CN108280149A - A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort - Google Patents
A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort Download PDFInfo
- Publication number
- CN108280149A CN108280149A CN201810007270.3A CN201810007270A CN108280149A CN 108280149 A CN108280149 A CN 108280149A CN 201810007270 A CN201810007270 A CN 201810007270A CN 108280149 A CN108280149 A CN 108280149A
- Authority
- CN
- China
- Prior art keywords
- various dimensions
- tag along
- along sort
- label
- doctor
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/358—Browsing; Visualisation therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The doctor-patient dispute class case based on various dimensions tag along sort that the invention discloses a kind of recommending method, including：(1) the central issue template of doctor-patient dispute case is defined, includes multiple elements in each central issue template；(2) using the element in central issue template as basic label, the various dimensions tag along sort system of doctor-patient dispute case is established；(3) decimation rule is defined using regular expression, central issue is extracted from doctor-patient dispute class case, a various dimensions tag along sort is formed for each case；(4) various dimensions tag along sort is generated according to the query statement of user, and calculates the similarity of itself and the various dimensions tag along sort of each case, the up to minimum user that is ordered as recommends case according to similarity.Accuracy higher of the present invention.
Description
Technical field
The present invention relates to natural language processing more particularly to a kind of doctor-patient dispute class cases based on various dimensions tag along sort
Recommendation method.
Background technology
Doctor-patient dispute refers to being based on medical act between hospital (medical institutions) and trouble side (patient or patients' relatives)
Generate, lead to divergence on concept to medical act, result and its reason, responsibility etc. and the dispute that causes.In recent years, people
Demand for medical service is constantly being increased, the requirement and troxerutine tabtets to service quality are also improving；And Health Care in China thing
The reform and development of industry relatively lag behind, and doctor-patient dispute caseload is thus caused to rise year by year, even occur in many places
A lot of felonies caused by doctor-patient dispute.Doctor-patient dispute class case commending system is to assist trouble-shooter or doctors and patients party or general
The logical masses carry out the brief input of dispute situation, then by big data analysis tool in a large amount of existing judgement document library, allusion quotations
The comparison that text similarity, case element similitude are carried out in type case library and existing dispute case library, provides and is entangled with input
Confused similar case for reference, helps trouble-shooter to carry out case analysis and argues, can also assist in doctors and patients party's objective analysis present situation,
The desired value of effective doctor and patient that furthers, improves and reconciles efficiency and success rate.
Accuracy rate is to weigh the key index of class case recommendation effect, directly reflects the availability of system；And it existing is based on
The proposed algorithm of text subject or word frequency weight, accuracy rate is commonly relatively low in terms of doctor-patient dispute class case recommendation, lacks practical
Application value.Topic model is a kind of statistical model for finding to be abstracted theme in a series of document, and topic model is automatic
Each document is analyzed, the word in statistic document concludes which theme current document includes according to the information of statistics, and every
Ratio shared by a theme is respectively how many, to weigh the similarity of text.However, can not be accurate using theme and its ratio
Weigh the similarity between doctor-patient dispute decision in a case book in ground.For example, two doctor-patient dispute cases in merit description section with same
The medical act measure that the length of sample describes the symptom of patient and hospital takes, in conclusion part, a case is " hospital
The harmful consequences of medical act and patient have causality ", and another case is that " patient surprisingly slips in hospital, doctor
Institute bears management responsibility ".The case of two themes and its ratio very " similar " is actually entirely different.In the above example, word-based
The algorithm of frequency weight such as vector space model and TF-IDF methods are not proved effective equally.
Invention content
Goal of the invention：In view of the problems of the existing technology the present invention, provides a kind of doctor based on various dimensions tag along sort
Suffering from dispute class case recommends method, this method to build the multidimensional tag along sort system of class case and corresponding central issue mould first
Existing case and user's query statement are carried out the classification that multiple dimensions are stamped in classification by plate by the method for supervised learning
Label realizes the pretreatment of various dimensions tag along sort filtering, compresses search space and effectively prominent central issue, is then based on and strives
The calculating that focus template carries out case similarity is discussed, the precision of class case push is improved, solves previous various algorithm doctors and patients class cases
Recommend the problem that irrelevance is high, accuracy rate is low.
Technical solution：Doctor-patient dispute class case of the present invention based on various dimensions tag along sort recommends the method to include：
(1) the central issue template of doctor-patient dispute case is defined, includes multiple elements in each central issue template；
(2) using the element in central issue template as basic label, the various dimensions contingency table of doctor-patient dispute case is established
Label system；
(3) decimation rule is defined using regular expression, central issue is extracted from doctor-patient dispute class case, for per case
Part forms a various dimensions tag along sort；
(4) various dimensions tag along sort is generated according to the query statement of user, and calculates its various dimensions point with each case
The similarity of class label, according to similarity, the up to minimum user that is ordered as recommends case.
Further, the central issue template in the step (1) is specially the formalization of central issue, central issue
Element corresponds to the attribute that the central issue is described and indicates.
Further, the step (2) specifically includes：
The various dimensions tag along sort system of doctor-patient dispute case is divided into three-level, including by doctor-patient dispute central issue template
Three-level label, the two level label that third level label is summarized and the level-one mark that second level label is summarized that element is constituted
Label, each doctor-patient dispute case correspond to a level-one label, have multiple two level labels, each two level label under each level-one label
Under have one or more three-level label.
Further, step (3) specifically includes：
(3.1) using the central issue of the central issue template matches doctor-patient dispute class case of definition, wherein a doctors and patients
Dispute class case matches one or more central issue template；
(3.2) regular expression is used to build rule, the central issue element of rule-based extraction doctor-patient dispute class case；
(3.3) central issue element is converted to the three-level label of corresponding case；
(3.4) according to the three-level label of case, two level label and level-one label are added for the case.
Further, the step (4) specifically includes：
(4.1) query statement input by user is obtained, by the decimation rule of central issue template and step (3) to inquiry
Sentence is extracted, and the corresponding various dimensions tag along sort of user's query statement is obtained；
(4.2) the various dimensions tag along sort of the corresponding various dimensions tag along sort of user's query statement and each case is calculated
Similarity, wherein calculating formula of similarity is：
Sim (x, y)=α sim (x1,y1)+β·sim(x21...x2i,y21...y2k)+γ·sim(x31...x3j,
y31...y3t)
In formula, sim (x, y) indicates that the similarity of various dimensions tag along sort x and various dimensions tag along sort y, α, beta, gamma are power
Weight parameter, and meet alpha+beta+γ=1, sim (x1,y1) indicate the level-one label x of various dimensions tag along sort x1With various dimensions contingency table
Sign the level-one label y of y1Similarity, sim (x21...x2i,y21...y2k) indicate various dimensions tag along sort x two level label and
The similarity of the two level label of various dimensions tag along sort y, sim (x31...x3j,y31...y3t) indicate various dimensions tag along sort x's
The similarity of the three-level label of three-level label and various dimensions tag along sort y, x21...x2iIndicate i of various dimensions tag along sort x
Two level label, y21...y2kIndicate the k two level label of various dimensions tag along sort y, x31...x3jIndicate various dimensions tag along sort x
J three-level label, y31...y3tIndicate the t three-level label of various dimensions tag along sort y；
(4.3) recommend case according to the up to minimum user that is ordered as of similarity.
Further, sim (x1,y1)、sim(x21...x2i,y21...y2k)、sim(x31...x3j,y31...y3t) calculating
Formula is respectively：
In formula, count (*) is indicated in this grade of label, the number of same label.
Wherein, the weight parameter α, beta, gamma can obtain in the following manner：
It is at different levels at its that (4.2.1) fetching portion doctor-patient dispute class case as training set, using formula acquires case two-by-two
Similarity sim (x on label1,y1),sim(x21...x2i,y21...y2k),sim(x31...x3j,y31...y3t), form one
Sample set；
(4.2.2) takes logarithm to likelihood function, obtains optimization object function：
In formula,Indicate the sim (x for first of sample that step (4.2.1) is calculated1,y1),Indicate first of sample
This sim (x21...x2i,y21...y2k),Indicate the sim (x of first of sample31...x3j,y31...y3t)；
(4.2.3) solves object function using gradient descent method, obtains α, beta, gamma optimal value；
(4.2.4) randomly chooses other sample sets, returns and executes (4.2.1), multiple optimal values is averaged, as most
Whole parameter value.
Alternatively, weight parameter α, the α that beta, gamma is directly filled in by obtaining user, beta, gamma is worth to, or is used by user
Addition that family carries out label, the operation deleted, move up and moved down assign different weights for different labels.
Advantageous effect：Compared with prior art, the present invention its remarkable advantage is：The present invention is striven using the extraction of rule extraction method
Focus is discussed, and is that case stamps various dimensions tag along sort according to central issue, realizes the pretreatment of various dimensions tag along sort filtering,
Influence of the redundancy to recommendation in decision in a case book can be eliminated；Use striving for central issue template matches doctor-patient dispute case
Focus is discussed, the complexity of similarity calculation can be reduced and improves the precision of class case push.
Description of the drawings
Fig. 1 is the flow diagram of one embodiment of the present of invention.
Specific implementation mode
A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort is present embodiments provided, such as Fig. 1 institutes
Show, including：
(1) the central issue template of doctor-patient dispute case is defined, includes multiple elements in each central issue template.
Wherein, central issue template is specially the formalization of central issue, and the element of central issue corresponds to the central issue
The attribute for being described and indicating, for example, disease type, medical act, diagnosis and treatment process, to cause consequence and attribution of liability etc. all
Description and expression of the various aspects to central issue.
(2) using the element in central issue template as basic label, the various dimensions contingency table of doctor-patient dispute case is established
Label system.The various dimensions tag along sort system of doctor-patient dispute case is specifically divided into three-level, including by doctor-patient dispute central issue
Three-level label that template element is constituted, the two level label that third level label is summarized and second level label is summarized one
Grade label, each doctor-patient dispute case correspond to a level-one label, have multiple two level labels, each two level under each level-one label
There is one or more three-level label under label.
In the recommendation of doctors and patients' class case, the pass of " doctor-patient dispute case ", " central issue " and " central issue template " three
System is：" central issue " is the refinement and summary to " doctor-patient dispute case ", has important work for judging whether case is similar
With；" central issue template " is one-to-one relationship with " central issue ", and the form of user element carries out table to " central issue "
Show, meanwhile, each element is a three-level label.For example, [hospital name, if over range operation causes consequence] is doctor
Institute's qualification central issue template, attribute therein【Hospital name】It is exactly an element.The label specifically established is as shown in table 1.
Table 1
(3) decimation rule is defined using regular expression, central issue is extracted from doctor-patient dispute class case, for per case
Part forms a various dimensions tag along sort.It specifically includes：
(3.1) using the central issue of the central issue template matches doctor-patient dispute class case of definition, wherein a doctors and patients
Dispute class case matches one or more central issue template；
(3.2) regular expression is used to build rule, the central issue element of rule-based extraction doctor-patient dispute class case；
(3.3) central issue element is converted to the three-level label of corresponding case；
(3.4) according to the three-level label of case, two level label and level-one label are added for the case.
For example, with the central issue template under two level label " operation "：[relate to thing hospital name, section office, disease name, hand
Art title, remaining foreign matter] for.It is extracted from case using rule " relating to thing hospital name ", " section office ", " disease name ",
" operation names ", the value of " remaining foreign matter ", and corresponding label is stamped for the case, finally stamp " operation " for the case two
The level-one label of grade label and " medical technology class ".
(4) various dimensions tag along sort is generated according to the query statement of user, and calculates its various dimensions point with each case
The similarity of class label, according to similarity, the up to minimum user that is ordered as recommends case.It specifically includes：
(4.1) query statement input by user is obtained, by the decimation rule of central issue template and step (3) to inquiry
Sentence is extracted, and the corresponding various dimensions tag along sort of user's query statement is obtained；
(4.2) the various dimensions tag along sort of the corresponding various dimensions tag along sort of user's query statement and each case is calculated
Similarity, wherein calculating formula of similarity is：
Sim (x, y)=α sim (x1,y1)+β·sim(x21...x2i,y21...y2k)+γ·sim(x31...x3j,
y31...y3t)
In formula, sim (x, y) indicates that the similarity of various dimensions tag along sort x and various dimensions tag along sort y, α, beta, gamma are power
Weight parameter, and meet alpha+beta+γ=1, sim (x1,y1) indicate the level-one label x of various dimensions tag along sort x1With various dimensions contingency table
Sign the level-one label y of y1Similarity, sim (x21...x2i,y21...y2k) indicate various dimensions tag along sort x two level label and
The similarity of the two level label of various dimensions tag along sort y, sim (x31...x3j,y31...y3t) indicate various dimensions tag along sort x's
The similarity of the three-level label of three-level label and various dimensions tag along sort y, x21...x2iIndicate i of various dimensions tag along sort x
Two level label, y21...y2kIndicate the k two level label of various dimensions tag along sort y, x31...x3jIndicate various dimensions tag along sort x
J three-level label, y31...y3tIndicate the t three-level label of various dimensions tag along sort y；
sim(x1,y1)、sim(x21...x2i,y21...y2k)、sim(x31...x3j,y31...y3t) calculation formula difference
For：
In formula, count (*) is indicated in this grade of label, the number of same label.
(4.3) recommend case according to the up to minimum user that is ordered as of similarity.
Wherein, the weight parameter α, beta, gamma can obtain in the following manner：
It is at different levels at its that (4.2.1) fetching portion doctor-patient dispute class case as training set, using formula acquires case two-by-two
Similarity sim (x on label1,y1),sim(x21...x2i,y21...y2k),sim(x31...x3j,y31...y3t), form one
Sample set；
(4.2.2) takes logarithm to likelihood function, obtains optimization object function：
In formula,Indicate the sim (x for first of sample that step (4.2.1) is calculated1,y1),Indicate first of sample
This sim (x21...x2i,y21...y2k),Indicate the sim (x of first of sample31...x3j,y31...y3t)；
(4.2.3) solves object function using gradient descent method, obtains α, beta, gamma optimal value；
(4.2.4) randomly chooses other sample sets, returns and executes (4.2.1), multiple optimal values is averaged, as most
Whole parameter value.
Alternatively, weight parameter α, the α that beta, gamma is directly filled in by obtaining user, beta, gamma is worth to, or passes through user couple
The addition of label progress, the operation deleted, move up and moved down, different weights is assigned for different labels.
It is above disclosed to be only a preferred embodiment of the present invention, the right model of the present invention cannot be limited with this
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (8)
1. a kind of doctor-patient dispute class case based on various dimensions tag along sort recommends method, it is characterised in that including：
(1) the central issue template of doctor-patient dispute case is defined, includes multiple elements in each central issue template；
(2) using the element in central issue template as basic label, the various dimensions tag along sort body of doctor-patient dispute case is established
System；
(3) decimation rule is defined using regular expression, central issue is extracted from doctor-patient dispute class case, be each case shape
At a various dimensions tag along sort；
(4) various dimensions tag along sort is generated according to the query statement of user, and calculates its various dimensions contingency table with each case
The similarity of label, according to similarity, the up to minimum user that is ordered as recommends case.
2. the doctor-patient dispute class case according to claim 1 based on various dimensions tag along sort recommends method, feature to exist
In：Central issue template in the step (1) is specially the formalization of central issue, and the element of central issue corresponds to the dispute
The attribute that focus is described and indicates.
3. the doctor-patient dispute class case according to claim 1 based on various dimensions tag along sort recommends method, feature to exist
In：The step (2) specifically includes：
The various dimensions tag along sort system of doctor-patient dispute case is divided into three-level, including by doctor-patient dispute central issue template element
The three-level label of composition, the two level label that third level label is summarized and the level-one label that second level label is summarized,
Each doctor-patient dispute case corresponds to a level-one label, there is multiple two level labels under each level-one label, under each two level label
There is one or more three-level label.
4. the doctor-patient dispute class case according to claim 1 based on various dimensions tag along sort recommends method, feature to exist
In：Step (3) specifically includes：
(3.1) using the central issue of the central issue template matches doctor-patient dispute class case of definition, wherein a doctor-patient dispute
Class case matches one or more central issue template；
(3.2) regular expression is used to build rule, the central issue element of rule-based extraction doctor-patient dispute class case；
(3.3) central issue element is converted to the three-level label of corresponding case；
(3.4) according to the three-level label of case, two level label and level-one label are added for the case.
5. the doctor-patient dispute class case according to claim 1 based on various dimensions tag along sort recommends method, feature to exist
In：The step (4) specifically includes：
(4.1) query statement input by user is obtained, by the decimation rule of central issue template and step (3) to query statement
It is extracted, obtains the corresponding various dimensions tag along sort of user's query statement；
(4.2) the similar of the various dimensions tag along sort of the corresponding various dimensions tag along sort of user's query statement and each case is calculated
Degree, wherein calculating formula of similarity is：
Sim (x, y)=α sim (x1,y1)+β·sim(x21...x2i,y21...y2k)+γ·sim(x31...x3j,
y31...y3t)
In formula, sim (x, y) indicates that the similarity of various dimensions tag along sort x and various dimensions tag along sort y, α, beta, gamma are joined for weight
Number, and meet alpha+beta+γ=1, sim (x1,y1) indicate the level-one label x of various dimensions tag along sort x1With various dimensions tag along sort y
Level-one label y1Similarity, sim (x21...x2i,y21...y2k) indicate the two level label and multidimensional of various dimensions tag along sort x
Spend the similarity of the two level label of tag along sort y, sim (x31...x3j,y31...y3t) indicate the three-level of various dimensions tag along sort x
The similarity of the three-level label of label and various dimensions tag along sort y, x21...x2iIndicate the i two level of various dimensions tag along sort x
Label, y21...y2kIndicate the k two level label of various dimensions tag along sort y, x31...x3jIndicate j of various dimensions tag along sort x
Three-level label, y31...y3tIndicate the t three-level label of various dimensions tag along sort y；
(4.3) recommend case according to the up to minimum user that is ordered as of similarity.
6. the doctor-patient dispute class case according to claim 5 based on various dimensions tag along sort recommends method, feature to exist
In：sim(x1,y1)、sim(x21...x2i,y21...y2k)、sim(x31...x3j,y31...y3t) calculation formula be respectively：
In formula, count (*) is indicated in this grade of label, the number of same label.
7. the doctor-patient dispute class case according to claim 5 based on various dimensions tag along sort recommends method, feature to exist
In：The weight parameter α, β, γ are obtained in the following manner：
(4.2.1) fetching portion doctor-patient dispute class case as training set, using formula acquire two-by-two case in its label at different levels
On similarity sim (x1,y1),sim(x21...x2i,y21...y2k),sim(x31...x3j,y31...y3t), form a sample
Collection；
(4.2.2) takes logarithm to likelihood function, obtains optimization object function：
In formula,Indicate the sim (x for first of sample that step (4.2.1) is calculated1,y1),Indicate first of sample
Sim (x21...x2i,y21...y2k),Indicate the sim (x of first of sample31...x3j,y31...y3t)；
(4.2.3) solves object function using gradient descent method, obtains α, beta, gamma optimal value；
(4.2.4) randomly chooses other sample sets, returns and executes (4.2.1), multiple optimal values is averaged, as final
Parameter value.
8. the doctor-patient dispute class case according to claim 5 based on various dimensions tag along sort recommends method, feature to exist
In：The weight parameter α, the α that beta, gamma is directly filled in by obtaining user, beta, gamma are worth to, or by user user to mark
The addition carried out, the operation deleted, move up and moved down are signed, different weights is assigned for different labels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810007270.3A CN108280149A (en) | 2018-01-04 | 2018-01-04 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810007270.3A CN108280149A (en) | 2018-01-04 | 2018-01-04 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108280149A true CN108280149A (en) | 2018-07-13 |
Family
ID=62803159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810007270.3A Pending CN108280149A (en) | 2018-01-04 | 2018-01-04 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108280149A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615088A (en) * | 2018-10-12 | 2019-04-12 | 国网浙江省电力有限公司电力科学研究院 | A kind of processing operation/maintenance work orders based on power information acquisition label |
| CN109783640A (en) * | 2018-12-20 | 2019-05-21 | 广州恒巨信息科技有限公司 | One type case recommended method, system and device |
| CN109992664A (en) * | 2019-03-12 | 2019-07-09 | 平安科技（深圳）有限公司 | Mark classification method, device, computer equipment and the storage medium of central issue |
| CN110516203A (en) * | 2019-08-28 | 2019-11-29 | 北京市律典通科技有限公司 | Central issue analysis method, device, electronic equipment and computer can storage mediums |
| CN110765266A (en) * | 2019-09-20 | 2020-02-07 | 成都星云律例科技有限责任公司 | Method and system for merging similar dispute focuses of referee documents |
| CN111126054A (en) * | 2019-12-03 | 2020-05-08 | 东软集团股份有限公司 | Method, device, storage medium and electronic equipment for determining similar texts |
| CN111198953A (en) * | 2018-11-16 | 2020-05-26 | 北京智慧正安科技有限公司 | Case text information based method and system for recommending cases and computer readable storage medium |
| CN111401047A (en) * | 2018-12-29 | 2020-07-10 | 北京国双科技有限公司 | Method and device for generating dispute focus of legal document and computer equipment |
| CN111666495A (en) * | 2020-06-05 | 2020-09-15 | 北京百度网讯科技有限公司 | Case recommendation method, device, equipment and storage medium |
| WO2021051865A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Case recommendation method and device, apparatus, and computer readable storage medium |
| CN114186559A (en) * | 2021-12-09 | 2022-03-15 | 北京深维智信科技有限公司 | Method and system for determining role label of session body from sales session |
| CN115374190A (en) * | 2022-10-25 | 2022-11-22 | 支付宝(杭州)信息技术有限公司 | Method and device for searching variety, storage medium and electronic equipment |
| CN116825304A (en) * | 2023-06-25 | 2023-09-29 | 湖南大学 | Online medical method and system based on deep interconnection |
| CN117390293A (en) * | 2023-12-12 | 2024-01-12 | 之江实验室 | Information recommendation method, device, medium and equipment for dispute cases |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218436A (en) * | 2013-04-17 | 2013-07-24 | 中国科学院自动化研究所 | Similar problem retrieving method fusing user category labels and device thereof |
| CN106126695A (en) * | 2016-06-30 | 2016-11-16 | 张春生 | A kind of similar case search method and device |
| CN106802925A (en) * | 2016-12-20 | 2017-06-06 | 深圳爱拼信息科技有限公司 | A kind of lawyer's intelligent Matching recommends method and server |
| CN107133283A (en) * | 2017-04-17 | 2017-09-05 | 北京科技大学 | A kind of Legal ontology knowledge base method for auto constructing |
| CN107330071A (en) * | 2017-06-30 | 2017-11-07 | 北京神州泰岳软件股份有限公司 | A kind of legal advice information intelligent replies method and platform |
-
2018
- 2018-01-04 CN CN201810007270.3A patent/CN108280149A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218436A (en) * | 2013-04-17 | 2013-07-24 | 中国科学院自动化研究所 | Similar problem retrieving method fusing user category labels and device thereof |
| CN106126695A (en) * | 2016-06-30 | 2016-11-16 | 张春生 | A kind of similar case search method and device |
| CN106802925A (en) * | 2016-12-20 | 2017-06-06 | 深圳爱拼信息科技有限公司 | A kind of lawyer's intelligent Matching recommends method and server |
| CN107133283A (en) * | 2017-04-17 | 2017-09-05 | 北京科技大学 | A kind of Legal ontology knowledge base method for auto constructing |
| CN107330071A (en) * | 2017-06-30 | 2017-11-07 | 北京神州泰岳软件股份有限公司 | A kind of legal advice information intelligent replies method and platform |
Non-Patent Citations (1)
| Title |
|---|
| 佘贵清 等: "审判案例自动抽取与标注模型研究", 《知识组织与知识管理》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615088A (en) * | 2018-10-12 | 2019-04-12 | 国网浙江省电力有限公司电力科学研究院 | A kind of processing operation/maintenance work orders based on power information acquisition label |
| CN111198953A (en) * | 2018-11-16 | 2020-05-26 | 北京智慧正安科技有限公司 | Case text information based method and system for recommending cases and computer readable storage medium |
| CN109783640A (en) * | 2018-12-20 | 2019-05-21 | 广州恒巨信息科技有限公司 | One type case recommended method, system and device |
| CN111401047A (en) * | 2018-12-29 | 2020-07-10 | 北京国双科技有限公司 | Method and device for generating dispute focus of legal document and computer equipment |
| CN109992664B (en) * | 2019-03-12 | 2023-04-18 | 平安科技（深圳）有限公司 | Dispute focus label classification method and device, computer equipment and storage medium |
| CN109992664A (en) * | 2019-03-12 | 2019-07-09 | 平安科技（深圳）有限公司 | Mark classification method, device, computer equipment and the storage medium of central issue |
| CN110516203A (en) * | 2019-08-28 | 2019-11-29 | 北京市律典通科技有限公司 | Central issue analysis method, device, electronic equipment and computer can storage mediums |
| WO2021051865A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Case recommendation method and device, apparatus, and computer readable storage medium |
| CN110765266A (en) * | 2019-09-20 | 2020-02-07 | 成都星云律例科技有限责任公司 | Method and system for merging similar dispute focuses of referee documents |
| CN110765266B (en) * | 2019-09-20 | 2022-07-22 | 成都星云律例科技有限责任公司 | Method and system for merging similar dispute focuses of referee documents |
| CN111126054A (en) * | 2019-12-03 | 2020-05-08 | 东软集团股份有限公司 | Method, device, storage medium and electronic equipment for determining similar texts |
| CN111126054B (en) * | 2019-12-03 | 2024-03-05 | 东软集团股份有限公司 | Method and device for determining similar text, storage medium and electronic equipment |
| CN111666495B (en) * | 2020-06-05 | 2023-08-11 | 北京百度网讯科技有限公司 | Case recommending method, device, equipment and storage medium |
| CN111666495A (en) * | 2020-06-05 | 2020-09-15 | 北京百度网讯科技有限公司 | Case recommendation method, device, equipment and storage medium |
| CN114186559B (en) * | 2021-12-09 | 2022-09-13 | 北京深维智信科技有限公司 | Method and system for determining role label of session body from sales session |
| CN114186559A (en) * | 2021-12-09 | 2022-03-15 | 北京深维智信科技有限公司 | Method and system for determining role label of session body from sales session |
| CN115374190A (en) * | 2022-10-25 | 2022-11-22 | 支付宝(杭州)信息技术有限公司 | Method and device for searching variety, storage medium and electronic equipment |
| CN116825304A (en) * | 2023-06-25 | 2023-09-29 | 湖南大学 | Online medical method and system based on deep interconnection |
| CN116825304B (en) * | 2023-06-25 | 2024-02-23 | 湖南大学 | Online medical method and system based on deep interconnection |
| CN117390293A (en) * | 2023-12-12 | 2024-01-12 | 之江实验室 | Information recommendation method, device, medium and equipment for dispute cases |
| CN117390293B (en) * | 2023-12-12 | 2024-04-02 | 之江实验室 | Information recommendation method, device, medium and equipment for dispute cases |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280149A (en) | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort | |
| Patra et al. | Extracting social determinants of health from electronic health records using natural language processing: a systematic review | |
| US8751495B2 (en) | Automated patient/document identification and categorization for medical data | |
| US20220044812A1 (en) | Automated generation of structured patient data record | |
| CN109065157A (en) | A kind of Disease Diagnosis Standard coded Recommendation list determines method and system | |
| CN112233746B (en) | Automatic medical data standardization method | |
| Almagro et al. | ICD-10 coding of Spanish electronic discharge summaries: An extreme classification problem | |
| Tremblay et al. | Identifying fall-related injuries: Text mining the electronic medical record | |
| Cao et al. | Multi-information source hin for medical concept embedding | |
| US20200293528A1 (en) | Systems and methods for automatically generating structured output documents based on structural rules | |
| US20190108264A1 (en) | System prototype of intelligent regional mobile healthcare integrated data center based on metadata | |
| Chen et al. | A bibliometric analysis of the development of ICD-11 in medical informatics | |
| Malakouti et al. | Predicting patient’s diagnoses and diagnostic categories from clinical-events in EHR data | |
| Fidahussein et al. | A corpus-based approach for automated LOINC mapping | |
| Bettencourt-Silva et al. | Discovering new social determinants of health concepts from unstructured data: framework and evaluation | |
| Falissard et al. | Neural translation and automated recognition of ICD-10 medical entities from natural language: Model development and performance assessment | |
| Mckensy-Sambola et al. | Ontology-based nutritional recommender system | |
| Singh et al. | Multi-label natural language processing to identify diagnosis and procedure codes from MIMIC-III inpatient notes | |
| Lin et al. | An exploratory study using an openEHR 2-level modeling approach to represent common data elements | |
| CN111460173B (en) | Method for constructing disease ontology model of thyroid cancer | |
| Memarzadeh et al. | A study into patient similarity through representation learning from medical records | |
| Aggarwal et al. | HEDEA: a Python tool for extracting and analysing semi-structured information from medical records | |
| WO2023217737A1 (en) | Health data enrichment for improved medical diagnostics | |
| CN116343980A (en) | Intelligent medical review follow-up data processing method and system | |
| CN114882985A (en) | Medicine multimedia management system and method based on database and AI algorithm identification |
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 |
Application publication date: 20180713 |
|
| RJ01 | Rejection of invention patent application after publication |