CN108182207A - The intelligent coding method and system of Chinese surgical procedure based on participle network - Google Patents
The intelligent coding method and system of Chinese surgical procedure based on participle network Download PDFInfo
- Publication number
- CN108182207A CN108182207A CN201711350705.6A CN201711350705A CN108182207A CN 108182207 A CN108182207 A CN 108182207A CN 201711350705 A CN201711350705 A CN 201711350705A CN 108182207 A CN108182207 A CN 108182207A
- Authority
- CN
- China
- Prior art keywords
- word
- surgical procedure
- icd
- network
- information
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2452—Query translation
- G06F16/24522—Translation of natural language queries to structured queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The intelligent coding method and system of Chinese surgical procedure provided by the invention based on participle network, include the following steps：Step 1, Chinese surgical procedure title is obtained；Step 2, Chinese surgical procedure title with Dynamic expansion participle network is adapted to, key message is extracted from Chinese surgical procedure title and the key message of extraction is formed into crucial phrase；Step 3, crucial phrase is adapted to phrase Code Mapping Tables and export not matched result or ICD coding.Compared with prior art, beneficial effects of the present invention are as follows：1st, the standard code of medical medical record data under isomerization conditions has been unified, and then the administrative decision for quality of medical care and medical insurance fund provides solid data normalization support, pushes the gradually standardization and standardization of the practice of China's clinical medicine.2nd, by this method, ICD coding works can be automatically performed, without manually participating in, have many advantages, such as that coding rate is high, at low cost, accuracy is high.3rd, unified standard ICD codings.
Description
Technical field
The present invention relates to managing medical information technical fields, and in particular, to a kind of Chinese operation based on participle network
The intelligent coding method and system of operation.
Background technology
International Classification of Diseases (International Classification of Diseases, ICD) is that WHO is formulated
International uniform classification of diseases method, it is according to characteristics such as the cause of disease of disease, pathology, clinical manifestation and anatomical positions, by disease
Disease classifies, and becomes an orderly combination, and the system represented with the method for coding.ICD causes disease name
Standardization formats.This is the application foundation of the clinic information systems such as medical information, hospital information management.Chinese medical art
The Standardization Construction of language lags behind the standardization of western language medical terminology significantly, and the medical terminology standardized process in China is from a large amount of
Introduce and translate what international standard started.ICD-10 Chinese editions defend planning commission by country and are appointed as clinical diagnosis, disease class term
The universal standard.
However, due to disease wide coverage, type is various, and name is sufficiently complex.It reports in disease, Medical Record Statistics management
With medical insurance reimbursement etc. in work, to disease code use, there are larger difference, the states of each leisure WHO offers for domestic each medical institutions
Localization modification has been carried out on border standard ICD codings, cause to encode it is multi-source heterogeneous, there is missing and be difficult to the problem of unified.Cause
This needs to build a kind of intelligent coding method of Chinese surgical procedure information, can be automatically by the Chinese hand of the difference of different medical mechanism
Art operation information carries out natural language processing, is standardized as the ICD codings of the universal standard, and then be quality of medical care and medical insurance fund
Administrative decision solid data normalization support is provided so that ICD disease informations obtain the shared of maximum magnitude, can reflect
National health situation and medical research and the tool and data of teaching.
As with the immediate prior art scheme of the present invention,《A kind of automatic coding of Chinese surgical procedure information
And system》It is a kind of easy automatic volume of Chinese surgical procedure information protected interconnected medical Information technology (Beijing) Co., Ltd and provided
Code method and system.This method is based on standard terminology library and expands terminology bank, searches the standard art to match with title to be encoded
Language expands term, and by the standard terminology of successful match or expands the coding of term, is determined as the coding of title to be encoded；Its
In, standard terminology is each disease term included in the ICD versions to be referred to, and expanding term is had together with standard terminology
The word of adopted relationship or the word with relation of genus and species；Expand term and the standard terminology pair with synonymy or relation of genus and species
The coding answered is consistent.This method is mainly the relation of genus and species studied between term, and our technology is to build first point
Word network, the participle network based on structure are adapted to the surgical procedure title of input, extract and close from surgical procedure title
Key information obtains position, art formula, approach, the cause of disease, purpose, other the six keyword combinations partly formed, then matches advance structure
" word combination and the Code Mapping Tables " built by accurately matching or fuzzy matching, obtain the corresponding final ICD of Chinese and compile
Code；The subordinate relation being not relevant between these terms concentrates on merely the processing to natural language.
Application No. is：It is 201510496500.3 entitled：A kind of automatic coding of Chinese surgical procedure information and it is
System is mainly based upon standard terminology library and expands terminology bank, searches the standard terminology to match with title to be encoded or expands art
Language, and by the standard terminology of successful match or expand the coding of term, it is determined as the coding of title to be encoded；Wherein, standard art
Language is each disease term included in the ICD versions to be referred to, and it is being commonly called as of standard terminology, nickname or breviary to expand term
The subclass disease term or newly generated disease term of language or standard terminology.
Above patent document is mainly to study the relation of genus and species of term, when the expansion term is any one of standard
When the subclass disease term of term or the newly generated disease term, by with the immediate mark of the relation of genus and species of the expansion term
The coding of quasi- term assigns the expansion term.And our method is to build participle network first, the participle based on structure
Network is adapted to the surgical procedure title of input, and key message is extracted from surgical procedure title, obtain position, art formula,
The keyword combination that approach, the cause of disease, purpose, other six parts form, then match " word combination and the coding mapping built in advance
Table " by accurately matching or fuzzy matching, obtains the corresponding final ICD codings of Chinese；Be not relevant for these terms it
Between subordinate relation, concentrate on the processing to natural language merely.
Application No. is：It is 201610571791.2 entitled：Diagnosis associated packets method based on intellectual coded adaptation and it is
System, the main purpose of adaptation are will to encode the international standard diagnosis coding (ICD-10- that is unified for case grouping system and can identify
CM) and surgical procedure encodes (ICD-10-PCS), improves the adaptability of case grouping system；And the width of our technology adaptation
More extensively, depth is deeper, and the ICD that arbitrary Chinese diagnosis name and surgical procedure title can be respectively fitted to particular version is diagnosed
Coding and ICD surgical procedures coding, to solve multi-source heterogeneous hospital's coding, missing and standard disunity, are conducive to information for hospital
The construction of change.In addition, the method for the two adaptation also has very big difference.Above patent document need to need when being adapted to by " block "
By the former diagnosis coding of input, and our technology does not need to be adapted to by original coding, based entirely on operation
Key message is extracted, then accurately matched or fuzzy matching after action name participle.The technical program is equally above-mentioned special
Basis and precondition of the sharp document in application.In addition, our technology can be applied to the coding of case of hospital section to code
The ICD versions used in the past, are such as corresponded to newest ICD versions, can improve the working efficiency of medical record coder by work.
Application number：201510831116.4 a kind of entitled intelligent diagnostics Operation encoding search method, above patent document
Diagnosis input by user or operation names are mainly based upon in preset entire diagnosis or Operation encoding character set, retrieval
Go out the highest code set of match strength, technological invention lays particular emphasis on matching journey of the searched targets character string in presetting database
Degree.The method of the two does not have similitude, and above-mentioned patent is not adapted to, and is realized based on retrieval；And our technology is head
Participle network is first built, and this network can be enriched constantly and perfect, to increase the range of adaptation, as long as input is appointed
The Chinese of meaning is encoded with regard to that can obtain the immediate ICD in indicated release.
Invention content
For the defects in the prior art, the object of the present invention is to provide a kind of Chinese operation behaviour based on participle network
The intelligent coding method and system of work.
In order to solve the above technical problems, the intelligently encoding side of the Chinese surgical procedure provided by the invention based on participle network
Method includes the following steps：
Step 1, Chinese surgical procedure title is obtained；
Step 2, Chinese surgical procedure title is adapted to Dynamic expansion participle network, from Chinese surgical procedure title
The key message of extraction is simultaneously formed crucial phrase by middle extraction key message；
Step 3, crucial phrase is adapted to phrase Code Mapping Tables and export not matched result or ICD coding.
Preferably, key message include location information, art formula information, approach information, cause of disease information, purpose information and other
Information.
Preferably, step 2 includes：
Key message is segmented into the position dictionary in network according to Dynamic expansion and matches location information from long to short, and combine
The priority of each location information, obtains position word in the word order table of position；
Key message is segmented into the art formula dictionary in network according to Dynamic expansion and matches art formula information from long to short, and combine
The priority of each art formula information, obtains art formula word in art formula word order table；
Key message is segmented into the approach dictionary in network according to Dynamic expansion and matches approach information from long to short, and combine
The priority of each approach information, obtains approach word in approach word order table；
Key message is segmented into the cause of disease dictionary in network according to Dynamic expansion and matches cause of disease information from long to short, and combine
The priority of each cause of disease information, obtains cause of disease word in cause of disease word order table；
Key message is segmented into the purpose dictionary in network according to Dynamic expansion and matches purpose information from long to short, and combine
The priority of each purpose information, obtains purpose word in purpose word order table；
Key message is segmented into other dictionaries in network according to Dynamic expansion and matches other information from long to short, and combine
The priority of each other information, obtains other words in other word order tables；
Crucial phrase includes at least position word, art formula word, approach word, cause of disease word, purpose word and other words.
Preferably, the adaptation in step 3 includes：
Step 3.1, the first order is adapted to：Accurate adaptation is carried out to crucial phrase and phrase Code Mapping Tables；
If crucial phrase is matched with phrase Code Mapping Tables, ICD codings corresponding with crucial phrase, intelligently encoding are exported
Method terminates；
If crucial phrase is mismatched with phrase Code Mapping Tables, 3.2 are entered step；
Step 3.2, the second level is adapted to：Fuzzy be adapted to is carried out with phrase Code Mapping Tables to crucial phrase.
Preferably, step 3.2, second level adaptation includes：
Step 3.2.1 searches the path for including most matching keywords in Dynamic expansion participle network；
Step 3.2.2 calculates remaining keyword and the key message of the Chinese surgical procedure title of input in path
The number matched chooses coupling path；Wherein
Remaining keyword is non-matched keyword in crucial phrase.
Preferably, step 3.2.1 includes：
Step 3.2.1.1 is filtered out from Dynamic expansion participle network and is contained all the first of matched position word
Screen path；If it is exported not matched as a result, intelligent coding method terminates without position word in crucial phrase；
Step 3.2.1.2, from first screening path in filter out contain matched art formula word, approach word, cause of disease word,
Second screening path of purpose word and other words；
Path is screens according to art formula word, approach word, cause of disease word, purpose word and other words in the second all screening paths
Include the most path of matching keywords.
Preferably, in step 3.2.2, when the number of matched keyword is identical, unmatched keyword number is chosen
Minimum path passes through phrase Code Mapping Tables and obtains the corresponding ICD of coupling path and encode and export this as coupling path
ICD is encoded.
Preferably, the establishment of Dynamic expansion participle network includes the following steps：
The ICD of different regions or different editions is encoded and corresponding Chinese surgical procedure name is referred to as training set input；Its
When if identical Chinese surgical procedure title corresponds to different ICD codings in, retain the smaller ICD codings of initial；If present bit
Letter is identical, then compares the letter of next bit, until last letter；
Symptom information, location information, cause of disease information and the corresponding keyword of other information are extracted from diagnosis name, respectively
Build position dictionary, art formula dictionary, approach dictionary, cause of disease dictionary, purpose dictionary and other dictionaries；
According to symptom word, position word, cause of disease word and other words length from long to short, respectively build position word order table, art
Formula word order table, approach word order table, cause of disease word order table, purpose word order table and other word order tables, generation sequence forest；Wherein
The longer sequence of length is more forward, and priority is higher.
Preferably, the establishment of phrase Code Mapping Tables includes the following steps：
The determining ICD versions to be referred to；
It extracts with determining Chinese surgical procedure title is identical in the ICD versions to be referred to record in training set, with true
ICD codings in the fixed ICD versions to be referred to replace the ICD codings in training set；
Record different from surgical procedure title Chinese in the determining ICD versions to be referred in training set is extracted, it will be true
The Chinese generated Dynamic expansion participle network of surgical procedure name-matches in the fixed ICD versions to be referred to, with most like
The ICD codings of the determining ICD colophons to be referred to are as mapping code；Wherein
The ICD of most like indicated release record is encoded to segments the matched keyword of network corresponding part with Dynamic expansion
Keyword number minimum record is mismatched when the largest number of records or identical matching keywords number.
A kind of system of the intelligent coding method of the Chinese surgical procedure based on participle network, including being stored with computer journey
The computer readable storage medium of sequence realizes the Chinese operation based on participle network when the computer program is executed by processor
The step of intelligent coding method of operation.
Compared with prior art, beneficial effects of the present invention are as follows：
1st, the standard code of medical medical record data under isomerization conditions has been unified, and then has been quality of medical care and medical insurance fund
Administrative decision provides solid data normalization support, pushes the gradually standardization and standardization of the practice of China's clinical medicine.
2nd, by this method, ICD coding works can be automatically performed, without manually participating in, there is coding rate height, cost
Low, the advantages that accuracy is high.
3rd, unified standard ICD codings can reflect national health disease condition and medical research and the tool of teaching
And data.
Description of the drawings
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature mesh of the invention
And advantage will become more apparent upon.
Fig. 1 is that the present invention is based on the intelligent coding method flow charts of the Chinese surgical procedure of participle network；
Fig. 2 is that the present invention is based on the accurate matching of the intelligent coding method of the Chinese surgical procedure of participle network and fuzzy
With flow chart；
Fig. 3 is point of the structure Dynamic expansion the present invention is based on the intelligent coding method of the Chinese surgical procedure of participle network
Word network and position word, art formula word, approach word, cause of disease word, purpose word and other word order table flow charts；
Fig. 4 is that the present invention is based on the structure word combinations of the intelligent coding method of the Chinese surgical procedure of participle network and coding
The first step flow chart of mapping table；
Fig. 5 is that the present invention is based on the structure word combinations of the intelligent coding method of the Chinese surgical procedure of participle network and coding
The second step flow chart of mapping table；
Fig. 6 is that the present invention is based on the structure word combinations of the intelligent coding method of the Chinese surgical procedure of participle network and coding
The third step flow chart of mapping table；
Fig. 7 is that the present invention is based on the structure word combinations of the intelligent coding method of the Chinese surgical procedure of participle network and coding
4th step flow chart of mapping table.
Specific embodiment
With reference to specific embodiment, the present invention is described in detail.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill to this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection domain.
According to a kind of intelligent coding method of the Chinese surgical procedure based on participle network provided by the invention, including as follows
Step：
Step 1：The Chinese surgical procedure title of input；
Step 2：Participle network based on the Dynamic expansion pre-established is adapted to, from Chinese surgical procedure title according to
Secondary extraction key message obtains location information, art formula information, approach information, cause of disease information, purpose information, other information six
The keyword combination of part composition, when adaptation follow participle from long to short, the principle of priority from high to low.
The step 2 further comprises the steps 2.1~2.6 (as shown in Figure 1)：
Step 2.1：After the Chinese surgical procedure title of input, according to the matching part from long to short of the position dictionary in participle network
Position, and the priority at each position in the position word order table pre-established is combined, obtain final position word；If draw during without matching
Enter the position synonym table pre-established to continue to match, obtain final position word；If it is still exported " not matching " without matching.
Step 2.2：According to the art formula dictionary in participle network art formula is matched from long to short, and combine the art formula pre-established
The priority of each art formula in word order table, obtains final art formula word；If the art formula synonym pre-established is introduced during without matching
Table continues to match, and obtains final art formula word.
Step 2.3：According to the approach dictionary in participle network approach is matched from long to short, and combine the approach pre-established
The priority of each approach in word order table obtains final approach word；If the approach synonym pre-established is introduced during without matching
Table continues to match, and obtains final approach word.
Step 2.4：According to the cause of disease dictionary in participle network the cause of disease is matched from long to short, and combine the cause of disease pre-established
The priority of each cause of disease in word order table obtains final cause of disease word；If the cause of disease synonym pre-established is introduced during without matching
Table continues to match, and obtains final cause of disease word.
Step 2.5：According to the purpose dictionary in participle network purpose is matched from long to short, and combine the purpose pre-established
The priority of each purpose in word order table, obtains final purpose word.
Step 2.6：According to participle network in other dictionaries match other from long to short, and combine pre-establish other
Each others priority, obtains other final words in word order table.
Step 3：The keyword combination that step 2 obtains matches " word combination and the Code Mapping Tables " built in advance again, if energy
Corresponding word combination path is enough found, then can accurately match the corresponding indicated release ICD codings of surgical procedure title, output
ICD is encoded；If the record in certain word combination path can not be found, need to carry out the fuzzy adaptation of next step.
Step 4：Not matched word combination in accurate matching process then does further adaptation by fuzzy adaptation rule, takes
The corresponding ICD codings of immediate word combination are described as output result.Fuzzy adaptation rule includes：
1) it first looks for position in participle network and contains all paths for having matched " position word ", if can not find, continue
It searches position in participle network and contains all paths for having matched " position synonym ", exported if it still can not find " not
With "；
2) based on the final path of previous step, continue art formula in screening participle network and include the path for having matched " art formula word ",
Screening includes the path for having matched " art formula synonym " if it can not find, and next step is performed if still can not find；
3) based on the final path of previous step, continue approach in screening participle network and include the path for having matched " approach word ",
Screening includes the path for having matched " approach synonym " if it can not find, and next step is performed if still can not find；
4) based on the final path of previous step, continue the cause of disease in screening participle network and include the path for having matched " cause of disease word ",
Screening includes the path for having matched " cause of disease synonym " if it can not find, and next step is performed if still can not find；
5) based on the final path of previous step, continue purpose in screening participle network and include the path for having matched " purpose word ",
Screening includes the path for having matched " purpose synonym " if it can not find, and next step is performed if still can not find；
6) based on the final path of previous step, continue other in screening participle network and include the path for having matched " other words ",
If can not find, the final path of previous step is the path L for the condition that meets；
At this point, path L is to be included at most according to what position, art formula, approach, the cause of disease, purpose, other sequences were screened successively
The path of matching word.
Second step calculates the matching word number that corresponding part and the diagnosis name of input are segmented in the L of path, selection respectively
With the largest number of paths of word as coupling path, matching word number is identical, chooses and mismatches the minimum path work of word number
For coupling path, the corresponding ICD of coupling path is obtained by mapping table and is encoded；Finally, it if path L is sky, exports " not
With ".
The specific implementation process of accurate matching and the fuzzy matching of step 3 and step 4 is as shown in Figure 2.
2. as shown in figure 3, the participle network and position word of Dynamic expansion described in establishment step 2, art formula word, approach word, disease
Because of word, purpose word and other word order tables and position, art formula, approach, cause of disease synonym table, specifically comprise the following steps：
First, by the ICD of different regions or different editions encode and corresponding Chinese surgical procedure name to be referred to as training set defeated
Enter, when identical Chinese there are different ICD codings, retain and encode more forwardly of record；Secondly, from corresponding surgical procedure title
Extract part, art formula, approach, the cause of disease, purpose, other corresponding keywords in six parts build position dictionary, art formula word respectively
Library, approach dictionary, cause of disease dictionary, purpose dictionary and other dictionaries；Then, build position word, art formula word, approach word, cause of disease word,
Purpose word and other word order tables generate a sequence forest, and increase particular order table, provide that certain is special to meet needs
The demand of sequence；Sequence list defines position, art formula, approach, the cause of disease, purpose, the priority of other keywords, and sequence is more leaned on
Before, priority is higher；Finally, ICD surgical procedures in training set is taken to encode identical phrase extraction synonym, separately constitute portion
Position, art formula, approach, cause of disease synonym table, but and the consistent phrase of not all coding be all summarized as synonym, screening strategy be by
Participle each section of the identical phrase of all codings is combined and counts two-by-two, the more priority in adaptation of count number
Higher.
3. word combination and Code Mapping Tables described in establishment step 3, specifically include as follows：
First, the surgical procedure ICD versions to be referred to are determined；Extract training set in indicated release surgical procedure title
Identical record directly replaces the ICD codings in training set with the ICD of indicated release codings, completes the mapping of the code segment；
The record different from indicated release diagnosis name in training set, then by generated point of the surgical procedure name-matches of indicated release
Word network completes automatic word segmentation, obtains the set S in Fig. 4；By before the ICD codings of training set ICD codings and set S four
Position, four set that coding is identical and art formula is identical before searching find most like indicated release record (wherein most in set
Similar definitions are that match word number with participle corresponding part most, i.e., match successively position, approach, the cause of disease, purpose and other, unite
It counts matching word number and mismatches word number, the largest number of matching word is most like record, and matching word number is chosen when identical
Mismatch the minimum most like record of conduct of word number), the ICD codings of most like indicated release record are as mapping code.
Detailed process is as shown in figure 4, obtain preceding four different set S1 of coding and preceding four codings are identical but do not have the art formula identical
Set S2, they will be used as matched input data in next step, and continue to be adapted to.
Second step, set S2 carry out art formula matching by generated art formula synonym table, then find most like specify
Colophon, the ICD codings of most like indicated release record are used as mapping code, and detailed process is as shown in Figure 5.
Third walks, and for the first two steps record that it fails to match, encodes front three in training set ICD in the same way and refers to
Determine in the identical record of version ICD coding front threes, find the identical set of art formula, most like indicated release is found in set
Record, the ICD codings of most like indicated release record are as mapping code.Detailed process is as shown in fig. 6, obtain front three volume
The different set S3 of code and front three encode identical but will be used as matched input in next step without art formula identical set S4, S4
Data continue to be adapted to.
4th step, detailed process as shown in fig. 7, set S4 by generated art formula synonym table carry out art formula matching,
Most like indicated release record is found again, and the ICD codings of most like indicated release record are as mapping code.
Finally, manpower intervention still can not matched training set record, complete all training sets and indicated release be recorded
Coding mapping.Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited in above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or change within the scope of the claims, this not shadow
Ring the substantive content of the present invention.In the absence of conflict, the feature in embodiments herein and embodiment can arbitrary phase
Mutually combination.
Claims (10)
1. a kind of intelligent coding method of the Chinese surgical procedure based on participle network, which is characterized in that include the following steps：
Step 1, Chinese surgical procedure title is obtained；
Step 2, Chinese surgical procedure title with Dynamic expansion participle network is adapted to, is carried from Chinese surgical procedure title
It takes key message and the key message of extraction is formed into crucial phrase；
Step 3, crucial phrase is adapted to phrase Code Mapping Tables and export not matched result or ICD coding.
2. the intelligent coding method of the Chinese surgical procedure according to claim 1 based on participle network, which is characterized in that
Key message includes location information, art formula information, approach information, cause of disease information, purpose information and other information.
3. the intelligent coding method of the Chinese surgical procedure according to claim 2 based on participle network, which is characterized in that
Step 2 includes：
Key message is segmented into the position dictionary in network according to Dynamic expansion and matches location information, and binding site from long to short
The priority of each location information in word order table, obtains position word；
Key message is matched into art formula information, and combine art formula from long to short according to the art formula dictionary that Dynamic expansion is segmented in network
The priority of each art formula information in word order table, obtains art formula word；
Key message is matched into approach information, and with reference to approach from long to short according to the approach dictionary that Dynamic expansion is segmented in network
The priority of each approach information, obtains approach word in word order table；
Key message is matched into cause of disease information, and with reference to the cause of disease from long to short according to the cause of disease dictionary that Dynamic expansion is segmented in network
The priority of each cause of disease information, obtains cause of disease word in word order table；
Key message is segmented into the purpose dictionary in network according to Dynamic expansion and matches purpose information, and binding purpose from long to short
The priority of each purpose information, obtains purpose word in word order table；
Key message is matched into other information, and with reference to other from long to short according to other dictionaries that Dynamic expansion is segmented in network
The priority of each other information in word order table, obtains other words；
Crucial phrase includes at least position word, art formula word, approach word, cause of disease word, purpose word and other words.
4. the intelligent coding method of the Chinese surgical procedure according to claim 3 based on participle network, which is characterized in that
Adaptation in step 3 includes：
Step 3.1, the first order is adapted to：Accurate adaptation is carried out to crucial phrase and phrase Code Mapping Tables；
If crucial phrase is matched with phrase Code Mapping Tables, ICD codings corresponding with crucial phrase, intelligent coding method are exported
Terminate；
If crucial phrase is mismatched with phrase Code Mapping Tables, 3.2 are entered step；
Step 3.2, the second level is adapted to：Fuzzy be adapted to is carried out with phrase Code Mapping Tables to crucial phrase.
5. the intelligent coding method of the Chinese surgical procedure according to claim 4 based on participle network, which is characterized in that
Step 3.2, second level adaptation includes：
Step 3.2.1 searches the path for including most matching keywords in Dynamic expansion participle network；
Step 3.2.2 calculates remaining keyword and the key information match of the Chinese surgical procedure title of input in path
Number chooses coupling path；Wherein
Remaining keyword is non-matched keyword in crucial phrase.
6. the intelligent coding method of the Chinese surgical procedure according to claim 5 based on participle network, which is characterized in that
Step 3.2.1 includes：
Step 3.2.1.1 segments all first screenings for being filtered out in network and containing matched position word from Dynamic expansion
Path；If it is exported not matched as a result, intelligent coding method terminates without position word in crucial phrase；
Step 3.2.1.2 is filtered out from the first screening path and is contained matched art formula word, approach word, cause of disease word, purpose
Second screening path of word and other words；
Path is the packet according to the screening of art formula word, approach word, cause of disease word, purpose word and other words in the second all screening paths
Containing the most path of matching keywords.
7. the intelligent coding method of the Chinese surgical procedure according to claim 6 based on participle network, which is characterized in that
In step 3.2.2, when the number of matched keyword is identical, the minimum path conduct of unmatched keyword number is chosen
With path, and pass through phrase Code Mapping Tables obtain the corresponding ICD of coupling path encode and export the ICD coding.
8. the intelligent coding method of the Chinese surgical procedure according to claim 7 based on participle network, which is characterized in that
The establishment of Dynamic expansion participle network includes the following steps：
The ICD of different regions or different editions is encoded and corresponding Chinese surgical procedure name is referred to as training set input；If wherein
When identical Chinese surgical procedure title corresponds to different ICD codings, retain the smaller ICD codings of initial；If present bit is alphabetical
It is identical, then compare the letter of next bit, until last letter；
Symptom information, location information, cause of disease information and the corresponding keyword of other information are extracted from diagnosis name, is built respectively
Position dictionary, art formula dictionary, approach dictionary, cause of disease dictionary, purpose dictionary and other dictionaries；
According to symptom word, position word, cause of disease word and other words length from long to short, respectively build position word order table, art formula word
Sequence table, approach word order table, cause of disease word order table, purpose word order table and other word order tables, generation sequence forest；Wherein
The longer sequence of length is more forward, and priority is higher.
9. the intelligent coding method of the Chinese surgical procedure according to claim 8 based on participle network, which is characterized in that
The establishment of phrase Code Mapping Tables includes the following steps：
The determining ICD versions to be referred to；
Record identical with surgical procedure title Chinese in the determining ICD versions to be referred in training set is extracted, with determining institute
ICD codings in the ICD versions to be referred to replace the ICD codings in training set；
Record different from surgical procedure title Chinese in the determining ICD versions to be referred in training set is extracted, by determining institute
The Chinese generated Dynamic expansion participle network of surgical procedure name-matches, is determined with most like in the ICD versions to be referred to
The ICD codings for the ICD colophons to be referred to are as mapping code；Wherein
The ICD of most like indicated release record is encoded to segments the matched keyword number of network corresponding part with Dynamic expansion
Keyword number minimum record is mismatched when most records or identical matching keywords number.
10. a kind of system of the intelligent coding method of the Chinese surgical procedure based on participle network, including being stored with computer journey
The computer readable storage medium of sequence, which is characterized in that when the computer program is executed by processor realize claim 1 to
The step of intelligent coding method of the Chinese surgical procedure based on participle network described in any one of 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711350705.6A CN108182207B (en) | 2017-12-15 | 2017-12-15 | Intelligent coding method and system for Chinese surgical operation based on word segmentation network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711350705.6A CN108182207B (en) | 2017-12-15 | 2017-12-15 | Intelligent coding method and system for Chinese surgical operation based on word segmentation network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108182207A true CN108182207A (en) | 2018-06-19 |
| CN108182207B CN108182207B (en) | 2020-11-13 |
Family
ID=62546087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711350705.6A Active CN108182207B (en) | 2017-12-15 | 2017-12-15 | Intelligent coding method and system for Chinese surgical operation based on word segmentation network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108182207B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522552A (en) * | 2018-11-09 | 2019-03-26 | 天津开心生活科技有限公司 | A kind of method for normalizing of medical information, device, medium and electronic equipment |
| CN109785959A (en) * | 2018-12-14 | 2019-05-21 | 平安医疗健康管理股份有限公司 | A kind of disease code method and apparatus |
| CN110032715A (en) * | 2019-03-21 | 2019-07-19 | 武汉金豆医疗数据科技有限公司 | A kind of method of disease code conversion |
| CN111128388A (en) * | 2019-12-03 | 2020-05-08 | 东软集团股份有限公司 | Value domain data matching method and device and related products |
| CN112131867A (en) * | 2020-09-22 | 2020-12-25 | 上海亿普医药科技有限公司 | Clinical trial medical coding system |
| CN112632910A (en) * | 2020-12-21 | 2021-04-09 | 北京惠及智医科技有限公司 | Operation encoding method, electronic device and storage device |
| CN112700825A (en) * | 2020-12-30 | 2021-04-23 | 杭州依图医疗技术有限公司 | Medical data processing method and device and storage medium |
| CN112802566A (en) * | 2020-12-31 | 2021-05-14 | 医渡云（北京）技术有限公司 | Method and device for encoding electronic medical record |
| WO2021217850A1 (en) * | 2020-04-26 | 2021-11-04 | 平安科技（深圳）有限公司 | Disease name code matching method and apparatus, computer device and storage medium |
| CN114155968A (en) * | 2021-04-29 | 2022-03-08 | 深圳市康比特信息技术有限公司 | Method for establishing mapping relation, and method and equipment for auditing surgical operation |
| CN115017326A (en) * | 2022-05-12 | 2022-09-06 | 青岛普瑞盛医药科技有限公司 | Medical coding method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6915254B1 (en) * | 1998-07-30 | 2005-07-05 | A-Life Medical, Inc. | Automatically assigning medical codes using natural language processing |
| CN104156415A (en) * | 2014-07-31 | 2014-11-19 | 沈阳锐易特软件技术有限公司 | Mapping processing system and method for solving problem of standard code control of medical data |
| CN105069123A (en) * | 2015-08-13 | 2015-11-18 | 易保互联医疗信息科技（北京）有限公司 | Automatic coding method and system for Chinese surgical operation information |
| CN105574103A (en) * | 2015-12-11 | 2016-05-11 | 浙江大学 | Method and system for automatically establishing medical term mapping relationship based on word segmentation and coding |
| CN106202955A (en) * | 2016-07-19 | 2016-12-07 | 中电科软件信息服务有限公司 | Diagnosis associated packets method and system based on intellectual coded adaptation |
-
2017
- 2017-12-15 CN CN201711350705.6A patent/CN108182207B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6915254B1 (en) * | 1998-07-30 | 2005-07-05 | A-Life Medical, Inc. | Automatically assigning medical codes using natural language processing |
| CN104156415A (en) * | 2014-07-31 | 2014-11-19 | 沈阳锐易特软件技术有限公司 | Mapping processing system and method for solving problem of standard code control of medical data |
| CN105069123A (en) * | 2015-08-13 | 2015-11-18 | 易保互联医疗信息科技（北京）有限公司 | Automatic coding method and system for Chinese surgical operation information |
| CN105574103A (en) * | 2015-12-11 | 2016-05-11 | 浙江大学 | Method and system for automatically establishing medical term mapping relationship based on word segmentation and coding |
| CN106202955A (en) * | 2016-07-19 | 2016-12-07 | 中电科软件信息服务有限公司 | Diagnosis associated packets method and system based on intellectual coded adaptation |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522552B (en) * | 2018-11-09 | 2023-08-29 | 天津开心生活科技有限公司 | Normalization method and device of medical information, medium and electronic equipment |
| CN109522552A (en) * | 2018-11-09 | 2019-03-26 | 天津开心生活科技有限公司 | A kind of method for normalizing of medical information, device, medium and electronic equipment |
| CN109785959A (en) * | 2018-12-14 | 2019-05-21 | 平安医疗健康管理股份有限公司 | A kind of disease code method and apparatus |
| CN110032715A (en) * | 2019-03-21 | 2019-07-19 | 武汉金豆医疗数据科技有限公司 | A kind of method of disease code conversion |
| CN111128388A (en) * | 2019-12-03 | 2020-05-08 | 东软集团股份有限公司 | Value domain data matching method and device and related products |
| CN111128388B (en) * | 2019-12-03 | 2024-02-27 | 东软集团股份有限公司 | Value range data matching method and device and related products |
| WO2021217850A1 (en) * | 2020-04-26 | 2021-11-04 | 平安科技（深圳）有限公司 | Disease name code matching method and apparatus, computer device and storage medium |
| CN112131867A (en) * | 2020-09-22 | 2020-12-25 | 上海亿普医药科技有限公司 | Clinical trial medical coding system |
| CN112632910A (en) * | 2020-12-21 | 2021-04-09 | 北京惠及智医科技有限公司 | Operation encoding method, electronic device and storage device |
| CN112700825A (en) * | 2020-12-30 | 2021-04-23 | 杭州依图医疗技术有限公司 | Medical data processing method and device and storage medium |
| CN112700825B (en) * | 2020-12-30 | 2024-03-05 | 杭州依图医疗技术有限公司 | Medical data processing method, device and storage medium |
| CN112802566A (en) * | 2020-12-31 | 2021-05-14 | 医渡云（北京）技术有限公司 | Method and device for encoding electronic medical record |
| CN114155968A (en) * | 2021-04-29 | 2022-03-08 | 深圳市康比特信息技术有限公司 | Method for establishing mapping relation, and method and equipment for auditing surgical operation |
| CN115017326A (en) * | 2022-05-12 | 2022-09-06 | 青岛普瑞盛医药科技有限公司 | Medical coding method and device |
| CN115017326B (en) * | 2022-05-12 | 2023-08-18 | 青岛普瑞盛医药科技有限公司 | Medical coding method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108182207B (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108182207A (en) | The intelligent coding method and system of Chinese surgical procedure based on participle network | |
| CN108182972A (en) | The intelligent coding method and system of Chinese medical diagnosis on disease based on participle network | |
| CN104156352B (en) | Method and system for handling Chinese event | |
| CN109947794B (en) | Interactive natural language query conversion method | |
| CN104391881B (en) | A kind of daily record analytic method and system based on segmentation methods | |
| CN102024027B (en) | Method for establishing medical database | |
| CN105069124A (en) | Automatic ICD (International Classification of Diseases) coding method and system | |
| CN102982076A (en) | Multi-dimensionality content labeling method based on semanteme label database | |
| CN110610751A (en) | Electronic medical record inputting system and method | |
| CN104252507B (en) | A kind of business data matching process and device | |
| CN105138829A (en) | Natural language processing method and system for Chinese diagnosis and treatment information | |
| JP2024027087A (en) | Standard medical term management system and method based on general model | |
| CN110019410A (en) | For the big data digging system of tcm clinical case information | |
| CN107436955A (en) | A kind of English word relatedness computation method and apparatus based on Wikipedia Concept Vectors | |
| CN108647199A (en) | A kind of discovery method of place name neologisms | |
| CN115794833A (en) | Data processing method, server and computer storage medium | |
| CN110321556A (en) | A kind of method and its system of doctor's diagnosis and treatment medical insurance control expense intelligent recommendation scheme | |
| CN107861965A (en) | Data intelligence recognition methods and system | |
| CN110297829A (en) | A kind of text searching method and system towards specific industry structuring business datum | |
| CN117251517B (en) | Annual-authentication administrative division information matching method and model under large data field of view | |
| Anquetil | A comparison of graphs of concept for reverse engineering | |
| CN116484084B (en) | Metadata blood-margin analysis method, medium and system based on application information mining | |
| CN101246473B (en) | Segmentation system evaluating method and segmentation evaluating system | |
| CN106802911A (en) | A kind of method that automatic full dose of periodicity extracts database data | |
| CN102968432A (en) | Control method for verifying tuple on basis of degree of confidence |
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: 20190422 Address after: Room 501-503, 43 Block 1485, Jialuo Road, Jiading District, Shanghai, 201800 Applicant after: Zhong electricity Ke software information Services Co., Ltd Applicant after: Shanghai Changjiang science and Technology Development Co Ltd Address before: Room 106-7, 50 Jiling Road, Jing'an District, Shanghai, 2003 Applicant before: Shanghai Changjiang science and Technology Development Co Ltd |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |