CN116777696A - Legal knowledge automatic learning system and method - Google Patents
Legal knowledge automatic learning system and method Download PDFInfo
- Publication number
- CN116777696A CN116777696A CN202310788521.7A CN202310788521A CN116777696A CN 116777696 A CN116777696 A CN 116777696A CN 202310788521 A CN202310788521 A CN 202310788521A CN 116777696 A CN116777696 A CN 116777696A
- Authority
- CN
- China
- Prior art keywords
- cases
- case
- laws
- historical
- legal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 52
- 238000013500 data storage Methods 0.000 claims abstract description 12
- 238000012163 sequencing technique Methods 0.000 claims abstract description 6
- 238000007726 management method Methods 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000000586 desensitisation Methods 0.000 claims description 7
- 238000003058 natural language processing Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 claims description 5
- 230000006835 compression Effects 0.000 claims description 4
- 238000007906 compression Methods 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 claims 5
- 238000005259 measurement Methods 0.000 claims 2
- 230000002596 correlated effect Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 abstract description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a legal knowledge automatic learning system and a legal knowledge automatic learning method, relates to the technical field of automatic learning, and is used for solving the problems of low data quality, data privacy and safety; the intelligent notification system comprises a data acquisition module, a data encryption module, a data storage module, an intelligent matching module and an intelligent notification terminal; the method comprises the steps of comprehensively analyzing a section test and learning process of students to obtain weak knowledge points and a program value, sequencing related cases according to the sequence from the large program value to the small program value of the weak knowledge points to generate a knowledge point learning path, and sending the knowledge point learning path to a student end; the efficiency and the effect of law knowledge learning are improved by utilizing an automation technology, and students are helped to learn and master law knowledge more efficiently; the student consultation cases are preprocessed, then a proper teacher is selected for further analysis to obtain target cases and legal suggestions, and the answering and confusing efficiency of the teacher is effectively improved.
Description
Technical Field
The invention relates to the technical field of automatic learning, in particular to a legal knowledge automatic learning system and a legal knowledge automatic learning method.
Background
The legal knowledge learning system trains and obtains a model through a large amount of data so as to learn and judge the relation between cases and legal provision, and organizes the relation into a structured knowledge base, thereby providing professional solutions for students.
The prior art has the following technical problems:
1. the case analysis efficiency is not high: in the existing case analysis, a teacher analyzes the type of cases through the cases which are searched or learned by the teacher, and the case analysis efficiency of the teacher is seriously lowered by the analysis method, so that the cases which are proposed by the students can not be analyzed at once with high efficiency;
2. data privacy and security issues: automated learning systems require large amounts of data for learning and training, but these data involve sensitive information such as personal privacy and business confidentiality;
in order to solve the defects, an automatic learning system and an automatic learning method for legal knowledge are provided.
Disclosure of Invention
The invention aims to provide a legal knowledge automatic learning system and a legal knowledge automatic learning method for solving the problems of low data quality, data privacy and safety.
The aim of the invention can be achieved by the following technical scheme: the legal knowledge automatic learning system comprises a data acquisition module, a database, a data encryption module, a data storage module, a learning analysis module, an intelligent matching module and an intelligent notification terminal, wherein the data acquisition unit is used for acquiring legal information and historical case information and storing the legal information and the historical case information into the database;
the database comprises a common database and a backup database;
the data encryption module is used for encrypting the historical case data and sending the historical case data to the data storage module;
the data storage module is used for carrying out storage analysis on the received encrypted case information to obtain a management value, comparing and analyzing the management value with a set threshold value, recording case information corresponding to the management value smaller than the set threshold value as a processing case, and carrying out backup compression on the processing case and storing the processing case into the backup database;
the learning analysis module is used for analyzing the learning progress of the students to generate learning weak knowledge points, performing deepening analysis on the weak knowledge points to generate knowledge point learning paths, and sending the knowledge point learning paths to the student ends;
the intelligent matching module analyzes the student consultation case by artificial intelligent natural language processing to obtain a case law related to the student; meanwhile, according to the legal rules, inquiring historical cases related to the legal rules in the historical cases in a database; calculating the relevance of the student consultation case and the historical case related to the legal condition by using a relevance calculation model; recording a set number of historical cases before ranking the relevant degree as relevant cases, and sending the relevant case individual student consultation cases to a target teacher end;
the selection steps of the target teacher end are as follows:
step one: extracting the number of case analysis times of a teacher;
step two: the intelligent matching module sends a position acquisition instruction to the teacher end to acquire a teacher position, and calculates a distance difference value between the teacher position and the student end position to acquire a distance difference;
step three: extracting laws related to a teacher historical analysis case and counting to obtain all related laws and times related to buying the laws; comparing and matching the laws related to the student consultation case with all the laws related to the teacher to obtain the number of overlapped laws; counting the number of overlapping laws, and analyzing the number of times of the overlapping laws involved by a teacher;
step four: calculating the number of case analysis times r1, distance difference r2, number of overlapped laws r3 and number of overlapped laws r4 of the teacher by using a formulaObtaining a tamper score SFZ, and recording a teacher end with the highest tamper score as a target end, wherein c1, c2, c3 and c4 are respectively set proportionality coefficients;
step five: the teacher analyzes the input cases and the set number of related cases through the teacher's received input cases, screens out the target cases closest to the input cases, gives out related legal suggestions at the same time, and sends the target cases and the related legal suggestions to the intelligent notification module;
and when receiving the target case and the case analysis opinion, the intelligent notification module sends a receiving instruction to the student end, and when the student replies confirmation, the intelligent notification module sends the target case, the case analysis opinion and the target teacher contact information to the student end.
As a preferred embodiment of the present invention, the specific steps of storage analysis are:
step one: acquiring the storage time of the data, and calculating the difference value between the storage time and the current time of the system to obtain the storage time of the data;
step two: the method comprises the steps of calling laws related to historical student consultation cases, and counting the related times of the related laws; matching the historical cases with all the design laws to obtain the number of times of related laws;
step three: the method comprises the steps of calling laws related to historical case information, counting laws related to updated or obsolete laws, and recording the historical case information as old case information; counting the overage number of updated or invalidated legal strips related to the overage case information;
step four: setting a set storage time length corresponding to old case information and other normal history case information respectively; when the storage time length is longer than the specified storage time length, marking the historical case information as a processing case; acquiring browsing time of a processing case, browsing time length corresponding to each browsing time and browsing times; performing difference value calculation on adjacent browsing moments to obtain browsing interval duration;
step five: calculating the difference value of adjacent browsing time lengths to obtain a browsing time length difference, and calculating a slope I by using the adjacent browsing time length difference as a least square method; calculating the difference value of adjacent browsing interval time lengths to obtain interval change values, and calculating the slope II by using the adjacent interval change values as a least square method;
step six: summing all the first slopes to obtain a first slope sum, and summing all the second slopes to obtain a second slope sum;
step seven: passing the storage time period q1, the related times q2, the over-old quantity q3, the specified storage time period q4, the slope and one q5, the slope and two q6 through a set formulaAnd calculating to obtain a management value ZJM, wherein b1, b2, b3 and b4 are preset weight coefficients respectively.
As a preferred embodiment of the present invention, the learning analysis module performs a deep analysis on weak knowledge points to generate a knowledge point learning path, where the specific steps of the deep analysis are as follows:
step one: dividing law into a plurality of chapters, and attaching a contact score to each chapter; extracting a chapter small score and marking the chapter small score as e1;
step two: calculating the time length of the eyes to the screen and the time length of the chapter video in each chapter learning video by adopting a human eye line-of-sight tracking algorithm, and respectively marking the time length as e2 and e3;
step three: calculation using formulaObtaining a program value XCZ, wherein a1 and a2 are respectively set proportion coefficients, and a1 and a2 are respectively set proportion coefficients; comparing and analyzing the program value with the set degree value, and marking a section corresponding to the program value as a weak knowledge point when the program value is smaller than the set degree value;
step four: and extracting the program values of the weak knowledge points and the historical cases related to the legal laws in the weak knowledge points as related cases, sequencing the related cases according to the sequence from the large program values to the small program values of the weak knowledge points to generate a knowledge point learning path, and sending the knowledge point learning path to a student end.
As a preferred embodiment of the present invention, the specific steps of the correlation analysis are:
step one: analyzing the student consultation cases by using an artificial intelligence language training model to obtain case laws related to the consultation cases;
step two: inquiring historical cases related to the legal rules in the historical cases in a database according to the legal rules; respectively extracting the number of laws related to the historical cases and the number of laws related to the student consultation cases, and counting the number of the same laws in the historical cases and the student consultation cases related to the laws;
step three: the method comprises the steps of relating the number fa1 of laws related to historical cases, the number fa2 of laws related to student consultation cases and the number of the same lawsCalculating to obtain the correlation Gu of the student consultation cases and the historical cases related to the laws, and recording the historical cases with the correlation ranking a preset number as the related cases;
step four: and after the name and the place name in the related cases are subjected to sensitive information naming processing, desensitization related cases are obtained, the desensitization related cases are sent to a target teacher end, and the number of times of analysis of the cases by the target teacher is increased once.
As a preferred embodiment of the present invention, the system further comprises a registration login module;
the registration login module is used for registering and logging in students, students and teachers and uploading the information of the students and the teachers which are successfully registered to the database for storage; wherein the student personal information includes name, grade, contact information; the teacher personal information comprises names, job titles and contact ways;
the mobile terminal of the student, the mobile terminal of the student and the mobile terminal of the teacher which are successfully registered are respectively recorded as a student terminal and a teacher terminal; students learn legal knowledge and study and check through a learning end, and meanwhile, proper legal teachers are selected for analysis.
As a preferred embodiment of the present invention, the legal knowledge automatic learning method comprises the steps of:
s1: collecting legal and historical case information and storing the legal and historical case information into a common database in a database;
s2: encrypting historical case data to obtain encrypted case information;
s3: storing and analyzing the encrypted case information to obtain a management value, comparing and analyzing the management value with a set threshold value, recording case information corresponding to the management value smaller than the set threshold value as a processing case, and carrying out backup compression on the processing case and storing the processing case in a backup database;
s4: the learning progress of the students is analyzed to generate learning weak knowledge points, and the weak knowledge points are deeply analyzed to generate knowledge point learning paths, and the knowledge point learning paths are sent to the students;
s5: the intelligence analyzes the student consultation cases by utilizing artificial intelligent natural language processing to obtain case laws related to the students; meanwhile, according to the legal rules, inquiring historical cases related to the legal rules in the historical cases in a database; calculating the relevance of the student consultation case and the historical case related to the legal condition by using a relevance calculation model; recording a set number of historical cases before ranking the relevant degree as relevant cases, and sending the relevant case individual student consultation cases to a target teacher end; the teacher receives the relevant cases for inputting the cases and the set quantity through the teacher, analyzes and screens out the target cases closest to the cases for inputting, gives out relevant legal suggestions at the same time, and sends the target cases and the relevant legal suggestions to the intelligent notification module
S6: and sending the target cases, the case analysis opinions and the target teacher contact ways to the student end when the students reply and confirm by sending or not receiving instructions to the student end.
Compared with the prior art, the invention has the beneficial effects that:
1. the historical case information is subjected to desensitization encryption processing through the data encryption module and the data storage module to obtain encrypted case information, so that the data privacy and safety are guaranteed; and then, carrying out specific analysis on the laws related to the encrypted case information to obtain a management value, carrying out comparison analysis on the management value and a set threshold value, compressing, packaging and sending the case information corresponding to the management value smaller than the set threshold value to a backup database, so that the situation that the required data is deleted wrongly due to the directly set nonstandard specified duration is avoided, meanwhile, the management on the information in the database can be effectively improved, and the situation that the laws related to the historical case information are not consistent with the current laws due to accumulation of excessive information occupies the database memory is avoided.
2. Comprehensively analyzing a student chapter test and learning process to obtain a program value, carrying out price comparison analysis on the program value and a set degree value, marking a chapter corresponding to the program value as a weak knowledge point when the program value is smaller than the set degree value, extracting the program value of the weak knowledge point and a history case related to a law in the weak knowledge point as related cases, sequencing the related cases in sequence according to the program value of the weak knowledge point from large to small to generate a knowledge point learning path, and sending the knowledge point learning path to a student end; by utilizing artificial intelligent natural language processing and machine learning technology, personalized learning paths and contents can be deeply analyzed and provided, students are helped to learn and master legal knowledge more efficiently, the efficiency and effect of learning legal knowledge are improved by utilizing an automation technology, and students are helped to learn and master legal knowledge more efficiently.
3. Analyzing the student consultation cases by using an artificial intelligence language training model to obtain case laws related to the consultation cases, calculating the relevance between the student consultation cases and the historical cases related to the laws by using a relevance calculation model, and recording the historical cases with the top 10 relevance ranks as related cases; the method comprises the steps of performing sensitive information name processing on person names and place names in related cases to obtain desensitized related cases, sending the desensitized related cases to a selected target teacher end, and increasing the number of times of analyzing the cases by the target teacher once; the student consultation cases can be subjected to pre-analysis to identify corresponding laws and related cases with higher correlation degree and sent to the teacher end, the teacher further analyzes and selects target cases and attaches related legal suggestions and sends the target cases to the student end 1, and therefore efficiency of answering questions and solving confusion of students by the teacher is effectively improved.
Drawings
The present invention is further described below with reference to the accompanying drawings for the convenience of understanding by those skilled in the art.
Fig. 1 is a general block diagram of the system of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the legal knowledge automatic learning system includes a data acquisition module, a database, a data processing module, a data encryption module, a data storage module, an intelligent matching module, an intelligent notification terminal and a registration login module; the data acquisition module acquires legal information and historical case information and sends the legal information and the historical case information to the service database for storage;
the data encryption module encrypts collected legal data and historical case data and sends the encrypted legal data and the historical case data to the data storage module: calling case information, and dividing the case information into sensitive information and non-sensitive information; the sensitive information refers to personal privacy information of a principal, such as name, ID card number, address, etc., and information related to trade secrets or intellectual property rights; information related to personal privacy, such as call records, short message content, social account numbers, and the like; the non-sensitive information refers to basic information of the case, such as case name, case type, acceptance organization and the like; the case comprises the following aesthetic processes, such as the time of court, court trial records, judgment books and the like; the results of the cases, such as decision results, execution conditions, etc.; information related to public interests such as environmental protection, food and drug safety, etc.
Classifying case information characters according to the classification of the sensitive information and the non-sensitive information, setting a corresponding numerical value for each character, wherein the numerical values corresponding to the sensitive information characters and the non-sensitive information characters are different, and comparing and matching the characters with all the set characters to obtain corresponding character sequence values; the positions of numerical values of 0, 1 and 2 in the character sequence values are recorded as repeated calculation positions; and performing value-added calculation on the repeated calculation positions in the character sequence value to obtain a secondary ciphertext value-added sequence, wherein the specific step of value-added calculation is as follows:
step one: counting the number of 0, 1 and 2 in the character sequence value and the corresponding serial numbers respectively; wherein the sequence number refers to the sequence number from the first left digit to the position of 0, 1, 2 in the character sequence value;
step two: subtracting the right side value from the left side value of 0, 1 and 2 to obtain a difference value, and marking the difference value as a symbol difference value, wherein when the symbol difference value is greater than or equal to zero, the value of n is output as an odd number, and when the symbol difference value is less than zero, the value of n is output as an even number;
step three: substituting the symbol difference fu1, the sequence numbers fu2 and n into a set formulaCalculating to obtain a value Fu, replacing the value Fu with ' 0 ', 1 and 2 ' corresponding to the sequence number position to obtain a ciphertext value sequence, wherein f1 and f2 are set proportionality coefficients, and the ciphertext value sequence obtained by the value adding operation enables the position of the ciphertext value sequence, which is 0, to be filled compared with a character sequence value, and meanwhile the size of the whole value of the character sequence value to be increased; and marking the ciphertext value-added sequence as case encryption data, and sending the encryption case information to a data storage module.
The data storage module stores the received encrypted case information into a database, and the specific steps of updating the encrypted case information in the database are as follows:
step one: acquiring the storage time of the encrypted case information, calculating the difference value between the storage time and the current time of the system to obtain the storage time of the data, and marking the storage time as q1;
step two: retrieving the laws related to the historical cases and counting the related times of the related laws; matching the historical cases with all the design laws to obtain the number of times of related laws and marking the number of times as q2;
step three: the method comprises the steps of calling laws related to historical case information, counting laws related to updated or obsolete laws, and recording the historical case information as old case information; it should be noted that the updating of the legal regulations means that the original legal regulations are modified, supplemented or perfected so as to adapt to the social development and practice requirements; the revocation of legal regulations means that the original legal regulations are no longer applicable for some reasons and need to be revoked; counting the overage number of the updated or invalidated legal strips related to the overage case information and marking the overage number as q3;
step four: setting the past case information and other normal history case information to respectively correspond to a specified storage duration, and marking the past case information and other normal history case information as q4; when the storage time length is longer than the specified storage time length, marking the historical case information as a processing case; acquiring browsing time of a processing case, browsing time length corresponding to each browsing time and browsing times; performing difference value calculation on adjacent browsing moments to obtain browsing interval duration;
step five: calculating the difference value of adjacent browsing time lengths to obtain a browsing time length difference, and calculating a slope I by using the adjacent browsing time length difference as a least square method; calculating the difference value of adjacent browsing interval time lengths to obtain interval change values, and calculating the slope II by using the adjacent interval change values as a least square method;
step six: summing all the first slopes to obtain a first slope sum, summing all the second slopes to obtain a second slope sum, and marking the second slope sum as ZQ1 and JQ1 respectively; through a preset modelCalculating to obtain a management value ZJM, wherein b1, b2, b3 and b4 are preset weight coefficients respectively; when the management value is larger than the preset management value, marking the processed data as temporary unnecessary data, packaging, compressing and sending the temporary unnecessary data to a backup database, and avoiding the data which are needed to be deleted by mistake due to the directly set nonstandard specified time length, so that the data management capability can be effectively improved;
the specific steps of the learning analysis module for analyzing the learning progress of the student are as follows:
step one: dividing law into a plurality of chapters, and attaching a contact score to each chapter; extracting a chapter small score and marking the chapter small score as e1;
step two: calculating the time length of the eyes to the screen and the time length of the chapter video in each chapter learning video by adopting a human eye line-of-sight tracking algorithm, and respectively marking the time length as e2 and e3;
step three: calculation using formulaObtaining a program value XCZ, wherein a1 and a2 are set proportion coefficients respectively; comparing and analyzing the program value with the set degree value, and marking a section corresponding to the program value as a weak knowledge point when the program value is smaller than the set degree value;
step four: extracting a program value of a weak knowledge point and a history case related to a legal rule in the weak knowledge point, recording the program value and the history case as related cases, sequencing the related cases according to the sequence from the large program value to the small program value of the weak knowledge point to generate a knowledge point learning path, and transmitting the knowledge point learning path to a student end;
and sending the legal rules of the chapter and the historical cases related to the corresponding legal rules to the student end;
the intelligent matching module analyzes the student consultation cases by using an artificial intelligent language training model to obtain case laws related to the consultation cases; meanwhile, according to the legal rules, inquiring historical cases related to the legal rules in the historical cases in a database; calculating the relevance of the student consultation case and the historical case related to the legal condition by using a relevance calculation model; the specific steps of the correlation calculation are as follows: the method comprises the steps of respectively extracting the quantity fa1 of laws related to historical cases and the quantity fa2 of laws related to student consultation cases, and counting the quantity fa of the same laws in the historical cases and the laws related to the student consultation cases; using correlation formulasCalculating to obtain the correlation Gu of the student consultation cases and the historical cases related to the laws, recording the historical cases with the correlation ranking of top 10 as the relevant cases, sending the relevant cases to a target teacher end, and increasing the number of times of analyzing the cases by the target teacher once;
the selection steps of the target teacher end are as follows:
step one: the number of analysis cases of a teacher is extracted and recorded as r1;
step two: the intelligent matching module sends a position acquisition instruction to the teacher end to acquire a teacher position, calculates a distance difference value between the teacher position and the student end position to acquire a distance difference, and marks the distance difference as r2;
step three: extracting laws related to a teacher historical analysis case and counting to obtain all related laws and times related to buying the laws; comparing and matching the laws related to the student consultation case with all the laws related to the teacher to obtain the number of overlapped laws, and marking the number as r3; the overlapping laws refer to the laws related to the student consultation case and the laws related to the case when the teacher makes the case analysis; counting the number of overlapping laws, and recording the number of times of overlapping laws involved analyzed by a teacher as r4;
step four: calculation using formulaObtaining a tamper score SFZ, and recording a teacher end with the highest tamper score as a target end, wherein c1, c2, c3 and c4 are respectively set proportionality coefficients;
the teacher analyzes the input cases and 10 related cases through the teacher's terminal, screens out the target case closest to the input cases, gives out related legal suggestions at the same time, and sends the target case and the related legal suggestions to the intelligent notification module;
when receiving the target case and the case analysis opinion, the intelligent notification module sends a receiving instruction to the student end, and when the student replies confirmation, the intelligent notification module sends the target case and the case analysis opinion to the student end;
when the method is used, each character is set to correspond to a numerical value through the sensitive information and the non-sensitive information of the characters in the collected historical case information, the characters of the sensitive information and the characters corresponding to the non-sensitive information are not repeated, the characters are matched with all the set characters to obtain a character numerical value sequence, the positions of numerical values 0, 1 and 2 in the identification character sequence values are recorded as repeated calculation positions, and the repeated calculation positions are subjected to value-added calculation to obtain the encrypted case information; the data privacy and safety are guaranteed; then, calculating the time difference between the storage time of the encrypted case information and the current system time to obtain the storage time; the method comprises the steps that the laws related to the historical cases and the times of the laws related to the historical cases are related in the historical cases, and the laws related to the historical cases are analyzed to be updated and obsolete laws and the overused quantity; setting a specified storage time length corresponding to each history; the browsing time of the processing case, the corresponding browsing time length of each browsing time and the browsing times are processed; performing difference value calculation on adjacent browsing moments to obtain browsing interval duration; calculating the difference value of adjacent browsing time lengths to obtain a browsing time length difference, and calculating a slope I by using the adjacent browsing time length difference as a least square method; calculating the difference value of adjacent browsing interval time lengths to obtain interval change values, and calculating the slope II by using the adjacent interval change values as a least square method; summing all the first slopes to obtain a first slope sum, and summing all the second slopes to obtain a second slope sum; carrying out formulated analysis on the storage time length, the over-old number, the specified storage time length, the slope and the first and second slopes to obtain a management value; when the management value is larger than the preset management value, marking the processed data as temporary unnecessary data, packaging, compressing and sending the temporary unnecessary data to a backup database, avoiding the data which are needed to be deleted by mistake due to the directly set nonstandard specified time length, effectively improving the management of the information in the database, and avoiding the situation occupation database memory which is not in accordance with the current legal rules due to the fact that excessive historical situation information is accumulated;
comprehensively analyzing a student chapter test and learning process to obtain a program value, carrying out price comparison analysis on the program value and a set degree value, marking a chapter corresponding to the program value as a weak knowledge point when the program value is smaller than the set degree value, extracting the program value of the weak knowledge point and a history case related to a law in the weak knowledge point as related cases, sequencing the related cases in sequence according to the program value of the weak knowledge point from large to small to generate a knowledge point learning path, and sending the knowledge point learning path to a student end; by utilizing artificial intelligent natural language processing and machine learning technology, personalized learning paths and contents can be deeply analyzed and provided, students are helped to learn and master legal knowledge more efficiently, the efficiency and effect of learning legal knowledge are improved by utilizing an automation technology, and students are helped to learn and master legal knowledge more efficiently.
Analyzing the student consultation cases by using an artificial intelligence language training model to obtain case laws related to the consultation cases, calculating the relevance between the student consultation cases and the historical cases related to the laws by using a relevance calculation model, and recording the historical cases with the top 10 relevance ranks as related cases; the method comprises the steps of performing sensitive information name processing on person names and place names in related cases to obtain desensitized related cases, sending the desensitized related cases to a selected target teacher end, and increasing the number of times of analyzing the cases by the target teacher once; the student consultation cases can be subjected to pre-analysis to identify corresponding laws and related cases with higher correlation degree and sent to the teacher end, the teacher further analyzes and selects target cases and attaches related legal suggestions and sends the target cases to the student end 1, and therefore efficiency of answering questions and solving confusion of students by the teacher is effectively improved.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (6)
1. The legal knowledge automatic learning system comprises a data acquisition module and a database, wherein the data acquisition unit is used for acquiring legal information and historical case information and storing the legal information and the historical case information into the database; the intelligent notification system is characterized by further comprising a data encryption module, a data storage module, a learning analysis module, an intelligent matching module and an intelligent notification terminal;
the database comprises a common database and a backup database;
the data encryption module is used for encrypting the historical case data and sending the historical case data to the data storage module;
the data storage module is used for carrying out storage analysis on the received encrypted case information to obtain a management value, comparing and analyzing the management value with a set threshold value, recording case information corresponding to the management value smaller than the set threshold value as a processing case, and carrying out backup compression on the processing case and storing the processing case into the backup database;
the learning analysis module is used for analyzing the learning progress of the students to generate learning weak knowledge points, performing deepening analysis on the weak knowledge points to generate knowledge point learning paths, and sending the knowledge point learning paths to the student ends;
the natural language processing of the artificial intelligence of the intelligent matching module analyzes the student consultation case to obtain a case law related to the student; meanwhile, according to the legal rules, inquiring historical cases related to the legal rules in the historical cases in a database; calculating the relevance of the student consultation case and the historical case related to the legal condition by using a relevance calculation model; recording a set number of historical cases before ranking the relevant degree as relevant cases, and sending the relevant case individual student consultation cases to a target teacher end;
the selection steps of the target teacher end are as follows:
step one: extracting the number of case analysis times of a teacher;
step two: the intelligent matching module sends a position acquisition instruction to the teacher end to acquire a teacher position, and calculates a distance difference value between the teacher position and the student end position to acquire a distance difference;
step three: extracting laws related to a teacher historical analysis case and counting to obtain all related laws and times related to buying the laws; comparing and matching the laws related to the student consultation case with all the laws related to the teacher to obtain the number of overlapped laws; counting the number of overlapping laws, and analyzing the number of times of the overlapping laws involved by a teacher;
step four: normalizing the number of cases, the distance difference, the number of overlapped laws and the number of overlapped laws analyzed by a teacher, taking the numerical value, analyzing the numerical value to obtain a tamper score, and marking the teacher end with the maximum tamper score as a target end;
step five: the teacher analyzes the desensitization related cases which are used for inputting the cases and the set number through the teacher's terminal, screens out the target cases which are closest to the input cases, gives out related legal suggestions at the same time, and sends the target cases and the related legal suggestions to the intelligent notification module;
and when receiving the target case and the case analysis opinion, the intelligent notification module sends a receiving instruction to the student end, and when the student replies confirmation, the intelligent notification module sends the target case, the case analysis opinion and the target teacher contact information to the student end.
2. The automated knowledge learning system of claim 1, wherein the specific steps of storing the analysis are:
step one: acquiring the storage time of the data, and calculating the difference value between the storage time and the current time of the system to obtain the storage time of the data;
step two: the method comprises the steps of calling laws related to historical student consultation cases, and counting the related times of the related laws; matching the historical cases with all the design laws to obtain the number of times of related laws;
step three: the method comprises the steps of calling laws related to historical case information, counting laws related to updated or obsolete laws, and recording the historical case information as old case information; counting the overage number of updated or invalidated legal strips related to the overage case information;
step four: setting a set storage time length corresponding to old case information and other normal history case information respectively; when the storage time length is longer than the specified storage time length, marking the historical case information as a processing case; acquiring browsing time of a processing case, browsing time length corresponding to each browsing time and browsing times; performing difference value calculation on adjacent browsing moments to obtain browsing interval duration;
step five: calculating the difference value of adjacent browsing time lengths to obtain a browsing time length difference, and calculating a slope I by using the adjacent browsing time length difference as a least square method; calculating the difference value of adjacent browsing interval time lengths to obtain interval change values, and calculating the slope II by using the adjacent interval change values as a least square method;
step six: summing all the first slopes to obtain a first slope sum, and summing all the second slopes to obtain a second slope sum;
step seven: and carrying out formulated analysis on the storage time length, the over-old number, the specified storage time length, the slope and the first and second slopes to obtain a management value.
3. The automated knowledge learning system of claim 1, wherein the learning analysis module performs a deep analysis on the weak knowledge points to generate knowledge point learning paths, wherein the deep analysis comprises the steps of:
step one: dividing law into a plurality of chapters, and attaching a contact score to each chapter; extracting a chapter small measurement score;
step two: calculating the time length of the eyes to the screen and the time length of the chapter video in each chapter learning video by adopting a human eye line-of-sight tracking algorithm;
step three: performing numerical analysis on the chapter small measurement score, the eye-looking screen duration and the chapter video duration to obtain a program value; comparing and analyzing the program value with the set degree value, and marking a section corresponding to the program value as a weak knowledge point when the program value is smaller than the set degree value;
step four: and extracting the program values of the weak knowledge points and the historical cases related to the legal laws in the weak knowledge points as related cases, sequencing the related cases according to the sequence from the large program values to the small program values of the weak knowledge points to generate a knowledge point learning path, and sending the knowledge point learning path to a student end.
4. The automated knowledge learning system of claim 1, wherein the correlation analysis comprises the specific steps of:
step one: analyzing the student consultation cases by using an artificial intelligence language training model to obtain case laws related to the consultation cases;
step two: inquiring historical cases related to the legal rules in the historical cases in a database according to the legal rules; respectively extracting the number of laws related to the historical cases and the number of laws related to the student consultation cases, and counting the number of the same laws in the historical cases and the student consultation cases related to the laws;
step three: carrying out formulated calculation analysis on the number of laws related to the historical cases, the number of laws related to the student consultation cases and the number of the same laws to obtain the correlation degree of the student consultation cases and the historical cases related to the laws, and recording the historical cases with the correlation degree ranked by a preset number as the correlated cases;
step four: and after the name and the place name in the related cases are subjected to sensitive information naming processing, desensitization related cases are obtained, the desensitization related cases are sent to a target teacher end, and the number of times of analysis of the cases by the target teacher is increased once.
5. The automated knowledge learning system of claim 1, further comprising a registration log-in module;
the registration login module is used for registering and logging in students, students and teachers and uploading the information of the students and the teachers which are successfully registered to the database for storage; wherein the student personal information includes name, grade, contact information; the teacher personal information comprises names, job titles and contact ways;
the mobile terminal of the student, the mobile terminal of the student and the mobile terminal of the teacher which are successfully registered are respectively recorded as a student terminal and a teacher terminal; students learn legal knowledge and study and check through a learning end, and meanwhile, proper legal teachers are selected for analysis.
6. An automatic learning method for legal knowledge, comprising the following steps:
s1: collecting legal and historical case information and storing the legal and historical case information into a common database in a database;
s2: encrypting historical case data to obtain encrypted case information;
s3: storing and analyzing the encrypted case information to obtain a management value, comparing and analyzing the management value with a set threshold value, recording case information corresponding to the management value smaller than the set threshold value as a processing case, and carrying out backup compression on the processing case and storing the processing case in a backup database;
s4: the learning progress of the students is analyzed to generate learning weak knowledge points, and the weak knowledge points are deeply analyzed to generate knowledge point learning paths, and the knowledge point learning paths are sent to the students;
s5: the intelligence analyzes the student consultation cases by utilizing artificial intelligent natural language processing to obtain case laws related to the students; meanwhile, according to the legal rules, inquiring historical cases related to the legal rules in the historical cases in a database; calculating the relevance of the student consultation case and the historical case related to the legal condition by using a relevance calculation model; recording a set number of historical cases before ranking the relevant degree as relevant cases, and sending the relevant case individual student consultation cases to a target teacher end; the teacher receives the desensitization related cases for inputting the cases and the set quantity through the teacher, analyzes and screens out the target cases closest to the cases for inputting, gives out related legal suggestions at the same time, and sends the target cases and the related legal suggestions to the intelligent notification module
S6: and sending the target cases, the case analysis opinions and the target teacher contact ways to the student end when the students reply and confirm by sending or not receiving instructions to the student end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310788521.7A CN116777696B (en) | 2023-06-30 | 2023-06-30 | Legal knowledge automatic learning system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310788521.7A CN116777696B (en) | 2023-06-30 | 2023-06-30 | Legal knowledge automatic learning system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116777696A true CN116777696A (en) | 2023-09-19 |
| CN116777696B CN116777696B (en) | 2024-04-30 |
Family
ID=87992802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310788521.7A Active CN116777696B (en) | 2023-06-30 | 2023-06-30 | Legal knowledge automatic learning system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116777696B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005952A (en) * | 2014-09-10 | 2015-10-28 | 中国人民解放军第二军医大学 | Device for obtaining learning results |
| CN107230174A (en) * | 2017-06-13 | 2017-10-03 | 深圳市鹰硕技术有限公司 | A kind of network online interaction learning system and method |
| CN109684532A (en) * | 2018-12-29 | 2019-04-26 | 重庆木舌科技有限公司 | Legal advice service system based on casebook |
| CN109726275A (en) * | 2018-12-29 | 2019-05-07 | 重庆工商大学融智学院 | Legal knowledge intelligent inquiry method applied to legal advice service |
| CN109726215A (en) * | 2018-12-29 | 2019-05-07 | 重庆工商大学融智学院 | Legal knowledge intelligent inquiry system towards legal advice service |
| CN111966902A (en) * | 2020-08-18 | 2020-11-20 | 联想(北京)有限公司 | Recommendation control method for class learning and electronic equipment |
| CN114461786A (en) * | 2022-04-13 | 2022-05-10 | 北京东大正保科技有限公司 | Learning path generation method and system |
| CN116303457A (en) * | 2023-03-16 | 2023-06-23 | 安徽文康科技有限公司 | Data acquisition and storage method for fatigue driving vehicle |
| CN116308935A (en) * | 2023-05-19 | 2023-06-23 | 湖南师范大学 | Learning early warning method and device based on multi-feature modeling and multi-level evaluation |
-
2023
- 2023-06-30 CN CN202310788521.7A patent/CN116777696B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005952A (en) * | 2014-09-10 | 2015-10-28 | 中国人民解放军第二军医大学 | Device for obtaining learning results |
| CN107230174A (en) * | 2017-06-13 | 2017-10-03 | 深圳市鹰硕技术有限公司 | A kind of network online interaction learning system and method |
| CN109684532A (en) * | 2018-12-29 | 2019-04-26 | 重庆木舌科技有限公司 | Legal advice service system based on casebook |
| CN109726275A (en) * | 2018-12-29 | 2019-05-07 | 重庆工商大学融智学院 | Legal knowledge intelligent inquiry method applied to legal advice service |
| CN109726215A (en) * | 2018-12-29 | 2019-05-07 | 重庆工商大学融智学院 | Legal knowledge intelligent inquiry system towards legal advice service |
| CN111966902A (en) * | 2020-08-18 | 2020-11-20 | 联想(北京)有限公司 | Recommendation control method for class learning and electronic equipment |
| CN114461786A (en) * | 2022-04-13 | 2022-05-10 | 北京东大正保科技有限公司 | Learning path generation method and system |
| CN116303457A (en) * | 2023-03-16 | 2023-06-23 | 安徽文康科技有限公司 | Data acquisition and storage method for fatigue driving vehicle |
| CN116308935A (en) * | 2023-05-19 | 2023-06-23 | 湖南师范大学 | Learning early warning method and device based on multi-feature modeling and multi-level evaluation |
Non-Patent Citations (1)
| Title |
|---|
| 习海旭;戴仁俊;白凤娥;张颖;黄纯国;: "SPOC学习支持服务的学习分析体系构建和实践", 教育现代化, no. 89, 5 November 2019 (2019-11-05) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116777696B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210301B (en) | Method, device, equipment and storage medium for evaluating interviewee based on micro-expression | |
| CN112333420B (en) | Big data information security management system of smart campus | |
| CN110909035A (en) | Personalized review question set generation method and device, electronic equipment and storage medium | |
| CN110858353B (en) | Method and system for obtaining case judge result | |
| CN112257740B (en) | Knowledge graph-based image hidden danger identification method and system | |
| CN115358897B (en) | Student management method, system, terminal and storage medium based on electronic student identity card | |
| CN105824805A (en) | Identification method and device | |
| JP2007265134A (en) | Motivation management system | |
| CN116777696B (en) | Legal knowledge automatic learning system and method | |
| CN113822907A (en) | Image processing method and device | |
| CN111611781B (en) | Data labeling method, question answering device and electronic equipment | |
| CN112733059A (en) | Intelligent reading tracking evaluation method, system, terminal and storage medium | |
| CN107193872A (en) | Question and answer data processing method and device | |
| CN110825930A (en) | Method for automatically identifying correct answers in community question-answering forum based on artificial intelligence | |
| CN114881827B (en) | Remote online education training method and system based on Internet and storage medium | |
| CN115545985A (en) | Library archives integrated management system based on wisdom community | |
| CN107464196A (en) | Student group is left school Forecasting Methodology and device | |
| CN111475699B (en) | Website data crawling method and device, electronic equipment and readable storage medium | |
| CN114612889A (en) | Instrument information acquisition method and system, electronic equipment and storage medium | |
| CN113554909A (en) | Online education platform | |
| CN114090882B (en) | Learning material pushing method and system based on mobile terminal | |
| AU2020103765A4 (en) | IoT and Machine Learning-Based Student Management System | |
| CN114241503B (en) | Method and system for acquiring error cause, readable storage medium and device | |
| CN112990030B (en) | Student emotion analysis system based on expression images | |
| CN118227676A (en) | Information acquisition method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |