CN114218505A - Abnormal space-time point identification method and device, electronic equipment and storage medium - Google Patents
Abnormal space-time point identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114218505A CN114218505A CN202111547351.0A CN202111547351A CN114218505A CN 114218505 A CN114218505 A CN 114218505A CN 202111547351 A CN202111547351 A CN 202111547351A CN 114218505 A CN114218505 A CN 114218505A
- Authority
- CN
- China
- Prior art keywords
- space
- time
- spatiotemporal
- data
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/04—Payment circuits
- G06Q20/06—Private payment circuits, e.g. involving electronic currency used among participants of a common payment scheme
- G06Q20/065—Private payment circuits, e.g. involving electronic currency used among participants of a common payment scheme using e-cash
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method for identifying an abnormal space-time point, which comprises the following steps: receiving a monitoring request and selecting a monitored space-time region; generating a space-time grid corresponding to the space-time area; traversing grid nodes of a space-time grid in a preset space-time kernel density estimation model by a grid search method, and outputting an estimation value; the grid nodes comprise paid order space-time data and unpaid space-time data; the paid order spatiotemporal data and unpaid spatiotemporal data comprise longitude and latitude data and time data; and comparing the estimated value with a preset abnormal space-time threshold value, and identifying an abnormal space-time point. According to the method, time data are introduced, constraints adjacent to time dimensions are established, a space-time kernel density estimation model is further established, abnormal space-time points presenting an aggregation state in a specific time period and a specific time region are effectively identified, the method defects of space and time fracture analysis are overcome, and the passenger order-escaping behavior is effectively identified.
Description
Technical Field
The invention belongs to the technical field of big data processing, and particularly relates to a method and a device for identifying an abnormal space-time point, electronic equipment and a storage medium.
Background
The network appointment car field, the operation mode is usually: the passenger terminal requests the car booking service, the driver terminal receives the request of the passenger terminal and generates a car booking order, when the car booking is dispatched to the order terminal, the passenger terminal pays the cost of the order to the car booking platform, and then the car booking platform pays the car fee of the order to the driver terminal. Due to the operation mode of ordering before paying, many passengers can drill empty to generate the behavior of order escape. The driver is usually paid the fare paid for the order for the platform, and then the platform reminds the passenger to pay the order in time in the forms of short message, telephone and APP message push, but a large number of unpaid orders still exist.
In the prior art, the passenger account number of the order escaping is monitored generally, but the passenger who escapes usually uses the riding service of the network booking platform only once, and discards the account number after the passenger finishes using the account number.
Disclosure of Invention
The present invention is directed to solve the above technical problems, and provides a method and an apparatus for identifying an abnormal space-time point, an electronic device, and a storage medium.
In order to solve the problems, the invention is realized according to the following technical scheme:
in a first aspect, the present invention provides a method for identifying an abnormal space-time point, including the following steps:
receiving a monitoring request and selecting a monitored space-time region;
generating a spatiotemporal grid corresponding to the spatiotemporal region;
traversing grid nodes of the space-time grid in a preset space-time kernel density estimation model by a grid search method, and outputting an estimation value; the preset space-time kernel density estimation model comprises a paid order kernel density estimation model and an unpaid order kernel density estimation model; the grid nodes comprise paid order spatiotemporal data and unpaid spatiotemporal data; the paid order spatiotemporal data and unpaid spatiotemporal data comprise longitude and latitude data and time data;
and comparing the estimated value with a preset abnormal space-time threshold value, and identifying an abnormal space-time point.
With reference to the first aspect, the present invention further provides a first implementation manner of the first aspect, where after the generating the spatio-temporal mesh corresponding to the spatio-temporal region, the method further includes:
receiving a resolution selection command, and re-dividing the spatiotemporal mesh of the spatiotemporal region according to the resolution selection command.
With reference to the first aspect, the present invention further provides a second implementation manner of the first aspect, where the comparing the estimated value with a preset abnormal spatiotemporal threshold value, and identifying an abnormal spatiotemporal point specifically includes:
comparing the estimation value of the paid order core density estimation model with the estimation value of the unpaid order core density estimation model through a preset formula, and outputting a real numerical value with a monotonous meaning; and if the real numerical value is larger than the preset abnormal space-time threshold value, the grid node is an abnormal space-time point.
With reference to the first aspect, the present invention further provides a third implementation manner of the first aspect, where an expression of the preset formula is:
wherein K (x, y, t) is a real number, KDEupEvaluation of a model for density estimation of unpaid orders, KDEpEvaluation of a model for the estimation of the nuclear density of paid orders, KDEupIs KDEup(x,y,t)，KDEpIs KDEp(x,y,t)。
With reference to the first aspect, the present invention further provides a 4 th implementation manner of the first aspect, where the preset spatiotemporal kernel density estimation model is obtained by a method including:
acquiring paid order space-time data or unpaid space-time data of a passenger terminal, and establishing a space-time data set;
and performing core density estimation on each paid order space-time data or unpaid space-time data in a space-time data set through a preset distribution function, a space bandwidth and a time bandwidth to generate a core density estimation function corresponding to the space-time data set.
With reference to the first aspect, the present invention further provides a 5 th implementation manner of the first aspect, where the preset distribution function is a gaussian kernel function, and an expression of the kernel density estimation function is:
in the formula, KDE (x, y, t) is a kernel density estimation value, n is the number of paid order space-time data or unpaid space-time data in the space-time data set, h1Is the spatial bandwidth, h2Is the time bandwidth, (x)i,yi) Latitude data, t, in the space-time data for the ith paid order or unpaid space-time dataiTime data in the ith paid order spatiotemporal data or unpaid spatiotemporal data.
In a second aspect, the present invention provides an apparatus for identifying an abnormal space-time point, including:
the space-time region selection module is used for receiving a monitoring request to select a monitored space-time region;
the space-time grid generating module is used for generating a space-time grid corresponding to the space-time region;
the traversal module is used for traversing grid nodes of the space-time grid in a preset space-time kernel density estimation model through a grid search method and outputting an estimation value; the preset space-time kernel density estimation model comprises a paid order kernel density estimation model and an unpaid order kernel density estimation model; the grid nodes comprise paid order spatiotemporal data and unpaid spatiotemporal data; the paid order spatiotemporal data and unpaid spatiotemporal data comprise longitude and latitude data and time data;
and the identification module is used for comparing the estimated value with a preset abnormal space-time threshold value and identifying an abnormal space-time point.
With reference to the second aspect, the present invention further provides embodiment 1 of the second aspect, further including:
and the re-division space-time grid module is used for receiving a resolution selection command and re-dividing the space-time grid of the space-time region according to the resolution selection command.
In a third aspect, the present invention provides an electronic device, including at least one processor, and a memory communicatively connected to the at least one processor, where the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, and when the at least one processor executes the instructions, the method for identifying an abnormal time-space point is specifically performed according to any one of the first aspect.
In a fourth aspect, the present invention provides a storage medium storing a computer program, characterized in that: the computer program, when executed by a processor, particularly performs a method for identifying an abnormal time-space point as defined in any one of the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
the paid order core density estimation model outputs an estimated value of a paid order, reflects the occurrence probability of the paid order of the grid node, the unpaid order core density estimation model outputs an estimated value of an unpaid order, reflects the occurrence probability of the unpaid order of the grid node, establishes constraints adjacent in time dimension by introducing time data, further establishes a space-time core density estimation model, calculates the space-time distribution density of behaviors of the unpaid order and the paid order, further analyzes the occurrence frequency of the unpaid order and the occurrence frequency of the paid order, effectively identifies an abnormal space-time point which presents an aggregation state in a specific time period and a specific time region, overcomes the defects of a space and time fracture analysis method, and effectively identifies the order escape behavior of passengers.
Drawings
Embodiments of the invention are described in further detail below with reference to the attached drawing figures, wherein:
FIG. 1 is a flow chart illustrating a method for identifying an abnormal space-time point according to the present invention;
fig. 2 is a schematic structural diagram of an abnormal space-time point identification apparatus according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The term "include" and variations thereof as used herein is meant to be inclusive in an open-ended manner, i.e., "including but not limited to". Unless specifically stated otherwise, the term "or" means "and/or". The term "based on" means "based at least in part on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first," "second," and the like may refer to different or the same object. Other explicit and implicit definitions are also possible below.
The operation mode in the field of network appointment vehicles is generally as follows: the passenger terminal requests the car booking service, the driver terminal receives the request of the passenger terminal and generates a car booking order, when the car booking is dispatched to the order terminal, the passenger terminal pays the cost of the order to the car booking platform, and then the car booking platform pays the car fee of the order to the driver terminal. Due to the operation mode of ordering before paying, many passengers can drill empty to generate the behavior of order escape. The driver is usually paid the fare paid for the order for the platform, and then the platform reminds the passenger to pay the order in time in the forms of short message, telephone and APP message push, but a large number of unpaid orders still exist.
In the prior art, a passenger account number for a passenger to escape from a list is usually monitored, but the passenger to escape from the list usually uses the riding service of the network booking platform only once, and discards the account number after the passenger finishes using the passenger, and the passenger can successfully register the passenger only through a mobile phone number when registering the network booking platform, but cannot acquire personal information of the passenger, so that the passenger's behavior of escaping from the list is difficult to effectively monitor.
In the related art, Uber corporation provides a hexagonal hierarchical grid system H3, H3 is a grid-based spatial index, which uses hexagons as basic units of grid index, spreads the whole earth over the hexagonal grid, encodes the longitude and latitude according to different hexagonal areas, changes the encoding into the encoding with different digits according to different grid precision, has the same encoding in the same area, and performs statistical analysis on the data by collecting the encoding containing the longitude and latitude of the grid where the unpaid order is located, so as to identify the time-space point of the unpaid order. However, the width of each hexagonal grid is preset, when the grid size needs to be adjusted, the whole grid index system needs to be reestablished, and when the width of the hexagonal grid is too large, the accuracy is low, and it is difficult to accurately identify the longitude and latitude characteristics of unpaid orders.
Example 1
As shown in fig. 1, in a first aspect, the present invention provides a method for identifying an abnormal space-time point, including the following steps:
receiving a monitoring request and selecting a monitored space-time region;
generating a spatiotemporal grid corresponding to the spatiotemporal region;
traversing grid nodes of the space-time grid in a preset space-time kernel density estimation model by a grid search method, and outputting an estimation value; the preset space-time kernel density estimation model comprises a paid order kernel density estimation model and an unpaid order kernel density estimation model; the grid nodes comprise paid order spatiotemporal data and unpaid spatiotemporal data; the paid order spatiotemporal data and unpaid spatiotemporal data comprise longitude and latitude data and time data;
and comparing the estimated value with a preset abnormal space-time threshold value, and identifying an abnormal space-time point.
In practice, it has been found that most passengers who escape are scofflators who frequently generate escape behavior through such a vulnerability of the payment mode, and the escape locations of these passengers usually occur within a specific time period and a specific area, and are aggregated to some extent in time and space, the platform can effectively identify the passengers who escape by identifying these areas of unpaid orders and unpaid time periods in an aggregated form, and marking these areas as abnormal space-time points, and by analyzing these abnormal space-time points.
In the embodiment, the paid order density estimation model outputs an estimated value of a paid order, reflects the probability of occurrence of the paid order of the grid node, the unpaid order density estimation model outputs an estimated value of an unpaid order, reflects the probability of occurrence of the unpaid order of the grid node, establishes constraints adjacent in time dimension by introducing time data, further establishes a space-time core density estimation model, calculates space-time distribution densities of behaviors of the unpaid order and the paid order, further analyzes the occurrence frequency of the unpaid order and the occurrence frequency of the paid order, effectively identifies abnormal space-time points in an aggregation state in a specific time period and a specific time region, makes up for the defects of a space and time splitting analysis method, and effectively identifies the order escape behavior of passengers.
Step 1: and receiving a monitoring request to select a monitored space-time region.
Specifically, before selecting a space-time region, a space region presenting an aggregation state is searched by establishing a space kernel density estimation model for analysis, an aggregation time period is searched by establishing a data clock, a monitoring request is received, a time region with the aggregation space region and the aggregation time period is selected as a monitoring region, the specific latitude and longitude region of the regions is identified, more unpaid orders are obtained in the specific time period, and order escaping behaviors are effectively identified.
Step 2: and generating a space-time grid corresponding to the space-time region.
Specifically, squares are used as basic units of grid index, the grids of squares are fully paved in the whole space-time area, longitude and latitude are coded according to different square areas, codes with different digits are changed into codes with different digits according to different grid precision, the codes in the same area are the same, codes containing the longitude and latitude of grids where unpaid orders and paid orders are located are collected, if the first five codes of two coordinates are the same, the two coordinates are located in the same space-time grid in five-level precision, if the first five codes of the two coordinates are the same, the sixth codes are different, the two coordinates are located in the same space-time grid in five-level precision, and the coordinates are located in different space-time grids in six-level precision.
In another embodiment, the entire spatio-temporal region is tiled over the mesh of regular triangles or hexagons, using regular triangles or hexagons as the basic unit of the mesh index. Because the area perimeter of the hexagon is lower, the sample deviation caused by the boundary effect of the grid shape can be reduced, the distances of the centroids between the hexagon grid and the grids around the hexagon grid are equal, no gap exists after the hexagon grid is paved in the whole space-time area, and when the space-time grids in the adjacent fields are searched, all the adjacent space-time grids can be found more conveniently and rapidly.
And step 3: traversing grid nodes of the space-time grid in a preset space-time kernel density estimation model by a grid search method, and outputting an estimation value; the preset space-time kernel density estimation model comprises a paid order kernel density estimation model and an unpaid order kernel density estimation model; the grid nodes comprise paid order spatiotemporal data and unpaid spatiotemporal data; the paid order spatiotemporal data and unpaid spatiotemporal data include latitude and longitude data and time data.
Specifically, the grid search method is to train unpaid data and paid order data in each grid node through a space-time core density estimation model according to a coding sequence, wherein the unpaid order space-time data is trained through the unpaid order core density estimation model to obtain a core density estimation value KDE of an unpaid order of the grid nodeupThe paid order space-time data is trained through a paid order kernel density estimation model to obtain a kernel density estimation value KDE of the paid order of the grid nodepThe undetected space-time area can be avoided by the grid search method, and the omission is hiddenThe grid nodes avoid missing and identifying abnormal space-time points.
Specifically, the preset spatiotemporal kernel density estimation model is obtained by the following method, including:
step 301: acquiring paid order space-time data or unpaid space-time data of a passenger terminal, and establishing a space-time data set;
step 302: and performing core density estimation on each paid order space-time data or unpaid space-time data in a space-time data set through a preset distribution function, a space bandwidth and a time bandwidth to generate a core density estimation function corresponding to the space-time data set.
Wherein the preset distribution function is a gaussian kernel function, and the expression of the kernel density estimation function is as follows:
in the formula, KDE (x, y, t) is a kernel density estimation value, n is the number of paid order space-time data or unpaid space-time data in the space-time data set, h1Is the spatial bandwidth, h1∈(0.05，2)，h2Is the time bandwidth, h2∈(0.05，2)，(xi,yi) Latitude data, t, in the space-time data for the ith paid order or unpaid space-time dataiTime data in the ith paid order spatiotemporal data or unpaid spatiotemporal data.
Specifically, the discretely distributed longitude and latitude data are difficult to capture relatively fine continuous changes, the preset distribution function adopts a Gaussian kernel function, the Gaussian kernel function can cross the similarity between different longitude and latitude data, and in a certain area, the longitude and latitude data are better gathered together, so that the data of the starting point position become linearly separable, and the accuracy of the kernel density estimation function is improved. Meanwhile, on the basis of longitude and latitude data, time data is introduced, constraints adjacent in time dimension are established, a space-time kernel density estimation model is further established, space-time distribution density of behaviors of unpaid orders and paid orders is calculated, the occurrence frequency of the unpaid orders and the occurrence frequency of the paid orders are further analyzed, abnormal space-time points in an aggregation state in a specific time period and a specific time region are effectively identified, the defects of a space and time splitting analysis method are overcome, and the order escaping behaviors of passengers are effectively identified.
The space bandwidth and the time bandwidth can be adjusted in a self-adaptive mode, when the space bandwidth and the time bandwidth are large, a curve corresponding to the kernel function is smooth, the included details are few, and the error is large; when the space bandwidth and the time bandwidth are small, the curve corresponding to the kernel function is steep in inflection and contains more noise, which is not beneficial to analyzing and finding out abnormal space-time points. The space bandwidth can be adjusted according to the number of unpaid orders and the number of paid orders in the space-time grid, and whether the space-time node is an abnormal space-time point or not is conveniently and clearly identified.
And 4, step 4: and comparing the estimated value with a preset abnormal space-time threshold value, and identifying an abnormal space-time point.
Specifically, the estimation value of the paid order core density estimation model and the estimation value of the unpaid order core density estimation model are compared through a preset formula, and a real numerical value with a monotonous meaning is output; and if the real numerical value is larger than the preset abnormal space-time threshold value, the grid node is an abnormal space-time point.
Wherein, the expression of the preset formula is as follows:
wherein K (x, y, t) is a real number, KDEupEvaluation of a model for density estimation of unpaid orders, KDEpEvaluation of a model for the estimation of the nuclear density of paid orders, KDEupIs KDEup(x,y,t)，KDEpIs KDEp(x,y,t)。
For example, K (x, y, t) indicates the quantity difference between the unpaid order and the paid order of the grid node, the larger the value of K (x, y, t) is, the more the unpaid order of the grid node is, the grid node is very likely to be an abnormal time slot, the important monitoring and precaution are required for the order of the place in the time period, and the longitude and latitude are the place.
Preferably, after generating the spatio-temporal mesh corresponding to the spatio-temporal region, the method further includes:
and 5: receiving a resolution selection command, and re-dividing the spatiotemporal mesh of the spatiotemporal region according to the resolution selection command.
When the precision of the primarily divided space-time grids is low, namely the number of the space-time grids in the space-time region is small, the divided area of each space-time grid is large, and the abnormal space-time points of specific longitude and latitude and time are difficult to accurately search; when the precision of the primarily divided space-time grids is higher, namely the number of the space-time grids in the space-time region is larger, the divided area of each space-time grid is smaller, more data are analyzed, and the maintenance time is longer. At the moment, the number of the proper space-time grids can be selected by resetting the resolution ratio, so that the abnormal space-time points in the space-time grids can be conveniently, quickly and accurately searched.
In summary, when the method is executed, on one hand, the method establishes constraints adjacent to time dimensions by introducing time data on the basis of longitude and latitude data, further establishes a space-time kernel density estimation model, calculates the space-time distribution density of behaviors of unpaid orders and paid orders, further analyzes the occurrence frequency of the unpaid orders and the occurrence frequency of the paid orders, effectively identifies abnormal space-time points in an aggregation state in a specific time period and a specific time region, overcomes the defects of the space and time fracture analysis method, and effectively identifies the order escape behaviors of passengers. On the other hand, by resetting the resolution ratio, the number of the proper space-time grids is selected, so that the abnormal space-time points in the space-time grids can be conveniently, quickly and accurately searched. In addition, the method can avoid missing the grid nodes which are difficult to perceive and hidden in the space-time region by the grid search method, and avoid missing and identifying abnormal space-time points
The other steps of the method for identifying an abnormal space-time point according to the invention refer to the prior art.
Example 2
In a second aspect, as shown in fig. 2, the present invention discloses an apparatus for identifying an abnormal spatiotemporal point, which includes a spatiotemporal region selection module M1, a spatiotemporal mesh generation module M2, a traversal module M3 and an identification module M4.
The spatiotemporal region selection module M1 is used for receiving a monitoring request to select a monitored spatiotemporal region;
the space-time grid generating module M2 is used for generating a space-time grid corresponding to the space-time region;
the traversal module M3 is used for traversing the grid nodes of the space-time grid in a preset space-time kernel density estimation model by a grid search method and outputting an estimation value; the preset space-time kernel density estimation model comprises a paid order kernel density estimation model and an unpaid order kernel density estimation model; the grid nodes comprise paid order spatiotemporal data and unpaid spatiotemporal data; the paid order spatiotemporal data and unpaid spatiotemporal data comprise longitude and latitude data and time data;
the identification module M4 is configured to compare the estimated value with a preset abnormal spatiotemporal threshold, and identify an abnormal spatiotemporal point.
For the second aspect, the method also includes the 1 st preferred implementation, and further includes a repartitioning spatiotemporal grid module M5.
The repartitioning spatiotemporal grid module M5 is configured to receive a resolution selection command and to repartition the spatiotemporal grid of spatiotemporal regions according to the resolution selection command.
In summary, when the apparatus of this embodiment is operated, all steps of the method for identifying an abnormal time-space point described in embodiment 1 can be implemented, so as to achieve the technical effect achieved in embodiment 1.
Other structures of the device for identifying an abnormal space-time point described in the present embodiment are referred to in the prior art.
Example 3
The invention also discloses an electronic device, at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor, and when the at least one processor executes the instructions, the following steps are specifically realized:
receiving a monitoring request and selecting a monitored space-time region;
generating a spatiotemporal grid corresponding to the spatiotemporal region;
traversing grid nodes of the space-time grid in a preset space-time kernel density estimation model by a grid search method, and outputting an estimation value; the preset space-time kernel density estimation model comprises a paid order kernel density estimation model and an unpaid order kernel density estimation model; the grid nodes comprise paid order spatiotemporal data and unpaid spatiotemporal data; the paid order spatiotemporal data and unpaid spatiotemporal data comprise longitude and latitude data and time data;
and comparing the estimated value with a preset abnormal space-time threshold value, and identifying an abnormal space-time point.
Example 4
The invention also discloses a storage medium, which stores a computer program, and when the computer program is executed by a processor, the following steps are concretely realized:
receiving a monitoring request and selecting a monitored space-time region;
generating a spatiotemporal grid corresponding to the spatiotemporal region;
traversing grid nodes of the space-time grid in a preset space-time kernel density estimation model by a grid search method, and outputting an estimation value; the preset space-time kernel density estimation model comprises a paid order kernel density estimation model and an unpaid order kernel density estimation model; the grid nodes comprise paid order spatiotemporal data and unpaid spatiotemporal data; the paid order spatiotemporal data and unpaid spatiotemporal data comprise longitude and latitude data and time data;
and comparing the estimated value with a preset abnormal space-time threshold value, and identifying an abnormal space-time point.
The present disclosure may be methods, apparatus, systems, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for carrying out various aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + +, Java, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A method for identifying an abnormal space-time point is characterized by comprising the following steps:
receiving a monitoring request and selecting a monitored space-time region;
generating a spatiotemporal grid corresponding to the spatiotemporal region;
traversing grid nodes of the space-time grid in a preset space-time kernel density estimation model by a grid search method, and outputting an estimation value; the preset space-time kernel density estimation model comprises a paid order kernel density estimation model and an unpaid order kernel density estimation model; the grid nodes comprise paid order spatiotemporal data and unpaid spatiotemporal data; the paid order spatiotemporal data and unpaid spatiotemporal data comprise longitude and latitude data and time data;
and comparing the estimated value with a preset abnormal space-time threshold value, and identifying an abnormal space-time point.
2. The method for identifying an abnormal spatiotemporal point according to claim 1, wherein after the generating the spatiotemporal mesh corresponding to the spatiotemporal region, the method further comprises:
receiving a resolution selection command, and re-dividing the spatiotemporal mesh of the spatiotemporal region according to the resolution selection command.
3. The method for identifying an abnormal spatiotemporal point as claimed in claim 1, wherein the comparing the estimated value with a preset abnormal spatiotemporal threshold value identifies an abnormal spatiotemporal point, specifically:
comparing the estimation value of the paid order core density estimation model with the estimation value of the unpaid order core density estimation model through a preset formula, and outputting a real numerical value with a monotonous meaning; and if the real numerical value is larger than the preset abnormal space-time threshold value, the grid node is an abnormal space-time point.
4. The method according to claim 3, wherein the expression of the predetermined formula is:
wherein K (x, y, t) is a real number, KDEupEvaluation of a model for density estimation of unpaid orders, KDEpEvaluation of a model for the estimation of the nuclear density of paid orders, KDEupIs KDEup(x,y,t)，KDEpIs KDEp(x,y,t)。
5. The method for identifying abnormal spatiotemporal points according to claim 1, wherein the preset spatiotemporal kernel density estimation model is obtained by a method comprising:
acquiring paid order space-time data or unpaid space-time data of a passenger terminal, and establishing a space-time data set;
and performing core density estimation on each paid order space-time data or unpaid space-time data in a space-time data set through a preset distribution function, a space bandwidth and a time bandwidth to generate a core density estimation function corresponding to the space-time data set.
6. The method for identifying an abnormal account according to claim 5, wherein the preset distribution function is a Gaussian kernel function, and the expression of the kernel density estimation function is as follows:
in the formula, KDE (x, y, t) is a kernel density estimation value, n is the number of paid order space-time data or unpaid space-time data in the space-time data set, h1Is the spatial bandwidth, h2Is the time bandwidth, (x)i,yi) Latitude data, t, in the space-time data for the ith paid order or unpaid space-time dataiTime data in the ith paid order spatiotemporal data or unpaid spatiotemporal data.
7. An apparatus for identifying an abnormal space-time point, comprising:
the space-time region selection module is used for receiving a monitoring request to select a monitored space-time region;
the space-time grid generating module is used for generating a space-time grid corresponding to the space-time region;
the traversal module is used for traversing grid nodes of the space-time grid in a preset space-time kernel density estimation model through a grid search method and outputting an estimation value; the preset space-time kernel density estimation model comprises a paid order kernel density estimation model and an unpaid order kernel density estimation model; the grid nodes comprise paid order spatiotemporal data and unpaid spatiotemporal data; the paid order spatiotemporal data and unpaid spatiotemporal data comprise longitude and latitude data and time data;
and the identification module is used for comparing the estimated value with a preset abnormal space-time threshold value and identifying an abnormal space-time point.
8. The apparatus for identifying an abnormal space-time point as claimed in claim 7, further comprising:
and the re-division space-time grid module is used for receiving a resolution selection command and re-dividing the space-time grid of the space-time region according to the resolution selection command.
9. An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor, wherein: the at least one processor, when executing instructions, is configured to perform a method for identifying an abnormal spatiotemporal point as recited in any of claims 1 to 6.
10. A storage medium storing a computer program, characterized in that: the computer program, when being executed by a processor, particularly performs a method of identifying an abnormal spatiotemporal point as set forth in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111547351.0A CN114218505A (en) | 2021-12-16 | 2021-12-16 | Abnormal space-time point identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111547351.0A CN114218505A (en) | 2021-12-16 | 2021-12-16 | Abnormal space-time point identification method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114218505A true CN114218505A (en) | 2022-03-22 |
Family
ID=80703237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111547351.0A Pending CN114218505A (en) | 2021-12-16 | 2021-12-16 | Abnormal space-time point identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114218505A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114547228A (en) * | 2022-04-22 | 2022-05-27 | 阿里云计算有限公司 | Track generation method, device, equipment and storage medium |
| CN116187936A (en) * | 2023-02-03 | 2023-05-30 | 上海麦德通软件技术有限公司 | Work order intelligent generation system based on cloud platform |
-
2021
- 2021-12-16 CN CN202111547351.0A patent/CN114218505A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114547228A (en) * | 2022-04-22 | 2022-05-27 | 阿里云计算有限公司 | Track generation method, device, equipment and storage medium |
| CN114547228B (en) * | 2022-04-22 | 2022-07-19 | 阿里云计算有限公司 | Track generation method, device, equipment and storage medium |
| CN116187936A (en) * | 2023-02-03 | 2023-05-30 | 上海麦德通软件技术有限公司 | Work order intelligent generation system based on cloud platform |
| CN116187936B (en) * | 2023-02-03 | 2023-08-29 | 上海麦德通软件技术有限公司 | Work order intelligent generation system based on cloud platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10565442B2 (en) | Picture recognition method and apparatus, computer device and computer- readable medium | |
| CN111178523B (en) | Behavior detection method and device, electronic equipment and storage medium | |
| CN111046027B (en) | Missing value filling method and device for time series data | |
| CN113205037B (en) | Event detection method, event detection device, electronic equipment and readable storage medium | |
| CN112200081A (en) | Abnormal behavior identification method and device, electronic equipment and storage medium | |
| US11144582B2 (en) | Method and system for parsing and aggregating unstructured data objects | |
| CN114218505A (en) | Abnormal space-time point identification method and device, electronic equipment and storage medium | |
| US11271957B2 (en) | Contextual anomaly detection across assets | |
| CN110070076B (en) | Method and device for selecting training samples | |
| CN110162518B (en) | Data grouping method, device, electronic equipment and storage medium | |
| CN110472599A (en) | Number of objects determines method, apparatus, storage medium and electronic equipment | |
| US11379741B2 (en) | Method, apparatus and storage medium for stay point recognition and prediction model training | |
| KR102359090B1 (en) | Method and System for Real-time Abnormal Insider Event Detection on Enterprise Resource Planning System | |
| CN112200173B (en) | Multi-network model training method, image labeling method and face image recognition method | |
| US20210049414A1 (en) | Deep graph de-noise by differentiable ranking | |
| CN110717597A (en) | Method and device for acquiring time sequence characteristics by using machine learning model | |
| CN110766184A (en) | Order quantity prediction method and device | |
| CN111427915B (en) | Information processing method and device, storage medium and electronic equipment | |
| CN113722588A (en) | Resource recommendation method and device and electronic equipment | |
| CN113989720A (en) | Target detection method, training method, device, electronic equipment and storage medium | |
| US20220414394A1 (en) | Method of determining state of target object, electronic device, and storage medium | |
| CN113920381B (en) | Repeated derivative index identification method, electronic device and readable storage medium | |
| CN110532304B (en) | Data processing method and device, computer readable storage medium and electronic device | |
| CN115482353A (en) | Training method, reconstruction method, device, equipment and medium for reconstructing network | |
| CN114461499A (en) | Abnormal information detection model construction method and gray scale environment abnormal detection method |
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 |