CN110580570B - Law enforcement analysis method, device and medium - Google Patents
Law enforcement analysis method, device and medium Download PDFInfo
- Publication number
- CN110580570B CN110580570B CN201910748995.2A CN201910748995A CN110580570B CN 110580570 B CN110580570 B CN 110580570B CN 201910748995 A CN201910748995 A CN 201910748995A CN 110580570 B CN110580570 B CN 110580570B
- Authority
- CN
- China
- Prior art keywords
- illegal
- law enforcement
- change index
- repeated
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 32
- 230000008859 change Effects 0.000 claims abstract description 184
- 230000036541 health Effects 0.000 claims abstract description 69
- 230000002596 correlated effect Effects 0.000 claims abstract description 8
- 238000012552 review Methods 0.000 claims description 46
- 238000000034 method Methods 0.000 claims description 25
- 108090000623 proteins and genes Proteins 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 230000007547 defect Effects 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 8
- 239000002131 composite material Substances 0.000 claims description 7
- 230000000875 corresponding effect Effects 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 238000010191 image analysis Methods 0.000 claims description 5
- 230000007423 decrease Effects 0.000 claims description 4
- 238000000418 atomic force spectrum Methods 0.000 claims description 3
- 101150077543 st gene Proteins 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 150000001875 compounds Chemical class 0.000 description 12
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013145 classification model Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to data analysis, and provides a law enforcement analysis method, which comprises the following steps: sending an event picture collected by a law enforcement terminal to a server, extracting image characteristics of the event picture, judging whether the event picture is illegal or not, obtaining illegal quantities at different moments to form an illegal quantity data set, collecting an event which is judged to be illegal and proposed for redaction, and obtaining a redaction quantity data set; obtaining a double-conference rate data set through the illegal data set and the double-conference data set uploaded to the server; the server respectively obtains an illegal increment change index, a repeated incremental change index and a repeated rate change index at each moment through the data set; the server obtains the law enforcement health degree through the illegal increment change index, the repeated increment change index and the repeated rate change index, and the illegal increment change index, the repeated increment change index and the repeated rate change index are negatively correlated with the law enforcement health degree. The invention also provides an electronic device and a storage medium. The invention objectively analyzes whether law enforcement is civilized or healthy.
Description
Technical Field
The present invention relates to the field of data analysis technologies, and in particular, to a law enforcement analysis method, apparatus, and medium.
Background
The civilized law enforcement is to establish the concept of people-oriented law enforcement, law-based law enforcement and law-based law enforcement as residents in the law enforcement, fully honor the rights and interests of the administrative law enforcement relative to the residents, strictly follow law enforcement procedures specified by law, insist on the combination of education and punishment, combine management and service, continuously improve the efficiency of the administrative law enforcement and provide guarantee for the construction of harmonious society and legal society.
In the prior art, the civilization law enforcement degree is artificially and subjectively analyzed through pictures, images, the number and the like of illegal events and repeated events, changes of law enforcement conditions along with time change are not considered, an objective evaluation method for the civilization law enforcement does not exist, whether the law enforcement is healthy or not cannot be judged, the health law enforcement is related to various industries of the society, and a method for analyzing the law enforcement health degree is not available in the prior art.
Disclosure of Invention
In view of the above problems, it is an object of the present invention to provide a law enforcement analysis method, an electronic device, and a storage medium for objectively analyzing whether law enforcement is healthy or not.
In order to achieve the above object, the present invention provides an electronic device comprising a memory and a processor, the memory including a law enforcement analysis program, the law enforcement analysis program when executed by the processor implementing the steps of:
step S1, sending an event picture collected by a law enforcement terminal to a server, extracting image characteristics of the event picture and judging whether the event picture is illegal, collecting the number of the events judged to be illegal at different moments to form an illegal volume data set, collecting the number of the events judged to be illegal and proposed for redaction by the server, and obtaining a redaction volume data set formed by redaction volumes at different moments, wherein the law enforcement terminal comprises a law enforcement recorder and a mobile terminal with a shooting function;
step S2, obtaining a double rate data set according to the following formula through the illegal volume data set and the double volume data set uploaded to the server:
wherein, FtIs an illegal quantity at time t, MtFor the amount of review at time t, ptThe rate of the reemergence at time t;
step S3, the server obtains an illegal increment change index, a repeated increment change index and a repeated rate change index at each moment through the illegal amount data set, the repeated amount data set and the repeated rate data set;
and step S4, the server obtains the law enforcement health degree through the illegal increment change index, the repeated increment change index and the repeated rate change index, wherein the illegal increment change index, the repeated increment change index and the repeated rate change index are negatively related to the law enforcement health degree.
In addition, in order to achieve the above object, the present invention also provides a law enforcement analysis method, including:
step S1, sending an event picture collected by a law enforcement terminal to a server, extracting image characteristics of the event picture and judging whether the event picture is illegal, collecting the number of the events judged to be illegal at different moments to form an illegal volume data set, collecting the number of the events judged to be illegal and proposed for redaction by the server, and obtaining a redaction volume data set formed by redaction volumes at different moments, wherein the law enforcement terminal comprises a law enforcement recorder and a mobile terminal with a shooting function;
step S2, obtaining a double rate data set according to the following formula through the illegal volume data set and the double volume data set uploaded to the server:
wherein, FtIs an illegal quantity at time t, MtFor the amount of review at time t, ptThe rate of the reemergence at time t;
step S3, the server obtains an illegal increment change index, a repeated increment change index and a repeated rate change index at each moment through the illegal amount data set, the repeated amount data set and the repeated rate data set;
and step S4, the server obtains the law enforcement health degree through the illegal increment change index, the repeated increment change index and the repeated rate change index, wherein the illegal increment change index, the repeated increment change index and the repeated rate change index are negatively related to the law enforcement health degree.
Preferably, between step S3 and step S4, further comprising:
weighting and combining the illegal increment change index, the repeated increment change index and the repeated rate change index according to the following formula to obtain a comprehensive index:
wherein Z is a comprehensive index, WM、WfAnd WpRespectively, an illegal incremental change index BMRenegotiate incremental Change index BfAnd a rate of change of redaction index BpWeight of (1), WM+Wf+Wp＝1，
Wherein, in step S4, the composite index is positively correlated with the law enforcement health degree.
Further, it is preferable that in step S4, the weighted increment values { W) of the illegal incremental change index, the review incremental change index, and the review rate change index are obtained by the following formulasM*B′M，Wf*B′f，Wp*B′pThe weighted incremental value is inversely related to the law enforcement health degree
Wherein, B'iThe increment of the illegal increment change index, the repeating increment change index or the repeating rate change index from the t-1 moment to the t moment.
Further, preferably, the step S4 includes:
the comprehensive index is subjected to numerical mapping through a mapping function to obtain the law enforcement health degree
E＝f(Z)
Wherein,
x＝[-1，1]，f(x)＝[a，b]，[a，b]and E is the law enforcement health degree which is positively correlated with the law enforcement health degree.
Further, it is preferable that between step S3 and step S4, further comprising: a step of optimizing the weights of the illegal incremental change index, the repeated incremental change index and the repeated rate change index by using a genetic algorithm, the step comprising:
collecting a sample, wherein the sample comprises an illegal volume data set and a corresponding repeated volume data set;
obtaining the health degrees of a plurality of samples through an expert knowledge base;
the population size is set to be P,randomly generating an initial population of P individuals, G ═ G1，G2，...，Gp)TSelecting [0, 1]]The random real numbers in the population form a non-all-zero real number vector with the length of 3, and the vector is endowed to individuals G in the populationi＝(g1，g2，g3)，i＝1，2，...，P，g1Is an individual G i1 st gene in (a);
and respectively taking each gene of each individual as the weight of the illegal increment change index, the repeated increment change index and the repeated rate change index, and obtaining the fitness of each individual according to the comprehensive index of the sample belonging to each topic class, wherein:
wherein,
is the fitness of individual Gi in the initial population G, m is the number of samples, K is the sample index, EKIs a comprehensive index, E'KObtaining the health degree of the sample through an expert knowledge base;
selecting individuals in the initial population by adopting a roulette operator and a selection strategy based on fitness proportion to obtain selected individuals Gu；
Adopting a single-point crossover operator to carry out crossover updating on the selected individuals, taking the maximum value of each updated gene as the upper bound of the gene, and taking the minimum value of each updated gene as the lower bound of the gene;
carrying out variation operation on the selected individuals after cross updating to obtain the varied individuals, substituting the varied individuals into an individual evaluation subunit, and evolving the initial population, wherein:
wherein, gjTo select an individual GuThe jth gene of (1), gjmaxAnd gjminIs gene gjUpper and lower bounds of rpTo select an individual GuPseudo-random number generated P-th time, iternowIs the current evolutionary algebra, itermaxIs the set maximum evolution algebra, gj' is an evolved individual GuThe j gene of (3);
judging whether the genetic algorithm meets an algorithm ending condition or not, wherein the algorithm ending condition comprises that the change of the individual fitness value is smaller than a set target value when the current evolution algebra is larger than a set maximum evolution algebra or when the current evolution algebra is continuously evolved for multiple times;
and if the algorithm end condition is met, outputting the optimal population individuals as an illegal increment change index, a repeated increment change index and a repeated rate change index.
Preferably, in step S1, the method for obtaining the illegal volume comprises:
uploading pictures of possible illegal events shot by a law enforcement officer law enforcement recorder and mobile terminals with shooting functions of law enforcement officers and masses to an image analysis server, and extracting image characteristics;
inputting the image characteristics into a convolutional neural network to obtain the illegal probability of the event corresponding to the picture;
taking an event of which the illegal probability exceeds a first set threshold value as an illegal event;
and counting the number of the illegal events at different moments to further obtain the illegal quantities at different moments.
Further, preferably, in step S1, the method for obtaining the double-volume data set and the violation data set includes:
obtaining the number of illegal events proposing a repeated conference, thereby obtaining a repeated conference volume data set;
carrying out weighted summation on the violation probability of the violation event, the violation record times of the offenders, the violation severity and the unlawful credit level of the unlawful event which is proposed to be subjected to the review and has not obtained the review result, and obtaining the violation confidence coefficient of the unlawful event;
counting the illegal events with the illegal confidence coefficient not greater than a second set threshold value and the illegal events with successful reedit;
and deleting the illegal events with the confidence coefficient not greater than the second set threshold value and the illegal events with successful redecoration in the illegal volume data set, and updating the illegal volume data set.
Preferably, after step S3, the method further comprises:
and abnormal value detection is carried out on the illegal increment change index, the repeated rate change index or/and the comprehensive index through normal distribution.
In addition, in order to achieve the above object, the present invention also provides a computer-readable storage medium including a law enforcement analysis program, which when executed by a processor implements the steps of the law enforcement analysis method described above.
The law enforcement analysis method, the electronic device and the computer readable storage medium can intuitively know the law enforcement health degree through quantitative numerical values, increment information is added into the illegal increment change index, the reexamination increment change index and the reexamination rate change index, the law enforcement health degree is objectively analyzed by using the law enforcement quantity and the change direction and positive or negative information of the law enforcement index, and factors which specifically influence the decline of the health degree can be known through the influence factors of each index, so that relevant departments can make decisions.
Drawings
FIG. 1 is a schematic diagram of an environment in which a preferred embodiment of the law enforcement analysis method of the present invention is implemented;
FIG. 2 is a block diagram of a preferred embodiment of the law enforcement analysis program of FIG. 1;
FIG. 3 is a flow chart of a preferred embodiment of a law enforcement analysis method of the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The invention provides a law enforcement analysis method, which is applied to an electronic device 1. FIG. 1 is a schematic diagram of an application environment of a preferred embodiment of the law enforcement analysis method of the present invention.
In the present embodiment, the electronic device 1 may be a terminal client having an arithmetic function, such as a server, a mobile phone, a tablet computer, a portable computer, and a desktop computer.
The memory 11 includes at least one type of readable storage medium. The at least one type of readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory, and the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic apparatus 1, such as a hard disk of the electronic apparatus 1. In other embodiments, the readable storage medium may also be an external memory of the electronic device 1, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1.
In the present embodiment, the readable storage medium of the memory 11 is generally used for storing the law enforcement analysis program 10 and the like installed in the electronic device 1. The memory 11 may also be used to temporarily store data that has been output or is to be output.
Processor 12, which in some embodiments may be a Central Processing Unit (CPU), microprocessor or other data Processing chip, executes program code or processes data stored in memory 11, such as executing law enforcement analysis program 10.
The network interface 13 may optionally comprise a standard wired interface, a wireless interface (e.g. WI-FI interface), typically used for establishing a communication connection between the electronic apparatus 1 and other electronic clients.
The communication bus 14 is used to enable connection communication between these components.
Fig. 1 only shows the electronic device 1 with components 11-14, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may alternatively be implemented.
Optionally, the electronic device 1 may further include a user interface, the user interface may include an input unit such as a Keyboard (Keyboard), a voice input device such as a microphone (microphone) or other client with a voice recognition function, a voice output device such as a sound box, a headset, and the like, and optionally the user interface may further include a standard wired interface, a wireless interface.
Optionally, the electronic device 1 may further comprise a display, which may also be referred to as a display screen or a display unit.
In some embodiments, the display device may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch device, or the like. The display is used for displaying information processed in the electronic apparatus 1 and for displaying a visualized user interface.
Optionally, the electronic device 1 further comprises a touch sensor. The area provided by the touch sensor for the user to perform touch operation is called a touch area. Further, the touch sensor described herein may be a resistive touch sensor, a capacitive touch sensor, or the like. The touch sensor may include not only a contact type touch sensor but also a proximity type touch sensor. Further, the touch sensor may be a single sensor, or may be a plurality of sensors arranged in an array, for example.
Optionally, the electronic device 1 may further include logic gates, sensors, audio circuits, and the like, which are not described herein.
In the apparatus embodiment shown in fig. 1, the memory 11, which is a type of computer storage medium, may include an operating system and a law enforcement analysis program 10 therein; the execution of law enforcement analysis program 10 stored in memory 11 by processor 12 implements the following steps:
step S1, sending the event pictures collected by the law enforcement terminal to a server, extracting image features of the event pictures and judging whether the event pictures are illegal, collecting the quantity of the illegal events at different moments to form an illegal volume data set, collecting the quantity of the event judged as illegal and proposed to be repeated by the server, obtaining the repeated volume data set formed by the repeated volume at different moments, wherein the law enforcement terminal comprises a law enforcement recorder and a mobile terminal (mobile phone, camera and the like) with a shooting function, for example, law enforcement personnel can transmit the illegal events to the server through the law enforcement recorder or the mobile phone through the network to form the illegal volume data set in actual law enforcement, the illegal data and records can inform illegal personnel through mails, short messages, telephones and the like, and the illegal personnel can propose to be repeated on line through a law enforcement record network under the condition that the illegal personnel have disputes, or a repeated conference is proposed through a manual work window, and repeated conference data are uploaded to a server to form a repeated conference volume data set;
step S2, obtaining a double rate data set according to the following formula (1) through the illegal amount data set and the double amount data set uploaded to the server
Wherein, FtIs an illegal quantity at time t, MtFor the amount of review at time t, ptThe rate of the reemergence at time t;
step S3, the server respectively obtains the illegal increment change index, the compound conference increment change index and the compound conference rate change index at each moment according to the following formulas (2) - (4) through the illegal amount data set, the compound conference amount data set and the compound conference amount data set
Wherein N is a set time period before the current time, ZMIs the average violation of said time period, ZfFor the average number of repetitions, Z, of the periodpAverage rate of review, max (M) for said period of timeN) Is the maximum violation, min (M) of the time periodN) Is the minimum violation of said time period, max (f)N) For the maximum review amount, min (f) of said time periodN) For the minimum number of repetitions of said period, max (p)N) Maximum review rate, min (p) for said time periodN) Is the minimum rate of repetition, B, of said time periodMChange index for illegal increments, BfFor reviewing incremental change index, BpIs a review rate change index;
step S4, the server obtains the law enforcement health degree through the illegal incremental change index, the repeated incremental change index and the repeated rate change index, which are negatively related to the law enforcement health degree, that is, the larger the illegal incremental change index, the repeated incremental change index and the repeated rate change index are, the lower the law enforcement health degree is, wherein the law enforcement health degree is a quantitative index for measuring the health degree (civilized law enforcement degree) of law enforcement of administrative bodies.
Preferably, the processor 12, when executing the law enforcement analysis program 10 stored in the memory 11, also implements the following steps: further included between step S3 and step S4 is: weighting and combining the illegal increment change index, the repeated increment change index and the repeated rate change index according to the following formula (5) to obtain a comprehensive index
Wherein Z is a comprehensive index, WM、WfAnd WpAre respectively BM、BfAnd BpWeight of (1), WM+Wf+Wp＝1。
At this time, in step S4, the composite index is positively correlated with the law enforcement health degree, that is, as the composite index is larger, the law enforcement health degree is higher, for example, the value range of the composite index [ -1, 1], through the conversion of the numerical sign, Z greater than 0 indicates that the law enforcement health degree is good, Z less than 0 indicates that the law enforcement health degree is low, and Z and 0 indicate that the law enforcement health degree is normal.
In other embodiments, the law enforcement analysis program 10 may also be partitioned into one or more modules, which are stored in the memory 11 and executed by the processor 12 to implement the present invention. The modules referred to herein are referred to as a series of computer program instruction segments capable of performing specified functions. Referring to FIG. 2, a functional block diagram of a preferred embodiment of the law enforcement analysis program 10 of FIG. 1 is shown. The law enforcement analysis program 10 may be divided into a collection module 110 and a server 120, the server 120 including an illegal volume obtaining unit 121, a repeated volume obtaining unit 122, a repeated rate obtaining unit 123, a law enforcement change index obtaining unit 124 and a law enforcement analysis unit 125, wherein the collection module 110 transmits an event picture collected by a law enforcement terminal to the server 120; the illegal amount obtaining unit 121 extracts image features and judges whether the illegal event is illegal, the sum of illegal events at one moment is used as illegal amount, and the illegal amounts at different moments form an illegal amount data set; the review volume obtaining unit 122 determines that one moment is illegal and provides the total sum of the review events as the review volume, and the review volume data set is composed of the review volumes at different moments; the compound rate obtaining unit 123 obtains a compound rate data set from the illicit amount data set obtained by the illicit amount obtaining unit 121 and the compound amount data set obtained by the compound amount obtaining unit 122; the law enforcement change index obtaining unit 124 obtains an illegal incremental change index, a repeated incremental change index and a repeated rate change index at each moment through the illegal volume data set, the repeated volume data set and the repeated rate data set; the law enforcement analysis unit 126 obtains the law enforcement health degree through the illegal incremental change index, the repeated incremental change index and the repeated rate change index.
Preferably, the server 120 further includes a comprehensive index obtaining unit 125 that performs a weighted combination of the illegal incremental change index, the repeated incremental change index, and the repeated rate change index according to the following formula to obtain a comprehensive index, in which the law enforcement analysis unit analyzes the law enforcement health degree according to the comprehensive index, and the law enforcement health degree is higher as the comprehensive index is larger.
In addition, the invention also provides a law enforcement analysis method. Referring to FIG. 3, a flow chart of a preferred embodiment of the law enforcement analysis method of the present invention is shown. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
In this embodiment, the law enforcement analysis method includes:
step S1, sending an event picture collected by a law enforcement terminal to a server to extract image features of the event picture and judge whether the event picture is illegal, collecting the number of the events judged to be illegal at different moments to form an illegal volume data set, collecting the number of the events judged to be illegal and providing a repeated conference by the server to obtain a repeated conference volume data set formed by the repeated conference volumes at different moments, wherein the law enforcement terminal comprises a law enforcement recorder and a mobile terminal (a mobile phone, a camera and the like) with a shooting function;
step S2, obtaining a double rate data set according to the following formula (1) through the illegal amount data set and the double amount data set uploaded to the server
Wherein, FtIs an illegal quantity at time t, MtFor the amount of review at time t, ptThe rate of the reemergence at time t;
step S3, the server respectively obtains the illegal increment change index, the compound conference increment change index and the compound conference rate change index at each moment according to the following formulas (2) - (4) through the illegal amount data set, the compound conference amount data set and the compound conference amount data set
Wherein N is a set time period before the current time, ZMIs the average violation of said time period, ZfFor the average number of repetitions, Z, of the periodpAverage rate of review, max (M) for said period of timeN) Is the maximum violation, min (M) of the time periodN) Is the minimum violation of said time period, max (f)N) For the maximum review amount, min (f) of said time periodN) For the minimum number of repetitions of said period, max (p)N) Maximum review rate, min (p) for said time periodN) A minimum rate of review for the time period;
step S4, the server obtains the law enforcement health degree through the illegal incremental change index, the repeated incremental change index, and the repeated rate change index, where the illegal incremental change index, the repeated incremental change index, and the repeated rate change index are negatively related to the law enforcement health degree, that is, the larger the illegal incremental change index, the repeated incremental change index, and the repeated rate change index, the lower the law enforcement health degree.
In an alternative embodiment, in step S1, the method for obtaining the illegal volume comprises:
uploading pictures of possible illegal events shot by a law enforcement officer law enforcement recorder and mobile terminals with shooting functions of law enforcement officers and masses to an image analysis server, and extracting image characteristics, for example, pictures shot by the law enforcement officer law enforcement recorder, mobile phones of law enforcement officers and pictures shot by masses are uploaded to the image analysis server through public numbers and official networks, the image analysis server is composed of a high-performance artificial intelligence image recognition technology, and the image characteristics are extracted through an image recognition algorithm;
inputting the image features into a convolutional neural network to obtain the illegal probability of the event corresponding to the picture, for example, training a classification model of the illegal picture by using a convolutional neural network such as vgnet, AlexNet or GoogleNet and the like and using a convolutional deep learning method. A batch of illegal photos need to be marked in advance during classification model training, other photos are mixed, and whether the photos are illegal photos is classified through a model training classifier. The classification model predicts an input photo, outputs the photo violation probability or whether the photo violation state is violated, for example, an RGB (red, green and blue) picture with the size of 224x224 pixels of the convolutional neural network input picture is processed by multilayer 3D (three-dimensional) convolution and maximum pooling operation, then a full connection layer of the neural network is added, finally the picture is mapped into a 1000-dimensional feature vector, the feature vector is used as an input training classifier of a two-classifier (logistic regression, decision Tree, random forest and support vector machine), the classifier can be fully connected onto a two-dimensional feature vector by the neural network, a softmax function is used as a target function for mapping, a final result violation probability value is output, a decimal with the value of 0-1 is obtained, the violation probability is higher if the value is larger, the violation fact is about to be definite, and models such as logist, svm and Tree of a machine learning algorithm can be used for carrying out two-classification to output the violation probability;
taking an event of which the illegal probability exceeds a first set threshold value as an illegal event;
the method comprises the steps of counting the number of illegal events at different moments to further obtain illegal quantities at different moments, preferably recording images, corresponding illegal information and illegal states into a database serving as a server to form an illegal quantity data set, wherein the illegal information comprises information such as illegal places, illegal persons, law enforcement personnel, numerous reporters, contact ways, illegal photos, whether illegal states exist and the like.
In step S1, the method for obtaining the complex volume data set and the illegal volume data set includes:
obtaining the number of the illegal events which are proposed for redaction, thereby obtaining a redaction data set, for example, sending the illegal information to the illegal person by the modes of short messages, mails, WeChat and public numbers, and redaction is carried out by the illegal person through the channels of public numbers, manual acceptance windows, government official networks and the like when the illegal information is disputed;
carrying out weighted summation on the violation probability of the violation event, the violation record times of the offenders, the violation severity and the unlawful credit level of the unlawful event which is proposed to be subjected to the review and has not obtained the review result, and obtaining the violation confidence coefficient of the unlawful event;
counting the illegal events with the illegal confidence coefficient not greater than a second set threshold value and the illegal events with successful reedit;
and deleting the illegal events with the confidence coefficient not greater than the second set threshold and the illegal events with the reply success from the illegal volume data set, updating the illegal volume data set, namely judging the reply success or the reply failure of the illegal record, canceling the illegal record and the illegal penalty of the illegal person if the reply is successful, keeping the illegal state of the illegal record if the reply is failed, and recording the flow of the reply into a database, wherein all the data for lifting the reply form the duplicate volume data set.
In an alternative embodiment, between step S3 and step S4, further comprising: weighting and combining the illegal increment change index, the repeated increment change index and the repeated rate change index according to the following formula (5) to obtain a comprehensive index
Wherein Z is a comprehensive index, WM、WfAnd WpAre respectively BM、BfAnd BpWeight of (1), WM+Wf+Wp＝1，
At this time, in step S4, the composite index is positively correlated with the law enforcement health degree, that is, the law enforcement health degree is higher as the composite index is larger.
Preferably, step S4 includes:
the comprehensive index is subjected to numerical mapping through a mapping function to obtain the law enforcement health degree
E＝f(Z)
Wherein,
x＝[-1，1]，f(x)＝[a，b]，[a，b]for mapping intervals, E is the law enforcement health level, law enforcement health level and law enforcement healthThe degree is positively correlated.
Preferably, after step S3, the method further comprises:
abnormal value detection is carried out on the illegal incremental change index, the repeated rate change index or/and the comprehensive index through normal distribution, and the abnormal value detection comprises the following steps:
the mean and standard deviation of each index were obtained by the following formulas (7) and (8), respectively
Wherein, XiThe value of an index at the ith moment in the illegal increment change index, the repeated rate change index and the comprehensive index is shown, mu is the average value of the indexes, and sigma is the standard deviation of the indexes;
the value of the index at each time is judged to be true or false by the following equation (9)
The result of one of the illegal increment change index, the repeated rate change index and the comprehensive index after being judged is a true value (normal value) or a false value (abnormal value), and a true and false result can be represented by binarization.
The abnormal value detection eliminates particularly large values which are not in accordance with the conventional method, prevents the whole calculation result from being small due to a plurality of abnormal values, and prevents the abnormal values from being concentrated in a small data interval, so that the subsequent calculation is inconvenient, and the difference between the results is difficult to reflect.
In an alternative embodiment of the present invention, between step S3 and step S4, the method further comprises: a step of optimizing the weights of the illegal incremental change index, the repeated incremental change index and the repeated rate change index by using a genetic algorithm, the step comprising:
collecting a sample, wherein the sample comprises an illegal volume data set and a corresponding repeated volume data set;
obtaining the health degrees of a plurality of samples through an expert knowledge base;
assuming the population size is P, randomly generating an initial population of P individuals, and G ═ G1，G2，...，Gp)TSelecting [0, 1]]The random real numbers in the population form a non-all-zero real number vector with the length of 3, and the vector is endowed to individuals G in the populationi＝(g1，g2，g3)，i＝1，2，...，P，g1Is an individual G i1 st gene in (a);
and respectively taking each gene of each individual as the weight of the illegal increment change index, the repeated increment change index and the repeated rate change index, and obtaining the fitness of each individual according to the comprehensive index of the sample belonging to each topic class, wherein:
wherein,
is an individual G in an initial population GiM is the number of samples, K is the sample index, EKIs a comprehensive index, E'KObtaining the health degree of the sample through an expert knowledge base;
selecting individuals in the initial population by adopting a roulette operator and a selection strategy based on fitness proportion to obtain selected individuals Gu；
Adopting a single-point crossover operator to carry out crossover updating on the selected individuals, taking the maximum value of each updated gene as the upper bound of the gene, and taking the minimum value of each updated gene as the lower bound of the gene;
carrying out variation operation on the selected individuals after cross updating to obtain the varied individuals, substituting the varied individuals into an individual evaluation subunit, and evolving the initial population, wherein:
wherein, gjTo select an individual GuThe jth gene of (1), gjmaxAnd gjminIs gene gjUpper and lower bounds of rpTo select an individual GuPseudo-random number generated P-th time, iternowIs the current evolutionary algebra, itermaxIs the set maximum evolution algebra, gj' is an evolved individual GuThe j gene of (3);
judging whether the genetic algorithm meets an algorithm ending condition or not, wherein the algorithm ending condition comprises that the change of the individual fitness value is smaller than a set target value when the current evolution algebra is larger than a set maximum evolution algebra or when the current evolution algebra is continuously evolved for multiple times;
and if the algorithm end condition is met, outputting the optimal population individuals as an illegal increment change index, a repeated increment change index and a repeated rate change index.
In the above embodiments, in step S3, N represents N times before the current time, the value of N may be set to a fixed value or a sliding window size of a defined time according to the requirement, and the statistical result will be set according to the fixed reference value or the sliding reference value, where the average illegal amount of the N time periods is
Average review amount of
A rate of review of
For example, if the change situation of the recent data needs to be considered, N is set as the recent time period; to take into account the influence of all data, N is set to all time periods.
Preferably, law enforcement health is influenced by a plurality of factors due to time change of different policies among different cities, and a time attenuation factor is added to restrict changes caused by various factors at different times, specifically: for data at different times (said data including the average violation Z)MAverage review amount ZfAverage review rate ZpMaximum violation max (M)N) And minimum violation quantity min (M)N) Maximum review max (f)N) And minimum review min (f)N) Maximum review rate max (p)N) And minimum review rate min (p)N) A time attenuation factor is given, and the time attenuation factors of other time instants closer to the current time instant are larger, that is, the weights of the other time instants closer to the current time instant are larger.
Preferably, factors specifically influencing the decline of the health degree are known through the influence factors of the various indexes so as to facilitate relevant department decisions, such as: when the illegal amount is too large, an alarm signal is sent to a public security department and each living committee, and the strategy is that the public security department strengthens law enforcement and the living committee strengthens general law; when the reexamination amount is too large, rule explanation of illegal violation is added, so that citizens can know the reason of the illegal violation more clearly; the quality of law enforcement personnel and the standard of illegal judgment are improved; the reemergence rate is too large, and the scale and the force of law enforcement personnel are increased.
Further, preferably, in step S4, the weighted increment values { W) of the illegal incremental change index, the review incremental change index, and the review rate change index are obtained by the following equation (13)M*B′M，Wf*B′f，Wp*B′pThe weighted incremental value is inversely related to law enforcement health, e.g. [ W ]M*B′M＞Wf*B′f＞Wp*B′p]It indicates that the illegal incremental change index has the greatest impact on health,
wherein, B'iThe increment of the illegal increment change index, the repeating increment change index or the repeating rate change index from the t-1 moment to the t moment.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a law enforcement analysis program, and the law enforcement analysis program, when executed by a processor, implements the following steps:
step S1, sending an event picture collected by a law enforcement terminal to a server, extracting image characteristics of the event picture and judging whether the event picture is illegal, collecting the number of the events judged to be illegal at different moments to form an illegal volume data set, collecting the number of the events judged to be illegal and providing a repeated conference by the server, and obtaining a repeated conference volume data set formed by the repeated conference volumes at different moments, wherein the law enforcement terminal comprises a law enforcement recorder and a mobile terminal with a shooting function;
step S2, obtaining a double rate data set according to the following formula through the illegal volume data set and the double volume data set uploaded to the server:
wherein, FtIs an illegal quantity at time t, MtFor the amount of review at time t, ptThe rate of the reemergence at time t;
step S3, the server obtains an illegal increment change index, a repeated increment change index and a repeated rate change index at each moment through the illegal amount data set, the repeated amount data set and the repeated rate data set;
and step S4, the server obtains the law enforcement health degree through the illegal increment change index, the repeated increment change index and the repeated rate change index, wherein the illegal increment change index, the repeated increment change index and the repeated rate change index are negatively related to the law enforcement health degree.
The embodiment of the computer readable storage medium of the present invention is substantially the same as the embodiment of the law enforcement analysis method and the electronic device, and will not be described herein again.
According to the law enforcement analysis method, the electronic device and the computer-readable storage medium, the reexamination amount, the reexamination rate and the illegal amount are used as main evaluation indexes, and time attenuation factors are added to the indexes, so that the influence of the recent event development rule is improved, the influence of historical data is reduced, and the method is close to reality as far as possible.
In the various embodiments of the law enforcement analysis method, the electronic device, and the computer-readable storage medium, it is preferable that the method further includes optimizing police strength distribution density according to law enforcement health degree, and specifically includes:
constructing a police force distribution density model according to the following formula (14)
Wherein PLijThe police strength distribution density of the jth street in the ith area;
determining PLijIn that
In the range of, wherein aijIs the building area of the jth street in the ith area, aiE is the accuracy error, and the higher the required accuracy is, the smaller the e value is;
if PL has a defect ofijIn that
Within range, it is reasonable to state the street's current actual police force profile;
if PL has a defect ofijIs less than
The range shows that the actual police force of the street is distributed more at present, and the police force can be reduced;
if PL has a defect ofijIs greater than
Ranges, which indicate that the street currently has less of an actual distribution of police force, may increase police force.
The law enforcement analysis method, the electronic device and the computer readable storage medium evaluate the health degree of law enforcement in one city or one region through main evaluation indexes such as police strength distribution density, reexamination amount, reexamination rate, illegal amount and the like, are suitable for different cities, and the health degree of different cities can have certain comparability.
In the above embodiments of the present invention, the information collected by the law enforcement terminal is not limited to the time picture, but may also be a text describing an event.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. The term "comprising" is used to specify the presence of stated features, integers, steps, operations, elements, components, groups, integers, operations, elements, components, groups, elements, groups, integers, operations, elements.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal client (e.g., a mobile phone, a computer, a server, or a network client) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (12)
1. A law enforcement analysis method, comprising:
step S1, sending an event picture collected by a law enforcement terminal to a server, extracting image characteristics of the event picture and judging whether the event picture is illegal, collecting the number of the events judged to be illegal at different moments to form an illegal volume data set, collecting the number of the events judged to be illegal and proposed for redaction by the server, and obtaining a redaction volume data set formed by redaction volumes at different moments, wherein the law enforcement terminal comprises a law enforcement recorder and a mobile terminal with a shooting function;
step S2, obtaining a double rate data set according to the following formula through the illegal volume data set and the double volume data set uploaded to the server:
wherein, FtIs an illegal quantity at time t, MtFor the amount of review at time t, ptThe rate of the reemergence at time t;
step S3, the server obtains the illegal increment change index, the repeated increment change index and the repeated rate change index of each moment according to the following formula through the illegal amount data set, the repeated amount data set and the repeated rate data set
Wherein N is a set time period before the current time, ZMIs the average violation of said time period, ZfFor the average number of repetitions, Z, of the periodpAverage rate of review, max (M) for said period of timeN) Is the maximum violation, min (M) of the time periodN) Is the minimum violation of said time period, max (f)N) For the maximum review amount, min (f) of said time periodN) For the minimum number of repetitions of said period, max (p)N) Maximum review rate, min (p) for said time periodN) Is the minimum rate of repetition, B, of said time periodMChange index for illegal increments, BfFor reviewing incremental change index, BpIs a review rate change index;
step S4, the server obtains law enforcement health degree through the illegal increment change index, the repeated increment change index and the repeated rate change index, incremental information is added into the illegal increment change index, the repeated increment change index and the repeated rate change index, the law enforcement index change direction is used according to law enforcement quantity, the illegal increment change index, the repeated increment change index and the repeated rate change index are negatively related to the law enforcement health degree, the law enforcement health degree is a quantitative index for measuring the civilized law enforcement degree of the law enforcement of administrative bodies,
and obtaining factors influencing the decline of the health degree through the influencing factors of each index so as to facilitate the decision of related departments.
2. The law enforcement analysis method of claim 1, further comprising, between steps S3 and S4:
weighting and combining the illegal increment change index, the repeated increment change index and the repeated rate change index according to the following formula to obtain a comprehensive index:
wherein Z is a comprehensive index, WM、WfAnd WpRespectively, an illegal incremental change index BMRenegotiate incremental Change index BfAnd a rate of change of redaction index BpWeight of (1), WM+Wf+Wp＝1，
Wherein, in step S4, the composite index is positively correlated with the law enforcement health degree.
3. The law enforcement analysis method according to claim 2, wherein step S4 includes:
the comprehensive index is subjected to numerical mapping through a mapping function to obtain the law enforcement health degree
E＝f(Z)
Wherein,
x＝[-1，1]，f(x)＝[a，b]，[a，b]and E is the law enforcement health degree which is positively correlated with the law enforcement health degree.
4. The law enforcement analysis method according to claim 2, wherein in step S4, the weighted increment values { W) of the illegal incremental change index, the repetitious incremental change index and the repetitious rate change index are obtained by the following formulaM*B′M，Wf*B′f，Wp*B′pThe weighted incremental value is inversely related to the law enforcement health degree
Wherein, B'iThe increment of the illegal increment change index, the repeating increment change index or the repeating rate change index from the t-1 moment to the t moment.
5. The law enforcement analysis method of claim 3, further comprising, between steps S3 and S4: a step of optimizing the weights of the illegal incremental change index, the repeated incremental change index and the repeated rate change index by using a genetic algorithm, the step comprising:
collecting a sample, wherein the sample comprises an illegal volume data set and a corresponding repeated volume data set;
obtaining the health degrees of a plurality of samples through an expert knowledge base;
assuming the population size is P, randomly generating an initial population of P individuals, and G ═ G1，G2，…，Gp)TSelecting [0, 1]]The random real numbers in the population form a non-all-zero real number vector with the length of 3, and the vector is endowed to individuals G in the populationi＝(g1，g2，g3)，i＝1，2，…，P，g1Is an individual Gi1 st gene in (a);
and respectively taking each gene of each individual as the weight of the illegal increment change index, the repeated increment change index and the repeated rate change index, and obtaining the fitness of each individual according to the health degree of each sample, wherein:
wherein,
is an individual G in an initial population GiM is the number of samples, K is the sample index, EKIs the Law Enforcement health of the sample, E'KObtaining the law enforcement health degree of the sample through an expert knowledge base;
selection strategy based on fitness proportion by adopting roulette operatorSelecting individuals in the initial population to obtain selected individuals Gu；
Adopting a single-point crossover operator to carry out crossover updating on the selected individuals, taking the maximum value of each updated gene as the upper bound of the gene, and taking the minimum value of each updated gene as the lower bound of the gene;
carrying out variation operation on the selected individuals after cross updating to obtain the varied individuals, substituting the varied individuals into an individual evaluation subunit, and evolving the initial population, wherein:
wherein, gjTo select an individual GuThe jth gene of (1), gjmaxAnd gjminIs gene gjUpper and lower bounds of rpTo select an individual GuPseudo-random number generated P-th time, iternowIs the current evolutionary algebra, itermaxIs the set maximum evolution algebra, gj' is an evolved individual GuThe j gene of (3);
judging whether the genetic algorithm meets an algorithm ending condition or not, wherein the algorithm ending condition comprises that the change of the individual fitness value is smaller than a set target value when the current evolution algebra is larger than a set maximum evolution algebra or when the current evolution algebra is continuously evolved for multiple times;
and if the algorithm end condition is met, outputting the optimal population individuals as an illegal increment change index, a repeated increment change index and a repeated rate change index.
6. The law enforcement analysis method according to claim 1, wherein in step S1, the method for obtaining the illegal volume comprises:
uploading pictures of possible illegal events shot by a law enforcement officer law enforcement recorder and mobile terminals with shooting functions of law enforcement officers and masses to an image analysis server, and extracting image characteristics;
inputting the image characteristics into a convolutional neural network to obtain the illegal probability of the event corresponding to the picture;
taking an event of which the illegal probability exceeds a first set threshold value as an illegal event;
and counting the number of the illegal events at different moments to further obtain the illegal quantities at different moments.
7. The law enforcement analysis method according to claim 6, wherein in step S1, the method for obtaining the double volume data set and the violation data set comprises:
obtaining the number of illegal events proposing a repeated conference, thereby obtaining a repeated conference volume data set;
carrying out weighted summation on the violation probability of the violation event, the violation record times of the offenders, the violation severity and the unlawful credit level of the unlawful event which is proposed to be subjected to the review and has not obtained the review result, and obtaining the violation confidence coefficient of the unlawful event;
counting the illegal events with the illegal confidence coefficient not greater than a second set threshold value and the illegal events with successful reedit;
and deleting the illegal events with the confidence coefficient not greater than the second set threshold value and the illegal events with successful redecoration in the illegal volume data set, and updating the illegal volume data set.
8. The law enforcement analysis method according to claim 1, wherein after step S3, the method further comprises:
and abnormal value detection is carried out on the illegal increment change index, the repeated rate change index or/and the comprehensive index through normal distribution.
9. The law enforcement analysis method of claim 1, further comprising optimizing police force distribution density based on law enforcement health, comprising:
constructing a police force distribution density model according to the following formula
Wherein PLijThe police strength distribution density of the jth street in the ith area;
determining PLijIn that
In the range of, wherein aijIs the building area of the jth street in the ith area, aiE is the accuracy error, and the higher the required accuracy is, the smaller the e value is;
if PL has a defect ofijIn that
Within range, it is reasonable to state the street's current actual police force profile;
if PL has a defect ofijIs less than
The range shows that the actual police force of the street is distributed more at present, and the police force can be reduced;
if PL has a defect ofijIs greater than
Ranges, which indicate that the street currently has less of an actual distribution of police force, may increase police force.
10. An electronic device comprising a memory and a processor, the memory having a law enforcement analysis program stored therein, the law enforcement analysis program when executed by the processor implementing the steps of:
step S1, sending an event picture collected by a law enforcement terminal to a server, extracting image characteristics of the event picture and judging whether the event picture is illegal, collecting the number of the events judged to be illegal at different moments to form an illegal volume data set, collecting the number of the events judged to be illegal and proposed for redaction by the server, and obtaining a redaction volume data set formed by redaction volumes at different moments, wherein the law enforcement terminal comprises a law enforcement recorder and a mobile terminal with a shooting function;
step S2, obtaining a double rate data set according to the following formula through the illegal volume data set and the double volume data set uploaded to the server:
wherein, FtIs an illegal quantity at time t, MtFor the amount of review at time t, ptThe rate of the reemergence at time t;
step S3, the server obtains the illegal increment change index, the repeated increment change index and the repeated rate change index of each moment according to the following formula through the illegal amount data set, the repeated amount data set and the repeated rate data set
Wherein N is a set time period before the current time, ZMIs the average violation of said time period, ZfFor the average number of repetitions, Z, of the periodpAverage rate of review, max (M) for said period of timeN) Is the maximum violation, min (M) of the time periodN) Is the minimum violation of said time period, max (f)N) Is a stand forMaximum amount of review, min (f) of said periodN) For the minimum number of repetitions of said period, max (p)N) Maximum review rate, min (p) for said time periodN) Is the minimum rate of repetition, B, of said time periodMChange index for illegal increments, BfFor reviewing incremental change index, BpIs a review rate change index;
step S4, the server obtains law enforcement health degree through the illegal increment change index, the repeated increment change index and the repeated rate change index, incremental information is added into the illegal increment change index, the repeated increment change index and the repeated rate change index, the law enforcement index change direction is used according to law enforcement quantity, the illegal increment change index, the repeated increment change index and the repeated rate change index are negatively related to the law enforcement health degree, the law enforcement health degree is a quantitative index for measuring the civilized law enforcement degree of the law enforcement of administrative bodies,
and obtaining factors influencing the decline of the health degree through the influencing factors of each index so as to facilitate the decision of related departments.
11. The electronic device of claim 10, further comprising optimizing police force distribution density based on law enforcement health, comprising:
constructing a police force distribution density model according to the following formula
Wherein PLijThe police strength distribution density of the jth street in the ith area;
determining PLijIn that
In the range of, wherein aijIs the building area of the jth street in the ith area, aiE is the accuracy error, and the higher the required accuracy is, the smaller the e value is;
if PL has a defect ofijIn that
Within range, it is reasonable to state the street's current actual police force profile;
if PL has a defect ofijIs less than
The range shows that the actual police force of the street is distributed more at present, and the police force can be reduced;
if PL has a defect ofijIs greater than
Ranges, which indicate that the street currently has less of an actual distribution of police force, may increase police force.
12. A computer-readable storage medium, comprising a law enforcement analysis program, which when executed by a processor, performs the steps of the law enforcement analysis method of any one of claims 1 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910748995.2A CN110580570B (en) | 2019-08-14 | 2019-08-14 | Law enforcement analysis method, device and medium |
| PCT/CN2020/105341 WO2021027569A1 (en) | 2019-08-14 | 2020-07-29 | Law enforcement analysis method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910748995.2A CN110580570B (en) | 2019-08-14 | 2019-08-14 | Law enforcement analysis method, device and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110580570A CN110580570A (en) | 2019-12-17 |
| CN110580570B true CN110580570B (en) | 2021-01-15 |
Family
ID=68811180
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910748995.2A Active CN110580570B (en) | 2019-08-14 | 2019-08-14 | Law enforcement analysis method, device and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110580570B (en) |
| WO (1) | WO2021027569A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110580570B (en) * | 2019-08-14 | 2021-01-15 | 平安国际智慧城市科技股份有限公司 | Law enforcement analysis method, device and medium |
| CN111553816B (en) * | 2020-04-20 | 2023-11-03 | 北京北大软件工程股份有限公司 | Administrative multiple-proposal influence factor analysis method and device |
| CN112132455A (en) * | 2020-09-22 | 2020-12-25 | 平安国际智慧城市科技股份有限公司 | Traffic law enforcement evaluation method, device, equipment and storage medium |
| CN118134195B (en) * | 2024-03-27 | 2024-10-15 | 上海大帜信息技术有限公司 | Handheld terminal of law enforcement appearance with optimize management function |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992976A (en) * | 2017-12-15 | 2018-05-04 | 中国传媒大学 | Much-talked-about topic early-stage development trend predicting system and Forecasting Methodology |
| CN109993056A (en) * | 2019-02-25 | 2019-07-09 | 平安科技（深圳）有限公司 | A kind of method, server and storage medium identifying vehicle violation behavior |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7024360B2 (en) * | 2003-03-17 | 2006-04-04 | Rensselaer Polytechnic Institute | System for reconstruction of symbols in a sequence |
| US20130185234A1 (en) * | 2012-01-16 | 2013-07-18 | Amrinder Arora | System and Method for Using Genetic Algorithm for Optimization of Targeting Systems, Based on Aggregated Scoring Models |
| CN103164787A (en) * | 2013-02-27 | 2013-06-19 | 四川省鼎宸科技发展有限公司 | System and method of culture enforcement digitization terminal |
| CN103929617A (en) * | 2014-04-14 | 2014-07-16 | 李兴海 | Multi-angle on-site law enforcement information acquisition and transmission system for police |
| CN106529902A (en) * | 2016-10-19 | 2017-03-22 | 苏州市吴江区公安局 | Method and system of detecting audit quality of off-site law enforcement officers |
| CN106874863B (en) * | 2017-01-24 | 2020-02-07 | 南京大学 | Vehicle illegal parking and reverse running detection method based on deep convolutional neural network |
| US10706297B2 (en) * | 2017-09-20 | 2020-07-07 | International Business Machines Corporation | Management of parking spaces |
| CN108256554A (en) * | 2017-12-20 | 2018-07-06 | 深圳市金溢科技股份有限公司 | Vehicle reverse stopping judgment method, server and system based on deep learning |
| CN110580570B (en) * | 2019-08-14 | 2021-01-15 | 平安国际智慧城市科技股份有限公司 | Law enforcement analysis method, device and medium |
-
2019
- 2019-08-14 CN CN201910748995.2A patent/CN110580570B/en active Active
-
2020
- 2020-07-29 WO PCT/CN2020/105341 patent/WO2021027569A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992976A (en) * | 2017-12-15 | 2018-05-04 | 中国传媒大学 | Much-talked-about topic early-stage development trend predicting system and Forecasting Methodology |
| CN109993056A (en) * | 2019-02-25 | 2019-07-09 | 平安科技（深圳）有限公司 | A kind of method, server and storage medium identifying vehicle violation behavior |
Non-Patent Citations (1)
| Title |
|---|
| 行政执法绩效评估指标研究;陈书笋;《社会科学》;20140331(第3期);第98-103页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110580570A (en) | 2019-12-17 |
| WO2021027569A1 (en) | 2021-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110580570B (en) | Law enforcement analysis method, device and medium | |
| CN111177473B (en) | Personnel relationship analysis method, device and readable storage medium | |
| CN111538827B (en) | Case recommendation method, device and storage medium based on content and graph neural network | |
| CN107909299A (en) | People hinders Claims Resolution data risk checking method and system | |
| CN113722611B (en) | Recommendation method, device and equipment for government affair service and computer readable storage medium | |
| CN107153847A (en) | Predict method and computing device of the user with the presence or absence of malicious act | |
| CN113111930B (en) | End-to-end Ethernet fishing account detection method and system | |
| CN111754044B (en) | Employee behavior auditing method, device, equipment and readable storage medium | |
| CN108388969A (en) | Inside threat personage's Risk Forecast Method based on personal behavior temporal aspect | |
| CN106095939B (en) | The acquisition methods and device of account authority | |
| CN114143049B (en) | Abnormal flow detection method and device, storage medium and electronic equipment | |
| WO2022217711A1 (en) | Multi-layer association knowledge graph-based information prediction method and apparatus, device, and medium | |
| CN114638633A (en) | Abnormal flow detection method and device, electronic equipment and storage medium | |
| CN112995414A (en) | Behavior quality inspection method, device, equipment and storage medium based on voice call | |
| CN111159481B (en) | Edge prediction method and device for graph data and terminal equipment | |
| CN115545103A (en) | Abnormal data identification method, label identification method and abnormal data identification device | |
| CN114841526A (en) | Detection method of high-risk user, computing device and readable storage medium | |
| CN109918914B (en) | Hierarchical information system attack defense capability comprehensive evaluation system and method | |
| CN113409096B (en) | Target object identification method and device, computer equipment and storage medium | |
| CN116029760A (en) | Message pushing method, device, computer equipment and storage medium | |
| CN116310920A (en) | Image privacy prediction method based on scene context awareness | |
| CN113538199B (en) | Image steganography detection method based on multi-layer perception convolution and channel weighting | |
| JP4938367B2 (en) | Security diagnostic system | |
| CN114358186A (en) | Data processing method and device and computer readable storage medium | |
| CN113821498A (en) | Data screening method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |