CN113052413A - Risk passenger assessment method, device, terminal and computer readable medium - Google Patents

Risk passenger assessment method, device, terminal and computer readable medium Download PDF

Info

Publication number
CN113052413A
CN113052413A CN201911368970.6A CN201911368970A CN113052413A CN 113052413 A CN113052413 A CN 113052413A CN 201911368970 A CN201911368970 A CN 201911368970A CN 113052413 A CN113052413 A CN 113052413A
Authority
CN
China
Prior art keywords
passenger
risk
candidate
evaluated
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911368970.6A
Other languages
Chinese (zh)
Inventor
郝艳妮
孔庆超
王宇琪
罗引
彭鑫
张西娜
王磊
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.)
Beijing Zhongke Wenge Technology Co ltd
Original Assignee
Beijing Zhongke Wenge 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 Beijing Zhongke Wenge Technology Co ltd filed Critical Beijing Zhongke Wenge Technology Co ltd
Priority to CN201911368970.6A priority Critical patent/CN113052413A/en
Publication of CN113052413A publication Critical patent/CN113052413A/en
Pending legal-status Critical Current

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
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • 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
    • G06Q50/14—Travel agencies

Landscapes

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

Abstract

The application provides a risk passenger assessment method, which comprises the following steps: the method comprises the steps of obtaining information of a plurality of passengers to be evaluated, wherein the information of each passenger to be evaluated comprises a plurality of trip information and a plurality of attribute information; calculating a first risk value of each passenger to be evaluated according to the trip information, and bringing the passenger to be evaluated, of which the first risk value exceeds a first preset threshold value, into a first candidate passenger set; inputting the travel information into a gradient lifting decision tree, outputting a second risk value of the passenger to be evaluated, and bringing the passenger to be evaluated, of which the second risk value exceeds a first preset threshold value, into a second candidate passenger set; obtaining a third candidate passenger set according to the first candidate passenger set and the second candidate passenger set; and calculating a third risk value according to the identity information of a third candidate passenger in the third candidate passenger set, determining the third candidate passenger with the third risk value exceeding a second preset threshold value as the risky passenger, and evaluating the risky passenger by adopting multi-party information and a gradient promotion decision tree, so that the evaluation accuracy is improved.

Description

Risk passenger assessment method, device, terminal and computer readable medium
Technical Field
The present application relates to the field of big data technologies, and in particular, to a method, an apparatus, a terminal, and a computer-readable medium for risk passenger assessment.
Background
In real life, security check needs to be performed on a passenger to evaluate whether the passenger is a passenger with a risk, for example, whether the passenger is a passenger who has carried flammable and explosive materials to get on a bus or not, and the evaluation of the passenger with the risk in the prior art is performed manually by a worker, which has the disadvantages of low accuracy and low efficiency.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method, an apparatus, a terminal and a computer-readable medium for risk passenger assessment, so as to solve the problem that efficiency of manually searching for risk passengers is inaccurate.
The specific technical scheme is as follows:
in a first aspect, a method for risk passenger assessment is provided, the method comprising:
the method comprises the steps of obtaining information of a plurality of passengers to be evaluated, wherein the information of each passenger to be evaluated comprises a plurality of trip information and a plurality of attribute information;
calculating a first risk value of each passenger to be evaluated according to the trip information, and bringing the passenger to be evaluated, of which the first risk value exceeds a first preset threshold value, into a first candidate passenger set;
inputting the travel information into a gradient lifting decision tree, outputting a second risk value of the passenger to be evaluated, and bringing the passenger to be evaluated, of which the second risk value exceeds the first preset threshold, into a second candidate passenger set;
obtaining a third candidate passenger set according to the first candidate passenger set and the second candidate passenger set;
and calculating a third risk value according to the identity information of a third candidate passenger in the third candidate passenger set, and determining the third candidate passenger with the third risk value exceeding a second preset threshold value as the risky passenger.
Optionally, after determining that the third candidate passenger with the third risk value exceeding the second preset threshold is a risky passenger, the method further includes:
arranging the risk passengers according to the sequence of the third risk values from large to small to obtain a risk passenger sequence;
and outputting the risk passenger sequence.
Optionally, the calculating a first risk value of each passenger to be assessed according to the travel information includes:
calculating a sub-risk value of each piece of travel information;
and weighting and summing all the sub-risk values of each passenger to be evaluated to obtain the first risk value.
Optionally, the calculating the sub-risk value of each piece of travel information includes:
determining a sorting position of the travel information in a preset risk passenger database aiming at each travel information, wherein the risk passenger database comprises a sorting sequence of each travel information of preset risk passengers;
and determining a sub-risk value corresponding to the sorting position as a sub-risk value of the travel information.
Optionally, obtaining a third candidate passenger set according to the first candidate passenger set and the second candidate passenger set includes:
calculating a union of the first set of candidate passengers and the second set of candidate passengers;
and using the union as the third candidate passenger set.
In a second aspect, an apparatus for assessing at risk passengers, the apparatus comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring information of a plurality of passengers to be evaluated, and the information of each passenger to be evaluated comprises a plurality of trip information and a plurality of attribute information;
the calculation module is used for calculating a first risk value of each passenger to be evaluated according to the trip information, and bringing the passenger to be evaluated, of which the first risk value exceeds a first preset threshold value, into a first candidate passenger set;
the input and output module is used for inputting the trip information into a gradient lifting decision tree, outputting a second candidate passenger set, and obtaining a third candidate passenger set according to the first candidate passenger set and the second candidate passenger set;
and the determining module is used for calculating a second risk value according to the identity information of the third candidate passenger in the third candidate passenger set, and determining the third candidate passenger with the second risk value exceeding a second preset threshold value as the risky passenger.
Optionally, the apparatus further comprises:
the arrangement module is used for arranging the risky passengers according to the sequence of the second risk values from large to small to obtain a risky passenger sequence;
and the output module is used for outputting the risk passenger sequence.
Optionally, the calculation module includes:
the first calculating unit is used for calculating the sub-risk value of each piece of travel information;
and the second calculation unit is used for weighting and summing all the sub-risk values of each passenger to be evaluated to obtain the first risk value.
In a third aspect, an electronic device includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing any of the method steps described herein when executing the program stored in the memory.
In a fourth aspect, a computer-readable storage medium is characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, performs any of the method steps.
The embodiment of the application has the following beneficial effects:
the embodiment of the application provides a risk passenger assessment method, can assess risk passengers from a plurality of trip information and a plurality of attribute information simultaneously, increase the accuracy and the comprehensiveness of assessment, contrast risk passengers with preset risk passengers in a risk passenger database, increased the authenticity, in addition, adopt gradient promotion decision tree to assess risk passengers and also improved accuracy and validity. Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flowchart of a method for risk passenger assessment according to an embodiment of the present disclosure;
FIG. 2 is a flowchart of a method for sorting risky passengers according to an embodiment of the present application;
FIG. 3 is a flowchart of a method for calculating a first risk value according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an apparatus for determining a risky passenger according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
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. 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.
The embodiment of the application provides a risk passenger assessment method, which can be applied to a server, wherein the server is used for accurately searching risk passengers from passengers to be assessed, and the efficiency of searching the risk passengers is improved.
The method for assessing a risky traveler provided in the embodiments of the present application will be described in detail below with reference to specific embodiments, as shown in fig. 1, the specific steps are as follows:
step 101: the method comprises the steps of obtaining information of a plurality of passengers to be evaluated, wherein the information of each passenger to be evaluated comprises a plurality of trip information and a plurality of attribute information.
In the embodiment of the invention, the server needs to search one or more risky passengers from a plurality of passengers to be evaluated, so the server obtains the information of the plurality of passengers to be evaluated, wherein the information of each passenger to be evaluated comprises a plurality of travel information and a plurality of attribute information, and the server can obtain a plurality of travel information and a plurality of attribute information of the passenger to be evaluated in one searching process. In the embodiment of the invention, the travel information at least comprises one or more of the departure place, the total exit and entry frequency, the exit and entry time length, the adjacent exit and entry time interval, the age, the flight, the nationality and the co-workers of the passenger to be evaluated; the attribute information at least includes one or more of a school calendar, a household registration and a nationality of the passenger to be evaluated.
Step 102: and calculating a first risk value of each passenger to be evaluated according to the travel information, and bringing the passenger to be evaluated, of which the first risk value exceeds a first preset threshold value, into a first candidate passenger set.
In the embodiment of the invention, the server determines the sub-risk value corresponding to the travel information according to the travel information of each passenger to be evaluated, and performs weighted summation on all the sub-risk values of the passenger to be evaluated to obtain the first risk value, wherein the weight is set for each piece of travel information, each piece of travel information is provided with a weight, and the weight is determined according to the importance degree of the travel information in the evaluation. For example, if the frequency and age of entry and exit are important in the evaluation values, the frequency and age of entry and exit are given greater weight.
In the embodiment of the invention, the greater the risk value, the higher the probability that the passenger to be evaluated may be a risky passenger. The server judges whether the first risk value of the passenger to be evaluated exceeds a first preset threshold value, if the first risk value of the passenger to be evaluated exceeds the first preset threshold value, the probability that the passenger to be evaluated is a risky passenger is high, and the server brings the passenger to be evaluated into a first candidate passenger set; if the first risk value of the passenger to be assessed does not exceed the first preset threshold value, which indicates that the probability that the passenger to be assessed is a risky passenger is low, the server does not bring the passenger to be assessed into the first candidate passenger set.
Step 103: and inputting the travel information into a gradient lifting decision tree, outputting a second risk value of the passenger to be evaluated, and bringing the passenger to be evaluated, of which the second risk value exceeds a first preset threshold value, into a second candidate passenger set.
In the embodiment of the invention, the server inputs the travel information of all the passengers to be evaluated into a GBDT (Gradient Boosting Decision Tree) GBDT (guaranteed binary Tree), the GBDT can determine the passenger to be evaluated corresponding to each travel information through a label, the GBDT performs regression prediction on the passenger to be evaluated so as to predict the risk passenger, the GBDT outputs a second risk value of the corresponding passenger to be evaluated through the travel information, and judges whether the second risk value of the passenger to be evaluated exceeds a first preset threshold value, if the second risk value of the passenger to be evaluated exceeds the first preset threshold value, the probability that the passenger to be evaluated is the risk passenger is high, the server brings the passenger to be evaluated into a second candidate passenger set; and if the second risk value of the passenger to be evaluated does not exceed the first preset threshold value, which indicates that the probability that the passenger to be evaluated is a risk passenger is low, the server does not bring the passenger to be evaluated into the second candidate passenger set.
Step 104: and obtaining a third candidate passenger set according to the first candidate passenger set and the second candidate passenger set.
In the embodiment of the present invention, the server may obtain the third candidate passenger set according to the first candidate passenger set and the second candidate passenger set, and the specific calculation manner may be various. In one implementation, the server may calculate a union of the first set of candidate passengers and the second set of candidate passengers, and use the union as the third set of candidate passengers. In another implementation, the server may further calculate an intersection of the first set of candidate passengers and the second set of candidate passengers, and use the intersection as a third set of candidate passengers.
Step 105: and calculating a third risk value according to the identity information of the third candidate passenger in the third candidate passenger set, and determining the third candidate passenger with the third risk value exceeding a second preset threshold value as the risky passenger.
In the embodiment of the present invention, the server determines third candidate passengers in a third candidate passenger set, determines each identity information of each third candidate passenger, determines a sub-risk value corresponding to the identity information, and obtains a third risk value by weighting and summing up all the sub-risk values of the third candidate passengers, where the weight is set for each identity information, each identity information is provided with a weight, and the weight is determined according to the importance degree of the identity information in the evaluation. For example, if the nationality is important in the evaluation, the nationality is given a larger weight.
In the embodiment of the present invention, the server determines whether the third risk value of the third candidate passenger exceeds a second preset threshold, and if the third risk value of the third candidate passenger exceeds the second preset threshold, it indicates that the third candidate passenger is a risky passenger; and if the third risk value of the passenger to be evaluated does not exceed the second preset threshold value, indicating that the third candidate passenger is not a risk passenger.
Optionally, as shown in fig. 2, after determining that the third candidate passenger with the third risk value exceeding the second preset threshold is an at-risk passenger, the method further includes:
step 201: and arranging the risk passengers according to the sequence of the third risk values from large to small to obtain a risk passenger sequence.
In the embodiment of the invention, the server acquires the third risk value of the risky passengers, and arranges the risky passengers according to the sequence of the third risk value from large to small to obtain a risky passenger sequence.
Step 202: and outputting the risk passenger sequence.
In the embodiment of the invention, after obtaining the risk passenger sequence, the server outputs the risk passenger sequence to the terminal. The larger the third risk value is, the more probable the risk passenger is the key risk passenger, the key risk passenger can be sorted in sequence according to the importance degree of the risk passenger, the key risk passenger can be screened out more intuitively and more quickly through sorting, and the efficiency of screening the key risk passenger is improved.
Optionally, calculating a first risk value of each passenger to be assessed according to the travel information, as shown in fig. 3, includes:
step 301: and calculating the sub-risk value of each piece of travel information.
In the embodiment of the invention, each passenger to be evaluated has a plurality of travel information, and the server determines the sorting position of the travel information in a preset risk passenger database aiming at each travel information, wherein the risk passenger database comprises the sorting sequence of each travel information of the preset risk passengers.
In the embodiment of the invention, the risky passenger database comprises a plurality of types of travel information of preset risky passengers, and each type of travel information is sequentially arranged from low to high according to the risk degree to form a sequence, for example, one of the travel information of the preset risky passengers in the risky passenger database is an age, the server sorts the ages according to the risk degree, the age with the highest risk degree is arranged at the lowest position in the sequence, and the age with the lowest risk degree is arranged at the highest position in the sequence.
The risk degree is obtained according to the frequency of the trip information appearing in the risk passenger database, and the higher the frequency of each trip information appearing is, the larger the corresponding risk degree is. For example, the preset risky travelers are 20 years old, 23 years old and 25 years old, wherein 12 preset risky travelers are available for 20 years old, 10 preset risky travelers are available for 23 years old, 9 preset risky travelers are available for 25 years old, then the frequency of occurrence is highest for 23 years old, and the risk value is larger for 23 years old.
And the server determines a sub-risk value corresponding to the sorting position as a sub-risk value of the trip information.
Specifically, the calculation formula is as follows:
Figure BDA0002339172540000081
the method comprises the following steps of obtaining travel information of a risk passenger database, wherein S is source data, namely original data of the risk passenger database, T is target data, namely target data of each passenger to be evaluated, K is a constant, rj represents that the sorting position of the travel information in the preset risk passenger database is the jth, if the age of the risk passenger is 18 years, the sorting position of the risk passenger in the risk passenger database is the fifth position after the age of the risk passenger is 18 years.
The calculation result of this formula is: the ratio of the sorting position of the trip information of the risky traveler to the number of the corresponding trip information in the risky traveler database. Such as: the age of the risky traveler is 18 years, the 18 years are ranked fifth in the risky traveler database, the common age in the risky traveler database is 31, and then the sub-risk value for the age is 5/31.
In the embodiment of the present invention, the process of determining the sub-risk value through the identity information is the same as the process of determining the sub-risk value through the travel information, and the present invention is not described in detail again.
Step 302: and weighting and summing all the sub-risk values of each passenger to be evaluated to obtain a first risk value.
In the embodiment of the present invention, each passenger to be assessed has a plurality of travel information in common, and the first risk value is obtained by weighted summation of the sub-risk values of each travel information, and the calculation formula of the first risk value is as follows:
Figure BDA0002339172540000091
wherein R is1Is a first risk value, aiFor each tripWeight of information, sciSub-risk values for each trip information.
Namely, the first risk value is the total exit and entry frequency weight, the total exit and entry frequency sub-risk value + the origin weight, the departure place sub-risk value + the age weight, the age sub-risk value + the flight weight, the flight sub-risk value + the nationality weight, the nationality sub-risk value + the sibling weight, the sibling sub-risk value + the exit and entry time length weight, the exit and entry time length sub-risk value + the adjacent exit and entry time interval weight, the adjacent exit and entry time interval sub-risk value.
Optionally, before the information of the passenger to be assessed is obtained, the information of the passenger to be assessed is preprocessed. In particular to a method for preparing a high-performance nano-silver alloy,
and (3) total frequency of entry and exit: the server calculates the total exit-entry frequency of the passenger to be evaluated according to the historical exit-entry record of the passenger to be evaluated, and the server removes the record which repeatedly appears in the same exit-entry time.
Age: and the server calculates the age of the risky passenger according to the difference value between the current time and the birth time of the risky passenger.
The starting place: and the server converts the origin codes in the risk passenger ticket into uniform format codes.
And the flight server cleans the linguistic data of the flight number, specifically, the letter contained in the flight number is converted into a uniform format in a case-by-case mode, the letter format contained in the flight number is unified into upper case or lower case, blank spaces or other foreign symbols are removed, and the storage format of the flight number is unified into the same format.
The same person: and the server determines the risk passengers taking the same flight at the same time as the preset risk passengers according to the risk passenger database, and takes the risk passengers with the occurrence frequency more than the preset number as the same passengers.
Nationality: the server cleans the nationality according to the corpus, and removes data with wrongly written characters, nonstandard storage formats and the like.
Length of entry/exit time: the length of the entry and exit time is the length of time that a passenger to be evaluated waits in an entry and exit country in the process of one entry and exit. The server filters out the record of the mismatching of the exit time and the entry time in the ticket, and calculates the absolute value of the time difference between the exit time and the entry time, namely the exit time and the entry time.
Adjacent entry-exit time interval: the adjacent entry time interval is the time interval of two adjacent entry times and the time interval of two adjacent exit times. If the entry time of two adjacent times in the ticket is the same, the server only records one entry time; if the exit time of two adjacent times in the ticket is the same, the server only records one exit time.
Learning a calendar: the server divides the study calendar into a plurality of stages, for example, the server divides the study calendar into a literacy little, a primary school study calendar, a junior high school study calendar, a secondary school study calendar, a college study calendar and a subject study calendar. The server marks 32900of primary school and graduation thereof as the pupil calendar and 32900of primary school, marks 32900of graduation thereof as the junior middle school calendar and high school student calendar, marks 32900of graduation thereof as the high school student calendar and high school student calendar, marks 32900of graduation thereof as the middle school student calendar and high school student calendar, marks 32900of graduation thereof as the big school calendar and graduate graduation thereof, marks 32900of graduation thereof as the subject calendar, and marks other graduates thereof as the subject calendar.
Household registration: the server divides the household registration into agricultural household registration and town household registration, and automatic completion is performed on incomplete household registration information.
The national methods are as follows: the server filters out the passengers to be evaluated which are not registered with the nationality, and divides the foreign passengers to be evaluated which do not contain the nationality into separate areas.
The embodiment of the invention selects the above information by the following factors:
the exit-entry frequency refers to the sum of the historical exit and entry frequencies of the passengers to be evaluated, and is used for measuring the frequency of the passengers to be evaluated in international round trip.
The departure place refers to the departure place of the passenger to be evaluated, and is a risk departure place due to the high risk related frequency of the departure place in the risk passenger database.
The age refers to the age of the passenger to be assessed, and because the age of the passenger to be assessed is distributed in a certain age group, the probability of risk of the passenger to be assessed in the age group is higher than that of the passenger to be assessed in other age groups due to the reasons of living stress or external temptation and the like.
The flight refers to the flight taken by the passenger to be evaluated, and if the flight taken by the passenger to be evaluated is the same as the number of the flight taken by the preset risky passenger, the flight is the risky flight.
The nationality refers to the nationality of the passenger to be evaluated, and the server can judge certain nationalities as risk frequently-occurring places according to the nationality of the risk passenger preset in the risk passenger database.
The co-passenger refers to a passenger to be assessed who takes the same flight at the same time with the preset risk passenger for a plurality of times, and the passenger to be assessed is at risk and is a member of the preset risk passenger.
The length of the departure and entry time refers to the length of the time interval between the departure and entry of the passenger to be assessed once, and the passenger to be assessed with the longer departure and entry time interval can be filtered because the preset time interval between the departure and entry of the risky passenger is shorter.
The adjacent exit-entry time interval refers to the time interval between two adjacent exits or exits of the passenger to be evaluated, the time interval between the current exit-entry time and the last exit-entry time and the time interval between the current exit-entry time and the last exit-entry time are calculated, and the adjacent exit-entry time interval of the passenger with the risk is preset to have a certain rule, so that whether the passenger to be evaluated is the passenger with the risk can be judged by using the rule.
The household registration refers to the information of the place of the household of the domestic passenger to be evaluated and is divided into an agricultural household and a town household. Because the risk rate of the passengers to be evaluated of certain households in the risk passenger database is too low, the passengers to be evaluated conforming to the households can be excluded.
The learnings refer to the learnings information of the passengers to be evaluated, wherein the learnings of the passengers with the preset risks in the risk passenger database are generally low, so that some passengers with higher learnings to be evaluated can be filtered.
The nationality refers to national information of domestic passengers to be evaluated, wherein the probability that certain nationality passengers to be evaluated carry risks is extremely low, and the nationality passengers to be evaluated are excluded.
Based on the same technical concept, the embodiment of the present application further provides a risky passenger assessment apparatus, as shown in fig. 4, the apparatus includes:
the obtaining module 401 is configured to obtain information of a plurality of passengers to be assessed, where the information of each passenger to be assessed includes a plurality of travel information and a plurality of attribute information;
the calculating module 402 is configured to calculate a first risk value of each passenger to be assessed according to the travel information, and bring the passenger to be assessed, whose first risk value exceeds a first preset threshold, into a first candidate passenger set;
the input and output module 403 is configured to input the trip information into the gradient boosting decision tree, output the second candidate passenger set, and obtain a third candidate passenger set according to the first candidate passenger set and the second candidate passenger set;
the determining module 404 is configured to calculate a second risk value according to the identity information of a third candidate passenger in the third candidate passenger set, and determine that the third candidate passenger with the second risk value exceeding a second preset threshold is an at-risk passenger.
Optionally, the apparatus further comprises:
the arrangement module is used for arranging the risky passengers according to the sequence of the second risk values from large to small to obtain a risky passenger sequence;
and the output module is used for outputting the risk passenger sequence.
Optionally, the calculating module 402 includes:
the first calculating unit is used for calculating the sub-risk value of each piece of travel information;
and the second calculating unit is used for weighting and summing all the sub-risk values of each passenger to be evaluated to obtain a first risk value.
Optionally, the first computing unit includes:
the determining subunit is used for determining a sorting position of each piece of travel information in a preset risk passenger database aiming at each piece of travel information, wherein the risk passenger database comprises a sorting sequence of each piece of travel information of a preset risk passenger;
and the generating subunit is used for determining the sub-risk value corresponding to the sorting position as the sub-risk value of the travel information.
Optionally, the input/output module 403 includes:
the third calculating unit is used for calculating the union of the first candidate passenger set and the second candidate passenger set;
and the generating unit is used for taking the union set as a third candidate passenger set.
The embodiment of the application provides a method for assessing risk passengers, which can assess risk passengers from multiple dimensions simultaneously, increases the accuracy and comprehensiveness of assessment, compares the risk passengers with preset risk passengers in a risk passenger database, increases the authenticity, and in addition, adopts a gradient promotion decision tree to assess the risk passengers, thereby also improving the accuracy and the effectiveness. Of course, not all of the above advantages need be achieved in the practice of any one product or method of the present application.
Based on the same technical concept, the embodiment of the present invention further provides an electronic device, as shown in fig. 5, including a processor 501, a communication interface 502, a memory 503 and a communication bus 504, where the processor 501, the communication interface 502 and the memory 503 complete mutual communication through the communication bus 504,
a memory 503 for storing a computer program;
the processor 501 is configured to implement the above method steps when executing the program stored in the memory 503.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
In yet another embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any of the above-mentioned methods for risk passenger assessment.
In yet another embodiment, there is provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the above-described methods of risk passenger assessment.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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 merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A method for risk passenger assessment, the method comprising:
the method comprises the steps of obtaining information of a plurality of passengers to be evaluated, wherein the information of each passenger to be evaluated comprises a plurality of trip information and a plurality of attribute information;
calculating a first risk value of each passenger to be evaluated according to the trip information, and bringing the passenger to be evaluated, of which the first risk value exceeds a first preset threshold value, into a first candidate passenger set;
inputting the travel information into a gradient lifting decision tree, outputting a second risk value of the passenger to be evaluated, and bringing the passenger to be evaluated, of which the second risk value exceeds the first preset threshold, into a second candidate passenger set;
obtaining a third candidate passenger set according to the first candidate passenger set and the second candidate passenger set;
and calculating a third risk value according to the identity information of a third candidate passenger in the third candidate passenger set, and determining the third candidate passenger with the third risk value exceeding a second preset threshold value as the risky passenger.
2. The method of claim 1, wherein after determining that the third candidate passenger with the third risk value exceeding the second preset threshold is an at-risk passenger, further comprising:
arranging the risk passengers according to the sequence of the third risk values from large to small to obtain a risk passenger sequence;
and outputting the risk passenger sequence.
3. The method according to claim 1, wherein the calculating a first risk value of each passenger to be assessed according to the travel information comprises:
calculating a sub-risk value of each piece of travel information;
and weighting and summing all the sub-risk values of each passenger to be evaluated to obtain the first risk value.
4. The method of claim 3, wherein said calculating a sub-risk value for each said travel information comprises:
determining a sorting position of the travel information in a preset risk passenger database aiming at each travel information, wherein the risk passenger database comprises a sorting sequence of each travel information of preset risk passengers;
and determining a sub-risk value corresponding to the sorting position as a sub-risk value of the travel information.
5. The method of claim 1, wherein deriving a third set of candidate passengers based on the first set of candidate passengers and the second set of candidate passengers comprises:
calculating a union of the first set of candidate passengers and the second set of candidate passengers;
and using the union as the third candidate passenger set.
6. An at-risk passenger assessment apparatus, the apparatus comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring information of a plurality of passengers to be evaluated, and the information of each passenger to be evaluated comprises a plurality of trip information and a plurality of attribute information;
the calculation module is used for calculating a first risk value of each passenger to be evaluated according to the trip information, and bringing the passenger to be evaluated, of which the first risk value exceeds a first preset threshold value, into a first candidate passenger set;
the input and output module is used for inputting the trip information into a gradient lifting decision tree, outputting a second candidate passenger set, and obtaining a third candidate passenger set according to the first candidate passenger set and the second candidate passenger set;
and the determining module is used for calculating a second risk value according to the identity information of the third candidate passenger in the third candidate passenger set, and determining the third candidate passenger with the second risk value exceeding a second preset threshold value as the risky passenger.
7. The apparatus of claim 6, further comprising:
the arrangement module is used for arranging the risky passengers according to the sequence of the second risk values from large to small to obtain a risky passenger sequence;
and the output module is used for outputting the risk passenger sequence.
8. The apparatus of claim 7, wherein the computing module comprises:
the first calculating unit is used for calculating the sub-risk value of each piece of travel information;
and the second calculation unit is used for weighting and summing all the sub-risk values of each passenger to be evaluated to obtain the first risk value.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any one of claims 1 to 5 when executing a program stored in the memory.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of the claims 1-5.
CN201911368970.6A 2019-12-26 2019-12-26 Risk passenger assessment method, device, terminal and computer readable medium Pending CN113052413A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911368970.6A CN113052413A (en) 2019-12-26 2019-12-26 Risk passenger assessment method, device, terminal and computer readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911368970.6A CN113052413A (en) 2019-12-26 2019-12-26 Risk passenger assessment method, device, terminal and computer readable medium

Publications (1)

Publication Number Publication Date
CN113052413A true CN113052413A (en) 2021-06-29

Family

ID=76505569

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911368970.6A Pending CN113052413A (en) 2019-12-26 2019-12-26 Risk passenger assessment method, device, terminal and computer readable medium

Country Status (1)

Country Link
CN (1) CN113052413A (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7805362B1 (en) * 2006-10-10 2010-09-28 United Services Automobile Association (Usaa) Methods of and systems for money laundering risk assessment
US8280805B1 (en) * 2006-01-10 2012-10-02 Sas Institute Inc. Computer-implemented risk evaluation systems and methods
US20160042305A1 (en) * 2014-08-05 2016-02-11 Environmental Protection Administration, R.O.C. (Taiwan) Environment risk sorting system
CN106529830A (en) * 2016-12-01 2017-03-22 贵州电网有限责任公司电力科学研究院 Multi-dimensional evaluation-based power transmission line risk evaluation system and evaluation method thereof
WO2017133456A1 (en) * 2016-02-01 2017-08-10 腾讯科技（深圳）有限公司 Method and device for determining risk evaluation parameter
CN109002988A (en) * 2018-07-18 2018-12-14 平安科技（深圳）有限公司 Risk passenger method for predicting, device, computer equipment and storage medium
CN109242740A (en) * 2018-07-18 2019-01-18 平安科技（深圳）有限公司 Identity information risk assessment method, apparatus, computer equipment and storage medium
CN110210673A (en) * 2019-06-05 2019-09-06 福建工程学院 A kind of clearance safety check queuing optimization method
CN110349038A (en) * 2019-06-13 2019-10-18 中国平安人寿保险股份有限公司 Risk evaluation model training method and methods of risk assessment

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8280805B1 (en) * 2006-01-10 2012-10-02 Sas Institute Inc. Computer-implemented risk evaluation systems and methods
US7805362B1 (en) * 2006-10-10 2010-09-28 United Services Automobile Association (Usaa) Methods of and systems for money laundering risk assessment
US20160042305A1 (en) * 2014-08-05 2016-02-11 Environmental Protection Administration, R.O.C. (Taiwan) Environment risk sorting system
WO2017133456A1 (en) * 2016-02-01 2017-08-10 腾讯科技（深圳）有限公司 Method and device for determining risk evaluation parameter
CN106529830A (en) * 2016-12-01 2017-03-22 贵州电网有限责任公司电力科学研究院 Multi-dimensional evaluation-based power transmission line risk evaluation system and evaluation method thereof
CN109002988A (en) * 2018-07-18 2018-12-14 平安科技（深圳）有限公司 Risk passenger method for predicting, device, computer equipment and storage medium
CN109242740A (en) * 2018-07-18 2019-01-18 平安科技（深圳）有限公司 Identity information risk assessment method, apparatus, computer equipment and storage medium
CN110210673A (en) * 2019-06-05 2019-09-06 福建工程学院 A kind of clearance safety check queuing optimization method
CN110349038A (en) * 2019-06-13 2019-10-18 中国平安人寿保险股份有限公司 Risk evaluation model training method and methods of risk assessment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
唐玉丽: "机场旅客风险分类指标体系研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, pages 22 *

Similar Documents

Publication Publication Date Title
US11704325B2 (en) Systems and methods for automatic clustering and canonical designation of related data in various data structures
CN109815314B (en) Intent recognition method, recognition device and computer readable storage medium
US20220147023A1 (en) Method and device for identifying industry classification of enterprise and particular pollutants of enterprise
CN110968699A (en) Logic map construction and early warning method and device based on event recommendation
CN115982765A (en) Data desensitization method, device, equipment and computer readable storage medium
CN110458324B (en) Method and device for calculating risk probability and computer equipment
CN106651057A (en) Mobile terminal user age prediction method based on installation package sequence table
CN110489449B (en) Chart recommendation method and device and electronic equipment
CN112632989B (en) Method, device and equipment for prompting risk information in contract text
CN112231431B (en) Abnormal address identification method and device and computer readable storage medium
CN110741376A (en) Automatic document analysis for different natural languages
CN109933648B (en) Real user comment distinguishing method and device
CN116541752B (en) Metadata management method, device, computer equipment and storage medium
CN113836128A (en) Abnormal data identification method, system, equipment and storage medium
US10229194B2 (en) Providing known distribution patterns associated with specific measures and metrics
CN112835910B (en) Method and device for processing enterprise information and policy information
CN107908649B (en) Text classification control method
US8346685B1 (en) Computerized system for enhancing expert-based processes and methods useful in conjunction therewith
CN112464670A (en) Recognition method, recognition model training method, device, equipment and storage medium
CN112434862A (en) Financial predicament method and device for enterprise on market
CN116189215A (en) Automatic auditing method and device, electronic equipment and storage medium
CN110796178A (en) Decision model training method, sample feature selection method, device and electronic equipment
CN113052413A (en) Risk passenger assessment method, device, terminal and computer readable medium
CN115408527A (en) Text classification method and device, electronic equipment and storage medium
US20210241147A1 (en) Method and device for predicting pair of similar questions and electronic equipment

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