WO2019062824A1 - 点击热力图异常检测方法及装置 - Google Patents

点击热力图异常检测方法及装置 Download PDF

Info

Publication number
WO2019062824A1
WO2019062824A1 PCT/CN2018/108160 CN2018108160W WO2019062824A1 WO 2019062824 A1 WO2019062824 A1 WO 2019062824A1 CN 2018108160 W CN2018108160 W CN 2018108160W WO 2019062824 A1 WO2019062824 A1 WO 2019062824A1
Authority
WO
WIPO (PCT)
Prior art keywords
click
area
detected
heat map
source data
Prior art date
Application number
PCT/CN2018/108160
Other languages
English (en)
French (fr)
Inventor
刘振华
Original Assignee
北京国双科技有限公司
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 北京国双科技有限公司 filed Critical 北京国双科技有限公司
Priority to US16/642,276 priority Critical patent/US20210079866A1/en
Publication of WO2019062824A1 publication Critical patent/WO2019062824A1/zh

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
    • F02D—CONTROLLING COMBUSTION ENGINES
    • F02D41/00—Electrical control of supply of combustible mixture or its constituents
    • F02D41/22—Safety or indicating devices for abnormal conditions
    • F02D41/222—Safety or indicating devices for abnormal conditions relating to the failure of sensors or parameter detection devices
    • 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
    • G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
    • F02D—CONTROLLING COMBUSTION ENGINES
    • F02D41/00—Electrical control of supply of combustible mixture or its constituents
    • F02D41/22—Safety or indicating devices for abnormal conditions
    • F02D41/221—Safety or indicating devices for abnormal conditions relating to the failure of actuators or electrically driven elements
    • 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
    • G06F16/951—Indexing; Web crawling techniques
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0248—Avoiding fraud
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
    • G09B29/003—Maps
    • G09B29/006—Representation of non-cartographic information on maps, e.g. population distribution, wind direction, radiation levels, air and sea routes
    • G09B29/007—Representation of non-cartographic information on maps, e.g. population distribution, wind direction, radiation levels, air and sea routes using computer methods

Definitions

  • the present application relates to the field of traffic cheating detection, and in particular to a method and device for detecting anomaly abnormality of a click.
  • the abnormal traffic can be identified by determining the abnormal click behavior according to the click heat map.
  • the prior art manually identifies the abnormal click behavior in the click heat map, and the accuracy and recognition efficiency are low.
  • the present application has been made in order to provide a click heat map abnormality detecting method and apparatus that overcomes the above problems or at least partially solves the above problems, and the solution is as follows:
  • a method for clicking the heat map anomaly detection including:
  • the determining the area to be detected in the first click heat map includes:
  • the method further includes determining an area of the first click heat map other than the area to be detected as a normal click area.
  • it also includes:
  • the first click heat map is a click heat map of the first page in a first time period
  • the second click The heat map is a click heat map of the first page in a second time period, the first time period and the second time period being different
  • the comparing the click source data of the to-be-detected area with the click source data of the normal click area to obtain the first comparison result including:
  • the comparison of the click source data is performed by calculating the correlation coefficient between the click source data of the to-be-detected area and the click source data of the normal click area, and the calculated correlation coefficient is used as the first comparison result.
  • the determining, according to the first comparison result, whether the to-be-detected area is an abnormal click area includes:
  • it also includes:
  • a preset identifier is added to determine the area to be detected that is an abnormal click area.
  • a click heat map abnormality detecting device comprises: a to-be-detected area determining unit, a first comparing unit and an abnormality determining unit,
  • the to-be-detected area determining unit is configured to obtain a first click heat map, and determine an area to be detected in the first click heat map;
  • the first comparison unit is configured to compare the click source data of the to-be-detected area with the click source data of the normal click area to obtain a first comparison result
  • the abnormality determining unit is configured to determine, according to the first comparison result, whether the to-be-detected area is an abnormal click area.
  • the to-be-detected area determining unit includes: a dividing subunit and a dividing subunit,
  • the dividing subunit is configured to divide the first click heat map into a plurality of sub-areas of equal area, wherein each sub-area has the same shape;
  • the segmentation subunit is configured to segment the first click heat map divided into a plurality of sub-regions by using an image segmentation algorithm to obtain a to-be-detected region composed of a plurality of complete sub-regions, wherein the to-be-detected region The amount of clicks in each sub-area in the middle is greater than the first preset threshold;
  • the device further includes: a normal area determining unit, configured to determine an area of the first click heat map other than the area to be detected as a normal click area.
  • a storage medium comprising a stored program, wherein the device in which the storage medium is located is controlled to perform the click heat map abnormality detecting method described above when the program is running.
  • a processor for running a program wherein the program is executed to perform the click heat map anomaly detection method described above.
  • the method and device for detecting abnormality of the click heat map provided by the present application can determine the area to be detected in the first click heat map, and the click source data of the area to be detected and the click source data of the normal click area. Performing an alignment, obtaining a first comparison result, and determining whether the area to be detected is an abnormal click area according to the first comparison result.
  • the inventor found through research that the click source data of the abnormal click area is quite different from the click source data of the normal click area. Therefore, it can be determined according to the comparison result of the two whether the area to be detected is an abnormal click area, thereby realizing abnormal clicks. Automatic identification of areas and improved accuracy and recognition efficiency.
  • FIG. 1 is a flowchart of a method for detecting an abnormality of a click heat map according to an embodiment of the present application
  • FIG. 2 is a schematic diagram of click data provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of a click heat map provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram of an area to be detected provided by an embodiment of the present application.
  • FIG. 5 is a schematic diagram of a normal click area provided by an embodiment of the present application.
  • FIG. 6 is a schematic diagram showing correlation coefficients of click source ratios of each to-be-detected area and a normal click area provided by an embodiment of the present application;
  • FIG. 7 is a schematic diagram showing the effect of the click heat map provided on the interface provided by the embodiment of the present application.
  • FIG. 8 is a flowchart of another method for detecting an abnormality of a click heat map provided by an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a click heat map abnormality detecting apparatus provided by an embodiment of the present application.
  • a method for detecting an abnormality of a click heat map provided by an embodiment of the present application may include:
  • the application can obtain the first click heat map directly from other electronic devices, and can also generate the first click heat map according to the click data obtained from other electronic devices.
  • the application may first normalize the click data, then perform transposition, data interval and filtering processing, and then generate a click heat map according to the filtered click data.
  • the area to be detected in the first click heat map may be an area with a higher click amount in the first click heat map.
  • the process of determining the area to be detected in the first click heat map may include:
  • the first click heat map divided into a plurality of sub-areas by using an image segmentation algorithm to obtain a to-be-detected area composed of a plurality of complete sub-areas, wherein clicks in each sub-area in the to-be-detected area The amount is greater than the first preset threshold.
  • the method shown in FIG. 1 may further include: determining an area of the first click heat map other than the area to be detected as a normal click area.
  • each sub-area may be composed of one or more pixels.
  • the image segmentation algorithm used in the present application may be a threshold-based segmentation algorithm, a region-based segmentation algorithm, or an edge-based segmentation algorithm.
  • the following uses the threshold-based segmentation algorithm as an example to illustrate the image segmentation process:
  • the first preset threshold is an average value of the click amounts of each sub-area
  • Determining whether there is an unfused sub-region in each sub-region with a click amount higher than the first preset threshold, and if yes, selecting a sub-region from the unfused sub-region as the current region, returning to perform the determination may be current
  • the area is merged into a sub-area in which the other hits of the area are higher than the first preset threshold, and the determined sub-area is merged with the current area.
  • the inventor of the present application has found in the process of implementing the present application that the click data generated by the cheating traffic is generally concentrated in certain areas, and the click volume of these areas is relatively high, so the application can determine the area with a higher click volume. For the area to be tested. Correspondingly, the area with a lower click volume is generally the normal click area.
  • the inventor of the present application found that when the click data is generated by the real user, the source distribution of the click data in the two different regions is similar. For example, a webpage includes a first area and a second area, and the click data of the webpage has three sources of B, C, and D, and the proportion of the click data of the three sources in the total click data of the first area is respectively : 10%, 20% and 70%. The click data of these three sources accounted for 8%, 23%, and 69% of the total click data in the second region.
  • step S200 may include:
  • the comparison of the click source data is performed by calculating the correlation coefficient between the click source data of the to-be-detected area and the click source data of the normal click area, and the calculated correlation coefficient is used as the first comparison result.
  • step S200 the comparison of the click source data may be performed by other methods, such as calculating the covariance, etc., which is not limited herein.
  • S300 Determine, according to the first comparison result, whether the area to be detected is an abnormal click area.
  • the step S300 may include: determining whether a correlation coefficient as a result of the first comparison is smaller than a second preset threshold, and if yes, determining that the to-be-detected area is an abnormal click area.
  • the application may further determine that the to-be-detected area is a normal click area.
  • the method shown in FIG. 1 may further include:
  • a preset identifier is added to determine the area to be detected that is an abnormal click area.
  • the advertisement purchaser can conveniently find the abnormal click area determined by the application.
  • the application may further cover the first click heat map in which the abnormal click area with the preset identifier is added on the interface map corresponding to the first click heat map.
  • the interface diagram may be a web interface diagram, an application interface diagram, or the like. By overlaying the interface map, it is further convenient for the user to find the location in the interface map corresponding to the abnormal click area, thereby analyzing and using the same.
  • the click data obtained after the normalization process is as shown in FIG. 2, and after the click data shown in FIG. 2 is transposed, data intervalized, and filtered, the click data after the filtering process can be generated as shown in the figure. 3 click on the heat map.
  • the nine to-be-detected areas 001 to 009 shown in FIG. 4 and the normal click area shown in FIG. 5 are obtained by the image segmentation algorithm.
  • the correlation coefficient of each of the to-be-detected area and the normal click area of the click source is calculated, and the correlation coefficient as shown in FIG. 6 can be obtained.
  • the correlation coefficient of the area to be detected 3, the area to be detected 4, and the area to be detected 5 is very low, and it can be determined that the three areas to be detected are abnormal click areas.
  • the correlation coefficients of the other six areas to be detected are very good, and it can be determined that the six areas to be detected are not abnormal click areas.
  • the application circled the abnormal click area (the area to be detected 3, the area to be detected 4 and the area to be detected 5) for identification, and covers the click heat map to the corresponding interface (this The application has blurred the interface).
  • the present application may compare the to-be-detected area of the abnormal click area with the click source data of the other click heat map determined in step S300.
  • the click heat map abnormality detecting method provided by the embodiment of the present application can determine the to-be-detected area in the first click heat map, compare the click source data of the to-be-detected area with the click source data of the normal click area, and obtain the first A comparison result determines whether the area to be detected is an abnormal click area according to the first comparison result.
  • the inventor found through research that the click source data of the abnormal click area is quite different from the click source data of the normal click area. Therefore, it can be determined according to the comparison result of the two whether the area to be detected is an abnormal click area, thereby realizing abnormal clicks. Automatic identification of areas and improved accuracy and recognition efficiency.
  • another method for detecting the abnormality of the click heat map provided by the embodiment of the present application may further include:
  • S400 Obtain a second click heat map to determine an area to be detected in the second click heat map, where the first click heat map is a click heat map of the first page in a first time period;
  • the two-click heat map is a click heat map of the first page in a second time period, the first time period and the second time period being different;
  • the source of clicks may not change in different time periods (for example, two adjacent days).
  • the first comparison result in the method shown in Figure 1 is used in the previous time period. It is determined that the click source data of the area to be detected that is not the abnormal click area can be used to compare with the click source data of the area to be detected in the click heat map in the subsequent time period.
  • S600 Determine, according to the second comparison result, whether the area to be detected in the second click heat map is an abnormal click area.
  • Steps S400 to S600 in the method shown in FIG. 8 may use the to-be-detected area that is not the abnormal click area and the click heat in the latter period determined by the first comparison result in the method shown in FIG. 1 in the previous period.
  • the comparison of the click source data in the area to be detected in the figure simplifies the process of determining the abnormal click area.
  • the embodiment of the present application further provides a click heat map abnormality detecting device.
  • a click heat map abnormality detecting apparatus may include: a to-be-detected area determining unit 100, a first comparing unit 200, and an abnormality determining unit 300.
  • the to-be-detected area determining unit 100 is configured to obtain a first click heat map, and determine an area to be detected in the first click heat map;
  • the application can obtain the first click heat map directly from other electronic devices, and can also generate the first click heat map according to the click data obtained from other electronic devices.
  • the application may first normalize the click data, then perform transposition, data interval and filtering processing, and then generate a click heat map according to the filtered click data.
  • the to-be-detected area determining unit 100 may include: a dividing subunit and a dividing subunit,
  • the dividing subunit is configured to divide the first click heat map into a plurality of sub-areas of equal area, wherein each sub-area has the same shape;
  • the segmentation subunit is configured to segment the first click heat map divided into a plurality of sub-regions by using an image segmentation algorithm to obtain a to-be-detected region composed of a plurality of complete sub-regions, wherein the to-be-detected region The amount of clicks in each sub-area in the middle is greater than the first preset threshold;
  • the apparatus shown in FIG. 9 may further include: a normal area determining unit configured to determine an area of the first click heat map other than the area to be detected as a normal click area.
  • the area to be detected in the first click heat map may be an area with a higher click amount in the first click heat map.
  • the inventor of the present application has found in the process of implementing the present application that the click data generated by the cheating traffic is generally concentrated in certain areas, and the click volume of these areas is relatively high, so the application can determine the area with a higher click volume. For the area to be tested. Correspondingly, the area with a lower click volume is generally the normal click area.
  • the inventor of the present application found that when the click data is generated by the real user, the source distribution of the click data in the two different regions is similar. For example, a webpage includes a first area and a second area, and the click data of the webpage has three sources of B, C, and D, and the proportion of the click data of the three sources in the total click data of the first area is respectively : 10%, 20% and 70%. The click data of these three sources accounted for 8%, 23%, and 69% of the total click data in the second region.
  • the first comparison unit 200 is configured to compare the click source data of the to-be-detected area with the click source data of the normal click area to obtain a first comparison result
  • the first comparison unit 200 may be specifically configured to compare the click source data by calculating a correlation coefficient between the click source data of the to-be-detected area and the click source data of the normal click area, and calculate the correlation.
  • the coefficient is used as the first alignment result.
  • the abnormality determining unit 300 is configured to determine, according to the first comparison result, whether the to-be-detected area is an abnormal click area.
  • the abnormality determining unit 300 may be specifically configured to determine whether a correlation coefficient that is a result of the first comparison is less than a second preset threshold, and if yes, determine that the to-be-detected area is an abnormal click area.
  • the abnormality determining unit 300 may further determine that the to-be-detected area is a normal click area.
  • the apparatus shown in FIG. 9 may further include: a heat map obtaining unit, a second comparing unit, and an abnormal area determining unit,
  • the heat map obtaining unit is configured to obtain a second click heat map to determine an area to be detected in the second click heat map, wherein the first click heat map is the first page in the first time period Clicking on the heat map; the second click heat map is a click heat map of the first page in a second time period, the first time period and the second time period being different;
  • the source of the clicks may not change in different time periods (for example, two adjacent days).
  • the first comparison result determined by the first comparison result is not the abnormal click area.
  • the click source data of the area to be detected can be used to compare with the click source data of the area to be detected in the click heat map in the latter period.
  • the second comparison unit is configured to perform click source data of the to-be-detected area in the second click heat map and click source data of the to-be-detected area that is determined not to be an abnormal click area in the first click heat map Compare, obtain a second comparison result;
  • the abnormal region determining unit is configured to determine, according to the second comparison result, whether the to-be-detected region in the second click heat map is an abnormal click region.
  • This embodiment may use the area to be detected that is not the abnormal click area determined by the first comparison result in the apparatus shown in FIG. 9 in the previous period, and the click area to be detected in the click heat map in the latter period of time.
  • the comparison of the source data simplifies the process of determining the abnormal click area.
  • the apparatus shown in FIG. 9 may further include: an identifier adding unit, configured to add a preset identifier to the to-be-detected area determined to be an abnormal click area.
  • the advertisement purchaser can conveniently find the abnormal click area determined by the application.
  • the application may further cover the first click heat map in which the abnormal click area with the preset identifier is added on the interface map corresponding to the first click heat map.
  • the interface diagram may be a web interface diagram, an application interface diagram, or the like. By overlaying the interface map, it is further convenient for the user to find the location in the interface map corresponding to the abnormal click area, thereby analyzing and using the same.
  • the click heat map abnormality detecting device provided by the embodiment of the present application can determine the to-be-detected area in the first click heat map, compare the click source data of the to-be-detected area with the click source data of the normal click area, and obtain the first A comparison result determines whether the area to be detected is an abnormal click area according to the first comparison result.
  • the inventor found through research that the click source data of the abnormal click area is quite different from the click source data of the normal click area. Therefore, it can be determined according to the comparison result of the two whether the area to be detected is an abnormal click area, thereby realizing abnormal clicks. Automatic identification of areas and improved accuracy and recognition efficiency.
  • the click heat map abnormality detecting device includes a processor and a memory, and the to-be-detected region determining unit, the first comparing unit, and the abnormality determining unit are stored in a memory as a program unit, and the program stored in the memory is executed by the processor. Unit to achieve the corresponding function.
  • the processor contains a kernel, and the kernel removes the corresponding program unit from the memory.
  • the kernel can be set to one or more, and the abnormal click area can be determined by adjusting the kernel parameters.
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory (flash RAM), the memory including at least one Memory chip.
  • RAM random access memory
  • ROM read only memory
  • flash RAM flash memory
  • the embodiment of the present application provides a storage medium on which a program is stored, and when the program is executed by the processor, the click heat map abnormality detecting method is implemented.
  • the embodiment of the present application provides a processor for running a program, wherein the click heat map abnormality detecting method is executed when the program runs.
  • An embodiment of the present application provides a device, including a processor, a memory, and a program stored on the memory and executable on the processor.
  • the processor implements the following steps when executing the program:
  • the determining the area to be detected in the first click heat map includes:
  • An area other than the area to be detected in the first click heat map is determined as a normal click area.
  • the processor can also implement the following steps when executing the program:
  • the first click heat map is a click heat map of the first page in a first time period
  • the second click The heat map is a click heat map of the first page in a second time period, the first time period and the second time period being different
  • the comparing the click source data of the to-be-detected area with the click source data of the normal click area to obtain the first comparison result including:
  • the comparison of the click source data is performed by calculating the correlation coefficient between the click source data of the to-be-detected area and the click source data of the normal click area, and the calculated correlation coefficient is used as the first comparison result.
  • the determining, according to the first comparison result, whether the to-be-detected area is an abnormal click area includes:
  • the processor can also implement the following steps when executing the program:
  • a preset identifier is added to determine the area to be detected that is an abnormal click area.
  • the devices in this document can be servers, PCs, PADs, mobile phones, and the like.
  • the present application also provides a computer program product, when executed on a data processing device, adapted to perform a process of initializing the method steps as follows:
  • the determining the area to be detected in the first click heat map includes:
  • the computer program product described above when executed on a data processing device, may also be adapted to perform a process of initializing the method steps as follows:
  • An area other than the area to be detected in the first click heat map is determined as a normal click area.
  • the computer program product when executed on the data processing device, may be further adapted to perform a process of initializing the following method steps:
  • the first click heat map is a click heat map of the first page in a first time period
  • the second click The heat map is a click heat map of the first page in a second time period, the first time period and the second time period being different
  • the comparing the click source data of the to-be-detected area with the click source data of the normal click area to obtain the first comparison result including:
  • the comparison of the click source data is performed by calculating the correlation coefficient between the click source data of the to-be-detected area and the click source data of the normal click area, and the calculated correlation coefficient is used as the first comparison result.
  • the determining, according to the first comparison result, whether the to-be-detected area is an abnormal click area includes:
  • the computer program product when executed on the data processing device, may be further adapted to perform a process of initializing the following method steps:
  • a preset identifier is added to determine the area to be detected that is an abnormal click area.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Databases & Information Systems (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Combustion & Propulsion (AREA)
  • Chemical & Material Sciences (AREA)
  • Mechanical Engineering (AREA)
  • Computer Hardware Design (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Ecology (AREA)
  • Mathematical Physics (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Debugging And Monitoring (AREA)

Abstract

本申请公开了一种点击热力图异常检测方法及装置，可以确定第一点击热力图中的待检测区域，将待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果，根据第一比对结果确定待检测区域是否为异常点击区域。发明人经过研究发现，异常点击区域的点击来源数据相对于正常点击区域的点击来源数据有较大差别，因此可以根据二者的比对结果确定待检测区域是否为异常点击区域，从而实现异常点击区域的自动识别，并提高了准确性和识别效率。

Description

点击热力图异常检测方法及装置
本申请要求于2017年09月29日提交中国专利局、申请号为201710904819.4、发明名称为“点击热力图异常检测方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及流量作弊检测领域，尤其涉及点击热力图异常检测方法及装置。
背景技术
随着互联网的发展，用户更多的通过电子设备浏览各种网站的网页或应用程序的界面。通过购买广告可以为广告购买方带来更多的互联网流量，从而使得更多的用户浏览和点击广告购买方网站的网页或应用程序的界面。但流量作弊行为长期损害着广告购买方的正当权益，例如一些刷流量的软件会自动且大量的访问广告购买方的网站并进行大量点击操作，这些点击操作没有为广告购买方带来收益，但广告购买方却需要为之付费。
由于点击热力图可以很好的体现网站的网页或应用程序的界面中的点击情况，因此可以根据点击热力图确定异常点击行为从而识别异常流量。现有技术通过人工对点击热力图中的异常点击行为进行识别，准确性和识别效率较低。
发明内容
鉴于上述问题，提出了本申请以便提供一种克服上述问题或者至少部分地解决上述问题的点击热力图异常检测方法及装置，方案如下：
一种点击热力图异常检测方法，包括：
获得第一点击热力图，确定所述第一点击热力图中的待检测区域；
将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果；
根据所述第一比对结果确定所述待检测区域是否为异常点击区域。
可选的，所述确定所述第一点击热力图中的待检测区域，包括：
将所述第一点击热力图划分为多个面积相等的子区域，其中，各子区域的形状相同；
使用图像分割算法对划分为多个子区域的所述第一点击热力图进行分割，获得由多个完整的子区域构成的待检测区域，其中，所述待检测区域中的各子区域内的点击量均大于第一预设阈值；
所述方法还包括：将所述第一点击热力图中除所述待检测区域外的区域确定为正常点击区域。
可选的，还包括：
获得第二点击热力图，确定所述第二点击热力图中的待检测区域，其中，所述第一点击热力图为第一页面在第一时间段内的点击热力图；所述第二点击热力图为所述第一页面在第二时间段内的点击热力图，所述第一时间段和所述第二时间段不同；
将所述第二点击热力图中的待检测区域的点击来源数据与所述第一点击热力图中确定为不是异常点击区域的待检测区域的点击来源数据进行比对，获得第二比对结果；
根据所述第二比对结果确定所述第二点击热力图中的待检测区域是否为异常点击区域。
可选的，所述将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果，包括：
通过计算所述待检测区域的点击来源数据与正常点击区域的点击来源数据的相关系数来进行点击来源数据的比对，将计算得到的相关系数作为第一比对结果。
可选的，所述根据所述第一比对结果确定所述待检测区域是否为异常点击区域，包括：
确定作为所述第一比对结果的相关系数是否小于第二预设阈值，如果是，则确定所述待检测区域为异常点击区域。
可选的，还包括：
为确定为异常点击区域的待检测区域添加预设标识。
一种点击热力图异常检测装置，包括：待检测区域确定单元、第一对比单元和异常确定单元，
所述待检测区域确定单元，用于获得第一点击热力图，确定所述第一点击热力图中的待检测区域；
所述第一对比单元，用于将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果；
所述异常确定单元，用于根据所述第一比对结果确定所述待检测区域是否为异常点击区域。
可选的，所述待检测区域确定单元，包括：划分子单元和分割子单元，
所述划分子单元，用于将所述第一点击热力图划分为多个面积相等的子区域，其中，各子区域的形状相同；
所述分割子单元，用于使用图像分割算法对划分为多个子区域的所述第一点击热力图进行分割，获得由多个完整的子区域构成的待检测区域，其中，所述待检测区域中的各子区域内的点击量均大于第一预设阈值；
所述装置还包括：正常区域确定单元，用于将所述第一点击热力图中除所述待检测区域外的区域确定为正常点击区域。
一种存储介质，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行上述的点击热力图异常检测方法。
一种处理器，所述处理器用于运行程序，其中，所述程序运行时执行上述的点击热力图异常检测方法。
借由上述技术方案，本申请提供的一种点击热力图异常检测方法及装置，可以确定第一点击热力图中的待检测区域，将待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果，根据第一比对结果确定待检测区域是否为异常点击区域。发明人经过研究发现，异常点击区域的点击来源数据相对于正常点击区域的点击来源数据有较大差别，因此可以根据二者的比对结果确定待检测区域是否为异常点击区域，从而实现异常点击区域的自动识别，并提高了准确性和识别效率。
上述说明仅是本申请技术方案的概述，为了能够更清楚了解本申请的技术 手段，而可依照说明书的内容予以实施，并且为了让本申请的上述和其它目的、特征和优点能够更明显易懂，以下特举本申请的具体实施方式。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据提供的附图获得其他的附图。
图1示出了本申请实施例提供的一种点击热力图异常检测方法的流程图；
图2示出了本申请实施例提供的点击数据示意图；
图3示出了本申请实施例提供的点击热力图示意图；
图4示出了本申请实施例提供的待检测区域示意图；
图5示出了本申请实施例提供正常点击区域示意图；
图6示出了本申请实施例提供的各待检测区域与正常点击区域的点击来源占比的相关系数示意图；
图7示出了本申请实施例提供的点击热力图覆盖到界面上的效果示意图；
图8示出了本申请实施例提供的另一种点击热力图异常检测方法的流程图；
图9示出了本申请实施例提供的一种点击热力图异常检测装置的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
如图1所示，本申请实施例提供的一种点击热力图异常检测方法，可以包括：
S100、获得第一点击热力图，确定所述第一点击热力图中的待检测区域；
其中，本申请可以直接从其他电子设备中获得第一点击热力图，也可以根 据从其他电子设备中获得的点击数据生成该第一点击热力图。
具体的，本申请在获得点击数据后可以首先对点击数据进行归一化处理，然后进行转置、数据区间化与滤波处理，然后根据滤波处理后的点击数据生成点击热力图即可。
其中，第一点击热力图中的待检测区域可以为该第一点击热力图中点击量较高的区域。
可选的，确定所述第一点击热力图中的待检测区域的过程可以包括：
将所述第一点击热力图划分为多个面积相等的子区域，其中，各子区域的形状相同；
使用图像分割算法对划分为多个子区域的所述第一点击热力图进行分割，获得由多个完整的子区域构成的待检测区域，其中，所述待检测区域中的各子区域内的点击量均大于第一预设阈值。
在此基础上，图1所示方法还可以包括：将所述第一点击热力图中除所述待检测区域外的区域确定为正常点击区域。
其中，每个子区域可以由一个或多个像素点构成。
其中，本申请使用的图像分割算法可以为基于阈值的分割算法、基于区域的分割算法或基于边缘的分割算法等。下面以基于阈值的分割算法为例对图像分割过程进行说明：
首先根据第一点击热力图中各子区域的点击量确定所述第一预设阈值(例如第一预设阈值为各子区域的点击量的平均值)；
然后遍历各子区域的点击量，获得点击量高于该第一预设阈值的各子区域；
从点击量高于该第一预设阈值的各子区域中选取一个子区域作为当前区域；
确定可与当前区域融合为一个区域的其他点击量高于第一预设阈值的子区域，将确定的子区域与当前区域融合；
确定点击量高于第一预设阈值的各子区域中是否存在未融合的子区域，如果是，则从未融合的子区域中选择一个子区域作为当前区域，返回执行所述确 定可与当前区域融合为一个区域的其他点击量高于第一预设阈值的子区域，将确定的子区域与当前区域融合的步骤。
本申请发明人在实现本申请的过程中研究发现：作弊流量产生的点击数据一般均集中在某些区域，并导致这些区域的点击量较高，因此本申请可以将点击量较高的区域确定为待检测区域。相应的，点击量较低的区域一般为正常点击区域。本申请发明人研究发现，当点击数据均由真实用户产生时，不同的两个区域内的点击数据的来源分布相似。例如：某网页中包括第一区域和第二区域，该网页的点击数据有B、C和D三个来源，这三个来源的点击数据在第一区域的全部点击数据中的占比分别为：10％、20％和70％。这三个来源的点击数据在第二区域的全部点击数据中的占比分别为：8％、23％和69％。
S200、将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果；
可选的，步骤S200可以包括：
通过计算所述待检测区域的点击来源数据与正常点击区域的点击来源数据的相关系数来进行点击来源数据的比对，将计算得到的相关系数作为第一比对结果。
步骤S200也可以通过其他方式，如计算协方差等来进行点击来源数据的比对，本申请在此不做限定。
S300、根据所述第一比对结果确定所述待检测区域是否为异常点击区域。
具体的，步骤S300可以包括：确定作为所述第一比对结果的相关系数是否小于第二预设阈值，如果是，则确定所述待检测区域为异常点击区域。
可选的，在作为所述第一比对结果的相关系数不小于第二预设阈值时，本申请还可以确定所述待检测区域为正常点击区域。
可选的，图1所示方法还可以包括：
为确定为异常点击区域的待检测区域添加预设标识。
通过该预设标识的添加就可以使得广告购买方方便的找到本申请确定的异常点击区域。
进一步，本申请还可以将添加了预设标识的异常点击区域所在的第一点击 热力图覆盖该第一点击热力图对应的界面图上。其中，该界面图可以为网页界面图、应用程序界面图等。通过覆盖到界面图上，可以进一步方便用户找到异常点击区域对应的界面图中的位置，从而对其进行分析和使用。
为方便理解，下面举例说明：
设获得的进行归一化处理后的点击数据如图2所示，则对图2所示的点击数据进行转置、数据区间化与滤波处理后，可以根据滤波处理后的点击数据生成如图3所示的点击热力图。通过图像分割算法获得图4所示的九个待检测区域001至009和图5所示的正常点击区域。
其中，各待检测区域和正常点击区域的点击来源占比如表1所示：
表1、各待检测区域和正常点击区域的点击来源占比表
Figure PCTCN2018108160-appb-000001
分别计算各待检测区域与正常点击区域的点击来源占比的相关系数，可以获得如图6所示的相关系数。
通过图6所示的相关系数可知，待检测区域3、待检测区域4和待检测区 域5的相关系数很低，可以确定这三个待检测区域为异常点击区域。而其他六个待检测区域的相关系数很好，可以确定这六个待检测区域不是异常点击区域。
如图7所示，本申请将确定的异常点击区域(待检测区域3、待检测区域4和待检测区域5)圈起来以进行标识，同时将该点击热力图覆盖到对应的界面上(本申请对界面进行了模糊处理)。
可选的，本申请可以将步骤S300确定的不是异常点击区域的待检测区域与其他点击热力图中的待检测区域进行点击来源数据的比对。
本申请实施例提供的一种点击热力图异常检测方法，可以确定第一点击热力图中的待检测区域，将待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果，根据第一比对结果确定待检测区域是否为异常点击区域。发明人经过研究发现，异常点击区域的点击来源数据相对于正常点击区域的点击来源数据有较大差别，因此可以根据二者的比对结果确定待检测区域是否为异常点击区域，从而实现异常点击区域的自动识别，并提高了准确性和识别效率。
如图8所示，在图1所示实施例基础上，本申请实施例提供的另一种点击热力图异常检测方法，还可以包括：
S400、获得第二点击热力图，确定所述第二点击热力图中的待检测区域，其中，所述第一点击热力图为第一页面在第一时间段内的点击热力图；所述第二点击热力图为所述第一页面在第二时间段内的点击热力图，所述第一时间段和所述第二时间段不同；
对于同一页面而言，不同时间段内(例如相邻的两天)的点击来源可能并未发生变化，这种情况下，前一时间段内通过图1所示方法中的第一比对结果确定的不是异常点击区域的待检测区域的点击来源数据可以用于与后一时间段内的点击热力图中的待检测区域的点击来源数据进行比对。
S500、将所述第二点击热力图中的待检测区域的点击来源数据与所述第一点击热力图中确定为不是异常点击区域的待检测区域的点击来源数据进行比对，获得第二比对结果；
S600、根据所述第二比对结果确定所述第二点击热力图中的待检测区域是否为异常点击区域。
图8所示方法中的步骤S400至S600可以使用前一时间段内通过图1所示方法中的第一比对结果确定的不是异常点击区域的待检测区域与后一时间段内的点击热力图中的待检测区域进行点击来源数据的比对，简化了异常点击区域的确定过程。
与上述方法实施例相对应，本申请实施例还提供了一种点击热力图异常检测装置。
如图9所示，本申请实施例提供的一种点击热力图异常检测装置，可以包括：待检测区域确定单元100、第一对比单元200和异常确定单元300，
所述待检测区域确定单元100，用于获得第一点击热力图，确定所述第一点击热力图中的待检测区域；
其中，本申请可以直接从其他电子设备中获得第一点击热力图，也可以根据从其他电子设备中获得的点击数据生成该第一点击热力图。
具体的，本申请在获得点击数据后可以首先对点击数据进行归一化处理，然后进行转置、数据区间化与滤波处理，然后根据滤波处理后的点击数据生成点击热力图即可。
可选的，待检测区域确定单元100可以包括：划分子单元和分割子单元，
所述划分子单元，用于将所述第一点击热力图划分为多个面积相等的子区域，其中，各子区域的形状相同；
所述分割子单元，用于使用图像分割算法对划分为多个子区域的所述第一点击热力图进行分割，获得由多个完整的子区域构成的待检测区域，其中，所述待检测区域中的各子区域内的点击量均大于第一预设阈值；
图9所示装置还可以包括：正常区域确定单元，用于将所述第一点击热力图中除所述待检测区域外的区域确定为正常点击区域。
其中，第一点击热力图中的待检测区域可以为该第一点击热力图中点击量较高的区域。
本申请发明人在实现本申请的过程中研究发现：作弊流量产生的点击数据 一般均集中在某些区域，并导致这些区域的点击量较高，因此本申请可以将点击量较高的区域确定为待检测区域。相应的，点击量较低的区域一般为正常点击区域。本申请发明人研究发现，当点击数据均由真实用户产生时，不同的两个区域内的点击数据的来源分布相似。例如：某网页中包括第一区域和第二区域，该网页的点击数据有B、C和D三个来源，这三个来源的点击数据在第一区域的全部点击数据中的占比分别为：10％、20％和70％。这三个来源的点击数据在第二区域的全部点击数据中的占比分别为：8％、23％和69％。
所述第一对比单元200，用于将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果；
可选的，第一对比单元200，可以具体用于通过计算所述待检测区域的点击来源数据与正常点击区域的点击来源数据的相关系数来进行点击来源数据的比对，将计算得到的相关系数作为第一比对结果。
所述异常确定单元300，用于根据所述第一比对结果确定所述待检测区域是否为异常点击区域。
具体的，异常确定单元300，可以具体用于确定作为所述第一比对结果的相关系数是否小于第二预设阈值，如果是，则确定所述待检测区域为异常点击区域。
可选的，在作为所述第一比对结果的相关系数不小于第二预设阈值时，异常确定单元300还可以确定所述待检测区域为正常点击区域。
在本申请另一实施例中，图9所示装置还可以包括：热力图获得单元、第二对比单元和异常区域确定单元，
所述热力图获得单元，用于获得第二点击热力图，确定所述第二点击热力图中的待检测区域，其中，所述第一点击热力图为第一页面在第一时间段内的点击热力图；所述第二点击热力图为所述第一页面在第二时间段内的点击热力图，所述第一时间段和所述第二时间段不同；
对于同一页面而言，不同时间段内(例如相邻的两天)的点击来源可能并未发生变化，这种情况下，前一时间段内通过第一比对结果确定的不是异常点击区域的待检测区域的点击来源数据可以用于与后一时间段内的点击热力图 中的待检测区域的点击来源数据进行比对。
所述第二对比单元，用于将所述第二点击热力图中的待检测区域的点击来源数据与所述第一点击热力图中确定为不是异常点击区域的待检测区域的点击来源数据进行比对，获得第二比对结果；
所述异常区域确定单元，用于根据所述第二比对结果确定所述第二点击热力图中的待检测区域是否为异常点击区域。
该实施例可以使用前一时间段内通过图9所示装置中的第一比对结果确定的不是异常点击区域的待检测区域与后一时间段内的点击热力图中的待检测区域进行点击来源数据的比对，简化了异常点击区域的确定过程。
在本申请另一实施例中，图9所示装置还可以包括：标识添加单元，用于为确定为异常点击区域的待检测区域添加预设标识。
通过该预设标识的添加就可以使得广告购买方方便的找到本申请确定的异常点击区域。
进一步，本申请还可以将添加了预设标识的异常点击区域所在的第一点击热力图覆盖该第一点击热力图对应的界面图上。其中，该界面图可以为网页界面图、应用程序界面图等。通过覆盖到界面图上，可以进一步方便用户找到异常点击区域对应的界面图中的位置，从而对其进行分析和使用。
本申请实施例提供的一种点击热力图异常检测装置，可以确定第一点击热力图中的待检测区域，将待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果，根据第一比对结果确定待检测区域是否为异常点击区域。发明人经过研究发现，异常点击区域的点击来源数据相对于正常点击区域的点击来源数据有较大差别，因此可以根据二者的比对结果确定待检测区域是否为异常点击区域，从而实现异常点击区域的自动识别，并提高了准确性和识别效率。
所述点击热力图异常检测装置包括处理器和存储器，上述待检测区域确定单元、第一对比单元和异常确定单元等均作为程序单元存储在存储器中，由处理器执行存储在存储器中的上述程序单元来实现相应的功能。
处理器中包含内核，由内核去存储器中调取相应的程序单元。内核可以设 置一个或以上，通过调整内核参数来确定异常点击区域。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。
本申请实施例提供了一种存储介质，其上存储有程序，该程序被处理器执行时实现所述点击热力图异常检测方法。
本申请实施例提供了一种处理器，所述处理器用于运行程序，其中，所述程序运行时执行所述点击热力图异常检测方法。
本申请实施例提供了一种设备，设备包括处理器、存储器及存储在存储器上并可在处理器上运行的程序，处理器执行程序时实现以下步骤：
获得第一点击热力图，确定所述第一点击热力图中的待检测区域；
将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果；
根据所述第一比对结果确定所述待检测区域是否为异常点击区域。
可选的，所述确定所述第一点击热力图中的待检测区域，包括：
将所述第一点击热力图划分为多个面积相等的子区域，其中，各子区域的形状相同；
使用图像分割算法对划分为多个子区域的所述第一点击热力图进行分割，获得由多个完整的子区域构成的待检测区域，其中，所述待检测区域中的各子区域内的点击量均大于第一预设阈值；
处理器执行程序时还可以实现以下步骤：
将所述第一点击热力图中除所述待检测区域外的区域确定为正常点击区域。
可选的，处理器执行程序时还可以实现以下步骤：
获得第二点击热力图，确定所述第二点击热力图中的待检测区域，其中，所述第一点击热力图为第一页面在第一时间段内的点击热力图；所述第二点击热力图为所述第一页面在第二时间段内的点击热力图，所述第一时间段和所述第二时间段不同；
将所述第二点击热力图中的待检测区域的点击来源数据与所述第一点击热力图中确定为不是异常点击区域的待检测区域的点击来源数据进行比对，获得第二比对结果；
根据所述第二比对结果确定所述第二点击热力图中的待检测区域是否为异常点击区域。
可选的，所述将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果，包括：
通过计算所述待检测区域的点击来源数据与正常点击区域的点击来源数据的相关系数来进行点击来源数据的比对，将计算得到的相关系数作为第一比对结果。
可选的，所述根据所述第一比对结果确定所述待检测区域是否为异常点击区域，包括：
确定作为所述第一比对结果的相关系数是否小于第二预设阈值，如果是，则确定所述待检测区域为异常点击区域。
可选的，处理器执行程序时还可以实现以下步骤：
为确定为异常点击区域的待检测区域添加预设标识。
本文中的设备可以是服务器、PC、PAD、手机等。
本申请还提供了一种计算机程序产品，当在数据处理设备上执行时，适于执行初始化有如下方法步骤的程序：
获得第一点击热力图，确定所述第一点击热力图中的待检测区域；
将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果；
根据所述第一比对结果确定所述待检测区域是否为异常点击区域。
可选的，所述确定所述第一点击热力图中的待检测区域，包括：
将所述第一点击热力图划分为多个面积相等的子区域，其中，各子区域的形状相同；
使用图像分割算法对划分为多个子区域的所述第一点击热力图进行分割，获得由多个完整的子区域构成的待检测区域，其中，所述待检测区域中的各子 区域内的点击量均大于第一预设阈值；
上述计算机程序产品，当在数据处理设备上执行时，还可以适于执行初始化有如下方法步骤的程序：
将所述第一点击热力图中除所述待检测区域外的区域确定为正常点击区域。
可选的，上述计算机程序产品，当在数据处理设备上执行时，还可以适于执行初始化有如下方法步骤的程序：
获得第二点击热力图，确定所述第二点击热力图中的待检测区域，其中，所述第一点击热力图为第一页面在第一时间段内的点击热力图；所述第二点击热力图为所述第一页面在第二时间段内的点击热力图，所述第一时间段和所述第二时间段不同；
将所述第二点击热力图中的待检测区域的点击来源数据与所述第一点击热力图中确定为不是异常点击区域的待检测区域的点击来源数据进行比对，获得第二比对结果；
根据所述第二比对结果确定所述第二点击热力图中的待检测区域是否为异常点击区域。
可选的，所述将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果，包括：
通过计算所述待检测区域的点击来源数据与正常点击区域的点击来源数据的相关系数来进行点击来源数据的比对，将计算得到的相关系数作为第一比对结果。
可选的，所述根据所述第一比对结果确定所述待检测区域是否为异常点击区域，包括：
确定作为所述第一比对结果的相关系数是否小于第二预设阈值，如果是，则确定所述待检测区域为异常点击区域。
可选的，上述计算机程序产品，当在数据处理设备上执行时，还可以适于执行初始化有如下方法步骤的程序：
为确定为异常点击区域的待检测区域添加预设标识。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存 (PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (10)

  1. 一种点击热力图异常检测方法，其特征在于，包括：
    获得第一点击热力图，确定所述第一点击热力图中的待检测区域；
    将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果；
    根据所述第一比对结果确定所述待检测区域是否为异常点击区域。
  2. 根据权利要求1所述的方法，其特征在于，所述确定所述第一点击热力图中的待检测区域，包括：
    将所述第一点击热力图划分为多个面积相等的子区域，其中，各子区域的形状相同；
    使用图像分割算法对划分为多个子区域的所述第一点击热力图进行分割，获得由多个完整的子区域构成的待检测区域，其中，所述待检测区域中的各子区域内的点击量均大于第一预设阈值；
    所述方法还包括：将所述第一点击热力图中除所述待检测区域外的区域确定为正常点击区域。
  3. 根据权利要求1或2所述的方法，其特征在于，还包括：
    获得第二点击热力图，确定所述第二点击热力图中的待检测区域，其中，所述第一点击热力图为第一页面在第一时间段内的点击热力图；所述第二点击热力图为所述第一页面在第二时间段内的点击热力图，所述第一时间段和所述第二时间段不同；
    将所述第二点击热力图中的待检测区域的点击来源数据与所述第一点击热力图中确定为不是异常点击区域的待检测区域的点击来源数据进行比对，获得第二比对结果；
    根据所述第二比对结果确定所述第二点击热力图中的待检测区域是否为异常点击区域。
  4. 根据权利要求1所述的方法，其特征在于，所述将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果，包括：
    通过计算所述待检测区域的点击来源数据与正常点击区域的点击来源数据的相关系数来进行点击来源数据的比对，将计算得到的相关系数作为第一比对结果。
  5. 根据权利要求4所述的方法，其特征在于，所述根据所述第一比对结果确定所述待检测区域是否为异常点击区域，包括：
    确定作为所述第一比对结果的相关系数是否小于第二预设阈值，如果是，则确定所述待检测区域为异常点击区域。
  6. 根据权利要求1至3中任一项所述的方法，其特征在于，还包括：
    为确定为异常点击区域的待检测区域添加预设标识。
  7. 一种点击热力图异常检测装置，其特征在于，包括：待检测区域确定单元、第一对比单元和异常确定单元，
    所述待检测区域确定单元，用于获得第一点击热力图，确定所述第一点击热力图中的待检测区域；
    所述第一对比单元，用于将所述待检测区域的点击来源数据与正常点击区域的点击来源数据进行比对，获得第一比对结果；
    所述异常确定单元，用于根据所述第一比对结果确定所述待检测区域是否为异常点击区域。
  8. 根据权利要求7所述的装置，其特征在于，所述待检测区域确定单元，包括：划分子单元和分割子单元，
    所述划分子单元，用于将所述第一点击热力图划分为多个面积相等的子区域，其中，各子区域的形状相同；
    所述分割子单元，用于使用图像分割算法对划分为多个子区域的所述第一点击热力图进行分割，获得由多个完整的子区域构成的待检测区域，其中，所述待检测区域中的各子区域内的点击量均大于第一预设阈值；
    所述装置还包括：正常区域确定单元，用于将所述第一点击热力图中除所述待检测区域外的区域确定为正常点击区域。
  9. 一种存储介质，其特征在于，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行如权利要求1-6中任一项所 述的点击热力图异常检测方法。
  10. 一种处理器，其特征在于，所述处理器用于运行程序，其中，所述程序运行时执行如权利要求1-6中任一项所述的点击热力图异常检测方法。
PCT/CN2018/108160 2017-09-29 2018-09-28 点击热力图异常检测方法及装置 WO2019062824A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/642,276 US20210079866A1 (en) 2017-09-29 2018-09-28 Click heatmap abnormality detection method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710904819.4A CN110020351B (zh) 2017-09-29 2017-09-29 点击热力图异常检测方法及装置
CN201710904819.4 2017-09-29

Publications (1)

Publication Number Publication Date
WO2019062824A1 true WO2019062824A1 (zh) 2019-04-04

Family

ID=65900704

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/108160 WO2019062824A1 (zh) 2017-09-29 2018-09-28 点击热力图异常检测方法及装置

Country Status (3)

Country Link
US (1) US20210079866A1 (zh)
CN (1) CN110020351B (zh)
WO (1) WO2019062824A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021262170A1 (en) * 2020-06-25 2021-12-30 Google Llc Anomalous user interface input detection
CN118246076B (zh) * 2024-05-27 2024-08-27 中核武汉核电运行技术股份有限公司 一种核电数据完整性自校验方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103530431A (zh) * 2013-11-06 2014-01-22 北京国双科技有限公司 用于网页页面点击量统计的数据处理方法和装置
CN104199939A (zh) * 2014-09-09 2014-12-10 北京国双科技有限公司 网页热力图生成方法及装置
CN104731894A (zh) * 2015-03-18 2015-06-24 百度在线网络技术（北京）有限公司 热力图的展现方法及装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101777080B (zh) * 2010-03-19 2013-02-13 北京国双科技有限公司 基于用户点击数据的网页分析方法
KR20150061102A (ko) * 2013-11-25 2015-06-04 주식회사 케이티 관제 시스템 및 이를 이용한 관제 방법
CN103684885B (zh) * 2013-12-31 2017-03-29 新浪网技术(中国)有限公司 一种网站服务器访问异常确定方法及装置
CN105357216A (zh) * 2015-11-30 2016-02-24 上海斐讯数据通信技术有限公司 一种安全访问方法及系统
CN105653724B (zh) * 2016-01-20 2019-07-02 北京京东尚科信息技术有限公司 一种页面曝光量的监控方法和装置
CN107168854B (zh) * 2017-06-01 2020-06-30 北京京东尚科信息技术有限公司 互联网广告异常点击检测方法、装置、设备及可读存储介质
US10419460B2 (en) * 2017-07-21 2019-09-17 Oath, Inc. Method and system for detecting abnormal online user activity

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103530431A (zh) * 2013-11-06 2014-01-22 北京国双科技有限公司 用于网页页面点击量统计的数据处理方法和装置
CN104199939A (zh) * 2014-09-09 2014-12-10 北京国双科技有限公司 网页热力图生成方法及装置
CN104731894A (zh) * 2015-03-18 2015-06-24 百度在线网络技术（北京）有限公司 热力图的展现方法及装置

Also Published As

Publication number Publication date
US20210079866A1 (en) 2021-03-18
CN110020351B (zh) 2021-08-13
CN110020351A (zh) 2019-07-16

Similar Documents

Publication Publication Date Title
US11086646B2 (en) Tenant-side detection, classification, and mitigation of noisy-neighbor-induced performance degradation
RU2628127C2 (ru) Способ и устройство для идентификации поведения пользователя
TW202008237A (zh) 針對新場景的預測模型訓練方法及裝置
US11170027B2 (en) Error factor and uniqueness level for anonymized datasets
WO2019085327A1 (zh) 电子装置、产品推荐方法、系统和计算机可读存储介质
CN106407210B (zh) 一种业务对象的展示方法和装置
WO2019105226A1 (zh) 一种用于营销活动效果预测的方法、装置及电子设备
JP2019525309A (ja) データリスクを制御する方法及び装置
JP2019504380A (ja) 注文クラスタリング方法及び装置並びに悪意の情報に対抗する方法及び装置
CN106934648B (zh) 一种数据处理方法和装置
WO2014169139A1 (en) Method and device for testing multiple versions
CN109191133B (zh) 支付渠道的选择方法及终端设备
WO2016177280A1 (zh) 记录及还原网页中点击位置的方法和装置
WO2019169964A1 (zh) 一种资源和营销推荐方法、装置及电子设备
TW201734893A (zh) 信用分的獲取、特徵向量值的輸出方法及其裝置
WO2019062824A1 (zh) 点击热力图异常检测方法及装置
WO2020063523A1 (zh) 图像检测方法及装置
WO2018227931A1 (zh) 信息判断方法及装置
US20160117781A1 (en) Inferred matching of payment card accounts by matching to common mobile device via time and location data analysis
CN112052857A (zh) 一种票据图像中目标字段的检测方法及相关装置
CN106157281B (zh) 一种图像主体识别方法及装置
WO2019161718A1 (zh) 归因方法和装置
Lukas et al. Practical use of robust GCV and modified GCV for spline smoothing
WO2019062841A1 (zh) 品牌曝光效果分析方法及装置
CN117520645A (zh) 基于金融产品的用户确定方法、装置以及电子设备

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 21/08/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18863131

Country of ref document: EP

Kind code of ref document: A1