CN110377819A - Arbitrator's recommended method, device and computer equipment based on big data - Google Patents
Arbitrator's recommended method, device and computer equipment based on big data Download PDFInfo
- Publication number
- CN110377819A CN110377819A CN201910520069.XA CN201910520069A CN110377819A CN 110377819 A CN110377819 A CN 110377819A CN 201910520069 A CN201910520069 A CN 201910520069A CN 110377819 A CN110377819 A CN 110377819A
- Authority
- CN
- China
- Prior art keywords
- arbitrator
- case
- information
- recommendation
- mark
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004590 computer program Methods 0.000 claims description 25
- 238000012216 screening Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 description 14
- 238000010586 diagram Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 210000000056 organ Anatomy 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 108090000623 proteins and genes Proteins 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 240000004282 Grewia occidentalis Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
- G06Q50/182—Alternative dispute resolution
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application involves a kind of arbitrator's recommended method, device, computer equipment and storage medium based on big data.The described method includes: receiving the retrieval request of user terminal uploads, case mark and arbitrator's search condition are carried in the retrieval request;Corresponding case information is obtained according to case mark;The arbitrator's information being consistent with arbitrator's search condition is retrieved by big data platform;It include that arbitrator identifies in arbitrator's information;Matching primitives will be carried out with the arbitrator's information retrieved to the case information using recommended models, recommendation index corresponding with arbitrator mark is obtained according to matching result;It is screened according to the multiple arbitrator's marks of the recommendation exponent pair, at least one arbitrator filtered out is identified into corresponding arbitrator's information and is sent to the user terminal.The arbitrator being adapted with case can quickly be selected convenient for party using this method.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of arbitrator's recommended method based on big data, dress
It sets, computer equipment and storage medium.
Background technique
Arbitration as it is a kind of it is non-tell settling entanglements mode, it is different from form of action.Arbitration is that party will voluntarily tell and strive thing
By the Dispute resolutions for submitting to neutral third party judge.The member of arbitral court is by both parties in arbitration organ
Select or entrust arbitration commission director specified in arbitrator's register of engagement.If party does not know arbitrator,
Suitable arbitrator can not then be selected.Therefore, how quickly and effectively to select to be adapted with case in a large amount of arbitrator's information
Arbitrator become a technical problem needing to solve at present.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind can quickly have in a large amount of arbitrator's information
Arbitral arbitrator's recommended method, device, computer equipment and the storage based on big data that effect selection is adapted with case
Medium.
A kind of arbitrator's recommended method based on big data, which comprises
The retrieval request of user terminal uploads is received, case mark is carried in the retrieval request with arbitrator and retrieves item
Part;
Corresponding case information is obtained according to case mark;
The arbitrator's information being consistent with arbitrator's search condition is retrieved by big data platform;Arbitrator's information
In include arbitrator identify;
Using recommended models matching primitives will be carried out with the arbitrator's information retrieved to the case information, according to
Matching result obtains recommendation index corresponding with arbitrator mark;
It is screened according to the multiple arbitrator's marks of the recommendation exponent pair, at least one arbitrator filtered out is identified
Corresponding arbitrator's information is sent to the user terminal.
It in one of the embodiments, include posterior infromation in arbitrator's information;It is described to utilize recommended models be right
It is described state case information and arbitrator's information and carry out matching primitives include:
Case key message is extracted in the case information;
The case key message and the posterior infromation are input to the recommended models;
The case key message and the posterior infromation are subjected to matching primitives by the recommended models.
In one of the embodiments, the method also includes:
It obtains the case and identifies corresponding case type;
It is filtered out in the corresponding history award of the arbitrator and the consistent history award of the case type;Sieve
It include multiple ruling factors in the history award selected;
The case key message is carried out matching primitives with the posterior infromation by the recommended models
The ruling factor is matched with the case key message by the recommended models, obtains multiple ruling
The corresponding recommendation of the factor;
The corresponding recommendation of multiple ruling factors is added up, recommendation corresponding with arbitrator mark is obtained and refers to
Number.
In one of the embodiments, the method also includes:
Obtain the portrait factor of multiple dimensions;
According to the portrait factor in the corresponding portrait information of arbitrator's information extraction filtered out;
Using the portrait information and the portrait factor, corresponding arbitrator's portrait is generated;
The arbitrator filtered out described in corresponding to that the arbitrator is drawn a portrait is sent to the user terminal.
In one of the embodiments, the method also includes:
Arbitral court is formed using the arbitrator of user terminal selecting;
After forming arbitral court, approximate case is searched in big data platform using the case information;
The approximate case is sent to the corresponding arbitration terminal of the arbitral court.
A kind of arbitrator's recommendation apparatus based on big data, described device include:
Module is obtained, for obtaining case mark, corresponding case information and arbitration are obtained according to case mark
Member's search condition;
Retrieval module, for retrieving the arbitrator's information being consistent with arbitrator's search condition by big data platform;
It include that arbitrator identifies in arbitrator's information;
Matching module, by that will be carried out based on matching to the case information and arbitrator's information using recommended models
It calculates, obtains recommendation index corresponding with arbitrator mark;
Screening module will filter out at least for being screened according to the multiple arbitrator's marks of the recommendation exponent pair
One arbitrator identifies corresponding arbitrator's information and is sent to the user terminal.
It in one of the embodiments, include posterior infromation in arbitrator's information;The matching module is also used to
Case key message is extracted in the case information;The case key message and the posterior infromation are input to the recommendation
Model;The case key message and the posterior infromation are subjected to matching primitives by the recommended models.
The screening module is also used to obtain the case and identifies corresponding case type in one of the embodiments,;
It is filtered out in the corresponding history award of the arbitrator and the consistent history award of the case type;What is filtered out goes through
It include multiple ruling factors in history award;The matching module be also used to by the recommended models by the ruling factor with
The case key message is matched, and the corresponding recommendation of multiple ruling factors is obtained;It pushes away multiple ruling factors are corresponding
It recommends value to add up, obtains recommendation index corresponding with arbitrator mark.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes the step in above-mentioned each embodiment of the method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step in above-mentioned each embodiment of the method is realized when row.
Above-mentioned arbitrator's recommended method, device, computer equipment and storage medium based on big data is flat by big data
Platform retrieves the multiple arbitrator's information being consistent with arbitrator's search condition, by recommended models to case information and the arbitrator
Information carries out matching primitives, obtains each arbitrator and identifies corresponding recommendation index.By being screened to recommendation index, thus
The available multiple arbitrators being adapted with current arbiter case.The multiple arbitrators filtered out are identified into corresponding arbitrator
After information is sent to the user terminal, and then it can be convenient party or Arbitration Committee director quickly selects suitable arbitrator.
Detailed description of the invention
Fig. 1 is the application scenario diagram of arbitrator's recommended method based on big data in one embodiment;
Fig. 2 is the flow diagram of arbitrator's recommended method based on big data in one embodiment;
Fig. 3 is the flow diagram of arbitrator's recommended method based on big data in another embodiment;
Fig. 4 is the structural block diagram of arbitrator's recommendation apparatus based on big data in one embodiment;
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Arbitrator's recommended method provided by the present application based on big data, can be applied to application environment as shown in Figure 1
In.Wherein, user terminal 102 is communicated by network with server 104.Wherein, user terminal 102 can be, but not limited to be
Various personal computers, laptop, smart phone, tablet computer and portable wearable device, server 104 can be used
The server cluster of independent server either multiple servers composition is realized.
In one embodiment, as shown in Fig. 2, a kind of arbitrator's recommended method based on big data is provided, with the party
Method is applied to be illustrated for the server in Fig. 1, comprising the following steps:
Step 202, the retrieval request of user terminal uploads is received, case mark is carried in retrieval request and is examined with arbitrator
Rope condition obtains corresponding case information according to case mark.
Online arbitration system has been run on server.Party can (the corresponding user of people be whole at that time by user terminal
End is referred to as first terminal) account of the online arbitration system of registration, utilize the account to log in online arbitration system.First eventually
End can upload request for arbitration request to online arbitration system.Server is requested to return to first terminal and be arbitrated according to request for arbitration
Apply for the page.The request for arbitration page may include a variety of pages, select the page and information enrollment page for example including arbitration organ
Face etc..It is that current arbiter case is arbitrated online that first terminal can choose arbitration organ in request for arbitration page.Party
It can choose corresponding group of front yard mode of arbitral court by first terminal, group front yard mode includes system of sole judge proceedings and collegiate system.
When using system of sole judge proceedings, user terminal (the corresponding user terminal of Arbitration Committee director can be passed through by Arbitration Committee director
It is referred to as second terminal) an adaptable arbitrator of specified and current arbiter case.When using collegiate system, Ke Yiyou
Arbitration Committee director passes through first by the specified multidigit arbitrator being adapted with current arbiter case of second terminal or party
The specified multidigit arbitrator being adapted with current arbiter case of terminal.First terminal or second terminal can be sent to server
Retrieval request carries arbitrator's search condition in retrieval request.First terminal and second terminal may be collectively referred to as user's end
End.Arbitrator's search condition includes arbitrator nationality, speciality, existing residence, working language, arbitration length of service, educational background, specially
Industry, industry type etc..
Step 204, the arbitrator's information being consistent with arbitrator's search condition is retrieved by big data platform;Arbitrator's information
In include arbitrator identify.
Step 206, matching primitives will be carried out with the arbitrator's information retrieved to case information using recommended models, according to
Matching result obtains recommendation index corresponding with arbitrator's mark.
Step 208, it is screened according to the multiple arbitrators' marks of recommendation exponent pair, at least one arbitrator that will be filtered out
Corresponding arbitrator's information is identified to be sent to the user terminal.
Crawler technology is first passed through in big data platform in advance and has crawled the arbitral relevant information of multidigit in multiple websites.Clothes
Business device searches for the multidigit arbitrator's information for meeting arbitrator's search condition in big data platform.In the arbitrator's information searched
It further include arbitration posterior infromation other than including above-mentioned field contents.Arbitrate includes arbitration case type, hair in posterior infromation
Radix Rehmanniae, accumulation process caseload, is good at case type etc. at the case-involving amount of money.
Server extracts case key message in case information, case key message include case by, the fact, evidence, tell
Dispute request etc..Recommended models, server calls recommended models, by case key message and arbitrator have been pre-established in service
Posterior infromation be input to recommended models, case key message and posterior infromation are carried out matching primitives by recommended models, according to
Each arbitrator, which is obtained, with result identifies corresponding recommendation index.Wherein, matching result can be matching similarity.Further
, when matching similarity reaches threshold value, server screens multiple matching results according to matching similarity, after screening
In matching result, corresponding recommendation index is identified using matching similarity as each arbitrator.
Multiple recommendation indexes are ranked up and screen to arbitrator by server.The arbitrator filtered out can be more
It is a.For example, the 1-7 forward arbitrator that sort can be filtered out.Server identifies the multiple arbitrators filtered out corresponding
Arbitrator's information is sent to the user terminal, i.e. the corresponding first terminal of party or the corresponding second terminal of Arbitration Committee director.
Specifically, user is whole after the corresponding arbitrator's information of the arbitrator filtered out mark can be sent to the user terminal by server
End is by recommending interface to be shown.Party or Arbitration Committee director can select it in recommending interface by user terminal
In 2-3 people be compared.Server can be enumerated selected arbitral main information in interface, so as to
It is compared.Main contents include arbitration experience, basic information and loyalty information etc..After comparison, user terminal can will be selected
Arbitrator be added in candidate list.User terminal can be selected with current arbiter case in candidate list to applicable secondary
It reduces the staff.
In the present embodiment, the multiple arbitrator's information being consistent with arbitrator's search condition are retrieved by big data platform, are led to
It crosses recommended models and matching primitives is carried out to case information and arbitrator's information, obtain the corresponding recommendation of each arbitrator's mark and refer to
Number.By being screened to recommendation index, it is hereby achieved that the multiple arbitrators being adapted with current arbiter case.It will screening
After the corresponding arbitrator's information of multiple arbitrators mark out is sent to the user terminal, and then it can be convenient party or arbitration
Committee director quickly selects suitable arbitrator.
In one embodiment, matching primitives packet will be carried out with arbitrator's information to case information is stated using recommended models
It includes: extracting case key message in case information;Case key message and posterior infromation are input to recommended models, by pushing away
It recommends model and case key message and posterior infromation is subjected to matching primitives.
Server can call recommended models by case key message, including case by, the fact, evidence, claims etc. with
Arbitral posterior infromation is matched.Specifically, server can obtain case type, party in case key message
Address, economic loss amount of money etc..By recommended models by case type, party address, economic loss amount of money etc. as matching
The factor and arbitral posterior infromation include arbitration case type, spot, the case-involving amount of money, accumulation process caseload, are good at
Case type etc. is matched.If successful match, the corresponding available corresponding recommendation of matching attribute is pushed away multiple
It recommends value to add up, obtains arbitrator and identify corresponding recommendation index.From there through recommended models, symbol can quickly be calculated
Close the arbitral recommendation index of each of arbitrator's search condition.
When carrying out matching primitives, server can use keyword and be matched, and also can use vector and is matched.
When being matched using keyword, server can be believed according to the corresponding keyword of above-mentioned matching attribute and arbitral experience
Keyword in breath is matched.If keyword matches, the corresponding available corresponding recommendation of matching attribute will be more
A recommendation adds up, and obtains arbitrator and identifies corresponding recommendation index.
When being matched using vector, server can also extract case type, party in case key message
The Partial key information extracted is converted to the case vector of current case by address, economic loss amount of money etc..Big data platform
The corresponding experience vector of multiple arbitral posterior infromations can also be stored in advance.Server can be by the case of current case
Vector is input to recommended models, is carried out multiple experience vectors in case vector and big data platform by recommended models
Match, recommendation index corresponding with arbitrator's mark is obtained according to matching similarity.Thus, it is possible to effectively improve arbitrator to recommend to refer to
Several computational efficiencies.
It further, can also include arbitral history award in arbitral posterior infromation.In order to further mention
The accuracy that height recommends index-matched to calculate, server can also be matched using history award.In one embodiment,
As shown in figure 3, providing a kind of arbitrator's recommended method based on big data, specifically comprise the following steps:
Step 302, case mark is obtained, corresponding case information is obtained according to case mark and arbitrator retrieves item
Part.
Step 304, the arbitrator's information being consistent with arbitrator's search condition is retrieved by big data platform;Arbitrator's information
In include arbitrator identify.
Step 306, it obtains case and identifies corresponding case type;Filtered out in the corresponding history award of arbitrator with
The consistent history award of case type;It include multiple ruling factors in the history award filtered out.
Step 308, case key message is extracted in case information, it is by recommended models that the ruling factor and case is crucial
Information is matched, and the corresponding recommendation of multiple ruling factors is obtained.
Step 310, the corresponding recommendation of multiple ruling factors is added up, obtains recommendation corresponding with arbitrator's mark
Index.
Step 312, it is screened according to the multiple arbitrators' marks of recommendation exponent pair, at least one arbitrator that will be filtered out
Corresponding arbitrator's information is identified to be sent to the user terminal.
After server retrieves the multiple arbitrator's information being consistent with arbitrator's search condition by big data platform,
Server obtains the case type of current arbiter case, is sieved according to the case type to multiple arbitral history awards
Choosing, screening and the consistent history award of the case type.It include multiple ruling factors in history award, the ruling factor includes
Case by, the fact, evidence, claims, court verdict etc..Corresponding multiple ruling keywords are arranged in each ruling factor.
Server can extract case key message in case information, including case by, the fact, evidence, claims etc..
Also corresponding case keyword can be set in case key message.It is corresponding multiple to each ruling factor by recommended models
Ruling keyword is matched with case keyword, if ruling keyword and case keyword are same or similar, and quantity is more than threshold
Value, then this thinks that the ruling factor matches, and can recorde the corresponding recommendation of the factor, will be with multiple in a history award
The recommendation of the ruling factor carries out the corresponding recommendation index of the available history award that adds up.
If history award has more parts, recommended models can in the manner described above be closed every part of history award and case
Key information is matched, and obtains recommending index accordingly.Recommended models add up multiple recommendation indexes, available arbitration
The corresponding combined recommendation index of member.Wherein, the quantity of the history award of identical case type is more, and combined recommendation index is corresponding
It is higher.Server screens multiple arbitral combined recommendation indexes in the way of providing in above-described embodiment, will
Arbitrator after screening identifies corresponding arbitrator's information and is sent to the user terminal.
In the present embodiment, the multiple arbitrator's information being consistent with arbitrator's search condition are retrieved by big data platform.By
The content more relevant with case key message is had recorded in history award, from there through recommended models by case key message
It is matched with arbitral history award, the corresponding recommendation of each arbitrator's mark can more accurately be calculated and refer to
Number.So as to recommend the arbitrator more adapted to current arbiter case to party.
Further, since arbitration case is using Chinese description, for effectively high matched accuracy, recommended models are right
It, can be corresponding similar to case keyword to ruling keyword when history award is matched with case key message
Degree is compared.
Specifically, similarity includes pronunciation similarity and font similarity.In order to effectively improve the accurate of similarity comparison
Property, pronunciation similarity can be respectively equipped with corresponding weight with font similarity.For example, d=aP+bS, wherein d is two words
Between similarity, P be pronunciation similarity, S be font similarity.A is the weight of pronunciation similarity, and b is font similarity
Weight.Recommended models can be to be encoded according to the phonetic and tone of word, pronunciation character string is generated, to pronunciation character string
Hash calculation is carried out, switchs to obtain pronunciation similarity thus for pronunciation cryptographic Hash.Recommended models can be right with font similarity
Font is encoded, and glyph characters string is generated, and is carried out Hash calculation to glyph characters string, is switched to for font cryptographic Hash, thus
To font similarity.Wherein, the coding mode that can use the four-corner system is encoded to font.Recommended models are by pronunciation Hash
Value, font cryptographic Hash and its corresponding weight, add up, and obtain total cryptographic Hash to get similarity value is arrived.
Recommended models calculate separately ruling keyword and the corresponding similarity of case keyword in the manner described above, will
The similarity of multiple ruling keywords corresponding to each ruling factor is compared with the similarity of case keyword, if two
The difference of the similarity of keyword is within a preset range, it is determined that both keyword matches.When the same ruling factor is corresponding
When the quantity that ruling keyword and case keyword match is more than threshold value, then this thinks that the ruling factor matches, and can recorde
The recommendation of multiple ruling factors in same a history award is carried out available be somebody's turn to do of adding up by the corresponding recommendation of the factor
History award corresponds to a recommendation index.It is matched by the similarity to keyword, so as to effectively improve Chinese
The matching accuracy of font, and then can more accurately calculate each arbitrator and identify corresponding recommendation index.
Further, for effectively high matched accuracy, recommended models are to history award and case key message
When being matched, it also can use vector and be compared.Wherein, server can also extract case class in case key message
The Partial key information extracted is converted to the case vector of current case by type, party address, economic loss amount of money etc..
The corresponding history case vector of multiple history cases can also be stored in advance in big data platform, and history case vector can be root
It is generated according to the award of history case.Server can will filter out and the consistent history of case type in history award
Award is labeled as primary election history award.The case vector of current case can be input to recommended models by server, be passed through
Recommended models match case vector history case vector corresponding with multiple primary election history awards, similar according to matching
Degree obtains recommendation index corresponding with arbitrator's mark.Recommend the computational efficiency of index thus, it is possible to effectively improve arbitrator.
In one embodiment, this method further include: obtain the portrait factor of multiple dimensions;It is being screened according to the portrait factor
The corresponding portrait information of arbitrator's information extraction out;Using portrait information and the portrait factor, corresponding arbitrator's portrait is generated;
The corresponding arbitrator filtered out of arbitrator's portrait is sent to the user terminal.
Server filters out multiple arbitrations being adapted with current arbiter case in the way of providing in above-described embodiment
After member, can also it be generated for the ease of party or the arbitral situation of understanding of Arbitration Committee's director's quicklook, server
Corresponding arbitrator's portrait.
Specifically, server obtains the portrait factor of multiple dimensions.Portrait the factor include main gene, from the factor, subfactor,
Molecular group and the corresponding index of molecular group.Each main gene includes at least one from the factor.It may include each more from the factor
Corresponding index can be set in a molecular group, each molecular group.For example, main gene includes that basic information, capability evaluation, program are commented
Valence etc..This main gene of basic information it is corresponding from the factor include personal information, social information etc. from the factor.Social information this
It include the subfactors such as education background, professional background from the factor.This subfactor of professional background includes work experience, tenure industry class
Type, corresponding tenure industry are engaged in multiple molecular groups such as time limit.Each molecular group can correspond to one or more indexs.Different fingers
The corresponding different field of mark.Server is corresponding with each portrait factor of form storage for tree of drawing a portrait according to multiple portrait factors
Field.Each arbitrator can correspond to a portrait tree.Server is according to the corresponding field of each index in arbitrator's information
Corresponding portrait information is extracted, using portrait information and the portrait factor, generates corresponding arbitrator's portrait.Server is by arbitrator
The corresponding arbitrator filtered out of portrait is sent to the user terminal.User terminal can show the arbitration filtered out in recommending interface
Member's information and corresponding head portrait.Wherein, user terminal can successively show arbitrator's information according to the portrait factor.When head portrait quilt
When user terminal triggers, corresponding arbitrator's portrait can be shown.
In one embodiment, this method further include: form arbitral court using the arbitrator of user terminal selecting;It is forming
After arbitral court, approximate case is searched in big data platform using case information;It is corresponding that approximate case is sent to arbitral court
Arbitration terminal.
Server acquisition group front yard mode forms corresponding arbitral court using selected arbitrator according to group front yard mode.Its
In, group front yard mode can be party's protocol conventions, be also possible to according to arbitration rules determination.The arbitration of different places is advised
It is then different, for example, can determine the group front yard mode of arbitral court according to arbitration case target amount of money size.When arbitration case target
When the amount of money is more than or equal to 1,000,000, using collegiate system, when the arbitration case target amount of money is less than 1,000,000, using system of sole judge proceedings.Panel discussion
System can be made of 3 arbitrators, and system of sole judge proceedings can be made of 1 arbitrator.
After group front yard, arbitrator can try case online.Before trial, server can be according to working as thing
The material of putting on record (including application for arbitration, billof defence and relevant evidence) that people submits searches for approximate case, in order to arbitrator's ginseng
Approximate case is examined quickly to be tried.Specifically, server obtains the case type of current arbiter case, requests for arbitration, the fact
It is used as search factor with evidence, central issue (if any), the approximate case to match with search factor is searched for by big data platform
Part.Wherein, approximate case may be more, and corresponding weight can be set in each search factor.Different search factors, weight
It can be different.For example, true and evidence weight is 60%, requests for arbitration weight is 30%, central issue weight is 10%.Service
Device is according to the corresponding weight of search factor, it is hereby achieved that multiple approximation cases.
Further, in order to improve the accuracy of approximate case, server can also screen multiple approximate cases.
Wherein, server can be screened from multiple dimensions such as time decision, arbitration organ's level, regions, for example, can be according to sentencing
Certainly the time, which updates, arbitration organ's level is higher, region is closer is ranked up screening, the approximate case filtered out.Server
The case information of the approximate case filtered out is sent to the corresponding arbitration terminal of multiple arbitrators in arbitral court.It is possible thereby to side
Just arbitrator quickly tries current arbiter case by reference to approximate case.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of arbitrator's recommendation apparatus based on big data, comprising: obtain
Modulus block 402, retrieval module 404, matching module 406, screening module 408, in which:
Obtain module 402, for receiving the retrieval request of user terminal uploads, carried in retrieval request case mark with
Arbitrator's search condition;Corresponding case information is obtained according to case mark.
Retrieval module 404, for retrieving the arbitrator's information being consistent with arbitrator's search condition by big data platform;It is secondary
It include that arbitrator identifies in information of reducing the staff.
Matching module 406, for will be matched to case information with the arbitrator's information retrieved using recommended models
It calculates, recommendation index corresponding with arbitrator's mark is obtained according to matching result.
Screening module 408, for being screened according to the multiple arbitrators' marks of recommendation exponent pair, at least one will filtered out
A arbitrator identifies corresponding arbitrator's information and is sent to the user terminal.
It in one embodiment, include posterior infromation in arbitrator's information;Matching module is also used to mention in case information
Take case key message;Case key message and posterior infromation are input to recommended models;It is by recommended models that case is crucial
Information and posterior infromation carry out matching primitives.
In one embodiment, screening module is also used to obtain case and identifies corresponding case type;It is corresponding in arbitrator
History award in filter out and the consistent history award of case type;It include multiple sanctions in the history award filtered out
The certainly factor;Matching module is also used to match the ruling factor with case key message by recommended models, obtains multiple sanctions
The certainly corresponding recommendation of the factor;The corresponding recommendation of multiple ruling factors is added up, is obtained corresponding with arbitrator's mark
Recommend index.
In one embodiment, the device further include: portrait generation module, for obtaining the portrait factor of multiple dimensions;
According to the portrait factor in the corresponding portrait information of arbitrator's information extraction filtered out;It is raw using portrait information and the portrait factor
It draws a portrait at corresponding arbitrator;The corresponding arbitrator filtered out of arbitrator's portrait is sent to the user terminal.
In one embodiment, retrieval module is also used to form arbitral court using the arbitrator of user terminal selecting;In group
After arbitral court, approximate case is searched in big data platform using case information;Approximate case is sent to arbitral court pair
The arbitration terminal answered.
Specific restriction about arbitrator's recommendation apparatus based on big data may refer to above for based on big data
Arbitrator's recommended method restriction, details are not described herein.Each mould in above-mentioned arbitrator's recommendation apparatus based on big data
Block can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independence
In processor in computer equipment, it can also be stored in a software form in the memory in computer equipment, in order to
Processor, which calls, executes the corresponding operation of the above modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 5.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used for the case information etc. of memory arbitration case.The network interface of the computer equipment is used for and outside
Terminal passes through network connection communication.To realize that a kind of arbitrator based on big data pushes away when the computer program is executed by processor
Recommend method.
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of the retrieval request for receiving user terminal uploads, inspection when executing computer program
Case mark and arbitrator's search condition are carried in rope request;Corresponding case information is obtained according to case mark;By big
Data platform retrieves the arbitrator's information being consistent with arbitrator's search condition;It include that arbitrator identifies in arbitrator's information;It utilizes
Recommended models will carry out matching primitives to case information and arbitrator's information for retrieving, be obtained according to matching result and arbitrator
Identify corresponding recommendation index;According to recommending exponent pair multiple arbitrators mark to screen, by filter out at least one is secondary
It reduces the staff and identifies corresponding arbitrator's information and be sent to the user terminal.
It in one embodiment, include posterior infromation in arbitrator's information;The processor goes back reality when executing computer program
Existing following steps: case key message is extracted in case information;Case key message and posterior infromation are input to recommendation mould
Type;Case key message and posterior infromation are subjected to matching primitives by recommended models.
In one embodiment, it is also performed the steps of when which executes computer program and obtains case mark pair
The case type answered;It is filtered out in the corresponding history award of arbitrator and the consistent history award of case type;Screening
It include multiple ruling factors in history award out;Case key message and posterior infromation are carried out matching primitives by recommended models
Include: to be matched the ruling factor with case key message by recommended models, obtains the corresponding recommendation of multiple ruling factors
Value;The corresponding recommendation of multiple ruling factors is added up, recommendation index corresponding with arbitrator's mark is obtained.
In one embodiment, it is also performed the steps of when which executes computer program and obtains multiple dimensions
The portrait factor;According to the portrait factor in the corresponding portrait information of arbitrator's information extraction filtered out;Using portrait information and draw
As the factor, corresponding arbitrator's portrait is generated;The corresponding arbitrator filtered out of arbitrator's portrait is sent to the user terminal.
In one embodiment, it also performs the steps of when which executes computer program and is selected using user terminal
The arbitrator selected forms arbitral court;After forming arbitral court, approximate case is searched in big data platform using case information;
Approximate case is sent to the corresponding arbitration terminal of arbitral court.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of the retrieval request for receiving user terminal uploads when being executed by processor, carry in retrieval request
Case mark and arbitrator's search condition;Corresponding case information is obtained according to case mark;By big data platform retrieval with
Arbitrator's information that arbitrator's search condition is consistent;It include that arbitrator identifies in arbitrator's information;It will be to case using recommended models
Part information carries out matching primitives with the arbitrator's information retrieved, obtains recommendation corresponding with arbitrator's mark according to matching result
Index;According to recommending the multiple arbitrator's marks of exponent pair to screen, at least one arbitrator filtered out is identified corresponding
Arbitrator's information is sent to the user terminal.
In one embodiment, it also performs the steps of when computer program is executed by processor and is mentioned in case information
Take case key message;Case key message and posterior infromation are input to recommended models;It is by recommended models that case is crucial
Information and posterior infromation carry out matching primitives.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains case mark pair
The case type answered;It is filtered out in the corresponding history award of arbitrator and the consistent history award of case type;Screening
It include multiple ruling factors in history award out;Case key message and posterior infromation are carried out matching primitives by recommended models
Include: to be matched the ruling factor with case key message by recommended models, obtains the corresponding recommendation of multiple ruling factors
Value;The corresponding recommendation of multiple ruling factors is added up, recommendation index corresponding with arbitrator's mark is obtained.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains multiple dimensions
The portrait factor;According to the portrait factor in the corresponding portrait information of arbitrator's information extraction filtered out;Using portrait information and draw
As the factor, corresponding arbitrator's portrait is generated;The corresponding arbitrator filtered out of arbitrator's portrait is sent to the user terminal.
In one embodiment, it also performs the steps of when computer program is executed by processor and is selected using user terminal
The arbitrator selected forms arbitral court;After forming arbitral court, approximate case is searched in big data platform using case information;
Approximate case is sent to the corresponding arbitration terminal of arbitral court.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of arbitrator's recommended method based on big data, which comprises
The retrieval request of user terminal uploads is received, case mark and arbitrator's search condition are carried in the retrieval request,
Corresponding case information is obtained according to case mark;
The arbitrator's information being consistent with arbitrator's search condition is retrieved by big data platform;It is wrapped in arbitrator's information
Include arbitrator's mark;
Matching primitives will be carried out with the arbitrator's information retrieved to the case information using recommended models, according to matching
As a result recommendation index corresponding with arbitrator mark is obtained;
It is screened according to the multiple arbitrator's marks of the recommendation exponent pair, at least one arbitrator filtered out is identified and is corresponded to
Arbitrator's information be sent to the user terminal.
2. the method according to claim 1, wherein including posterior infromation in arbitrator's information;The benefit
With recommended models will to it is described state case information and carry out matching primitives with arbitrator's information include:
Case key message is extracted in the case information;
The case key message and the posterior infromation are input to the recommended models;
The case key message and the posterior infromation are subjected to matching primitives by the recommended models.
3. according to the method described in claim 2, it is characterized in that, the method also includes:
It obtains the case and identifies corresponding case type;
It is filtered out in the corresponding history award of the arbitrator and the consistent history award of the case type;It filters out
History award in include multiple ruling factors;
The case key message is carried out matching primitives with the posterior infromation by the recommended models
The ruling factor is matched with the case key message by the recommended models, obtains multiple ruling factors
Corresponding recommendation;
The corresponding recommendation of multiple ruling factors is added up, recommendation index corresponding with arbitrator mark is obtained.
4. the method according to claim 1, wherein the method also includes:
Obtain the portrait factor of multiple dimensions;
Corresponding portrait information is extracted in the arbitrator's information filtered out according to the portrait factor;
Using the portrait information and the portrait factor, corresponding arbitrator's portrait is generated;
The arbitrator filtered out described in corresponding to that the arbitrator is drawn a portrait is sent to the user terminal.
5. the method according to claim 1, wherein the method also includes:
Arbitral court is formed using the arbitrator of user terminal selecting;
After forming arbitral court, approximate case is searched in big data platform using the case information;
The approximate case is sent to the corresponding arbitration terminal of the arbitral court.
6. a kind of arbitrator's recommendation apparatus based on big data, which is characterized in that described device includes:
Obtain module, for receiving the retrieval request of user terminal uploads, carried in the retrieval request case mark with it is secondary
It reduces the staff search condition;Corresponding case information is obtained according to case mark;
Retrieval module, for retrieving the arbitrator's information being consistent with arbitrator's search condition by big data platform;It is described
It include that arbitrator identifies in arbitrator's information;
Matching module, for will be matched to the case information with the arbitrator's information retrieved using recommended models
It calculates, recommendation index corresponding with arbitrator mark is obtained according to matching result;
Screening module, for being screened according to the multiple arbitrator's marks of the recommendation exponent pair, by least one filtered out
Arbitrator identifies corresponding arbitrator's information and is sent to the user terminal.
7. device according to claim 6, which is characterized in that include posterior infromation in arbitrator's information;Described
It is also used to extract case key message in the case information with module;By the case key message and the posterior infromation
It is input to the recommended models;The case key message and the posterior infromation are subjected to matching meter by the recommended models
It calculates.
8. device according to claim 7, which is characterized in that the screening module is also used to obtain the case mark pair
The case type answered;It is filtered out in the corresponding history award of the arbitrator and the consistent history ruling of the case type
Book;It include multiple ruling factors in the history award filtered out;The matching module is also used to will by the recommended models
The ruling factor is matched with the case key message, obtains the corresponding recommendation of multiple ruling factors;By multiple sanctions
Certainly the corresponding recommendation of the factor adds up, and obtains recommendation index corresponding with arbitrator mark.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 5 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 5 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910520069.XA CN110377819A (en) | 2019-06-17 | 2019-06-17 | Arbitrator's recommended method, device and computer equipment based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910520069.XA CN110377819A (en) | 2019-06-17 | 2019-06-17 | Arbitrator's recommended method, device and computer equipment based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110377819A true CN110377819A (en) | 2019-10-25 |
Family
ID=68248909
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910520069.XA Pending CN110377819A (en) | 2019-06-17 | 2019-06-17 | Arbitrator's recommended method, device and computer equipment based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110377819A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111460280A (en) * | 2020-02-25 | 2020-07-28 | 中通服创发科技有限责任公司 | Legal service personnel recommendation method based on public legal service platform |
CN111738822A (en) * | 2020-06-16 | 2020-10-02 | 中国银行股份有限公司 | Auditor recommendation method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012066571A1 (en) * | 2010-11-16 | 2012-05-24 | Shardul Suresh Shroff | System and method for providing virtual arbitration |
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 |
CN109741168A (en) * | 2018-12-07 | 2019-05-10 | 上海指旺信息科技有限公司 | Online arbitration information exchange method and system |
-
2019
- 2019-06-17 CN CN201910520069.XA patent/CN110377819A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012066571A1 (en) * | 2010-11-16 | 2012-05-24 | Shardul Suresh Shroff | System and method for providing virtual arbitration |
US20130339256A1 (en) * | 2010-11-16 | 2013-12-19 | Shardul Suresh Shroff | System and method for providing virtual arbitration |
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 |
CN109741168A (en) * | 2018-12-07 | 2019-05-10 | 上海指旺信息科技有限公司 | Online arbitration information exchange method and system |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111460280A (en) * | 2020-02-25 | 2020-07-28 | 中通服创发科技有限责任公司 | Legal service personnel recommendation method based on public legal service platform |
CN111460280B (en) * | 2020-02-25 | 2023-10-24 | 中通服创发科技有限责任公司 | Legal service personnel recommendation method based on public legal service platform |
CN111738822A (en) * | 2020-06-16 | 2020-10-02 | 中国银行股份有限公司 | Auditor recommendation method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | A gated peripheral-foveal convolutional neural network for unified image aesthetic prediction | |
Cui et al. | Distribution-oriented aesthetics assessment with semantic-aware hybrid network | |
Kordopatis-Zilos et al. | Near-duplicate video retrieval by aggregating intermediate cnn layers | |
Kao et al. | Visual aesthetic quality assessment with a regression model | |
US9984402B2 (en) | Method, system, and computer program product for recommending online products | |
CN113449187B (en) | Product recommendation method, device, equipment and storage medium based on double images | |
US20230222285A1 (en) | Layout-Aware Multimodal Pretraining for Multimodal Document Understanding | |
CN110633421B (en) | Feature extraction, recommendation, and prediction methods, devices, media, and apparatuses | |
CN111028006B (en) | Service delivery auxiliary method, service delivery method and related device | |
CN110362799A (en) | Processing method, device and computer equipment are generated based on the award arbitrated online | |
CN113159013B (en) | Paragraph identification method, device, computer equipment and medium based on machine learning | |
CN110377819A (en) | Arbitrator's recommended method, device and computer equipment based on big data | |
CN110968664A (en) | Document retrieval method, device, equipment and medium | |
CN110532229B (en) | Evidence file retrieval method, device, computer equipment and storage medium | |
CN110213660B (en) | Program distribution method, system, computer device and storage medium | |
CN112749723A (en) | Sample labeling method and device, computer equipment and storage medium | |
CN111552810B (en) | Entity extraction and classification method, entity extraction and classification device, computer equipment and storage medium | |
CN109190615A (en) | Nearly word form identification decision method, apparatus, computer equipment and storage medium | |
CN117251622A (en) | Method, device, computer equipment and storage medium for recommending objects | |
Lu et al. | Learning multimodal neural network with ranking examples | |
CN110688516A (en) | Image retrieval method, image retrieval device, computer equipment and storage medium | |
CN115269765A (en) | Account identification method and device, electronic equipment and storage medium | |
US11763094B2 (en) | Cascade pooling for natural language processing | |
CN117688390A (en) | Content matching method, apparatus, computer device, storage medium, and program product | |
CN115269998A (en) | Information recommendation method and device, electronic equipment and storage medium |
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 |