CN109656904B - Case risk detection method and system - Google Patents
Case risk detection method and system Download PDFInfo
- Publication number
- CN109656904B CN109656904B CN201811343649.8A CN201811343649A CN109656904B CN 109656904 B CN109656904 B CN 109656904B CN 201811343649 A CN201811343649 A CN 201811343649A CN 109656904 B CN109656904 B CN 109656904B
- Authority
- CN
- China
- Prior art keywords
- risk
- case
- keyword
- risks
- detection
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 130
- 238000000034 method Methods 0.000 claims abstract description 19
- 230000002688 persistence Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012502 risk assessment Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 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)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Technology Law (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (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)
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a case risk detection method and a system, wherein the method comprises the following steps: starting a case risk detection database; selecting a business unit matched with a case to be detected, and finding out a risk model matched with the case from the business unit; acquiring all risk keyword trees of a risk model, iterating each risk keyword sub-node of all risk keyword trees, judging whether the risk keyword sub-nodes contain risks according to a detection mode of the risk keyword sub-nodes, and outputting a risk path in which the risk keyword sub-nodes with risks are located and a risk grade of each risk keyword sub-node; counting the number of each risk level in all risk paths containing risks, and obtaining a risk rating result of the case according to a risk rating calculation rule configured by the risk model. The invention realizes the accurate calculation of risk detection in legal cases, avoids larger error caused by subjective judgment of risk values, and improves the efficiency of risk detection of cases.
Description
Technical Field
The invention relates to the field of risk detection, in particular to a method and a system for detecting risks of legal cases.
Background
With the continuous perfection of the law in China, the risk detection of legal cases of various businesses is also more and more important. The risk information of the legal case system is usually managed by maintaining risk labels, selecting relevant labels for the cases in a manual identification mode, storing the risk results of the cases, and identifying the risk information of the cases. The disadvantage of this approach is that: first, if the human judgment is wrong, the situation that the maintenance result is wrong exists, the result is completely determined by the consciousness of the human, and the risk is high; secondly, in the artificial judgment process, the historical data may need to be repeatedly used as a reference, the workload is huge, the possibility of error judgment in the whole process is high, and the efficiency is quite low; third, the risk results show hash, singleness, and insignificant reference significance. Therefore, there is a need to develop a method and system that enables risk detection of legal cases.
Disclosure of Invention
The invention aims to provide a case risk detection method and system, which are used for solving the problems in the technical background.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect of the present application, a method for constructing a case risk detection database is disclosed, including:
a1: constructing a first database, wherein a plurality of risk keywords are stored in the first database, and the risk keywords support parent-child relationships to form a plurality of risk keyword trees; each risk keyword tree comprises a risk keyword root node and at least one risk keyword sub-node, and a risk path is formed from a set of risk keywords traversed from the risk keyword root node to the risk keyword sub-nodes;
a2: setting the attribute of the risk keyword, wherein the attribute of the risk keyword comprises one or more of a risk keyword ID, a risk keyword name, a risk keyword concrete description, a risk grade, a detection mode and a system detection implementation configuration; wherein the risk level comprises a primary risk, a secondary risk and a tertiary risk;
a3: and carrying out statistical classification on the data in the first database according to the service to form a plurality of service units, wherein each service unit is provided with an independent risk model, and the risk model comprises a service unit unique identifier, a plurality of risk keyword trees and a risk rating calculation rule.
In a second aspect of the present application, a case risk detection method is disclosed, including:
b1: starting the case risk detection database;
b2: the case to be detected is provided with a business unit attribute, a business unit matched with the business unit attribute is selected from the first database, and a risk model matched with the case is determined according to a risk model corresponding to the business unit;
b3: acquiring all risk keyword trees of the risk model matched with the case;
b4: iterating each risk keyword sub-node of all risk keyword trees in the risk model, and judging whether the risk keyword sub-nodes contain risks or not according to the detection mode of the risk keyword sub-nodes; if yes, recording the risk level of the risk keyword sub-node and the risk path of the risk keyword sub-node, otherwise classifying the risk keyword sub-node into a category without risk;
b5: counting the number of primary risks, the number of secondary risks and the number of tertiary risks in all risk paths containing risks, and obtaining a risk rating result of the case according to a risk rating calculation rule configured by the risk model;
b6: and displaying the risk rating result of the case.
Preferably, in the step B4, the detection mode of the risk keyword child node includes system detection, human detection and non-detection;
if the system detection is performed, executing the step D1;
if the detection is artificial, executing the step D2;
if not, executing the step D3;
wherein, D1: executing a corresponding system detection implementation method according to the attribute of the system detection implementation configuration of the risk keyword child node;
wherein, D2: judging whether the user has data persistence; if yes, directly reading the risk level set by the user, otherwise, waiting for human detection;
wherein, D3: and classifying the risk keyword child nodes into undetectable categories, and not participating in calculating the risk rating result of the case.
Preferably, in the step B5, the risk rating calculation rule includes the steps of:
c1: setting four risk level rating results which are respectively a heavy risk, a high risk, a medium risk and a low risk; each risk level grading result is provided with a primary risk threshold value, a secondary risk threshold value and a tertiary risk threshold value;
c2: comparing the number of the primary risks, the number of the secondary risks and the number of the tertiary risks with the threshold value of the primary risk, the threshold value of the secondary risk and the threshold value of the tertiary risk of the major risk in sequence, and judging that the case is a major risk if the two risks are consistent with each other; otherwise, executing C3;
and C3: comparing the number of the first-level risks, the number of the second-level risks and the number of the third-level risks with the threshold value of the first-level risks, the threshold value of the second-level risks and the threshold value of the third-level risks in sequence, and judging that the case is high risk if the first-level risks, the second-level risks and the third-level risks are consistent with each other; otherwise, executing C4;
and C4: comparing the number of the first-level risks, the number of the second-level risks and the number of the third-level risks with the threshold value of the first-level risks, the threshold value of the second-level risks and the threshold value of the third-level risks in sequence, and judging that the case is a middle-level risk if the first-level risks, the number of the second-level risks and the number of the third-level risks are consistent; otherwise, executing C5;
c6: comparing the number of the first-level risks, the number of the second-level risks and the number of the third-level risks with the threshold value of the first-level risks, the threshold value of the second-level risks and the threshold value of the third-level risks of the low risks in sequence, and judging that the case is low risk if the first-level risks, the second-level risks and the third-level risks are consistent with each other; otherwise, executing C7;
c7: judging that the case has no risk.
Preferably, the case risk detection method further includes:
constructing a second database, and setting risk countermeasures corresponding to the risk paths in the first database in the second database.
Preferably, the case risk detection method further includes:
constructing a third database, wherein the third database stores a plurality of risk complaint cases, and each risk complaint case comprises a unique identifier of the risk complaint case and a risk path of the risk complaint case;
and a one-to-many relationship is formed between the unique identifier of the risk complaint case and the risk path of the risk complaint case.
More preferably, the case risk detection method further includes:
judging whether the risk path of the case coincides with the risk path of the risk complaint case of the third database; if the case is overlapped with the risk case, judging that the case and the risk complaint case have the same risk situation.
In a third aspect of the present invention, a case risk detection system is disclosed, comprising:
the first database is used for storing a plurality of risk keywords, wherein the risk keywords support parent-child relationships to form a plurality of risk keyword trees; each risk keyword tree comprises a risk keyword root node and at least one risk keyword sub-node, and a risk path is formed from a set of risk keywords traversed from the risk keyword root node to the risk keyword sub-nodes;
the risk classification module is used for carrying out statistical classification on the data in the first database according to the service to form a plurality of service units, and each service unit is provided with an independent risk model which comprises a service unit unique identifier, a plurality of risk keyword trees and a risk rating calculation rule;
the receiving module is used for receiving the case to be detected sent by the user and taking the case as a risk detection target;
the risk identification module is used for selecting a business unit matched with the business unit attribute from the first database according to the business unit attribute of the case, and determining a risk model matched with the case according to a risk model corresponding to the business unit;
the risk detection module is used for acquiring all risk keyword trees in the risk model determined by the risk identification module, iterating each risk keyword sub-node of all risk keyword trees in the risk model, judging whether the risk keyword sub-node contains risks according to the detection mode of the risk keyword sub-node, and outputting the risk grade of the risk keyword sub-node with risks and the risk path of the risk keyword sub-node;
the risk assessment module is used for assessing the output of the risk detection module and calculating the risk rating result of the case.
Preferably, the case risk rating result includes a significant risk, a high risk, a medium risk, and a low risk.
Preferably, the attribute of the risk keyword includes, but is not limited to, one or more of a risk keyword ID, a risk keyword name, a risk keyword concrete description, a risk level, a detection mode, and a system detection implementation configuration.
More preferably, the risk level includes a primary risk, a secondary risk, and a tertiary risk.
More preferably, the detection mode comprises system detection, human detection and non-detection.
Preferably, the case risk detection system further comprises a second database, and risk countermeasures corresponding to the risk paths in the first database are arranged in the second database.
More preferably, the risk path in the first database is in a one-to-many relationship with the corresponding risk countermeasure.
Preferably, the case risk detection system further comprises a third database, wherein the third database is provided with a plurality of risk complaint cases, and each risk complaint case comprises a risk complaint case unique identifier and a risk complaint case risk path; the relationship between the unique identifier of the risk complaint case and the risk path of the risk complaint case is one-to-many; the third database is used for judging whether the risk path of the case is overlapped with the risk path of the case of the risk complaint of the third database.
Preferably, the case risk detection system further comprises a display module, wherein the display module is used for displaying the output of the risk detection module and the risk evaluation module to calculate the risk rating result of the case.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
1) The accurate calculation of risk detection in legal cases is realized, the result accuracy guarantee is provided for users, and larger errors caused by subjective judgment of risk values are avoided;
2) The workload of artificial judgment is avoided, and the case risk detection efficiency is greatly improved;
3) The risk results of the risk detection are displayed in real time in a diversified mode, and the method has important practical reference significance.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a flow chart of a method of constructing a case risk detection database in accordance with a preferred embodiment of the present invention;
FIG. 2 is a schematic diagram of a risk keyword tree structure in accordance with a preferred embodiment of the present invention;
FIG. 3 is a flow chart of a case risk detection method in accordance with a preferred embodiment of the present invention;
FIG. 4 is a block diagram of a case risk detection system in accordance with a preferred embodiment of the present invention;
FIG. 5 is a schematic diagram of an overview interface of risk detection results displayed by a display module according to a preferred embodiment of the present invention;
FIG. 6 is a schematic diagram of a risk detection result detail tree interface displayed by a display module according to a preferred embodiment of the present invention;
fig. 7 is a schematic diagram of a risk rating result interface displayed by the display module according to the preferred embodiment of the present invention.
Detailed Description
The invention provides a case risk detection method and a system, which are used for making the purposes, technical schemes and effects of the invention clearer and more definite, and the invention is further described in detail below by referring to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It is noted that the terms "first," "second," and the like in the description and claims of the present invention and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order, and it is to be understood that the data so used may be interchanged where appropriate. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the invention provides a method for constructing a case risk detection database. Fig. 1 is a flowchart of a method of constructing a case risk detection database in accordance with a preferred embodiment of the present invention.
As shown in fig. 1, the flow includes the following steps (step A1-step A3):
a1: constructing a first database, wherein a plurality of risk keywords are stored in the first database, and the risk keywords support parent-child relationships to form a plurality of risk keyword trees; each risk keyword tree comprises a risk keyword root node and at least one risk keyword sub-node, and a risk path is formed from a set of risk keywords traversed from the risk keyword root node to the risk keyword sub-nodes.
A2: and setting the attribute of the risk keyword, wherein the attribute of the risk keyword comprises one or more of a risk keyword ID, a risk keyword name, a risk keyword concrete description, a risk grade, a detection mode and a system detection implementation configuration. The risk level comprises a primary risk, a secondary risk and a tertiary risk.
A3: and carrying out statistical classification on the data in the first database according to the service to form a plurality of service units, wherein each service unit is provided with an independent risk model, and the risk model comprises a service unit unique identifier, a plurality of risk keyword trees and a risk rating calculation rule.
Fig. 2 is a schematic diagram of a risk keyword tree structure in accordance with a preferred embodiment of the present invention.
Each block in fig. 2 represents a risk key, which is the smallest unit component. The risk keywords support to form a father-son relationship, the risk keywords form a plurality of risk keyword trees, and the structure of the risk keyword trees is not limited to the graph.
As shown in fig. 2, risk keywords A1, A2, A3 form a risk keyword tree. Wherein A1 is a risk keyword root node, A2 and A3 are risk keyword child nodes, A1 and A2 are parent-child relationships, and A1 and A3 are parent-child relationships. If the risk exists in the A2, one risk path is A1-A2; if A3 is at risk, one risk path is A1-A3.
The risk keywords B1 and B2 form a risk keyword tree. Wherein B1 is a risk keyword root node, B2 is a risk keyword child node, and B1 and B2 are parent-child relationships. If B2 is at risk, one risk path is B1-B2.
The risk keywords C1, C2, C3 and C4 form a risk keyword tree. Wherein, C1 is a risk keyword root node, C2, C3 and C4 are risk keyword child nodes, C1 and C2 are father-son relations, C2 and C4 are father-son relations, and C1 and C3 are father-son relations. If the risk exists in the C2, one risk path is C1-C2; if the risk exists in the C3, one risk path is C1-C3; if there is a risk for C4, one risk path is C1-C2-C4.
The embodiment of the invention provides a case risk detection method. Fig. 3 is a flowchart of a case risk detection method according to a preferred embodiment of the present invention.
As shown in fig. 3, the flow includes the following steps (step B1 to step B6):
b1: and starting the case risk detection database.
B2: the case to be detected is provided with a business unit attribute, a business unit matched with the business unit attribute is selected from the first database, and a risk model matched with the case is determined according to a risk model corresponding to the business unit.
B3: and acquiring all risk keyword trees of the risk model matched with the case.
B4: iterating each risk keyword sub-node of all risk keyword trees in the risk model, and judging whether the risk keyword sub-nodes contain risks or not according to the detection mode of the risk keyword sub-nodes; if yes, recording the risk grade of the risk keyword sub-node and the risk path of the risk keyword sub-node, otherwise, classifying the risk keyword sub-node into a category without risk.
B5: counting the number of primary risks, the number of secondary risks and the number of tertiary risks in all risk paths containing risks, and obtaining a risk rating result of the case according to a risk rating calculation rule configured by the risk model.
B6: and displaying the risk rating result of the case.
In the step B4, the detection modes of the risk key sub-nodes include systematic detection, artificial detection and non-detection (step D1-step D3);
if the system detection is performed, step D1 is performed.
If the detection is artificial, the step D2 is executed.
If not, step D3 is performed.
Wherein, D1: and executing a corresponding system detection implementation method according to the attribute of the system detection implementation configuration of the risk keyword child node. For example, if the case is at risk of the same judge, the logic implemented by the system detection is: and comparing the judge of the current case with the judge of the court of case complaints in the checking range, and if the judge is the same, detecting that the judge is at risk of complaints.
Wherein, D2: judging whether the user has data persistence; if yes, directly reading the risk level set by the user, otherwise, waiting for human detection.
Wherein, D3: and classifying the risk keyword child nodes into undetectable categories, and not participating in calculating the risk rating result of the case.
In the above step B5, the risk rating calculation rule includes the following steps (step C1 to step C7):
c1: setting four risk level rating results which are respectively a heavy risk, a high risk, a medium risk and a low risk; and each risk level grading result is provided with a primary risk threshold value, a secondary risk threshold value and a tertiary risk threshold value.
C2: comparing the number of the primary risks, the number of the secondary risks and the number of the tertiary risks with the threshold value of the primary risk, the threshold value of the secondary risk and the threshold value of the tertiary risk of the major risk in sequence, and judging that the case is a major risk if the two risks are consistent with each other; otherwise, C3 is performed.
And C3: comparing the number of the first-level risks, the number of the second-level risks and the number of the third-level risks with the threshold value of the first-level risks, the threshold value of the second-level risks and the threshold value of the third-level risks in sequence, and judging that the case is high risk if the first-level risks, the second-level risks and the third-level risks are consistent with each other; otherwise, C4 is performed.
And C4: comparing the number of the first-level risks, the number of the second-level risks and the number of the third-level risks with the threshold value of the first-level risks, the threshold value of the second-level risks and the threshold value of the third-level risks in sequence, and judging that the case is a middle-level risk if the first-level risks, the number of the second-level risks and the number of the third-level risks are consistent; otherwise, C5 is performed.
C6: comparing the number of the first-level risks, the number of the second-level risks and the number of the third-level risks with the threshold value of the first-level risks, the threshold value of the second-level risks and the threshold value of the third-level risks of the low risks in sequence, and judging that the case is low risk if the first-level risks, the second-level risks and the third-level risks are consistent with each other; otherwise, C7 is performed.
C7: judging that the case has no risk.
It should be noted that the setting of the risk level is not limited to three levels, the risk level rating result is not limited to four, and the setting of the risk level and the risk level rating result may be extended according to specific requirements.
In addition, the case risk detection method further comprises the following steps:
constructing a second database, and setting risk countermeasures corresponding to the risk paths in the first database in the second database.
Constructing a third database, wherein the third database stores a plurality of risk complaint cases, and each risk complaint case comprises a unique identifier of the risk complaint case and a risk path of the risk complaint case; and a one-to-many relationship is formed between the unique identifier of the risk complaint case and the risk path of the risk complaint case. Judging whether the risk path of the case coincides with the risk path of the risk complaint case of the third database; if the case is overlapped with the risk case, judging that the case and the risk complaint case have the same risk situation.
The embodiment of the invention also provides a case risk detection system corresponding to the case risk detection method provided by the embodiment of the invention. Fig. 4 is a block diagram of a case risk detection system according to a preferred embodiment of the present invention.
As shown in fig. 4, a case risk detection system includes:
(1) A first database 101, wherein a plurality of risk keywords are stored in the first database 101, and the risk keywords support parent-child relationships to form a plurality of risk keyword trees; each risk keyword tree comprises a risk keyword root node and at least one risk keyword sub-node, and a risk path is formed from a set of risk keywords traversed from the risk keyword root node to the risk keyword sub-nodes. The attributes of the risk keywords comprise a risk keyword ID, a risk keyword name, a risk keyword concrete description, a risk grade, a detection mode and system detection implementation configuration. The detection mode comprises system detection, human detection and non-detection.
(2) The risk classification module 104 performs statistical classification on the data in the first database 101 according to the service to form a plurality of service units, and each service unit sets an independent risk model, where the risk model includes a service unit unique identifier, a plurality of risk keyword trees, and a risk rating calculation rule.
(3) The receiving module 201 is configured to receive a case to be detected sent by a user, and take the case as a risk detection target.
(4) And the risk identification module 203, where the risk identification module 203 selects a service unit matching with the service unit attribute in the first database 101 according to the service unit attribute of the case, and determines a risk model matching with the case according to a risk model corresponding to the service unit.
(5) The risk detection module 204, where the risk detection module 204 obtains all risk keyword trees in the risk model determined by the risk identification module 203, iterates each risk keyword sub-node of all risk keyword trees in the risk model, determines whether the risk keyword sub-node contains a risk according to a detection mode of the risk keyword sub-node, and outputs a risk level of the risk keyword sub-node with a risk and a risk path where the risk keyword sub-node is located. Wherein the risk level includes a primary risk, a secondary risk, and a tertiary risk. The higher the risk level, the first level of risk being the risk with the relatively lowest risk level, and the third level of risk being the risk with the relatively highest risk level.
(6) The risk assessment module 205 is configured to assess an output of the risk detection module 204, and calculate a risk rating result of the case. Wherein the risk rating result includes a significant risk, a high risk, a medium risk, and a low risk.
Of course, the setting of the risk levels is not limited to three levels, the risk rating results of the cases are not limited to four, and the setting of the risk levels and the risk rating results can be expanded according to specific requirements.
(7) The display module 206 is configured to display an output of the risk detection module 204 and a risk rating result of the case calculated by the risk evaluation module 205.
In a preferred implementation manner of the embodiment of the present invention, the case risk detection system further includes a second database 102, where risk countermeasures corresponding to the risk paths in the first database 101 are set in the second database 102. A one-to-many relationship exists between the risk path in the first database 101 and the corresponding risk countermeasure.
In another preferred implementation of the embodiment of the present invention, the case risk detection system further includes a third database 103, where the third database 103 is provided with a plurality of risk complaint cases, and each risk complaint case includes a risk complaint case unique identifier and a risk path of the risk complaint case; the relationship between the unique identifier of the risk complaint case and the risk path of the risk complaint case is one-to-many; the third database 103 is configured to determine whether the case risk path coincides with the risk case risk path of the third database 103.
In a preferred embodiment, the display module 206 of the case risk detection system may display all risk paths included in the risk model to which the case belongs through a risk detection result overview interface. The risk detection result overview interface may further display that each risk path obtains a risk countermeasure corresponding to the risk countermeasure in the second database 102.
The display module 206 of the case risk detection system may display, through a risk detection result detail tree interface, all risk paths included in the risk model to which the case belongs and risk levels of each risk keyword child node of each risk path.
The display module 206 of the case risk detection system may display the risk rating result of the case through a risk rating result interface.
Fig. 5 is a schematic diagram of an overview interface of risk detection results displayed by the display module according to the preferred embodiment of the present invention.
As shown in fig. 5, the risk model matched with the case includes five risk keyword trees including regional risk, consumption entity risk, personnel risk, special subject risk and public opinion risk, and each risk keyword tree may show a risk path thereof. For example, a risk keyword tree for "regional risk" includes one risk path: regional risk-complaint region-same original notice. An icon written with a ' phrase ' is arranged on the right side of the same original report ' of the risk keyword child node, and the risk countermeasures corresponding to the risk path can be displayed by clicking the icon:
and (1) comparing whether the complaint points are overlapped with the case, and if so, checking the progress condition of the original complaint case.
2. Find out similar complaints of the same area as the court or other areas. "
Fig. 6 is a schematic diagram of a risk detection result detail tree interface displayed by the display module according to the preferred embodiment of the present invention.
As shown in fig. 6, the display module 206 presents a plurality of risk keyword trees of the same risk model in the form of detail trees, each of which may be expanded from the risk keyword root node layer by layer. An icon is arranged on the right side of each risk keyword child node and used for displaying a specific risk detection result, manual modification is supported, data can be stored after the manual modification to realize data persistence, and a new risk detection result can be obtained after an interface is refreshed.
Examples of the graph are as follows:
Fig. 7 is a schematic diagram of a risk rating result interface displayed by the display module according to the preferred embodiment of the present invention.
As shown in FIG. 7, the risk rating result interface displays the finally calculated risk rating result of the case, and can provide clear and visual legal service for the user.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: ROM, RAM, magnetic or optical disks, etc.
The above description of the specific embodiments of the present invention has been given by way of example only, and the present invention is not limited to the above described specific embodiments. Any equivalent modifications and substitutions for the present invention will occur to those skilled in the art, and are also within the scope of the present invention. Accordingly, equivalent changes and modifications are intended to be included within the scope of the present invention without departing from the spirit and scope thereof.
Claims (7)
1. A case risk detection method, comprising:
b0: constructing a case risk detection database, which comprises the steps of A1 to A3:
a1: constructing a first database, wherein a plurality of risk keywords are stored in the first database, and the risk keywords support parent-child relationships to form a plurality of risk keyword trees; each risk keyword tree comprises a risk keyword root node and at least one risk keyword sub-node, and a risk path is formed from a set of risk keywords traversed from the risk keyword root node to the risk keyword sub-nodes;
a2: setting the attribute of the risk keyword, wherein the attribute of the risk keyword comprises one or more of a risk keyword ID, a risk keyword name, a risk keyword concrete description, a risk grade, a detection mode and a system detection implementation configuration; wherein the risk level comprises a primary risk, a secondary risk and a tertiary risk;
a3: the data in the first database are statistically classified according to the service to form a plurality of service units, and each service unit is provided with an independent risk model, wherein the risk model comprises a unique identifier of the service unit, a plurality of risk keyword trees and a risk rating calculation rule;
b1: starting the case risk detection database;
b2: the case to be detected is provided with a business unit attribute, a business unit matched with the business unit attribute is selected from the first database, and a risk model matched with the case is determined according to a risk model corresponding to the business unit;
b3: acquiring all risk keyword trees of the risk model matched with the case;
b4: iterating each risk keyword sub-node of all risk keyword trees in the risk model, and judging whether the risk keyword sub-nodes contain risks or not according to the detection mode of the risk keyword sub-nodes; if yes, recording the risk level of the risk keyword sub-node and the risk path of the risk keyword sub-node, otherwise classifying the risk keyword sub-node into a category without risk;
b5: counting the number of primary risks, the number of secondary risks and the number of tertiary risks in all risk paths containing risks, and obtaining a risk rating result of the case according to a risk rating calculation rule configured by the risk model;
b6: displaying the risk rating result of the case;
the method further comprises the steps of:
constructing a second database, wherein a risk countermeasure corresponding to the risk path in the first database is set in the second database, and a one-to-many relationship is formed between the risk path in the first database and the risk countermeasure corresponding to the risk path; and
constructing a third database, wherein the third database stores a plurality of risk complaint cases, and each risk complaint case comprises a unique identifier of the risk complaint case and a risk path of the risk complaint case; the unique identifier of the risk complaint case and the risk path of the risk complaint case are in one-to-many relation;
judging whether a case risk path coincides with a case risk path of the risk complaint case of the third database or not during case risk detection; if the case is overlapped with the risk case, judging that the case and the risk complaint case have the same risk situation.
2. The case risk detection method according to claim 1, wherein: in the step B4, the detection modes of the risk keyword child nodes include system detection, human detection and non-detection;
if the system detection is performed, executing the step D1;
if the detection is artificial, executing the step D2;
if not, executing the step D3;
wherein, D1: executing a corresponding system detection implementation method according to the attribute of the system detection implementation configuration of the risk keyword child node;
wherein, D2: judging whether the user has data persistence; if yes, directly reading the risk level set by the user, otherwise, waiting for human detection;
wherein, D3: and classifying the risk keyword child nodes into undetectable categories, and not participating in calculating the risk rating result of the case.
3. The case risk detection method according to claim 1, wherein in the step B5, the risk rating calculation rule includes the steps of:
c1: setting four risk level rating results which are respectively a heavy risk, a high risk, a medium risk and a low risk; each risk level grading result is provided with a primary risk threshold value, a secondary risk threshold value and a tertiary risk threshold value;
c2: comparing the number of the primary risks, the number of the secondary risks and the number of the tertiary risks with the threshold value of the primary risk, the threshold value of the secondary risk and the threshold value of the tertiary risk of the major risk in sequence, and judging that the case is a major risk if the two risks are consistent with each other; otherwise, executing C3;
and C3: comparing the number of the first-level risks, the number of the second-level risks and the number of the third-level risks with the threshold value of the first-level risks, the threshold value of the second-level risks and the threshold value of the third-level risks in sequence, and judging that the case is high risk if the first-level risks, the second-level risks and the third-level risks are consistent with each other; otherwise, executing C4;
and C4: comparing the number of the first-level risks, the number of the second-level risks and the number of the third-level risks with the threshold value of the first-level risks, the threshold value of the second-level risks and the threshold value of the third-level risks in sequence, and judging that the case is a middle-level risk if the first-level risks, the number of the second-level risks and the number of the third-level risks are consistent; otherwise, executing C5;
c6: comparing the number of the first-level risks, the number of the second-level risks and the number of the third-level risks with the threshold value of the first-level risks, the threshold value of the second-level risks and the threshold value of the third-level risks of the low risks in sequence, and judging that the case is low risk if the first-level risks, the second-level risks and the third-level risks are consistent with each other; otherwise, executing C7;
c7: judging that the case has no risk.
4. A case risk detection system, comprising:
the first database is used for storing a plurality of risk keywords, wherein the risk keywords support parent-child relationships to form a plurality of risk keyword trees; each risk keyword tree comprises a risk keyword root node and at least one risk keyword sub-node, and a risk path is formed from a set of risk keywords traversed from the risk keyword root node to the risk keyword sub-nodes;
the risk classification module is used for carrying out statistical classification on the data in the first database according to the service to form a plurality of service units, and each service unit is provided with an independent risk model which comprises a service unit unique identifier, a plurality of risk keyword trees and a risk rating calculation rule;
the receiving module is used for receiving the case to be detected sent by the user and taking the case as a risk detection target;
the risk identification module is used for selecting a business unit matched with the business unit attribute from the first database according to the business unit attribute of the case, and determining a risk model matched with the case according to a risk model corresponding to the business unit;
the risk detection module is used for acquiring all risk keyword trees in the risk model determined by the risk identification module, iterating each risk keyword sub-node of all risk keyword trees in the risk model, judging whether the risk keyword sub-node contains risks according to the detection mode of the risk keyword sub-node, and outputting the risk grade of the risk keyword sub-node with risks and the risk path of the risk keyword sub-node;
the risk evaluation module is used for evaluating the output of the risk detection module and calculating the risk rating result of the case;
the system further comprises a second database and a third database;
the second database is provided with risk countermeasures corresponding to the risk paths in the first database, and the risk paths in the first database and the corresponding risk countermeasures are in one-to-many relation;
the third database is provided with a plurality of risk complaint cases, and each risk complaint case comprises a risk complaint case unique identifier and a risk complaint case risk path; the relationship between the unique identifier of the risk complaint case and the risk path of the risk complaint case is one-to-many; the third database is used for judging whether the risk path of the case is overlapped with the risk path of the case of the risk complaint of the third database.
5. The case risk detection system of claim 4, wherein: the risk rating results include significant risk, high risk, medium risk, and low risk.
6. The case risk detection system of claim 4, wherein: the attribute of the risk keyword comprises one or more of a risk keyword ID, a risk keyword name, a risk keyword concrete description, a risk grade, a detection mode and a system detection implementation configuration.
7. The case risk detection system of claim 6, wherein: the risk level comprises a primary risk, a secondary risk and a tertiary risk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811343649.8A CN109656904B (en) | 2018-11-13 | 2018-11-13 | Case risk detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811343649.8A CN109656904B (en) | 2018-11-13 | 2018-11-13 | Case risk detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109656904A CN109656904A (en) | 2019-04-19 |
| CN109656904B true CN109656904B (en) | 2023-05-30 |
Family
ID=66110865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811343649.8A Active CN109656904B (en) | 2018-11-13 | 2018-11-13 | Case risk detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109656904B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110297816A (en) * | 2019-06-18 | 2019-10-01 | 浙江无极互联科技有限公司 | A kind of data quick-processing system |
| CN110458412A (en) * | 2019-07-16 | 2019-11-15 | 阿里巴巴集团控股有限公司 | The generation method and device of risk monitoring and control data |
| CN111260223A (en) * | 2020-01-17 | 2020-06-09 | 山东省计算中心（国家超级计算济南中心） | Intelligent identification and early warning method, system, medium and equipment for trial and judgment risk |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107230008A (en) * | 2016-03-25 | 2017-10-03 | 阿里巴巴集团控股有限公司 | A kind of risk information output, risk information construction method and device |
| CN107451710A (en) * | 2017-04-27 | 2017-12-08 | 北京鼎泰智源科技有限公司 | A kind of Information Risk grade five-category method and system |
| CN107844914A (en) * | 2017-11-27 | 2018-03-27 | 安徽经邦软件技术有限公司 | Risk management and control system and implementation method based on group management |
| CN107993144A (en) * | 2017-11-30 | 2018-05-04 | 平安科技（深圳）有限公司 | Customer risk grade determines method, apparatus, equipment and readable storage medium storing program for executing |
-
2018
- 2018-11-13 CN CN201811343649.8A patent/CN109656904B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107230008A (en) * | 2016-03-25 | 2017-10-03 | 阿里巴巴集团控股有限公司 | A kind of risk information output, risk information construction method and device |
| CN107451710A (en) * | 2017-04-27 | 2017-12-08 | 北京鼎泰智源科技有限公司 | A kind of Information Risk grade five-category method and system |
| CN107844914A (en) * | 2017-11-27 | 2018-03-27 | 安徽经邦软件技术有限公司 | Risk management and control system and implementation method based on group management |
| CN107993144A (en) * | 2017-11-30 | 2018-05-04 | 平安科技（深圳）有限公司 | Customer risk grade determines method, apparatus, equipment and readable storage medium storing program for executing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109656904A (en) | 2019-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492111B (en) | Shortest path query method, shortest path query system, computer device and storage medium | |
| CN104756106B (en) | Data source in characterize data storage system | |
| CN109656904B (en) | Case risk detection method and system | |
| CN105868373B (en) | Method and device for processing key data of power business information system | |
| CN106952159B (en) | Real estate collateral risk control method, system and storage medium | |
| CN106570778A (en) | Big data-based data integration and line loss analysis and calculation method | |
| WO2012045496A2 (en) | Probabilistic data mining model comparison engine | |
| CN111078897A (en) | System for generating six-dimensional knowledge map | |
| US20150161545A1 (en) | Visualization of spare parts inventory | |
| CN110991553B (en) | BIM model comparison method | |
| CN107545043A (en) | A kind of data application method and device based on data quality checking | |
| CN111428095B (en) | Graph data quality verification method and graph data quality verification device | |
| CN112860769A (en) | Energy planning data management system | |
| Ebden et al. | Network analysis on provenance graphs from a crowdsourcing application | |
| CN111951104A (en) | Risk conduction early warning method based on associated graph | |
| de Almeida et al. | Taxonomy of data quality problems in multidimensional Data Warehouse models | |
| Chatagnier et al. | Scale and zonation effects on internal migration indicators in the United Kingdom | |
| Li et al. | Data error propagation in stacked bioclimatic envelope models | |
| CN115587333A (en) | Failure analysis fault point prediction method and system based on multi-classification model | |
| Malvandi et al. | Provide a method for increasing the efficiency of learning management systems using educational data mining | |
| CN114399202A (en) | Big data visualization system for urban community | |
| KR102217092B1 (en) | Method and apparatus for providing quality information of application | |
| Abdulkarim et al. | Using social network analysis to study diversity in business partnerships | |
| CN113205270B (en) | Method and system for automatically generating satisfaction evaluation table and calculating evaluation score | |
| Afijal et al. | Decision Support System Determination for Poor Houses Beneficiary Using Profile Matching Method |
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 |