CN116052848B (en) | Data coding method and system for medical imaging quality control | |
| CN117010362A (en) | Medical record writing method, system, terminal and storage medium | |
| CN116304050A (en) | Single disease reporting method, system, terminal and medium | |
| CN117743522A (en) | Medical reply generation method, device, equipment and storage medium | |
| CN114842982B (en) | Knowledge expression method, device and system for medical information system | |
| CN115798664A (en) | Medical record quality evaluation method, system, terminal and storage medium | |
| CN114520035A (en) | Volunteer screening method and device, electronic equipment and storage medium | |
| CN113988067A (en) | Sentence segmentation method and device and electronic equipment | |
| CN117497116A (en) | Medical record generation method, system, terminal and storage medium | |
| CN118035504B (en) | Medical core word knowledge base construction method, device, medium and terminal | |
| CN117809792B (en) | Method and system for structuring disease seed data during cross-disease seed migration | |
| CN118194097B (en) | Intelligent laboratory management method, device, equipment and storage medium | |
| CN114238588B (en) | Data retrieval method, system, readable storage medium and computer device | |
| CN112507703B (en) | Medical entity identification method, device, medium and electronic equipment | |
| CN112927806B (en) | Medical record structured network cross-disease migration training method, device, medium and equipment | |
| CN117612736A (en) | Disease name processing method, device, computer equipment and storage medium | |
| CN117637101A (en) | Large model training method, system, terminal and storage medium | |
| CN118468873A (en) | Medical special disease database generation method, device, equipment and medium | |
| CN118506966A (en) | Medical advice chemoradiotherapy medicine identification method and system based on deep learning |
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 |