CN110175791B - Stagnation point determination method and stagnation point determination device - Google Patents

Stagnation point determination method and stagnation point determination device Download PDF

Info

Publication number
CN110175791B
CN110175791B CN201910482163.0A CN201910482163A CN110175791B CN 110175791 B CN110175791 B CN 110175791B CN 201910482163 A CN201910482163 A CN 201910482163A CN 110175791 B CN110175791 B CN 110175791B
Authority
CN
China
Prior art keywords
stagnation point
hiding
information
bus
regional
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
Application number
CN201910482163.0A
Other languages
Chinese (zh)
Other versions
CN110175791A (en
Inventor
沈贝伦
沈俊青
李冰
盛丽兰
陆韵
黄刚
张宇杰
夏逢鑫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Chinaoly Technology Co ltd
Original Assignee
Hangzhou Chinaoly Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Chinaoly Technology Co ltd filed Critical Hangzhou Chinaoly Technology Co ltd
Priority to CN201910482163.0A priority Critical patent/CN110175791B/en
Publication of CN110175791A publication Critical patent/CN110175791A/en
Application granted granted Critical
Publication of CN110175791B publication Critical patent/CN110175791B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Computer Security & Cryptography (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Alarm Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the invention provides a stagnation point determining method and a stagnation point determining device, and relates to the technical field of stagnation point determination. The stagnation point determination method is used for determining the stagnation point of a criminal suspect, and comprises the following steps: determining at least one stagnation point according to the current case information of the criminal suspect, calculating a personnel hiding index corresponding to each stagnation point, and generating a discrimination data set according to each stagnation point and the corresponding personnel hiding index; and determining at least one target stagnation point in the at least one stagnation point based on a preset deep learning model and the discrimination data set, wherein the deep learning model is generated based on historical case information training. By the method, the efficiency of searching and catching the criminal suspects can be improved.

Description

Stagnation point determination method and stagnation point determination device
Technical Field
The present invention relates to the technical field of stagnation point determination, and in particular, to a stagnation point determination method and a stagnation point determination device.
Background
The police needs to guess the stagnation point of the criminal suspect when searching and catching the criminal suspect. However, the present inventors have found that, in the prior art, since the number of stagnation points is large, a method of estimating a point where a suspect may stagnate in a short time by the experience of a police is prone to error, and thus there is a problem that efficiency of searching for a criminal suspect is low.
Disclosure of Invention
In view of the above, the present invention provides a stagnation point determination method and a stagnation point determination apparatus to solve the problems in the prior art.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
a stagnation point determination method for determining a stagnation point of a criminal suspect, the method comprising:
determining at least one stagnation point according to the current case information of the criminal suspect, calculating a personnel hiding index corresponding to each stagnation point, and generating a discrimination data set according to each stagnation point and the corresponding personnel hiding index;
and determining at least one target stagnation point in the at least one stagnation point based on a preset deep learning model and the discrimination data set, wherein the deep learning model is generated based on historical case information training.
In a preferred selection of the embodiment of the present invention, the historical case information includes first stagnation point information and second stagnation point information, the method further includes a step of training the deep learning model, and the step includes:
processing the random noise signal through a generator model to obtain a corresponding random noise vector, and comparing the random noise vector with the first stagnation point information through a discriminator model to obtain a comparison result;
adjusting parameters of the generator model and the discriminator model according to the comparison result, and processing the random noise signal based on the adjusted generator model to obtain a new random noise vector, so that the discriminator model compares the new random noise vector with the first stagnation point information to obtain a comparison result which is a preset value;
obtaining new first stagnation point information through the new random noise vector and the first stagnation point information;
and generating new historical case information according to the new first stagnation point information and the second stagnation point information, and training based on the new historical case information to obtain a deep learning model.
In a preferred selection of the embodiment of the present invention, the people hiding index includes a hiding value, and the step of calculating the people hiding index corresponding to each detaining point includes:
acquiring hiding value information of the stagnation point, wherein the hiding value information comprises regional floating population, regional general population, regional external population ratio, regional camera coverage ratio, the number of convenience stores in the region and regional area;
and calculating the hiding value of the stagnation point according to the hiding value information and a first formula.
In a preferred selection of the embodiment of the present invention, the first formula includes:
Figure BDA0002084193570000021
wherein e represents a hiding value, minRepresenting regional floating population, m representing regional general population, w representing regional external population proportion, PcIndicates area camera coverage ratio, msNumber of convenience stores in area, S area, Num number of hidden points of criminal suspect in history case, NumsIndicates the same number of hidden points, t, as the area where the stagnation point is locatedhThe average hiding time length of the criminal suspect in the hiding point in the historical case is shown, n is the number of acquaintances in the area,
Figure BDA0002084193570000022
representing the historical number of interactions of the criminal suspect with the ith individual,
Figure BDA0002084193570000031
and representing the number of interactions between the criminal suspect and the ith person within a preset time length.
In a preferred selection of the embodiment of the present invention, the people hiding index includes a convenience degree, and the step of calculating the people hiding index corresponding to each retention point includes:
acquiring convenience degree information of the stagnation point, wherein the convenience degree information comprises the convenience degree of the bus and the convenience degrees of other modes;
and calculating the convenience degree of the stagnation point according to the convenience degree information and a second formula.
In a preferred selection of the embodiment of the present invention, the second formula includes:
Figure BDA0002084193570000032
Figure BDA0002084193570000033
Carea＝CBus+Cother；
wherein, CBusThe convenience degree of the bus is represented, n represents the number of bus stops in the preset range of the stagnation point, NumiIndicates the number of bus routes, t, in station ijRepresents the departure interval, T, of bus ji trainIndicates the time, T, at which station i arrives at the railway stationi busIndicating the time of arrival of station i at the long-distance bus stop, Ti planeRepresenting the time of arrival of site i at the airport; cotherIndicating the degree of convenience of other modes, nbikeIndicates the number of daily public bicycles within the preset range of the stagnation point, ntaxiIndicates the number of free taxis in the preset range of the stagnation point, nlIndicates the number of large roads connected to the stagnation point, nmIndicating the number of medium roads connected to the stagnation point, nsIndicates the number of small roads connected to the stagnation point, toutRepresenting the average time, t, for self-driving to drive away from the stagnation pointtaxiRepresents the average time spent calling a taxi; careaIndicating the convenience of various traffic modes at the stagnation point.
In a preferred selection of the embodiment of the present invention, the human hiding index includes a hiding cost, and the step of calculating the human hiding index corresponding to each detaining point includes:
acquiring hiding cost information of the stagnation point, wherein the hiding cost information comprises a house vacancy rate, a criminal suspect deposit and a regional daily average hiding cost;
and calculating the hiding cost of the stagnation point according to the hiding cost information and a third formula.
In a preferred selection of the embodiment of the present invention, the third formula includes:
Figure BDA0002084193570000041
where Y denotes a hiding cost, E denotes a house vacancy rate, G denotes a criminal suspect deposit, and d denotes a regional average daily hiding cost.
The embodiment of the invention also provides a stagnation point determining device, which is used for determining the stagnation point of a criminal suspect, and comprises the following components:
the system comprises a judgment data set generation module, a judgment data set generation module and a judgment data set generation module, wherein the judgment data set generation module is used for determining at least one stagnation point according to current case information of a criminal suspect, calculating a personnel hiding index corresponding to each stagnation point, and generating a judgment data set according to each stagnation point and the corresponding personnel hiding index;
and the target stagnation point determining module is used for determining at least one target stagnation point in the at least one stagnation point based on a preset deep learning model and the discrimination data set, wherein the deep learning model is generated based on historical case information training.
In a preferred selection of the embodiment of the present invention, the historical case information includes first stagnation point information and second stagnation point information, the apparatus further includes a deep learning model training module for training the deep learning model, and the module includes:
the comparing unit is used for processing the random noise signal through a generator model to obtain a corresponding random noise vector, and comparing the random noise vector with the first stagnation point information through a discriminator model to obtain a comparison result;
a noise vector generation unit, configured to adjust parameters of the generator model and the discriminator model according to the comparison result, and process the random noise signal based on the adjusted generator model to obtain a new random noise vector, so that the discriminator model compares the new random noise vector with the first stagnation point information to obtain a comparison result that is a preset value;
a stagnation point information generating unit, configured to obtain new first stagnation point information through the new random noise vector and the first stagnation point information;
and the deep learning model training unit is used for generating new historical case information according to the new first stagnation point information and the second stagnation point information and training on the basis of the new historical case information to obtain a deep learning model.
The stagnation point determining method and the stagnation point determining device provided by the embodiment of the invention can confirm each stagnation point and the corresponding personnel hiding index according to the current case information of the criminal suspect to generate the discrimination data set, and determine at least one target stagnation point according to the preset deep learning model and the discrimination data set so as to improve the efficiency of searching and catching the criminal suspect.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a block diagram of an electronic device according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a stagnation point determining method according to an embodiment of the present invention.
Fig. 3 is a schematic flowchart of step S110 in fig. 2.
Fig. 4 is another flowchart of step S110 in fig. 3.
Fig. 5 is another flowchart of step S110 in fig. 3.
Fig. 6 is another schematic flow chart of the stagnation point determining method according to the embodiment of the present invention.
Fig. 7 is a block diagram of a stagnation point determination apparatus according to an embodiment of the present invention.
Fig. 8 is a block diagram of another structure of the stagnation point determination apparatus according to the embodiment of the present invention.
Icon: 10-an electronic device; 12-a memory; 14-a processor; 100-stagnation point determination means; 110-a discrimination data set generation module; 120-target stagnation point determination module; 130-deep learning model training module; 131-a comparison unit; 132-a noise vector generation unit; 133-stagnation point information generating unit; 134-deep learning model training unit.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. In the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not intended to be construed as only or implying relative importance.
In the description of the present invention, unless otherwise expressly specified or limited, the terms "disposed," "connected," and "connected" are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
As shown in fig. 1, an electronic device 10 according to an embodiment of the present invention may include a memory 12, a processor 14, and a stagnation point determination apparatus 100.
Optionally, the specific form of the electronic device 10 is not limited, and may be set according to the actual application requirement. In the present embodiment, a feasible example is provided, and the electronic device 10 may be a computer.
Wherein the memory 12 and the processor 14 are electrically connected directly or indirectly to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The stagnation point determination apparatus 100 includes at least one software functional module that can be stored in the memory 12 in the form of software or firmware (firmware). The processor 14 is used for executing executable computer programs stored in the memory 12, such as software functional modules and computer programs included in the stagnation point determination apparatus 100, and the like, to realize the stagnation point determination method.
The Memory 12 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. Wherein the memory 12 is used for storing a program, and the processor 14 executes the program after receiving the execution instruction.
The processor 14 may be an integrated circuit chip having signal processing capabilities. The Processor 14 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
It will be appreciated that the configuration shown in FIG. 1 is merely illustrative and that the electronic device 10 may include more or fewer components than shown in FIG. 1 or may have a different configuration than shown in FIG. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.
With reference to fig. 2, an embodiment of the present invention provides a stagnation point determination method applicable to the electronic device 10. Wherein the method steps defined by the method related flow may be implemented by the processor 14. The specific process shown in fig. 2 will be described in detail below.
Step S110, at least one stagnation point is determined according to the current case information of the criminal suspect, the personnel hiding indexes corresponding to the stagnation points are calculated, and a judgment data set is generated according to the stagnation points and the corresponding personnel hiding indexes.
In detail, the case information may include, but is not limited to, a case location, a case property, a case time, financial transaction class data of a suspect, a crime record, an educational background, a historical behavior track, a relationship of relatives and friends, stay information (a place of daily use), and a work history. The person hiding index specifically refers to an evaluation index of the criminal suspect hiding at each stagnation point, and the feature vector of each stagnation point and the person hiding index corresponding to the stagnation point can be matched to generate a new vector to be used as the discrimination data set.
