CN111259635A - Method and system for completing and predicting medical record written text - Google Patents
Method and system for completing and predicting medical record written text Download PDFInfo
- Publication number
- CN111259635A CN111259635A CN202010021681.5A CN202010021681A CN111259635A CN 111259635 A CN111259635 A CN 111259635A CN 202010021681 A CN202010021681 A CN 202010021681A CN 111259635 A CN111259635 A CN 111259635A
- Authority
- CN
- China
- Prior art keywords
- semantic
- medical record
- completing
- predicting
- written
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
Abstract
The invention relates to the technical field of electronic medical records, in particular to a method and a system for completing and predicting a written text of a medical record. The method comprises the following steps: semantic analysis, according to the medical record content written by a doctor at ordinary times, carrying out intelligent word segmentation and sentence segmentation processing and semantic association, carrying out context semantic association on semantic segments with segmented words and sentences, carrying out frequency and weight analysis, triggering recommendation, triggering a recommendation algorithm when a writing disease occurs, recommending the remaining content to be input by combining with the writing context environment, and automatically completing, wherein the recommended semantic segments are displayed at a written cursor. According to the method and the system for completing and predicting the medical record written text, the content written by a doctor can be learned by self, words or sentences needing to be input next step can be predicted intelligently according to the input context environment and the input frequency, and the doctor can automatically complete the rest words or sentences after confirming that the predicted sentences are correct.
Description
Technical Field
The invention relates to the technical field of electronic medical records, in particular to a method and a system for completing and predicting a written text of a medical record.
Background
A doctor usually needs to enter a large number of professional vocabularies and sentences when writing the electronic medical records, mistakes are easily made when the medical records containing a large number of medical professional vocabularies are input, the entering efficiency is very low, and the working efficiency of the doctor is influenced. Most of the existing electronic medical record systems rely on the association function of simple manual input or input methods, or realize the association recommendation function of the systems, but the recommendation of the methods is not very accurate. The intelligent medical vocabulary recommendation system has self-learning capacity, recommendation accuracy is higher and higher through continuous self-learning, and even medical vocabularies rarely used in the profession can be efficiently recorded.
Disclosure of Invention
The invention aims to provide a method and a system for completing and predicting a medical record written text, so as to solve the problems in the background technology.
In order to solve the above technical problems, an object of the present invention is to provide a method for completing and predicting a written text of a medical record, which comprises the following steps:
and S1, performing semantic analysis, and performing intelligent word segmentation and sentence segmentation according to the content of the medical record written by the doctor at ordinary times. The step is not simple Chinese word segmentation processing, but uses intelligent algorithm to process professional medical statement with context semantic segmentation, forms context related semantic segments, and processes numbers, units and the like specially;
s2, performing semantic association, performing context semantic association on the semantic fragments with the segmented words, performing frequency and weight analysis, and storing the processed semantic fragments into a background big data system;
and S3, triggering recommendation, wherein a recommendation algorithm is triggered when a doctor writes a disease, and the rest content to be input is recommended after the doctor analyzes the writing context environment from the background big data system. According to the recommended semantic segments obtained by the intelligent algorithm, sequencing from high to low according to the precision;
s4, automatically completing, wherein the recommended semantic segments are displayed at a cursor written by a doctor, the doctor selects the recommended semantic segments according to actual conditions, medical record contents to be input are automatically completed, if the semantic segments contain numbers, the cursor can be automatically positioned at the position of the numbers, and the complete semantic segments can be input by inputting the numbers and returning;
s5, self-learning, wherein the doctor saves the medical record and repeatedly executes S1-S3, so that the self-learning purpose is achieved, and the more times the doctor uses, the more accurate the recommended semantic path is.
Preferably, in S1, the semantic analysis method includes the following steps:
s1.1, analyzing sentence semantic fragments according to punctuations such as commas, periods and semicolons;
s1.2, matching and analyzing common semantic fragments by using medical common semantic fragments with built-in codes;
s1.3, analyzing by using a Natural Language Processing (NLP) technology to obtain natural semantic fragments;
s1.4, analyzing the digital characters to obtain digital semantic fragments;
s1.5, analyzing the unit character string to obtain a unit type semantic fragment.
Preferably, in S2, the semantic association method includes the following steps:
s2.1, using the semantic segments obtained in the S1, combining context contents in medical records, and sequentially stringing the semantic segments to obtain a directed graph, which is specifically shown in FIG. 4;
s2.2, if a digital type is encountered, replacing the digital type with "? ", so that the weight impact caused by the number can be erased;
s2.3, storing the digraphs obtained in the previous step in a graph database, so that the graph database contains a plurality of digraphs;
s2.4, in the process of storage, if the graph database has the semantic segment nodes which are the same as those in the graph, carrying out comparison analysis on the existing related directed graphs in the database, then carrying out merging operation to obtain a new directed graph, and giving association relation frequency weight; for example "? Cough "and" weakness "nodes, for example as shown in FIG. 5, and a new directed graph as shown in FIG. 6;
s2.5, adding the relevant information of the department user to attribute relationship weight to update frequency information;
and S2.6, finally updating the latest directed graph to a graph database for storage.
Preferably, in S2.5, in the step of adding information on the attribute relationship weight to the information on the update frequency of the department user, if a unit type is encountered, the analysis is performed by a built-in common unit, for example, the body temperature.
Preferably, in S3, the method for triggering recommendation includes the following steps:
s3.1, performing Natural Language Processing (NLP) technology according to the sentences written by the doctor to obtain keywords;
s3.2, searching a related directed graph in the graph database by using the keywords;
s3.3, specifying the nodes of the depth-oriented traversal graph to obtain a plurality of statement paths;
for example, a doctor writes two words "palpitation" to get a path:
① palpitation- > chest distress- >;
② palpitation- > chest distress- >;
③ palpitation- > chest distress- >;
④ palpitation- > chest distress;
⑤...；
and S3.4, sequencing the paths according to the frequency weight and the attribute weight to obtain a recommended semantic path list.
Preferably, in S4, the method for automatically completing includes the steps of:
s4.1, displaying in an interface according to the recommended semantic path list obtained in the S3.4, wherein the semantic path with the largest weight is displayed at the top of the list;
s4.2, the doctor selects a desired semantic path and directly fills the semantic path into a medical record text;
and S4.3, if the selected recommended semantic segment contains numbers, popping up a number entry box, entering the actually required numbers, and determining to insert the numbers into a medical record text after carriage return.
Another object of the present invention is to provide a system for completing and predicting a written text of a medical record, comprising:
a semantic analysis module: the intelligent word segmentation and sentence segmentation device is used for carrying out intelligent word segmentation and sentence segmentation according to the medical record content written by a doctor at ordinary times;
a semantic association module: the semantic association system is used for performing context semantic association on the semantic segments with the segmented words and the segmented sentences, and performing frequency and weight analysis;
the trigger recommendation module: the system is used for analyzing and recommending contents to be input from a background big data system;
automatic completion module: the method is used for automatically completing the medical record content required to be input.
It is a further object of the present invention to provide an apparatus for completing and predicting a written text of a medical record, comprising a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method for completing and predicting a written text of a medical record as described in any of the above when executing the computer program.
It is a fourth object of the present invention to provide a computer readable storage medium, wherein at least one program is stored in the storage medium, and the at least one program is executed by the processor to implement the steps of the method for completing and predicting the written text of a medical record as described in any of the above.
Compared with the prior art, the invention has the beneficial effects that:
1. in the method and the system for completing and predicting the medical record written text, a semantic segment analysis method is adopted, and semantic segments are analyzed according to punctuation marks, common sentences, numbers and unit multi-dimensional attributes.
2. In the method and the system for completing and predicting the medical record writing text, a self-learning method is adopted, and the system can continuously update the nodes and the weights of the recommended semantic segments according to the medical record written and stored by a doctor, so that the recommendation accuracy is improved, the self-learning purpose is achieved, and a large amount of pre-configuration and learning work is not needed before the system is used.
3. In the method and the system for completing and predicting the medical record writing text, numerical type input processing is carried out, digital characters are analyzed, weight influence caused by the digital characters is erased, if the selected recommended semantic segment contains numbers, a number input box can be popped up, actually needed numbers are input, and the numbers can be inserted into the medical record text after carriage return determination.
4. In the method and the system for completing and predicting the medical record written text, medical unit symbols are commonly used for processing, most of unit symbols used in medical science are arranged in the medical unit symbols, and the unit symbols written by doctors can be displayed in a recommendation list after being written with numbers.
5. In the method and the system for completing and predicting the medical record written text, a directed graph data model uses a directed graph as a basic model of the method, a directed graph network of a graph and a semantic segment is constructed, and a graph database is used for storing the directed graph network.
Drawings
FIG. 1 is an overall flow diagram of the present invention;
FIG. 2 is a flow chart of a method of semantic analysis according to the present invention;
FIG. 3 is a flow chart of a method of semantic association of the present invention;
FIG. 4 is an exemplary diagram of a directed graph with semantic segments concatenated sequentially in accordance with the present invention;
fig. 5 is "? An example graph of two nodes, cough "and" weakness ";
FIG. 6 is an exemplary diagram of obtaining a new directed graph according to the present invention;
FIG. 7 is a flowchart of a method for triggering a recommendation in accordance with the present invention;
FIG. 8 is a flow chart of a method of automatic completion of the present invention;
FIG. 9 is a flow chart of a method for populating medical records text in accordance with the present invention;
FIG. 10 is a schematic diagram of an apparatus for completing and predicting written text of medical records according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-10, the present invention provides a technical solution:
the invention provides a method for completing and predicting a medical record written text, which comprises the following steps:
s1, semantic analysis, namely performing intelligent word segmentation and sentence segmentation according to the medical record content written by a doctor at ordinary times, wherein the step is not simply performing Chinese language word segmentation, but performing context semantic segmentation on a professional medical statement by using an intelligent algorithm to form context-related semantic segments, and performing special processing on numbers, units and the like;
s2, performing semantic association, performing context semantic association on the semantic fragments with the segmented words, performing frequency and weight analysis, and storing the processed semantic fragments into a background big data system;
and S3, triggering recommendation, wherein a recommendation algorithm is triggered when a doctor writes a disease, and the rest content to be input is recommended after the doctor analyzes the writing context environment from the background big data system. According to the recommended semantic segments obtained by the intelligent algorithm, sequencing from high to low according to the precision;
s4, automatically completing, wherein the recommended semantic segments are displayed at a cursor written by a doctor, the doctor selects the recommended semantic segments according to actual conditions, medical record contents to be input are automatically completed, if the semantic segments contain numbers, the cursor can be automatically positioned at the position of the numbers, and the complete semantic segments can be input by inputting the numbers and returning;
s5, self-learning, wherein the doctor saves the medical record and repeatedly executes S1-S3, so that the self-learning purpose is achieved, and the more times the doctor uses, the more accurate the recommended semantic path is.
In this embodiment, in S1, the semantic analysis method includes the following steps:
s1.1, analyzing sentence semantic fragments according to punctuations such as commas, periods and semicolons;
s1.2, matching and analyzing common semantic fragments by using medical common semantic fragments with built-in codes;
s1.3, analyzing by using a Natural Language Processing (NLP) technology to obtain natural semantic fragments;
s1.4, analyzing the digital characters to obtain digital semantic fragments;
s1.5, analyzing the unit character string to obtain a unit type semantic fragment.
Further, in S2, the semantic association method includes the following steps:
s2.1, using the semantic segments obtained in the S1, combining context contents in medical records, and sequentially stringing the semantic segments to obtain a directed graph, which is specifically shown in FIG. 4;
s2.2, if a digital type is encountered, replacing the digital type with "? ", so that the weight impact caused by the number can be erased;
s2.3, storing the digraphs obtained in the previous step in a graph database, so that the graph database contains a plurality of digraphs;
s2.4, in the process of storage, if the graph database has the semantic segment nodes which are the same as those in the graph, carrying out comparison analysis on the existing related directed graphs in the database, then carrying out merging operation to obtain a new directed graph, and giving association relation frequency weight; for example "? Cough "and" weakness "nodes, for example as shown in FIG. 5, and a new directed graph as shown in FIG. 6;
s2.5, adding the relevant information of the department user to attribute relationship weight to update frequency information;
and S2.6, finally updating the latest directed graph to a graph database for storage.
Specifically, in S2.5, in the step of adding information on the attribute relationship weight assigned to the department user to update the frequency information, if a unit type is encountered, analysis is performed by a built-in common unit, such as body temperature.
It should be noted that in S3, the method for triggering recommendation includes the following steps:
s3.1, performing Natural Language Processing (NLP) technology according to the sentences written by the doctor to obtain keywords;
s3.2, searching a related directed graph in the graph database by using the keywords;
s3.3, specifying the nodes of the depth-oriented traversal graph to obtain a plurality of statement paths;
for example, a doctor writes two words "palpitation" to get a path:
① palpitation- > chest distress- >;
② palpitation- > chest distress- >;
③ palpitation- > chest distress- >;
④ palpitation- > chest distress;
⑤...；
and S3.4, sequencing the paths according to the frequency weight and the attribute weight to obtain a recommended semantic path list.
In S4, the method for automatic completion includes the steps of:
s4.1, displaying in an interface according to the recommended semantic path list obtained in the S3.4, wherein the semantic path with the largest weight is displayed at the top of the list;
s4.2, the doctor selects a desired semantic path and directly fills the semantic path into a medical record text;
and S4.3, if the selected recommended semantic segment contains numbers, popping up a number entry box, entering the actually required numbers, and determining to insert the numbers into a medical record text after carriage return.
Another object of the present invention is to provide a system for completing and predicting a written text of a medical record, comprising:
a semantic analysis module: the intelligent word segmentation and sentence segmentation device is used for carrying out intelligent word segmentation and sentence segmentation according to the medical record content written by a doctor at ordinary times;
a semantic association module: the semantic association system is used for performing context semantic association on the semantic segments with the segmented words and the segmented sentences, and performing frequency and weight analysis;
the trigger recommendation module: the system is used for analyzing and recommending contents to be input from a background big data system;
automatic completion module: the method is used for automatically completing the medical record content required to be input.
It should be noted that the functions of the semantic analysis module, the semantic association module, the trigger recommendation module, and the automatic completion module are specifically described in the description of the method portion corresponding to each module, and are not repeated here.
Referring to fig. 10, a schematic diagram of an apparatus for completing and predicting medical record written text according to an embodiment of the present invention is shown, the apparatus including a processor, a memory and a bus.
The processor comprises one or more processing cores, the processor is connected with the processor through a bus, the memory is used for storing program instructions, and the processor executes the program instructions in the memory to realize the method for completing and predicting the medical record writing text.
Alternatively, the memory may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The present invention further provides a computer readable storage medium, wherein at least one program is stored in the storage medium, and the at least one program is executed by the processor to implement the steps of the method for completing and predicting the written text of the medical record.
Optionally, the present invention also provides a computer program product containing instructions which, when run on a computer, cause the computer to perform the steps of the above-described methods for completing and predicting medical record written text.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by hardware related to instructions of a program, where the program may be stored in a computer readable storage medium, and the above mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A method for completing and predicting written text of a medical record comprises the following steps:
s1, performing semantic analysis, and performing intelligent word segmentation and sentence segmentation according to the content of the medical record written by the doctor at ordinary times;
s2, performing semantic association, performing context semantic association on the semantic fragments with the segmented words, performing frequency and weight analysis, and storing the processed semantic fragments into a background big data system;
s3, triggering recommendation, wherein a recommendation algorithm is triggered when the writing diseases are generated, and the content which needs to be input is recommended after the writing diseases are analyzed from a background big data system in combination with a writing context environment;
s4, automatically completing, wherein the recommended semantic segments are displayed at a written cursor, the recommended semantic segments are selected, the rest medical record content needing to be input is automatically completed, if the semantic segments contain numbers, the cursor can be automatically positioned at the position of the numbers, and the complete semantic segments can be input by inputting the numbers and returning;
and S5, self-learning, wherein the medical record is stored and is repeatedly executed in steps S1-S3, so that the purpose of self-learning is achieved.
2. The method of completing and predicting medical record written text according to claim 1, wherein: in S1, the semantic analysis method includes the following steps:
s1.1, analyzing sentence semantic fragments according to punctuations such as commas, periods and semicolons;
s1.2, matching and analyzing common semantic fragments by using medical common semantic fragments with built-in codes;
s1.3, analyzing by using a Natural Language Processing (NLP) technology to obtain natural semantic fragments;
s1.4, analyzing the digital characters to obtain digital semantic fragments;
s1.5, analyzing the unit character string to obtain a unit type semantic fragment.
3. The method of completing and predicting medical record written text according to claim 1, wherein: in S2, the semantic association method includes the following steps:
s2.1, using the semantic segments obtained in the S1, combining context content in medical records, and sequentially concatenating the semantic segments to obtain a directed graph;
s2.2, if a digital type is encountered, replacing the digital type with "? ";
s2.3, storing the directed graph obtained in the previous step in a graph database;
s2.4, in the process of storage, if the graph database has semantic segment nodes which are the same as those in the graph, carrying out comparison analysis on the existing related directed graphs in the database, then carrying out merging operation to obtain a new directed graph, and giving association relation frequency weight;
s2.5, adding the relevant information of the department user to attribute relationship weight to update frequency information;
and S2.6, finally updating the new directed graph to a graph database for storage.
4. The method of completing and predicting medical record written text according to claim 3, wherein: in S2.5, in the step of adding the attribute relationship weighting update frequency information to the information related to the department user, if a unit type is encountered, analysis is performed by a built-in unit.
5. The method of completing and predicting medical record written text according to claim 1, wherein: in S3, the method for triggering recommendation includes the following steps:
s3.1, performing Natural Language Processing (NLP) technology according to the written sentences to obtain keywords;
s3.2, searching a related directed graph in the graph database by using the keywords;
s3.3, specifying the nodes of the depth-oriented traversal graph to obtain a plurality of statement paths;
and S3.4, sequencing the paths according to the frequency weight and the attribute weight to obtain a recommended semantic path list.
6. The method of completing and predicting medical record written text according to claim 5, wherein: in S4, the method for automatically completing includes the following steps:
s4.1, displaying in an interface according to the recommended semantic path list obtained in the S3.4, wherein the semantic path with the largest weight is displayed at the top of the list;
s4.2, selecting a desired semantic path, and directly filling the semantic path into a medical record text;
and S4.3, if the selected recommended semantic segment contains numbers, popping up a number entry box, and entering the actually required numbers.
7. A system for completing and predicting written text of a medical record, comprising:
a semantic analysis module: the intelligent word segmentation and sentence segmentation device is used for carrying out intelligent word segmentation and sentence segmentation according to the medical record content written by a doctor at ordinary times;
a semantic association module: the semantic association system is used for performing context semantic association on the semantic segments with the segmented words and the segmented sentences, and performing frequency and weight analysis;
the trigger recommendation module: the system is used for analyzing and recommending contents to be input from a background big data system;
automatic completion module: the method is used for automatically completing the medical record content required to be input.
8. An apparatus for completing and predicting written text of a medical record, comprising: comprising a processor, a memory and a computer program stored in and run on said memory, said processor implementing the steps of the method of filling and predicting written text of medical records according to any of claims 1-6 when executing said computer program.
9. A computer-readable storage medium, wherein at least one program is stored in the storage medium, and the at least one program is executed by a processor to implement the steps of the method for completing and predicting medical record written text according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010021681.5A CN111259635A (en) | 2020-01-09 | 2020-01-09 | Method and system for completing and predicting medical record written text |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010021681.5A CN111259635A (en) | 2020-01-09 | 2020-01-09 | Method and system for completing and predicting medical record written text |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111259635A true CN111259635A (en) | 2020-06-09 |
Family
ID=70950319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010021681.5A Pending CN111259635A (en) | 2020-01-09 | 2020-01-09 | Method and system for completing and predicting medical record written text |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111259635A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417130A (en) * | 2020-11-19 | 2021-02-26 | 贝壳技术有限公司 | Word screening method and device, computer readable storage medium and electronic equipment |
| CN112486336A (en) * | 2020-11-09 | 2021-03-12 | 深圳市鹰硕教育服务有限公司 | Intelligent pen data processing method and device based on cloud service platform and electronic equipment |
| CN112883712A (en) * | 2021-02-05 | 2021-06-01 | 中国人民解放军南部战区总医院 | Intelligent input method and device for electronic medical record |
| CN114743621A (en) * | 2022-03-21 | 2022-07-12 | 北京左医科技有限公司 | Medical record input prediction method, medical record input prediction device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| CN105468900A (en) * | 2015-11-20 | 2016-04-06 | 邹远强 | Intelligent medical record input platform based on knowledge base |
| KR20160120456A (en) * | 2015-04-08 | 2016-10-18 | 김대진 | patient evaluation chart prior estimation system for care hospital linked hospital information system and the method |
| CN109542247A (en) * | 2018-11-14 | 2019-03-29 | 腾讯科技（深圳）有限公司 | Clause recommended method and device, electronic equipment, storage medium |
-
2020
- 2020-01-09 CN CN202010021681.5A patent/CN111259635A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| KR20160120456A (en) * | 2015-04-08 | 2016-10-18 | 김대진 | patient evaluation chart prior estimation system for care hospital linked hospital information system and the method |
| CN105468900A (en) * | 2015-11-20 | 2016-04-06 | 邹远强 | Intelligent medical record input platform based on knowledge base |
| CN109542247A (en) * | 2018-11-14 | 2019-03-29 | 腾讯科技（深圳）有限公司 | Clause recommended method and device, electronic equipment, storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112486336A (en) * | 2020-11-09 | 2021-03-12 | 深圳市鹰硕教育服务有限公司 | Intelligent pen data processing method and device based on cloud service platform and electronic equipment |
| CN112417130A (en) * | 2020-11-19 | 2021-02-26 | 贝壳技术有限公司 | Word screening method and device, computer readable storage medium and electronic equipment |
| CN112417130B (en) * | 2020-11-19 | 2023-06-16 | 贝壳技术有限公司 | Word screening method, device, computer readable storage medium and electronic equipment |
| CN112883712A (en) * | 2021-02-05 | 2021-06-01 | 中国人民解放军南部战区总医院 | Intelligent input method and device for electronic medical record |
| CN114743621A (en) * | 2022-03-21 | 2022-07-12 | 北京左医科技有限公司 | Medical record input prediction method, medical record input prediction device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259635A (en) | Method and system for completing and predicting medical record written text | |
| KR100650427B1 (en) | Integrated development tool for building a natural language understanding application | |
| US11138005B2 (en) | Methods and systems for automatically generating documentation for software | |
| US9098479B2 (en) | Methods and apparatus for improved navigation among controlled terms in one or more user documents | |
| US20080168341A1 (en) | Digital spreadsheet formula automation | |
| US8386238B2 (en) | Systems and methods for evaluating a sequence of characters | |
| CN109858010A (en) | Field new word identification method, device, computer equipment and storage medium | |
| JP2016091078A (en) | Generation apparatus, generation method, and program | |
| US9754083B2 (en) | Automatic creation of clinical study reports | |
| JP2002215617A (en) | Method for attaching part of speech tag | |
| US20230076658A1 (en) | Method, apparatus, computer device and storage medium for decoding speech data | |
| JP2016099741A (en) | Information extraction support apparatus, method and program | |
| CN109522396B (en) | Knowledge processing method and system for national defense science and technology field | |
| US11568150B2 (en) | Methods and apparatus to improve disambiguation and interpretation in automated text analysis using transducers applied on a structured language space | |
| CN111984845A (en) | Website wrongly-written character recognition method and system | |
| JP2005181928A (en) | System and method for machine learning, and computer program | |
| WO2019085118A1 (en) | Topic model-based associated word analysis method, and electronic apparatus and storage medium | |
| CN111368547A (en) | Entity identification method, device, equipment and storage medium based on semantic analysis | |
| KR100353549B1 (en) | Method and system for learning a language | |
| US20210318949A1 (en) | Method for checking file data, computer device and readable storage medium | |
| JP6181890B2 (en) | Literature analysis apparatus, literature analysis method and program | |
| CN117494806B (en) | Relation extraction method, system and medium based on knowledge graph and large language model | |
| WO2023204724A1 (en) | Method for analyzing a legal document | |
| CN113628756A (en) | Method, device and system for extracting symptoms and causes of diseases from medical texts | |
| CN114398853A (en) | Extraction method and device of document numerical index based on machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 361000 unit 404, No. 24, guanri Road, phase II, software park, Xiamen, Fujian Applicant after: XIAMEN ZHIYE SOFTWARE ENGINEERING CO.,LTD. Address before: 361000 No.24 guanri Road, Siming District, Xiamen City, Fujian Province Applicant before: XIAMEN ZHIYE SOFTWARE ENGINEERING CO.,LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200609 |