CN111652737B - Insurance verification method and apparatus based on text semantic processing - Google Patents
Insurance verification method and apparatus based on text semantic processing Download PDFInfo
- Publication number
- CN111652737B CN111652737B CN202010306058.4A CN202010306058A CN111652737B CN 111652737 B CN111652737 B CN 111652737B CN 202010306058 A CN202010306058 A CN 202010306058A CN 111652737 B CN111652737 B CN 111652737B
- Authority
- CN
- China
- Prior art keywords
- disease
- knowledge base
- diseases
- matching
- dangerous
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012795 verification Methods 0.000 title claims abstract description 18
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 115
- 201000010099 disease Diseases 0.000 claims abstract description 112
- 238000001914 filtration Methods 0.000 claims description 6
- 238000003058 natural language processing Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 2
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 208000024891 symptom Diseases 0.000 description 3
- JRIFOENGVFOJPK-UHFFFAOYSA-N 2,2-difluoro-N-(2-hydroxypropyl)-3-(3-nitro-1,2,4-triazol-1-yl)propanamide Chemical compound CC(O)CNC(=O)C(F)(F)CN1C=NC([N+]([O-])=O)=N1 JRIFOENGVFOJPK-UHFFFAOYSA-N 0.000 description 1
- 101000802371 Homo sapiens Zinc transporter 1 Proteins 0.000 description 1
- 101000802375 Homo sapiens Zinc transporter 2 Proteins 0.000 description 1
- 102100034993 Zinc transporter 1 Human genes 0.000 description 1
- 102100034994 Zinc transporter 2 Human genes 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides an insurance verification method and device based on text semantic processing. Receiving a disease name input by a user; all synonymous diseases matching the entered disease name; matching all sub-diseases of the input disease name and corresponding synonyms; matching all father diseases of the disease names and corresponding synonyms; aiming at the sub-diseases, matching all the sub-diseases of the sub-diseases and corresponding synonyms according to the inclusion relation in the related table knowledge base; aiming at the father disease, all father diseases of the father disease and corresponding synonyms are matched according to the inclusion relation in the knowledge base of the correlation table; according to the disease names of all synonymous diseases, matching the dangerous seed names which cannot be applied according to the dangerous seed non-applicable disease knowledge base; matching suspected risk names according to the risk non-insurable disease knowledge base; matching the name of the dangerous seed which cannot be applied according to the knowledge base of the dangerous seed diseases which cannot be applied; and finally determining the non-applicable dangerous seed and the suspected dangerous seed.
Description
Technical Field
The invention relates to the field of insurance, in particular to an insurance verification method and device based on text semantic processing.
Background
Most insurance products will require the user to be informed of health. Generally speaking, a great deal of "health advice" will be a list of diseases or symptoms that require the user to meet the requirements of a condition or symptom not specified. However, the insurance products on the market are quite abundant and the requirements of the health notification of each product are different, and once a user suffers from some previous symptoms, it is difficult to judge which products meet the requirements of the health notification of the products and which products do not meet the requirements of the health notification of the products. Thus, the method brings trouble to the insurance user and also influences the operation efficiency of the insurance market.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an insurance verification method and an insurance verification device based on text semantic processing, which can automatically match insurance products which can be applied, cannot be applied and are suspected to be applied according to a matching rule based on the input of a client.
According to the invention, an insurance verification method based on text semantic processing is provided, comprising the following steps:
a first step of: establishing a knowledge base based on insurance underwriting correlation;
and a second step of: receiving a disease name input by a user;
and a third step of: matching all synonymous diseases of the input disease names according to the synonymous relation in the related table knowledge base;
fourth step: according to the containing relation in the knowledge base of the correlation table, all the sub-diseases of the input disease name and corresponding synonyms are matched;
fifth step: according to the containing relation in the knowledge base of the correlation table, all father diseases of the disease names and corresponding synonyms are matched;
sixth step: aiming at the sub-diseases, matching all the sub-diseases of the sub-diseases and corresponding synonyms according to the inclusion relation in the related table knowledge base;
seventh step: aiming at the father disease, all father diseases of the father disease and corresponding synonyms are matched according to the inclusion relation in the knowledge base of the correlation table;
eighth step: according to the disease names of all synonymous diseases obtained in the third step, matching the name of the dangerous seed which cannot be applied according to the knowledge base of the dangerous seed which cannot be applied;
ninth step: according to all the disease names obtained in the fourth step and the sixth step, matching suspected and administrable risk names according to the risk non-applicable disease knowledge base;
tenth step: according to all disease names obtained in the fifth step and the seventh step, matching the name of the dangerous seed which cannot be applied according to the knowledge base of the dangerous seed which cannot be applied;
eleventh step: filtering repeated dangerous seeds in the results of the eighth step, the ninth step and the tenth step according to filtering rules to finally determine non-applicable dangerous seeds and suspected dangerous seeds;
twelfth step: and determining the applicable dangerous seed according to the finally determined non-applicable dangerous seed and suspected dangerous seed.
Preferably, the knowledge base based on insurance underwriting includes:
a disorder library in which disease names, disease interpretations, and warranty conclusions are stored in an associative manner;
a dangerous non-insurable disease knowledge base in which a dangerous identification code and a non-insurable disease name are stored in an associative manner;
a relational table knowledge base in which synonym relationships of disease names are stored in an associative manner, and inclusion relationships between disease names are stored;
a health notification rich text knowledge base in which a risk identification code and a health notification rich text format are stored in an associated manner;
a health notification highlighting table in which disease names and health notification text content are stored in an associative manner.
Preferably, in the second step, the text similarity measurement is performed on the disease name input by the user by using a natural language processing model Jaro-Winkler score, and the text of which Jaro-Winkler score is greater than a predetermined threshold (for example, 0.6) is determined as the similar text.
Preferably, the insurance underwriting method based on text semantic processing further comprises: based on the disease name input by the user, outputting the interpretation of the disease and the check and protection conclusion of serious disease, medical risk and life risk.
Preferably, the insurance underwriting method based on text semantic processing further comprises:
extracting the disease names obtained in the third step to the seventh step, and matching possible health notification text contents by combining the health notification highlight table;
aiming at the dangerous seeds obtained in the eighth step, the ninth step and the tenth step, combining the health notification rich text knowledge base to match the health notification rich text of each dangerous seed;
and matching the health notification text content with the health notification rich text to obtain the health notification text.
Preferably, in the health notification for each risk, non-insurable relevant text content is highlighted.
According to the invention, an insurance verification device based on text semantic processing is also provided, which is used for realizing the insurance verification method based on text semantic processing.
The invention provides an insurance verification method and an insurance verification device based on text semantic processing, which can automatically match insurance products which can be applied, cannot be applied and are suspected to be applied according to a matching rule based on the input of a client.
Drawings
The invention will be more fully understood and its attendant advantages and features will be more readily understood by reference to the following detailed description, when taken in conjunction with the accompanying drawings, in which:
fig. 1 schematically shows a flow chart of an insurance verification method based on text semantic processing according to a preferred embodiment of the present invention.
Fig. 2 schematically illustrates an insurance matching example of an insurance verification method based on text semantic processing according to a preferred embodiment of the present invention.
It should be noted that the drawings are for illustrating the invention and are not to be construed as limiting the invention. Note that the drawings representing structures may not be drawn to scale. Also, in the drawings, the same or similar elements are denoted by the same or similar reference numerals.
Detailed Description
In order that the invention may be more readily understood, a detailed description of the invention is provided below along with specific embodiments and accompanying figures.
Fig. 1 schematically shows a flow chart of an insurance verification method based on text semantic processing according to a preferred embodiment of the present invention.
As shown in fig. 1, the insurance underwriting method based on text semantic processing according to the preferred embodiment of the present invention includes:
a first step of: establishing a knowledge base based on insurance underwriting correlation;
the knowledge base based on insurance underwriting includes:
a disorder library in which disease names, disease interpretations, and warranty conclusions are stored in an associative manner;
a dangerous non-insurable disease knowledge base in which a dangerous identification code and a non-insurable disease name are stored in an associative manner;
a relational table knowledge base in which synonym relationships of disease names are stored in an associative manner, and inclusion relationships between disease names are stored;
a health notification rich text knowledge base in which a risk identification code and a health notification rich text format are stored in an associated manner;
a health notification highlighting table in which disease names and health notification text content are stored in an associative manner.
And a second step of: receiving a disease name input by a user;
more specifically, in the second step, the natural language processing model Jaro-Winkler score is used to measure the similarity of texts to the names of diseases entered by the user, and texts in which Jaro-Winkler score is greater than a predetermined threshold (for example, 0.6) are determined as similar texts.
And a third step of: matching all synonymous diseases T1, T2, … and TN of the input disease names according to the synonymous relation in the related table knowledge base;
fourth step: according to the inclusion relation in the knowledge base of the correlation table, all the sub-diseases Z1, Z2, …, ZN and corresponding synonyms Z1T1, Z1T2, …, Z1TN, Z2T1, Z2T2, …, Z2TN, …, ZNT1, ZNT2, … and ZNTN of the input disease names are matched;
fifth step: according to the inclusion relation in the knowledge base of the correlation table, all the father diseases F1, F2, …, FN of the disease name and corresponding synonyms F1T1, F1T2, …, F1TN, F2T1, F2T2, …, F2TN, …, FNT1, FNT2, … and FNTN are matched, as shown in FIG. 2;
sixth step: for the sub-diseases Z1, Z2, … and ZN, taking Z1 as an example, according to the inclusion relation in the knowledge base of the correlation table, all the sub-diseases Z1Z1, Z1Z2, … and Z1ZN of Z1 and corresponding synonyms Z1Z1T1, Z1Z1T2, …, Z1Z1TN, Z1Z2T1, Z1Z2T2, …, Z1Z2TN, Z1ZNT1, Z1ZNT2, … and Z1ZNTN are matched, as shown in FIG. 2;
seventh step: for the father diseases F1, F2, …, FN, taking F1 as an example, according to the inclusion relation in the knowledge base of the correlation table, all the father diseases F1, F1F2, …, F1FN of F1 and corresponding synonyms F1T1, F1T2, …, F1TN, F1F2T1, F1F2T2, …, F1F2TN, F1FNT1, F1FNT2, …, F1FNTN are matched, as shown in fig. 2;
eighth step: according to the disease names of all synonymous diseases obtained in the third step, matching the name of the dangerous seed which cannot be applied according to the knowledge base of the dangerous seed which cannot be applied;
ninth step: according to all the disease names obtained in the fourth step and the sixth step, matching suspected and administrable risk names according to the risk non-applicable disease knowledge base;
tenth step: according to all disease names obtained in the fifth step and the seventh step, matching the name of the dangerous seed which cannot be applied according to the knowledge base of the dangerous seed which cannot be applied;
eleventh step: filtering repeated dangerous seeds in the results of the eighth step, the ninth step and the tenth step according to filtering rules to finally determine non-applicable dangerous seeds and suspected dangerous seeds;
twelfth step: and determining the applicable dangerous seed according to the finally determined non-applicable dangerous seed and suspected dangerous seed.
Thus, based on the disease name input by the user, insurance product names which can be applied, cannot be applied and are suspected to be applied are matched according to the knowledge base related to the verification.
Furthermore, for the underwriting theory output, the insurance underwriting method based on text semantic processing according to the preferred embodiment of the present invention may further include: based on the disease name input by the user, outputting the interpretation of the disease and the check and protection conclusion of serious disease, medical risk and life risk.
Furthermore, the text semantic processing-based insurance underwriting method according to the preferred embodiment of the present invention may further include:
extracting the disease names obtained in the third step to the seventh step, and matching possible health notification text contents by combining the health notification highlight table;
aiming at the dangerous seeds obtained in the eighth step, the ninth step and the tenth step, combining the health notification rich text knowledge base to match the health notification rich text of each dangerous seed;
and matching the health notification text content with the health notification rich text to obtain the health notification text. Preferably, in the health notification for each risk, non-insurable relevant text content is highlighted.
Therefore, the invention provides an insurance verification method and an insurance verification device based on text semantic processing, which can automatically match insurance products which can be applied, cannot be applied and are suspected to be applied according to a matching rule based on the input of a client.
< technology of text similarity coefficient in Natural language processing >
Jaro Distance: a measure of string similarity, also an edit distance, is the higher the Jaro distance, the higher the text similarity, the similarity is defined as follows:
wherein M represents the number of matches (guaranteed to be the same), s represents the string length, t represents the number of permutations, and the number of permutations represents: if the distance between two characters from S1 and S2 respectively is not more thanThe two strings are considered to be matched; and these are mutuallyThe number of transposition T is determined by the matched characters, that is, half the number of matched characters in different order, for example, MARTHA and MARHTA are matched, but of the matched characters, T and H need to be transposed to change MARTHA into MARHTA, then T and H are matched characters in different order, and t=2/2=1.
Jaro-Winklerdstandom is a variant of JaroDistance. The Jaro-Winkler gives a higher score to the string that is identical for the beginning part, where a prefix p is defined, giving both strings, if the prefix part has a part of length iota that is identical, then Jaro-Winkler Distance is:
d w =d j +(ιp(1-d j ));
wherein d j Jaro Distance, which is two strings; iota is the same length of the prefix, but specifies a maximum of 4; p is a constant that adjusts the fraction, specifying that 0.25 cannot be exceeded, or d may occur w Greater than 1, winkler defines this constant as 0.1.
It should be noted that, unless specifically stated otherwise, the terms "first," "second," "third," and the like in the specification are used merely as a distinction between various components, elements, steps, etc. in the specification, and are not used to denote a logical or sequential relationship between various components, elements, steps, etc.
It will be appreciated that although the invention has been described above in terms of preferred embodiments, the above embodiments are not intended to limit the invention. Many possible variations and modifications of the disclosed technology can be made by anyone skilled in the art without departing from the scope of the technology, or the technology can be modified to be equivalent. Therefore, any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present invention still fall within the scope of the technical solution of the present invention.
Claims (5)
1. An insurance underwriting method based on text semantic processing is characterized by comprising the following steps:
a first step of: establishing a knowledge base based on insurance underwriting correlation;
and a second step of: receiving a disease name input by a user;
and a third step of: matching all synonymous diseases of the input disease names according to the synonymous relation in the related table knowledge base;
fourth step: according to the containing relation in the knowledge base of the correlation table, all the sub-diseases of the input disease name and corresponding synonyms are matched;
fifth step: according to the containing relation in the knowledge base of the correlation table, all father diseases of the disease names and corresponding synonyms are matched;
sixth step: aiming at the sub-diseases, matching all the sub-diseases of the sub-diseases and corresponding synonyms according to the inclusion relation in the related table knowledge base;
seventh step: aiming at the father disease, all father diseases of the father disease and corresponding synonyms are matched according to the inclusion relation in the knowledge base of the correlation table;
eighth step: according to the disease names of all synonymous diseases obtained in the third step, matching the name of the dangerous seed which cannot be applied according to the knowledge base of the dangerous seed which cannot be applied;
ninth step: according to all disease names obtained in the fourth step and the sixth step, matching suspected and administrable risk names according to a risk non-applicable disease knowledge base, and outputting disease interpretation and serious disease, medical risk and life risk nuclear insurance conclusion based on the disease names input by a user;
tenth step: extracting the disease names obtained in the third step to the seventh step, and matching possible health notification text contents by combining the health notification highlight table;
eleventh step: according to all disease names obtained in the fifth step and the seventh step, matching the name of the dangerous seed which cannot be applied according to the knowledge base of the dangerous seed which cannot be applied;
twelfth step: filtering repeated dangerous seeds in the results of the eighth step, the ninth step and the tenth step according to filtering rules to finally determine non-applicable dangerous seeds and suspected dangerous seeds, and matching the health notification rich text of each dangerous seed by combining a health notification rich text knowledge base;
thirteenth step: according to the finally determined non-applicable dangerous seed and suspected dangerous seed, determining all the remaining dangerous seeds in the dangerous seed library to be applicable to the dangerous seed, and based on the disease name input by the user, matching the names of the insurance products which can be applied, cannot be applied and suspected to be applicable to the dangerous seed according to the knowledge base related to the insurance, wherein the output of the insurance theory of the insurance nuclear insurance method based on text semantic processing further comprises: based on the disease name input by the user, outputting the interpretation of the disease and the check and protection conclusion of serious disease, medical risk and life risk.
2. The text semantic processing-based insurance underwriting method of claim 1, wherein the insurance underwriting-related knowledge base comprises: a disorder library in which disease names, disease interpretations, and warranty conclusions are stored in an associative manner;
a dangerous non-insurable disease knowledge base in which a dangerous identification code and a non-insurable disease name are stored in an associative manner;
a relational table knowledge base in which synonym relationships of disease names are stored in an associative manner, and inclusion relationships between disease names are stored;
a health notification rich text knowledge base in which a risk identification code and a health notification rich text format are stored in an associated manner; a health notification highlighting table in which disease names and health notification text content are stored in an associative manner.
3. The text semantic processing-based insurance verification method according to claim 1 or 2, wherein in the second step, a natural language processing model, namely a Jaro-Winkler score, is used for performing text similarity measurement on disease names input by a user, and texts with Jaro-Winkler score being greater than a preset threshold value of 0.6 are determined to be similar texts.
And matching the health notification text content with the health notification rich text to obtain the health notification text.
4. A text semantic processing based insurance underwriting method according to claim 1 or 2, wherein non-insurable related text content is highlighted in the health notification of each risk.
5. An insurance underwriting device based on text semantic processing, characterized by being used for realizing the insurance underwriting method based on text semantic processing according to one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010306058.4A CN111652737B (en) | 2020-04-17 | 2020-04-17 | Insurance verification method and apparatus based on text semantic processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010306058.4A CN111652737B (en) | 2020-04-17 | 2020-04-17 | Insurance verification method and apparatus based on text semantic processing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111652737A CN111652737A (en) | 2020-09-11 |
CN111652737B true CN111652737B (en) | 2023-12-22 |
Family
ID=72346017
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010306058.4A Active CN111652737B (en) | 2020-04-17 | 2020-04-17 | Insurance verification method and apparatus based on text semantic processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111652737B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102332142A (en) * | 2011-07-22 | 2012-01-25 | 大连亿创天地科技发展有限公司 | On-line insurance recommendation method and system |
CN105809549A (en) * | 2016-02-23 | 2016-07-27 | 平安科技(深圳)有限公司 | Medical affair intelligent insurance checking method and system |
JPWO2017013712A1 (en) * | 2015-07-17 | 2018-03-08 | 株式会社日立製作所 | Insurance information providing system and insurance information providing method |
CN108922633A (en) * | 2018-06-22 | 2018-11-30 | 北京海德康健信息科技有限公司 | A kind of disease name standard convention method and canonical system |
CN109064343A (en) * | 2018-08-13 | 2018-12-21 | 中国平安人寿保险股份有限公司 | Risk model method for building up, risk matching process, device, equipment and medium |
CN109285076A (en) * | 2018-02-07 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Intelligent core protects processing method, server and storage medium |
CN109829830A (en) * | 2018-12-22 | 2019-05-31 | 中国平安人寿保险股份有限公司 | A danger marketing method, device, electronic equipment and computer readable storage medium |
CN109994215A (en) * | 2019-04-25 | 2019-07-09 | 清华大学 | Disease automatic coding system, method, equipment and storage medium |
CN110070449A (en) * | 2019-03-15 | 2019-07-30 | 平安科技(深圳)有限公司 | Project kind matching process, device, computer equipment and storage medium |
CN110111207A (en) * | 2019-04-12 | 2019-08-09 | 中国平安人寿保险股份有限公司 | Core protects method and relevant device |
CN110993103A (en) * | 2019-11-28 | 2020-04-10 | 阳光人寿保险股份有限公司 | Method for establishing disease risk prediction model and method for recommending disease insurance product |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170069035A1 (en) * | 2009-03-06 | 2017-03-09 | Marilyn C. Quinlan | Systems and methods for matching consumer requests with insurance underwriter appetites |
US20100031134A1 (en) * | 2009-08-17 | 2010-02-04 | Netform Exchange, Inc. | System for electronically collecting and distributing health insurance information |
-
2020
- 2020-04-17 CN CN202010306058.4A patent/CN111652737B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102332142A (en) * | 2011-07-22 | 2012-01-25 | 大连亿创天地科技发展有限公司 | On-line insurance recommendation method and system |
JPWO2017013712A1 (en) * | 2015-07-17 | 2018-03-08 | 株式会社日立製作所 | Insurance information providing system and insurance information providing method |
CN105809549A (en) * | 2016-02-23 | 2016-07-27 | 平安科技(深圳)有限公司 | Medical affair intelligent insurance checking method and system |
CN109285076A (en) * | 2018-02-07 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Intelligent core protects processing method, server and storage medium |
CN108922633A (en) * | 2018-06-22 | 2018-11-30 | 北京海德康健信息科技有限公司 | A kind of disease name standard convention method and canonical system |
CN109064343A (en) * | 2018-08-13 | 2018-12-21 | 中国平安人寿保险股份有限公司 | Risk model method for building up, risk matching process, device, equipment and medium |
CN109829830A (en) * | 2018-12-22 | 2019-05-31 | 中国平安人寿保险股份有限公司 | A danger marketing method, device, electronic equipment and computer readable storage medium |
CN110070449A (en) * | 2019-03-15 | 2019-07-30 | 平安科技(深圳)有限公司 | Project kind matching process, device, computer equipment and storage medium |
CN110111207A (en) * | 2019-04-12 | 2019-08-09 | 中国平安人寿保险股份有限公司 | Core protects method and relevant device |
CN109994215A (en) * | 2019-04-25 | 2019-07-09 | 清华大学 | Disease automatic coding system, method, equipment and storage medium |
CN110993103A (en) * | 2019-11-28 | 2020-04-10 | 阳光人寿保险股份有限公司 | Method for establishing disease risk prediction model and method for recommending disease insurance product |
Non-Patent Citations (1)
Title |
---|
配置保险要"避坑";宋占军;《金融博览(财富)》;20190731(第7期);第56-59页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111652737A (en) | 2020-09-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7428487B2 (en) | Semi-automatic construction method for knowledge base of encyclopedia question answering system | |
US10565533B2 (en) | Systems and methods for similarity and context measures for trademark and service mark analysis and repository searches | |
US10503828B2 (en) | System and method for answering natural language question | |
US11182435B2 (en) | Model generation device, text search device, model generation method, text search method, data structure, and program | |
US9483557B2 (en) | Keyword generation for media content | |
CN110765257A (en) | Intelligent consulting system of law of knowledge map driving type | |
US9058308B2 (en) | System and method for identifying text in legal documents for preparation of headnotes | |
US9251133B2 (en) | Approximate named-entity extraction | |
US20090259670A1 (en) | Apparatus and Method for Conditioning Semi-Structured Text for use as a Structured Data Source | |
JP2008511075A (en) | System and method for searching legal points | |
JPWO2005096182A1 (en) | Information extraction system | |
CN111104488B (en) | Method, device and storage medium for integrating retrieval and similarity analysis | |
CN104063497A (en) | Viewpoint processing method and device and searching method and device | |
US20140289260A1 (en) | Keyword Determination | |
CN110569349A (en) | Big data-based method, system, equipment and storage medium for pushing articles for education | |
Goldin et al. | Abstfinder, a prototype abstraction finder for natural language text for use in requirements elicitation: design, methodology, and evaluation | |
CN111652737B (en) | Insurance verification method and apparatus based on text semantic processing | |
Glöckner | University of Hagen at CLEF 2007: Answer Validation Exercise. | |
Lecoeuche | Finding comparatively important concepts between texts | |
US20180005300A1 (en) | Information presentation device, information presentation method, and computer program product | |
US20200257735A1 (en) | System and method for phrase search within document section | |
US20210216721A1 (en) | System and method to quantify subject-specific sentiment | |
Patrick et al. | Developing SNOMED CT subsets from clinical notes for intensive care service | |
CN107203616A (en) | The mask method and device of video file | |
Finch et al. | TagLine: information extraction for semi-structured text in medical progress notes |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |