CN111198953A - Case text information based method and system for recommending cases and computer readable storage medium - Google Patents
Case text information based method and system for recommending cases and computer readable storage medium Download PDFInfo
- Publication number
- CN111198953A CN111198953A CN201811369302.0A CN201811369302A CN111198953A CN 111198953 A CN111198953 A CN 111198953A CN 201811369302 A CN201811369302 A CN 201811369302A CN 111198953 A CN111198953 A CN 111198953A
- Authority
- CN
- China
- Prior art keywords
- case
- processed
- text
- specific
- tags
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 229940079593 drug Drugs 0.000 claims description 9
- 239000003814 drug Substances 0.000 claims description 9
- 208000014674 injury Diseases 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000006378 damage Effects 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 206010011878 Deafness Diseases 0.000 claims description 4
- 208000027418 Wounds and injury Diseases 0.000 claims description 4
- 230000003340 mental effect Effects 0.000 claims description 3
- 230000002747 voluntary effect Effects 0.000 claims description 3
- 238000010521 absorption reaction Methods 0.000 claims 1
- 206010012218 Delirium Diseases 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 241000596504 Tamarindus Species 0.000 description 2
- 235000004298 Tamarindus indica Nutrition 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 206010002091 Anaesthesia Diseases 0.000 description 1
- GVGLGOZIDCSQPN-PVHGPHFFSA-N Heroin Chemical compound O([C@H]1[C@H](C=C[C@H]23)OC(C)=O)C4=C5[C@@]12CCN(C)[C@@H]3CC5=CC=C4OC(C)=O GVGLGOZIDCSQPN-PVHGPHFFSA-N 0.000 description 1
- 230000037005 anaesthesia Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 229960002069 diamorphine Drugs 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- VIKNJXKGJWUCNN-XGXHKTLJSA-N norethisterone Chemical compound O=C1CC[C@@H]2[C@H]3CC[C@](C)([C@](CC4)(O)C#C)[C@@H]4[C@@H]3CCC2=C1 VIKNJXKGJWUCNN-XGXHKTLJSA-N 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 239000002574 poison Substances 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Images
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 discloses a method, a system and a computer readable storage medium for recommending cases based on case text information, wherein the method for recommending cases based on case text information comprises the steps of constructing a database of specific tags of case text elements, wherein the case text elements comprise case causes, facts, plots, criminal subjects and criminal objects; importing a case text to be processed; analyzing the case text to be processed, and marking a corresponding specific label according to the case text element in the case text to be processed; matching the specific label of the case text to be processed with the class in the server; and sorting and displaying at least part of corresponding class information according to the matching degree. The case text information-based case recommending method is quicker in finding the case, more convenient and efficient to use and higher in matching accuracy.
Description
Technical Field
The invention relates to the technical field of legal case recommendation, in particular to a case text information-based method and system for recommending cases and a computer-readable storage medium.
Background
At present, when a judicial staff of a public inspection and law department needs to search for a case type, the corresponding case and fact plot need to be summarized by reading case documents, and then information such as the case is input on a case website to search for the corresponding case. This approach has several major drawbacks: 1. by referring to the case document to extract the corresponding case, fact and plot information, the process is time-consuming and some errors may occur. 2. The comprehensive matching degree can not be calculated on the case website according to a group of factual plot classes, so that a case which is more matched with the current case integrally is difficult to find. 3. No guiding case typical of local comparisons can be recommended. Therefore, the method wastes time and labor for looking up related cases, has low precision and is very inconvenient to use.
Disclosure of Invention
The invention mainly aims to provide a case text information-based case recommending method, which aims to search cases more quickly, use more conveniently and efficiently and match cases more accurately.
In order to achieve the purpose, the invention provides a method for recommending a case based on case text information, which comprises the following steps:
s10: constructing a database of specific tags of case text elements, wherein the case text elements comprise case causes, facts, plots, criminal subjects and criminal objects;
s30: importing a case text to be processed;
s40: analyzing the case text to be processed, and marking a corresponding specific label according to the case text element in the case text to be processed;
s50: matching the specific label of the case text to be processed with the class in the server;
s60: and sorting and displaying at least part of corresponding class information according to the matching degree.
Preferably, the specific tags of the culprit include a bribery tag, a greedy tag, a rape tag, a thunderstorm tag, an intentional injury-to-the-gunit tag, an illegal acquaintance-to-the-public deposit-to-the-gunit tag, an illegal arrest-to-the-gunit tag, a masking tag, a concealed criminal acquaintance-to-the-criminal tag, a criminal income-to-the-criminal, an aggressive pursuit-to-the-criminal tag, and a duty-to-the-job-to-the-criminal tag;
the specific labels of facts include smuggling labels, selling labels, transportation labels, labels for manufacturing large amount of drugs, labels for large amount of personal collective fraud, labels for other serious plots for which telecommunication fraud is difficult to be verified, labels for illegally absorbing large amount of public deposit, labels for illegally banning death of one person, labels for large amount of fraud, labels for manufacturing large amount of drugs, labels for large amount of personal collective fraud, labels for illegally banning serious injury of one person, labels for large amount of unit collective fraud, labels for serious plots for illegally holding drugs, and labels for especially large amount of fraud;
specific tags for an episode include an adherence criminal and settlement agreement tag, a chief offence tag, a denial of service tag, a withdrawal tag, a reimbursement tag, a positive compensation tag, a procurement understanding tag, a faithful statement tag, a crime failure tag, a antecedent handicap tag, a voluntary crime tag, a criminal offender tag, a corporate crime tag, and a crime termination tag;
the specific labels of the criminal subject include a deaf and mute label, a blind label, a mental patient label, an old person label and a minor label;
the specific tags of the criminal object include a minor tag, an old tag, and a disabled tag.
Preferably, S30 includes the steps of:
s31: dividing case texts to be processed into case headings, facts, plots, criminal bodies and criminal objects according to a regular matching rule;
s32: and respectively marking corresponding specific labels for case reasons, facts, plots, criminal subjects and criminal objects of the case texts to be processed according to the regular matching rules and the specific labels of the case text elements in the database.
Preferably, S40 specifically includes the following steps:
s41: matching key sentences and/or words in case text elements with corresponding case phrases, facts, plots, criminal subjects and criminal objects of the case text to be processed respectively according to the regular matching rules,
s42: and marking a specific label on the whole of the case text to be processed or the corresponding paragraph of the case text to be processed according to the matching result.
Preferably, S50 specifically includes the following steps:
s51: respectively assigning weights to case routing, facts, plots, criminal subjects, criminal objects and examination levels;
s52: calculating the score D of the case text to be processed, wherein the calculation formula is as follows: d × (number of specific tags by × R1+ number of specific tags of fact × R2+ number of specific tags of story × R3+ number of specific tags of body × R4+ number of specific tags of object × R5+ R6),
s53: calculating the score L of each class by the following formula: l × (number of cases of the class by the number of specific tags of cases hit by the case text to be processed × R1-X1/Y1 × R1+ the fact that the case text to be processed is hit by the fact of the class × R2-X2/Y2 × R2+ the number of specific tags of the episode of the case text to be processed in the episode hit by the case text to be processed × R3-X3/Y3 × R3+ the number of specific tags of the body of the case text to be processed × R4-X4/Y4 × R4+ the number of specific tags of the object of the class hit by the object of the case text to be processed × R5-X5/Y5 × R5+ the number of trial hits × R6),
s54: calculating the matching degree P, wherein the calculation formula is that P is D/L multiplied by 100 percent,
wherein R1 is case weight, R2 is fact weight, R3 is plot weight, R4 is crime subject weight, R5 is crime object weight, R6 is trial weight, a is matched single label score,
x1 is the number of specific tags in case group different from the text of case to be processed, X2 is the number of specific tags in fact different from the text of case to be processed, X3 is the number of specific tags in episode different from the text of case to be processed, X4 is the number of specific tags in criminal subject different from the text of case to be processed, X5 is the number of specific tags in criminal object different from the text of case to be processed,
y1 is the de-duplication number of the specific label and the class label of the case text to be processed in case composition, Y2 is the de-duplication number of the specific label and the class label of the case text to be processed in fact, Y3 is the de-duplication number of the specific label and the class label of the case text to be processed in the story, Y4 is the de-duplication number of the specific label and the class label of the case text to be processed in the criminal subject, and Y5 is the de-duplication number of the specific label and the class label of the case text to be processed in the criminal object.
Preferably, S60 specifically includes the following steps:
s61: and sorting and at least partially displaying according to the matching degree of the class information from high to low.
Preferably, after S10, S30 is preceded by the steps of:
s20: and analyzing the class in the server and marking a corresponding specific label.
Preferably, the following steps are also included after S60:
s70: when at least one specific label of the text of the case to be processed is selected, the corresponding case is highlighted.
The invention also provides a system for recommending the case based on the case text information, which comprises the following steps: a memory, a processor, and a program stored on the memory and executable on the processor that recommends a class based on case text information, wherein:
the program for recommending cases based on case text information realizes the steps of the method for recommending cases based on case text information as described above when being executed by the processor.
The invention also provides a computer readable storage medium, wherein the computer readable storage medium is stored with a program for recommending a case based on case text information, and the program for recommending a case based on case text information realizes the steps of the method for recommending a case based on case text information when being executed by a processor.
The technical scheme of the invention constructs a database of specific labels of case text elements, wherein the case text elements comprise case causes, facts, plots, criminal subjects and criminal objects; importing a case text to be processed; analyzing the case text to be processed, and marking a corresponding specific label according to the case text element in the case text to be processed; matching the specific label of the case text to be processed with the class in the server; and sorting and displaying at least part of corresponding class information according to the matching degree. When the method and the device are used for searching the type of the case text to be processed, only the case to be processed needs to be imported, and the specific label of the imported case to be processed is searched for the type through automatic operation processing, so that the type information with accurate matching degree is obtained, and the method and the device can search the type more quickly, use more conveniently and efficiently, and have higher matching precision.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a schematic view of a flow structure of an embodiment of a case text information-based case recommendation method according to the present invention;
FIG. 2 is a flow chart illustrating a method for recommending a case based on case text information according to another embodiment of the present invention;
FIG. 3 is a schematic diagram of a detailed flow chart of step S30 in FIGS. 1 and 2;
FIG. 4 is a schematic diagram of a detailed flow structure of step S40 in FIGS. 1 and 2;
FIG. 5 is a schematic diagram of a detailed flow structure of step S50 in FIGS. 1 and 2;
fig. 6 is a schematic diagram of a detailed flow structure of step S60 in fig. 1 and 2.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that all the directional indicators (such as up, down, left, right, front, and rear … …) in the embodiment of the present invention are only used to explain the relative position relationship between the components, the movement situation, etc. in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indicator is changed accordingly.
In the present invention, unless otherwise expressly stated or limited, the terms "connected," "secured," and the like are to be construed broadly, and for example, "secured" may be a fixed connection, a removable connection, or an integral part; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In addition, the descriptions related to "first", "second", etc. in the present invention are only for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
The invention provides a case text information based system for recommending cases. The case text information based system for recommending cases can be mobile devices such as mobile phones, smart phones, notebook computers, PAD (tablet personal computer) and the like, and fixed terminals such as desktop computers, servers and the like. The case text information based case text information recommendation type system comprises a memory, a processor and a case text information based case text information recommendation type program which is stored on the memory and can run on the processor.
Wherein the memory comprises at least one computer readable storage medium for storing an operating system installed in the case text information based recommended category system and various application software, such as program codes of a program for recommending a category based on case text information. In addition, the memory may also be used to temporarily store various types of data that have been output or are to be output.
The processor may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor is generally configured to control the overall operation of the case text information based case recommendation system. In this embodiment, the processor is configured to run a program code stored in the memory or process data, for example, run the program that recommends a class based on case text information.
Referring to fig. 1, when executed by the processor, the program for recommending cases based on case text information implements the following steps:
s10: constructing a database of specific tags of case text elements, wherein the case text elements comprise case causes, facts, plots, criminal subjects and criminal objects;
s30: importing a case text to be processed;
s40: analyzing the case text to be processed, and marking a corresponding specific label according to the case text element in the case text to be processed;
s50: matching the specific label of the case text to be processed with the class in the server;
s60: and sorting and displaying at least part of corresponding class information according to the matching degree.
The database can be stored in a server memory or a cloud server, case information in the database can be obtained through direct reading or internet, specific tags in the database are classified according to case text elements, and the specific tags of a case comprise bribery tags, greedy tags, rape tags, slub rump tags, intentional injury rump tags, illegal public deposit crime absorbing tags, illegal arrest tags, camouflage tags, concealed crime income tags, crime pursuit tags, and duty occupational crime tags;
the specific labels of facts include smuggling labels, selling labels, transportation labels, labels for manufacturing large amount of drugs, labels for large amount of personal collective fraud, labels for other serious plots for which telecommunication fraud is difficult to be verified, labels for illegally absorbing large amount of public deposit, labels for illegally banning death of one person, labels for large amount of fraud, labels for manufacturing large amount of drugs, labels for large amount of personal collective fraud, labels for illegally banning serious injury of one person, labels for large amount of unit collective fraud, labels for serious plots for illegally holding drugs, and labels for especially large amount of fraud;
specific tags for an episode include an adherence criminal and settlement agreement tag, a chief offence tag, a denial of service tag, a withdrawal tag, a reimbursement tag, a positive compensation tag, a procurement understanding tag, a faithful statement tag, a crime failure tag, a antecedent handicap tag, a voluntary crime tag, a criminal offender tag, a corporate crime tag, and a crime termination tag;
the specific labels of the criminal subject include a deaf and mute label, a blind label, a mental patient label, an old person label and a minor label;
the specific tags of the criminal object include a minor tag, an old tag, and a disabled tag.
One embodiment is: inputting the information which can only determine the case, such as the case number of the case to be processed, and the like, into a computer or a server, or directly reading the text of the case to be processed by the computer, analyzing and processing the text by an arithmetic processor, and splitting the text elements of the case in the text of the case to be processed into the text elements of the case according to a regular matching rule, wherein the method specifically comprises the following steps:
referring to fig. 3, S31: dividing case texts to be processed into case headings, facts, plots, criminal bodies and criminal objects according to a regular matching rule;
s32: and respectively marking corresponding specific labels for case reasons, facts, plots, criminal subjects and criminal objects of the case texts to be processed according to the regular matching rules and the specific labels of the case text elements in the database.
The regular matching rules for the facts are:
(stealing | total amount) [ ^. | A (ii) a Element ([ \\ \ s \ d, ] + [ million superfluous ]);
([ \ d-two-three-five-six-seven-eight ninety. ]) + [ thousand milli ] {0,1} g [ < Lambda >,. | a! (ii) a (ii) a Heroin;
(robbery | capture) [ ^. | A {0,30} ([ \ d, ] + [ million superfluous ]) element, (causing | to constitute | to beat) ([ ^ The.,; |) {0,5} minor injury.
The story elements correspond to regular matching rules such as:
(. | The! ,. ]? {0,10} (dirty | economic loss) (;
(use | adopt | + a (violence means | coercion means | anesthesia means);
{0,4} (disaster relief | rescue | flood prevention | pacifying | poverty-poverty | immigration | relief | medical treatment) {0,4} (money | property | material);
the imposition (military police | justice) {0,5} of a person is illegal (detained | arrest).
The criminal body corresponds to a regular matching rule such as:
but also deaf and dumb;
blind people;
a psychiatric patient;
elderly people in their seventy-five years of age;
minor.
The criminal object corresponds to a regular matching rule such as:
(victim | (crime);
(victim | (crime);
(victim | (crime).
Referring to fig. 4, S41 is executed again: matching key sentences and/or words in case text elements with corresponding case phrases, facts, plots, criminal subjects and criminal objects of the case text to be processed respectively according to the regular matching rules,
s42: and marking a specific label on the whole of the case text to be processed or the corresponding paragraph of the case text to be processed according to the matching result.
The method specifically comprises the steps of matching related keywords, words, sentences and the like in each case text element through a regular matching rule to mark specific labels, wherein the related keywords, words and sentences can be the same as or equal to information in the specific labels, analyzing the contents of the case text to be processed with the related keywords, words and sentences sentence by sentence according to each case text element, and marking the corresponding specific labels, the whole case text to be processed or corresponding paragraphs of the case text to be processed with the specific labels after matching is successful.
And then matching the specific label of the case text to be processed with the class case in the server through a regular matching rule, so that the matching efficiency and accuracy are higher, and the method specifically comprises the following steps:
referring to fig. 5, S51: respectively assigning weights to case routing, facts, plots, criminal subjects, criminal objects and examination levels;
s52: calculating the score D of the case text to be processed, wherein the calculation formula is as follows: d × (number of specific tags by × R1+ number of specific tags of fact × R2+ number of specific tags of story × R3+ number of specific tags of body × R4+ number of specific tags of object × R5+ R6),
s53: calculating the score L of each class by the following formula: l × (number of cases of the class by the number of specific tags of cases hit by the case text to be processed × R1-X1/Y1 × R1+ the fact that the case text to be processed is hit by the fact of the class × R2-X2/Y2 × R2+ the number of specific tags of the episode of the case text to be processed in the episode hit by the case text to be processed × R3-X3/Y3 × R3+ the number of specific tags of the body of the case text to be processed × R4-X4/Y4 × R4+ the number of specific tags of the object of the class hit by the object of the case text to be processed × R5-X5/Y5 × R5+ the number of trial hits × R6),
s54: calculating the matching degree P, wherein the calculation formula is that P is D/L multiplied by 100 percent,
wherein R1 is case weight, R2 is fact weight, R3 is plot weight, R4 is crime subject weight, R5 is crime object weight, R6 is trial weight, a is matched single label score,
x1 is the number of specific tags in case group different from the text of case to be processed, X2 is the number of specific tags in fact different from the text of case to be processed, X3 is the number of specific tags in episode different from the text of case to be processed, X4 is the number of specific tags in criminal subject different from the text of case to be processed, X5 is the number of specific tags in criminal object different from the text of case to be processed,
y1 is the de-duplication number of the specific label and the class label of the case text to be processed in case composition, Y2 is the de-duplication number of the specific label and the class label of the case text to be processed in fact, Y3 is the de-duplication number of the specific label and the class label of the case text to be processed in the story, Y4 is the de-duplication number of the specific label and the class label of the case text to be processed in the criminal subject, and Y5 is the de-duplication number of the specific label and the class label of the case text to be processed in the criminal object.
And finally, sequencing according to the matching degree and displaying at least part of corresponding type information on a display screen of the user side. For the user to review the class, further referring to fig. 6, by S61: and sorting and at least partially displaying according to the matching degree of the class information from high to low. The user can conveniently and quickly select the class with higher matching degree, and the use is more convenient and quicker.
Referring to fig. 2, further, the step of S60 is followed by the following steps:
s70: when at least one specific label of the text of the case to be processed is selected, the corresponding case is highlighted.
Specifically, after step S40, the specific label of the case text to be processed may be displayed, and the user may adjust and confirm the specific label, and when looking up the case, by clicking at least one specific label, the corresponding case or the corresponding word, or sentence in the corresponding case may be highlighted, such as one or more of the word, or sentence that is highlighted, changed in color, increased in size, changed in font, increased in background color, and the like, so as to facilitate the user to look up the case text more efficiently and conveniently.
Referring to fig. 2, in one embodiment, after S10 and before S30, the method includes the following steps:
s20: and analyzing the class in the server and marking a corresponding specific label.
The specific tags of the case text to be processed and the specific tags of the cases in the server can be matched, sequencing is carried out according to the matching degree, and at least part of corresponding case information is displayed, so that the operation processing is faster, the matching efficiency is higher, and the matching is more accurate.
One specific case is, for example, the following:
the defendant XX, male, 24 sunrise 6.1999, was born in delirium city in Hainan province, Han nationality, junior middle school culture degree, farmer, town XX town. The case is held by criminals at 2016, 7 and 21 days, and arrested at 2016, 8 and 26 days.
Legal attorney Li XX, male, born in 1976 at 12/7, Han nationality, farmer, lived XX town. Is the father of the defendant XX.
Legal attorney symbol XX, female, born at 6/14/1978, Han nationality, farmer, lived XX town. Is the mother of the advertised person XX.
The debate forest X, XX law firm lawyers are designated.
The case is detected by the public bureau of delirium, and the waited person XX is suspected of stealing, and the waited person XX is transferred to the home for examination and prosecution 10, 12 and 2016. After the admission of the hospital, the person to be defended is informed of having the right to entrust the defender in 2016 (10 months and 12 days), the person to be defended is informed of having the right to entrust the litigation attorney in 2016 (10 months and 12 days), the person to be defended is inquired legally, the opinion of the person to be defended is listened, and all the file materials are examined.
The examination finds out that:
1. in 2016, 5/22/11 hours, the defendees XX, ancient XX and "brother" (in escape) come to the vicinity of the parking lot of the heroic market in township, delirium, see that the defendees leaf X rides the electric vehicle to come out of the parking lot of the heroic market, put the leaf X in a handbag under the car head to steal, and the handbag is internally provided with 14783 yuan of cash RMB, 1 part of the iPhone and a bank card. After the solution, the stolen property is recovered and returned to the victim.
Because the price certification item does not meet the relevant regulations, the price certification center in delirium city does not accept the price identification for a apple mobile phone with the leaf X stolen.
2. In 2016, 5 months and 29 days, and in 19 days, people to be notified XX, ancient XX and "brother" come to the front of the great-way Baijiahui supermarket in Zhongxing of delirium city, and the bag carried by the person to be notified X is torn by a sharp blade, so that a wallet with cash RMB 6817 yuan is stolen. The victim is a disabled person. After the solution, the stolen property is recovered and returned to the victim.
In 2016, 7, 21 and 21 days, the police catches the XX with suspicious patterns in the released south road of the town, and after the disk inquiry education, the XX faithfully provides the criminal facts of the theft.
Evidence for the above facts is considered as follows:
the method comprises the following steps of standing population information with certificates, case arrival process, criminal judgment and release certificates;
statement of victim leaf X, Zhang X;
a supply for notifier XX;
the price is not accepted;
and (5) surveying the notes and the photos on site.
The institute believes that XX of a notifier is ignorant of national laws, aims at illegal occupation, associates adopt secret means, carries fiercers to secondarily steal the common RMB of other people in public places, has 21600 Yuan and larger amount, acts on the stipulation of the second hundred sixty four of the Chinese people's republic of China, and can pursue criminal responsibility of the notifier by stealing crimes. The defendant XX is full of sixteen years and less than eighteen years when carrying out the theft, is a crime of a minor, and is applicable to the rules of the seventeenth first and third clauses of the Chinese people's republic of China criminal law, and the punishment should be lightened or lightened. The waited person XX is considered as the first person by actively dealing with the crime fact after questioning and education due to suspicious patterns, and is applicable to the provision of sixty-seven items of the criminal action law of the people's republic of China, and the law can lighten the penalty.
Matching class results:
1. through a semantic analysis technology, the information of the specific label of the current case part is analyzed by combining a database of the specific label as follows:
the scheme is as follows: theft crime
Case type: criminal
Judging program: one trial
Case attribution: courts of delirium, delirium in Hainan province
Case type: disclosure case
A crime subject: sex: age at the time of committing a crime: age 17, ethnic group: chinese, cultural degree: junior middle school, occupation: farmers and addresses: XX City XX town, institute crime name: theft crime
Crime object: disabled person
Crime facts: the actual point label has large amount, the actual point label carries the murder to steal, the actual numerical value label has an involved case amount of 3 thousands to 3 thousands, and the actual numerical value label has a stealing frequency of more than 3 times
Crime scenes: minor, first, anti-contamination and anti-claim
2. According to the analyzed specific label information, the recommended partial classification scheme result is as follows:
criminal judgment book for criminal criminals of stealing certain yellow and certain Wu
[ fact ] the theft amount is large
[ episode ] to abate the dirt and refund the claim; tamarind white
The court considers that some farewebe Wu and some yellow have illegal possession as the purpose, the money of other people with property value 1692 yuan is secretly stolen, the amount is large, the behavior forms the stealing crime, and the farewebe is punished. . The criminal fact instructed and controlled by the public complaint organ is clear, the evidence is true and sufficient, and the name of the instructed and controlled criminal is established. The law can be penalized with light consideration that some advertised person Wu and some advertised person yellow really supply the criminal of the advertised person Wu and the stolen goods are returned to the infected person. According to the fact, nature, plot and degree of harm of behavior of the defended people to the society, the fact, nature, plot and degree of harm are regulated according to the regulations of the second hundred sixty four, the first, the sixth seventy third, the fifty fifth and the sixty fourth in the Chinese people's republic of China criminal law.
Criminal judgement book for illegal stealing and criminal
Multiple theft [ facts ]; the theft amount is large
[ episode ] to abate the dirt and refund the claim; tamarind white
The court considers that the defended person secretly steals other people's property three times with the purpose of illegal occupation by certain ignorant national laws, the covalent value of RMB 16180 yuan is large, the behavior forms the stealing crime, the fact that the official apperceive department indicates is clear, the evidence is sufficient, the crime name is established, and the defended person should be supported. The fatten people take a certain poison to implement theft, and the fatten people pay attention to the situation. The penalty may be paid from the light in view of the fact that the defendant is in a certain plain sight and the stolen goods have been recovered. According to the second hundred sixty four, fifty-second, sixty-fourth and sixty-seventh provisions of the Chinese people's republic of China law.
When the method and the device are used for searching the type of the case text to be processed, only the case to be processed needs to be imported, the specific label of the imported case to be processed is searched for the type through automatic operation processing, and the type information with accurate matching degree is obtained, so that the method and the device can search the type more quickly, use more conveniently and efficiently, and the matching accuracy is higher.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for recommending cases based on case text information is characterized by comprising the following steps:
s10: constructing a database of specific tags of case text elements, wherein the case text elements comprise case causes, facts, plots, criminal subjects and criminal objects;
s30: importing a case text to be processed;
s40: analyzing the case text to be processed, and marking a corresponding specific label according to the case text element in the case text to be processed;
s50: matching the specific label of the case text to be processed with the class in the server;
s60: and sorting and displaying at least part of corresponding class information according to the matching degree.
2. The case text information-based case recommendation class method of claim 1,
specific tags of the culprit include bribery tags, greedy tags, rape tags, extortion rump tags, intentional injury rump tags, illegal absorption public deposit rump tags, illegal containment rump tags, camouflage tags, concealed rump tags, crim income rump tags, aggressive rump tags, and duty encroachment tags;
the specific labels of facts include smuggling labels, selling labels, transportation labels, labels for manufacturing large amount of drugs, labels for large amount of personal collective fraud, labels for other serious plots for which telecommunication fraud is difficult to be verified, labels for illegally absorbing large amount of public deposit, labels for illegally banning death of one person, labels for large amount of fraud, labels for manufacturing large amount of drugs, labels for large amount of personal collective fraud, labels for illegally banning serious injury of one person, labels for large amount of unit collective fraud, labels for serious plots for illegally holding drugs, and labels for especially large amount of fraud;
specific tags for an episode include an adherence criminal and settlement agreement tag, a chief offence tag, a denial of service tag, a withdrawal tag, a reimbursement tag, a positive compensation tag, a procurement understanding tag, a faithful statement tag, a crime failure tag, a antecedent handicap tag, a voluntary crime tag, a criminal offender tag, a corporate crime tag, and a crime termination tag;
the specific labels of the criminal subject include a deaf and mute label, a blind label, a mental patient label, an old person label and a minor label;
the specific tags of the criminal object include a minor tag, an old tag, and a disabled tag.
3. The case text information-based case recommendation method according to claim 2, wherein S30 comprises the steps of:
s31: dividing case texts to be processed into case headings, facts, plots, criminal bodies and criminal objects according to a regular matching rule;
s32: and respectively marking corresponding specific labels for case reasons, facts, plots, criminal subjects and criminal objects of the case texts to be processed according to the regular matching rules and the specific labels of the case text elements in the database.
4. The case text information-based case recommendation class method according to claim 3, wherein S40 specifically comprises the steps of:
s41: matching key sentences and/or words in case text elements with corresponding case phrases, facts, plots, criminal subjects and criminal objects of the case text to be processed respectively according to the regular matching rules,
s42: and marking a specific label on the whole of the case text to be processed or the corresponding paragraph of the case text to be processed according to the matching result.
5. The case text information-based case recommendation class method according to claim 1, wherein S50 specifically comprises the steps of:
s51: respectively assigning weights to case routing, facts, plots, criminal subjects, criminal objects and examination levels;
s52: calculating the score D of the case text to be processed, wherein the calculation formula is as follows: d × (number of specific tags by × R1+ number of specific tags of fact × R2+ number of specific tags of story × R3+ number of specific tags of body × R4+ number of specific tags of object × R5+ R6),
s53: calculating the score L of each class by the following formula: l × (number of cases of the class by the number of specific tags of cases hitting the text of the case to be processed × R1-X1/Y1 × R1+ the fact that the case of the class hits the text of the case to be processed × number of specific tags of the fact that the case of the class hits the text of the case to be processed × R2-X2/Y2 × R2+ the episode of the case to be processed in the episode hit × R3-X3/Y3 × R3+ the number of specific tags of the body of the text of the case to be processed × R4-X4/Y4 × R4+ the number of specific tags of the object of the class hitting the text of the case to be processed × R5-X5/Y5 × R5+ the number of examination hits × R6),
s54: calculating the matching degree P, wherein the calculation formula is that P is D/L multiplied by 100 percent,
wherein R1 is case weight, R2 is fact weight, R3 is plot weight, R4 is crime subject weight, R5 is crime object weight, R6 is trial weight, a is matched single label score,
x1 is the number of specific tags in case group different from the text of case to be processed, X2 is the number of specific tags in fact different from the text of case to be processed, X3 is the number of specific tags in episode different from the text of case to be processed, X4 is the number of specific tags in criminal subject different from the text of case to be processed, X5 is the number of specific tags in criminal object different from the text of case to be processed,
y1 is the de-duplication number of the specific label and the class label of the case text to be processed in case composition, Y2 is the de-duplication number of the specific label and the class label of the case text to be processed in fact, Y3 is the de-duplication number of the specific label and the class label of the case text to be processed in the story, Y4 is the de-duplication number of the specific label and the class label of the case text to be processed in the criminal subject, and Y5 is the de-duplication number of the specific label and the class label of the case text to be processed in the criminal object.
6. The case text information-based case recommendation class method according to claim 5, wherein S60 specifically comprises the steps of:
s61: and sorting and at least partially displaying according to the matching degree of the class information from high to low.
7. The case text information-based case recommendation class method of claim 6, after S10, before S30 comprising the steps of:
s20: and analyzing the class in the server and marking a corresponding specific label.
8. The case text information-based case recommendation category method of claim 5, further comprising the following steps after S60:
s70: when at least one specific label of the text of the case to be processed is selected, the corresponding case is highlighted.
9. A system for recommending cases based on case text information is characterized in that the system for recommending cases based on case text information comprises: a memory, a processor, and a program stored on the memory and executable on the processor that recommends a class based on case text information, wherein:
the case text information based recommended class program, when executed by the processor, implements the steps of the case text information based recommended class method according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program for recommending a class based on case text information, which, when executed by a processor, implements the steps of the method for recommending a class based on case text information as recited in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811369302.0A CN111198953B (en) | 2018-11-16 | 2018-11-16 | Case text information based case recommending method, system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811369302.0A CN111198953B (en) | 2018-11-16 | 2018-11-16 | Case text information based case recommending method, system and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111198953A true CN111198953A (en) | 2020-05-26 |
| CN111198953B CN111198953B (en) | 2023-07-07 |
Family
ID=70746122
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811369302.0A Active CN111198953B (en) | 2018-11-16 | 2018-11-16 | Case text information based case recommending method, system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111198953B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111858925A (en) * | 2020-06-04 | 2020-10-30 | 国家计算机网络与信息安全管理中心 | Script extraction method and device for telecommunication network fraud event |
| CN112100212A (en) * | 2020-09-04 | 2020-12-18 | 中国航天科工集团第二研究院 | Case scenario extraction method based on machine learning and rule matching |
| CN112348714A (en) * | 2020-11-05 | 2021-02-09 | 科大讯飞股份有限公司 | Evidence chain construction method, electronic device and storage medium |
| CN113486158A (en) * | 2021-09-08 | 2021-10-08 | 中国司法大数据研究院有限公司 | Case situation comparison-based case retrieval method, device, equipment and storage medium |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1566418A (en) * | 2003-06-16 | 2005-01-19 | 旺宏电子股份有限公司 | Parameter monitoring system and method for wafer processing capacity per hour of wafer processing furnace |
| US20080282255A1 (en) * | 2007-05-09 | 2008-11-13 | Shinichi Kawamoto | Highly-available application operation method and system, and method and system of changing application version on line |
| JP2009276923A (en) * | 2008-05-13 | 2009-11-26 | Meiji Milk Prod Co Ltd | Facility management system in manufacturing plant |
| CN102111405A (en) * | 2010-12-17 | 2011-06-29 | 国家计算机网络与信息安全管理中心 | Method for compiling regular expression by proportionally dividing into two groups |
| CN102142009A (en) * | 2010-12-09 | 2011-08-03 | 华为技术有限公司 | Method and device for matching regular expressions |
| CN102609459A (en) * | 2012-01-12 | 2012-07-25 | 神州数码网络(北京)有限公司 | Method and device for string matching based on regular expression |
| CN103078808A (en) * | 2012-12-29 | 2013-05-01 | 大连环宇移动科技有限公司 | Data stream exchanging and multiplexing system and method suitable for multi-stream regular expression matching |
| JP2015138395A (en) * | 2014-01-22 | 2015-07-30 | 三菱重工業株式会社 | Maintenance management device, maintenance management method, and program |
| CN107145895A (en) * | 2017-03-13 | 2017-09-08 | 东方网力科技股份有限公司 | Public security crime class case analysis method based on k means algorithms |
| CN107798033A (en) * | 2017-03-01 | 2018-03-13 | 中南大学 | A kind of sorting technique of police field case text |
| CN107818138A (en) * | 2017-09-28 | 2018-03-20 | 银江股份有限公司 | A kind of case legal regulation recommends method and system |
| CN108009299A (en) * | 2017-12-28 | 2018-05-08 | 北京市律典通科技有限公司 | Law tries method and device for business processing |
| CN108073569A (en) * | 2017-06-21 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of law cognitive approach, device and medium based on multi-layer various dimensions semantic understanding |
| CN108197163A (en) * | 2017-12-14 | 2018-06-22 | 上海银江智慧智能化技术有限公司 | A kind of structuring processing method based on judgement document |
| US20180181924A1 (en) * | 2016-12-28 | 2018-06-28 | Yokogawa Electric Corporation | Maintenance management device, maintenance management method, and non-transitory computer readable storage medium |
| CN108280149A (en) * | 2018-01-04 | 2018-07-13 | 东南大学 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
| CN108595547A (en) * | 2018-04-09 | 2018-09-28 | 南京网感至察信息科技有限公司 | A kind of similar case search method based on semantics extraction |
| CN108763484A (en) * | 2018-05-25 | 2018-11-06 | 南京大学 | A kind of law article recommendation method based on LDA topic models |
-
2018
- 2018-11-16 CN CN201811369302.0A patent/CN111198953B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1566418A (en) * | 2003-06-16 | 2005-01-19 | 旺宏电子股份有限公司 | Parameter monitoring system and method for wafer processing capacity per hour of wafer processing furnace |
| US20080282255A1 (en) * | 2007-05-09 | 2008-11-13 | Shinichi Kawamoto | Highly-available application operation method and system, and method and system of changing application version on line |
| JP2009276923A (en) * | 2008-05-13 | 2009-11-26 | Meiji Milk Prod Co Ltd | Facility management system in manufacturing plant |
| CN102142009A (en) * | 2010-12-09 | 2011-08-03 | 华为技术有限公司 | Method and device for matching regular expressions |
| CN102111405A (en) * | 2010-12-17 | 2011-06-29 | 国家计算机网络与信息安全管理中心 | Method for compiling regular expression by proportionally dividing into two groups |
| CN102609459A (en) * | 2012-01-12 | 2012-07-25 | 神州数码网络(北京)有限公司 | Method and device for string matching based on regular expression |
| CN103078808A (en) * | 2012-12-29 | 2013-05-01 | 大连环宇移动科技有限公司 | Data stream exchanging and multiplexing system and method suitable for multi-stream regular expression matching |
| JP2015138395A (en) * | 2014-01-22 | 2015-07-30 | 三菱重工業株式会社 | Maintenance management device, maintenance management method, and program |
| US20180181924A1 (en) * | 2016-12-28 | 2018-06-28 | Yokogawa Electric Corporation | Maintenance management device, maintenance management method, and non-transitory computer readable storage medium |
| CN107798033A (en) * | 2017-03-01 | 2018-03-13 | 中南大学 | A kind of sorting technique of police field case text |
| CN107145895A (en) * | 2017-03-13 | 2017-09-08 | 东方网力科技股份有限公司 | Public security crime class case analysis method based on k means algorithms |
| CN108073569A (en) * | 2017-06-21 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of law cognitive approach, device and medium based on multi-layer various dimensions semantic understanding |
| CN107818138A (en) * | 2017-09-28 | 2018-03-20 | 银江股份有限公司 | A kind of case legal regulation recommends method and system |
| CN108197163A (en) * | 2017-12-14 | 2018-06-22 | 上海银江智慧智能化技术有限公司 | A kind of structuring processing method based on judgement document |
| CN108009299A (en) * | 2017-12-28 | 2018-05-08 | 北京市律典通科技有限公司 | Law tries method and device for business processing |
| CN108280149A (en) * | 2018-01-04 | 2018-07-13 | 东南大学 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
| CN108595547A (en) * | 2018-04-09 | 2018-09-28 | 南京网感至察信息科技有限公司 | A kind of similar case search method based on semantics extraction |
| CN108763484A (en) * | 2018-05-25 | 2018-11-06 | 南京大学 | A kind of law article recommendation method based on LDA topic models |
Non-Patent Citations (2)
| Title |
|---|
| FIFTH NOVIYANTO ET.AL: "《Tracking online fraud using regular expression》" * |
| 王禄生: "《司法大数据与人工智能开发的技术障碍》", no. 20 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111858925A (en) * | 2020-06-04 | 2020-10-30 | 国家计算机网络与信息安全管理中心 | Script extraction method and device for telecommunication network fraud event |
| CN111858925B (en) * | 2020-06-04 | 2023-08-18 | 国家计算机网络与信息安全管理中心 | Script extraction method and device of telecommunication phishing event |
| CN112100212A (en) * | 2020-09-04 | 2020-12-18 | 中国航天科工集团第二研究院 | Case scenario extraction method based on machine learning and rule matching |
| CN112348714A (en) * | 2020-11-05 | 2021-02-09 | 科大讯飞股份有限公司 | Evidence chain construction method, electronic device and storage medium |
| CN113486158A (en) * | 2021-09-08 | 2021-10-08 | 中国司法大数据研究院有限公司 | Case situation comparison-based case retrieval method, device, equipment and storage medium |
| CN113486158B (en) * | 2021-09-08 | 2021-12-14 | 中国司法大数据研究院有限公司 | Case situation comparison-based case retrieval method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111198953B (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mercado et al. | The impact of specialized sex offender legislation on community reentry | |
| Lam | Pandemic sex workers’ resilience: COVID-19 crisis met with rapid responses by sex worker communities | |
| Duwe et al. | Does residential proximity matter? A geographic analysis of sex offense recidivism | |
| CN111198953A (en) | Case text information based method and system for recommending cases and computer readable storage medium | |
| Szablewska et al. | Anti-human trafficking campaigns: A systematic literature review | |
| Marx et al. | Routinizing the discovery of secrets: Computers as informants | |
| Sparrow et al. | Prevalence of self-reported intimate partner violence victimization among military personnel: A systematic review and meta-analysis | |
| Wantchekon et al. | The “game” of torture | |
| Gorman | Feminist legal archeology, domestic violence and the raced-gendered juridical boundaries of US asylum law | |
| Brewster et al. | Sex offender registries: A content analysis | |
| Pina-Sánchez et al. | Exploring the punitive surge: Crown Court sentencing practices before and after the 2011 English riots | |
| Hayes et al. | Are honor killings unique? A comparison of honor killings, domestic violence homicides, and hate homicides by far-right extremists | |
| Stassen et al. | Environmental and Wildlife Crime in Sweden from 2000 to 2017 | |
| Sleath et al. | Factor structure and validation of the controlling behaviors scale–revised and revised conflict tactics scale | |
| Arseniev-Koehler et al. | Aggression, escalation, and other latent themes in legal intervention deaths of non-hispanic Black and White men: Results from the 2003‒2017 National Violent Death Reporting System | |
| Kim et al. | Domestic violence in the context of the COVID-19 pandemic: a synthesis of systematic reviews | |
| Chaudhary et al. | Digital warfare against COVID-19: Global use of contact-tracing apps | |
| Howell | ‘We have to start showing who is boss now’: constructing methamphetamine use and users in the South African print media | |
| Aljehani | the Legal Definition of the Smuggling of Migrants in Light of the Provisions of the Migrant Smuggling Protocol | |
| Boehringer | Asia-Pacific: Duterte’s drug war: Violating rights for a quick fix | |
| Ryan et al. | From corpus creation to formative discovery: the power of big-data-rhetoric teams and methods | |
| Christensen et al. | Understanding what works in the police management of child sex offenders in the community | |
| Kim et al. | Does transnational terrorism stimulate foreign assistance? | |
| Karageorgos et al. | Perpetration, victimhood, and blame: Australian newspaper representations of domestic violence, 2000–2020 | |
| Schoon et al. | Repertoires of terror: News media classification of militant groups, 1970 to 2013 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |