CN112862645A - Method for establishing multi-dimensional criminal state information model - Google Patents
Method for establishing multi-dimensional criminal state information model Download PDFInfo
- Publication number
- CN112862645A CN112862645A CN201911181112.0A CN201911181112A CN112862645A CN 112862645 A CN112862645 A CN 112862645A CN 201911181112 A CN201911181112 A CN 201911181112A CN 112862645 A CN112862645 A CN 112862645A
- Authority
- CN
- China
- Prior art keywords
- data
- state information
- target
- prisoner
- prisoners
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 239000002245 particle Substances 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims description 8
- 230000001131 transforming effect Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000007704 transition Effects 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 7
- 238000013077 scoring method Methods 0.000 description 7
- 239000013598 vector Substances 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 230000003340 mental effect Effects 0.000 description 2
- 230000006996 mental state Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036210 malignancy Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention relates to a method for establishing a multi-dimensional prisoner state information model, which divides factors influencing the risk degree of an analyst into a plurality of dimensions: basic factors, personalities, psychology, social factors, comprehensive factors and the like, scoring relevant attributes of the factors, structuring unstructured data of criminals to form a multi-dimensional array structure of criminal data, then calculating the distance between criminal data and particles by selecting particles, and finally dividing criminal persons into three categories: normal pipe, tight pipe, wide pipe. The invention predicts the analysis model of the crime trend of the monitored object by analyzing the state transition of particles and criminals, and helps the monitoring personnel to perform personalized management education and reasonable decision of supervision departments.
Description
Technical Field
The invention discloses a method for establishing a multi-dimensional criminal state information model, and belongs to the technical field of judicial intelligent monitoring.
Background
With the advance of social informatization, all aspects of society begin to pay attention to information acquisition and analysis work, but classification management aiming at specific crowds still has no specific technical means to process and distinguish, and the main objective technical reason is that: relates to the judicial field, and has a plurality of factors influencing individual behaviors. Especially, it is difficult for criminals to make accurate dangerous behavior prejudgment according to short-term personal information data.
According to the research of criminal behaviors, criminals with the same penalty often have different probabilities of dangerous behaviors made subsequently according to different multiple objective factors such as individual family environment, social relationship, personal education background, personal health condition and the like. Therefore, establishing a personnel state information model capable of considering multidimensional factors becomes a technical difficulty which is always sought to be broken through in the technical field.
In order to solve the technical problems, the chinese patent CN110458101A discloses a method and a device for monitoring the physical signs of prisoners based on the combination of video and device, wherein the method comprises the following steps: identifying facial expression characteristics and categories of prisoners from video frames by acquiring a current monitoring video of the prisoners; the human face facial feature area is tracked in real time through video monitoring, and meanwhile, the heart rate of prisoners is detected by the vital sign monitoring equipment. And judging whether prisoners have potential disease risks or abnormal behaviors or not by combining the heart rates of the prisoners at rest and the facial expression characteristics and the heart rates of the prisoners identified from the videos. However, the document only monitors the physical condition of the person taking a criminal and gives an early warning in time, and other kinds of influence factors are not considered in the process of prejudging the dangerous behaviors of the person taking a criminal.
Chinese patent CN109998570A discloses a criminal person mental state assessment method, terminal, device and system, according to the inputted fingerprint information, extracting the mental index to be tested corresponding to the fingerprint information, and selecting the animation game scene corresponding to the current mental index to be tested; meanwhile, selecting a VR experience scene corresponding to the current psychological index to be tested; collecting a first physiological signal of a criminal person to be tested in an animation game scene; collecting a second physiological signal and a first behavior signal of a criminal person to be tested in a VR experience scene; preprocessing the acquired signals; performing feature extraction on the preprocessed signals to obtain feature vectors; and performing feature vector fusion on the feature vectors, inputting the fused feature vectors into a pre-trained prediction model, and outputting a psychological state classification result of the prisoner to be tested by the prediction model. The document is to put the person taking a criminal in a specific simulation scene, and to realize psychological state assessment of the person taking a criminal by distinguishing the reaction behavior or answer feedback of the specific person.
In conclusion, the prior art is still limited to the estimation of the prisoner's prediction and evaluation to the health condition or psychological condition, however, other factors affecting the prisoner are still not effectively identified and evaluated.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses a method for establishing a multi-dimensional criminal state information model.
The detailed technical scheme of the invention is as follows:
a method for establishing a multi-dimensional criminal state information model comprises the following steps:
1) collecting status information of all target prisoners, characterized in that said status information at least comprises:
character data, psychological data, education background data, family environment data, physical health data, crime background data, crime penalty data, prison expression data and community evaluation feedback data;
2) collecting all target prisoner data according to the type of state information to form a multi-dimensional array structure; according to different target prisoners, assigning and scoring the state information;
3) selecting mass points of the array structure from the array structures, and calculating the distance between the state information of each prisoner and the mass points;
4) finally classifying the prisoners into three categories according to the distance between the state information of each prisoner and the mass point: normal pipe, tight pipe, wide pipe.
According to the invention, a multidimensional array of the target prisoners is formed, and the mass points of the array structure are selected: common tube mass point, wide tube mass point and tight tube mass point;
and calculating the distance between the state information of each target prisoner and the corresponding mass point, wherein the type of the mass point with the closest state information of the target prisoner is judged as the type of the prisoner's tendency, namely common pipe, strict pipe or wide pipe.
According to the invention, preferably, the multi-dimensional arrays of all the target prisoners are set to be clustered K values, and the prisoners are divided into 3 types of common pipes, wide pipes and strict pipes, so that K is 3;
5) randomly selecting 3 points as mass points;
6) and calculating the similarity of other prisoners and the 3 mass points according to a formula:
7) wherein the closest is classified as a class;
8) the arithmetic mean of each dimension is calculated in class:
forming new particles according to the arithmetic mean of each dimension, and updating 3 particles;
9) and repeating the step 8) until the particle points are not changed or are changed slightly, namely determining that the target prisoner belongs to the common pipe, the wide pipe or the strict pipe.
A method for tracking and transforming target prisoners by establishing a multi-dimensional prisoner state information model is characterized by comprising the following steps:
according to the categories of common pipes, strict pipes or wide pipes where the target prisoners are located, by adjusting the state information of the personnel: the system comprises character data, psychological data, education background data, family environment data, body health data, crime background data, crime penalty data, prison expression data and community evaluation feedback data, and therefore the type of the target prisoner belonging to the education is improved.
According to the invention, preferably, the judicial supervision department and/or the community supervision department adjust information at any time according to the state information of the personnel, so that the type of the director belonging to the target prisoner is improved until the director target is reached.
The technical advantages of the invention are as follows:
the invention can utilize the advantages of information collection and classification to accurately classify the target prisoner into a common pipe, a strict pipe or a wide pipe object. The invention also utilizes the state information of the prisoner to carry out effective information tracking, further effectively feeds back various data information of the prisoner to a judicial supervision department and/or a community supervision department, and makes a management and education plan by the corresponding department until the prisoner reaches a management and education target.
Detailed Description
The following is a detailed description of the embodiments, but is not limited thereto.
Examples 1,
A method for establishing a multi-dimensional criminal state information model comprises the following steps:
1) collecting state information of all target prisoners, wherein the state information at least comprises the following components:
character data, psychological data, education background data, family environment data, physical health data, crime background data, crime penalty data, prison expression data and community evaluation feedback data;
5) collecting all target prisoner data according to the type of state information to form a multi-dimensional array structure; according to different target prisoners, assigning and scoring the state information;
6) selecting mass points of the array structure from the array structures, and calculating the distance between the state information of each prisoner and the mass points;
7) finally classifying the prisoners into three categories according to the distance between the state information of each prisoner and the mass point: normal pipe, tight pipe, wide pipe.
The specific assignment scoring method of the character data and the psychological data is as shown in table 1:
table 1: concrete assignment scoring table for character data and psychological data
The educational background data includes: education, specific assignment scoring method as in table 2:
table 2: education background data specific assignment scoring table
The home environment data includes: marital family conditions, life sources, fixed residences, crime records of family members, family member relationships and attitudes of family member coordination correction work, and the specific assignment scoring method is as shown in table 3:
table 3: family environment data specific assignment scoring table
The physical health data included a psychiatric history and a psychiatric genetic history, and the specific assignment scoring method is as shown in table 4:
table 4: the body health data is specifically assigned to a scoring table
The crime background data includes the age, employment attitude and condition, subjective malignancy, whether violence is used or whether the crime is deceived, and the specific assignment scoring method is as shown in table 5:
table 5: the crime background data is specifically assigned to a scoring table
The crime penalty data and the prison presence data comprise crime service attitudes, mental states of a real society, legal knowledge or legal concepts, law violation crime record owners, past criminal penalty records and past administrative penalty records, and the specific assignment and scoring method is as shown in the following table 6:
table 6: criminal penalty data and prison presence data specific assignment scoring table
According to the preferable embodiment of the present invention, the community evaluation feedback data includes a friend-making situation, an individual growth experience, a community correction category, and a community correction attitude acceptance, and the specific assignment scoring method is as follows:
examples 2,
The method for establishing the multi-dimensional criminal state information model according to embodiment 1 forms a multi-dimensional array of a target criminal, and selects mass points with an array structure: common tube mass point, wide tube mass point and tight tube mass point;
and calculating the distance between the state information of each target prisoner and the corresponding mass point, wherein the type of the mass point with the closest state information of the target prisoner is judged as the type of the prisoner's tendency, namely common pipe, strict pipe or wide pipe.
Setting a clustered K value for all the multidimensional arrays of the target prisoners, and dividing the prisoners into 3 types of common pipes, wide pipes and strict pipes, wherein K is 3;
5) randomly selecting 3 points as mass points;
6) and calculating the similarity of other prisoners and the 3 mass points according to a formula:
7) wherein the closest is classified as a class;
8) the arithmetic mean of each dimension is calculated in class:
forming new particles according to the arithmetic mean of each dimension, and updating 3 particles;
10) and repeating the step 8) until the particle points are not changed or are changed slightly, namely determining that the target prisoner belongs to the common pipe, the wide pipe or the strict pipe.
Examples 3,
A method for tracking and transforming target prisoners by establishing a multi-dimensional prisoner state information model comprises the following steps:
according to the categories of common pipes, strict pipes or wide pipes where the target prisoners are located, by adjusting the state information of the personnel: the system comprises character data, psychological data, education background data, family environment data, body health data, crime background data, crime penalty data, prison expression data and community evaluation feedback data, and therefore the type of the target prisoner belonging to the education is improved.
Preferably, the judicial supervision department and/or the community supervision department adjust information at any time according to the state information of the persons, so that the types of the director to which the target prisoner belongs are improved until the director target is reached.
Claims (5)
1. A method for establishing a multi-dimensional criminal state information model comprises the following steps:
1) collecting status information of all target prisoners, characterized in that said status information at least comprises:
character data, psychological data, education background data, family environment data, physical health data, crime background data, crime penalty data, prison expression data and community evaluation feedback data;
2) collecting all target prisoner data according to the type of state information to form a multi-dimensional array structure; according to different target prisoners, assigning and scoring the state information;
3) selecting mass points of the array structure from the array structures, and calculating the distance between the state information of each prisoner and the mass points;
4) finally classifying the prisoners into three categories according to the distance between the state information of each prisoner and the mass point: normal pipe, tight pipe, wide pipe.
2. The method for establishing the multi-dimensional criminal state information model according to claim 1, wherein a multi-dimensional array of target criminal persons is formed, and the mass points of the array structure are selected: common tube mass point, wide tube mass point and tight tube mass point;
and calculating the distance between the state information of each target prisoner and the corresponding mass point, wherein the type of the mass point with the closest state information of the target prisoner is judged as the type of the prisoner's tendency, namely common pipe, strict pipe or wide pipe.
3. The method for establishing the multi-dimensional prisoner state information model according to claim 1, wherein all the target prisoners are set in a multi-dimensional array with a clustered K value, and the prisoners are classified into 3 types of common pipes, wide pipes and strict pipes, so that K is 3;
5) randomly selecting 3 points as mass points;
6) and calculating the similarity of other prisoners and the 3 mass points according to a formula:
7) wherein the closest is classified as a class;
8) the arithmetic mean of each dimension is calculated in class:
forming new particles according to the arithmetic mean of each dimension, and updating 3 particles;
9) and repeating the step 8) until the particle points are not changed or are changed slightly, namely determining that the target prisoner belongs to the common pipe, the wide pipe or the strict pipe.
4. A method for tracking and transforming target prisoners by establishing a multi-dimensional prisoner state information model is characterized by comprising the following steps:
according to the categories of common pipes, strict pipes or wide pipes where the target prisoners are located, by adjusting the state information of the personnel: the system comprises character data, psychological data, education background data, family environment data, body health data, crime background data, crime penalty data, prison expression data and community evaluation feedback data, and therefore the type of the target prisoner belonging to the education is improved.
5. The method for tracking and transforming target prisoners by establishing the multi-dimensional prisoner state information model according to claim 4, wherein the judicial supervision department and/or the community supervision department can adjust information at any time according to the state information of the prisoners, so as to improve the types of the custody and education of the target prisoners until the custody and education target is reached.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911181112.0A CN112862645A (en) | 2019-11-27 | 2019-11-27 | Method for establishing multi-dimensional criminal state information model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911181112.0A CN112862645A (en) | 2019-11-27 | 2019-11-27 | Method for establishing multi-dimensional criminal state information model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112862645A true CN112862645A (en) | 2021-05-28 |
Family
ID=75985560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911181112.0A Pending CN112862645A (en) | 2019-11-27 | 2019-11-27 | Method for establishing multi-dimensional criminal state information model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862645A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000077688A1 (en) * | 1999-06-11 | 2000-12-21 | Layson Hoyt M | System to correlate crime incidents with a subject's location |
| JP2008204219A (en) * | 2007-02-21 | 2008-09-04 | Sharp Corp | Crime prevention system, suspicious person detection device using the same and crime prevention server |
| CN104050361A (en) * | 2014-06-04 | 2014-09-17 | 杭州华亭科技有限公司 | Intelligent analysis early warning method for dangerousness tendency of prison persons serving sentences |
| CN105139029A (en) * | 2015-08-14 | 2015-12-09 | 哈尔滨华夏矿安科技有限公司 | Activity recognition method and activity recognition device for persons serving sentences |
| CN106447194A (en) * | 2016-09-27 | 2017-02-22 | 上海中信信息发展股份有限公司 | Assessment method for criminal risk factor by combining static and dynamic information |
| CN108399190A (en) * | 2018-01-24 | 2018-08-14 | 山东中磁视讯股份有限公司 | A kind of panorama image space method applied to prison convict |
| CN110059079A (en) * | 2019-04-28 | 2019-07-26 | 北京深醒科技有限公司 | A kind of personnel based on big data modeling analysis break laws and commit crime prediction technique and system |
-
2019
- 2019-11-27 CN CN201911181112.0A patent/CN112862645A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000077688A1 (en) * | 1999-06-11 | 2000-12-21 | Layson Hoyt M | System to correlate crime incidents with a subject's location |
| JP2008204219A (en) * | 2007-02-21 | 2008-09-04 | Sharp Corp | Crime prevention system, suspicious person detection device using the same and crime prevention server |
| CN104050361A (en) * | 2014-06-04 | 2014-09-17 | 杭州华亭科技有限公司 | Intelligent analysis early warning method for dangerousness tendency of prison persons serving sentences |
| CN105139029A (en) * | 2015-08-14 | 2015-12-09 | 哈尔滨华夏矿安科技有限公司 | Activity recognition method and activity recognition device for persons serving sentences |
| CN106447194A (en) * | 2016-09-27 | 2017-02-22 | 上海中信信息发展股份有限公司 | Assessment method for criminal risk factor by combining static and dynamic information |
| CN108399190A (en) * | 2018-01-24 | 2018-08-14 | 山东中磁视讯股份有限公司 | A kind of panorama image space method applied to prison convict |
| CN110059079A (en) * | 2019-04-28 | 2019-07-26 | 北京深醒科技有限公司 | A kind of personnel based on big data modeling analysis break laws and commit crime prediction technique and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ryu et al. | Prediction model of dementia risk based on XGBoost using derived variable extraction and hyper parameter optimization | |
| Yin et al. | Sensor-based abnormal human-activity detection | |
| Chackravarthy et al. | Intelligent crime anomaly detection in smart cities using deep learning | |
| CN105787472B (en) | A kind of anomaly detection method based on the study of space-time laplacian eigenmaps | |
| CN104050361A (en) | Intelligent analysis early warning method for dangerousness tendency of prison persons serving sentences | |
| Shermila et al. | Crime data analysis and prediction of perpetrator identity using machine learning approach | |
| CN110837523A (en) | High-confidence reconstruction quality and false-transient-reduction quantitative evaluation method based on cascade neural network | |
| CN108009690A (en) | A kind of routine bus system optimized based on modularity steals group's automatic testing method | |
| CN115691034A (en) | Intelligent household abnormal condition warning method, system and storage medium | |
| Hirzi et al. | Literature study of face recognition using the viola-jones algorithm | |
| Ateş et al. | Big data, data mining, machine learning, and deep learning concepts in crime data | |
| CN117197726B (en) | Important personnel accurate management and control system and method | |
| CN110543583A (en) | information processing method and apparatus, image device, and storage medium | |
| Stoffel et al. | Fuzzy clustering based methodology for multidimensional data analysis in computational forensic domain | |
| CN105930430B (en) | Real-time fraud detection method and device based on non-accumulative attribute | |
| CN111723869A (en) | Special personnel-oriented intelligent behavior risk early warning method and system | |
| CN112862645A (en) | Method for establishing multi-dimensional criminal state information model | |
| Ogunde et al. | A decision tree algorithm based system for predicting crime in the university | |
| Hnoohom et al. | Weapon Detection Using Faster R-CNN Inception-V2 for a CCTV Surveillance System | |
| CN114491156A (en) | Method for intelligently pushing approximate object based on video image | |
| McCormick et al. | Letting go of the Grail: Falsifying the theory of ‘true’eyewitness identifications | |
| CN112686141A (en) | Personnel filing method and device and electronic equipment | |
| CN113012006A (en) | Intelligent investigation and research method, system, computer equipment and storage medium | |
| US20220237727A1 (en) | System and method for performing legal background checks | |
| Silva et al. | Detecting possible persons of interest in a physical activity program using step entries: Including a web‐based application for outlier detection and decision‐making |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210528 |