CN109558993A - Prediction technique, device, storage medium and the server of theory of crime prison term - Google Patents
Prediction technique, device, storage medium and the server of theory of crime prison term Download PDFInfo
- Publication number
- CN109558993A CN109558993A CN201811546757.5A CN201811546757A CN109558993A CN 109558993 A CN109558993 A CN 109558993A CN 201811546757 A CN201811546757 A CN 201811546757A CN 109558993 A CN109558993 A CN 109558993A
- Authority
- CN
- China
- Prior art keywords
- crime
- prediction
- user
- charge
- input
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services; Handling legal documents
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Abstract
The invention discloses prediction technique, device, storage medium and the servers of a kind of theory of crime prison term, wherein the described method includes: successively obtaining crime charge and the crime area of user's input based on user terminal input interface；Based on crime charge condition and the measurement of penalty algorithm of determining a crime corresponding with regional Auto-matching of committing a crime；Preliminary sentence calculation processing is carried out using the measurement of penalty algorithm based on the information of the condition entry of determining a crime according to user is received, obtains the tentative prediction prison term；Impact factor of the user based on the impact factor list input for influencing the measurement of penalty is received, sentence calculation is carried out based on the tentative prediction prison term and the impact factor, obtains the prediction theory prison term.In embodiments of the present invention, respective handling can be carried out by the information that user inputs on terminal interface, it is final to calculate to the prediction prison term and to user's visualization display, it can greatly improve the working efficiency of bench and bar.
Description
Technical field
The present invention relates to technical field of data prediction more particularly to a kind of prediction technique of theory of crime prison term, device, deposit
Storage media and server.
Background technique
In law aid or law demand, user need to carry out a certain crime charge the prediction of crime prison term when
It waits, needs to carry out merit and circumstances of crime depth analysis by veteran judge or lawyer, can just provide corresponding crime
Prison term prediction, greatly increases the working strength and operating pressure of judge or lawyer in this way.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, and the present invention provides the predictions of theory of crime prison term a kind of
Method, apparatus, storage medium and server can carry out respective handling by the information that user inputs on terminal interface, most
It calculates eventually to the prediction prison term and to user's visualization display, can greatly improve the working efficiency of bench and bar.
In order to solve the above-mentioned technical problem, the embodiment of the invention provides the prediction technique of theory of crime prison term a kind of, institutes
The method of stating includes:
Crime charge and the crime area of user's input are successively obtained based on user terminal input interface；
Based on crime charge condition and the measurement of penalty algorithm of determining a crime corresponding with regional Auto-matching of committing a crime；
The preliminary prison term is carried out using the measurement of penalty algorithm based on the information of the condition entry of determining a crime according to user is received
Calculation processing obtains the tentative prediction prison term；
Impact factor of the user based on the impact factor list input for influencing the measurement of penalty is received, the tentative prediction prison term is based on
Sentence calculation is carried out with the impact factor, obtains the prediction theory prison term.
Optionally, the crime charge and crime area packet that user's input is successively obtained based on user terminal input interface
It includes:
Based on charge list information or input frame that user terminal input interface provides, user selects to click the charge column
Corresponding crime charge field input or carries out being manually entered crime the text field in input frame in table information；
The crime charge field of the corresponding input of Auto-matching, obtains crime charge in charge database；Or it is based on
NLP analysis model to it is described be manually entered crime the text field carry out charge analysis identify, obtain crime charge；
After obtaining crime charge, crime zone list information, user's selection are provided based on user terminal input interface
Corresponding Region field in the crime zone list information is clicked to be inputted；
The Region field of the corresponding input of Auto-matching, obtains crime area in crime area data library.
Optionally, described based on crime charge condition and the measurement of penalty algorithm of determining a crime corresponding with regional Auto-matching of committing a crime
Include:
After obtaining the crime charge and crime area, according to the crime charge and crime area respectively in correspondence
Determine a crime condition database and measurement of penalty algorithm data-base in carry out Auto-matching, obtain for user's input and/or user's selection
Condition of determining a crime and measurement of penalty algorithm.
Optionally, the condition of determining a crime includes that individual event selection determine a crime condition, text input of condition, multinomial selection of determining a crime is determined a crime
Condition, choose whether with it is multinomial now and the judgement situation that inputs determine a crime in condition any one or more combine.
Optionally, the basis receive user based on the condition entry of determining a crime information using the measurement of penalty algorithm into
Row preliminary sentence calculation processing, obtaining the tentative prediction prison term includes:
Judge whether the information based on the condition entry of determining a crime reaches the preset minimum crime of the crime charge and set up
Condition；
If it is not, continuing to determine whether to constitute the particular condition in the case which constitutes a crime from weight plot；
If it is not, then can't constitute a crime to user feedback；
If so, the basis receive user based on the condition entry of determining a crime information using the measurement of penalty algorithm into
The preliminary sentence calculation processing of row, obtains the tentative prediction prison term.
Optionally, the influence shadow includes from weight plot, from light plot, special body situation and the illegal resistance but origin of an incident；
It is described receive user based on influence the measurement of penalty impact factor list input impact factor include:
The impact factor list for influencing prison term prediction is provided at user terminal interface to select and/or input to user, is obtained
The impact factor for influencing prison term prediction of user's input.
Optionally, described that sentence calculation is carried out based on the tentative prediction prison term and the impact factor, obtain prediction reason
Include: by the prison term
Obtain increase and decrease prison term weight corresponding to the impact factor；
Sentence calculation is carried out based on the increase and decrease prison term weight and the tentative prediction prison term, obtains the prediction theory prison term.
Optionally, the method also includes:
Prediction result and legal opinion are generated based on the prediction theory prison term, and the prediction result and law are anticipated
See that book pushes to user terminal interface.
Optionally, described to include: based on prediction theory prison term generation prediction result and legal opinion
It is matched in legal opinion template database based on NLP algorithm highest with the prediction theory prison term similarity
Legal opinion template generates prediction result and legal opinion based on the highest legal opinion template example of the similarity.
Optionally, described the prediction result and legal opinion are pushed into user terminal interface to include:
Big data visualization processing is carried out to the prediction result and legal opinion, obtain visual prediction result and
Legal opinion；
Visual prediction result and legal opinion are pushed into user terminal interface.
In addition, the embodiment of the invention also provides the prediction meanss of theory of crime prison term a kind of, described device includes:
Information receives mould: for successively obtaining the crime charge and crime ground of user's input based on user terminal input interface
Area；
Matching module: for based on the crime charge corresponding with regional Auto-matching of committing a crime determine a crime condition and measurement of penalty calculation
Method；
Primary Calculation module: user is received based on the information of the condition entry of determining a crime using the measurement of penalty for basis
Algorithm carries out preliminary sentence calculation processing, obtains the tentative prediction prison term；
Prediction module: for receiving impact factor of the user based on the impact factor list input for influencing the measurement of penalty, it is based on institute
It states the tentative prediction prison term and the impact factor carries out sentence calculation, obtain the prediction theory prison term.
In addition, it is stored thereon with computer program the embodiment of the invention also provides a kind of computer readable storage medium,
The program realized when being executed by processor it is any one of above-mentioned described in the theory of crime prison term prediction technique.
In addition, the embodiment of the invention also provides a kind of servers comprising:
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and quilt
Be configured to be executed by one or more of processors, one or more of application programs are configured to: execution is appointed among the above
The prediction technique of theory of crime prison term described in meaning one.
In embodiments of the present invention, corresponding item of determining a crime is generated by the crime charge and crime area that obtain user's input
Part is inputted or is selected to user, to calculate the preliminary prison term, according to user's input on the prison term, there may be the influence shadows of influence
Son obtains the final prediction prison term to calculating, and the work effect of bench and bar is greatly improved in predictablity rate with higher
Rate.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it is clear that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow diagram of the prediction technique of the theory of crime prison term in the embodiment of the present invention；
Fig. 2 is the flow diagram of the prediction technique of the theory of crime prison term in another embodiment of the present invention；
Fig. 3 is the composed structure schematic diagram of the prediction meanss of the theory of crime prison term in the embodiment of the present invention；
Fig. 4 is the composed structure schematic diagram of the prediction meanss of the theory of crime prison term in another embodiment of the present invention；
Fig. 5 is the server composed structure schematic diagram in the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts all other
Embodiment shall fall within the protection scope of the present invention.
Embodiment
Referring to Fig. 1, Fig. 1 is the flow diagram of the prediction technique of the theory of crime prison term in the embodiment of the present invention.
As shown in Figure 1, a kind of prediction technique of theory of crime prison term, which comprises
S11: crime charge and the crime area of user's input are successively obtained based on user terminal input interface；
In specific implementation process of the present invention, the crime that user's input is successively obtained based on user terminal input interface
Charge and crime area include: the charge list information or input frame provided based on user terminal input interface, user's selected element
Corresponding crime charge field in the charge list information is hit input or carry out being manually entered crime text in input frame
This field；The crime charge field of the corresponding input of Auto-matching, obtains crime charge in charge database；Or it is based on
NLP analysis model to it is described be manually entered crime the text field carry out charge analysis identify, obtain crime charge；It is obtaining
After crime charge, crime zone list information is provided based on user terminal input interface, user selects to click the crime ground
Corresponding Region field is inputted in area's list information；In crime area data library the corresponding input of Auto-matching describedly
Area's field obtains crime area.
Specifically, user terminal includes any one end in the intelligent terminals such as smart phone, tablet computer, individual PC
End equipment should wherein be installed with corresponding user application software on the user terminal, after opening the application software, by answering
Input interface is provided to user terminal with software, and the charge list letter of user's input or selection is provided on the input interface
Breath, user is inputted by clicking the field of corresponding crime charge in the charge list information, or is directly manually entered
Corresponding charge field, the application software on user terminal are based on internet after the charge field for receiving user's input
The charge field is transmitted in server by network communication protocol, and server is after receiving band charge field, using the crime
File-name field is matched accordingly in charge database, obtains the crime being mutually matched with charge field crime by matching
Name；Server feeds back and provides into user terminal interface after obtaining the crime charge being mutually matched with the charge field
Crime zone list information selects to input for user, and user selects the Region field of crime in the crime zone list information,
It is inputted, which is based on Internet communication protocol and is transmitted in server, and server is in the criminal of receiving
After guilty Region field, crime Region field of Auto-matching input in the database in corresponding storage crime area, from
And it obtains accurate user and inputs the area of crime corresponding to crime Region field.
Specifically, server is carried out in charge database after receiving band charge field using the charge field
Corresponding matching obtains the crime charge being mutually matched with the charge field by matching, is by NLP (Natural
Language Processing) algorithm progress term vector calculates and text classification tool, and cooperate weighted model, judges automatically use
The field text information maximum probability of family input belongs to any crime charge, is linked from the background according to the prediction for pushing the charge；
NLP term vector calculates and text classification tool belongs to shallow-layer network, and precision is high, while being permitted fastly on the training time than depth network
Most magnitudes.
S12: based on crime charge condition and the measurement of penalty algorithm of determining a crime corresponding with regional Auto-matching of committing a crime；
It is described corresponding fixed based on the crime charge and regional Auto-matching of committing a crime in specific implementation process of the present invention
Guilty condition and measurement of penalty algorithm include: after obtaining the crime charge and crime area, according to the crime charge and crime
Area carries out Auto-matching in corresponding determine a crime condition database and measurement of penalty algorithm data-base respectively, obtains and inputs for user
And/or determine a crime condition and the measurement of penalty algorithm of user's selection.
Further, the condition of determining a crime includes that individual event selection determine a crime condition, text input of condition, multinomial selection of determining a crime is fixed
Guilty condition, choose whether with it is multinomial now and the judgement situation that inputs determine a crime in condition any one or more combine.
Specifically, the crime charge acquired and crime area are carried out corresponding by server in corresponding database
Match, such as determine a crime condition database and measurement of penalty algorithm data-base；Wherein, condition database of determining a crime is stored with different crime charges and criminal
The condition list information of determining a crime in guilty area；It is previously stored with different crime charges in measurement of penalty algorithm data-base and crime area calculates
Computational algorithm corresponding to prison term；The different measurement of penalty computational algorithms that each area and/or each crime charge have, i.e., together
One crime charge, in different crime areas, measurement of penalty computational algorithm may be different, as each determines a crime corresponding to condition
Calculating parameter it is default may be different, calculated result may be also different.
It is matched, is matched accordingly in condition database of determining a crime according to corresponding crime charge and crime area first
For the condition of determining a crime of user's input and/or user's selection, Auto-matching is then carried out in measurement of penalty algorithm data-base, matches this
Measurement of penalty algorithm of the crime charge in crime area.
S13: it is carried out tentatively based on the information of the condition entry of determining a crime using the measurement of penalty algorithm according to user is received
Sentence calculation processing, obtains the tentative prediction prison term；
In specific implementation process of the present invention, the basis is received user and is adopted based on the information of the condition entry of determining a crime
Preliminary sentence calculation processing is carried out with the measurement of penalty algorithm, obtaining the tentative prediction prison term includes: judgement based on the condition of determining a crime
Whether the information of input reaches the preset minimum crime establishment condition of the crime charge；If it is not, continue to determine whether constitute from
Particular condition in the case which constitutes a crime in weight plot；If it is not, then can't constitute a crime to user feedback；If so, described according to reception
Preliminary sentence calculation processing is carried out using the measurement of penalty algorithm based on the information of the condition entry of determining a crime to user, is obtained preliminary
Predict the prison term.
Specifically, specifically, server get input crime charge and crime area after, in the server in advance
In the prediction model being initially formed, which needs determining for user's offer according to crime charge is corresponding with the generation of crime area
Guilty condition is shown by server to user terminal interface, and when showing on terminal interface, the format provided is that user is defeated
The form and/or user that enter field select the form of input, and wherein these conditions of determining a crime include being not limited to individual event to select item of determining a crime
Part, multinomial selection determine a crime condition, text input determine a crime condition, choose whether with it is multinomial now and the judgement situation that inputs is determined a crime item
Any one or more combination in part.
Prediction model is the model built in advance on the server, and corresponding condition is arranged on prediction model, is being connect
Receive user for field information after (field information include crime charge, crime area, the prison term prediction impact factor
Deng), the corresponding field information of meeting Auto-matching generates corresponding guidance user and input is filled in or selected on terminal interface
Description is conducive to subsequent prison term prediction so that reaching guidance user fills in or input complete crime merit and area, and
And be conducive to ensure the precision of prediction；Prediction model first carries out the case carried out in data according to charge and regional keyword
Two layers of screening, using accurate fields match mode；It is precisely matched and fuzzy matching further according to the data of determining a crime of user's input
The mode mixed, partial key of determining a crime in database have carried out range to number respectively in case process,
The data for being related to property number are positioned and are matched in classification；It is related to number, number etc. to determine a crime case in factor, with database
Example is accurately matched.
Specifically, the input or selection that user is guided according to the condition of determining a crime input by above-mentioned condition of determining a crime
Field information, in the server, the prediction model are mutually matched the information of input in corresponding database, judge defeated
In the information entered, if reach minimum standard of determining a crime in corresponding charge, so that judging the field information of user's input is
No composition crime；If discovery is not up to minimum standard of determining a crime after matching, then pass through user terminal interface to the non-structure of user feedback
At crime, if after matching, reach it is minimum determine a crime standard or more when, in prediction model using relative to algorithm according to
The condition of determining a crime of input is calculated, and the preliminary prison term is predicted, to obtain the tentative prediction prison term.
S14: impact factor of the user based on the impact factor list input for influencing the measurement of penalty is received, the tentative prediction is based on
Prison term and the impact factor carry out sentence calculation, obtain the prediction theory prison term.
In specific implementation process of the present invention, the influence shadow includes from weight plot, from light plot, special body situation
The but origin of an incident is hindered with illegal；It is described receive user based on influence the measurement of penalty impact factor list input impact factor include: with
Family terminal interface provides the impact factor list for influencing prison term prediction and selects and/or input to user, obtains the shadow of user's input
Ring the impact factor of prison term prediction.
Further, described that sentence calculation is carried out based on the tentative prediction prison term and the impact factor, obtain prediction
The theoretical prison term includes: to obtain increase and decrease prison term weight corresponding to the impact factor；Based on the increase and decrease prison term weight and described
The tentative prediction prison term carries out sentence calculation, obtains the prediction theory prison term.
Specifically, specifically, server predicts mould after predicting the tentative prediction prison term by the calculating of relevant algorithm
The corresponding impact factor for influencing prison term prediction can be produced in type, the influence prison term impact factor of prediction passes through server feedback
It is to guide user that input and field is selected to input after feeding back onto user terminal interface to user terminal interface
Form, user according to shown on user terminal interface again guidance user select input and field input form impact factor into
The selection input of row actual conditions or field input, user terminal will be transmitted to server based on Internet communication protocol
End obtains the impact factor for influencing prison term prediction of user's input to complete to input.Wherein comprising being not limited in impact factor
From weight plot impact factor and/or from light plot impact factor, each plot impact factor includes multiple fields inputs, such as from
Plots impact factor such as calculated crime, subornation etc. during weight plot impact factor includes recidivist, previous conviction, disaster；From light feelings
Section impact factor includes to confess, confess one's crime, rendering meritorious service, giving up ill-gotten gains and pay compensation for, plead guilty in court；Special body situation is divided into reduction punishment by situation
Phase and directly negative crime；Backstage from weight plot to each corresponding to the increased measurement of penalty and carry out setting corresponding amplitude or ratio.
On the basis of the preliminary prison term, if recognizing user's input from the severe punishment phase, increase the punishment of corresponding amplitude or ratio
Phase similarly reduces the prison term, finally obtains total prison term.
Specifically, corresponding increase and decrease prison term weight is obtained by different impact factors, in the base of tentative prediction prison term
On plinth, corresponding plus-minus is carried out using increase and decrease prison term weight and is calculated, it is final to obtain the prediction theory prison term.
(belonged in legal sense from weight, from light plot, main information and other marks according to other labels of user's input
Label), parts of speech classification is carried out in NLP classifier, establishes keywords database；According to keywords database, according to progress in case database
The filtering and matching of full text or part paragraph；Full text matching, which refers to, to be scanned for and matches in the full text of official documents and correspondence case, part
Paragraph matching is identified and positioned according to paragraph field, be under the jurisdiction of the section or several sections of content of text be filtered and
Match, reaches the accurate screening purpose of document case；Sentence calculation is increased and decreased in conjunction with the correspondence situation in official documents and correspondence case.
In embodiments of the present invention, corresponding item of determining a crime is generated by the crime charge and crime area that obtain user's input
Part is inputted or is selected to user, to calculate the preliminary prison term, according to user's input on the prison term, there may be the influence shadows of influence
Son obtains the final prediction prison term to calculating, and the work effect of bench and bar is greatly improved in predictablity rate with higher
Rate.
Embodiment
Referring to Fig. 2, Fig. 2 is the process signal of the prediction technique of the theory of crime prison term in another embodiment of the present invention
Figure.
As shown in Fig. 2, a kind of prediction technique of theory of crime prison term, which comprises
S21: crime charge and the crime area of user's input are successively obtained based on user terminal input interface；
S22: based on crime charge condition and the measurement of penalty algorithm of determining a crime corresponding with regional Auto-matching of committing a crime；
S23: it is carried out tentatively based on the information of the condition entry of determining a crime using the measurement of penalty algorithm according to user is received
Sentence calculation processing, obtains the tentative prediction prison term；
S24: impact factor of the user based on the impact factor list input for influencing the measurement of penalty is received, the tentative prediction is based on
Prison term and the impact factor carry out sentence calculation, obtain the prediction theory prison term
In specific implementation process of the present invention, the specific implementation process in S21, S22, S23 and S24 can refer to above-mentioned implementation
Example, details are not described herein.
S25: generating prediction result and legal opinion based on the prediction theory prison term, and by the prediction result and method
Rule position paper pushes to user terminal interface.
It is described that prediction result and legal advice are generated based on the prediction theory prison term in specific implementation process of the present invention
Book include: matched in legal opinion template database based on NLP algorithm it is highest with the prediction theory prison term similarity
Legal opinion template generates prediction result and legal opinion based on the highest legal opinion template example of the similarity.
Specifically, NLP algorithm for identification charge, identify other labels；Identification charge predicts charge identification one with determining a crime
Cause, other than identifying charge, provide fixed labels such as: label of determining a crime is selected from weight plot label for user.Selected mark
Label, itself belong to the field attribute of database, which carries out data mistake according to NLP algorithm in the case data completed the process
Filter and matching, filter out corresponding case；Extraction includes identifying to judge to document, filters the document of not data, is extracted a large amount of
The document case prison term, the reprieve, remission data；The keyword of location data is established keyword database by NLP algorithm,
It in document case data after screening, is positioned by keyword database, and intellectual analysis changes paragraph where keyword
The data of prison term, the reprieve, fine are extracted within the scope of correlation length；The data of extraction are converted into uniting by participle and format conversion
One format is prepared for later data processing；Specifically based on NLP algorithm match in case database with prediction the prison term and
The highest legal opinion template of crime charge similarity is based on the legal advice after obtaining the legal opinion template
Book template generation prediction result and legal opinion.
It is further, described that the prediction result and legal opinion are pushed to user terminal interface includes: to described
Prediction result and legal opinion carry out big data visualization processing, obtain visual prediction result and legal opinion；It will
Visual prediction result and legal opinion push to user terminal interface.
Specifically, needing to carry out big data visualization processing to prediction result and legal opinion, obtain visual pre-
Survey result and legal opinion；Big data visualization processing is the data according to extraction, is made by the visualization in database
Tool, realizes prison term, the reprieve, the key production of remission data, and result includes: line chart, histogram, pie chart, map distribution
Model etc., processing result are controlled in Millisecond；Prediction result and complete legal opinion push, by guidance, case screening, can
Depending on change chart production, prediction result is pushed from the background, result includes: determine a crime judgement, measurement of penalty judgement, result point
The modules such as analysis, commutation suggestion, complete legal opinion；Legal opinion database template is established on backstage, real according to template function
When synchronous production legal opinion template, be pushed to user.
In embodiments of the present invention, corresponding item of determining a crime is generated by the crime charge and crime area that obtain user's input
Part is inputted or is selected to user, to calculate the preliminary prison term, according to user's input on the prison term, there may be the influence shadows of influence
Son obtains the final prediction prison term to calculating, and the work effect of bench and bar is greatly improved in predictablity rate with higher
Rate.
Embodiment
Referring to Fig. 3, Fig. 3 is the composed structure signal of the prediction meanss of the theory of crime prison term in the embodiment of the present invention
Figure.
As shown in figure 3, a kind of prediction meanss of theory of crime prison term, described device include:
Information receives mould 11: for successively obtaining the crime charge and crime of user's input based on user terminal input interface
Area；
In specific implementation process of the present invention, the crime that user's input is successively obtained based on user terminal input interface
Charge and crime area include: the charge list information or input frame provided based on user terminal input interface, user's selected element
Corresponding crime charge field in the charge list information is hit input or carry out being manually entered crime text in input frame
This field；The crime charge field of the corresponding input of Auto-matching, obtains crime charge in charge database；Or it is based on
NLP analysis model to it is described be manually entered crime the text field carry out charge analysis identify, obtain crime charge；It is obtaining
After crime charge, crime zone list information is provided based on user terminal input interface, user selects to click the crime ground
Corresponding Region field is inputted in area's list information；In crime area data library the corresponding input of Auto-matching describedly
Area's field obtains crime area.
Specifically, user terminal includes any one end in the intelligent terminals such as smart phone, tablet computer, individual PC
End equipment should wherein be installed with corresponding user application software on the user terminal, after opening the application software, by answering
Input interface is provided to user terminal with software, and the charge list letter of user's input or selection is provided on the input interface
Breath, user is inputted by clicking the field of corresponding crime charge in the charge list information, or is directly manually entered
Corresponding charge field, the application software on user terminal are based on internet after the charge field for receiving user's input
The charge field is transmitted in server by network communication protocol, and server is after receiving band charge field, using the crime
File-name field is matched accordingly in charge database, obtains the crime being mutually matched with charge field crime by matching
Name；Server feeds back and provides into user terminal interface after obtaining the crime charge being mutually matched with the charge field
Crime zone list information selects to input for user, and user selects the Region field of crime in the crime zone list information,
It is inputted, which is based on Internet communication protocol and is transmitted in server, and server is in the criminal of receiving
After guilty Region field, crime Region field of Auto-matching input in the database in corresponding storage crime area, from
And it obtains accurate user and inputs the area of crime corresponding to crime Region field.
Specifically, server is carried out in charge database after receiving band charge field using the charge field
Corresponding matching obtains the crime charge being mutually matched with the charge field by matching, is by NLP (Natural
Language Processing) algorithm progress term vector calculates and text classification tool, and cooperate weighted model, judges automatically use
The field text information maximum probability of family input belongs to any crime charge, is linked from the background according to the prediction for pushing the charge；
NLP term vector calculates and text classification tool belongs to shallow-layer network, and precision is high, while being permitted fastly on the training time than depth network
Most magnitudes.
Matching module 12: for based on the crime charge corresponding with regional Auto-matching of committing a crime determine a crime condition and the measurement of penalty
Algorithm；
It is described corresponding fixed based on the crime charge and regional Auto-matching of committing a crime in specific implementation process of the present invention
Guilty condition and measurement of penalty algorithm include: after obtaining the crime charge and crime area, according to the crime charge and crime
Area carries out Auto-matching in corresponding determine a crime condition database and measurement of penalty algorithm data-base respectively, obtains and inputs for user
And/or determine a crime condition and the measurement of penalty algorithm of user's selection.
Further, the condition of determining a crime includes that individual event selection determine a crime condition, text input of condition, multinomial selection of determining a crime is fixed
Guilty condition, choose whether with it is multinomial now and the judgement situation that inputs determine a crime in condition any one or more combine.
Specifically, the crime charge acquired and crime area are carried out corresponding by server in corresponding database
Match, such as determine a crime condition database and measurement of penalty algorithm data-base；Wherein, condition database of determining a crime is stored with different crime charges and criminal
The condition list information of determining a crime in guilty area；It is previously stored with different crime charges in measurement of penalty algorithm data-base and crime area calculates
Computational algorithm corresponding to prison term；The different measurement of penalty computational algorithms that each area and/or each crime charge have, i.e., together
One crime charge, in different crime areas, measurement of penalty computational algorithm may be different, as each determines a crime corresponding to condition
Calculating parameter it is default may be different, calculated result may be also different.
It is matched, is matched accordingly in condition database of determining a crime according to corresponding crime charge and crime area first
For the condition of determining a crime of user's input and/or user's selection, Auto-matching is then carried out in measurement of penalty algorithm data-base, matches this
Measurement of penalty algorithm of the crime charge in crime area.
Primary Calculation module 13: user is received based on the information of the condition entry of determining a crime using the amount for basis
Punishment algorithm carries out preliminary sentence calculation processing, obtains the tentative prediction prison term；
In specific implementation process of the present invention, the basis is received user and is adopted based on the information of the condition entry of determining a crime
Preliminary sentence calculation processing is carried out with the measurement of penalty algorithm, obtaining the tentative prediction prison term includes: judgement based on the condition of determining a crime
Whether the information of input reaches the preset minimum crime establishment condition of the crime charge；If it is not, continue to determine whether constitute from
Particular condition in the case which constitutes a crime in weight plot；If it is not, then can't constitute a crime to user feedback；If so, described according to reception
Preliminary sentence calculation processing is carried out using the measurement of penalty algorithm based on the information of the condition entry of determining a crime to user, is obtained preliminary
Predict the prison term.
Specifically, specifically, server get input crime charge and crime area after, in the server in advance
In the prediction model being initially formed, which needs determining for user's offer according to crime charge is corresponding with the generation of crime area
Guilty condition is shown by server to user terminal interface, and when showing on terminal interface, the format provided is that user is defeated
The form and/or user that enter field select the form of input, and wherein these conditions of determining a crime include being not limited to individual event to select item of determining a crime
Part, multinomial selection determine a crime condition, text input determine a crime condition, choose whether with it is multinomial now and the judgement situation that inputs is determined a crime item
Any one or more combination in part.
Prediction model is the model built in advance on the server, and corresponding condition is arranged on prediction model, is being connect
Receive user for field information after (field information include crime charge, crime area, the prison term prediction impact factor
Deng), the corresponding field information of meeting Auto-matching generates corresponding guidance user and input is filled in or selected on terminal interface
Description is conducive to subsequent prison term prediction so that reaching guidance user fills in or input complete crime merit and area, and
And be conducive to ensure the precision of prediction；Prediction model first carries out the case carried out in data according to charge and regional keyword
Two layers of screening, using accurate fields match mode；It is precisely matched and fuzzy matching further according to the data of determining a crime of user's input
The mode mixed, partial key of determining a crime in database have carried out range to number respectively in case process,
The data for being related to property number are positioned and are matched in classification；It is related to number, number etc. to determine a crime case in factor, with database
Example is accurately matched.
Specifically, the input or selection that user is guided according to the condition of determining a crime input by above-mentioned condition of determining a crime
Field information, in the server, the prediction model are mutually matched the information of input in corresponding database, judge defeated
In the information entered, if reach minimum standard of determining a crime in corresponding charge, so that judging the field information of user's input is
No composition crime；If discovery is not up to minimum standard of determining a crime after matching, then pass through user terminal interface to the non-structure of user feedback
At crime, if after matching, reach it is minimum determine a crime standard or more when, in prediction model using relative to algorithm according to
The condition of determining a crime of input is calculated, and the preliminary prison term is predicted, to obtain the tentative prediction prison term.
Prediction module 14: it for receiving impact factor of the user based on the impact factor list input for influencing the measurement of penalty, is based on
The tentative prediction prison term and the impact factor carry out sentence calculation, obtain the prediction theory prison term.
In specific implementation process of the present invention, the influence shadow includes from weight plot, from light plot, special body situation
The but origin of an incident is hindered with illegal；It is described receive user based on influence the measurement of penalty impact factor list input impact factor include: with
Family terminal interface provides the impact factor list for influencing prison term prediction and selects and/or input to user, obtains the shadow of user's input
Ring the impact factor of prison term prediction.
Further, described that sentence calculation is carried out based on the tentative prediction prison term and the impact factor, obtain prediction
The theoretical prison term includes: to obtain increase and decrease prison term weight corresponding to the impact factor；Based on the increase and decrease prison term weight and described
The tentative prediction prison term carries out sentence calculation, obtains the prediction theory prison term.
Specifically, specifically, server predicts mould after predicting the tentative prediction prison term by the calculating of relevant algorithm
The corresponding impact factor for influencing prison term prediction can be produced in type, the influence prison term impact factor of prediction passes through server feedback
It is to guide user that input and field is selected to input after feeding back onto user terminal interface to user terminal interface
Form, user according to shown on user terminal interface again guidance user select input and field input form impact factor into
The selection input of row actual conditions or field input, user terminal will be transmitted to server based on Internet communication protocol
End obtains the impact factor for influencing prison term prediction of user's input to complete to input.Wherein comprising being not limited in impact factor
From weight plot impact factor and/or from light plot impact factor, each plot impact factor includes multiple fields inputs, such as from
Plots impact factor such as calculated crime, subornation etc. during weight plot impact factor includes recidivist, previous conviction, disaster；From light feelings
Section impact factor includes to confess, confess one's crime, rendering meritorious service, giving up ill-gotten gains and pay compensation for, plead guilty in court；Special body situation is divided into reduction punishment by situation
Phase and directly negative crime；Backstage from weight plot to each corresponding to the increased measurement of penalty and carry out setting corresponding amplitude or ratio.
On the basis of the preliminary prison term, if recognizing user's input from the severe punishment phase, increase the punishment of corresponding amplitude or ratio
Phase similarly reduces the prison term, finally obtains total prison term.
Specifically, corresponding increase and decrease prison term weight is obtained by different impact factors, in the base of tentative prediction prison term
On plinth, corresponding plus-minus is carried out using increase and decrease prison term weight and is calculated, it is final to obtain the prediction theory prison term.
(belonged in legal sense from weight, from light plot, main information and other marks according to other labels of user's input
Label), parts of speech classification is carried out in NLP classifier, establishes keywords database；According to keywords database, according to progress in case database
The filtering and matching of full text or part paragraph；Full text matching, which refers to, to be scanned for and matches in the full text of official documents and correspondence case, part
Paragraph matching is identified and positioned according to paragraph field, be under the jurisdiction of the section or several sections of content of text be filtered and
Match, reaches the accurate screening purpose of document case；Sentence calculation is increased and decreased in conjunction with the correspondence situation in official documents and correspondence case.
In embodiments of the present invention, corresponding item of determining a crime is generated by the crime charge and crime area that obtain user's input
Part is inputted or is selected to user, to calculate the preliminary prison term, according to user's input on the prison term, there may be the influence shadows of influence
Son obtains the final prediction prison term to calculating, and the work effect of bench and bar is greatly improved in predictablity rate with higher
Rate.
Embodiment
Referring to Fig. 4, the composed structure that Fig. 4 is the prediction meanss of the theory of crime prison term in another embodiment of the present invention is shown
It is intended to.
As shown in figure 4, a kind of prediction meanss of theory of crime prison term, described device include:
Information receives mould 21: for successively obtaining the crime charge and crime of user's input based on user terminal input interface
Area；
Matching module 22: for based on the crime charge corresponding with regional Auto-matching of committing a crime determine a crime condition and the measurement of penalty
Algorithm；
Primary Calculation module 23: user is received based on the information of the condition entry of determining a crime using the amount for basis
Punishment algorithm carries out preliminary sentence calculation processing, obtains the tentative prediction prison term；
Prediction module 24: it for receiving impact factor of the user based on the impact factor list input for influencing the measurement of penalty, is based on
The tentative prediction prison term and the impact factor carry out sentence calculation, obtain the prediction theory prison term；
In specific implementation process of the present invention, information receives mould 21, matching module 22, primary Calculation module 23 and prediction mould
The specific embodiment of block 24 can refer to above-described embodiment, and details are not described herein.
Pushing module 25: generating prediction result and legal opinion based on the prediction theory prison term, and by the prediction
As a result user terminal interface is pushed to legal opinion.
It is described that prediction result and legal advice are generated based on the prediction theory prison term in specific implementation process of the present invention
Book include: matched in legal opinion template database based on NLP algorithm it is highest with the prediction theory prison term similarity
Legal opinion template generates prediction result and legal opinion based on the highest legal opinion template example of the similarity.
Specifically, NLP algorithm for identification charge, identify other labels；Identification charge predicts charge identification one with determining a crime
Cause, other than identifying charge, provide fixed labels such as: label of determining a crime is selected from weight plot label for user.Selected mark
Label, itself belong to the field attribute of database, which carries out data mistake according to NLP algorithm in the case data completed the process
Filter and matching, filter out corresponding case；Extraction includes identifying to judge to document, filters the document of not data, is extracted a large amount of
The document case prison term, the reprieve, remission data；The keyword of location data is established keyword database by NLP algorithm,
It in document case data after screening, is positioned by keyword database, and intellectual analysis changes paragraph where keyword
The data of prison term, the reprieve, fine are extracted within the scope of correlation length；The data of extraction are converted into uniting by participle and format conversion
One format is prepared for later data processing；Specifically based on NLP algorithm match in case database with prediction the prison term and
The highest legal opinion template of crime charge similarity is based on the legal advice after obtaining the legal opinion template
Book template generation prediction result and legal opinion.
It is further, described that the prediction result and legal opinion are pushed to user terminal interface includes: to described
Prediction result and legal opinion carry out big data visualization processing, obtain visual prediction result and legal opinion；It will
Visual prediction result and legal opinion push to user terminal interface.
Specifically, needing to carry out big data visualization processing to prediction result and legal opinion, obtain visual pre-
Survey result and legal opinion；Big data visualization processing is the data according to extraction, is made by the visualization in database
Tool, realizes prison term, the reprieve, the key production of remission data, and result includes: line chart, histogram, pie chart, map distribution
Model etc., processing result are controlled in Millisecond；Prediction result and complete legal opinion push, by guidance, case screening, can
Depending on change chart production, prediction result is pushed from the background, result includes: determine a crime judgement, measurement of penalty judgement, result point
The modules such as analysis, commutation suggestion, complete legal opinion；Legal opinion database template is established on backstage, real according to template function
When synchronous production legal opinion template, be pushed to user.
In embodiments of the present invention, corresponding item of determining a crime is generated by the crime charge and crime area that obtain user's input
Part is inputted or is selected to user, to calculate the preliminary prison term, according to user's input on the prison term, there may be the influence shadows of influence
Son obtains the final prediction prison term to calculating, and the work effect of bench and bar is greatly improved in predictablity rate with higher
Rate.
Embodiment
A kind of computer readable storage medium provided in an embodiment of the present invention stores on the computer readable storage medium
There is computer program, the prediction side of theory of crime prison term described in any one technical solution is realized when which is executed by processor
Method.Wherein, the computer readable storage medium includes but is not limited to any kind of disk (including floppy disk, hard disk, CD, CD-
ROM and magneto-optic disk), ROM (Read-Only Memory, read-only memory), RAM (Random AcceSS Memory, immediately
Memory), EPROM (EraSable Programmable Read-Only Memory, Erarable Programmable Read only Memory),
(Electrically EraSable ProgrammableRead-Only Memory, electric erazable programmable is read-only to be deposited EEPROM
Reservoir), flash memory, magnetic card or light card.It is, storage equipment includes by equipment (for example, computer, mobile phone) with energy
Any medium for the form storage or transmission message enough read can be read-only memory, disk or CD etc..
Referring to Fig. 5, Fig. 5 is the server composed structure schematic diagram in the embodiment of the present invention.
As shown in figure 5, a kind of server, processor 502, memory 503, input unit 504 and display unit 505 etc.
Device.Structure devices shown in fig. 5 do not constitute the restriction to Servers-all, can components more more or less than Fig. 5 or group
Close certain components.
Memory 503 can be used for storing application program 501 and each functional module, and the operation of processor 502 is stored in storage
The application program 501 of device 503, thereby executing the various function application and data processing of equipment.Memory can be interior storage
Device or external memory, or including both built-in storage and external memory.Built-in storage may include read-only memory (ROM),
Programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory or
Random access memory.External memory may include hard disk, floppy disk, ZIP disk, USB flash disk, tape etc..Memory packet disclosed in this invention
Include but be not limited to the memory of these types.Memory disclosed in this invention is only used as example rather than as restriction.
Input unit 504 is used to receive the input of signal, and receives the keyword of user's input.Input unit 504 can
Including touch panel and other input equipments.Touch panel collects the touch operation of user on it or nearby and (for example uses
Family uses the operations of any suitable object or attachment on touch panel or near touch panel such as finger, stylus), and root
According to the corresponding attachment device of preset driven by program；Other input equipments can include but is not limited to physical keyboard, function
One of key (such as broadcasting control button, switch key etc.), trace ball, mouse, operating stick etc. are a variety of.Display unit
505 can be used for showing the information of user's input or be supplied to the information of user and the various menus of terminal device.Display unit
505 can be used the forms such as liquid crystal display, Organic Light Emitting Diode.Processor 502 is the control centre of terminal device, using each
The various pieces of kind interface and connection whole equipment, by running or executing the software program being stored in memory 502
And/or module, and the data being stored in memory are called, perform various functions and handle data.
As one embodiment, the server includes: one or more processors 502, memory 503, and one or more
A application program 501, wherein one or more of application programs 501 are stored in memory 503 and are configured as by institute
The execution of one or more processors 502 is stated, one or more of programs 501 are configured to carry out the crime in above-described embodiment
The prediction technique of theoretical prison term.
Server provided in an embodiment of the present invention can realize the implementation of the prediction technique of the theory of crime prison term of above-mentioned offer
Example, concrete function realize the explanation that please be considered and examined in embodiment of the method, and details are not described herein.
In embodiments of the present invention, corresponding item of determining a crime is generated by the crime charge and crime area that obtain user's input
Part is inputted or is selected to user, to calculate the preliminary prison term, according to user's input on the prison term, there may be the influence shadows of influence
Son obtains the final prediction prison term to calculating, and the work effect of bench and bar is greatly improved in predictablity rate with higher
Rate.
In addition, be provided for the embodiments of the invention above the prediction technique of theory of crime prison term, device, storage medium and
Server is described in detail, and should use specific case herein and be explained the principle of the present invention and embodiment
It states, the above description of the embodiment is only used to help understand the method for the present invention and its core ideas；Meanwhile for this field
Those skilled in the art, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, to sum up institute
It states, the contents of this specification are not to be construed as limiting the invention.
Claims (13)
1. a kind of prediction technique of theory of crime prison term, which is characterized in that the described method includes:
Crime charge and the crime area of user's input are successively obtained based on user terminal input interface；
Based on crime charge condition and the measurement of penalty algorithm of determining a crime corresponding with regional Auto-matching of committing a crime；
Preliminary sentence calculation is carried out using the measurement of penalty algorithm based on the information of the condition entry of determining a crime according to user is received
Processing obtains the tentative prediction prison term；
Impact factor of the user based on the impact factor list input for influencing the measurement of penalty is received, the tentative prediction prison term and institute are based on
It states impact factor and carries out sentence calculation, obtain the prediction theory prison term.
2. prediction technique according to claim 1, which is characterized in that described successively to be obtained based on user terminal input interface
The crime charge of user's input and crime area include:
Based on charge list information or input frame that user terminal input interface provides, user selects to click the charge list letter
Corresponding crime charge field input or carries out being manually entered crime the text field in input frame in breath；
The crime charge field of the corresponding input of Auto-matching, obtains crime charge in charge database；Or based on NLP points
Analysis model to it is described be manually entered crime the text field carry out charge analysis identify, obtain crime charge；
After obtaining crime charge, crime zone list information is provided based on user terminal input interface, user selects to click
Corresponding Region field is inputted in the crime zone list information；
The Region field of the corresponding input of Auto-matching, obtains crime area in crime area data library.
3. prediction technique according to claim 1, which is characterized in that described regional certainly based on the crime charge and crime
Dynamic matching is corresponding to determine a crime condition and measurement of penalty algorithm includes:
After obtaining the crime charge and crime area, according to the crime charge and crime area respectively corresponding fixed
Auto-matching is carried out in guilty condition database and measurement of penalty algorithm data-base, is obtained and is determined a crime for what user's input and/or user selected
Condition and measurement of penalty algorithm.
4. prediction technique according to claim 3, which is characterized in that the condition of determining a crime includes that individual event selects item of determining a crime
Part, multinomial selection determine a crime condition, text input determine a crime condition, choose whether with it is multinomial now and the judgement situation that inputs is determined a crime item
Any one or more combination in part.
5. prediction technique according to claim 1, which is characterized in that the basis receives user and is based on the item of determining a crime
The information of part input carries out preliminary sentence calculation processing using the measurement of penalty algorithm, obtains the tentative prediction prison term and includes:
Judge whether the information based on the condition entry of determining a crime reaches the preset minimum crime establishment condition of the crime charge；
If it is not, continuing to determine whether to constitute the particular condition in the case which constitutes a crime from weight plot；
If it is not, then can't constitute a crime to user feedback；
It is carried out just based on the information of the condition entry of determining a crime using the measurement of penalty algorithm if so, the basis receives user
Sentence calculation processing is walked, the tentative prediction prison term is obtained.
6. prediction technique according to claim 1, which is characterized in that the influence shadow includes from weight plot, from light feelings
Section, special body situation and the illegal resistance but origin of an incident；
It is described receive user based on influence the measurement of penalty impact factor list input impact factor include:
The impact factor list for influencing prison term prediction is provided at user terminal interface to select and/or input to user, obtains user
The impact factor for influencing prison term prediction of input.
7. prediction technique according to claim 6, which is characterized in that described to be based on the tentative prediction prison term and the shadow
Ring the factor carry out sentence calculation, obtain the prediction theory prison term include:
Obtain increase and decrease prison term weight corresponding to the impact factor；
Sentence calculation is carried out based on the increase and decrease prison term weight and the tentative prediction prison term, obtains the prediction theory prison term.
8. prediction technique according to claim 1, which is characterized in that the method also includes:
Prediction result and legal opinion are generated based on the prediction theory prison term, and by the prediction result and legal opinion
Push to user terminal interface.
9. prediction technique according to claim 8, which is characterized in that described to generate prediction based on the prediction theory prison term
As a result include: with legal opinion
It is matched in legal opinion template database based on NLP algorithm and the highest law of prediction theory prison term similarity
Position paper template generates prediction result and legal opinion based on the highest legal opinion template example of the similarity.
10. prediction technique according to claim 9, which is characterized in that described by the prediction result and legal opinion
Pushing to user terminal interface includes:
Big data visualization processing is carried out to the prediction result and legal opinion, obtains visual prediction result and law
Position paper；
Visual prediction result and legal opinion are pushed into user terminal interface.
11. a kind of prediction meanss of theory of crime prison term, which is characterized in that described device includes:
Information receives mould: for successively obtaining crime charge and the crime area of user's input based on user terminal input interface；
Matching module: for based on crime charge condition and the measurement of penalty algorithm of determining a crime corresponding with regional Auto-matching of committing a crime；
Primary Calculation module: user is received based on the information of the condition entry of determining a crime using the measurement of penalty algorithm for basis
Preliminary sentence calculation processing is carried out, the tentative prediction prison term is obtained；
Prediction module: for receiving impact factor of the user based on the impact factor list input for influencing the measurement of penalty, based on described first
Step prediction prison term and the impact factor carry out sentence calculation, obtain the prediction theory prison term.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The prediction technique of the theory of crime prison term as described in any one of claims 1 to 10 is realized when execution.
13. a kind of server, characterized in that it comprises:
One or more processors；
Memory；
One or more application program, wherein one or more of application programs are stored in the memory and are configured
To be executed by one or more of processors, one or more of application programs are configured to: being executed according to claim 1
To the prediction technique of theory of crime prison term described in any one of 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546757.5A CN109558993A (en) | 2018-12-18 | 2018-12-18 | Prediction technique, device, storage medium and the server of theory of crime prison term |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546757.5A CN109558993A (en) | 2018-12-18 | 2018-12-18 | Prediction technique, device, storage medium and the server of theory of crime prison term |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109558993A true CN109558993A (en) | 2019-04-02 |
Family
ID=65870448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811546757.5A Pending CN109558993A (en) | 2018-12-18 | 2018-12-18 | Prediction technique, device, storage medium and the server of theory of crime prison term |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109558993A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751316A (en) * | 2019-09-26 | 2020-02-04 | 平安科技（深圳）有限公司 | Method and device for predicting resolution result and terminal equipment |
| CN111815485A (en) * | 2020-06-12 | 2020-10-23 | 中国司法大数据研究院有限公司 | Sentencing prediction method and device based on deep learning BERT model |
| CN112559855A (en) * | 2020-12-03 | 2021-03-26 | 北京博雅英杰科技股份有限公司 | Information query method, device, equipment and medium |
| CN112749826A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Criminal period prediction method, device, storage medium and equipment |
| CN113642756A (en) * | 2021-05-27 | 2021-11-12 | 复旦大学 | Criminal reduction criminal period prediction method based on deep learning technology |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950310A (en) * | 2010-10-08 | 2011-01-19 | 北京博雅英杰科技有限公司 | Sentencing normalizing system |
| CN103246925A (en) * | 2013-05-21 | 2013-08-14 | 林宝宗 | Sentencing suggestion management system |
| CN107578355A (en) * | 2017-09-08 | 2018-01-12 | 北京博雅英杰科技股份有限公司 | A kind of measurement of penalty method and apparatus |
| CN107918921A (en) * | 2017-11-21 | 2018-04-17 | 南京擎盾信息科技有限公司 | Criminal case court verdict measure and system |
| CN108460025A (en) * | 2018-04-09 | 2018-08-28 | 北京智慧正安科技有限公司 | Criminal case automates measurement of penalty method, apparatus and computer readable storage medium |
| CN109002431A (en) * | 2018-07-20 | 2018-12-14 | 吴怡 | Legal opinion generates system and production method |
-
2018
- 2018-12-18 CN CN201811546757.5A patent/CN109558993A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950310A (en) * | 2010-10-08 | 2011-01-19 | 北京博雅英杰科技有限公司 | Sentencing normalizing system |
| CN103246925A (en) * | 2013-05-21 | 2013-08-14 | 林宝宗 | Sentencing suggestion management system |
| CN107578355A (en) * | 2017-09-08 | 2018-01-12 | 北京博雅英杰科技股份有限公司 | A kind of measurement of penalty method and apparatus |
| CN107918921A (en) * | 2017-11-21 | 2018-04-17 | 南京擎盾信息科技有限公司 | Criminal case court verdict measure and system |
| CN108460025A (en) * | 2018-04-09 | 2018-08-28 | 北京智慧正安科技有限公司 | Criminal case automates measurement of penalty method, apparatus and computer readable storage medium |
| CN109002431A (en) * | 2018-07-20 | 2018-12-14 | 吴怡 | Legal opinion generates system and production method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751316A (en) * | 2019-09-26 | 2020-02-04 | 平安科技（深圳）有限公司 | Method and device for predicting resolution result and terminal equipment |
| CN112749826A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Criminal period prediction method, device, storage medium and equipment |
| CN111815485A (en) * | 2020-06-12 | 2020-10-23 | 中国司法大数据研究院有限公司 | Sentencing prediction method and device based on deep learning BERT model |
| CN112559855A (en) * | 2020-12-03 | 2021-03-26 | 北京博雅英杰科技股份有限公司 | Information query method, device, equipment and medium |
| CN113642756A (en) * | 2021-05-27 | 2021-11-12 | 复旦大学 | Criminal reduction criminal period prediction method based on deep learning technology |
| CN113642756B (en) * | 2021-05-27 | 2023-11-24 | 复旦大学 | Criminal investigation period prediction method based on deep learning technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109558993A (en) | Prediction technique, device, storage medium and the server of theory of crime prison term | |
| CN108089843B (en) | Intelligent bank enterprise-level demand management system | |
| CN108830745B (en) | Power grid cascading failure diagnosis, early warning and evaluation system based on monitoring information | |
| CN101645088B (en) | Determine the method for auxiliary lexicon, device and the input method system that need to load | |
| CN104392006B (en) | A kind of event query processing method and processing device | |
| CN109599114A (en) | Method of speech processing, storage medium and device | |
| CN109740928A (en) | Electric power consultation service treating method and apparatus | |
| CN110765268B (en) | Client appeal-based accurate distribution network investment strategy method | |
| CN102004792A (en) | Method and system for generating hot-searching word | |
| CN107704512A (en) | Financial product based on social data recommends method, electronic installation and medium | |
| CN107102993A (en) | A kind of user's demand analysis method and device | |
| CN112989761B (en) | Text classification method and device | |
| CN110909542B (en) | Intelligent semantic serial-parallel analysis method and system | |
| CN113779195B (en) | Hot event state evaluation method | |
| CN100470547C (en) | Method, system and device for implementing data mining model conversion and application | |
| CN109658156A (en) | A kind of material price measuring method, device, terminal device and storage medium | |
| CN109190716A (en) | Processing method, device and the electronic equipment of low-voltage collecting meter reading failure | |
| KR20100063289A (en) | System and method for managing work for integrating | |
| KR102519033B1 (en) | Artificial intelligence learning-based monitoring method for artificial intelligence learning-based laws and regulations and a program for this | |
| CN115794803A (en) | Engineering audit problem monitoring method and system based on big data AI technology | |
| CN103488750A (en) | Implementation method and system of network robot | |
| CN109472424B (en) | Method and device for predicting actual criminal period of crime, storage medium and server | |
| CN109918420B (en) | Competitor recommendation method and server | |
| CN111475548A (en) | Power utilization abnormity analysis decision system based on big data mining technology | |
| CN109598597A (en) | Business datum classifying method, device and storage medium, server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190402 |