CN106097193A - A kind of lawyer's evaluating data processing method - Google Patents
A kind of lawyer's evaluating data processing method Download PDFInfo
- Publication number
- CN106097193A CN106097193A CN201610413016.4A CN201610413016A CN106097193A CN 106097193 A CN106097193 A CN 106097193A CN 201610413016 A CN201610413016 A CN 201610413016A CN 106097193 A CN106097193 A CN 106097193A
- Authority
- CN
- China
- Prior art keywords
- lawyer
- information
- mark
- image
- user
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 48
- 210000001508 eye Anatomy 0.000 claims description 85
- 230000033001 locomotion Effects 0.000 claims description 84
- 230000001815 facial effect Effects 0.000 claims description 75
- 238000013507 mapping Methods 0.000 claims description 23
- 238000003860 storage Methods 0.000 claims description 14
- 210000001747 pupil Anatomy 0.000 claims description 12
- 238000006073 displacement reaction Methods 0.000 claims description 9
- 230000002349 favourable effect Effects 0.000 claims description 6
- 210000005252 bulbus oculi Anatomy 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 15
- 230000015654 memory Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000005070 sampling Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 5
- 238000005859 coupling reaction Methods 0.000 description 5
- 210000003128 head Anatomy 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- SBNFWQZLDJGRLK-UHFFFAOYSA-N phenothrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=CC=CC(OC=2C=CC=CC=2)=C1 SBNFWQZLDJGRLK-UHFFFAOYSA-N 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Engineering & Computer Science (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Technology Law (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a kind of lawyer's evaluating data processing method, wherein, the method includes: receive the acquisition request of lawyer's evaluating data that user terminal sends；According to the identification information of lawyer, the user satisfaction information that the inquiry INFORMATION of lawyer, professional information and lawyer obtain；The user satisfaction information that INFORMATION, professional information and lawyer according to the lawyer inquired obtains generates lawyer's evaluating data of lawyer；Lawyer's evaluating data of generation is sent to user terminal to be shown.Lawyer's evaluating data processing method that the present invention provides, it is possible to use the professional skill of lawyer can be intuitively understood at family.
Description
Technical field
The present invention relates to technical field of data processing, in particular to a kind of lawyer's evaluating data processing method.
Background technology
Along with the country's continuous publicity to the theory of running the country according to law, law government idea deepens continuously the popular feeling, when going out between men
During existing dispute, client can expect by finding lawyer, and processes relevant to dispute to lawyer's consulting or mandatory lawyer
Law matters, ensure the legitimate rights and interests of oneself.
In correlation technique, user, during finding lawyer, can go rule to be directly found and be familiar with dispute relevant law
Lawyer seek advice from, and restrain often recommend lawyer to user, it is relevant that the lawyer allowing user be recommended with Lv carries out dispute
The contact of business；User can also be by the lawyer on network at line platform, according to lawyer's introduction of lawyer on line platform, choosing
Select and be familiar with the lawyer of dispute relevant law and carry out the contact of dispute related service.
In realizing process of the present invention, inventor finds that in prior art, at least there are the following problems:
User is during searching lawyer seeks advice from law matters, it is impossible to obtains rule objectively and does its lawyer's recommended
Level, it is possible to the actual professional standards of this lawyer are relatively low, it is impossible to meet the demand even cause the user loss of user；And use
When family is by lawyer online platform selecting lawyer, also can only be introduced by the one-side subjective of default lawyer, come lawyer's
Speciality is tentatively understood, but still can not grasp lawyer true, objectively handle a case level；Therefore, either user oneself
Actively look for lawyer still by the lawyer on network line platform lawyer, all cannot save time, laborsaving, find coupling user accurately
The lawyer of demand.
Summary of the invention
In view of this, the purpose of the embodiment of the present invention is to provide a kind of lawyer's evaluating data processing method, so that user
Can intuitively understand the professional skill of lawyer.
First aspect, embodiments provides a kind of lawyer's evaluating data processing method, including:
Receiving the acquisition request of lawyer's evaluating data that user terminal sends, wherein, described acquisition request carries lawyer
Identification information, described lawyer's evaluating data obtains according to INFORMATION, professional information and the described lawyer of described lawyer
User satisfaction information generates；
According to the identification information of described lawyer, inquire about the INFORMATION of described lawyer, professional information and described lawyer and obtain
The user satisfaction information arrived；
The user satisfaction letter obtained according to the INFORMATION of described lawyer inquired, professional information and described lawyer
Breath generates lawyer's evaluating data of described lawyer；
The described lawyer's evaluating data generated is sent to described user terminal to be shown.
In conjunction with first aspect, embodiments provide the first possible embodiment of first aspect, wherein: institute
Method of stating also includes:
Obtaining the lawyer information editing request that user terminal sends, wherein, described lawyer information editing request carries rule
The identification information of teacher and first facial image of lawyer；
According to the identification information of described lawyer, inquire second facial image of the described lawyer prestored；
It is multiple image-region by the first face image division of described lawyer；
From multiple described image-regions, select k image-region to splice respectively, obtain multiple face subimage, wherein,
Multiple described image-regions are the most averagely divided by described first facial image and obtain,
M represents the image-region quantity of described first face image division；
The plurality of face subimage and described second facial image to obtaining carry out degree of depth study, obtain described
One facial image and the feature difference figure of described second facial image；
The described feature difference figure obtained is carried out degree of depth study, obtains described first facial image and described second face
The comparison result of image；
When obtaining the described first facial image comparing result similar with described second facial image, to described user eventually
End sends ocular movement information so that user enters according to the described ocular movement information of display on described user terminal
Row ocular movement；
Acquisition user carries out multiple ocular movement images during ocular movement；
From multiple the ocular movement images of the described user obtained, obtain the motion of the point of fixation of the eyes of described user
Track；
When the movement locus of the point of fixation according to the eyes got, determine that the eyes of described user are according to ocular movement
During the motion that the prompting of information is carried out, it is allowed to user by described user terminal to the INFORMATION of described lawyer, operation
The user satisfaction information that information and described lawyer obtain is edited.
In conjunction with first aspect, embodiments provide the embodiment that the second of first aspect is possible, wherein: right
The plurality of face subimage and described second facial image that obtain carry out degree of depth study, obtain described first facial image
Include with the feature difference figure of described second facial image:
Multiple described face subimages and described second facial image are carried out degree of depth study, obtains multiple first face figure
As characteristic pattern and the second facial image characteristic pattern；
It is characterized value regional center, according to default with each pixel coordinate of storage in default pixel coordinate set
Eigenvalue area size, will work as ex-first lady's face characteristics of image figure respectively and described second facial image characteristic pattern is divided into multiple
The First Eigenvalue region and multiple Second Eigenvalue region；
Profile maxima is obtained respectively from the plurality of the First Eigenvalue region and the plurality of Second Eigenvalue region；
Calculate and obtain from the First Eigenvalue region with same characteristic features value regional center and Second Eigenvalue region respectively
The difference of the profile maxima taken, obtains multiple feature difference；
With the plurality of feature difference as pixel value, according to default feature difference figure size, generate described current first
Facial image characteristic pattern and the feature difference figure of described second facial image characteristic pattern.
In conjunction with first aspect, embodiments provide the third possible embodiment of first aspect, wherein: right
The described feature difference figure obtained carries out degree of depth study, obtains described first facial image and the comparison of described second facial image
As a result, including:
The each feature difference figure obtained is carried out degree of depth study, obtains people's face that each described feature difference figure is corresponding
Image and the similar parameter of described second facial image；
Determine the similar parameter similarity as described first facial image Yu described second facial image of maximum；
When described similarity is more than or equal to the similarity threshold set, obtain described first facial image and described second
The comparison result that facial image is similar.
In conjunction with first aspect, embodiments provide the 4th kind of possible embodiment of first aspect, wherein: from
In multiple the ocular movement images of the described user obtained, obtain the movement locus of the point of fixation of the eyes of described user, including:
Ball moving image of often opening one's eyes in multiple ocular movement images described in obtaining is carried out respectively eye location, and from
Described ball moving image of often opening one's eyes behind location intercepts the eyes subimage of described ball moving image of often opening one's eyes；
Iris image and/or the pupil of described eyes is extracted respectively from the eyes subimage of described ball moving image of often opening one's eyes
Hole pattern picture；
According to the described iris image extracted in ocular movement image described from every and/or described pupil image, calculate
Eyes in multiple ocular movement images described between relative displacement, and determine institute according to calculated described relative displacement
State the movement locus of the point of fixation of eyes.
In conjunction with first aspect, embodiments provide the 5th kind of possible embodiment of first aspect, wherein: root
According to the movement locus of the point of fixation of the eyes got, determine that the eyes of described user are carrying according to ocular movement information
Show the motion carried out, including one of in the following manner:
When determining that the point of fixation of eyes of described user targeted by target fiducials object, determine that the eyes of described user are
The motion carried out according to the prompting of ocular movement information, wherein, described target fiducials object, is by described ocular movement
Information prompts the user with the object that need to watch attentively in advance；
When the movement locus of point of fixation of the eyes determining described user and the described target fiducials of display on user terminal
When the movement locus of object is consistent, determine that the eyes of described user are to carry out according to the prompting of described ocular movement information
Motion.
In conjunction with first aspect, embodiments provide the 6th kind of possible embodiment of first aspect, wherein: root
The user satisfaction information obtained according to the INFORMATION of described lawyer inquired, professional information and described lawyer generates described
Lawyer's evaluating data of lawyer, including:
The academic information of described lawyer of record in INFORMATION according to described lawyer, universities and colleges teach information and deliver literary composition
Chapter quantity information, obtains the academic index in described lawyer's evaluating data；
The operation year limit information of the described lawyer of record in professional information according to described lawyer, the overall number held brief
Amount information and the working quality of case handling information held brief, obtain the operation index in described lawyer's evaluating data, wherein, described in do
Case quality information includes: described lawyer undertakes the rate of winning a lawsuit of case and undertakes the success rate of non-case；
Believe according to favorable comment quantity information and the evaluation customer quantity of record in the user satisfaction information that described lawyer obtains
Breath, obtains the Satisfaction index in described lawyer's evaluating data.
In conjunction with first aspect, embodiments provide the 7th kind of possible embodiment of first aspect, wherein: root
The user satisfaction information obtained according to the INFORMATION of described lawyer inquired, professional information and described lawyer generates described
Lawyer's evaluating data of lawyer, also includes:
Obtain quantity information that described lawyer held brief under the default type that respectively holds brief and respectively hold brief
The working quality of case handling information held brief under type, wherein, described in hold brief type, including contract law type, marriage law class
Type, Infringement Law type, merger and acquisition type, investment and financing type and stock's coming-into market type；
The quantity information held brief under the default type that respectively holds brief according to the described lawyer got is with each
The working quality of case handling information held brief under the type that holds brief generates the professional index in described lawyer's evaluating data.
In conjunction with first aspect, embodiments provide the 8th kind of possible embodiment of first aspect, wherein: root
According in the INFORMATION of described lawyer record the academic information of described lawyer, universities and colleges teach information and quantity of publishing an article letter
Breath, obtains the academic index in described lawyer's evaluating data, including:
Teach duty according to educational background and the corresponding relation of mark, the universities and colleges of record in default educational background-mark mapping table
The educational background of record and the corresponding relation of mark and quantity of publishing an article-mark mapping table in title-mark mapping table
The educational background of middle record and the corresponding relation of mark, determine that the described educational background information of described lawyer, described universities and colleges are taught information respectively
With the described mark published an article corresponding to quantity information；
By mark and the mark of quantity information of publishing an article of information that the mark of academic information obtained, universities and colleges are taught
Calculate, generate the academic index in lawyer's evaluating data.
In conjunction with first aspect, embodiments provide the 9th kind of possible embodiment of first aspect, wherein: root
According in the professional information of described lawyer record the operation year limit information of described lawyer, the total number information held brief and
The working quality of case handling information held brief, obtains the operation index in described lawyer's evaluating data, including:
Close according to the operation time limit of record in default operation year limit information-mark mapping table is corresponding with mark
System, determine lawyer operation year limit information mark；
Quantity and mark is undertaken according to the case of record in default undertaking case quantity-mark mapping table
Corresponding relation, determines that described lawyer undertakes the mark of case；
When determining that described lawyer undertakes the mark of case more than or equal to preset fraction, obtain described lawyer's undertaking case
Rate of the winning a lawsuit information of part；
When according to rate information of winning a lawsuit described in getting, determining that the winning rate of described attorney's procuration plaintiff is more than first preset
Winning rate threshold value and when acting on behalf of the winning rate of defendant more than the second winning rate threshold value preset, by the first default numerical value to described lawyer
The mark undertaking case carries out autoincrementing operation；
When according to rate information of winning a lawsuit described in getting, determining that the winning rate of described attorney's procuration plaintiff is more than first preset
Winning rate threshold value or when acting on behalf of the winning rate of defendant more than the second winning rate threshold value preset, by default second value to described rule
Transmission from master to disciple is done the mark of case and is carried out autoincrementing operation, and wherein, the first numerical value preset is more than the second value preset；
Undertake the case of record in non-case quantity-mark mapping table according to default described lawyer and undertake number
Amount and the corresponding relation of mark, determine that described lawyer undertakes the mark of non-case；
When described lawyer undertakes the mark of non-case more than or equal to preset fraction, by the described success got
Rate information, it is judged that whether described lawyer undertakes the success rate of non-case more than the success rate threshold value preset；
If it is, described lawyer undertaken the mark of non-case by the second value preset to carry out autoincrementing operation；
By to obtain operation year limit information mark, described lawyer undertake the mark of case and described lawyer
The mark undertaking non-case calculates, and obtains the operation index in lawyer's evaluating data.
Lawyer's evaluating data processing method that the embodiment of the present invention provides, when receiving lawyer's evaluation that user terminal sends
When the acquisition of data is asked, according to the identification information of the lawyer carried in acquisition request, inquire corresponding with this identification information
The user satisfaction information that obtains of the INFORMATION of lawyer, professional information and lawyer, and according to of the lawyer inquired
The user satisfaction information that art information, professional information and lawyer obtain generates lawyer's evaluating data of lawyer, finally will generate
Lawyer's evaluating data be sent to user terminal, thus show lawyer's evaluating data by user terminal to user, with existing skill
In art user cannot rule or network be directly acquainted with the level of handling a case of lawyer and compare so that user can evaluate number by lawyer
According to, the professional standards of lawyer are got information about so that user select lawyer time can save time, laborsaving, accurate
The lawyer finding applicable user oneself, greatly reduce and select professional standards relatively low or lawyer unmatched with self-demand
Probability.
For making the above-mentioned purpose of the present invention, feature and advantage to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below by embodiment required use attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, and it is right to be therefore not construed as
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to this
A little accompanying drawings obtain other relevant accompanying drawings.
Fig. 1 shows the applied environment schematic diagram of lawyer's evaluating data processing method that the embodiment of the present invention provided；
Fig. 2 shows the user processing user profile in lawyer's evaluating data processing method that the embodiment of the present invention is provided
The structural representation of terminal；
Fig. 3 shows the knot of the executive agent server of lawyer's evaluating data processing method that the embodiment of the present invention provided
Structure schematic diagram；
Fig. 4 shows the flow chart of a kind of lawyer's evaluating data processing method method that the embodiment of the present invention provided.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
Middle accompanying drawing, is clearly and completely described the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only
It is a part of embodiment of the present invention rather than whole embodiments.Generally real with the present invention illustrated described in accompanying drawing herein
The assembly executing example can be arranged with various different configurations and design.Therefore, below to the present invention's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit the scope of claimed invention, but is merely representative of the selected reality of the present invention
Execute example.Based on embodiments of the invention, the institute that those skilled in the art are obtained on the premise of not making creative work
There are other embodiments, broadly fall into the scope of protection of the invention.
Lawyer's evaluating data processing method that the embodiment of the present invention is provided can be applicable to applied environment as shown in Figure 1
In.As it is shown in figure 1, user terminal 100, server 200 are positioned in wireless network or cable network 300, by this wireless network
Or cable network 300, user terminal 100 and server 200 carry out data interaction.
In the embodiment of the present invention, user terminal 100 is preferably mobile terminal device, such as can include smart mobile phone,
Panel computer, pocket computer on knee, vehicle-mounted computer, Wearable mobile terminal etc., naturally it is also possible to use individual calculus
Machine (Personal Computer, PC).
Fig. 2 shows the structured flowchart of a kind of user terminal that can be applicable in the embodiment of the present invention.As in figure 2 it is shown, use
Family terminal 100 includes memorizer 102, storage control 104, one or more (only illustrating one in figure) processor 106, peripheral hardware
Interface 108, radio-frequency module 110, audio-frequency module 112, Touch Screen 114 etc..These assemblies by one or more communication bus/
The mutual communication of holding wire 116.
Memorizer 102 can be used for storing software program and module, at the lawyer's evaluating data in the embodiment of the present invention
Programmed instruction/module that reason method is corresponding, processor 106 is stored in the software program in memorizer 102 and mould by operation
Block, thus the application of various function and data process, the lawyer's evaluating data processing method provided such as the embodiment of the present invention are provided.
Memorizer 102 can include high speed random access memory, may also include nonvolatile memory, such as one or more magnetic
Property storage device, flash memory or other non-volatile solid state memories.Processor 106 and other possible assemblies are to storage
The access of device 102 can be carried out under the control of storage control 104.
Various input/output devices are coupled to processor 106 and memorizer 102 by Peripheral Interface 108.Implement at some
In example, Peripheral Interface 108, processor 106 and storage control 104 can realize in one single chip.In some other reality
In example, they can be realized by independent chip respectively.
Radio-frequency module 110 is used for receiving and sending electromagnetic wave, it is achieved electromagnetic wave is changed with the mutual of the signal of telecommunication, thus with
Communication network or other equipment carry out communication.
Audio-frequency module 112 provides a user with audio interface, and it can include one or more mike, one or more raises
Sound device and voicefrequency circuit.
Touch Screen 114 provides an output and inputting interface between user terminal 100 and user simultaneously.Specifically,
Touch Screen 114 displays to the user that video frequency output, and the content of these video frequency output can include word, figure, video and arbitrarily
Combination.
Be appreciated that the structure shown in Fig. 2 be only signal, user terminal 100 may also include more more than shown in Fig. 2 or
Less assembly, or there is the configuration different from shown in Fig. 2.Each assembly shown in Fig. 2 can use hardware, software or its
Combination realizes.
Fig. 3 shows the structured flowchart of a kind of server that can be applicable in the embodiment of the present invention.As it is shown on figure 3, service
Device 200 includes: memorizer 201, processor 202 and mixed-media network modules mixed-media 203.
Memorizer 201 can be used for storing software program and module, at the lawyer's evaluating data in the embodiment of the present invention
Programmed instruction/module that reason method is corresponding, processor 202 is stored in the software program in memorizer 201 and mould by operation
Block, thus perform the application of various function and data process, i.e. realize the lawyer's evaluating data process side in the embodiment of the present invention
Method.Memorizer 201 can include high speed random access memory, may also include nonvolatile memory, as one or more magnetic is deposited
Storage device, flash memory or other non-volatile solid state memories.Further, above-mentioned software program and module may also include that
Operating system 221 and service module 222.Wherein operating system 221, such as, can be LINUX, UNIX, WINDOWS, and it can wrap
Include the various component software for managing system task (such as memory management, storage device control, power management etc.) and/or drive
Dynamic, and can communication mutual with various hardware or component software, thus provide the running environment of other component softwares.Service module
On the basis of 222 operate in operating system 221, and monitor the request of automatic network by the network service of operating system 221, root
Complete corresponding data according to request to process, and return result to client.It is to say, service module 222 is for visitor
Family end provides network service.
Mixed-media network modules mixed-media 203 is used for receiving and sending network signal.Above-mentioned network signal can include wireless signal or have
Line signal.
Being appreciated that the structure shown in Fig. 3 is only signal, server 200 may also include more more than shown in Fig. 3 or more
Few assembly, or there is the configuration different from shown in Fig. 3.Each assembly shown in Fig. 3 can use hardware, software or its group
Close and realize.It addition, the server in the embodiment of the present invention can also include the server of multiple concrete difference in functionality.
In the embodiment of the present invention, being provided with client in user terminal 100, this client can be that browser can also
It is third-party application software, holds corresponding with server (Server), provide the user service, such as, show lawyer's evaluating data
Service.
In correlation technique, user is during searching lawyer seeks advice from law matters, it is impossible to obtains rule objectively and does it
The level of the lawyer recommended, it is possible to the actual professional standards of this lawyer are relatively low, it is impossible to meet the demand of user even to user
Cause damage；And user by lawyer online platform selecting lawyer time, also can only be situated between by the one-side subjective of default lawyer
Continue, the speciality of lawyer tentatively understood, but still can not grasp lawyer true, objectively handle a case level；Therefore, nothing
Opinion is that user oneself actively looks for lawyer or passes through the lawyer on network line platform lawyer, all cannot save time, laborsaving, accurately
Find coupling user's request lawyer based on this, the application provide a kind of lawyer's evaluating data processing method.
Embodiment:
The present embodiment provides a kind of lawyer's evaluating data processing method, and the executive agent of the present embodiment is server, when connecing
When receiving the acquisition request of lawyer's evaluating data that user terminal sends, according to the mark letter obtaining the lawyer carried in request
Breath, inquires the user satisfaction that the INFORMATION of the lawyer corresponding with this identification information, professional information and lawyer obtain
Information, and the user satisfaction information generation rule obtained according to INFORMATION, professional information and the lawyer of the lawyer inquired
Lawyer's evaluating data of teacher, is finally sent to user terminal by lawyer's evaluating data of generation.
The flow chart of a kind of lawyer's evaluating data processing method that the present embodiment shown in Figure 4 provides, the method bag
Include following steps:
Step 400, the acquisition of the lawyer's evaluating data receiving user terminal transmission are asked.
Wherein, the request of acquisition carries the identification information of lawyer, above-mentioned lawyer's evaluating data according to the INFORMATION of lawyer,
The user satisfaction information that professional information and lawyer obtain generates.
The identification information of above-mentioned lawyer, is the information that can uniquely identify lawyer prestored on server, is lawyer
After server registration, server is to the lawyer's distribution succeeded in registration.
After user signs in server by user terminal, lawyer can be preset according to the hobby click of oneself and show interface
On name of attorney or lawyer's head portrait to understand the data of relevant lawyer, thus send obtaining of lawyer's evaluating data to server
Take request so that server, can be by the lawyer of this lawyer while shown the data of lawyer to user by user terminal
Evaluating data displays that on the subscriber terminal so that user passes through lawyer's evaluating data, carries out the professional standards of lawyer intuitively
Understanding.
In the present embodiment, when determining that user passes through user terminal selecting name of attorney or lawyer's head portrait, user
According to name of attorney set in advance or lawyer's head portrait and the corresponding relation of the identification information of lawyer, terminal can determine that user will
The identification information of the lawyer of data to be checked, and generate the acquisition request of lawyer's evaluating data according to the identification information of lawyer, so
After ask to be sent to server by the acquisition of lawyer's evaluating data of generation so that server evaluates number according to the lawyer received
According to lawyer's information aggregate of prestoring in the memorizer of server of the request that obtains in inquire about corresponding with this identification information
Lawyer's information.
Step 402, identification information according to lawyer, the inquiry INFORMATION of lawyer, professional information and lawyer obtain
User satisfaction information.
In above-mentioned steps 402, server from storage lawyer's information inquire about the INFORMATION of lawyer, professional information with
And the user satisfaction information that lawyer obtains.
In one embodiment, the INFORMATION of lawyer, include but not limited to: educational background information, universities and colleges teach information and
Publish an article quantity information.
The professional information of lawyer, includes but not limited to: operation year limit information, the total number information that holds brief and holding
Handle a case the working quality of case handling information of part.
User satisfaction information, be lawyer be after user carries out legal services, user by user terminal to this lawyer's
Comment marking.
Above-mentioned comment is given a mark, and can use 5 points of systems, by user according to oneself impression during accepting legal services,
Giving a mark lawyer, wherein, in comment marking, 5 points is full marks, so the mark of the comment marking obtained of going to the bar is more
Height, illustrates that the satisfaction of the legal services that lawyer provided by user is the highest.
Wherein, the INFORMATION of above-mentioned lawyer is the data of lawyer oneself input server, and lawyer can be inputted by server
INFORMATION store, as a part for lawyer's information.
And the professional information of lawyer and user satisfaction information, as another part of teacher's information, lawyer also can be recorded
In information.
Operation year limit information in the professional information of above-mentioned lawyer, is that server inquires holding of lawyer by bar association
Information determined by industry card number and initial operation time；And in the professional information of lawyer record this lawyer hold brief total
Body quantity information and the working quality of case handling information held brief, be rule institute relevant staff situation of the handling typing according to case
In server, the state that oneself can not be held brief by lawyer during typing is edited and is revised, so
The total number information held brief of this lawyer recorded in the professional information of lawyer and the working quality of case handling letter held brief
Breath credibility is higher, lawyer can be selected to make guidance user.
When restraining institute relevant staff and the situation of handling of case being entered into server, also lawyer can be held brief
Case information be entered into the most together in server, such as: the case letters such as the type that holds brief and the client that holds brief
Breath.
Step 404, the user satisfaction letter obtained according to the INFORMATION of lawyer, professional information and the lawyer inquired
Breath generates lawyer's evaluating data of lawyer.
In one embodiment, above-mentioned steps 404 includes that step (1) is to step (3) in detail below:
(1) teach information and number of publishing an article according to the academic information of lawyer of record, universities and colleges in the INFORMATION of lawyer
Amount information, obtains the academic index in lawyer's evaluating data；
(2) according in the professional information of lawyer record lawyer operation year limit information, hold brief total number letter
Breath and the working quality of case handling information held brief, obtain the operation index in lawyer's evaluating data, and wherein, above-mentioned working quality of case handling is believed
Breath includes: lawyer undertakes the rate of winning a lawsuit of case and undertakes the success rate of non-case；
(3) the favorable comment quantity information of record and evaluate customer quantity letter in the user satisfaction information obtained according to lawyer
Breath, obtains the Satisfaction index in lawyer's evaluating data.
In above-mentioned steps 1, specifically include following steps (11) to step (12):
(11) appoint with corresponding relation, the universities and colleges of mark according to the educational background of record in the educational background-mark mapping table preset
Teaching job claims-mark mapping table in the educational background pass corresponding with the corresponding relation of mark and quantity-mark of publishing an article of record
It is the corresponding relation of educational background and the mark of record in table, determines that the academic information of lawyer, universities and colleges are taught information and deliver literary composition respectively
Mark corresponding to chapter quantity information；
(12) by mark and the quantity information of publishing an article of information that the mark of academic information obtained, universities and colleges are taught
Mark calculates, and generates the academic index in lawyer's evaluating data.
Educational background information, universities and colleges the are taught mark of information and quantity information of publishing an article of step 12 calculates, and generates rule
Academic index in teacher's evaluating data, comprises the following steps (121) to step (122):
(121) calculate educational background information, universities and colleges to teach the meansigma methods of mark of information and quantity information of publishing an article；
(122) meansigma methods obtained is carried out downward floor operation, obtain the numerical value as academic index.
Specifically, educational background-mark mapping table includes: undergraduate course educational background or degree and the corresponding relation of 1 point；Master's educational background
Or degree and the corresponding relation of 2 points；Doctor's educational background or degree and the corresponding relation of 3 points.
Universities and colleges' academic title-mark mapping table of teaching includes: say divisional with corresponding relation 1 point；Associate professor's level with 2 points
Corresponding relation；Professor's level corresponding relation with 3 points.
Quantity-mark mapping table of publishing an article includes: the corresponding pass of less than three articles and 1 point delivered by relevant publication
System；Relevant publication delivers three to five articles and the corresponding relation of 2 points；Relevant publication delivers five and above article and 3 points
Corresponding relation.
Above-mentioned universities and colleges teach academic title, refer to the lawyer academic title in the tenure of law class universities and colleges.
In step 2 above, following steps (21) are specifically included to step (29):
(21) corresponding with mark according to the operation time limit of record in the operation year limit information-mark mapping table preset
Relation, determine lawyer operation year limit information mark；
(22) in undertaking case quantity-mark mapping table that basis is preset, the case of record is undertaken quantity and is divided
The corresponding relation of number, determines that lawyer undertakes the mark of case；
(23) when determining that lawyer undertakes the mark of case more than or equal to preset fraction, obtain what lawyer held brief
Rate of winning a lawsuit information；
(24) when according to rate of the winning a lawsuit information got, determining that the winning rate of attorney's procuration plaintiff is more than the first winning rate preset
Threshold value and when acting on behalf of the winning rate of defendant more than the second winning rate threshold value preset, undertakes lawsuit by the first default numerical value to lawyer
The mark of case carries out autoincrementing operation；
(25) when according to rate of the winning a lawsuit information got, determining that the winning rate of attorney's procuration plaintiff is more than the first winning rate preset
Threshold value or when acting on behalf of the winning rate of defendant more than the second winning rate threshold value preset, is undertaken lawyer by default second value and tells
The mark of lawsuit part carries out autoincrementing operation, and wherein, the first numerical value preset is more than the second value preset；
(26) undertake the case of record in non-case quantity-mark mapping table according to the lawyer preset and undertake number
Amount and the corresponding relation of mark, determine that lawyer undertakes the mark of non-case；
(27) go to the bar the quantity information undertaking non-case mark more than or equal to preset fraction time, by getting
Success rate information, it is judged that lawyer undertakes the success rate of non-case whether more than the 3rd winning rate threshold value preset, if
Then perform step 28, if otherwise performing step 29；
(28) lawyer is undertaken the mark of non-case and carries out autoincrementing operation by the second value by presetting；
(29) by obtain operation year limit information mark, lawyer undertakes the mark of case and lawyer undertakes
The mark of non-case calculates, and obtains the operation index in lawyer's evaluating data.
In above-mentioned steps 24,25 and 28, by default numerical value, lawyer is undertaken case/non-case and divide
Number carries out autoincrementing operation and refers to: on the basis of current lawyer undertakes the mark of case/non-case, add default
First numerical value or default second value, obtain final lawyer and undertake the mark of case/non-case.
Wherein, in the calculating process described by step 29, with the calculating process described by above-mentioned steps 121 to step 122
Similar, repeat the most one by one.
Specifically, operation year limit information-mark mapping table includes: less than the 5 years operation time limits and the corresponding pass of 1 point
System；5 years to the 10 years operation time limits and the corresponding relation of 2 points；More than the 10 years corresponding relations with 3 points of the operation time limit.
Undertake case quantity-mark mapping table to include: less than 20 caseloads and the corresponding relation of 1 point；
20 to 100 caseloads and the corresponding relation of 2 points；More than 100 caseloads and the corresponding relation of 3 points.
Undertake non-case quantity-mark mapping table to include: less than 20 caseloads and the corresponding pass of 1 point
System；20 to 50 caseloads and the corresponding relation of 2 points；More than 50 caseloads and the corresponding relation of 3 points.
In above-mentioned steps 3, including step in detail below (30) to step (32):
(30) obtain the favorable comment quantity information of record in the user satisfaction information that this lawyer obtains and evaluate customer quantity
Information；
(31) by the favorable comment quantity of record in favorable comment quantity information divided by the customer quantity of record in customer quantity information,
Obtain satisfaction result of calculation；
(32) the satisfaction result of calculation obtained is carried out downward floor operation, obtain the numerical value as Satisfaction index.
After the academic index obtained in lawyer's evaluating data, operation index and Satisfaction index, server can divide
Will not there is the star pattern of the academic index of different score value, operation index and the Satisfaction index different colours by presetting
Show.
Step 406, lawyer's evaluating data of generation is sent to user terminal to be shown.
In sum, lawyer's evaluating data processing method that the present embodiment provides, when receiving the rule that user terminal sends
When the acquisition of teacher's evaluating data is asked, according to the identification information of the lawyer carried in acquisition request, inquire and this identification information
The user satisfaction information that the INFORMATION of corresponding lawyer, professional information and lawyer obtain, and according to the rule inquired
The user satisfaction information that the INFORMATION of teacher, professional information and lawyer obtain generates lawyer's evaluating data of lawyer, finally
Lawyer's evaluating data of generation is sent to user terminal, thus shows lawyer's evaluating data by user terminal to user, with
In prior art user cannot rule or network be directly acquainted with the level of handling a case of lawyer and compare so that user can pass through lawyer
The professional standards of lawyer are got information about by evaluating data, so that user can save time when selecting lawyer, save
Power, find the lawyer of applicable user oneself accurately, greatly reduce selection professional standards relatively low or do not mate with self-demand
The probability of lawyer.
In correlation technique, user can not by rule institute introduction or lawyer lawyer on line platform data understand restrain
Shi Zhenzheng is good at the case type undertaken, it is therefore possible to the case type be good at of lawyer selected and user oneself need to solve
The case type belonging to dispute certainly does not also meet, thus cause the user loss, so, in order to make the user can more intuitively
To understand the type that holds brief of lawyer, in the present embodiment, according to the INFORMATION of the lawyer inquired, professional information and
The user satisfaction information that lawyer obtains generates lawyer's evaluating data of lawyer, further comprising the steps of (1) to step (2):
(1) obtain quantity information that this lawyer held brief under the default type that respectively holds brief and respectively hold brief
The working quality of case handling information held brief under type, wherein, hold brief type, including: contract law type, marriage law type,
Law of obligation type, merger and acquisition type, investment and financing type and stock's coming-into market type；
(2) quantity information that held brief under the default type that respectively holds brief according to the lawyer that gets and respectively holding
Do the working quality of case handling information held brief under case type, obtain the professional index in lawyer's evaluating data.
In above-mentioned steps 1, the type that holds brief is except including above-mentioned contract law type, marriage law type and the debt pointed out
Outside power method type, it is also possible to include other law segmentation field in existing law, repeat the most one by one.
The type that respectively holds brief preset, can be previously recorded in the case information that lawyer is held brief, so service
Device is by obtaining the case information that lawyer is held brief, it is possible to obtains lawyer and is held under the default type that respectively holds brief
The working quality of case handling information held brief under the quantity information of part and the type that respectively holds brief of handling a case.
In step 2 above, specialty index is exactly directly to show the type that respectively holds brief that this lawyer was undertaken
The working quality of case handling information held brief under the quantity information held brief and the type that respectively holds brief.
In sum, by showing lawyer's institute's undertaking case under the default type that respectively holds brief in lawyer's evaluating data
The working quality of case handling information held brief under the quantity information of part and the type that respectively holds brief, it is possible to use family can be intuitively
Solve the case type that lawyer is good at, and according to the case type belonging to the dispute of oneself needs solution, select to be good at this case class
The lawyer of type, thus improve rate of winning a lawsuit or the success rate of self case, it is ensured that the rights and interests of user self are not suffered a loss.
In correlation technique, when needs amendment lawyer's information, commission of jurists first passes through the operation card login service device of oneself,
Then carry out the amendment of lawyer's information, but the operation of lawyer card number is the information that can inquire about, can be obtained by other people, institute
With any other people operation card number by lawyer, can login service device be revised the most broken by lawyer's information wantonly
Bad, so, the safety of lawyer's information is revised in order to improve lawyer, lawyer's evaluating data processing method that the present embodiment provides,
Further comprising the steps of (1) to step (10):
(1) obtaining the lawyer information editing request that user terminal sends, wherein, above-mentioned lawyer information editing request carries
The identification information of lawyer and first facial image of lawyer；
(2) according to the identification information of lawyer, second facial image of the lawyer prestored is inquired；
(3) it is multiple image-region by the first face image division of lawyer；
(4) from multiple image-regions, select k image-region to splice respectively, obtain multiple face subimage, its
In, multiple image-regions are the most averagely divided by the first facial image and obtain,m
Represent the image-region quantity of the first face image division；
(5) multiple face subimages and the second facial image to obtaining carry out degree of depth study, obtain the first face figure
The feature difference figure of picture and the second facial image；
(6) the feature difference figure obtained is carried out degree of depth study, obtain the ratio of the first facial image and the second facial image
To result；
(7) when obtaining the first facial image and the similar comparing result of the second facial image, eye is sent to user terminal
Ball motion information so that user carries out ocular movement according to the ocular movement information of display on user terminal；
(8) multiple ocular movement images when user carries out ocular movement are obtained；
(9) from multiple the ocular movement images of the user obtained, the movement locus of the point of fixation of the eyes of user is obtained；
(10) when the movement locus of the point of fixation according to the eyes got, determine that the eyes of user are according to ocular movement
During the motion that the prompting of information is carried out, it is allowed to user by user terminal to the INFORMATION of lawyer, professional information and
The user satisfaction information that lawyer obtains is edited.
Above-mentioned first facial image is the view data taken by photographic head that user terminal passes through to install.
In above-mentioned steps 3, by existing any image division method, the first human body image division is become predetermined number
Image-region, repeat the most one by one.Wherein, predetermined number may be greater than the natural number of 3, so in the present embodiment
One human body image is generally divided into the image-region of multiple quantity such as 4,5,6 or 7.
In above-mentioned steps 4, human body subimage, include the different piece of human body in the first human body image respectively, such as entering
After the splicing of row image-region, somebody's body subimage includes the head of human body in the first body image, somebody's body sub-picture pack
Include the upper body portion of human body in the first human body image, and somebody's body subimage includes the whole of human body in the first body image
Part.
By the description of above-mentioned steps 4, by from multiple image-regions, take varying number respectivelyImage-region splice, thus obtain multiple human body subimage, permissible
In the first human body image, human body is blocked in image only in the case of a part of human body image, can be by many to obtaining
Individual human body subimage is compared, and removes the part of the unrelated human body impact on human body image comparison in image as far as possible, improves
Success rate to human body image comparison.
In above-mentioned steps 5, multiple human body subimages and the second human body image are passed through have mutually isostructural two
Sub-convolutional neural networks carries out degree of depth study, and the sub-convolutional neural networks of the two is processed computing list by identical primary image
Unit, convolution algorithm unit and down-sampling arithmetic element are constituted.
Feature difference figure, is to represent the first human body image and the image of the second human body image similarity degree, Qi Zhongte
Levying each pixel value in differential chart and more tend to 0, the similarity degree of the first human body image and the second human body image is the highest.
In above-mentioned steps 6, use and in above-mentioned steps 5, above-mentioned human body subimage and the second human body image are carried out deeply
The sub-convolutional neural networks of the sub-convolutional neural networks different structure of degree study carries out degree of depth study to feature difference figure.
The sub-convolutional neural networks that feature difference figure carries out degree of depth study is processed arithmetic element, convolution fortune by primary image
Calculate unit, down-sampling arithmetic element and softmax grader composition.
Above-mentioned steps 9 specifically includes following steps (91) to step (93):
(91) the ball moving image of often opening one's eyes in multiple the ocular movement images obtained is carried out respectively eye location, and from
Ball moving image of often opening one's eyes behind location intercepts the eyes subimage of ball moving image of often opening one's eyes；
(92) from the eyes subimage of ball moving image of often opening one's eyes, extract iris image and/or the pupillogram of eyes respectively
Picture；
(93) according to the iris image extracted from ball moving image of often opening one's eyes and/or pupil image, eyes are calculated many
Open one's eyes the relative displacement between in ball moving image, and determine the motion of the point of fixation of eyes according to calculated relative displacement
Track.
In above-mentioned steps 91, the feature at each position of face can obtain from facial image, therefore to eyes
The when of location, eye location can be carried out according to the feature of eyes.After eye location, acquired should be
Eye contour coordinate in facial image, place can intercept in facial image according to the coordinate of acquired eyes,
Obtain the eyes subimage of ball moving image of often opening one's eyes.
In above-mentioned steps 92, under the conditions of various light sources, such as under visible ray or infrared ray radiation, the eye of people
The iris image of eyeball and pupil image are all directly can to obtain from eyes subimage, thus to eyes subimage
After reason, such as, removing noise jamming, then according to the iris prestored or the feature of pupil, from eyes subimage really
Make iris image or pupil image.
In above-mentioned steps 93, owing to people is seeing to certain target fiducials object when, eyeball can rotate, and then produces
Displacement.Usually, during dead ahead that eyes are visual the axis of pupil or iris as datum axis, then when eyes are seen to certain
During target fiducials object, even if the iris image that can obtain or pupil image, obtain iris or the axis of pupil at that time,
The axis of iris at that time or pupil is contrasted with datum axis, it becomes possible to calculate oculogyral relative displacement.And
In multiple face picture, oculogyral relative displacement combines, and just can form the movement locus of the point of fixation of eyes.This
The mode of point of fixation kind obtaining eyes is made without eye location, rely solely on eyeball be look to diverse location time
Waiting, the change in location of pupil or iris judges.
In above-mentioned steps 10, according to the movement locus of the point of fixation of the eyes got, determine the eyes of user be by
The motion carried out according to the prompting of ocular movement information, including one of in the following manner (a) and (b):
(a) when determining that the point of fixation of eyes of user targeted by target fiducials object, determine the eyes of user be according to
The motion that the prompting of ocular movement information is carried out, wherein, target fiducials object, is by ocular movement information in advance
Prompt the user with the object that need to watch attentively；
B () is when the movement locus of the point of fixation of the eyes determining user and the target fiducials object of display on user terminal
When movement locus is consistent, determine that the eyes of user are the motions carried out according to the prompting of ocular movement information.
In above-mentioned steps (a), after obtaining multiple ocular movement images when user carries out ocular movement, by judging
On multiple ocular movement images above-mentioned, the eye gaze point of display is the most consistent with target fiducials object position, determines user
Eyes whether targeted by target fiducials object.
In above-mentioned steps (b), after obtaining multiple ocular movement images when user carries out ocular movement, it is judged that above-mentioned
The movement locus of the eyes of display point of fixation formed in multiple facial images and target base on multiple ocular movement images
The movement locus of quasi-object is the most consistent, determines that the eyes of user are the fortune carried out according to the prompting of ocular movement information
Dynamic.
In sum, similarity pair is carried out by first facial image of acquisition lawyer with the second facial image prestored
Ratio, and when determining the first facial image and the second facial image is similar, then allow the eyes of lawyer believe according to ocular movement prompting
The motion that the prompting of breath is carried out, the most just allows lawyer to revise the lawyer's data of oneself, improves lawyer and revise lawyer's information
Safety.
In correlation technique, during carrying out human body image comparison, need the human body image obtained from image library
Carry out degree of depth study after dividing again, thus add the process time of human body image comparison；In order to reduce human figure
As the process time span of comparison, so in the present embodiment, above-mentioned steps 5 comprises the following steps (51) to step (55):
(51) multiple face subimages and the second facial image are carried out degree of depth study, obtain multiple first facial image special
Levy figure and the second facial image characteristic pattern；
(52) it is characterized value regional center, according in advance with each pixel coordinate of storage in default pixel coordinate set
If eigenvalue area size, ex-first lady's face characteristics of image figure will be worked as respectively and the second facial image characteristic pattern will be divided into multiple
The First Eigenvalue region and multiple Second Eigenvalue region；
(53) from multiple the First Eigenvalue regions and multiple Second Eigenvalue region, profile maxima is obtained respectively；
(54) calculate respectively from the First Eigenvalue region and the Second Eigenvalue region with same characteristic features value regional center
The difference of the profile maxima of middle acquisition, obtains multiple feature difference；
(55) with multiple feature differences as pixel value, according to default feature difference figure size, generate when ex-first lady's face
Characteristics of image figure and the feature difference figure of the second facial image characteristic pattern.
Specifically, step 51 comprises the following steps (511) to (512):
(511) from convolutional neural networks, the human body subimage obtained is carried out degree of depth study by first, obtain multiple the
One human body image characteristic pattern；
(512) from convolutional neural networks, arbitrary second human body image selected from image library is carried out the degree of depth by second
Study, obtains the second human body image characteristic pattern, and second is identical from the structure of convolutional neural networks from convolutional neural networks and first.
Wherein, from convolutional neural networks, first all includes that identical primary image processes fortune from convolutional neural networks and second
Calculate unit, convolution algorithm unit and down-sampling arithmetic element.
Certainly, first other can also be used in convolutional neural networks can to realize figure from convolutional neural networks and second
As any arithmetic element of degree of depth learning functionality, with substitute above-mentioned primary image process arithmetic element, convolution algorithm unit and
At least one arithmetic element in down-sampling arithmetic element, repeats the most one by one.
By the way of the description of above-mentioned step 52 to step 55, the first human body characteristics of image figure and the second people can be obtained
The feature difference figure of body characteristics of image figure, when the pixel value of each pixel in feature difference figure tends to 0, illustrates the first
The similarity degree of body image and the second human body image is the highest, thus to due to shooting angle and shooting time human body posture not
With causing, different photo seeming, difference is very greatly that the human body of same people effectively identifies in fact.
In sum, during human body image comparison, directly the second human body image is carried out degree of depth study, it is not necessary to will
Second human body image carries out dividing and carries out degree of depth study again, it is possible to reduce amount of calculation during image comparison, improves human body image
Comparison speed.
In correlation technique, the degree of depth learning outcome of each several part in respectively obtaining human body image to be detected and comparison people's image
After, just must can obtain human body image to be detected and the comparison of comparison people's image through more complicated Feature Fusion operation
As a result, in order to the comparison result of human body image, above-mentioned steps 6 can be obtained faster, (61) are comprised the following steps to step
(63):
(61) each feature difference figure obtained is carried out degree of depth study, obtain people's face that each feature difference figure is corresponding
Image and the similar parameter of the second facial image；
(62) determine that the similar parameter of maximum is as the first facial image and the similarity of the second facial image；
(63) when similarity is more than or equal to the similarity threshold set, the first facial image and the second facial image are obtained
Similar comparison result.
Above-mentioned steps 61 includes: draw, from convolutional neural networks, the human body subgraph that every feature difference figure is corresponding by the 3rd
As the similar parameter with the second human body image.
Above-mentioned 3rd sub-convolutional neural networks is processed arithmetic element, convolution algorithm unit, down-sampling computing by primary image
Unit and softmax grader composition.
Certainly, the 3rd other can also be used in convolutional neural networks can to realize any of picture depth learning functionality
Arithmetic element, with substitute above-mentioned primary image process arithmetic element, convolution algorithm unit, down-sampling arithmetic element and
At least one arithmetic element in softmax grader, repeats the most one by one.
In sum, by the degree of depth study and simple numeric ratio to operation, it is possible to determine the first human body image with
Second human body image is the most similar, accelerates the comparison speed of human body image.
The computer program carrying out lawyer's evaluating data processing method that the embodiment of the present invention is provided, including storage
The computer-readable recording medium of program code, the instruction that described program code includes can be used for performing previous methods embodiment
Described in method, implement and can be found in embodiment of the method, do not repeat them here.
Those skilled in the art is it can be understood that arrive, for convenience and simplicity of description, the system of foregoing description,
The specific works process of device and unit, is referred to the corresponding process in preceding method embodiment, does not repeats them here.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method, permissible
Realize by another way.Device embodiment described above is only schematically, such as, and the division of described unit,
Being only a kind of logic function to divide, actual can have other dividing mode when realizing, and the most such as, multiple unit or assembly can
To combine or to be desirably integrated into another system, or some features can be ignored, or does not performs.Another point, shown or beg for
The coupling each other of opinion or direct-coupling or communication connection can be indirect by some communication interfaces, device or unit
Coupling or communication connection, can be electrical, machinery or other form.
The described unit illustrated as separating component can be or may not be physically separate, shows as unit
The parts shown can be or may not be physical location, i.e. may be located at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected according to the actual needs to realize the mesh of the present embodiment scheme
's.
It addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to two or more unit are integrated in a unit.
If described function is using the form realization of SFU software functional unit and as independent production marketing or use, permissible
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is the most in other words
The part contributing prior art or the part of this technical scheme can embody with the form of software product, this meter
Calculation machine software product is stored in a storage medium, including some instructions with so that a computer equipment (can be individual
People's computer, server, or the network equipment etc.) perform all or part of step of method described in each embodiment of the present invention.
And aforesaid storage medium includes: USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory), random access memory are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic disc or CD.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art, in the technical scope that the invention discloses, can readily occur in change or replace, should contain
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should described be as the criterion with scope of the claims.
Claims (10)
1. lawyer's evaluating data processing method, it is characterised in that including:
Receiving the acquisition request of lawyer's evaluating data that user terminal sends, wherein, described acquisition request carries the mark of lawyer
Knowledge information, the user that described lawyer's evaluating data obtains according to INFORMATION, professional information and the described lawyer of described lawyer
Satisfaction information generates；
According to the identification information of described lawyer, inquire about what the INFORMATION of described lawyer, professional information and described lawyer obtained
User satisfaction information；
Raw according to the user satisfaction information that the INFORMATION of described lawyer inquired, professional information and described lawyer obtain
Become lawyer's evaluating data of described lawyer；
The described lawyer's evaluating data generated is sent to described user terminal to be shown.
Method the most according to claim 1, it is characterised in that described method also includes:
Obtaining the lawyer information editing request that user terminal sends, wherein, described lawyer information editing request carries lawyer's
Identification information and first facial image of lawyer；
According to the identification information of described lawyer, inquire second facial image of the described lawyer prestored；
It is multiple image-region by the first face image division of described lawyer；
From multiple described image-regions, select k image-region to splice respectively, obtain multiple face subimage, wherein,
Multiple described image-regions are the most averagely divided by described first facial image and obtain,m
Represent the image-region quantity of described first face image division；
The plurality of face subimage and described second facial image to obtaining carry out degree of depth study, obtain described the first
Face image and the feature difference figure of described second facial image；
The described feature difference figure obtained is carried out degree of depth study, obtains described first facial image and described second facial image
Comparison result；
When obtaining the described first facial image comparing result similar with described second facial image, send out to described user terminal
Send ocular movement information so that user carries out eye according to the described ocular movement information of display on described user terminal
Ball moves；
Acquisition user carries out multiple ocular movement images during ocular movement；
From multiple the ocular movement images of the described user obtained, obtain the motion rail of the point of fixation of the eyes of described user
Mark；
When the movement locus of the point of fixation according to the eyes got, determine that the eyes of described user are to point out according to ocular movement
During the motion that the prompting of information is carried out, it is allowed to user by described user terminal to the INFORMATION of described lawyer, professional information
And the user satisfaction information that described lawyer obtains edits.
Method the most according to claim 2, it is characterised in that to the plurality of face subimage obtained and described
Two facial images carry out degree of depth study, obtain the feature difference figure bag of described first facial image and described second facial image
Include:
Multiple described face subimages and described second facial image are carried out degree of depth study, obtains multiple first facial image special
Levy figure and the second facial image characteristic pattern；
It is characterized value regional center, according to default feature with each pixel coordinate of storage in default pixel coordinate set
Value area size, will work as ex-first lady's face characteristics of image figure respectively and described second facial image characteristic pattern will be divided into multiple first
Eigenvalue region and multiple Second Eigenvalue region；
Profile maxima is obtained respectively from the plurality of the First Eigenvalue region and the plurality of Second Eigenvalue region；
Calculate acquisition from the First Eigenvalue region with same characteristic features value regional center and Second Eigenvalue region respectively
The difference of profile maxima, obtains multiple feature difference；
With the plurality of feature difference as pixel value, according to default feature difference figure size, generate described when ex-first lady's face
Characteristics of image figure and the feature difference figure of described second facial image characteristic pattern.
Method the most according to claim 2, it is characterised in that the described feature difference figure obtained is carried out degree of depth study,
Obtain described first facial image and the comparison result of described second facial image, including:
The each feature difference figure obtained is carried out degree of depth study, obtains the face subimage that each described feature difference figure is corresponding
Similar parameter with described second facial image；
Determine the similar parameter similarity as described first facial image Yu described second facial image of maximum；
When described similarity is more than or equal to the similarity threshold set, obtain described first facial image and described second face
The comparison result of image similarity.
Method the most according to claim 2, it is characterised in that from multiple the ocular movement images of the described user obtained
In, obtain the movement locus of the point of fixation of the eyes of described user, including:
Ball moving image of often opening one's eyes in multiple ocular movement images described in obtaining is carried out eye location respectively, and from location
After described ball moving image of often opening one's eyes in intercept the eyes subimage of described ball moving image of often opening one's eyes；
Iris image and/or the pupillogram of described eyes is extracted respectively from the eyes subimage of described ball moving image of often opening one's eyes
Picture；
According to the described iris image extracted in ocular movement image described from every and/or described pupil image, calculate eyes
Relative displacement between in multiple ocular movement images described, and determine described eye according to calculated described relative displacement
The movement locus of the point of fixation of eyeball.
Method the most according to claim 2, it is characterised in that according to the movement locus of the point of fixation of the eyes got,
The eyes determining described user are the motions carried out according to the prompting of ocular movement information, including one of in the following manner:
When determining that the point of fixation of eyes of described user targeted by target fiducials object, determine the eyes of described user be according to
The motion that the prompting of ocular movement information is carried out, wherein, described target fiducials object, is to be pointed out by described ocular movement
Information prompts the user with the object that need to watch attentively in advance；
When the movement locus of point of fixation of the eyes determining described user and the described target fiducials object of display on user terminal
Movement locus consistent time, determine that the eyes of described user are the fortune carried out according to the prompting of described ocular movement information
Dynamic.
Method the most according to claim 1, it is characterised in that according to the INFORMATION of described lawyer inquired, operation
The user satisfaction information that information and described lawyer obtain generates lawyer's evaluating data of described lawyer, including:
In INFORMATION according to described lawyer, the academic information of described lawyer of record, universities and colleges teach information and number of publishing an article
Amount information, obtains the academic index in described lawyer's evaluating data；
In professional information according to described lawyer record described lawyer operation year limit information, hold brief total number letter
Breath and the working quality of case handling information that holds brief, obtain the operation index in described lawyer's evaluating data, wherein, described in handle a case matter
Amount information includes: described lawyer undertakes the rate of winning a lawsuit of case and undertakes the success rate of non-case；
According to the favorable comment quantity information of record in the user satisfaction information that described lawyer obtains and evaluation customer quantity information,
Satisfaction index in described lawyer's evaluating data.
Method the most according to claim 7, it is characterised in that according to the INFORMATION of described lawyer inquired, operation
The user satisfaction information that information and described lawyer obtain generates lawyer's evaluating data of described lawyer, also includes:
Obtain quantity information and the type that respectively holds brief that described lawyer is held brief under the default type that respectively holds brief
Lower held brief working quality of case handling information, wherein, described in hold brief type, including: contract law type, marriage law type,
Infringement Law type, merger and acquisition type, investment and financing type and stock's coming-into market type；
The quantity information held brief under the default type that respectively holds brief according to the described lawyer got and each undertaking
The working quality of case handling information held brief under case type generates the professional index in described lawyer's evaluating data.
Method the most according to claim 7, it is characterised in that according to the described rule of record in the INFORMATION of described lawyer
The academic information of teacher, universities and colleges teach information and quantity information of publishing an article, and obtain the academic index in described lawyer's evaluating data,
Including:
According to educational background and the corresponding relation of mark, the universities and colleges of record in default educational background-mark mapping table teach academic title-point
Number mapping table is remembered in the educational background of record and the corresponding relation of mark and quantity of publishing an article-mark mapping table
The corresponding relation of educational background and the mark of record, determines that the described educational background information of described lawyer, described universities and colleges are taught information and institute respectively
State the mark published an article corresponding to quantity information；
By the mark of academic information obtained, universities and colleges being taught the mark of information and the mark of quantity information of publishing an article is carried out
Calculate, generate the academic index in lawyer's evaluating data.
Method the most according to claim 7, it is characterised in that according to record in the professional information of described lawyer
The operation year limit information of lawyer, the total number information held brief and the working quality of case handling information held brief, obtain described
Operation index in lawyer's evaluating data, including:
According to the corresponding relation of the operation time limit of record in default operation year limit information-mark mapping table with mark, really
Law teacher operation year limit information mark；
Quantity is undertaken corresponding with mark according to the case of record in default undertaking case quantity-mark mapping table
Relation, determines that described lawyer undertakes the mark of case；
When determining that described lawyer undertakes the mark of case more than or equal to preset fraction, obtain what described lawyer held brief
Rate of winning a lawsuit information；
When according to rate information of winning a lawsuit described in getting, determining that the winning rate of described attorney's procuration plaintiff is more than the first winning rate preset
Threshold value and when acting on behalf of the winning rate of defendant more than the second winning rate threshold value preset, is undertaken described lawyer by the first default numerical value
The mark of case carries out autoincrementing operation；
When according to rate information of winning a lawsuit described in getting, determining that the winning rate of described attorney's procuration plaintiff is more than the first winning rate preset
Threshold value or when acting on behalf of the winning rate of defendant more than the second winning rate threshold value preset, is held described lawyer by default second value
The mark doing case carries out autoincrementing operation, and wherein, the first numerical value preset is more than the second value preset；
According to default described lawyer undertake in non-case quantity-mark mapping table the case of record undertake quantity with
The corresponding relation of mark, determines that described lawyer undertakes the mark of non-case；
When described lawyer undertakes the mark of non-case more than or equal to preset fraction, believed by the described success rate got
Breath, it is judged that whether described lawyer undertakes the success rate of non-case more than the success rate threshold value preset；
If it is, described lawyer undertaken the mark of non-case by the second value preset to carry out autoincrementing operation；
By to obtain operation year limit information mark, described lawyer undertakes the mark of case and described lawyer undertakes
The mark of non-case calculates, and obtains the operation index in lawyer's evaluating data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610413016.4A CN106097193A (en) | 2016-06-13 | 2016-06-13 | A kind of lawyer's evaluating data processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610413016.4A CN106097193A (en) | 2016-06-13 | 2016-06-13 | A kind of lawyer's evaluating data processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106097193A true CN106097193A (en) | 2016-11-09 |
Family
ID=57846691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610413016.4A Pending CN106097193A (en) | 2016-06-13 | 2016-06-13 | A kind of lawyer's evaluating data processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106097193A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107705227A (en) * | 2017-10-16 | 2018-02-16 | 窦尔翔 | A kind of network system for being used to provide law financial service |
| WO2018176861A1 (en) * | 2017-03-28 | 2018-10-04 | 华为技术有限公司 | Quality-of-service assessment method and terminal device |
| CN109508370A (en) * | 2018-09-28 | 2019-03-22 | 北京百度网讯科技有限公司 | Opinions Extraction method, equipment and storage medium |
| CN109919806A (en) * | 2019-03-11 | 2019-06-21 | 孟宪生 | A kind of one-stop wisdom law works platform and lawyer's evaluation method |
| CN109961225A (en) * | 2019-03-22 | 2019-07-02 | 成都华律就问信息技术服务有限公司 | A kind of lawyer's capability assessment model and method |
| CN111553577A (en) * | 2020-04-20 | 2020-08-18 | 北京北大软件工程股份有限公司 | Perfect law enforcement efficiency evaluation method and system |
| CN111861188A (en) * | 2020-07-15 | 2020-10-30 | 中国工商银行股份有限公司 | Case distribution method and device |
| CN112132455A (en) * | 2020-09-22 | 2020-12-25 | 平安国际智慧城市科技股份有限公司 | Traffic law enforcement evaluation method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120089640A1 (en) * | 2005-01-28 | 2012-04-12 | Thomson Reuters Global Resources | Systems, Methods, Software For Integration of Case Law, Legal Briefs, and Litigation Documents into Law Firm Workflow |
| CN104866969A (en) * | 2015-05-25 | 2015-08-26 | 百度在线网络技术（北京）有限公司 | Personal credit data processing method and device |
| CN105046219A (en) * | 2015-07-12 | 2015-11-11 | 上海微桥电子科技有限公司 | Face identification system |
| CN105096221A (en) * | 2015-07-21 | 2015-11-25 | 湖北翰群通信有限公司 | Lawyer mutual assistance system based on wireless network and method thereof |
| CN105208045A (en) * | 2015-10-28 | 2015-12-30 | 广东欧珀移动通信有限公司 | Identity authentication method, equipment and system |
-
2016
- 2016-06-13 CN CN201610413016.4A patent/CN106097193A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120089640A1 (en) * | 2005-01-28 | 2012-04-12 | Thomson Reuters Global Resources | Systems, Methods, Software For Integration of Case Law, Legal Briefs, and Litigation Documents into Law Firm Workflow |
| CN104866969A (en) * | 2015-05-25 | 2015-08-26 | 百度在线网络技术（北京）有限公司 | Personal credit data processing method and device |
| CN105046219A (en) * | 2015-07-12 | 2015-11-11 | 上海微桥电子科技有限公司 | Face identification system |
| CN105096221A (en) * | 2015-07-21 | 2015-11-25 | 湖北翰群通信有限公司 | Lawyer mutual assistance system based on wireless network and method thereof |
| CN105208045A (en) * | 2015-10-28 | 2015-12-30 | 广东欧珀移动通信有限公司 | Identity authentication method, equipment and system |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018176861A1 (en) * | 2017-03-28 | 2018-10-04 | 华为技术有限公司 | Quality-of-service assessment method and terminal device |
| US11966872B2 (en) | 2017-03-28 | 2024-04-23 | Huawei Technologies Co., Ltd. | Service quality evaluation method and terminal device |
| CN107705227A (en) * | 2017-10-16 | 2018-02-16 | 窦尔翔 | A kind of network system for being used to provide law financial service |
| CN109508370A (en) * | 2018-09-28 | 2019-03-22 | 北京百度网讯科技有限公司 | Opinions Extraction method, equipment and storage medium |
| CN109919806A (en) * | 2019-03-11 | 2019-06-21 | 孟宪生 | A kind of one-stop wisdom law works platform and lawyer's evaluation method |
| CN109961225A (en) * | 2019-03-22 | 2019-07-02 | 成都华律就问信息技术服务有限公司 | A kind of lawyer's capability assessment model and method |
| CN111553577A (en) * | 2020-04-20 | 2020-08-18 | 北京北大软件工程股份有限公司 | Perfect law enforcement efficiency evaluation method and system |
| CN111861188A (en) * | 2020-07-15 | 2020-10-30 | 中国工商银行股份有限公司 | Case distribution method and device |
| CN112132455A (en) * | 2020-09-22 | 2020-12-25 | 平安国际智慧城市科技股份有限公司 | Traffic law enforcement evaluation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106097193A (en) | A kind of lawyer's evaluating data processing method | |
| US9176579B2 (en) | Visual indication of user interests in a computer-generated virtual environment | |
| WO2022022028A1 (en) | Virtual object control method and apparatus, and device and computer-readable storage medium | |
| US20180308107A1 (en) | Living-body detection based anti-cheating online research method, device and system | |
| AU2023258377A1 (en) | Electronic platform for managing investment products | |
| CN108229280A (en) | Time domain motion detection method and system, electronic equipment, computer storage media | |
| CN108197532A (en) | The method, apparatus and computer installation of recognition of face | |
| CN110674664A (en) | Visual attention recognition method and system, storage medium and processor | |
| CN108491823A (en) | Method and apparatus for generating eye recognition model | |
| CN115437507B (en) | AR (augmented reality) -glasses-based equipment maintenance guiding method and system and related equipment | |
| US11810136B2 (en) | Systems and methods for assessing implicit associations | |
| US20230410435A1 (en) | Contextual positioning in virtual space | |
| US20240020813A1 (en) | Method and system for compliance determination | |
| Hussain et al. | The Impact of User-Generated Content, Social Interactions and virtual Economies on Metaverse Environments | |
| Watkins | Face Work: A Human-Centered Investigation into Facial Verification in Gig Work | |
| US20210241648A1 (en) | Systems and methods to provide mental distress therapy through subject interaction with an interactive space | |
| CN109034085B (en) | Method and apparatus for generating information | |
| CN114917590B (en) | Virtual reality game system | |
| CN114648900A (en) | Immersive interactive training method and system under VR combination | |
| CN114357132A (en) | Generation method, sorting method, device, equipment and storage medium of sorting model | |
| JP2007183792A (en) | Equipment operability evaluation device, equipment operability evaluation method and equipment operability evaluation program | |
| US20170039618A1 (en) | Automated Personalized Product Specification | |
| CN113850653A (en) | Product recommendation method based on convolutional neural network and related equipment | |
| Knigge | Virtual Reality in Manual Order Picking: Using Head-Mounted Devices for Planning and Training | |
| JP7418711B1 (en) | Attention extraction system and attention extraction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |