CN110718305A - Method and device for automatically combing medicine labels based on medicine knowledge system - Google Patents
Method and device for automatically combing medicine labels based on medicine knowledge system Download PDFInfo
- Publication number
- CN110718305A CN110718305A CN201910963815.2A CN201910963815A CN110718305A CN 110718305 A CN110718305 A CN 110718305A CN 201910963815 A CN201910963815 A CN 201910963815A CN 110718305 A CN110718305 A CN 110718305A
- Authority
- CN
- China
- Prior art keywords
- medicine
- label
- knowledge system
- combed
- tree structure
- 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
Images
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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Abstract
The invention discloses a method for automatically combing a medicine label based on a medicine knowledge system, which comprises the following steps: constructing a medicine knowledge system of a tree structure, wherein data on leaf nodes at each tail end of the tree structure are disease identifications, and each disease identification corresponds to a symptom label and/or a hidden word element label; based on the medical knowledge system, a word segmentation tool supporting part of speech recognition is utilized, a longest migration result, namely corresponding to a specific branch in a tree structure, is obtained from the annotation of the medicine to be combed by adopting a random migration algorithm model, and the medicine to be combed is corresponding to a leaf node at the tail end of the specific branch; therefore, the symptom labels and/or the hidden word element labels corresponding to the disease identifiers on the corresponding tail end leaf nodes are given to the medicines to be combed, so that the automatic label combing work of the medicines is completed, and various medicines are automatically annotated and unified into the standardized labels. The invention also discloses a device, electronic equipment and a storage medium based on the method.
Description
Technical Field
The invention relates to the field of Chinese word segmentation of computers. And more particularly to a method for automatically combing drug labels based on a medical knowledge system.
Background
As a medicine management system, a large number of new medicines are often required to be recorded into the management system. Due to the fact that the number of the input users and the standards are different, the description of the newly input medicine is also greatly different. Particularly, because of the operation and market intervention, the description publisher is easy to stand at the kpi position to consider the problem, and the slow commodity is likely to be maintained, the function is changed or the medicine is magical and treats all diseases.
Therefore, it is necessary to develop a label that can quickly and automatically classify drugs into a medication management system according to the descriptions of the drugs, analyze and calculate the actual drugs and only manage other functions, and restore the original objects of the drugs.
A new technology needs to be developed to solve the problem of describing different medicines as standard as possible, and to automatically label various medicines with standardized labels so as to correctly call the medicines in the subsequent development.
Disclosure of Invention
An object of the present invention is to solve at least the above problems and to provide at least the advantages described later.
Still another object of the present invention is to provide a low frequency RFID power management method, which can reduce the amount of energy stored in the energy storage capacitor of the circuit, reduce the area of the energy storage capacitor, and thus reduce the chip area. .
To achieve these objects and other advantages in accordance with the purpose of the invention, there is provided a low frequency RFID power management method including:
the steel bar net comprises a main body, a steel bar net and a steel bar net, wherein the upper end of the main body is of a cuboid structure with an opening;
the supporting members comprise a plurality of supporting rods and a plurality of steel bars, the supporting rods are arranged below the steel bar mesh in parallel at equal intervals, the steel bars are arranged between two adjacent supporting rods at equal intervals, and the laying direction of the steel bars is vertical to that of the supporting rods;
the walking member comprises a pair of first sliding rails arranged in parallel and a push-pull piece arranged on one side wall of the main body, two ends of each first sliding rail are respectively arranged on the roadbed at two sides below the bridge to be constructed, and the push-pull piece is connected with a driving member arranged beside the bridge to be constructed;
two sets of parallel arrangement's gyro wheel is installed to the bottom of main part, the mounted position of a plurality of gyro wheels with first slide rail corresponds, and the pivot setting of each gyro wheel is between two adjacent reinforcing bars.
Preferably, a simple and easy movable hanging flower basket for bridge construction and maintenance, the vertical support pole of main part includes an outer pole and an interior pole, interior pole cover is established in the outer pole, be provided with the second slide rail on the inner wall of outer pole, be provided with on the outer wall of interior pole with second slide rail complex slider, just outer pole top is provided with the setting element.
Preferably, a simple and easy movable hanging flower basket for bridge construction and maintenance, the setting element is a detachable piece of buckling, the piece of buckling sets up to the U type, a support arm setting of the piece of buckling is in between outer pole and the interior pole, another support arm setting is in the outer pole outside.
Preferably, the simple movable hanging basket for bridge construction and maintenance is characterized in that the push-pull piece is a hydraulic oil cylinder, and the driving member is a hydraulic pump.
Preferably, an object of the present invention for bridge construction is to solve at least the above problems and provide other advantages which will be described later;
the invention also aims to provide a method for automatically combing the medicine label based on the medicine knowledge system, which can obviously improve the reliability of medicine description;
still another object of the present invention is to provide a method for automatically combing medicine labels based on a medical knowledge system, which can improve the efficiency of combing medicines; and
it is a further object of the present invention to provide an apparatus, an electronic device, and a storage medium for automatically combing a medicine label based on a medical knowledge system to implement the above method.
To achieve these objects and other advantages in accordance with the purpose of the invention, there is provided a method for automatically combing a label of a medicine based on a medical knowledge system, comprising the steps of:
constructing a medical knowledge system of a tree structure, wherein data on leaf nodes at each tail end of the tree structure are disease identifications, and each disease identification corresponds to a symptom label and/or a hidden word element label;
based on the medical knowledge system, a word segmentation tool supporting part of speech recognition is utilized, a longest migration result is obtained by annotating the medicine to be combed by adopting a random migration algorithm model, namely the longest migration result corresponds to a specific branch in the tree structure, and the medicine to be combed corresponds to a leaf node at the tail end of the specific branch;
therefore, the symptom label and/or the implicit word element label corresponding to the disease identification on the corresponding tail end leaf node are/is given to the medicine to be combed, so that the automatic label combing work of the medicine is completed.
For example, the disease is identified as the wind-heat type cold, or as the ID of the wind-heat type cold. The corresponding symptom labels are: yellow phlegm, yellow nasal discharge, cough, fever, etc., and the hidden lemma includes wind-warm syndrome, warm disease, apoplexy, typhoid fever, etc. The drug to be combed is, for example, Tongrentang FengGao granules, and the drug is hung on the leaf node at the tail end of the Fengren Gao. Or, the ID of the Tongrentang Fengren granules is related to the ID of the Fengren cold. Also, more drug IDs can be associated with the ID of wind-heat type common cold. Such as XIAOERHEFENGREJIAO, FENGREFENGGANMAO Capsule, etc. Thus, the newly recorded medicine, like Rentang Fengren Ganmao granules, can obtain symptom labels of yellow phlegm, yellow nasal discharge, cough, fever and the like, and implicit word element labels of wind-warm, epidemic febrile disease, apoplexy, typhoid fever and the like.
The method for automatically combing the medicine label based on the medicine knowledge system comprises the following steps of: manually marking a batch of sample data; and training and learning the professional data periodically crawled out on the professional site by utilizing a word segmentation tool according to the sample data, thereby constructing a medical knowledge system with a tree structure.
This is an artificial intelligence learning method.
The method for automatically combing the medicine labels based on the medicine knowledge system is characterized in that the part of speech recognition is that each disease mark is defined as different part of speech, and the medicine to be combed corresponds to a terminal leaf node, namely the corresponding part of speech is endowed to the medicine to be combed.
That is, although it is necessary to use a segmentation tool capable of recognizing parts of speech, the segmentation tool is not directly used to distinguish nouns, verbs, adjectives, and the like. Instead, the individual disease identifiers are defined in terms of different parts of speech, for example, the ID of the wind-heat type cold is defined in terms of one part of speech, and the purpose is to distinguish the disease identifiers to which the medicine to be combed should belong.
The method for automatically combing the medicine label based on the medicine knowledge system is characterized in that the disease identification is the unique identification code of the disease with the finest granularity.
The method for automatically combing the medicine label based on the medicine knowledge system is characterized in that the medicine to be combed comprises a medicine name and a unique identification code thereof.
Finally, the identification code of the drug is associated with the identification code of the disease.
According to the method for automatically combing the medicine labels based on the medicine knowledge system, if the annotations of the medicine to be combed cannot be matched with the medicine knowledge system, the medicine is moved to a region to be manually processed for subsequent manual processing.
This means that the drugs that are not hung in the knowledge base will also be recorded, and then can be manually maintained in the knowledge base, and the information of the drug name will also be pushed to the training set for the subsequent off-line training to continue training. At present, the identification is not available, and most of the identification is manual dry processing. The frequency of new shelved medications that cannot be identified is low. Because data is built, after data is extracted from an external source, newly added medicines are few and slow, the medicines have long flow in the market, and most of the medicines are health-care medicines, such as supplementary proteins, vitamins, weight-losing medicines sold in Wenxui and the like, and miraculous ointments.
According to the method for automatically combing the medicine labels based on the medicine knowledge system, after the medicine knowledge system with the tree structure is updated by crawling out the professional data, all medicines are combed again so as to update the labels of the medicines.
In practical application, the knowledge tree is updated every day according to new information, and then the relationship between the medicine and the knowledge tree is recalculated. Assuming that there are eighty thousand drugs, it will take only about 5 minutes to re-card the label for eighty thousand drugs against the updated knowledge tree.
The invention also provides a device for automatically combing the medicine label based on the medicine knowledge system, wherein the device comprises: the method comprises the steps of constructing a medicine knowledge system module, constructing a medicine knowledge system module of a tree structure, wherein data on leaf nodes at each tail end of the constructed tree structure are disease identifications, and each disease identification corresponds to a symptom label and/or a hidden lemma label;
the combing module is used for acquiring a longest migration result of the annotation of the medicine to be combed by adopting a random migration algorithm model based on the medicine knowledge system and by utilizing a word segmentation tool supporting part of speech recognition, namely the longest migration result corresponds to a specific branch in the tree structure, and the medicine to be combed corresponds to a leaf node at the tail end of the specific branch;
therefore, the symptom label and/or the implicit word element label corresponding to the disease identification on the corresponding tail end leaf node are/is given to the medicine to be combed, so that the automatic label combing work of the medicine is completed.
The device for automatically combing the medicine label based on the medical knowledge system, wherein the module for constructing the medical knowledge system comprises: the sample marking module is used for manually marking a batch of sample data; and
and the training module is used for training and learning the professional data periodically crawled out on the professional site by utilizing the word segmentation tool according to the sample data, so that a medical knowledge system with a tree structure is constructed.
The invention also discloses an electronic device, which comprises: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform any of the above-described methods.
The invention also discloses a storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method of any of the above methods.
The invention at least comprises the following beneficial effects: 1) standardizing the medicine description; 2) the medicine input efficiency is improved; 3) the reliability of the medicine label is improved, so that the subsequent utilization efficiency and effect of the medicine database are obviously improved.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
FIG. 1 is a schematic flow diagram representing a drug label combing system according to the present invention;
FIG. 2 is a schematic view of the use of a drug label combed by the present invention;
FIG. 3 is a schematic diagram of the architecture of the drug knowledge system of the present invention; and
fig. 4 is a schematic diagram of the apparatus for automatically combing the label of the medicine based on the medical knowledge system of the present invention.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
It will be understood that terms such as "having," "including," and "comprising," as used herein, do not preclude the presence or addition of one or more other elements or groups thereof.
Data is organized in an artificial intelligence manner, and a knowledge graph formed based on a graph database is generally needed.
Knowledge maps require a large amount of data to train, the accuracy of the knowledge maps is limited by the quality of the data and the quality of algorithms, and no better application example exists temporarily in the field of medicine with more complex logic relations. The characteristics of medical knowledge are analyzed, the aim of accurate prediction and quick response is achieved, a medicine label carding method aiming at a medical knowledge system is invented, and a medical knowledge forest is built and serves as an accurate and neutral commodity label for all departments of a company to use.
In the medicine commodity library, because the intervention of operators and market personnel is deeper and more frequent, the targets such as each appeal, KPI (Key performance indicator) and the like are inconsistent, the difference of the input medicine comments (medicine specifications) is very large, and the input medicine comments are not necessarily objective and accurate, so that the deviation and error probability of the maintained commodity data are gradually increased. There is a trend of treating a large number of diseases with most of the drugs.
The function utilizes the formed medicine knowledge system to carry out commodity label and commodity atlas depiction again on the commodity, so that the medicine returns to the disease which is mainly treated in the medicine explanation. The upper layer searching, recommending and user portrait can use an accurate and neutral commodity label.
Therefore, as shown in fig. 1, the term tree chain is first designed using a hierarchical structure, the top level is a generalized classification, the disease is refined layer by layer, and finally the disease falls to the leaf node with the finest granularity. Under the disease, there are some terms (some can also be expressed as terms of the disease) corresponding to the symptoms and effective treatment of the disease, so as to form a forest of medicine knowledge with N tree structures.
Then, step 1 is performed: based on the knowledge system, an NLP word segmentation tool such as Ansj and the like which supports the recognition of the part of speech is used in a program for knowledge loading and learning (all term are mounted with the identifier of the final leaf node, and a plurality of leaf nodes can be bound to one term, namely 1: N);
step 2: the name and unique identification of the loaded medicine;
and step 3: obtaining a longest walk result by using an NLP word segmentation tool and a random walk algorithm model to find a specific branch (final leaf node) in a specific knowledge tree in a knowledge forest by using an iterative drug name;
and 4, step 4: the identified leaf nodes can be used for cleaning out the labels of diseases which can be treated by the medicine and detailed symptoms of the medicines;
and 5: curing the automatically identified medicine label for subsequent business use;
in the aspect of the implementation scheme execution efficiency, the single-medicine identification execution efficiency can ensure that the prediction result is output within 50ms, so that the method can be simultaneously applied to real-time online identification prediction and offline identification of the washing commodity map.
A clean commodity map can be automatically cleaned through the name of the medicine (a commodity label data which can automatically filter out operation interference words, description and the like and enable the medicine to return to the real nature) and then the commodity map can enrich the bottom layer of user portrait labels according to the user behavior data, so that possible diseases and symptoms of the user can be accurately sketched. The shopping experience closer to the user is brought by the influence of the commodity recommendation and sequencing model carried out on the label in the user portrait, the shopping path of the user is shortened as far as possible, and the possibility of purchasing by the user is increased. As shown in fig. 2, fig. 2 illustrates a method of use of the present invention. That is, on the basis that the medicine label is obtained, the appropriate medicine can be recommended to the user by combining the behavior data of the user.
Fig. 3 shows a schematic diagram of a medical knowledge map of the invention, for example, separating a cold into phlegm-heat obstructing lungs, which are the end leaf nodes of the knowledge tree. And the lower symptom branch and the cryptic word are labels for the next drugs.
Multiple different drugs may have the same label.
Fig. 4 is a device disclosed by the invention and used for realizing the method of the invention.
Thus, the present invention can realize:
1. algorithm for rapidly identifying finest disease node through term system of medicine knowledge system
2. Method for automatically combing medicine label based on medicine knowledge system
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (11)
1. A method for automatically combing medicine labels based on a medicine knowledge system is characterized by comprising the following steps:
constructing a medical knowledge system of a tree structure, wherein data on leaf nodes at each tail end of the tree structure are disease identifications, and each disease identification corresponds to a symptom label and/or a hidden word element label;
based on the medical knowledge system, a word segmentation tool supporting part of speech recognition is utilized, a longest migration result is obtained by annotating the medicine to be combed by adopting a random migration algorithm model, namely the longest migration result corresponds to a specific branch in the tree structure, and the medicine to be combed corresponds to a leaf node at the tail end of the specific branch;
therefore, the symptom label and/or the implicit word element label corresponding to the disease identification on the corresponding tail end leaf node are/is given to the medicine to be combed, so that the automatic label combing work of the medicine is completed.
2. The method of claim 1, wherein the step of constructing a tree-structured medical knowledge system comprises:
manually marking a batch of sample data; and
according to the sample data, training and learning the professional data regularly crawled on the professional site by utilizing a word segmentation tool, thereby constructing a medical knowledge system with a tree structure.
3. The method according to claim 1 or 2, wherein the word of speech recognition is to define each disease label as different word of speech, and the corresponding word of speech of the drug to be combed is assigned to the end leaf node.
4. The method of claim 3, wherein the disease identification is a unique identifier of the finest granularity of disease.
5. The method of claim 3, wherein the drug to be combed includes a drug name and its unique identification code.
6. The method of claim 3, wherein if the annotation of the drug to be combed does not match the medical knowledge system, the drug is moved to a region to be manually processed for subsequent manual processing.
7. The method of claim 2, wherein after the medical knowledge system of the tree structure is updated by crawling out the professional data, all the medicines are also re-ranked to update the label of each medicine.
8. Device based on automatic drug label of carding of medical knowledge system, its characterized in that includes:
the method comprises the steps of constructing a medicine knowledge system module, constructing a medicine knowledge system module of a tree structure, wherein data on leaf nodes at each tail end of the constructed tree structure are disease identifications, and each disease identification corresponds to a symptom label and/or a hidden lemma label;
the combing module is used for acquiring a longest migration result of the annotation of the medicine to be combed by adopting a random migration algorithm model based on the medicine knowledge system and by utilizing a word segmentation tool supporting part of speech recognition, namely the longest migration result corresponds to a specific branch in the tree structure, and the medicine to be combed corresponds to a leaf node at the tail end of the specific branch;
therefore, the symptom label and/or the implicit word element label corresponding to the disease identification on the corresponding tail end leaf node are/is given to the medicine to be combed, so that the automatic label combing work of the medicine is completed.
9. The apparatus for automatically teasing label of medicine based on medical knowledge system of claim 8, wherein said module for constructing medical knowledge system comprises: the sample marking module is used for manually marking a batch of sample data; and
and the training module is used for training and learning the professional data periodically crawled out on the professional site by utilizing the word segmentation tool according to the sample data, so that a medical knowledge system with a tree structure is constructed.
10. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of any of claims 1-7.
11. Storage medium on which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910963815.2A CN110718305A (en) | 2019-10-11 | 2019-10-11 | Method and device for automatically combing medicine labels based on medicine knowledge system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910963815.2A CN110718305A (en) | 2019-10-11 | 2019-10-11 | Method and device for automatically combing medicine labels based on medicine knowledge system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110718305A true CN110718305A (en) | 2020-01-21 |
Family
ID=69212509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910963815.2A Pending CN110718305A (en) | 2019-10-11 | 2019-10-11 | Method and device for automatically combing medicine labels based on medicine knowledge system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110718305A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049490A (en) * | 2012-12-05 | 2013-04-17 | 北京海量融通软件技术有限公司 | Attribute generation system and generation method among knowledge network nodes |
| CN104615753A (en) * | 2015-02-13 | 2015-05-13 | 杜雨阳 | Method and system of acquiring application relations between drugs and diseases |
| CN105653846A (en) * | 2015-12-25 | 2016-06-08 | 中南大学 | Integrated similarity measurement and bi-directional random walk based pharmaceutical relocation method |
| CN108550401A (en) * | 2018-03-20 | 2018-09-18 | 昆明理工大学 | A kind of illness data correlation method based on Apriori |
| CN109411033A (en) * | 2018-11-05 | 2019-03-01 | 杭州师范大学 | A kind of curative effect of medication screening technique based on complex network |
| US20190156938A1 (en) * | 2017-11-20 | 2019-05-23 | Michael Brunner | System, method and data model for secure prescription management |
| CN110134772A (en) * | 2019-04-18 | 2019-08-16 | 五邑大学 | Medical text Relation extraction method based on pre-training model and fine tuning technology |
| CN110246590A (en) * | 2019-06-17 | 2019-09-17 | 上海米帝信息技术有限公司 | A kind of construction method of blood disease knowledge mapping database |
-
2019
- 2019-10-11 CN CN201910963815.2A patent/CN110718305A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049490A (en) * | 2012-12-05 | 2013-04-17 | 北京海量融通软件技术有限公司 | Attribute generation system and generation method among knowledge network nodes |
| CN104615753A (en) * | 2015-02-13 | 2015-05-13 | 杜雨阳 | Method and system of acquiring application relations between drugs and diseases |
| CN105653846A (en) * | 2015-12-25 | 2016-06-08 | 中南大学 | Integrated similarity measurement and bi-directional random walk based pharmaceutical relocation method |
| US20190156938A1 (en) * | 2017-11-20 | 2019-05-23 | Michael Brunner | System, method and data model for secure prescription management |
| CN108550401A (en) * | 2018-03-20 | 2018-09-18 | 昆明理工大学 | A kind of illness data correlation method based on Apriori |
| CN109411033A (en) * | 2018-11-05 | 2019-03-01 | 杭州师范大学 | A kind of curative effect of medication screening technique based on complex network |
| CN110134772A (en) * | 2019-04-18 | 2019-08-16 | 五邑大学 | Medical text Relation extraction method based on pre-training model and fine tuning technology |
| CN110246590A (en) * | 2019-06-17 | 2019-09-17 | 上海米帝信息技术有限公司 | A kind of construction method of blood disease knowledge mapping database |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107103057B (en) | A kind of resource supplying method and device | |
| CN107391906B (en) | Healthy diet knowledge network construction method based on neural network and map structure | |
| CN107656952B (en) | The modeling method of parallel intelligence case recommended models | |
| CN111401066B (en) | Artificial intelligence-based word classification model training method, word processing method and device | |
| CN104516942B (en) | The automatic merogenesis mark of Concept-driven test | |
| CN110532397B (en) | Question-answering method and device based on artificial intelligence, computer equipment and storage medium | |
| CN109920540A (en) | Construction method, device and the computer equipment of assisting in diagnosis and treatment decision system | |
| Zhao et al. | EMR-based medical knowledge representation and inference via Markov random fields and distributed representation learning | |
| CN107833603A (en) | Electronic medical record document sorting technique, device, electronic equipment and storage medium | |
| CN110069252A (en) | A kind of source code file multi-service label mechanized classification method | |
| CN108630322A (en) | Drug interaction modeling and methods of risk assessment, terminal device and storage medium | |
| CN110929752A (en) | Knowledge-driven and data-driven clustering method and related equipment | |
| CN109542966B (en) | Data fusion method and device, electronic equipment and computer readable medium | |
| CN111048167A (en) | Hierarchical case structuring method and system | |
| Ji et al. | A BILSTM-CRF method to Chinese electronic medical record named entity recognition | |
| CN112232065A (en) | Method and device for mining synonyms | |
| CN113707303A (en) | Method, device, equipment and medium for solving medical problems based on knowledge graph | |
| CN110119991A (en) | Checking method, device and storage medium are compensated in medical treatment based on machine learning | |
| CN112445845A (en) | Model deployment method, device, equipment and storage medium based on big data mining | |
| CN111696661A (en) | Patient clustering model construction method, patient clustering method and related equipment | |
| CN115293161A (en) | Reasonable medicine taking system and method based on natural language processing and medicine knowledge graph | |
| Sharmin et al. | White matter tract segmentation as multiple linear assignment problems | |
| CN111785383A (en) | Data processing method and related equipment | |
| Biseda et al. | Prediction of ICD codes with clinical BERT embeddings and text augmentation with label balancing using MIMIC-III | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200121 |