CN109523088A - The abnormal behaviour forecasting system of forced quarantine addict received treatment based on big data - Google Patents
The abnormal behaviour forecasting system of forced quarantine addict received treatment based on big data Download PDFInfo
- Publication number
- CN109523088A CN109523088A CN201811451746.9A CN201811451746A CN109523088A CN 109523088 A CN109523088 A CN 109523088A CN 201811451746 A CN201811451746 A CN 201811451746A CN 109523088 A CN109523088 A CN 109523088A
- Authority
- CN
- China
- Prior art keywords
- predicted
- personnel
- abnormal behaviour
- tuple
- classification
- 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
- 206010000117 Abnormal behaviour Diseases 0.000 title claims abstract description 167
- 230000003542 behavioural effect Effects 0.000 claims abstract description 19
- 230000003533 narcotic effect Effects 0.000 claims abstract description 16
- 238000013500 data storage Methods 0.000 claims abstract description 12
- 210000000352 storage cell Anatomy 0.000 claims abstract description 12
- 238000007405 data analysis Methods 0.000 claims abstract description 8
- 230000004044 response Effects 0.000 claims abstract description 7
- 230000006399 behavior Effects 0.000 claims description 100
- 239000003814 drug Substances 0.000 claims description 24
- 229940079593 drug Drugs 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 21
- 206010010144 Completed suicide Diseases 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 14
- 238000007726 management method Methods 0.000 claims description 13
- 238000005070 sampling Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 206010013654 Drug abuse Diseases 0.000 claims description 9
- 208000011117 substance-related disease Diseases 0.000 claims description 9
- 239000003550 marker Substances 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 6
- 208000019901 Anxiety disease Diseases 0.000 claims description 3
- 230000036506 anxiety Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 241001269238 Data Species 0.000 abstract 1
- 230000002159 abnormal effect Effects 0.000 description 7
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the abnormal behaviour forecasting systems of the forced quarantine addict received treatment based on big data, comprising: data acquisition unit, data storage cell, data analysis unit, data application unit;The data acquisition unit acquires the data information of forced quarantine addict received treatment from the operation system and security system of forced quarantine narcotic house;The data analysis unit carries out model learning according to the data information of known people, obtains learning model, and predict using the abnormal behaviour that learning model treats prognosticator, obtains prediction result;The data application unit is according to prediction result as relevant response.The present invention is based on big datas to construct behavioural characteristic integrated study model, the abnormal behaviour of forced quarantine addict received treatment is precisely predicted and alarmed to realize, effectively the abnormal behaviour of forced quarantine addict received treatment is taken precautions against, safety precaution and the personnel's supervision for improving forced quarantine narcotic house are horizontal.
Description
Technical field
The present invention relates to the forecast analysis technical fields based on big data, are based especially on the forced quarantine drug rehabilitation of big data
The abnormal behaviour forecasting system of personnel.
Background technique
Forced quarantine addict received treatment easily occurs escaping, committing suiside, exert violence, destroying etc. the unknown abnormal behaviour that can not be judged, this
The unknown abnormal behaviour that can not be judged a bit brings unprecedented challenge to the safety and stability of drug rehabilitation system and personnel's supervision,
The project that must be solved is built as drug rehabilitation System information.
Currently, assessing forced quarantine addict received treatment's abnormal behaviour, mainly pass through artificial experience assessment, psychological test amount
The mode that table assessment, single disaggregated model are assessed is assessed, this three kinds of modes have the following problems: one, excessively being relied on artificial
Assessment, cannot comprehensive, accurately predicted anomaly behavior;Two, the classification of predicted anomaly behavior is not finely divided, is unfavorable for the people
It is alert to use specific aim measure prevention with the generation of the different abnormal behaviours of correspondence;Three, artificial to the classification heavy dependence of abnormal behaviour
The index of design, estimated performance are poor.Therefore, presently, there are forced quarantine addict received treatment's abnormal behaviour assessment mode is difficult to
Reach ideal nicety of grading and stability.
Summary of the invention
In order to overcome above-mentioned defect in the prior art, the present invention provides the forced quarantine addict received treatment's based on big data
Abnormal behaviour forecasting system, the safety and stability faced in conjunction with forced quarantine narcotic house and personnel supervise actual demand, construct base
In the behavioural characteristic integrated study model of the forced quarantine addict received treatment of big data, to realize to the different of forced quarantine addict received treatment
Chang Hangwei is precisely predicted and is alarmed, and is effectively taken precautions against the abnormal behaviour of forced quarantine addict received treatment, is improved
The safety precaution of forced quarantine narcotic house and personnel supervise horizontal.
To achieve the above object, the present invention uses following technical scheme, comprising:
The abnormal behaviour forecasting system of forced quarantine addict received treatment based on big data, which is characterized in that the system packet
It includes: data acquisition unit (1), data storage cell (2), data analysis unit (3), data application unit (4);
The data acquisition unit (1) is connected with the operation system of forced quarantine narcotic house and security system, and from strong
The data information of forced quarantine addict received treatment is acquired in the operation system and security system of system isolation narcotic house;The data acquisition
Unit (1) is by the data information memory of forced quarantine addict received treatment collected to the data storage cell (2);
Described data analysis (3) unit includes data preprocessing module (31), analysis model module (32), prediction and warning mould
Block (33);Wherein,
The data preprocessing module (31) obtains the number of forced quarantine addict received treatment from the data storage cell (2)
It is believed that breath, the characteristic attribute item of forced quarantine addict received treatment is constructed according to the data information of forced quarantine addict received treatment;The number
Data preprocess module (31) carries out numeralization pretreatment to the characteristic attribute item of forced quarantine addict received treatment, obtains forced quarantine ring
The tuple of malicious personnel;The data preprocessing module (31) for the forced quarantine with abnormal behaviour also pair it is determined that quit drug abuse people
Member is that the tuple of known people is marked, the tuple of the known people after being marked, and marks content by abnormal behaviour
Classification determines;
The analysis model module (32) is trained according to the tuple of the known people after label, obtains learning model;
Forced quarantine of the prediction and warning module (33) using learning model to that can not judge whether that there is abnormal behaviour
Addict received treatment personnel to be predicted carry out abnormal behaviour prediction, and according to the prediction result of personnel to be predicted to the data application list
First (4) send alarm and predictive information;
The data application unit (4) is according to the transmitted alarm of the prediction and warning module (33) and predictive information, with peace
Anti- system carries out coordination and response.
The data information of the forced quarantine addict received treatment includes: personal information, health and fitness information, family information, consumption letter
Breath, location information, drug abuse information, exception information;The data storage cell (2) carries out classification storage to all data information.
The operation system defends system including drug rehabilitation law enforcement comprehensive management platform, Education Correction system, medical treatment life, produces labor
Dynamic system, drug rehabilitation safeguards system;The security system includes drug rehabilitation security protection comprehensive management platform, video monitoring system, meets with pipe
Reason system, access control system, broadcast system, alarm system.
It include: M in the forced quarantine addict received treatment it is determined that for the forced quarantine drug rehabilitation people with abnormal behaviour
Member is that M known people and S can not judge whether have the forced quarantine addict received treatment i.e. S of abnormal behaviour a to be predicted
Personnel;And the classification of the abnormal behaviour of the M known people is also known, the classification of the abnormal behaviour includes: without extreme
Behavior, escape behavior, suicide, behavior of exerting violence, it is broken go in ring be, other abnormal behaviours;
The characteristic attribute item includes: essential information feature, individual character assessment dimensional characteristics, drug rehabilitation dynamic event information;Its
In, the essential information feature includes age, nationality, education degree, in the past occupation, history of drug abuse, locating strong ring phase, drug rehabilitation shape
State;The individual character assessment dimensional characteristics include flare, clever and quick, sympathy, subordinate, fluctuation, impulsion, guard, feel oneself inferior, anxiety, violence
Tendency, abnormal psychology;The drug rehabilitation dynamic event information includes event type, manual evaluation grade and corresponding score value.
The pretreated concrete mode of numeralization is as follows:
Numeralization pretreatment is carried out to the characteristic attribute of M known people and S personnel to be predicted respectively, is obtained each
The tuple X of known peoplem, 1≤m≤M, Xm=[Xmj], j=1,2,3 ... d, i.e. Xm=[Xm1,Xm2,Xm3,…Xmd], and tuple Xm
In each element XmjCorrespond to a characteristic attribute item;And obtain the tuple X of each personnel to be predicteds, 1≤s≤S, Xs
=[Xsj], j=1,2,3 ... d, i.e. Xs=[Xs1,Xs2,Xs3,…Xsd], and tuple XsIn each element XsjCorrespond to a spy
Levy attribute item;
Wherein, m indicates m-th of known people, XmIndicate the tuple of m-th of known people, j indicates j-th of characteristic attribute
, XmjIndicate the attribute value of j-th of characteristic attribute item of m-th of known people;
S indicates s-th of personnel to be predicted, XsIndicate the tuple of s-th of personnel to be predicted, j indicates j-th of characteristic attribute
, XsjIndicate the attribute value of j-th of characteristic attribute item of s-th of personnel to be predicted;
And each known people and the characteristic attribute item total number of each personnel to be predicted are d, each personnel to be predicted
Since the 1st characteristic attribute item terminate to be consistent to d-th of characteristic attribute item with each known people.
The concrete mode of the label is as follows:
In the tuple X of known peoplemOne marker bit Y of middle increasem, the tuple X ' of the known people after being markedm, i.e.,
X′m=[Xm1,Xm2,Xm3,…Xmd,Ym], Ym=0,1,2,3,4,5;Wherein, YmIndicate the abnormal behaviour of m-th of known people
Classification;YmThe classification of=0 expression abnormal behaviour belongs to no extreme behavior;YmThe classification of=1 expression abnormal behaviour, which belongs to, escapes row
For;YmThe classification of=2 expression abnormal behaviours belongs to suicide;YmThe classification of=3 expression abnormal behaviours belongs to the behavior of exerting violence;Ym
The classification of=4 expression abnormal behaviours, which belongs to brokenly to go in ring, is;YmThe classification of=5 expression abnormal behaviours belongs to other abnormal behaviours.
The analysis model module (32) is using Ensemble Learning Algorithms to the tuple X ' of the known people after M labelmInto
Row training, generates learning model, that is, behavioural characteristic integrated study model E S, the following institute of the concrete mode of the Ensemble Learning Algorithms
Show:
By the tuple X ' of the known people after M labelmSet as training set Dtr, Dtr={ X 'm, m=1,2,3 ...
M, that is, Dtr={ X '1,X′2,X′3…X′M, to training set DtrIn M label after known people tuple X 'mPut back to
Random sampling, that is, hoisting sampling, obtain T sample subset Dtr_t, t=1,2,3 ... T, i.e. Dtr_1,Dtr_2,Dtr_3,…,
Dtr_T;And each sample subset Dtr_tIn containing M label after known people tuple X 'm;Wherein, subscript tr_t is indicated
T-th, Dtr_tIndicate t-th of sample subset;
Using judging tree algorithm respectively to each sample subset Dtr_tLearning training is carried out, and obtains the sample subset Dtr_t
Corresponding disaggregated model Ct, t=1,2,3 ... T;I.e. according to T sample subset Dtr_tRespectively obtain T disaggregated model Ct;Its
In, subscript t is indicated t-th, CtIndicate t-th of disaggregated model;
It will be by T disaggregated model CtThe set of composition is as learning model, that is, behavioural characteristic integrated study model E S, ES=
{C1,C2,C3…CT}。
The prediction and warning module (33) is by the tuple X of S personnel to be predictedsSet as test set Dts, Ds={ X1,
X2…XS, abnormal behaviour prediction is carried out to each of test set personnel to be predicted respectively;The tool of the abnormal behaviour prediction
Body mode is as follows:
By the tuple X of s-th of personnel to be predictedsPass through T classification mould in behavioural characteristic integrated study model E S respectively
Type CtAbnormal behaviour prediction is carried out, and respectively obtains the T predicted value of this s-th personnel to be predicted t
=1,2,3 ... T, s=1,2,3 ... S;
Wherein,Indicate t-th of predicted value of s-th of personnel to be predicted;
Indicate that the classification of predicted anomaly behavior belongs to no extreme behavior;Indicate the classification of predicted anomaly behavior
Belong to the behavior of escaping;Indicate that the classification of predicted anomaly behavior belongs to suicide;Indicate predicted anomaly behavior
Classification belongs to the behavior of exerting violence;Indicating that the classification of predicted anomaly behavior belongs to brokenly to go in ring is;Indicate predicted anomaly row
For classification belong to other abnormal behaviours;
Count T predicted valueIn,Number be v0,Number be v1,Number be v2,Number be v3,Number be v4,Number be v5;To the size of v0, v1, v2, v3, v4, v5 into
Row compares,
If v0 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted is without abnormal
Behavior disposition is i.e. without extreme behavior;
If v1 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be exist it is abnormal
Behavior disposition, and the classification of predicted anomaly behavior belongs to the behavior of escaping;
If v2 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be exist it is abnormal
Behavior disposition, and the classification of predicted anomaly behavior belongs to suicide;
If v3 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be exist it is abnormal
Behavior disposition, and the classification of predicted anomaly behavior belongs to the behavior of exerting violence;
If v4 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be exist it is abnormal
Behavior disposition, and the classification of predicted anomaly behavior belongs to brokenly to go in ring and is;
If v5 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be exist it is abnormal
Behavior disposition, and the classification of predicted anomaly behavior belongs to other abnormal behaviours;
The prediction and warning module (33) is that there are the personnel to be predicted of abnormal behaviour tendency to alarm to prediction result,
And the predictive information i.e. predicted anomaly behavior classification that the personnel to be predicted of abnormal behaviour tendency will be present is sent to the data and answers
With unit (4).
The data application unit (4) includes data inquiry module (41), alarm linkage module (42), command scheduling module
(43), predictive information management module (44): where
The data inquiry module (41) is for inquiring all data information in whole system;
The alarm linkage module (42) is realized according to the transmitted alarm of the prediction and warning module (33) and predictive information
To the coordination and response of related security system;
The command scheduling module (43) realizes the unified command scheduling of emergency resources when being abnormal behavior event;
The predictive information management module (44) alarm transmitted to the prediction and warning module (33) and prediction message into
Row inquiry, statistics, export, for related personnel's reference.
The present invention also provides the abnormal behaviour prediction technique of the forced quarantine addict received treatment based on big data, including it is following
Specific steps:
S1 acquires the data of each forced quarantine addict received treatment from the operation system and security system of forced quarantine narcotic house
Information;
S2 stores the data information of each forced quarantine addict received treatment;
S3 constructs the characteristic attribute item of forced quarantine addict received treatment according to the data information of forced quarantine addict received treatment;
S4 carries out numeralization pretreatment to the characteristic attribute item of M known people and S personnel to be predicted respectively, obtains
To the tuple X of each known peoplem, 1≤m≤M, and Xm=[Xm1,Xm2,Xm3,…Xmd], tuple XmIn each element Xmj?
A corresponding characteristic attribute item;And obtain the tuple X of each personnel to be predicteds, 1≤s≤S, and Xs=[Xs1,Xs2,Xs3,…
Xsd], tuple XsIn each element XsjCorrespond to a characteristic attribute item;
S5 is marked the known people according to the classification of the abnormal behaviour of known people, label content be this
Know the classification of the abnormal behaviour of personnel;I.e. in the tuple X of known peoplemOne marker bit Y of middle increasem, known after being marked
The tuple X ' of personnelm, i.e. X 'm=[Xm1,Xm2,Xm3,…Xmd,Ym], Ym=0,1,2,3,4,5;
S6, by the tuple X ' of the known people after M labelmSet as training set Dtr, Dtr={ X '1,X′2,X′3…
X′M, to training set DtrIn M label after known people tuple X 'mCarry out the random sampling put back to i.e. hoisting
Sampling, obtains T sample subset Dtr_t, t=1,2,3 ... T, i.e. Dtr_1,Dtr_2,Dtr_3,…,Dtr_T;And each sample subset
Dtr_tIn containing M label after known people tuple X 'm;
S7, using judging tree algorithm respectively to each sample subset Dtr_tLearning training is carried out, and obtains the sample subset
Dtr_tCorresponding disaggregated model Ct, t=1,2,3 ... T;I.e. according to T sample subset Dtr_tRespectively obtain T disaggregated model
Ct;By T disaggregated model CtThe set of composition is behavioural characteristic integrated study model E S, ES={ C1,C2,C3…CT};
S8, by the tuple X of S personnel to be predictedsSet as test set Dts, Ds={ X1,X2…XS, respectively to survey
The tuple X of each of examination concentration personnel to be predictedsCarry out abnormal behaviour prediction;Wherein, by the tuple of s-th of personnel to be predicted
XsEach disaggregated model in learning model ES is integrated by behavior feature respectively and successively carries out abnormal behaviour prediction, and respectively
Obtain the T predicted value of this s-th personnel to be predictedT=1,2,3 ... T, s=1,2,3 ... S;
S9, to T predicted valueValue counted, whereinNumber be v0,Number be v1,Number be v2,Number be v3,Number be v4,Number be v5;And to v0, v1, v2,
The size of v3, v4, v5 are compared, if v0 is for maximum valueNumber it is most, then this s-th personnel's to be predicted is pre-
Surveying result is no abnormal behaviour tendency i.e. without extreme behavior;If v1 is for maximum valueNumber it is most, then this s-th
The prediction result of personnel to be predicted is that there are abnormal behaviour tendencies, and the classification of predicted anomaly behavior belongs to the behavior of escaping;If v2
It is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be there are abnormal behaviour tendencies, and
The classification of predicted anomaly behavior belongs to suicide;If v3 is for maximum valueNumber it is most, then this s-th it is to be predicted
The prediction result of personnel is that there are abnormal behaviour tendencies, and the classification of predicted anomaly behavior belongs to the behavior of exerting violence;If v4 is maximum
Value isNumber it is most, then the prediction result of this s-th personnel to be predicted is and to predict different there are abnormal behaviour tendency
The classification of Chang Hangwei belongs to brokenly to go in ring;If v5 is for maximum valueNumber it is most, then this s-th personnel to be predicted
Prediction result is that there are abnormal behaviour tendencies, and the classification of predicted anomaly behavior belongs to other abnormal behaviours;
S10 is that there are the personnel to be predicted of abnormal behaviour tendency to alarm to prediction result.
The present invention has the advantages that
(1) present invention uses big data technology, and obtains from the operation system and security system of forced quarantine narcotic house
Data construct multiple characteristic attribute items of forced quarantine addict received treatment, keep prediction more comprehensive, and are the accurate of prediction result
Degree provides guarantee.
(2) present invention is according to it is determined that be the data of the forced quarantine addict received treatment with abnormal behaviour, foundation is forced
The behavioural characteristic integrated study model of addict received treatment is isolated, realizes precisely pre- to the progress of forced quarantine addict received treatment's abnormal behaviour
It surveys, compensates for deficiency existing for traditional approach.
(3) behavioural characteristic integrated study model of the invention includes multiple disaggregated models, is distinguished by multiple disaggregated models
The abnormal behaviour of forced quarantine addict received treatment is predicted, and obtained multiple classification results are merged, is overcome
The disadvantage of the difference of system stability existing for only one disaggregated model effectively improves the nicety of grading and stability of system.
(4) present invention is finely divided the classification of predicted anomaly behavior, and pre- by behavioural characteristic integrated study model
The classification for surveying abnormal behaviour is conducive to people's police and uses specific aim measure prevention with the generation of the different abnormal behaviours of correspondence, improves
The safety precaution of forced quarantine narcotic house is horizontal.
(5) present invention classify and classification storage to the data information of forced quarantine addict received treatment, and believes prediction
The record of breath facilitates supervisor and inquires and count, and the personnel's supervision for improving forced quarantine narcotic house is horizontal.
(6) present invention has stronger adaptive ability, to the prediction accuracy of forced quarantine addict received treatment's abnormal behaviour
Height, influence caused by erroneous judgement are small.
Detailed description of the invention
Fig. 1 is the overall architecture of the abnormal behaviour forecasting system of the forced quarantine addict received treatment of the invention based on big data
Figure.
Fig. 2 is the prediction technique of the abnormal behaviour forecasting system of the forced quarantine addict received treatment of the invention based on big data
Flow chart.
Fig. 3 is the prediction technique of the abnormal behaviour forecasting system of the forced quarantine addict received treatment of the invention based on big data
Schematic diagram.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, the abnormal behaviour forecasting system of the forced quarantine addict received treatment based on big data, including form as follows
Part: data acquisition unit 1, data storage cell 2, data analysis unit 3, data application unit 4;
The data acquisition unit 1 is connected with the operation system of forced quarantine narcotic house and security system, and from pressure
It is isolated in the operation system and security system of narcotic house and acquires the data information of forced quarantine addict received treatment.Wherein,
The operation system defends system including drug rehabilitation law enforcement comprehensive management platform, Education Correction system, medical treatment life, produces labor
Dynamic system, drug rehabilitation safeguards system;
The security system includes drug rehabilitation security protection comprehensive management platform, video monitoring system, meets with management system, gate inhibition system
System, broadcast system, alarm system;
The data information of the forced quarantine addict received treatment includes: personal information, health and fitness information, family information, consumption letter
Breath, location information, drug abuse information, exception information.
The data storage cell 2 carries out classification storage to all data information of forced quarantine addict received treatment.
The data analysis unit 3 includes data preprocessing module 31, analysis model module 32, prediction and warning module 33.
Wherein,
The data preprocessing module 31 is guarded against according to all data information architecture forced quarantine of forced quarantine addict received treatment
The characteristic attribute item of malicious personnel, the characteristic attribute item include: essential information feature, individual character assessment dimensional characteristics, drug rehabilitation dynamic
Event information;The essential information feature includes the age, nationality, education degree, occupation in the past, history of drug abuse, the locating strong ring phase, guards against
Malicious state;Individual character assessment dimensional characteristics include flare, clever and quick, sympathy, subordinate, fluctuation, impulsion, guard, feel oneself inferior, anxiety,
Violent tenet, abnormal psychology;The drug rehabilitation dynamic event information includes event type, manual evaluation grade and corresponding score value;
It include: M in the forced quarantine addict received treatment it is determined that for the forced quarantine drug rehabilitation people with abnormal behaviour
Member is that M known people and S can not judge whether have the forced quarantine addict received treatment i.e. S of abnormal behaviour a to be predicted
Personnel;And the classification of the abnormal behaviour of the M known people is also known, the classification of the abnormal behaviour includes: without extreme
Behavior, escape behavior, suicide, behavior of exerting violence, it is broken go in ring be, other abnormal behaviours;
The data preprocessing module 31 is respectively to the characteristic attribute Xiang Junjin of M known people and S personnel to be predicted
Line number value pretreatment, obtains the tuple X of each known peoplem, 1≤m≤M, Xm=[Xmj], j=1,2,3 ... d, i.e. Xm=
[Xm1,Xm2,Xm3,…Xmd], and tuple XmIn each element XmjCorrespond to a characteristic attribute item;And it obtains each to pre-
The tuple X of survey personnels, 1≤s≤S, Xs=[Xsj], j=1,2,3 ... d, i.e. Xs=[Xs1,Xs2,Xs3,…Xsd], and tuple XsIn
Each element XsjCorrespond to a characteristic attribute item;
Wherein, m indicates m-th of known people, XmIndicate the tuple of m-th of known people, j indicates j-th of characteristic attribute
, XmjIndicate the attribute value of j-th of characteristic attribute item of m-th of known people;
S indicates s-th of personnel to be predicted, XsIndicate the tuple of s-th of personnel to be predicted, j indicates j-th of characteristic attribute
, XsjIndicate the attribute value of j-th of characteristic attribute item of s-th of personnel to be predicted;
And each known people and the characteristic attribute item total number of each personnel to be predicted are d, each personnel to be predicted
Since the 1st characteristic attribute item terminate to be consistent to d-th of characteristic attribute item with each known people;
Classification progress to the known people of the data preprocessing module 31 also according to the abnormal behaviour of known people
Label, label content are the classification of the abnormal behaviour of the known people;The concrete mode of the label are as follows: in the member of known people
Group XmOne marker bit Y of middle increasem, the tuple X ' of the known people after being markedm, i.e. X 'm=[Xm1,Xm2,Xm3,…Xmd,
Ym], Ym=0,1,2,3,4,5;Wherein, YmIndicate the classification of the abnormal behaviour of m-th of known people;Ym=0 indicates abnormal row
For classification belong to no extreme behavior;YmThe classification of=1 expression abnormal behaviour belongs to the behavior of escaping;Ym=2 indicate abnormal behaviour
Classification belongs to suicide;YmThe classification of=3 expression abnormal behaviours belongs to the behavior of exerting violence;Ym=4 indicate the classification category of abnormal behaviour
It is in broken go in ring;YmThe classification of=5 expression abnormal behaviours belongs to other abnormal behaviours.
The analysis model module 32 is using Ensemble Learning Algorithms to the tuple X ' of the known people after M labelmIt carries out
Training generates behavioural characteristic integrated study model E S, and the concrete mode of the Ensemble Learning Algorithms is as follows:
By the tuple X ' of the known people after M labelmSet as training set Dtr, Dtr={ X 'm, m=1,2,3 ...
M, that is, Dtr={ X '1,X′2,X′3…X′M, to training set DtrIn M label after known people tuple X 'mPut back to
Random sampling, that is, hoisting sampling, obtain T sample subset Dtr_t, t=1,2,3 ... T, i.e. Dtr_1,Dtr_2,Dtr_3,…,
Dtr_T;And each sample subset Dtr_tIn containing M label after known people tuple X 'm;Wherein, subscript tr_t is indicated
T-th, Dtr_tIndicate t-th of sample subset;
Using judging tree algorithm respectively to each sample subset Dtr_tLearning training is carried out, and obtains the sample subset Dtr_t
Corresponding disaggregated model Ct, t=1,2,3 ... T;I.e. according to T sample subset Dtr_tRespectively obtain T disaggregated model Ct;Its
In, subscript t is indicated t-th, CtIndicate t-th of disaggregated model;For details, reference can be made to the prior arts for the judgement tree algorithm;
By T disaggregated model CtThe set of composition is behavioural characteristic integrated study model E S, ES={ C1,C2,C3…CT}。
The prediction and warning module 33 respectively carries out each personnel to be predicted using behavioural characteristic integrated study model E S
Abnormal behaviour prediction, and alarm and predictive information are sent to the data application unit 4 according to the prediction result of personnel to be predicted,
Concrete mode is as follows:
By the tuple X of S personnel to be predictedsSet as test set Dts, Ds={ X1,X2…XS, respectively to test set
Each of the tuple of personnel to be predicted carry out abnormal behaviour prediction;The abnormal behaviour is predicted as, by s-th of people to be predicted
The tuple X of membersIt is pre- that abnormal behaviour is successively carried out by each disaggregated model in the integrated learning model ES of behavior feature respectively
It surveys, and respectively obtains the T predicted value of this s-th personnel to be predictedT=1,2,3 ... T, s=1,2,3 ... S;Wherein,
Indicate t-th of predicted value of s-th of personnel to be predicted;
AndWherein,Indicate that the classification of predicted anomaly behavior belongs to no extreme behavior;Table
Show that the classification of predicted anomaly behavior belongs to the behavior of escaping;Indicate that the classification of predicted anomaly behavior belongs to suicide;Indicate that the classification of predicted anomaly behavior belongs to the behavior of exerting violence;It indicates that the classification of predicted anomaly behavior belongs to brokenly to go in ring
For;Indicate that the classification of predicted anomaly behavior belongs to other abnormal behaviours;
Count T predicted valueIn,Number be v0,Number be v1,Number be v2,Number be v3,Number be v4,Number be v5;The size of v0, v1, v2, v3, v4, v5 are carried out
Compare, if v0 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted is without abnormal row
It is tendency i.e. without extreme behavior;If v1 is for maximum valueNumber it is most, then the prediction knot of this s-th personnel to be predicted
Fruit is that there are abnormal behaviour tendencies, and the classification of predicted anomaly behavior belongs to the behavior of escaping;If v2 is for maximum value?
At most, then the prediction result of this s-th personnel to be predicted is that there are abnormal behaviour tendencies, and the classification category of predicted anomaly behavior to number
In suicide;If v3 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be exist
Abnormal behaviour tendency, and the classification of predicted anomaly behavior belongs to the behavior of exerting violence;If v4 is for maximum valueNumber it is most,
Then the prediction result of this s-th personnel to be predicted is that there are abnormal behaviour tendencies, and the classification of predicted anomaly behavior belongs to brokenly ring
Behavior;If v5 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted is the presence of abnormal row
To be inclined to, and the classification of predicted anomaly behavior belongs to other abnormal behaviours;
The prediction and warning module 33 to prediction result be there are abnormal behaviour tendency personnel to be predicted alarm, and
The predictive information i.e. predicted anomaly behavior classification that the personnel to be predicted of abnormal behaviour tendency will be present is sent to the data application
Unit 4.
The data application unit 4 the prediction and warning module 33 send alarm when, realize to related security system into
Row coordination and response realizes that the unified command to emergency resources is dispatched, and can be inquired predictive information, counted, exported, for phase
Pass personnel reference;The data application unit 4 include data inquiry module 41, alarm linkage module 42, command scheduling module 43,
Predictive information management module 44.Wherein,
The data inquiry module 41 is for inquiring all data information in whole system;
The alarm linkage module 42 is alarmed according to transmitted by the prediction and warning module 33 and predictive information, realizes and phase
Close the coordination and response of security system;
The command scheduling module 43 realizes the unified command scheduling of emergency resources when being abnormal behavior event;
The predictive information management module 44 is to alarm transmitted by the prediction and warning module 33 and predicts that message is looked into
It askes, statistics, export, for related personnel's reference.
As shown in Fig. 2 and Fig. 3, the prediction side of the abnormal behaviour forecasting system of the forced quarantine addict received treatment based on big data
Method, comprising the following steps:
S1, data acquisition unit 1 acquire each forced quarantine from the operation system and security system of forced quarantine narcotic house
The data information of addict received treatment;
S2, data storage cell 2 carry out classification storage to all data information of each forced quarantine addict received treatment;
S3, data preprocessing module 31 are quit drug abuse according to all data information architecture forced quarantine of forced quarantine addict received treatment
The characteristic attribute item of personnel;
S4, data preprocessing module 31 is respectively to M it is determined that be the forced quarantine addict received treatment with abnormal behaviour
That is M known people and S can not judge whether the forced quarantine addict received treatment i.e. S personnel's to be predicted with abnormal behaviour
Characteristic attribute item carries out numeralization pretreatment, obtains the tuple X of each known peoplem, 1≤m≤M, and Xm=[Xmj], j=
1,2,3 ... d, that is, Xm=[Xm1,Xm2,Xm3,…Xmd], tuple XmIn each element XmjCorrespond to a characteristic attribute item;And
Obtain the tuple X of each personnel to be predicteds, 1≤s≤S, and Xs=[Xsj], j=1,2,3 ... d, that is, Xs=[Xs1,Xs2,Xs3,…
Xsd], tuple XsIn each element XsjCorrespond to a characteristic attribute item;
S5, data preprocessing module 31 is according to classification the marking to the known people of the abnormal behaviour of known people
Note, label content are the classification of the abnormal behaviour of the known people;I.e. in the tuple X of known peoplemOne marker bit of middle increase
Ym, the tuple X ' of the known people after being markedm, i.e. X 'm=[Xm1,Xm2,Xm3,…Xmd,Ym], Ym=0,1,2,3,4,5;
S6, analysis model module 32 by M label after known people tuple X 'mSet as training set Dtr, Dtr
={ X 'm, m=1,2,3 ... M, that is, Dtr={ X '1,X′2,X′3…X′M, to training set DtrIn M label after known people
Tuple X 'mThe random sampling put back to i.e. hoisting sampling is carried out, T sample subset D is obtainedtr_t, t=1,2,3 ... T,
That is Dtr_1,Dtr_2,Dtr_3,…,Dtr_T;And each sample subset Dtr_tIn containing M label after known people tuple X
′m;
S7, analysis model module 32, which uses, judges tree algorithm respectively to each sample subset Dtr_tLearning training is carried out, and
Obtain the sample subset Dtr_tCorresponding disaggregated model Ct, t=1,2,3 ... T;I.e. according to T sample subset Dtr_tRespectively
To T disaggregated model Ct;By T disaggregated model CtThe set of composition is behavioural characteristic integrated study model E S, ES={ C1,
C2,C3…CT};
S8, prediction and warning module 33 is by the tuple X of S personnel to be predictedsSet as test set Dts, Ds={ X1,
X2…XS, respectively to the tuple X of each of test set personnel to be predictedsCarry out abnormal behaviour prediction;The abnormal behaviour
Prediction are as follows: by the tuple X of s-th of personnel to be predictedsEach classification in learning model ES is integrated by behavior feature respectively
Model successively carries out abnormal behaviour prediction, and respectively obtains the T predicted value of this s-th personnel to be predictedT=1,2,3 ...
T, s=1,2,3 ... S;
S9, prediction and warning module 33 is also to T predicted valueValue counted, whereinNumber be v0,Number be v1,Number be v2,Number be v3,Number be v4,Number
For v5;The size of v0, v1, v2, v3, v4, v5 are compared, if v0 is for maximum valueNumber it is most, then the s
The prediction result of a personnel to be predicted is no abnormal behaviour tendency i.e. without extreme behavior;If v1 is for maximum value?
At most, then the prediction result of this s-th personnel to be predicted is that there are abnormal behaviour tendencies, and the classification category of predicted anomaly behavior to number
In escaping behavior;If v2 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be exist
Abnormal behaviour tendency, and the classification of predicted anomaly behavior belongs to suicide;If v3 is for maximum valueNumber it is most,
Then the prediction result of this s-th personnel to be predicted is there are abnormal behaviour tendency, and the classification of predicted anomaly behavior belongs to and exerts violence
Behavior;If v4 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted is the presence of abnormal row
For tendency, and the classification of predicted anomaly behavior belongs to brokenly to go in ring and is;If v5 is for maximum valueNumber it is most, then the s
The prediction result of a personnel to be predicted is that there are abnormal behaviour tendencies, and the classification of predicted anomaly behavior belongs to other abnormal rows
For;
S10, prediction and warning module 33 to prediction result be there are abnormal behaviour tendency personnel to be predicted alarm, and
The predictive information i.e. predicted anomaly behavior classification that the personnel to be predicted of abnormal behaviour tendency will be present is sent to the data application
Unit 4.
Behavioural characteristic integrated study model of the present invention using big data technology building forced quarantine addict received treatment, realization pair
The abnormal behaviour of forced quarantine addict received treatment is precisely predicted, is compensated for existing for the traditional approach such as artificial experience assessment not
Foot;The behavioural characteristic integrated study model of forced quarantine addict received treatment based on big data is by generating multiple differentiated classification
Model simultaneously merges their classification results, overcomes the defect of system stability difference existing for a disaggregated model, effectively
The nicety of grading and stability of ground raising system.Therefore, the present invention has stronger adaptive ability, to forced quarantine drug rehabilitation people
The prediction accuracy of the abnormal behaviour of member is higher, influences caused by erroneous judgement smaller.
The above is only the preferred embodiments of the invention, are not intended to limit the invention creation, all in the present invention
Made any modifications, equivalent replacements, and improvements etc., should be included in the guarantor of the invention within the spirit and principle of creation
Within the scope of shield.
Claims (10)
1. the abnormal behaviour forecasting system of the forced quarantine addict received treatment based on big data, which is characterized in that the system comprises:
Data acquisition unit (1), data storage cell (2), data analysis unit (3), data application unit (4);
The data acquisition unit (1) is connected with the operation system of forced quarantine narcotic house and security system, and from force every
The data information of forced quarantine addict received treatment is acquired in operation system and security system from narcotic house;The data acquisition unit
(1) by the data information memory of forced quarantine addict received treatment collected to the data storage cell (2);
Described data analysis (3) unit includes data preprocessing module (31), analysis model module (32), prediction and warning module
(33);Wherein,
The data preprocessing module (31) obtains the data letter of forced quarantine addict received treatment from the data storage cell (2)
Breath constructs the characteristic attribute item of forced quarantine addict received treatment according to the data information of forced quarantine addict received treatment;The data are pre-
Processing module (31) carries out numeralization pretreatment to the characteristic attribute item of forced quarantine addict received treatment, obtains forced quarantine drug rehabilitation people
The tuple of member;The data preprocessing module (31) also pair it is determined that be for the forced quarantine addict received treatment with abnormal behaviour
The tuple of known people is marked, the tuple of the known people after being marked, and marks content by the classification of abnormal behaviour
It determines;
The analysis model module (32) is trained according to the tuple of the known people after label, obtains learning model;
The prediction and warning module (33) quits drug abuse to the forced quarantine that can not judge whether to have abnormal behaviour using learning model
Personnel personnel to be predicted carry out abnormal behaviour prediction, and according to the prediction result of personnel to be predicted to the data application unit
(4) alarm and predictive information are sent;
The data application unit (4) is according to the transmitted alarm of the prediction and warning module (33) and predictive information, with security protection system
System carries out coordination and response.
2. the abnormal behaviour forecasting system of the forced quarantine addict received treatment according to claim 1 based on big data, special
Sign is that the data information of the forced quarantine addict received treatment includes: personal information, health and fitness information, family information, consumption letter
Breath, location information, drug abuse information, exception information;The data storage cell (2) carries out classification storage to all data information.
3. the abnormal behaviour forecasting system of the forced quarantine addict received treatment according to claim 1 based on big data, special
Sign is that the operation system defends system including drug rehabilitation law enforcement comprehensive management platform, Education Correction system, medical treatment life, produces labor
Dynamic system, drug rehabilitation safeguards system;The security system includes drug rehabilitation security protection comprehensive management platform, video monitoring system, meets with pipe
Reason system, access control system, broadcast system, alarm system.
4. the abnormal behaviour forecasting system of the forced quarantine addict received treatment according to claim 1 based on big data, special
Sign is, includes: M in the forced quarantine addict received treatment it is determined that for the forced quarantine addict received treatment with abnormal behaviour
That is M known people and the S forced quarantine addict received treatment i.e. S people to be predicted that can not judge whether that there is abnormal behaviour
Member;And the classification of the abnormal behaviour of the M known people is also known, the classification of the abnormal behaviour includes: without extreme row
For, escape behavior, suicide, behavior of exerting violence, it is broken go in ring be, other abnormal behaviours;
The characteristic attribute item includes: essential information feature, individual character assessment dimensional characteristics, drug rehabilitation dynamic event information;Wherein, institute
Stating essential information feature includes age, nationality, education degree, in the past occupation, history of drug abuse, locating strong ring phase, drug rehabilitation state;It is described
Individual character assessment dimensional characteristics include flare, clever and quick, sympathy, subordinate, fluctuation, impulsion, guard, feel oneself inferior, anxiety, violent tenet, change
State psychology;The drug rehabilitation dynamic event information includes event type, manual evaluation grade and corresponding score value.
5. the abnormal behaviour forecasting system of the forced quarantine addict received treatment according to claim 4 based on big data, special
Sign is that the pretreated concrete mode of numeralization is as follows:
Numeralization pretreatment is carried out to the characteristic attribute of M known people and S personnel to be predicted respectively, is obtained each known
The tuple X of personnelm, 1≤m≤M, Xm=[Xmj], j=1,2,3 ... d, i.e. Xm=[Xm1,Xm2,Xm3,…Xmd], and tuple XmIn
Each element XmjCorrespond to a characteristic attribute item;And obtain the tuple X of each personnel to be predicteds, 1≤s≤S, Xs=
[Xsj], j=1,2,3 ... d, i.e. Xs=[Xs1,Xs2,Xs3,…Xsd], and tuple XsIn each element XsjCorrespond to a feature
Attribute item;
Wherein, m indicates m-th of known people, XmIndicate the tuple of m-th of known people, j indicates j-th of characteristic attribute item, Xmj
Indicate the attribute value of j-th of characteristic attribute item of m-th of known people;
S indicates s-th of personnel to be predicted, XsIndicate the tuple of s-th of personnel to be predicted, j indicates j-th of characteristic attribute item, Xsj
Indicate the attribute value of j-th of characteristic attribute item of s-th of personnel to be predicted;
And each known people and the characteristic attribute item total number of each personnel to be predicted are d, each personnel to be predicted and every
A known people terminates to be consistent since the 1st characteristic attribute item to d-th of characteristic attribute item.
6. the abnormal behaviour forecasting system of the forced quarantine addict received treatment according to claim 5 based on big data, special
Sign is that the concrete mode of the label is as follows:
In the tuple X of known peoplemOne marker bit Y of middle increasem, the tuple X ' of the known people after being markedm, i.e. X 'm=
[Xm1,Xm2,Xm3,…Xmd,Ym], Ym=0,1,2,3,4,5;Wherein, YmIndicate the class of the abnormal behaviour of m-th of known people
Not;YmThe classification of=0 expression abnormal behaviour belongs to no extreme behavior;YmThe classification of=1 expression abnormal behaviour belongs to the behavior of escaping;
YmThe classification of=2 expression abnormal behaviours belongs to suicide;YmThe classification of=3 expression abnormal behaviours belongs to the behavior of exerting violence;Ym=4
Indicating that the classification of abnormal behaviour belongs to brokenly to go in ring is;YmThe classification of=5 expression abnormal behaviours belongs to other abnormal behaviours.
7. the abnormal behaviour forecasting system of the forced quarantine addict received treatment according to claim 6 based on big data, special
Sign is that the analysis model module (32) is using Ensemble Learning Algorithms to the tuple X ' of the known people after M labelmIt carries out
Training generates learning model, that is, behavioural characteristic integrated study model E S, and the concrete mode of the Ensemble Learning Algorithms is as follows:
By the tuple X ' of the known people after M labelmSet as training set Dtr, Dtr={ X 'm, m=1,2,3 ... M is
Dtr={ X '1,X′2,X′3…X′M, to training set DtrIn M label after known people tuple X 'mPut back to
Random sampling, that is, hoisting sampling, obtains T sample subset Dtr_t, t=1,2,3 ... T, i.e. Dtr_1,Dtr_2,Dtr_3,…,
Dtr_T;And each sample subset Dtr_tIn containing M label after known people tuple X 'm;Wherein, subscript tr_t is indicated
T-th, Dtr_tIndicate t-th of sample subset;
Using judging tree algorithm respectively to each sample subset Dtr_tLearning training is carried out, and obtains the sample subset Dtr_tRelatively
The disaggregated model C answeredt, t=1,2,3 ... T;I.e. according to T sample subset Dtr_tRespectively obtain T disaggregated model Ct;Wherein, under
Marking t indicates t-th, CtIndicate t-th of disaggregated model;
It will be by T disaggregated model CtThe set of composition is as learning model, that is, behavioural characteristic integrated study model E S, ES={ C1,
C2,C3…CT}。
8. the abnormal behaviour forecasting system of the forced quarantine addict received treatment according to claim 7 based on big data, special
Sign is, the prediction and warning module (33) is by the tuple X of S personnel to be predictedsSet as test set Dts, Ds={ X1,
X2…XS, abnormal behaviour prediction is carried out to each of test set personnel to be predicted respectively;The tool of the abnormal behaviour prediction
Body mode is as follows:
By the tuple X of s-th of personnel to be predictedsPass through T disaggregated model C in behavioural characteristic integrated study model E S respectivelytInto
The prediction of row abnormal behaviour, and respectively obtain the T predicted value of this s-th personnel to be predicted
Wherein,Indicate t-th of predicted value of s-th of personnel to be predicted;
Indicate that the classification of predicted anomaly behavior belongs to no extreme behavior;Indicate that the classification of predicted anomaly behavior belongs to
Escape behavior;Indicate that the classification of predicted anomaly behavior belongs to suicide;Indicate the classification of predicted anomaly behavior
Belong to the behavior of exerting violence;Indicating that the classification of predicted anomaly behavior belongs to brokenly to go in ring is;Indicate predicted anomaly behavior
Classification belongs to other abnormal behaviours;
Count T predicted valueIn,Number be v0,Number be v1,Number be v2,'s
Number is v3,Number be v4,Number be v5;The size of v0, v1, v2, v3, v4, v5 are compared,
If v0 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be no abnormal behaviour
Tendency is i.e. without extreme behavior;
If v1 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be there are abnormal behaviours
Tendency, and the classification of predicted anomaly behavior belongs to the behavior of escaping;
If v2 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be there are abnormal behaviours
Tendency, and the classification of predicted anomaly behavior belongs to suicide;
If v3 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be there are abnormal behaviours
Tendency, and the classification of predicted anomaly behavior belongs to the behavior of exerting violence;
If v4 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be there are abnormal behaviours
Tendency, and the classification of predicted anomaly behavior belongs to brokenly to go in ring and is;
If v5 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted be there are abnormal behaviours
Tendency, and the classification of predicted anomaly behavior belongs to other abnormal behaviours;
The prediction and warning module (33) is that there are the personnel to be predicted of abnormal behaviour tendency to alarm, and incites somebody to action to prediction result
There are predictive information, that is, predicted anomaly behavior classifications of the personnel to be predicted of abnormal behaviour tendency to be sent to the data application list
First (4).
9. the abnormal behaviour forecasting system of the forced quarantine addict received treatment according to claim 2 based on big data, special
Sign is that the data application unit (4) includes data inquiry module (41), alarm linkage module (42), command scheduling module
(43), predictive information management module (44): where
The data inquiry module (41) is for inquiring all data information in whole system;
The alarm linkage module (42) is realized and phase according to the transmitted alarm of the prediction and warning module (33) and predictive information
Close the coordination and response of security system;
The command scheduling module (43) realizes the unified command scheduling of emergency resources when being abnormal behavior event;
The predictive information management module (44) looks into the transmitted alarm of the prediction and warning module (33) and prediction message
It askes, statistics, export, for related personnel's reference.
10. the abnormal behaviour prediction technique of the forced quarantine addict received treatment based on big data, which is characterized in that including in detail below
Step:
S1 acquires the data letter of each forced quarantine addict received treatment from the operation system and security system of forced quarantine narcotic house
Breath;
S2 stores the data information of each forced quarantine addict received treatment;
S3 constructs the characteristic attribute item of forced quarantine addict received treatment according to the data information of forced quarantine addict received treatment;
S4 carries out numeralization pretreatment to the characteristic attribute item of M known people and S personnel to be predicted respectively, obtains every
The tuple X of a known peoplem, 1≤m≤M, and Xm=[Xm1,Xm2,Xm3,…Xmd], tuple XmIn each element XmjIt is corresponding
One characteristic attribute item;And obtain the tuple X of each personnel to be predicteds, 1≤s≤S, and Xs=[Xs1,Xs2,Xs3,…Xsd],
Tuple XsIn each element XsjCorrespond to a characteristic attribute item;
S5 is marked the known people according to the classification of the abnormal behaviour of known people, and label content is the known people
The classification of the abnormal behaviour of member;I.e. in the tuple X of known peoplemOne marker bit Y of middle increasem, known people after being marked
Tuple X 'm, i.e. X 'm=[Xm1,Xm2,Xm3,…Xmd,Ym], Ym=0,1,2,3,4,5;
S6, by the tuple X ' of the known people after M labelmSet as training set Dtr, Dtr={ X '1,X′2,X′3…X
′M, to training set DtrIn M label after known people tuple X 'mCarry out the random sampling put back to i.e. hoisting
Sampling, obtains T sample subset Dtr_t, t=1,2,3 ... T, i.e. Dtr_1,Dtr_2,Dtr_3,…,Dtr_T;And each sample subset
Dtr_tIn containing M label after known people tuple X 'm;
S7, using judging tree algorithm respectively to each sample subset Dtr_tLearning training is carried out, and obtains the sample subset Dtr_tPhase
Corresponding disaggregated model Ct, t=1,2,3 ... T;I.e. according to T sample subset Dtr_tRespectively obtain T disaggregated model Ct;By T
Disaggregated model CtThe set of composition is behavioural characteristic integrated study model E S, ES={ C1,C2,C3…CT};
S8, by the tuple X of S personnel to be predictedsSet as test set Dts, Ds={ X1,X2…XS, respectively in test set
Each of personnel to be predicted tuple XsCarry out abnormal behaviour prediction;Wherein, by the tuple X of s-th of personnel to be predictedsRespectively
Each disaggregated model in learning model ES is integrated by behavior feature and successively carries out abnormal behaviour prediction, and respectively obtains this
The T predicted value of s-th of personnel to be predicted
S9, to T predicted valueValue counted, whereinNumber be v0,Number be v1,
Number be v2,Number be v3,Number be v4,Number be v5;And to v0, v1, v2, v3,
The size of v4, v5 are compared, if v0 is for maximum valueNumber it is most, then the prediction knot of this s-th personnel to be predicted
Fruit is no abnormal behaviour tendency i.e. without extreme behavior;If v1 is for maximum valueNumber it is most, then this s-th to pre-
The prediction result of survey personnel is that there are abnormal behaviour tendencies, and the classification of predicted anomaly behavior belongs to the behavior of escaping;If v2 is most
Big value isNumber it is most, then the prediction result of this s-th personnel to be predicted is and to predict there are abnormal behaviour tendency
The classification of abnormal behaviour belongs to suicide;If v3 is for maximum valueNumber it is most, then this s-th personnel to be predicted
Prediction result be that there are abnormal behaviour tendencies, and the classification of predicted anomaly behavior belongs to the behavior of exerting violence;If v4 is for maximum valueNumber it is most, then the prediction result of this s-th personnel to be predicted is and the predicted anomaly row there are abnormal behaviour tendency
For classification belong to brokenly to go in ring and be;If v5 is for maximum valueNumber it is most, then the prediction of this s-th personnel to be predicted
As a result for there are abnormal behaviour tendencies, and the classification of predicted anomaly behavior belongs to other abnormal behaviours;
S10 is that there are the personnel to be predicted of abnormal behaviour tendency to alarm to prediction result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811451746.9A CN109523088A (en) | 2018-11-30 | 2018-11-30 | The abnormal behaviour forecasting system of forced quarantine addict received treatment based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811451746.9A CN109523088A (en) | 2018-11-30 | 2018-11-30 | The abnormal behaviour forecasting system of forced quarantine addict received treatment based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109523088A true CN109523088A (en) | 2019-03-26 |
Family
ID=65794562
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811451746.9A Pending CN109523088A (en) | 2018-11-30 | 2018-11-30 | The abnormal behaviour forecasting system of forced quarantine addict received treatment based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109523088A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110020687A (en) * | 2019-04-10 | 2019-07-16 | 北京神州泰岳软件股份有限公司 | Abnormal behaviour analysis method and device based on operator's Situation Awareness portrait |
CN111159210A (en) * | 2019-12-31 | 2020-05-15 | 北京明略软件***有限公司 | Information processing system, method and device |
CN112598184A (en) * | 2020-12-27 | 2021-04-02 | 上海达梦数据库有限公司 | Method and device for predicting relapse risk of drug-dropping person |
CN113077197A (en) * | 2021-06-08 | 2021-07-06 | 泰豪信息技术有限公司 | Escort personnel consumption supervision method, system, storage medium and equipment |
-
2018
- 2018-11-30 CN CN201811451746.9A patent/CN109523088A/en active Pending
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110020687A (en) * | 2019-04-10 | 2019-07-16 | 北京神州泰岳软件股份有限公司 | Abnormal behaviour analysis method and device based on operator's Situation Awareness portrait |
CN110020687B (en) * | 2019-04-10 | 2021-11-05 | 北京神州泰岳软件股份有限公司 | Abnormal behavior analysis method and device based on operator situation perception portrait |
CN111159210A (en) * | 2019-12-31 | 2020-05-15 | 北京明略软件***有限公司 | Information processing system, method and device |
CN111159210B (en) * | 2019-12-31 | 2023-06-13 | 北京明智和术科技有限公司 | Information processing system, method and device |
CN112598184A (en) * | 2020-12-27 | 2021-04-02 | 上海达梦数据库有限公司 | Method and device for predicting relapse risk of drug-dropping person |
CN112598184B (en) * | 2020-12-27 | 2024-02-02 | 上海达梦数据库有限公司 | Method and device for predicting repeated air suction risk of drug addict |
CN113077197A (en) * | 2021-06-08 | 2021-07-06 | 泰豪信息技术有限公司 | Escort personnel consumption supervision method, system, storage medium and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109523088A (en) | The abnormal behaviour forecasting system of forced quarantine addict received treatment based on big data | |
Gendreau et al. | The effects of prison sentences on recidivism | |
Thompson et al. | Subgroup differences and implications for contemporary risk-need assessment with juvenile offenders. | |
Gardiner | The Purpose of Criminal Punishment | |
CN111899893A (en) | Infectious disease early warning decision platform system | |
CN109543986A (en) | The pre- methods of risk assessment of prison convict three and system based on user's portrait | |
CN106776884A (en) | A kind of act of terrorism Forecasting Methodology that multi-categorizer is combined based on multi-tag | |
Bloise et al. | Predicting the spread of COVID-19 in Italy using machine learning: Do socio-economic factors matter? | |
CN106447194A (en) | Assessment method for criminal risk factor by combining static and dynamic information | |
Chermack et al. | The relationship between family aggression history and expressed aggression among college males | |
Loza et al. | Cross-validation of the Self-Appraisal Questionnaire: A tool for assessing violent and nonviolent recidivism with female offenders | |
Beck | Recidivism: A fruit salad concept in the criminal justice world | |
Chainey | Examining the extent to which hotspot analysis can support spatial predictions of crime | |
Taylor et al. | Problems of classification in investigative psychology | |
Clements | The future of offender classification: Some cautions and prospects | |
Shoemaker et al. | The subculture of violence and ethnicity | |
Daggett et al. | Faith-based correctional programming in federal prisons: Factors affecting program completion | |
Gomathy et al. | The fake news detection using machine learning algorithms | |
Li | Temporal changes of coastal community resilience in the Gulf of Mexico region | |
CN114601463A (en) | Psychological crisis monitoring system and method | |
Zhu et al. | Safety evaluation of human accidents in coal mine based on ant colony optimization and SVM | |
Guo | Mental Health State Prediction Method of College Students Based on Integrated Algorithm | |
Zhang et al. | Multiple classification models based student's phobia prediction study | |
Lin et al. | Can Cooke’s model sift out better experts and produce well-calibrated aggregated probabilities? | |
Sarkar et al. | Ento-epidemiological characterization of Dengue in Uttarakhand (India) |
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 |
Application publication date: 20190326 |
|
RJ01 | Rejection of invention patent application after publication |