Step S120, determining at least one target stagnation point among the at least one stagnation point based on a preset deep learning model and the discrimination data set.
The deep learning model is generated based on historical case information training. In detail, the historical case information may include all case information before the occurrence time of the case.
Through the arrangement, the efficiency of searching and catching criminal suspects can be improved.
In detail, the people hiding index may include a hiding value, a convenience level, and a hiding cost.
In conjunction with fig. 3, step S110 may include step S111 and step S112 to calculate the hiding value.
In step S111, the hidden value information of the held point is acquired.
The hidden value information can include regional floating population, regional general population, regional external population ratio, regional camera coverage ratio, the number of convenience stores in the region and regional area.
In step S112, the hidden value of the stagnation point is calculated based on the hidden value information and a first formula.
In detail, the first formula may include:
Figure BDA0002084193570000081
wherein e represents a hiding value, minRepresenting regional floating population, m representing regional general population, w representing regional external population proportion, PcIndicates area camera coverage ratio, msNumber of convenience stores in area, S area, Num number of hidden points of criminal suspect in history case, NumsIndicates the same number of hidden points, t, as the area where the stagnation point is locatedhThe average hiding time length of the criminal suspect in the hiding point in the historical case is shown, n is the number of acquaintances in the area,
Figure BDA0002084193570000082
representing the historical number of interactions of the criminal suspect with the ith individual,
Figure BDA0002084193570000083
and representing the number of interactions between the criminal suspect and the ith person within a preset time length.
In detail, the specific setting of the region where the stagnation point is located is not limited, and may be set according to the actual application requirement, for example, in this embodiment, the region where the stagnation point is located may be a region within 2 km of the stagnation point. Optionally, the specific setting of the preset duration is not limited, and may be set according to the actual application requirement, for example, in this embodiment, the preset duration may be 2 weeks.
In conjunction with fig. 4, step S110 may include step S113 and step S114 to calculate the convenience degree.
In step S113, convenience level information of the stagnation point is acquired.
Wherein, the convenience degree information comprises the convenience degree of the bus and the convenience degree of other modes.
Step S114, calculating the convenience degree of the stagnation point according to the convenience degree information and a second formula.
In detail, the second formula may include:
Figure BDA0002084193570000091
Figure BDA0002084193570000092
Carea＝CBus+Cother；
wherein, CBusThe convenience degree of the bus is represented, n represents the number of bus stops in the preset range of the stagnation point, NumiIndicates the number of bus routes, t, in station ijRepresents the departure interval, T, of bus ji trainIndicates the time, T, at which station i arrives at the railway stationi busIndicating the time of arrival of station i at the long-distance bus stop, Ti planeRepresenting the time of arrival of site i at the airport; cotherIndicating the degree of convenience of other modes, nbikeIndicates the number of daily public bicycles within the preset range of the stagnation point, ntaxiIndicates the number of free taxis in the preset range of the stagnation point, nlIndicates the number of large roads connected to the stagnation point, nmIndicating connection to the stagnation pointNumber of medium roads, nsIndicates the number of small roads connected to the stagnation point, toutRepresenting the average time, t, for self-driving to drive away from the stagnation pointtaxiRepresents the average time spent calling a taxi; careaIndicating the convenience of various traffic modes at the stagnation point.
In detail, the small road is a single lane road, the medium road is a double lane road, and the large road is a four lane road or more.
In connection with fig. 5, step S110 may include step S115 and step S116 to calculate the hiding cost.
In step S115, the hidden cost information of the held point is acquired.
The hiding cost information comprises a house vacancy rate, a criminal suspect deposit and a regional daily average hiding cost.
In step S116, the hidden cost of the stagnation point is calculated based on the hidden cost information and a third formula.
In detail, the third formula may include:
Figure BDA0002084193570000101
where Y denotes a hiding cost, E denotes a house vacancy rate, G denotes a criminal suspect deposit, and d denotes a regional average daily hiding cost.
Optionally, a specific calculation manner of the area daily average hiding cost is not limited, and the area daily average hiding cost may be set according to a place where the criminal suspect hides, for example, when the criminal suspect hides in a place where the criminal suspect rents monthly, such as a residential quarter, the area daily average hiding cost may be calculated according to a fourth formula; when the criminal suspect hides in a place where the criminal suspect rents daily such as a hotel, the regional daily average hiding cost can be calculated according to the fifth formula.
In detail, the fourth formula may include:
Figure BDA0002084193570000102
wherein d represents the regional daily hiding cost of the monthly rental locations, n represents the number of monthly rental houses in the region, and q represents the total number of the rented houses in the regioniRepresents the monthly rental rate during the ith time and p represents the average daily dietary cost in the area.
In detail, the fifth formula may include:
Figure BDA0002084193570000111
wherein d represents the regional daily average hiding cost per day rental location, n represents the room type in the hotel, numiIndicates the number of i-th rooms, fiRepresenting the unit price of the class i room and p the average daily dietary cost in the area.
The historical case information may include first stagnation point information and second stagnation point information, the first stagnation point information corresponds to stagnation points that cannot be hidden by evasion in the historical case, and the first stagnation point information may be generated according to eigenvectors of the stagnation points that cannot be hidden and the corresponding evasion information. The second stagnation point information corresponds to a stagnation point escaped from a historical case, and can be generated according to a feature vector of the stagnation point and a corresponding person hiding index.
With reference to fig. 6, the method may further include a step of training the deep learning model, where the step may include step S131, step S132, step S133, and step S134, which is described in detail below.
Step S131, a generator model processes the random noise signal to obtain a corresponding random noise vector, and a discriminator model compares the random noise vector with the first stagnation point information to obtain a comparison result.
In detail, the generator model adopts a deconvolution neural network, and can generate a corresponding vector according to an input signal, and the discriminator model adopts a convolution neural network, and can generate a discrimination result according to an input vector, and compare the discrimination result of the random noise vector with the discrimination result of the first stagnation point information to obtain a comparison result.
Step S132, adjusting the parameters of the generator model and the discriminator model according to the comparison result, and processing the random noise signal based on the adjusted generator model to obtain a new random noise vector, so that the discriminator model compares the new random noise vector with the first stagnation point information to obtain a comparison result which is a preset value.
In detail, the difference between the new random noise vector and the first stagnation point information may be determined according to the comparison result, and when the comparison result obtained by comparing the new random noise vector with the first stagnation point information by the discriminator model is a preset value, the discriminator model cannot distinguish the new random noise vector from the first stagnation point information.
In detail, in the present embodiment, the preset value may be 0.5.
Step S133, obtaining new first stagnation point information through the new random noise vector and the first stagnation point information.
In detail, in step S132, the discriminator model cannot distinguish between the new random noise vector and the first stagnation point information, and new first stagnation point information may be obtained through the new random noise vector and the first stagnation point information to expand the number of first stagnation point information.
And S134, generating new historical case information according to the new first stagnation point information and the second stagnation point information, and training based on the new historical case information to obtain a deep learning model.
In detail, new first stagnation point information is obtained in step S132, and new historical case information is generated according to the new first stagnation point information and the second stagnation point information to expand the number of the historical case information, so that the accuracy of the deep learning model obtained by training based on the new historical case information is higher.
With reference to fig. 7, an embodiment of the present invention further provides a stagnation point determination apparatus 100 applicable to the electronic device 10 described above, which may include a discrimination data set generation module 110 and a target stagnation point determination module 120.
The discrimination data set generating module 110 is configured to determine at least one stagnation point according to the current case information of the suspect, calculate a person hiding index corresponding to each stagnation point, and generate a discrimination data set according to each stagnation point and the corresponding person hiding index. In this embodiment, the discriminating data set generating module 110 can be used to execute step S110 described in fig. 2, and the detailed description about the discriminating data set generating module 110 can refer to the foregoing description about step S110.
The target stagnation point determining module 120 is configured to determine at least one target stagnation point among the at least one stagnation point based on a preset deep learning model and the discrimination data set. In this embodiment, the target stagnation point determination module 120 may be configured to perform step 120 described in fig. 2, and the detailed description about the target stagnation point determination module 120 may refer to the foregoing description about step S120.
With reference to fig. 8, the stagnation point determining apparatus 100 may further include a deep learning model training module 130 for training the deep learning model, and the module may include a comparing unit 131, a noise vector generating unit 132, a stagnation point information generating unit 133, and a deep learning model training unit 134.
The comparing unit 131 is configured to process a random noise signal through a generator model to obtain a corresponding random noise vector, and compare the random noise vector with the first stagnation point information through a discriminator model to obtain a comparison result. In this embodiment, the comparing unit 131 may be configured to perform step S131 shown in fig. 6, and the foregoing description of step S131 may be referred to for specific description of the comparing unit 131.
The noise vector generating unit 132 is configured to adjust parameters of the generator model and the discriminator model according to the comparison result, and process the random noise signal based on the adjusted generator model to obtain a new random noise vector, so that the discriminator model compares the new random noise vector with the first stagnation point information to obtain a comparison result which is a preset value. In this embodiment, the noise vector generation unit 132 may be configured to execute step S132 described in fig. 6, and the detailed description about the noise vector generation unit 132 may refer to the foregoing description about step S132.
The stagnation point information generating unit 133 is configured to obtain new first stagnation point information through the new random noise vector and the first stagnation point information. In this embodiment, the stagnation point information generating unit 133 may be configured to execute step S133 shown in fig. 6, and the foregoing description of step S133 may be referred to for specific description of the stagnation point information generating unit 133.
The deep learning model training unit 134 is configured to generate new historical case information according to the new first stagnation point information and the second stagnation point information, and train based on the new historical case information to obtain a deep learning model. In this embodiment, the deep learning model training unit 134 may be configured to perform step S134 described in fig. 6, and the detailed description about the deep learning model training unit 134 may refer to the foregoing description about step S134.
In summary, the stagnation point determination method and the stagnation point determination apparatus 100 provided in the embodiments of the present invention may determine each stagnation point and the corresponding person hiding index according to the current case information of the criminal suspect to generate the discrimination data set, and determine at least one target stagnation point according to the preset deep learning model and the discrimination data set, so as to improve the efficiency of searching for the criminal suspect.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. 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 and includes instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. 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, method, article, or apparatus 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, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (4)

1. A stagnation point determination method for determining a stagnation point of a criminal suspect, the method comprising:
determining at least one stagnation point according to the current case information of the criminal suspect, calculating a personnel hiding index corresponding to each stagnation point, and generating a discrimination data set according to each stagnation point and the corresponding personnel hiding index;
determining at least one target stagnation point in the at least one stagnation point based on a preset deep learning model and the discrimination data set, wherein the deep learning model is generated based on historical case information training;
the personnel hiding index comprises a hiding value, and the step of calculating the personnel hiding index corresponding to each detaining point comprises the following steps:
acquiring hiding value information of the stagnation point, wherein the hiding value information comprises regional floating population, regional general population, regional external population ratio, regional camera coverage ratio, the number of convenience stores in the region and regional area;
calculating the hiding value of the stagnation point according to the hiding value information and a first formula;
the first formula includes:
Figure FDA0002958011710000011
wherein e represents a hiding value, minRepresenting regional floating population, m representing regional general population, w representing regional external population proportion, PcIndicates area camera coverage ratio, msNumber of convenience stores in area, S area, Num number of hidden points of criminal suspect in history case, NumsIndicates the same number of hidden points, t, as the area where the stagnation point is locatedhThe average hiding time length of the criminal suspect in the hiding point in the historical case is shown, n is the number of acquaintances in the area,
Figure FDA0002958011710000021
representing the historical number of interactions of the criminal suspect with the ith individual,
Figure FDA0002958011710000022
representing the number of times of interaction between a criminal suspect and an ith person within a preset time length;
the personnel hiding indexes comprise convenience degrees, and the step of calculating the personnel hiding indexes corresponding to each detaining point comprises the following steps:
acquiring convenience degree information of the stagnation point, wherein the convenience degree information comprises the convenience degree of the bus and the convenience degrees of other modes;
calculating the convenience degree of the stagnation point according to the convenience degree information and a second formula;
the second formula includes:
Figure FDA0002958011710000023
Figure FDA0002958011710000024
Carea＝CBus+Cother；
wherein, CBusThe convenience degree of the bus is represented, n represents the number of bus stops in the preset range of the stagnation point, NumiIndicates the number of bus routes, t, in station ijRepresents the departure interval, T, of bus ji trainIndicates the time, T, at which station i arrives at the railway stationi busIndicating the time of arrival of station i at the long-distance bus stop, Ti planeRepresenting the time of arrival of site i at the airport; cotherIndicating the degree of convenience of other modes, nbikeIndicates the number of daily public bicycles within the preset range of the stagnation point, ntaxiIndicates the number of free taxis in the preset range of the stagnation point, nlIndicates the number of large roads connected to the stagnation point, nmIndicating the number of medium roads connected to the stagnation point, nsIndicating the number of mini-roads, T, connected to the stagnation pointtrainIndicating the time, T, at which the self-propelled vehicle arrives at the railway stationbusIndicating the time, T, at which the self-driving vehicle arrives at the long-distance bus stopplaneIndicating the time of arrival of the self-driving at the airport, toutRepresenting the average time, t, for self-driving to drive away from the stagnation pointtaxiRepresents the average time spent calling a taxi; careaIndicating the convenience of various traffic modes of the stagnation point;
the personnel hiding index comprises hiding cost, and the step of calculating the personnel hiding index corresponding to each detaining point comprises the following steps:
acquiring hiding cost information of the stagnation point, wherein the hiding cost information comprises a house vacancy rate, a criminal suspect deposit and a regional daily average hiding cost;
calculating the hiding cost of the stagnation point according to the hiding cost information and a third formula;
the third formula includes:
Figure FDA0002958011710000031
where Y denotes a hiding cost, E denotes a house vacancy rate, G denotes a criminal suspect deposit, and d denotes a regional average daily hiding cost.
2. The stagnation point determination method of claim 1, wherein the historical case information includes first and second stagnation point information, the method further comprising the step of training the deep-learning model, the step comprising:
processing the random noise signal through a generator model to obtain a corresponding random noise vector, and comparing the random noise vector with the first stagnation point information through a discriminator model to obtain a comparison result;
adjusting parameters of the generator model and the discriminator model according to the comparison result, and processing the random noise signal based on the adjusted generator model to obtain a new random noise vector, so that the discriminator model compares the new random noise vector with the first stagnation point information to obtain a comparison result which is a preset value;
obtaining new first stagnation point information through the new random noise vector and the first stagnation point information;
and generating new historical case information according to the new first stagnation point information and the second stagnation point information, and training based on the new historical case information to obtain a deep learning model.
3. A stagnation point determination apparatus for determining a stagnation point of a criminal suspect, the apparatus comprising:
the system comprises a judgment data set generation module, a judgment data set generation module and a judgment data set generation module, wherein the judgment data set generation module is used for determining at least one stagnation point according to current case information of a criminal suspect, calculating a personnel hiding index corresponding to each stagnation point, and generating a judgment data set according to each stagnation point and the corresponding personnel hiding index;
the target stagnation point determining module is used for determining at least one target stagnation point in the at least one stagnation point based on a preset deep learning model and the discrimination data set, wherein the deep learning model is generated based on historical case information training;
the personnel hiding index comprises a hiding value, and the step of calculating the personnel hiding index corresponding to each detaining point comprises the following steps:
acquiring hiding value information of the stagnation point, wherein the hiding value information comprises regional floating population, regional general population, regional external population ratio, regional camera coverage ratio, the number of convenience stores in the region and regional area;
calculating the hiding value of the stagnation point according to the hiding value information and a first formula;
the first formula includes:
Figure FDA0002958011710000041
wherein e represents a hiding value, minRepresenting regional floating population, m representing regional general population, w representing regional external population proportion, PcIndicates area camera coverage ratio, msNumber of convenience stores in area, S area, Num number of hidden points of criminal suspect in history case, NumsIndicates the same number of hidden points, t, as the area where the stagnation point is locatedhThe average hiding time length of the criminal suspect in the hiding point in the historical case is shown, n is the number of acquaintances in the area,
Figure FDA0002958011710000051
representing the historical number of interactions of the criminal suspect with the ith individual,
Figure FDA0002958011710000052
representing the number of times of interaction between a criminal suspect and an ith person within a preset time length;
the personnel hiding indexes comprise convenience degrees, and the step of calculating the personnel hiding indexes corresponding to each detaining point comprises the following steps:
acquiring convenience degree information of the stagnation point, wherein the convenience degree information comprises the convenience degree of the bus and the convenience degrees of other modes;
calculating the convenience degree of the stagnation point according to the convenience degree information and a second formula;
the second formula includes:
Figure FDA0002958011710000053
Figure FDA0002958011710000054
Carea＝CBus+Cother；
wherein, CBusThe convenience degree of the bus is represented, n represents the number of bus stops in the preset range of the stagnation point, NumiIndicates the number of bus routes, t, in station ijRepresents the departure interval, T, of bus ji trainIndicates the time, T, at which station i arrives at the railway stationi busIndicating the time of arrival of station i at the long-distance bus stop, Ti planeRepresenting the time of arrival of site i at the airport; cotherIndicating the degree of convenience of other modes, nbikeIndicates the number of daily public bicycles within the preset range of the stagnation point, ntaxiIndicates the number of free taxis in the preset range of the stagnation point, nlIndicates the number of large roads connected to the stagnation point, nmIndicating the number of medium roads connected to the stagnation point, nsIndicating the number of mini-roads, T, connected to the stagnation pointtrainIndicating the time, T, at which the self-propelled vehicle arrives at the railway stationbusIndicating the time, T, at which the self-driving vehicle arrives at the long-distance bus stopplaneIndicating the time of arrival of the self-driving at the airport, toutRepresenting the average time, t, for self-driving to drive away from the stagnation pointtaxiRepresents the average time spent calling a taxi; careaIndicating the convenience of various traffic modes of the stagnation point;
the personnel hiding index comprises hiding cost, and the step of calculating the personnel hiding index corresponding to each detaining point comprises the following steps:
acquiring hiding cost information of the stagnation point, wherein the hiding cost information comprises a house vacancy rate, a criminal suspect deposit and a regional daily average hiding cost;
calculating the hiding cost of the stagnation point according to the hiding cost information and a third formula;
the third formula includes:
Figure FDA0002958011710000061
where Y denotes a hiding cost, E denotes a house vacancy rate, G denotes a criminal suspect deposit, and d denotes a regional average daily hiding cost.
4. The stagnation point determination apparatus of claim 3, wherein the historical case information includes first and second stagnation point information, the apparatus further comprising a deep learning model training module for training the deep learning model, the module comprising:
the comparing unit is used for processing the random noise signal through a generator model to obtain a corresponding random noise vector, and comparing the random noise vector with the first stagnation point information through a discriminator model to obtain a comparison result;
a noise vector generation unit, configured to adjust parameters of the generator model and the discriminator model according to the comparison result, and process the random noise signal based on the adjusted generator model to obtain a new random noise vector, so that the discriminator model compares the new random noise vector with the first stagnation point information to obtain a comparison result that is a preset value;
a stagnation point information generating unit, configured to obtain new first stagnation point information through the new random noise vector and the first stagnation point information;
and the deep learning model training unit is used for generating new historical case information according to the new first stagnation point information and the second stagnation point information and training on the basis of the new historical case information to obtain a deep learning model.
CN201910482163.0A 2019-06-04 2019-06-04 Stagnation point determination method and stagnation point determination device Active CN110175791B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910482163.0A CN110175791B (en) 2019-06-04 2019-06-04 Stagnation point determination method and stagnation point determination device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910482163.0A CN110175791B (en) 2019-06-04 2019-06-04 Stagnation point determination method and stagnation point determination device

Publications (2)

Publication Number Publication Date
CN110175791A CN110175791A (en) 2019-08-27
CN110175791B true CN110175791B (en) 2021-08-27

Family

ID=67697887

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910482163.0A Active CN110175791B (en) 2019-06-04 2019-06-04 Stagnation point determination method and stagnation point determination device

Country Status (1)

Country Link
CN (1) CN110175791B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102843547A (en) * 2012-08-01 2012-12-26 安科智慧城市技术（中国）有限公司 Intelligent tracking method and system for suspected target
CN203689576U (en) * 2013-09-24 2014-07-02 刘茜 Mobile intelligent information collection terminal
KR101725880B1 (en) * 2016-02-03 2017-04-13 비트레스 주식회사 System for tracing location of suspect using hidden message and method of the same
CN107622465A (en) * 2016-07-15 2018-01-23 中国电信股份有限公司 For identifying the method and system of suspect
CN107679201A (en) * 2017-10-12 2018-02-09 杭州中奥科技有限公司 Hide people's method for digging, device and electronic equipment
CN109543312A (en) * 2018-11-27 2019-03-29 珠海市新德汇信息技术有限公司 A kind of space-time investigation analysis method and system
CN109614418A (en) * 2018-11-23 2019-04-12 武汉烽火众智数字技术有限责任公司 The method and system of excavation suspected target based on big data

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102843547A (en) * 2012-08-01 2012-12-26 安科智慧城市技术（中国）有限公司 Intelligent tracking method and system for suspected target
CN203689576U (en) * 2013-09-24 2014-07-02 刘茜 Mobile intelligent information collection terminal
KR101725880B1 (en) * 2016-02-03 2017-04-13 비트레스 주식회사 System for tracing location of suspect using hidden message and method of the same
CN107622465A (en) * 2016-07-15 2018-01-23 中国电信股份有限公司 For identifying the method and system of suspect
CN107679201A (en) * 2017-10-12 2018-02-09 杭州中奥科技有限公司 Hide people's method for digging, device and electronic equipment
CN109614418A (en) * 2018-11-23 2019-04-12 武汉烽火众智数字技术有限责任公司 The method and system of excavation suspected target based on big data
CN109543312A (en) * 2018-11-27 2019-03-29 珠海市新德汇信息技术有限公司 A kind of space-time investigation analysis method and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
犯罪轨迹重建理论研究;贾治辉 等;《中国人民公安大学学报（社会科学版）》;20181015(第5期);第118-130页 *

Also Published As

Publication number Publication date
CN110175791A (en) 2019-08-27

Similar Documents

Publication Publication Date Title
US20190102840A1 (en) Electronic System for Dynamic, Quasi-Realtime Measuring and Identifying Driver Maneuvers Solely Based on Mobile Phone Telemetry, and a Corresponding Method Thereof
Chaudhary et al. Flood-water level estimation from social media images
US7571146B2 (en) Event, threat and result change detection system and method
US20170357984A1 (en) Information processing device, information processing method, and program
US20200342430A1 (en) Information Processing Method and Apparatus
CN113196331B (en) Application service providing device and method using satellite image
US20150294422A1 (en) Assessing asynchronous authenticated data sources for use in driver risk management
CN109887283B (en) Road congestion prediction method, system and device based on checkpoint data
US20080104005A1 (en) Method and system for spatial behavior modification based on geospatial modeling
CN109191226B (en) Risk control method and device
CN108389421B (en) Parking lot accurate induction system and method based on image re-identification
CN103366602A (en) Method of determining parking lot occupancy from digital camera images
Kuffer et al. Do we underestimate the global slum population?
Ghosh et al. Customization of automatic incident detection algorithms for signalized urban arterials
CN110969190A (en) Illegal operation vehicle detection method, medium, equipment and device
WO2023006974A1 (en) Optical fraud detector for automated detection of fraud in digital imaginary-based automobile claims, automated damage recognition, and method thereof
CN111380530A (en) Navigation method and related product
Zhang et al. Vehicle re-identification for lane-level travel time estimations on congested urban road networks using video images
Corcoran et al. New technologies in the mix: Assessing N‐mixture models for abundance estimation using automated detection data from drone surveys
CN110175791B (en) Stagnation point determination method and stagnation point determination device
Gao et al. Exploring flood mitigation governance by estimating first-floor elevation via deep learning and google street view in coastal Texas
US20190362432A1 (en) Compliance Aware Crime Risk Avoidance System
CN117076788A (en) Personnel foothold point location analysis method and system based on multidimensional sensing data
Das et al. Why slammed the brakes on? auto-annotating driving behaviors from adaptive causal modeling
Kent et al. Incorporating land cover within bayesian journey-to-crime estimation models

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