CN111986765B - Electronic case entity marking method, electronic case entity marking device, electronic case entity marking computer equipment and storage medium - Google Patents
Electronic case entity marking method, electronic case entity marking device, electronic case entity marking computer equipment and storage medium Download PDFInfo
- Publication number
- CN111986765B CN111986765B CN202010917927.7A CN202010917927A CN111986765B CN 111986765 B CN111986765 B CN 111986765B CN 202010917927 A CN202010917927 A CN 202010917927A CN 111986765 B CN111986765 B CN 111986765B
- Authority
- CN
- China
- Prior art keywords
- entity
- electronic case
- historical electronic
- historical
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000004590 computer program Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 8
- 230000009191 jumping Effects 0.000 claims description 4
- 206010037660 Pyrexia Diseases 0.000 description 26
- 201000010099 disease Diseases 0.000 description 10
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 10
- 206010012735 Diarrhoea Diseases 0.000 description 8
- 239000012634 fragment Substances 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000012937 correction Methods 0.000 description 5
- 206010020751 Hypersensitivity Diseases 0.000 description 4
- 208000026935 allergic disease Diseases 0.000 description 4
- 230000007815 allergy Effects 0.000 description 4
- 238000012217 deletion Methods 0.000 description 4
- 230000037430 deletion Effects 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 208000024891 symptom Diseases 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 206010020772 Hypertension Diseases 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 208000006454 hepatitis Diseases 0.000 description 2
- 231100000283 hepatitis Toxicity 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/117—Tagging; Marking up; Designating a block; Setting of attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computing Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of digital medical treatment, and provides an electronic case entity marking method, an electronic case entity marking device, computer equipment and a storage medium, wherein the electronic case entity marking method comprises the following steps: identifying a plurality of entities in the historical electronic case; displaying the historical electronic case and the entities in the historical electronic case according to a preset entity display type; adding an anchor point for each entity, and receiving the update of a user to the corresponding entity through the anchor point to obtain update information; storing the historical electronic case and a plurality of entities in the historical electronic case and corresponding updated information in an entity table of the historical electronic case; training a BiLSTM-CRF model based on the historical electronic case entity table to obtain an entity marking model; and carrying out entity marking on the electronic cases to be marked by using the entity marking model. The invention can improve the accuracy of the entity marking of the electronic case.
Description
Technical Field
The invention relates to the technical field of digital medical treatment, in particular to an electronic case entity marking method, an electronic case entity marking device, computer equipment and a storage medium.
Background
The health medical big data is an important basic strategic resource in China, and the entity identification of the Chinese electronic medical record is beneficial to extracting important information from a large amount of unstructured texts, so that a foundation is laid for medical data mining and application. The common practice is to search the medical record library and find the electronic medical record meeting the above conditions from the medical record library, and then screen out the final result, which is complex and time-consuming and labor-consuming.
At present, artificial Intelligence (AI) and big data burst are labeled on electronic cases through an AI model so as to achieve the purpose of medical record screening, but the AI model is used for labeling the electronic cases with poor accuracy due to the fact that the Chinese has a word meaning and a word meaning, and the electronic cases are marked inaccurately, so that the accuracy of a query result is low when the electronic cases are queried according to the marks of the electronic cases.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, apparatus, computer device, and storage medium for marking an electronic case entity, which can improve the accuracy of marking an electronic case entity.
A first aspect of the present invention provides a method of electronic case entity tagging, the method comprising:
identifying a plurality of entities in the historical electronic case;
Displaying the historical electronic case and the entities in the historical electronic case according to a preset entity display type;
adding an anchor point for each entity, and receiving the update of a user to the corresponding entity through the anchor point to obtain update information;
storing the historical electronic case and a plurality of entities in the historical electronic case and corresponding updated information in an entity table of the historical electronic case;
training a BiLSTM-CRF model based on the historical electronic case entity table to obtain an entity marking model;
and carrying out entity marking on the electronic cases to be marked by using the entity marking model.
According to an alternative embodiment of the present invention, the identifying a plurality of entities in the historical electronic case includes:
acquiring a historical electronic case set;
word segmentation is carried out on the historical electronic case set through a barking word segmentation tool to obtain a plurality of phrases;
obtaining entity marks of the plurality of phrases;
constructing a medical knowledge graph according to the plurality of phrase and entity marks;
and identifying a plurality of entities in the historical electronic case by using the medical knowledge graph.
According to an optional embodiment of the invention, the displaying the historical electronic case and the plurality of entities in the historical electronic case according to a preset entity display type comprises:
Identifying a plurality of key fields in the historical electronic case;
positioning the historical electronic case by taking the key fields as paragraph marks;
acquiring a display type corresponding to each entity;
and adding a < span > tag at a position corresponding to the entity on the historical electronic case according to the display type.
According to an optional embodiment of the invention, the adding an anchor point for each entity, and receiving, by the anchor point, the update information obtained by updating the corresponding entity by the user includes:
adding an ID for each entity and taking the ID as an anchor point of the entity;
when detecting an instruction of which the anchor point is selected, jumping to a target entity corresponding to the selected anchor point;
when detecting that an operation instruction is received at a position corresponding to the target entity on the display interface, updating the target entity according to the operation instruction;
and acquiring the starting position, the ending position and the paragraph mark of the updated target entity to obtain updated information.
According to an optional embodiment of the invention, after the displaying the historical electronic case and the plurality of entities in the historical electronic case according to a preset entity display type, the method further comprises:
Displaying a plurality of entity virtual icons, wherein each entity virtual icon corresponds to one entity;
after detecting that any entity virtual icon in the plurality of entity virtual icons receives a selected instruction, displaying an entity text input box around a target entity virtual icon receiving the selected instruction;
receiving an entity input in the entity text input box;
and updating the entity corresponding to the target entity virtual icon to the entity input in the text input box, and synchronously updating the target entity virtual icon.
According to an alternative embodiment of the invention, the method further comprises:
receiving query text sent by computer equipment;
inquiring a target historical electronic case corresponding to the inquiring text through the historical electronic case entity table;
returning the target historical electronic case to the computer device.
According to an optional embodiment of the invention, the querying the target historical electronic case corresponding to the query text through the historical electronic case entity table includes:
analyzing the query text to obtain query entity information, wherein the query entity information comprises a query entity type and a query entity attribute;
Querying a plurality of target entities corresponding to the query entity type and target entity attributes corresponding to each target entity from the historical electronic case entity table;
matching the query entity attribute with the target entity attribute corresponding to each target entity;
determining a medical record identifier corresponding to the successfully matched target entity attribute as a target medical record identifier;
inquiring the corresponding target electronic medical record according to the target medical record identifier.
A second aspect of the present invention provides an electronic case entity marking device, the device comprising:
the identification module is used for identifying a plurality of entities in the historical electronic cases;
the display module is used for displaying the historical electronic case and the entities in the historical electronic case according to a preset entity display type;
the updating module is used for adding an anchor point for each entity and receiving updating information obtained by updating the corresponding entity by a user through the anchor point;
the storage module is used for storing the historical electronic case, a plurality of entities in the historical electronic case and corresponding updated information in an entity table of the historical electronic case;
the training module is used for training a BiLSTM-CRF model based on the historical electronic case entity table to obtain an entity marking model;
And the marking module is used for physically marking the electronic case to be marked by using the entity marking model.
A third aspect of the present invention provides a computer apparatus comprising:
a memory for storing a computer program;
and the processor is used for realizing the electronic case entity marking method when executing the computer program.
A fourth aspect of the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the electronic case entity marking method.
In summary, according to the electronic case entity marking method, the electronic case entity marking device, the computer equipment and the storage medium, different displays of the plurality of entities in the electronic case are realized by identifying the plurality of entities in the historical electronic case and then displaying the historical electronic case and the plurality of entities in the historical electronic case according to the preset entity display types, and the corresponding entities can be rapidly positioned through the display, so that whether the entities need to be corrected or not is conveniently determined; then receiving updating information of a user on a corresponding entity in an anchor point mode, storing the historical electronic case, a plurality of entities in the historical electronic case and the corresponding updating information in a historical electronic case entity table, thereby completing quick correction of the plurality of entities in the electronic case, obtaining accurate initial positions, end positions and paragraph marks of the entities in the historical electronic case entity table, solving the problem that context semantics cannot be associated, avoiding the conditions of words with ambiguity and words with ambiguity, so that the accuracy of an entity marking model obtained by training a BiLSTM-CRF model based on the historical electronic case entity table can be improved; and finally, when the entity marking model is used for marking the entity of the electronic case to be marked, the accuracy is higher.
Drawings
Fig. 1 is a flowchart of a method for marking an electronic case entity according to an embodiment of the present invention.
Fig. 2 is a block diagram of an electronic case entity marking device according to a second embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. It should be noted that, without conflict, the embodiments of the present invention and features in the embodiments may be combined with each other.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Fig. 1 is a flowchart of a method for marking an electronic case entity according to an embodiment of the present invention. The electronic case entity marking method specifically comprises the following steps, the sequence of the steps in the flow chart can be changed according to different requirements, and some steps can be omitted.
S11, identifying a plurality of entities in the historical electronic case.
Electronic medical records (Electronic Medical Record, EMR) are the primary information that hospitals record in an electronic manner the patient during treatment.
Wherein the entity refers to medical nouns such as diseases, symptoms, diagnosis classification, treatment, examination, human tissue, examination items, allergy history, genetic history, personal history and the like.
The computer equipment is provided with a display interface, an uploading interface of the historical electronic case is displayed on the display interface, the historical electronic case can be uploaded into the computer equipment through the uploading interface, and the historical electronic case is displayed on the display interface of the computer equipment. The electronic medical record can be in an html format or a txt format. And correcting a plurality of entities in the historical electronic cases by a professional medical entity marker through a display interface provided by the computer equipment, and training an entity marking model by the corrected entities, so that entity marking is carried out on the new electronic cases, and the accuracy of the entity marking of the new electronic cases is improved.
In an alternative embodiment, the identifying the plurality of entities in the historical electronic case includes:
Acquiring a historical electronic case set;
word segmentation is carried out on the historical electronic case set through a barking word segmentation tool to obtain a plurality of phrases;
obtaining entity marks of the plurality of phrases;
constructing a medical knowledge graph according to the plurality of phrase and entity marks;
and identifying a plurality of entities in the historical electronic case by using the medical knowledge graph.
The medical knowledge graph is a network structure graph of entities and entity attributes, each entity corresponds to a plurality of entity attributes, and each entity attribute corresponds to a unique entity. For example, the entity type is a disease, and the corresponding plurality of entity attributes may include: cold, diarrhea, cancer, etc.
The computer equipment can acquire a plurality of historical electronic cases in a web crawler mode, can also acquire a plurality of historical electronic cases from a medical institution database, and can determine a historical electronic case set from the plurality of historical electronic cases. The computer equipment divides words of the historical electronic case set through a barking word division tool to obtain a plurality of phrases, common personnel (non-professional medical entity markers) carry out entity marking on each phrase, and the phrases are used as entity attributes corresponding to the entity marking, so that the computer equipment constructs a medical knowledge graph according to the plurality of phrases and the corresponding entity marking and is used for carrying out entity marking on the uploaded electronic cases.
Because the medical knowledge graph cannot exhaust all the entities and the entity attributes, and the entities in the medical knowledge graph are not completely correct, when the trained entity marking model marks a plurality of entities in the historical electronic cases, the marking accuracy is not high, the entities in each historical electronic case are corrected by the method, and the entity marking model is retrained according to the corrected entities, so that the accuracy of the entity marking of the historical electronic cases is improved.
S12, displaying the historical electronic case and the entities in the historical electronic case according to a preset entity display type.
The computer equipment is pre-stored with a database table, and the database table stores the association relation between the entity type and the display type. For example, if the entity type is a disease, the display type is purple; the entity type is symptom, and the display type is yellow. The display type includes not only display color but also display pattern, character display size, and the like.
In an optional embodiment, the displaying the historical electronic case and the plurality of entities in the historical electronic case according to a preset entity display type includes:
Identifying a plurality of key fields in the historical electronic case;
positioning the historical electronic case by taking the key fields as paragraph marks;
acquiring a display type corresponding to each entity;
and adding a < span > tag at a position corresponding to the entity on the historical electronic case according to the display type.
Wherein the < span > tag is an in-line tag of hypertext markup language (HyperText Markup Language, HTML) used to combine in-line elements in a document. The displayed content may be rendered using a < span > tag.
The computer device is preset with a plurality of key fields, and the preset plurality of key fields may include, but are not limited to: patient information, complaints, present medical history, past history, personal history, marital history, family history, allergy history, assisted exam, admission diagnosis, and the like. And matching the characters in the historical electronic case with a plurality of preset key fields to identify the plurality of key fields in the historical electronic case.
In this optional embodiment, the plurality of key fields are used as paragraph marks to segment the historical electronic case, so that the content corresponding to the paragraph marks can be quickly located. By adding the < span > tag to the content corresponding to the entity on the historical electronic case, different entities can be distinguished and displayed in different display types, and the same entity type can be conveniently and quickly screened out through color.
S13, adding an anchor point for each entity, and receiving the update of the user to the corresponding entity through the anchor point to obtain update information.
The computer device adds an id or name for each entity so that an anchor point can be implemented by which a jump at a specified location on the electronic case can be implemented.
In an optional embodiment, adding an anchor point for each entity, and receiving, by the anchor point, an update of the corresponding entity by the user to obtain the update information includes:
adding an ID for each entity and taking the ID as an anchor point of the entity;
when detecting an instruction of which the anchor point is selected, jumping to a target entity corresponding to the selected anchor point;
when detecting that an operation instruction is received at a position corresponding to the target entity on the display interface, updating the target entity according to the operation instruction;
and acquiring the starting position, the ending position and the paragraph mark of the updated target entity to obtain updated information.
Wherein, the operation instruction comprises a deleting instruction, a replacing instruction, an adding instruction and the like. When the operation instruction is a deletion instruction, deleting the target entity; when the operation instruction is a replacement instruction, replacing the target entity as an entity newly input by a user; and when the operation instruction is an addition instruction, adding a new entity. When the entity type is incorrect (e.g., fever is symptomatic but marked as disease), the entity type may be modified. Missing marks (e.g., fever and fever are the same meaning but not marked) may also be added with marks.
For example, when a patient suffering from fever is queried, the traditional mode only performs key word retrieval on the patient suffering from fever, but fever may not be found, and update information is obtained by receiving update of a user on a corresponding entity through the anchor point, so that the patient suffering from fever is updated to the same entity.
For another example, when a patient with "fever" is queried, the "non-fever" is retrieved because the "non-fever" entity is marked in the "non-fever", and the deletion of the "fever" entity in the "non-fever" is received by the anchor point.
The computer equipment acquires the starting position, the ending position and the paragraph mark of the updated target entity through a getSelection method of the window object. In the implementation, the getSelection method may be called to obtain the starting position and the ending position of the updated entity in the whole electronic case text as the starting position and the ending position of the updated target entity, or may obtain the starting position and the ending position of the updated entity in the corresponding paragraph as the starting position and the ending position of the updated target entity.
And S14, storing the historical electronic case, a plurality of entities in the historical electronic case and corresponding updated information in an entity table of the historical electronic case.
And when the computer equipment receives the update information of one entity, storing the updated entity and the corresponding update information in the entity table of the historical electronic case.
The history electronic case entity table stores a plurality of entities, and the starting position, the ending position and the paragraph marks of each entity. The start position, end position and paragraph marks are needed in training the BiLSTM-CRF model.
And S15, training a BiLSTM-CRF model based on the historical electronic case entity table to obtain an entity marking model.
Because the dataset needs to be labeled in BIO format before training the BiLSTM-CRF model, each line consists of char and tags, char and tags are separated by "\t", and sentences are separated by empty lines. BIO labeling: each element is labeled "B-X", "I-X", or "O". Wherein "B-X" indicates that the fragment in which the element is located is of the X type and that the element is at the beginning of the fragment, "I-X" indicates that the fragment in which the element is located is of the X type and that the element is at the middle of the fragment, "O" indicates that the element is not of any type.
The computer equipment obtains the initial position, the final position and the paragraph marks of the corrected entity in the historical electronic case through correcting the plurality of entities of the displayed historical electronic case, which is equivalent to completing the preparation work of marking the data set in the BIO format before training the BiLSTM-CRF model. Therefore, a plurality of historical electronic cases and corresponding entity marking results can be directly obtained from the entity table of the historical electronic cases, and the entity marking model is trained. In the implementation, the corresponding entity marking results of a plurality of historical electronic case pairs in the historical electronic case entity table are used as data sets, the data sets are divided into training sets and test sets, the data sets are used as the parameters of the BiLSTM-CRF model, and the learning and training of the BiLSTM-CRF model are stopped until the first difference value between the predicted initial position of the entity in the electronic medical record and the actual initial position of the entity in the electronic medical record is obtained, the second difference value between the predicted final position of the entity in the electronic medical record and the actual final position of the entity in the electronic medical record is obtained, and the third difference value between the predicted paragraph marking of the entity in the electronic medical record and the actual paragraph marking of the entity in the electronic medical record is smaller than a preset threshold value.
S16, using the entity marking model to carry out entity marking on the electronic cases to be marked.
The electronic case to be marked refers to an electronic case needing entity marking, the electronic case to be marked is input into the entity marking model, and a plurality of entities in the electronic case to be marked are marked by the entity marking model.
In an optional embodiment, after the displaying the historical electronic case and the plurality of entities in the historical electronic case according to a preset entity display type, the method further comprises:
displaying a plurality of entity virtual icons, wherein each entity virtual icon corresponds to one entity;
after detecting that any entity virtual icon in the plurality of entity virtual icons receives a selected instruction, displaying an entity text input box around a target entity virtual icon receiving the selected instruction;
receiving an entity input in the entity text input box;
and updating the entity corresponding to the target entity virtual icon to the entity input in the text input box, and synchronously updating the target entity virtual icon.
In this alternative embodiment, the computer device displays the entity text entry box and inputs the new entity type through the entity text entry box, replacing the old entity type with the new entity type, enabling quick correction of the same entity.
In an optional embodiment, after the computer device detects that any entity virtual icon receives the selection instruction, the entity corresponding to the selected target entity virtual icon may be displayed, and the entity corresponding to the unselected entity virtual icon is not displayed, so that a user can quickly check whether the entity in the historical electronic case is the same or not and whether modification or replacement is required, thereby improving efficiency of calibrating entity marks in the historical electronic case.
In an alternative embodiment, the method further comprises:
receiving query text sent by computer equipment;
inquiring a target historical electronic case corresponding to the inquiring text through the historical electronic case entity table;
returning the target historical electronic case to the computer device.
The query text refers to a query keyword input by a user, for example, "diarrhea for more than two weeks" and "hepatitis patient with hypertension for 3 years".
The computer equipment inquires out a plurality of target historical electronic cases and returns the target historical electronic cases to the computer equipment.
In an optional embodiment, the querying the target historical electronic case corresponding to the query text through the historical electronic case entity table includes:
Analyzing the query text to obtain query entity information, wherein the query entity information comprises a query entity type and a query entity attribute;
querying a plurality of target entities corresponding to the query entity type and target entity attributes corresponding to each target entity from the historical electronic case entity table;
matching the query entity attribute with the target entity attribute corresponding to each target entity;
determining a medical record identifier corresponding to the successfully matched target entity attribute as a target medical record identifier;
inquiring the corresponding target electronic medical record according to the target medical record identifier.
As exemplified above, parsing the query text "diarrhea for more than two weeks" yields a query entity type of "disease" and a query entity attribute of "diarrhea".
The medical record mark is the number of the historical electronic case and has uniqueness.
According to the alternative embodiment, the target electronic medical record corresponding to the query text can be rapidly and accurately queried by querying the target medical record identifier which is the same as the query entity type and the query entity attribute from the historical electronic case entity table and then querying the target electronic medical record according to the target medical record identifier.
According to the method and the device, the plurality of entities in the historical electronic case are identified, and then the historical electronic case and the plurality of entities in the historical electronic case are displayed according to the preset entity display type, so that different displays of the plurality of entities in the electronic case are realized, the corresponding entities can be rapidly positioned through the display, and whether the entities need to be corrected or not is conveniently determined; then receiving updating information of a user on a corresponding entity in an anchor point mode, storing the historical electronic case, a plurality of entities in the historical electronic case and the corresponding updating information in a historical electronic case entity table, thereby completing quick correction of the plurality of entities in the electronic case, obtaining accurate initial positions, end positions and paragraph marks of the entities in the historical electronic case entity table, solving the problem that context semantics cannot be associated, avoiding the conditions of words with ambiguity and words with ambiguity, so that the accuracy of an entity marking model obtained by training a BiLSTM-CRF model based on the historical electronic case entity table can be improved; and finally, when the entity marking model is used for marking the entity of the electronic case to be marked, the accuracy is higher.
In addition, the invention can help to quickly search the electronic cases meeting the requirements when in actual search application, and distinguish different entities in the electronic cases through different colors.
The electronic case entity marking method can be applied to intelligent medical treatment and promotes construction of intelligent cities.
It is emphasized that to further guarantee the privacy and security of the entity marking model, the entity marking model may be stored in a node of the blockchain.
Fig. 2 is a block diagram of an electronic case entity marking device according to a second embodiment of the present invention.
In some embodiments, the electronic case entity marking device 20 may include a plurality of functional modules consisting of computer program segments. The computer program of the individual program segments in the electronic case entity marking means 20 may be stored in a memory of a computer device and executed by at least one processor to perform (see fig. 1 for details) the functions of electronic case entity marking.
In this embodiment, the electronic case entity marking device 20 may be divided into a plurality of functional modules according to the functions performed by the electronic case entity marking device. The functional module may include: an identification module 201, a display module 202, an update module 203, a storage module 204, a training module 205, a marking module 206, a synchronization module 207, and a query module 208. The module referred to in the present invention refers to a series of computer program segments capable of being executed by at least one processor and of performing a fixed function, stored in a memory. In the present embodiment, the functions of the respective modules will be described in detail in the following embodiments.
The identification module 201 is configured to identify a plurality of entities in the historical electronic case.
Electronic medical records (Electronic Medical Record, EMR) are the primary information that hospitals record in an electronic manner the patient during treatment.
Wherein the entity refers to medical nouns such as diseases, symptoms, diagnosis classification, treatment, examination, human tissue, examination items, allergy history, genetic history, personal history and the like.
The computer equipment is provided with a display interface, an uploading interface of the historical electronic case is displayed on the display interface, the historical electronic case can be uploaded into the computer equipment through the uploading interface, and the historical electronic case is displayed on the display interface of the computer equipment. The electronic medical record can be in an html format or a txt format. And correcting a plurality of entities in the historical electronic cases by a professional medical entity marker through a display interface provided by the computer equipment, and training an entity marking model by the corrected entities, so that entity marking is carried out on the new electronic cases, and the accuracy of the entity marking of the new electronic cases is improved.
In an alternative embodiment, the identifying module 201 identifies a plurality of entities in the historical electronic case includes:
Acquiring a historical electronic case set;
word segmentation is carried out on the historical electronic case set through a barking word segmentation tool to obtain a plurality of phrases;
obtaining entity marks of the plurality of phrases;
constructing a medical knowledge graph according to the plurality of phrase and entity marks;
and identifying a plurality of entities in the historical electronic case by using the medical knowledge graph.
The medical knowledge graph is a network structure graph of entities and entity attributes, each entity corresponds to a plurality of entity attributes, and each entity attribute corresponds to a unique entity. For example, the entity type is a disease, and the corresponding plurality of entity attributes may include: cold, diarrhea, cancer, etc.
The computer equipment can acquire a plurality of historical electronic cases in a web crawler mode, can also acquire a plurality of historical electronic cases from a medical institution database, and can determine a historical electronic case set from the plurality of historical electronic cases. The computer equipment divides words of the historical electronic case set through a barking word division tool to obtain a plurality of phrases, common personnel (non-professional medical entity markers) carry out entity marking on each phrase, and the phrases are used as entity attributes corresponding to the entity marking, so that the computer equipment constructs a medical knowledge graph according to the plurality of phrases and the corresponding entity marking and is used for carrying out entity marking on the uploaded electronic cases.
Because the medical knowledge graph cannot exhaust all the entities and the entity attributes, and the entities in the medical knowledge graph are not completely correct, when the trained entity marking model marks a plurality of entities in the historical electronic cases, the marking accuracy is not high, the entities in each historical electronic case are corrected by the method, and the entity marking model is retrained according to the corrected entities, so that the accuracy of the entity marking of the historical electronic cases is improved.
The display module 202 is configured to display the historical electronic case and the entities in the historical electronic case according to a preset entity display type.
The computer equipment is pre-stored with a database table, and the database table stores the association relation between the entity type and the display type. For example, if the entity type is a disease, the display type is purple; the entity type is symptom, and the display type is yellow. The display type includes not only display color but also display pattern, character display size, and the like.
In an alternative embodiment, the displaying module 202 displays the historical electronic case and the plurality of entities in the historical electronic case according to a preset entity display type includes:
Identifying a plurality of key fields in the historical electronic case;
positioning the historical electronic case by taking the key fields as paragraph marks;
acquiring a display type corresponding to each entity;
and adding a < span > tag at a position corresponding to the entity on the historical electronic case according to the display type.
Wherein the < span > tag is an in-line tag of hypertext markup language (HyperText Markup Language, HTML) used to combine in-line elements in a document. The displayed content may be rendered using a < span > tag.
The computer device is preset with a plurality of key fields, and the preset plurality of key fields may include, but are not limited to: patient information, complaints, present medical history, past history, personal history, marital history, family history, allergy history, assisted exam, admission diagnosis, and the like. And matching the characters in the historical electronic case with a plurality of preset key fields to identify the plurality of key fields in the historical electronic case.
In this optional embodiment, the plurality of key fields are used as paragraph marks to segment the historical electronic case, so that the content corresponding to the paragraph marks can be quickly located. By adding the < span > tag to the content corresponding to the entity on the historical electronic case, different entities can be distinguished and displayed in different display types, and the same entity type can be conveniently and quickly screened out through color.
The update module 203 is configured to add an anchor point to each entity, and receive, through the anchor point, an update of the user to the corresponding entity to obtain update information.
The computer device adds an id or name for each entity so that an anchor point can be implemented by which a jump at a specified location on the electronic case can be implemented.
In an alternative embodiment, the updating module 203 adds an anchor point to each entity, and receiving, through the anchor point, the update information obtained by updating the corresponding entity by the user includes:
adding an ID for each entity and taking the ID as an anchor point of the entity;
when detecting an instruction of which the anchor point is selected, jumping to a target entity corresponding to the selected anchor point;
when detecting that an operation instruction is received at a position corresponding to the target entity on the display interface, updating the target entity according to the operation instruction;
and acquiring the starting position, the ending position and the paragraph mark of the updated target entity to obtain updated information.
Wherein, the operation instruction comprises a deleting instruction, a replacing instruction, an adding instruction and the like. When the operation instruction is a deletion instruction, deleting the target entity; when the operation instruction is a replacement instruction, replacing the target entity as an entity newly input by a user; and when the operation instruction is an addition instruction, adding a new entity. When the entity type is incorrect (e.g., fever is symptomatic but marked as disease), the entity type may be modified. Missing marks (e.g., fever and fever are the same meaning but not marked) may also be added with marks.
For example, when a patient suffering from fever is queried, the traditional mode only performs key word retrieval on the patient suffering from fever, but fever may not be found, and update information is obtained by receiving update of a user on a corresponding entity through the anchor point, so that the patient suffering from fever is updated to the same entity.
For another example, when a patient with "fever" is queried, the "non-fever" is retrieved because the "non-fever" entity is marked in the "non-fever", and the deletion of the "fever" entity in the "non-fever" is received by the anchor point.
The computer equipment acquires the starting position, the ending position and the paragraph mark of the updated target entity through a getSelection method of the window object. In the implementation, the getSelection method may be called to obtain the starting position and the ending position of the updated entity in the whole electronic case text as the starting position and the ending position of the updated target entity, or may obtain the starting position and the ending position of the updated entity in the corresponding paragraph as the starting position and the ending position of the updated target entity.
The storage module 204 is configured to store the historical electronic case and a plurality of entities in the historical electronic case and corresponding update information in an entity table of the historical electronic case.
And when the computer equipment receives the update information of one entity, storing the updated entity and the corresponding update information in the entity table of the historical electronic case.
The history electronic case entity table stores a plurality of entities, and the starting position, the ending position and the paragraph marks of each entity. The start position, end position and paragraph marks are needed in training the BiLSTM-CRF model.
The training module 205 is configured to train a BiLSTM-CRF model to obtain a entity marking model based on the historical electronic case entity table.
Because the dataset needs to be labeled in BIO format before training the BiLSTM-CRF model, each line consists of char and tags, char and tags are separated by "\t", and sentences are separated by empty lines. BIO labeling: each element is labeled "B-X", "I-X", or "O". Wherein "B-X" indicates that the fragment in which the element is located is of the X type and that the element is at the beginning of the fragment, "I-X" indicates that the fragment in which the element is located is of the X type and that the element is at the middle of the fragment, "O" indicates that the element is not of any type.
The computer equipment obtains the initial position, the final position and the paragraph marks of the corrected entity in the historical electronic case through correcting the plurality of entities of the displayed historical electronic case, which is equivalent to completing the preparation work of marking the data set in the BIO format before training the BiLSTM-CRF model. Therefore, a plurality of historical electronic cases and corresponding entity marking results can be directly obtained from the entity table of the historical electronic cases, and the entity marking model is trained. In the implementation, the corresponding entity marking results of a plurality of historical electronic case pairs in the historical electronic case entity table are used as data sets, the data sets are divided into training sets and test sets, the data sets are used as the parameters of the BiLSTM-CRF model, and the learning and training of the BiLSTM-CRF model are stopped until the first difference value between the predicted initial position of the entity in the electronic medical record and the actual initial position of the entity in the electronic medical record is obtained, the second difference value between the predicted final position of the entity in the electronic medical record and the actual final position of the entity in the electronic medical record is obtained, and the third difference value between the predicted paragraph marking of the entity in the electronic medical record and the actual paragraph marking of the entity in the electronic medical record is smaller than a preset threshold value.
The marking module 206 is configured to use the entity marking model to perform entity marking on the electronic case to be marked.
The electronic case to be marked refers to an electronic case needing entity marking, the electronic case to be marked is input into the entity marking model, and a plurality of entities in the electronic case to be marked are marked by the entity marking model.
The synchronization module 207 is configured to update the entities of the same entity type synchronously.
In an alternative embodiment, the synchronization module 207 updates the entities of the same entity type synchronously, including:
displaying a plurality of entity virtual icons, wherein each entity virtual icon corresponds to one entity;
after detecting that any entity virtual icon in the plurality of entity virtual icons receives a selected instruction, displaying an entity text input box around a target entity virtual icon receiving the selected instruction;
receiving an entity input in the entity text input box;
and updating the entity corresponding to the target entity virtual icon to the entity input in the text input box, and synchronously updating the target entity virtual icon.
In this alternative embodiment, the computer device displays the entity text entry box and inputs the new entity type through the entity text entry box, replacing the old entity type with the new entity type, enabling quick correction of the same entity.
In an optional embodiment, after the computer device detects that any entity virtual icon receives the selection instruction, the entity corresponding to the selected target entity virtual icon may be displayed, and the entity corresponding to the unselected entity virtual icon is not displayed, so that a user can quickly check whether the entity in the historical electronic case is the same or not and whether modification or replacement is required, thereby improving efficiency of calibrating entity marks in the historical electronic case.
The query module 208 is configured to receive a query text sent by a computer device; inquiring a target historical electronic case corresponding to the inquiring text through the historical electronic case entity table; returning the target historical electronic case to the computer device.
The query text refers to a query keyword input by a user, for example, "diarrhea for more than two weeks" and "hepatitis patient with hypertension for 3 years".
The computer equipment inquires out a plurality of target historical electronic cases and returns the target historical electronic cases to the computer equipment.
In an alternative embodiment, the querying module 208 queries, via the historical electronic case entity table, the target historical electronic case corresponding to the query text, including:
Analyzing the query text to obtain query entity information, wherein the query entity information comprises a query entity type and a query entity attribute;
querying a plurality of target entities corresponding to the query entity type and target entity attributes corresponding to each target entity from the historical electronic case entity table;
matching the query entity attribute with the target entity attribute corresponding to each target entity;
determining a medical record identifier corresponding to the successfully matched target entity attribute as a target medical record identifier;
inquiring the corresponding target electronic medical record according to the target medical record identifier.
As exemplified above, parsing the query text "diarrhea for more than two weeks" yields a query entity type of "disease" and a query entity attribute of "diarrhea".
The medical record mark is the number of the historical electronic case and has uniqueness.
According to the alternative embodiment, the target electronic medical record corresponding to the query text can be rapidly and accurately queried by querying the target medical record identifier which is the same as the query entity type and the query entity attribute from the historical electronic case entity table and then querying the target electronic medical record according to the target medical record identifier.
According to the method and the device, the plurality of entities in the historical electronic case are identified, and then the historical electronic case and the plurality of entities in the historical electronic case are displayed according to the preset entity display type, so that different displays of the plurality of entities in the electronic case are realized, the corresponding entities can be rapidly positioned through the display, and whether the entities need to be corrected or not is conveniently determined; then receiving updating information of a user on a corresponding entity in an anchor point mode, storing the historical electronic case, a plurality of entities in the historical electronic case and the corresponding updating information in a historical electronic case entity table, thereby completing quick correction of the plurality of entities in the electronic case, obtaining accurate initial positions, end positions and paragraph marks of the entities in the historical electronic case entity table, solving the problem that context semantics cannot be associated, avoiding the conditions of words with ambiguity and words with ambiguity, so that the accuracy of an entity marking model obtained by training a BiLSTM-CRF model based on the historical electronic case entity table can be improved; and finally, when the entity marking model is used for marking the entity of the electronic case to be marked, the accuracy is higher.
In addition, the invention can help to quickly search the electronic cases meeting the requirements when in actual search application, and distinguish different entities in the electronic cases through different colors.
It is emphasized that to further guarantee the privacy and security of the entity marking model, the entity marking model may be stored in a node of the blockchain.
Fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present invention. In the preferred embodiment of the present invention, the computer device 3 includes a memory 31, at least one processor 32, at least one communication bus 33, and a transceiver 34.
It will be appreciated by those skilled in the art that the configuration of the computer device shown in fig. 3 is not limiting of the embodiments of the present invention, and that either a bus-type configuration or a star-type configuration is possible, and that the computer device 3 may include more or less other hardware or software than that shown, or a different arrangement of components.
In some embodiments, the computer device 3 is a computer device capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions, and its hardware includes, but is not limited to, a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The computer device 3 may also include a client device, which includes, but is not limited to, any electronic product that can interact with a client by way of a keyboard, mouse, remote control, touch pad, or voice control device, such as a personal computer, tablet, smart phone, digital camera, etc.
It should be noted that the computer device 3 is only used as an example, and other electronic products that may be present in the present invention or may be present in the future are also included in the scope of the present invention by way of reference.
In some embodiments, the memory 31 has stored therein a computer program which, when executed by the at least one processor 32, performs all or part of the steps in the electronic case entity tagging method as described. The Memory 31 includes Read-Only Memory (ROM), programmable Read-Only Memory (PROM), erasable programmable Read-Only Memory (EPROM), one-time programmable Read-Only Memory (One-time Programmable Read-Only Memory, OTPROM), electrically erasable rewritable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
In some embodiments, the at least one processor 32 is a Control Unit (Control Unit) of the computer device 3, connects the various components of the entire computer device 3 using various interfaces and lines, and performs various functions and processes of the computer device 3 by running or executing programs or modules stored in the memory 31, and invoking data stored in the memory 31. For example, the at least one processor 32, when executing the computer program stored in the memory, implements all or part of the steps of the electronic case entity tagging method described in embodiments of the present invention; or to implement all or part of the functionality of the electronic case entity marking device. The at least one processor 32 may be comprised of integrated circuits, such as a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functionality, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like.
In some embodiments, the at least one communication bus 33 is arranged to enable connected communication between the memory 31 and the at least one processor 32 or the like.
Although not shown, the computer device 3 may further comprise a power source (such as a battery) for powering the various components, preferably the power source is logically connected to the at least one processor 32 via a power management means, whereby the functions of managing charging, discharging, and power consumption are performed by the power management means. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The computer device 3 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described in detail herein.
The integrated units implemented in the form of software functional modules described above may be stored in a computer readable storage medium. The software functional modules described above are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, a computer device, or a network device, etc.) or processor (processor) to perform portions of the methods described in the various embodiments of the invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention 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 can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it will be obvious that the term "comprising" does not exclude other elements or that the singular does not exclude a plurality. A plurality of units or means recited in the apparatus claims can also be implemented by means of one unit or means in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (7)
1. A method for electronic case entity tagging, the method comprising:
identifying a plurality of entities in a historical electronic case, comprising: acquiring a historical electronic case set; word segmentation is carried out on the historical electronic case set through a barking word segmentation tool to obtain a plurality of phrases; obtaining entity marks of the plurality of phrases; constructing a medical knowledge graph according to the plurality of phrase and entity marks; identifying a plurality of entities in the historical electronic case using the medical knowledge graph;
displaying the historical electronic case and the entities in the historical electronic case according to a preset entity display type;
displaying a plurality of entity virtual icons, wherein each entity virtual icon corresponds to one entity; after detecting that any entity virtual icon in the plurality of entity virtual icons receives a selected instruction, displaying an entity text input box around a target entity virtual icon receiving the selected instruction; receiving an entity input in the entity text input box; updating the entity corresponding to the target entity virtual icon into the entity input in the text input box, and synchronously updating the target entity virtual icon;
Adding an anchor point for each entity, and receiving the update of the user to the corresponding entity through the anchor point to obtain update information, wherein the method comprises the following steps: adding an ID for each entity and taking the ID as an anchor point of the entity; when detecting an instruction of which the anchor point is selected, jumping to a target entity corresponding to the selected anchor point; when detecting that an operation instruction is received at a position corresponding to the target entity on a display interface, updating the target entity according to the operation instruction; acquiring the initial position, the final position and the paragraph mark of the updated target entity to obtain updated information;
storing the historical electronic case and a plurality of entities in the historical electronic case and corresponding updated information in an entity table of the historical electronic case;
training a BiLSTM-CRF model based on the historical electronic case entity table to obtain an entity marking model;
and carrying out entity marking on the electronic cases to be marked by using the entity marking model.
2. The electronic case entity marking method according to claim 1, wherein the displaying the historical electronic case and the plurality of entities in the historical electronic case according to a preset entity display type includes:
identifying a plurality of key fields in the historical electronic case;
Positioning the historical electronic case by taking the key fields as paragraph marks;
acquiring a display type corresponding to each entity;
and adding a < span > tag at a position corresponding to the entity on the historical electronic case according to the display type.
3. The electronic case entity marking method according to any one of claims 1 to 2, characterized in that the method further comprises:
receiving query text sent by computer equipment;
inquiring a target historical electronic case corresponding to the inquiring text through the historical electronic case entity table;
returning the target historical electronic case to the computer device.
4. The electronic case entity tagging method of claim 3, wherein the querying the target historical electronic case corresponding to the query text through the historical electronic case entity table comprises:
analyzing the query text to obtain query entity information, wherein the query entity information comprises a query entity type and a query entity attribute;
querying a plurality of target entities corresponding to the query entity type and target entity attributes corresponding to each target entity from the historical electronic case entity table;
Matching the query entity attribute with the target entity attribute corresponding to each target entity;
determining a medical record identifier corresponding to the successfully matched target entity attribute as a target medical record identifier;
inquiring the corresponding target electronic medical record according to the target medical record identifier.
5. An electronic case entity marking device for implementing the electronic case entity marking method of claim 1, the device comprising:
the identification module is used for identifying a plurality of entities in the historical electronic cases;
the display module is used for displaying the historical electronic case and the entities in the historical electronic case according to a preset entity display type;
the updating module is used for adding an anchor point for each entity and receiving updating information obtained by updating the corresponding entity by a user through the anchor point;
the storage module is used for storing the historical electronic case, a plurality of entities in the historical electronic case and corresponding updated information in an entity table of the historical electronic case;
the training module is used for training a BiLSTM-CRF model based on the historical electronic case entity table to obtain an entity marking model;
and the marking module is used for physically marking the electronic case to be marked by using the entity marking model.
6. A computer device, the computer device comprising:
a memory for storing a computer program;
a processor for implementing the electronic case entity marking method according to any one of claims 1 to 4 when executing the computer program.
7. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program, when executed by a processor, implements the electronic case entity marking method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010917927.7A CN111986765B (en) | 2020-09-03 | 2020-09-03 | Electronic case entity marking method, electronic case entity marking device, electronic case entity marking computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010917927.7A CN111986765B (en) | 2020-09-03 | 2020-09-03 | Electronic case entity marking method, electronic case entity marking device, electronic case entity marking computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111986765A CN111986765A (en) | 2020-11-24 |
| CN111986765B true CN111986765B (en) | 2023-11-21 |
Family
ID=73447462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010917927.7A Active CN111986765B (en) | 2020-09-03 | 2020-09-03 | Electronic case entity marking method, electronic case entity marking device, electronic case entity marking computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111986765B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113220896B (en) * | 2021-04-27 | 2024-03-19 | 北京大数医达科技有限公司 | Multi-source knowledge graph generation method, device and terminal equipment |
| CN114297207A (en) * | 2021-12-07 | 2022-04-08 | 腾讯数码（天津）有限公司 | Entity library updating method and device, computer equipment and storage medium |
| CN116205235B (en) * | 2023-05-05 | 2023-08-01 | 北京脉络洞察科技有限公司 | Data set dividing method and device and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408743A (en) * | 2018-08-21 | 2019-03-01 | 中国科学院自动化研究所 | Text link embedding grammar |
| CN110010217A (en) * | 2019-04-11 | 2019-07-12 | 中国医学科学院医学信息研究所 | A kind of mask method and device of electronic health record |
| CN110427491A (en) * | 2019-07-04 | 2019-11-08 | 北京爱医生智慧医疗科技有限公司 | A kind of medical knowledge map construction method and device based on electronic health record |
| CN110705293A (en) * | 2019-08-23 | 2020-01-17 | 中国科学院苏州生物医学工程技术研究所 | Electronic medical record text named entity recognition method based on pre-training language model |
| CN111126068A (en) * | 2019-12-25 | 2020-05-08 | 中电云脑(天津)科技有限公司 | Chinese named entity recognition method and device and electronic equipment |
| CN111445968A (en) * | 2020-03-16 | 2020-07-24 | 平安国际智慧城市科技股份有限公司 | Electronic medical record query method and device, computer equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070258100A1 (en) * | 2004-11-12 | 2007-11-08 | Justsystems Corporation | Document Processing Device and Document Processing Method |
| CN109376309B (en) * | 2018-12-28 | 2022-05-17 | 北京百度网讯科技有限公司 | Document recommendation method and device based on semantic tags |
-
2020
- 2020-09-03 CN CN202010917927.7A patent/CN111986765B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408743A (en) * | 2018-08-21 | 2019-03-01 | 中国科学院自动化研究所 | Text link embedding grammar |
| CN110010217A (en) * | 2019-04-11 | 2019-07-12 | 中国医学科学院医学信息研究所 | A kind of mask method and device of electronic health record |
| CN110427491A (en) * | 2019-07-04 | 2019-11-08 | 北京爱医生智慧医疗科技有限公司 | A kind of medical knowledge map construction method and device based on electronic health record |
| CN110705293A (en) * | 2019-08-23 | 2020-01-17 | 中国科学院苏州生物医学工程技术研究所 | Electronic medical record text named entity recognition method based on pre-training language model |
| CN111126068A (en) * | 2019-12-25 | 2020-05-08 | 中电云脑(天津)科技有限公司 | Chinese named entity recognition method and device and electronic equipment |
| CN111445968A (en) * | 2020-03-16 | 2020-07-24 | 平安国际智慧城市科技股份有限公司 | Electronic medical record query method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 中医病历术语识别方法探讨;孙超等;中国中医药图书情报杂志(第02期);第1-5页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111986765A (en) | 2020-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111986765B (en) | Electronic case entity marking method, electronic case entity marking device, electronic case entity marking computer equipment and storage medium | |
| US11562813B2 (en) | Automated clinical indicator recognition with natural language processing | |
| US10818397B2 (en) | Clinical content analytics engine | |
| CN110459320B (en) | Knowledge graph-based auxiliary diagnosis and treatment system | |
| US10509889B2 (en) | Data processing system and method for computer-assisted coding of natural language medical text | |
| US11881293B2 (en) | Methods for automatic cohort selection in epidemiologic studies and clinical trials | |
| CN111813963B (en) | Knowledge graph construction method and device, electronic equipment and storage medium | |
| US10552931B2 (en) | Automated clinical indicator recognition with natural language processing | |
| CN107239665B (en) | Medical information query system and method | |
| JP3998706B2 (en) | Document data management method, management system, and computer software | |
| US8600772B2 (en) | Systems and methods for interfacing with healthcare organization coding system | |
| CN112149409B (en) | Medical word cloud generation method and device, computer equipment and storage medium | |
| CN111341456A (en) | Method and device for generating diabetic foot knowledge map and readable storage medium | |
| CN114255884A (en) | Hypertension drug treatment knowledge graph construction method and device | |
| CN115482921A (en) | Modeled DRGs clinical path planning management information system and method | |
| CN110609910A (en) | Medical knowledge graph construction method and device, storage medium and electronic equipment | |
| CN114023462A (en) | Computerized clinical guideline construction method and device based on graphical representation | |
| CN116525053A (en) | Patient report generation method, device, electronic equipment and medium | |
| CN105683975A (en) | System and method enabling the efficient management of treatment plans and their revisions and updates | |
| CN114020926A (en) | Data processing method and device and electronic equipment | |
| CN1573787A (en) | Method for processing a data record comprising therapeutic advice items in the course of medical treatment | |
| WO2017132145A1 (en) | System and method for optimizing electronic medical terminology post-coordination coding | |
| Soares et al. | An interdisciplinary approach to reducing errors in extracted electronic health record data for research | |
| US20230335298A1 (en) | Intent-based clustering of medical information | |
| JP2015201093A (en) | Medical examination support system |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220922 Address after: Room 2601 (Unit 07), Qianhai Free Trade Building, No. 3048, Xinghai Avenue, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Ping An Smart Healthcare Technology Co.,Ltd. Address before: 1-34 / F, Qianhai free trade building, 3048 Xinghai Avenue, Mawan, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Applicant before: Ping An International Smart City Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |