CN113987113B - Multi-station naming service fusion method, device, storage medium and server - Google Patents
Multi-station naming service fusion method, device, storage medium and server Download PDFInfo
- Publication number
- CN113987113B CN113987113B CN202110710567.8A CN202110710567A CN113987113B CN 113987113 B CN113987113 B CN 113987113B CN 202110710567 A CN202110710567 A CN 202110710567A CN 113987113 B CN113987113 B CN 113987113B
- Authority
- CN
- China
- Prior art keywords
- behavior
- name
- names
- alignment
- legal
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a multi-station naming service fusion method, a device, a storage medium and a server; wherein the method comprises the following steps: s1: acquiring legal behavior text to be named; s2: automatically converting the legal action text to be named into a first legal action text, a second legal action text … … and an Nth legal action text supported by each of N naming servers; n is more than or equal to 2; s3: the N naming servers output first behavior names and second behavior names … … N behavior names according to the first legal behavior text and the second legal behavior text … … N legal behavior text supported by the N naming servers respectively; s4: performing behavior name alignment processing on the first behavior name and the second behavior name … … Nth behavior name to obtain a first alignment behavior name and a second alignment behavior name … … Nth alignment behavior name; s5: and automatically fusing and outputting the standard behavior names according to the first alignment behavior name and the N-th alignment behavior name of the second alignment behavior name … …. The application solves the problem that the behavior name forms with different levels and different granularities are difficult to fuse when being output, and achieves the purpose of intelligent naming judgment.
Description
Technical Field
The application relates to the technical field of legal behavior naming, in particular to a multi-station naming service fusion method, a device, a storage medium and a server.
Background
The computer nominated quantitative service is applied to judicial practice as an artificial intelligence legal tool, and can provide references for judicial judgment so as to improve efficiency. Currently, sites supporting naming service are widely deployed in public networks, and naming algorithms adopted by each naming service site and depending training data sets may be different, so that final naming results are not identical. To improve accuracy, a user may use naming services provided by two or more sites when he/she needs to sign a legal action fact, and fuse the results of their naming.
However, the current convergence of multisource naming services has the following drawbacks and disadvantages:
1. legal acts fact text entry requires different:
typically, the nomination service server requires the input of a literal description of legal facts, but some other servers may require the input of structured referee documents, prosecution documents, or prosecution comments of public security, etc. In practical use, it is difficult for a user to understand the input format requirements of each server, and usually only text in a certain format familiar or available to the user is used as input, and format conversion is not manually performed according to the format requirements of the server.
2. The format of the behavior name output is not standard:
the means of realizing the name server are different, the behavior name is output more randomly, and the method is mainly characterized in that:
1. text form difference of behavior name output
For the same behavior name, the texts output by different servers are different, and if the texts are used for "kidnapping", the texts are used for "kidnapping behavior"; for convenience of subsequent information processing, a specific symbol such as "[ forging, changing, buying and selling ] institutions [ documents, certificates, seals ]" has been added to some servers, and the entities in parallel relationship are bracketed with square brackets.
2. Different numbers of supported behavior names
Some servers only implement automatic naming of full behavioral names, others only support partial common behavioral names. The names of behaviors which are not supported by the server cannot be named together.
3. Granularity of behavior names is different
The different levels of behavior name forms at different granularities result in a difficult fusion at output.
Disclosure of Invention
The application aims to provide a multi-site naming service fusion method, a device, a storage medium and a server, which solve the problems of how to automatically adapt different servers under the condition that a user provides a format input and how to automatically fuse and output a standard behavior name under the condition that the behavior names of all sites are inconsistent.
The application is realized by the following technical scheme:
a multi-station naming service fusion method comprises the following steps:
s1: acquiring legal behavior text to be named;
s2: automatically converting the legal action text to be named into a first legal action text, a second legal action text … … and an Nth legal action text supported by each of N naming servers; n is more than or equal to 2;
s3: the N naming servers output first behavior names and second behavior names … … N behavior names according to the first legal behavior text and the second legal behavior text … … N legal behavior text supported by the N naming servers respectively;
s4: performing behavior name alignment processing on the first behavior name and the second behavior name … … Nth behavior name to obtain a first alignment behavior name and a second alignment behavior name … … Nth alignment behavior name;
s5: and automatically fusing and outputting the standard behavior names according to the first alignment behavior name and the N-th alignment behavior name of the second alignment behavior name … ….
According to the application, legal behavior texts input by a user are received, the legal behavior texts are automatically converted into legal behavior texts supported by N naming servers, the N naming servers output a plurality of behavior names in a matching mode according to the legal behavior texts supported by the N naming servers, the plurality of behavior names are uniformly identified and named by adopting a URI identification system, and finally recommended behavior names are fused and output.
Further, in S5, the automatically merging and outputting the canonical action name according to the first alignment action name, the second alignment action name … … and the nth alignment action name includes:
if the first alignment behavior name and the second alignment behavior name … … are the same, or only one effectively returned behavior name is adopted, the legal behavior name is directly output;
if different behavior names exist in the first alignment behavior names and the N alignment behavior names of the second alignment behavior names … …, and the legal behavior names in the different behavior names have different granularity, merging the behavior names based on the superior behavior names, and outputting the superior behavior names;
if different behavior names exist in the first alignment behavior names and the N alignment behavior names of the second alignment behavior names … …, and the condition that legal behavior names are different in granularity does not exist in the different behavior names, the recommended behavior names are output.
Further, in S4, the performing the action name alignment process on the first action name and the second action name … … nth action name specifically refers to unifying the first action name and the second action name … … nth action name with standardized texts.
Further, the standardized text includes text identified using a uniform resource identifier, URI.
Further, the outputting the recommended action name includes outputting the recommended action name by a machine learning or voting method.
Further, in S1, the method further includes obtaining a training data set covering the full action name, and testing the input formats supported by the N naming servers and the supported action names.
A multi-site naming service convergence device, comprising:
the obtaining module is used for obtaining legal action texts to be named;
the format conversion module is used for automatically converting legal action texts to be named into first legal action texts, second legal action texts … … Nth legal action texts supported by the N naming servers respectively; n is more than or equal to 2;
the behavior name acquisition module is used for outputting a first behavior name and a second behavior name … … N behavior name by the N naming servers according to the first legal behavior text and the second legal behavior text … … N legal behavior text supported by the N naming servers respectively;
the behavior name alignment module is used for performing behavior name alignment processing on the first behavior name and the second behavior name … … Nth behavior name to obtain a first alignment behavior name and a second alignment behavior name … … Nth alignment behavior name;
and the behavior name fusion module is used for automatically fusing and outputting the standard behavior name according to the first alignment behavior name and the N alignment behavior name of the second alignment behavior name … ….
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements a multi-site naming service fusion method as described above.
A server, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: and executing the multi-station naming service fusion method.
Compared with the prior art, the application has the following advantages and beneficial effects:
according to the multi-station naming service fusion method, device, storage medium and server, legal behavior texts input by a user are received, the legal behavior texts supported by N naming servers are automatically converted into legal behavior texts supported by the N naming servers, the N naming servers output a plurality of behavior names in a matching mode according to the legal behavior texts supported by the N naming servers, the plurality of behavior names are uniformly marked and named by a URI marking system, and finally recommended behavior names are fused and output, so that the problem that behavior name forms with different levels and different granularities are difficult to fuse in output is solved, and the purpose of intelligent naming judgment is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:
FIG. 1 is a flow diagram of a multi-site naming service fusion method of the present application;
FIG. 2 is a flow chart of a method for acquiring multi-station fixed-name data according to the present application;
FIG. 3 is a schematic diagram of a behavior name granularity merging and behavior name recommendation flow according to the present application;
FIG. 4 is a schematic diagram of a feed-back submitted to a nominated server in a variety of legal documents formats.
FIG. 5 is a schematic diagram of data submitted to a naming server for feedback under a variety of behavioral names.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present application, the present application will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present application and the descriptions thereof are for illustrating the present application only and are not to be construed as limiting the present application.
Examples
A multi-station naming service fusion method comprises the following steps:
s1: acquiring legal behavior text to be named;
s2: automatically converting the legal action text to be named into a first legal action text, a second legal action text … … and an Nth legal action text supported by each of N naming servers; n is more than or equal to 2;
s3: the N naming servers output first behavior names and second behavior names … … N behavior names according to the first legal behavior text and the second legal behavior text … … N legal behavior text supported by the N naming servers respectively;
s4: performing behavior name alignment processing on the first behavior name and the second behavior name … … Nth behavior name to obtain a first alignment behavior name and a second alignment behavior name … … Nth alignment behavior name;
s5: and automatically fusing and outputting the standard behavior names according to the first alignment behavior name and the N-th alignment behavior name of the second alignment behavior name … ….
The automatic merging and outputting of the canonical action name according to the first alignment action name, the second alignment action name … … and the nth alignment action name comprises:
if the first alignment behavior name and the second alignment behavior name … … are the same, or only one effectively returned behavior name is adopted, the legal behavior name is directly output;
if different behavior names exist in the first alignment behavior names and the N alignment behavior names of the second alignment behavior names … …, and the legal behavior names in the different behavior names have different granularity, merging the behavior names based on the superior behavior names, and outputting the superior behavior names;
if different behavior names exist in the first alignment behavior names and the N alignment behavior names of the second alignment behavior names … …, and the condition that legal behavior names are different in granularity does not exist in the different behavior names, the recommended behavior names are output.
In the step, if a plurality of nominated servers return the same legal action names or only one valid server returns, the legal action names are directly output; if the behavior names returned by the naming servers are inconsistent and legal behavior names are different in granularity, merging the behavior names based on the superior behavior names, and outputting the superior behavior names; if the behavior names returned by the naming servers are inconsistent and the legal behavior names are not different in granularity, outputting the recommended behavior names by adopting a machine learning or voting method.
The application adopts the hierarchy numbering to solve the problem of inconsistent granularity of the behavior names; for example: the legal laws of criminal law are marked in a layering manner according to 4 layers of 'braid, chapter, strip and money', the middle is connected by 'number', and 'X.2.1.103.2' represents 'criminal law 2, chapter 1, 103 and 2' by taking the 103 th criminal law as an example. Behavior names of different granularities, as shown in table 1:
the process of aligning the first behavior names and the second behavior names … … and the nth behavior names specifically refers to that the first behavior names and the second behavior names … … and the nth behavior names are uniformly represented by standardized texts. The standardized text includes text identified using a uniform resource identifier, URI.
The individual act/behavior names in criminal law are named with uniform resource identifiers URIs, each term having a unique identification number, the identification system may use, but is not limited to Guid, handle, DOI, or local URI identification, such as: "LAW0000251" with running water number added by letter.
The outputting of the recommended action name comprises outputting the recommended action name by adopting a machine learning or voting method.
In the S1 of the method of the application, the method further comprises the steps of obtaining a training data set covering the full behavior names, testing the input formats supported by N naming servers and the supported behavior names, wherein the method comprises the following steps: (1) Automatic markup server supported/unsupported input formats: as shown in fig. 4, the site is submitted in various formats such as legal facts, judge documents, prosecution documents, etc., and the input format supported by the site is determined according to the returned result and recorded in a named site knowledge base. (2) Automatic labeling server supported/unsupported behavior names: as shown in fig. 5, the site is submitted with data of each behavior name, and according to the statistical data of the returned result, which behavior names are supported or not supported by the site is determined and recorded in a named site knowledge base.
A multi-site naming service convergence device, comprising:
the obtaining module is used for obtaining legal action texts to be named;
the format conversion module is used for automatically converting legal action texts to be named into first legal action texts, second legal action texts … … Nth legal action texts supported by the N naming servers respectively; n is more than or equal to 2;
the behavior name acquisition module is used for outputting a first behavior name and a second behavior name … … N behavior name by the N naming servers according to the first legal behavior text and the second legal behavior text … … N legal behavior text supported by the N naming servers respectively;
the behavior name alignment module is used for performing behavior name alignment processing on the first behavior name and the second behavior name … … Nth behavior name to obtain a first alignment behavior name and a second alignment behavior name … … Nth alignment behavior name;
and the behavior name fusion module is used for automatically fusing and outputting the standard behavior name according to the first alignment behavior name and the N alignment behavior name of the second alignment behavior name … ….
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the multi-site naming service fusion method described above.
A server, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: and executing the multi-station naming service fusion method.
When a named service site is newly added, the application uses a Resource Description Framework (RDF) to describe the service content and service capability of the site. The method comprises the basic information of the IP of the site, the service port, the Web API/RESTful interface, the adopted algorithm, the scale of the training data set, the region and the like.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (5)
1. The multi-station naming service fusion method is characterized by comprising the following steps:
s1: acquiring legal behavior text to be named;
s2: automatically converting the legal action text to be named into a first legal action text, a second legal action text … … and an Nth legal action text supported by each of N naming servers; the N is more than or equal to 2;
s3: the N naming servers output first behavior names and second behavior names … … N behavior names according to the first legal behavior text and the second legal behavior text … … N legal behavior text supported by the N naming servers respectively;
s4: performing behavior name alignment processing on the first behavior name and the second behavior name … … Nth behavior name to obtain a first alignment behavior name and a second alignment behavior name … … Nth alignment behavior name;
s5: automatically fusing and outputting a standard behavior name according to the first alignment behavior name and the N-th alignment behavior name of the second alignment behavior name … …; in S5, the automatically merging and outputting the canonical behavior name according to the first alignment behavior name, the second alignment behavior name … … and the nth alignment behavior name includes:
if the first alignment behavior name and the second alignment behavior name … … are the same, or only one effectively returned behavior name is adopted, the legal behavior name is directly output;
if different behavior names exist in the first alignment behavior names and the N alignment behavior names of the second alignment behavior names … …, and the legal behavior names in the different behavior names have different granularity, merging the behavior names based on the superior behavior names, and outputting the superior behavior names;
if different behavior names exist in the first alignment behavior names and the N alignment behavior names of the second alignment behavior names … …, and the condition that legal behavior names are different in granularity does not exist in the different behavior names, the recommended behavior names are output.
2. The multi-site naming service fusion method according to claim 1, wherein in S4, the performing the behavior name alignment process on the first behavior name and the second behavior name … … nth behavior name is specifically to uniformly express the first behavior name and the second behavior name … … nth behavior name in standardized text.
3. The multi-site naming service convergence method of claim 2 wherein the standardized text comprises text identified using a uniform resource identifier URI.
4. The multi-site naming service fusion method of claim 1, wherein outputting the recommended action name includes outputting the recommended action name using machine learning or voting.
5. The method of claim 1, wherein in S1, further comprising obtaining a training dataset covering full action names, and testing the input formats supported by the N naming servers and the action names supported by the N naming servers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110710567.8A CN113987113B (en) | 2021-06-25 | 2021-06-25 | Multi-station naming service fusion method, device, storage medium and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110710567.8A CN113987113B (en) | 2021-06-25 | 2021-06-25 | Multi-station naming service fusion method, device, storage medium and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113987113A CN113987113A (en) | 2022-01-28 |
| CN113987113B true CN113987113B (en) | 2023-09-22 |
Family
ID=79734994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110710567.8A Active CN113987113B (en) | 2021-06-25 | 2021-06-25 | Multi-station naming service fusion method, device, storage medium and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113987113B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704474A (en) * | 2016-08-08 | 2018-02-16 | 华为技术有限公司 | Attribute alignment schemes and device |
| CN109308311A (en) * | 2018-09-05 | 2019-02-05 | 广州小楠科技有限公司 | A kind of multi-source heterogeneous data fusion system |
| CN111581976A (en) * | 2020-03-27 | 2020-08-25 | 平安医疗健康管理股份有限公司 | Method and apparatus for standardizing medical terms, computer device and storage medium |
| CN111696635A (en) * | 2020-05-13 | 2020-09-22 | 平安科技（深圳）有限公司 | Disease name standardization method and device |
| CN112084781A (en) * | 2020-09-10 | 2020-12-15 | 腾讯科技（深圳）有限公司 | Standard term determination method, device and storage medium |
| CN112183100A (en) * | 2020-10-12 | 2021-01-05 | 浪潮天元通信信息系统有限公司 | Multi-source homonymous expert disambiguation method |
| CN112417214A (en) * | 2020-11-02 | 2021-02-26 | 中关村科学城城市大脑股份有限公司 | Fusion method and system for multi-source heterogeneous data of urban brain scene |
-
2021
- 2021-06-25 CN CN202110710567.8A patent/CN113987113B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704474A (en) * | 2016-08-08 | 2018-02-16 | 华为技术有限公司 | Attribute alignment schemes and device |
| CN109308311A (en) * | 2018-09-05 | 2019-02-05 | 广州小楠科技有限公司 | A kind of multi-source heterogeneous data fusion system |
| CN111581976A (en) * | 2020-03-27 | 2020-08-25 | 平安医疗健康管理股份有限公司 | Method and apparatus for standardizing medical terms, computer device and storage medium |
| CN111696635A (en) * | 2020-05-13 | 2020-09-22 | 平安科技（深圳）有限公司 | Disease name standardization method and device |
| CN112084781A (en) * | 2020-09-10 | 2020-12-15 | 腾讯科技（深圳）有限公司 | Standard term determination method, device and storage medium |
| CN112183100A (en) * | 2020-10-12 | 2021-01-05 | 浪潮天元通信信息系统有限公司 | Multi-source homonymous expert disambiguation method |
| CN112417214A (en) * | 2020-11-02 | 2021-02-26 | 中关村科学城城市大脑股份有限公司 | Fusion method and system for multi-source heterogeneous data of urban brain scene |
Non-Patent Citations (3)
| Title |
|---|
| Hai-Yun Xu， et al.Multi-source data fusion study in scientometrics.《Scientometrics》.2017,第773-792页. * |
| 温书豪，黄学军等.刑事案件上诉原因文本挖掘--基于二审文书数据.《情报工程》.2021,第7卷(第1期),第103-114页. * |
| 王锦华等.基于多源数据融合的军事医学机构名称规范研究.《中华医学图书情报杂志》.2020,第29卷(第2期),第52-57页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113987113A (en) | 2022-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108337236A (en) | A kind of gRPC call methods and device based on Protobuf and HTTP/1.1 | |
| JP2005284334A (en) | Web page update notification method and apparatus | |
| CN103095823A (en) | Object description method and object information interaction system in Internet of Things system | |
| US7869585B2 (en) | Declarations for transformations within service sequences | |
| El Machkouri et al. | Asymptotic normality of kernel estimates in a regression model for random fields | |
| US20190163699A1 (en) | Method and apparatus for information interaction | |
| US8601001B2 (en) | Selectively structuring a table of contents for accessing a database | |
| CN108279987A (en) | The method for edition management and device of application program | |
| Zhu et al. | Web-based construction document processing via malleable frame | |
| CN101482875A (en) | Information query method and apparatus | |
| CN107870989A (en) | webpage generating method and terminal device | |
| Chujai et al. | On transforming the ER model to ontology using protégé OWL tool | |
| Abel et al. | Linkage, aggregation, alignment and enrichment of public user profiles with Mypes | |
| CN107220274A (en) | One kind visualization data-interface fairground implementation method | |
| CN113486187A (en) | Buddhism knowledge graph construction method, device, equipment and storage medium | |
| CN112667733A (en) | Data warehouse data importing method and system | |
| CN104008042A (en) | UI (user interface) automated testing method, system and device | |
| CN113987113B (en) | Multi-station naming service fusion method, device, storage medium and server | |
| CN105516269B (en) | The configuration method of application and the configuration device of application | |
| CN103092982B (en) | Based on the information service system of multi views business model | |
| CN110457527B (en) | XML message comparison method and system | |
| CN102456070B (en) | Indexing unit and search method | |
| CN106209936A (en) | Third party system data capture method and device | |
| US20190095542A1 (en) | Method and system of dynamic website creation through url parameter analysis | |
| CN111913821B (en) | Method for realizing cross-data-source real-time data stream production consumption |
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 |