WO2018032763A1 - 一种生成热力图的方法及装置 - Google Patents

一种生成热力图的方法及装置 Download PDF

Info

Publication number
WO2018032763A1
WO2018032763A1 PCT/CN2017/077942 CN2017077942W WO2018032763A1 WO 2018032763 A1 WO2018032763 A1 WO 2018032763A1 CN 2017077942 W CN2017077942 W CN 2017077942W WO 2018032763 A1 WO2018032763 A1 WO 2018032763A1
Authority
WO
WIPO (PCT)
Prior art keywords
cell
thermal
pixel
heat
diffusion
Prior art date
Application number
PCT/CN2017/077942
Other languages
English (en)
French (fr)
Inventor
高黎生
倪冰
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP17840740.9A priority Critical patent/EP3489904A1/en
Publication of WO2018032763A1 publication Critical patent/WO2018032763A1/zh
Priority to US16/279,622 priority patent/US10783673B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/20—Drawing from basic elements, e.g. lines or circles
    • G06T11/206—Drawing of charts or graphs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/001—Texturing; Colouring; Generation of texture or colour
    • 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
    • G06F16/903—Querying
    • G06F16/9038—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • 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

Definitions

  • the present application relates to the field of image processing, and in particular, to a method and apparatus for generating a heat map.
  • the user's usage information can be aggregated into density data, describing the density of the area at a certain time point or time period, and describing the correspondence between the location of the area and the number of people or clicks.
  • Density data can provide users with many conveniences. For example, the use of density data in electronic maps can predict the congestion status of roads and the congestion of locations. After the density data of different time is aggregated, information such as population distribution, distribution of work sites, etc. can be further displayed. .
  • the heat map technique can display the distribution and variation of a variable in a two-dimensional space naturally by using the continuous or discrete color gradation. Therefore, the heat map is applied to various scenes to present the density. Data, characteristics of the reaction area. For example, using heat maps to present density data of different regions in color maps in an electronic map, it is possible to clearly present a data-intensive "hot zone” on the map and a "cold zone” with sparse data to show important statistics such as population distribution. information.
  • the heat map is used to reflect the correspondence between the area of the webpage and the number of clicks of the user, so that the website administrator can determine the area that the user frequently clicks but is not the link, and consider placing the resource link in the area.
  • thermogram Currently, heat maps are usually drawn using a point method based on density data in an image suitable for scale.
  • a common drawing method is to draw a thermal point with a data point, or to draw a thermal point in the sum of the data in one area.
  • the thermogram will not be able to continuously and accurately characterize the reaction zone.
  • the electronic map is characterized by complete and continuous geographical location information, but the heat map generated by the existing heat map technology, when the user zooms in on the map, the heat map is rendered as a scatter plot. The overall cannot reflect the distribution of density data in different regions.
  • the heat map is presented as a large thermal point, and the coverage area of the point even exceeds the coverage area of the actual data, which has no practical significance.
  • thermogram technology can not accurately reflect the actual distribution characteristics of the image and the characteristics of the region when adjusting the scaling ratio of the image. And the thermal map is poor in continuity.
  • Embodiments of the present invention provide a method and apparatus for generating a heat map, which realizes the characteristics of a continuous and accurate reaction region of a heat map, and the change of the image scale does not affect the continuity and accuracy of the heat map.
  • the basic thermal force H, x of the radius of the thermal point region is less than or equal to
  • the basic thermal power of each pixel in a thermal point region is H; and according to the basic thermal power of the thermal point region of each cell, the diffusion heat received by each pixel in the current display region is calculated, and is in at least one cell.
  • the diffusion heat received by one pixel in the diffusion heat region is generated by the thermal point region of each of the at least one cell; on the basis of this, according to the basic heat of each pixel in the current display region and the received Diffusion heat, respectively obtaining the total thermal power of each pixel in the current display area; finally, correspondingly according to the preset thermal force, in the current display area of the original image, presenting the total thermal power of each pixel in the current display area Color, get the heat map of the current display area.
  • r 1 is the side length of the cell divided when the original image was generated for the previous time; ⁇ is a cell change function related to the scaling.
  • w 1 is the thermal weight of the original image when the thermogram was generated last time; ⁇ is the thermal weight change function related to the scaling.
  • the statistics of the original image include at least one data point for reflecting the characteristics of the original image area.
  • the diffusion heat region of a cell is a region in which a center of the one cell is a circle and a radius of R is a region other than a heat point region of the one cell; the R is greater than r.
  • the thermal representation correspondence includes a thermal interval and a color corresponding to each thermal interval.
  • the thermal point region and the diffusion thermal region of each cell may include each position and detail in the current display region of the original image, regardless of the user. How to adjust the scaling of the original image, each generated thermogram is continuous, ensuring the continuity of the thermogram, so that the thermogram can reflect the characteristics of the region; secondly, when generating the thermogram locally, the edge of the cell.
  • the length r and the thermal weight w are respectively related to the side length r 1 and the thermal weight w 1 of the cell when the heat map is generated by the cell change function ⁇ and the thermal weight change function ⁇ , respectively, on the basis of which reasonable Setting the cell change function ⁇ and the thermal weight change function ⁇ can ensure that the area of the corresponding area of a cell in the original image is similar each time the heat map is generated, and the heat in the same area in the original image is similar each time the heat map is generated. Regardless of how the user adjusts the scaling of the original image, the heat
  • the present application adopts a method of generating a heat map after dividing cells, and when the amount of data is large, the processing efficiency is greatly improved compared with the prior art drawing method, the processing time is saved, and the heat generating map is reduced. User's waiting time.
  • the original image is the basis for generating the heat map
  • the generated heat map is the regional feature of the original image.
  • the current display area of the original image in the screen is the area in the original image that the user sees in the terminal screen at the current zoom ratio, that is, the area in which the original image is displayed on the terminal interface.
  • the area of the thermal point of a cell refers to the area within the cell that is centered on the center of the cell and has a radius of x.
  • the thermal point area of the cell is used in the thermogram to present the raw image to the user, and the coordinates are located in the generated heat of the data point in the corresponding area of the cell in the original image.
  • the area of the diffusion heat of a cell refers to the area where the heat radiated from the area of the cell's thermal point reaches.
  • the diffusion heat region of a cell is defined as a region having a center of the cell and a region having a radius of R, excluding the region of the cell heat point.
  • the thermal point region of a cell produces diffusion heat to each pixel in the diffusion heat region of the cell.
  • a pixel at a region of the diffusion thermal region of at least one of the cells is subjected to a diffusion thermal component of each of the at least one cell.
  • the diffusion heat received by the pixel is calculated from all the diffusion thermodynamic components received by the pixel.
  • weights may be configured on the statistical objects or data points, so that the acquired thermal values are generated. The largest possible difference can be reflected in different colors.
  • the thermogram for the thermal weight w according to the original image and the thermal weight w of the current thermogram, the basic thermal power of each of the cells in the thermal point region with the center of the cell as the center and the radius of x is calculated.
  • each cell is processed in the same way.
  • any cell in the current display area of the original image (called the first cell) is taken as an example to describe the statistical data according to the original image and the generated heat map.
  • N is the statistical data of the original image, and the coordinates are located in the total number of data points or statistical objects in the corresponding area of the first cell in the original image.
  • the statistical object is a target individual when the data point for data analysis is obtained in the original image, and the data point refers to the binary data including the position and the statistical parameter generated after the statistical statistics are performed on the statistical object in the original image.
  • N it depends on the definition of w. If w is defined as the thermal value of the data point Weight, where N is the statistical data of the original image, the coordinates are located in the total number of data points in the corresponding area of the first cell in the original image; if w is defined as the weight value of the statistical object, then N is the original image In the statistical data, the coordinates are located in the total number of statistical objects in the corresponding area of the first cell in the original image.
  • the current display in order to accurately and accurately accurately reflect each position in the current display area of the original image in the heat map, the current display
  • the pixels in the area are affected by the diffusion heat generated by the thermal point area in the surrounding cells.
  • the hot spot area of a cell produces a greater diffusion heat for pixels closer to its center point. Therefore, the diffusion heat calculated from the distance from the pixel position to the center of the cell can more accurately reflect the actual data distribution.
  • the process of calculating the diffusion heat received by each pixel in the current display area is the same. In this implementation manner, any pixel in the diffusion heat region of at least one cell in the current display area is used.
  • a point (referred to as a first pixel) is taken as an example to describe a specific process of calculating the diffusion heat received by the first pixel.
  • the specific implementation is: firstly, according to the basic thermal force of the thermal point region of each cell, calculating a diffusion thermal component of the first pixel point subjected to the thermal point region of each cell, and then subjecting the first pixel point to at least one diffusion thermal component The weighted sum is the diffusion heat received by the first pixel; wherein the at least one diffusion thermal component received by the first pixel is generated for each cell to which the at least one diffusion thermal region in which the first pixel is located belongs.
  • the process for calculating the diffusion thermal component of the thermal point region of each cell by the first pixel is the same, and is described herein.
  • Calculating a process in which the first pixel is subjected to a diffusion thermal component of the thermal point region of the second cell calculating a diffusion thermal component of the first pixel by the second cell.
  • the second cell is any one of the cells to which the at least one diffusion heat region in which the first pixel is located; d is the distance from the first pixel position to the center of the second cell; H is the second unit The basic heat of the grid's thermal point area.
  • the current display area is in a thermal point area of one cell, but not in the diffusion thermal area of any one of the cells.
  • the pixel is subjected to the diffusion heat, which is the basic heat of the pixel.
  • the distance from the pixel position to the center of the cell refers to the distance d displayed in the current display area, and the same unit as r.
  • the distance from the pixel position to the center of the cell refers to the actual distance corresponding to the original image, and r is also the actual distance corresponding to the side length of the cell in the original image, as long as the unit distances of d and r represent the same content. Just fine.
  • each time the heat map is generated in order to achieve different scaling ratios, each time the heat map is generated, the side length r of the cell corresponds to the original image.
  • the distance is similar, and the thermal values in the same region in the original image are similar, and ⁇ and ⁇ can be defined as correlation functions of the change amount ⁇ Z of the scaling ratio.
  • ⁇ a ⁇ Z
  • a is a preset cell variation parameter, a is greater than or equal to 1, less than or equal to 2
  • ⁇ b ⁇ Z
  • b is a preset thermal weight change parameter, and b is greater than or equal to 1, Less than or equal to 4
  • ⁇ Z is the scaling of the original image when generating the thermogram minus the scaling of the original image when the thermogram was last generated.
  • the scheme of the first aspect is executed, that is, the heat map of the current display area is generated this time, the original image is the first time.
  • the heat map is generated, and there is no previous generation of the heat map.
  • r 1 is the initial value of the cell side length r 0
  • w 1 is the initial value of the heat weight w 0 .
  • r 0 and w 0 are preset values.
  • the edge length of the cell is generated each time the thermogram is generated.
  • the corresponding distances in the original image are similar, specifically defined as: ⁇ is used to control the absolute value of the corresponding actual length difference between r and r 1 in the original image is less than or equal to the first preset threshold.
  • the thermal values of the same region in the original image are similar, specifically defined as: ⁇ is used to control the same region in the original image every time the thermogram is generated.
  • the absolute value of the difference in the total thermal power value obtained is less than or equal to the second predetermined threshold.
  • the pixel point of the diffusion heat region in a certain cell in the current display area of the original image may also be in a unit.
  • the pixel has both basic heat and diffusion heat from other cells. Specifically, for each pixel point of the thermal point area of the cell in the current display area of the original image, the process of calculating the total thermal power is the same.
  • the thermal point of the cell in the current display area of the original image is Taking any pixel of the region (referred to as a second pixel) as an example, describing the total thermal power of acquiring the second pixel according to the basic thermal power and the diffusion thermal force is specifically realized as: the diffusion heat received by the second pixel and the second pixel The basic thermal power of the points is added to obtain the total thermal power of the second pixel; or the diffusion heat received by the second pixel and the basic thermal force of the second pixel are weighted to obtain the total thermal power of the second pixel.
  • the pixel points of the thermal power point region of a certain cell in the current display area of the original image may not be in any unit.
  • the pixel In the region of the diffusion heat, the pixel has only basic heat, and the total heat is the basic heat of the pixel.
  • the heat in the current display area of the original image that is only in the diffusion heat region of at least one cell but not in any of the cells
  • the pixel point of the dot area the total heat of the pixel is subjected to diffusion heat.
  • the process of calculating the total thermal power is the same.
  • the cell in the current display area of the original image is in the cell diffusion heat region and is not in the
  • the total thermal power of the third pixel is obtained by: the diffusion heat received by the third pixel is The total heat of the third pixel.
  • an embodiment of the present invention provides a device for generating a heat map, and the device may implement the foregoing method.
  • the function of the device may be implemented by using hardware or by executing corresponding software by hardware.
  • the hardware or software includes one or more modules corresponding to the above functions.
  • the apparatus includes a processor and a transceiver configured to support the apparatus to perform the above method.
  • the transceiver is used to support communication between the device and other network elements.
  • the apparatus can also include a memory for coupling with the processor that retains the program instructions and data necessary for the apparatus.
  • an embodiment of the present invention provides a computer storage medium for storing computer software instructions for use in the above apparatus, including a program designed to perform the above aspects.
  • the solution provided by the second aspect or the third aspect is used to implement the method for generating a heat map provided by the above first aspect, and thus the same beneficial effects can be achieved as the first aspect, and details are not described herein.
  • FIG. 1 is a schematic structural diagram of an Internet architecture in the prior art
  • FIG. 2 is a schematic structural diagram of a device 20 for generating a heat map according to an embodiment of the present invention
  • FIG. 3 is a schematic flowchart diagram of a method for generating a heat map according to an embodiment of the present invention
  • FIG. 4 is a schematic diagram of a position of a cell and a thermal point region according to an embodiment of the present invention
  • FIG. 5 is a schematic diagram of a position of a cell, a thermal point area, and a diffusion thermal area according to an embodiment of the present invention
  • FIG. 6 is a schematic diagram of a pixel point position according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of another pixel point position according to an embodiment of the present invention.
  • FIG. 8 is a schematic diagram of still another pixel point position according to an embodiment of the present invention.
  • FIG. 9 is a schematic structural diagram of another apparatus 20 for generating a heat map according to an embodiment of the present invention.
  • FIG. 10 is a schematic structural diagram of still another apparatus 20 for generating a heat map according to an embodiment of the present invention.
  • heat maps are generated at a fixed scale by using the plotting method.
  • the heat map will be discrete or converged as the scaling changes. This causes the thermal map to not accurately reflect the characteristics of the area.
  • thermogram refers to the parameters of the previous generation of the thermogram to ensure that the area and thermal force of the same region in the original image are similar under different scaling ratios, and the generated thermogram can be accurate. And continuously reflects the regional characteristics of the image.
  • the method for generating a heat map provided by the embodiment of the present invention is applied to the Internet architecture as shown in FIG. 1.
  • the Internet architecture includes a web server 101 and at least one terminal 102.
  • the method for generating a heat map provided by the embodiment of the present invention is specifically applied to the terminal 102.
  • the network server 101 obtains statistical data by counting the user data of each terminal 102, and provides it to each terminal 102 for data analysis.
  • Terminal 102 through network service
  • the server 101 interacts with the Internet to obtain statistical data obtained by the network server 101 for data analysis.
  • the data analysis performed by the terminal 102 may include generating a heat map for the user to visually view the statistical data.
  • the method for generating a heat map provided by the embodiment of the present invention is implemented by the apparatus 20 for generating a heat map provided by the embodiment of the present invention.
  • the apparatus 20 for generating a heat map provided by the embodiment of the present invention may be the terminal 102 of the architecture shown in FIG. Part or all.
  • the terminal 102 can be a mobile phone, a tablet computer, a notebook computer, a personal computer (English name: personal computer, PC), a super mobile personal computer (English name: Ultra-mobile Personal Computer, UMPC), a netbook, an individual.
  • Digital assistant English full name: Personal Digital Assistant, PDA
  • terminal equipment such as in-vehicle equipment.
  • FIG. 2 is a block diagram showing the structure of a device 20 for generating a heat map associated with various embodiments of the present application.
  • the apparatus 20 for generating a heat map may include a processor 201, a memory 202, a communication bus 203, and a display 204.
  • the memory 202 is configured to store program code and transmit the program code to the processor 201, so that the processor 201 executes the program code to implement various functions of the device 20 for generating a heat map.
  • the memory 202 can be a volatile memory, such as a random access memory (RAM), or a non-volatile memory (English name: non-volatile memory), such as a read only memory. (English full name: read-only memory, ROM), flash memory (English full name: flash memory), hard disk (English full name: hard disk drive, HDD) or solid state drive (English full name: solid-state drive, SSD); or A combination of the above types of memories.
  • the processor 201 is a control center of the device 20 for generating a heat map, and may be a central processing unit (CPU) or a specific integrated circuit (ASIC). Is one or more integrated circuits configured to implement embodiments of the present invention, such as: one or more microprocessors (English full name: digital singnal processor, DSP), or one or more field programmable gate arrays Full name: Field Programmable Gate Array, FPGA).
  • the processor 201 can implement various functions of the apparatus 20 for generating a thermogram by running or executing program code stored in the memory 202, as well as invoking data stored in the memory 202.
  • the communication bus 203 can be an industry standard architecture (English name: Industry Standard Architecture, ISA) bus, external device interconnection (English name: Peripheral Component, PCI) bus or extended industry standard architecture (English full name: Extended Industry Standard Architecture, EISA) bus, etc.
  • the bus 203 can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in Figure 2, but it does not mean that there is only one bus or one type of bus.
  • Display 204 can be the screen of terminal 102 for presenting a heat map to the user.
  • the area of the thermal point of a cell refers to the area within the cell that is centered on the center of the cell and has a radius of x.
  • the thermal point area of the cell is used in the thermogram to present the raw image to the user, and the coordinates are located in the generated heat of the data point in the corresponding area of the cell in the original image.
  • the area of the diffusion heat of a cell refers to the area where the heat radiated from the area of the cell's thermal point reaches.
  • the diffusion heat region of a cell is defined as a region having a center of the cell and a region having a radius of R, excluding the region of the cell heat point.
  • the thermal point region of a cell produces diffusion heat to each pixel in the diffusion heat region of the cell.
  • a pixel at a region of the diffusion thermal region of at least one of the cells is subjected to a diffusion thermal component of each of the at least one cell.
  • the diffusion heat received by the pixel is calculated from all the diffusion thermodynamic components received by the pixel.
  • an embodiment of the present invention provides a method for generating a heat map. As shown in FIG. 3, the method may include:
  • the current display area of the original image in the screen refers to an area that the original image can be seen by the user in the screen of the terminal at the current zoom ratio.
  • r 1 is the length of the cell divided by the original image when the thermogram was generated.
  • the * is a multiplication calculation.
  • the part less than r is regarded as a cell, that is, the length of the dividing side When the square cell is r, the maximum length of the cell is r.
  • the remaining area of the cell that is less than r is the upper or lower boundary of the current display area, or is the left or the right boundary, and can be set according to actual requirements. This is not specifically limited. It is only necessary to process the remaining area with a side length less than r in the same way every time the heat map is generated.
  • the heat map is generated for the original image for the first time, that is, if the heat map is generated for the first time to generate a heat map for the original image, r 1 is the cell edge length initial value r 0 .
  • r 0 may be set according to an actual requirement or an empirical value, which is not specifically limited in the embodiment of the present invention.
  • ⁇ is a cell change function related to the scaling ratio, which is used to control the speed of the thermal map discretization.
  • the ⁇ is used to control the absolute value of the actual length difference corresponding to r and r 1 in the original image to be less than or equal to the first preset threshold.
  • the value of the first preset threshold may be set according to actual requirements, which is not specifically limited in this application. Specifically, the smaller the first preset threshold is set, the more stable the thermal map is when the zoom ratio is large, but it is difficult to supplement the image details; the larger the first preset threshold is, the more generated The heat map will show additional details, but the overall stability and continuity of the image is poor. In practical applications, the value of the first preset threshold may be compromised according to actual needs.
  • a is a preset cell variation parameter, a is greater than or equal to 1, less than or equal to 2; ⁇ Z is the scaling of the original image when generating the thermogram minus the original image when the thermogram is generated last time. proportion.
  • the cell side length does not change, and the corresponding area size of the cell in the original image does not change with the zoom ratio, and the heat map will display additional detail information, but the overall stability of the image and The continuity is poor;
  • the side length of the cell changes with the change of the scaling ratio, and the corresponding area size of the cell in the original image does not change with the change of the scaling ratio, that is, the image represented by the cell
  • the actual area is certain, the heat map is stable under the magnifying operation, but it is difficult to supplement or ignore the details.
  • the original image is an electronic map
  • the user is assumed to enlarge the map by one level ([Delta]Z is 1), and the actual size of the cell of the same size on the map is only 1/4 of the original. If the data points are evenly distributed, the total amount of data in the cells will become approximately 1/4 of the original.
  • the total amount of data in the cell is similar to the total amount of data in one cell when the heat map was generated last time, and the side length r of the cell needs to be changed accordingly.
  • ⁇ Z 1
  • the side length of the cell becomes a times of the previous time
  • the actual area represented by the same size cell on the map is the original Times.
  • a is taken as 1
  • the actual area indicated by the same size cell on the map is 1/4 of the original
  • a is 2
  • the actual area indicated by the same size cell on the map is the original 1 times, that is, the cells divided when generating the heat map twice are equal in the actual area in the electronic map.
  • the a is 1.6.
  • ⁇ a ⁇ Z + c.
  • c can be a constant, and an exponential function about Z can also be used.
  • the basic thermal power of each pixel in a thermal point region is H.
  • the statistical data of the original image includes at least one data point for reflecting the characteristics of the original image region.
  • the statistical data of the original image may be acquired by the device that executes the method for generating the heat map of the present application and the network server through the Internet, and at least one data point generated after the original image of the network server is monitored in the statistical data.
  • the content and the acquisition process of the statistical data of the original image are not described in the present application.
  • the data point can be the statistical object density of the region.
  • x is less than or equal to
  • x it can be set according to actual needs.
  • x is equal to
  • x can also be close And less than Value.
  • the value of x in this embodiment of the present application is not specifically limited.
  • w 1 is the thermal weight of the original image when the heat map is generated.
  • the thermal weight is set in the heat map to set the data point (dual group data) or statistical object in order to facilitate the calculation of thermal power and to make the calculated thermal value distance so as to be indicated by different colors.
  • Weight coefficient is set in the heat map to set the data point (dual group data) or statistical object in order to facilitate the calculation of thermal power and to make the calculated thermal value distance so as to be indicated by different colors.
  • the heat map is generated for the original image for the first time. If the heat map is generated for the first time to generate a heat map for the original image, w 1 is the thermal weight initial value w 0 .
  • w 0 may be set according to an actual requirement or an empirical value, which is not specifically limited in this embodiment of the present invention.
  • ⁇ is a thermal weight change function related to the scaling ratio, which is used to maintain the stability of the thermogram.
  • the ⁇ is used to control the absolute value of the difference of the total thermal power value obtained by the same region in the original image in each time the heat map is generated is less than or equal to the second preset threshold.
  • the value of the second preset threshold may be set according to actual requirements, which is not specifically limited in this application.
  • the function relationship between ⁇ and scaling may be in various forms, such as a linear function, a power function, or the like.
  • b is a preset thermal weight change parameter
  • b is greater than or equal to 1, less than or equal to 4.
  • the determining method for b may be as follows: comparing the two-level scaling ratios i and (i+1), if the thermal value of one of the panes in the i-level is H, the geographical area represented is A. Then in the (i+1) level, the heat of A will be The basic heat of a small cell and the diffusion heat generated by A, while the thermal contribution value of each data point will become b times the original, and the heat of A in the (i+1) level is finally obtained.
  • the method for determining b above is only an implementation form, and is not specifically limited to the value of b. There may be other methods for determining the value of b, and only need to ensure that the value of b determined can achieve the function of ⁇ . Just fine.
  • the b is 1.3.
  • the area of the thermal point defining a cell is a cell
  • the center of the cell is a region with a radius of x as a center, and the basic thermal power value of each pixel in the region is equal
  • the thermal point of the cell is The basic heat of the area.
  • the thermal point area of the cell is illustrated.
  • the square area in the figure is a cell, and the circular area is the thermal point area of the cell.
  • x is
  • the execution process in S302 is phase
  • any cell (referred to as the first cell) divided in S301 is taken as an example.
  • the first unit is calculated according to the statistical data of the original image and the thermal weight w of the current heat generating map. In the grid, the process of the basic thermal force in the region of the thermal point with the center of the first cell as the center of the circle with x as the radius.
  • the basic heat of the thermal point region in the first cell with the center of the first cell as the center and the radius of x is calculated.
  • the process specific may include:
  • N is the statistical data of the original image, and the coordinates are located in the total number of data points or statistical objects in the corresponding area of the first cell in the original image.
  • the process of calculating the basic thermal power of the thermal energy point region of the first cell according to the statistical data of the original image and the thermal weight w of the current heat generating graph may specifically include:
  • the q is a preset constant, which can be set according to actual requirements, which is not specifically limited in the embodiment of the present invention.
  • the method for calculating the basic thermal power of the thermal point region of the cell can also be implemented by other methods than the above two methods, which are not specifically limited in the embodiment of the present invention.
  • the diffusion heat region of one cell is a circle centered on the center of the cell, and a region other than the heat point region of the cell in which R is a radius; R is greater than r.
  • the diffusion heat received by one pixel in the diffusion heat region of the at least one cell is generated by the thermal point region of each of the at least one cell.
  • FIG. 5 the relationship between the cells, the thermal point region, and the diffusion thermal region is illustrated.
  • the R of the diffusion heat region defining the cell prefferably, for efficient calculation, it is possible to limit the R of the diffusion heat region defining the cell to be less than or equal to 2r.
  • any pixel in the current display area if it is in the diffusion heat region of at least one cell, the diffusion thermal component of each cell in the at least one cell is received.
  • the diffusion thermal component of any cell in the at least one cell is received.
  • the diffusion heat of the pixel not in the diffusion heat region of any cell is zero.
  • the diffusion heat obtained by the pixel in the diffusion heat region of at least one cell is calculated.
  • only the diffusion heat received by the pixel in the diffusion heat region of the at least one cell may be calculated.
  • the process of calculating the diffusion heat received by each pixel in the diffusion heat region of the at least one cell in the current display area is the same, and is not described here, but only at least one cell in the current display area.
  • any one of the diffusion heat regions (referred to as a first pixel) is described.
  • the process of the diffusion heat received by the first pixel is calculated according to the basic thermal force of the thermal point region of each cell.
  • the process of calculating the diffusion thermal force received by the first pixel may specifically include: first calculating, by the first pixel, a diffusion thermal component of each cell; and weighting the weight of the at least one diffusion thermal component received by the first pixel, The diffusion heat that is received as the first pixel.
  • the weight of the weighting may be set according to actual requirements, which is not specifically limited in the embodiment of the present invention.
  • the weighting weight when calculating the diffusion heat received by the first pixel, may be proportional to the distance of the pixel from the center of the cell.
  • the weight of the weight may be 1, such that the diffusion heat received by the first pixel is the sum of the at least one diffusion thermal component received by the first pixel.
  • the at least one diffusion thermal component received by the first pixel is generated for each cell to which the at least one diffusion thermal region where the first pixel is located.
  • the process of calculating the first pixel point to be subjected to the diffusion thermal component of each cell is the same, and will not be further described herein.
  • An example of the process of calculating the diffusion thermodynamic component of the second cell by the first pixel is illustrated.
  • the second cell is any one of the cells to which the at least one diffusion heat region in which the first pixel is located belongs.
  • a method for calculating a diffusion thermal component of the first pixel by the second pixel may specifically include:
  • d is the distance from the first pixel point location to the center of the second cell.
  • H is the basic heat of the thermal point region of the second cell.
  • d is the position of the pixel in the current display area, and the distance from the cell center is consistent with the unit of the cell side length r. d can also be the position of the pixel in the original image, the actual distance from the center of the cell, as long as it matches the content of r.
  • a method for calculating a diffusion thermal component of the first pixel by the second pixel may specifically include:
  • ⁇ can be 3.14.
  • the function of calculating the diffusion thermal component of the first pixel by the second cell can be set according to actual requirements, and the function only needs to ensure a monotonic reduction from 1 to 0.
  • a diffusion heat component of each cell in the cells is received, and one calculation is required.
  • the calculation of the pixel is affected by the diffusion heat component of the cell, and may be implemented by other methods than the above two methods, which are not specifically limited in the embodiment of the present invention.
  • the pixel points in the thermal point region of the cell in the current display area there is basic thermal power, and may also be subjected to diffusion heat of other cells, and the total heat and basic heat of the pixel points and the received Diffusion heat is related.
  • the execution process of acquiring the total thermal power in S304 is the same.
  • the process of acquiring the total thermal power of the second pixel is described in S304.
  • the specific implementation manner of obtaining the total heat of the second pixel may include, but is not limited to, the following two methods:
  • the diffusion heat received by the second pixel and the basic heat of the second pixel are added to obtain the total heat of the second pixel.
  • the pixel point A is in the thermal point region of one cell, the basic thermal power is H, and the pixel point A is still in the diffusion thermal region of four cells, and the pixel point A will
  • the diffusion thermodynamic components of the thermal energy points of the four cells are recorded as h 1 , h 2 , h 3 , h 4 , respectively, and the diffusion heat received by pixel A is h 1 +h 2 +h 3 +h 4 , then the total heat of pixel A is H+h 1 +h 2 +h 3 +h 4 .
  • the diffusion heat received by the second pixel and the basic thermal force of the second pixel are weighted to obtain the total thermal power of the second pixel.
  • the mode 2 is similar to the mode 1 implementation, and will not be described in detail herein.
  • the weighting in the above-mentioned mode 2 may be set according to actual requirements, which is not specifically limited in the embodiment of the present invention.
  • the total thermal power of the second pixel is acquired, if the second pixel is not in the diffusion thermal region of any cell, the total thermal power of the second pixel is the base of the second pixel. This heat.
  • pixel in the current display area may be in a diffusion heat region of at least one cell and not in a thermal point region of any cell.
  • pixel only the diffusion heat of other cells is affected, and the total heat is related to the diffusion heat.
  • the execution process of acquiring the total heat in S304 is the same.
  • the process of acquiring the total heat of the third pixel point in S304 is described. .
  • the specific implementation of obtaining the total thermal power of the third pixel may include: the diffusion heat received by the third pixel is the total thermal power of the third pixel.
  • the pixel point B is located in the diffusion heat region of 4 cells and is not in the thermal point region of any cell, and the pixel point B will be subjected to the thermal point of the four cells.
  • the diffusion heat component of the region is recorded as h 1 , h 2 , h 3 , h 4 , respectively, and the diffusion heat received by pixel B is h 1 +h 2 +h 3 +h 4 , then the total heat of pixel B Then it is h 1 +h 2 +h 3 +h 4 .
  • the pixel point C is located only in the diffusion heat region of one cell and is not in the thermal point region of any cell, and the pixel point C will only be subjected to the thermal point of the cell.
  • the diffusion thermal component of the region, then the total thermal force of the pixel C is the diffusion thermal component of the thermal point region of the cell.
  • S305 Present a correspondence according to a preset thermal power, and present a color corresponding to the total thermal power of each pixel in the current display area of the original image to obtain a heat map of the current display area.
  • the preset thermal power correspondence relationship includes at least one thermodynamic value interval and a presentation color corresponding to each thermal value interval.
  • the preset color in the correspondence relationship of the thermal power can be deepened as the heat increases, and the color can be expressed by hue, saturation, brightness, and the like.
  • Table 1 only illustrates the content and form of the preset thermal power correspondence relationship by way of an example, and is not specifically limited to the content and form of the preset thermal power correspondence relationship.
  • the corresponding relationship between the preset thermal forces is firstly obtained, and the color corresponding to the total thermal power of each pixel in the current display area of the original image is obtained, and then the current image is displayed. In the display area, the color corresponding to the total thermal power of each pixel is displayed, and the heat map of the current display area is obtained.
  • the current display area of the original image will change, and the method S301 to S305 for generating the heat map provided by the present application is re-executed, and the heat map of the current display area after the change is generated.
  • the secondary generated thermogram shows no discrete points in succession, and the same position in the original image presents the same or similar color in the two generated thermograms.
  • the thermal point region of each cell and the diffusion thermal region of the cell may include each position and detail in the current display region of the original image. Regardless of how the user adjusts the scaling of the original image, each generated heat map is continuous, ensuring the continuity of the heat map, so that the heat map can reflect the characteristics of the area; secondly, when generating the heat map locally, the unit
  • the side length r and the thermal weight w of the lattice are respectively related to the side length r 1 of the cell and the thermal weight w 1 when the heat map is generated by the cell change function ⁇ and the thermal weight change function ⁇ , respectively.
  • the solution provided by the embodiment of the present invention is mainly introduced from the perspective of the working process of the device for generating the heat map.
  • the device for generating the heat map includes hardware structures and/or software modules corresponding to the execution of the respective functions in order to implement the above functions.
  • the present application can be implemented in a combination of hardware or hardware and computer software in combination with the elements and algorithm steps of the various examples described in the embodiments disclosed herein. Whether a function is implemented in hardware or computer software to drive hardware depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods to implement the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present application.
  • the embodiment of the present invention may divide the function module by the device for generating the heat map according to the above method example.
  • each function module may be divided according to each function, or two or more functions may be integrated into one processing module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of the module in the embodiment of the present invention is schematic, and is only a logical function division, and the actual implementation may have another division manner.
  • FIG. 9 is a schematic diagram showing a possible structure of the apparatus 20 for generating a heat map according to the foregoing embodiment.
  • the apparatus 20 for generating a heat map includes: a dividing unit 901. , the calculation unit 902, the acquisition unit 903, and the presentation unit 904.
  • the dividing unit 901 for supporting the device 20 for generating the heat map performs the process S301 of FIG. 3, the calculating unit 902 for supporting the device 20 for generating the heat map to execute the processes S302, S303 of FIG. 3, and the obtaining unit 903 for supporting the generating heat
  • the apparatus 20 of the figure performs the process S304 in FIG. 3; the presentation unit 904 is configured to support the apparatus 20 that generates the heat map to perform the process S305 in FIG. All relevant content of each step involved in the foregoing method embodiments may be referred to the function description of the corresponding functional module. As described, it will not be repeated here.
  • FIG. 10 shows a possible structural diagram of the apparatus 20 for generating a thermogram involved in the above embodiment.
  • the apparatus 20 for generating a heat map may include a processing module 1001, a communication module 1002, and a display module 1003.
  • the processing module 1001 is configured to control and manage the actions of the device 20 that generates the heat map.
  • the processing module 1001 is configured to support the apparatus for generating a thermogram to perform the processes S301 through S305 of FIG. 3, and/or other processes for the techniques described herein.
  • the communication module 1002 is configured to support communication of the device 20 that generates the thermogram with other network entities.
  • the display module 1003 is configured to support the apparatus for generating a thermogram to perform the process S305 of FIG.
  • the apparatus 20 for generating a heat map may further include a storage module 1004 for storing program codes and data of the apparatus 20 that generates the heat map.
  • the processing module 1001 may be the processor 201 in the physical structure of the device 20 for generating the heat map shown in FIG. 2, and may be a processor or a controller, such as a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or Other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It is possible to implement or carry out the various illustrative logical blocks, modules and circuits described in connection with the present disclosure.
  • the processor may also be a combination of computing functions, for example, including one or more microprocessor combinations, a combination of a DSP and a microprocessor, and the like.
  • the communication module 1002 may be a communication port or may be a transceiver, a transceiver circuit, a communication interface, or the like.
  • the display module 1003 can be the display 204 in the physical structure of the device 20 that generates the thermogram shown in FIG.
  • the storage module 1004 can be the memory 202 in the physical structure of the device 20 that generates the thermogram shown in FIG.
  • the device 20 for generating a heat map may be the device 20 for generating a heat map shown in FIG. .
  • the steps of a method or algorithm described in connection with the present disclosure may be implemented in a hardware or may be implemented by a processor executing software instructions.
  • the software instructions may be composed of corresponding software modules, which may be stored in RAM, flash memory, ROM, Erasable Programmable ROM (EPROM), and electrically erasable programmable read only memory (Electrically EPROM).
  • EEPROM electrically erasable programmable read only memory
  • registers hard disk, removable hard disk, compact disk read only (CD-ROM) or any other form of storage medium known in the art.
  • An exemplary storage medium is coupled to the processor to enable the processor to read information from, and write information to, the storage medium.
  • the storage medium can also be an integral part of the processor.
  • the processor and the storage medium can be located in an ASIC. Additionally, the ASIC can be located in a core network interface device.
  • the processor and the storage medium may also exist as discrete components in the core network interface device.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another The system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the software functional unit described above is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform portions of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, and the program code can be stored. Medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Control Of Indicators Other Than Cathode Ray Tubes (AREA)
  • Image Processing (AREA)
  • Radiation Pyrometers (AREA)

Abstract

一种生成热力图的方法及装置，涉及热力图生成，包括：将原始图像在屏幕中的当前显示区域划分为边长为r的方形单元格（S301）；根据原始图像的统计数据及本次生成热力图的热力权重w，分别计算每个单元格内，以单元格中心点为圆心以x为半径的的热力点区域的基本热力H（S302）；分别根据每个单元格的热力点区域的基本热力H，计算当前显示区域中每个像素点受到的扩散热力（S303）；根据当前显示区域中每个像素点的基本热力及受到的扩散热力，分别获取当前显示区域中每个像素点的总热力（S304）；按照预设的热力呈现对应关系，在原始图像的当前显示区域中，呈现每个像素点的总热力对应的颜色，得到当前显示区域的热力图（S305）。利用上述方法，实现热力图连续准确的反应区域的特征，且图像缩放比例的变化不影响热力图的连续性及准确性。

Description

一种生成热力图的方法及装置
本申请要求于2016年08月19日提交中国专利局、申请号为201610697944.8、发明名称为“一种生成热力图的方法及装置”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
本申请涉及图像处理领域，尤其涉及一种生成热力图的方法及装置。
背景技术
随着互联网技术及电子技术的飞速发展，互联网及智能终端已经成为人们日常生活不可或缺的内容。例如，通过互联网访问网页浏览所需信息、通过电子地图查询位置或者导航线路等。
用户的使用信息(地图中的定位信息、网页中的点击位置)，可以聚合为密度数据，描述在某一个时间点或时间段内区域的密度，描述了区域位置与人数或点击次数的对应关系。采用密度数据，可以为用户提供诸多便利。比如，在电子地图中采用密度数据可以预测道路的拥堵状况、地点的拥挤状况，而将不同时间的密度数据聚合整理之后，又可以进一步展示诸如人口居住地分布、工作地分布等等信息与规律。
热力图技术通过将数值用连续或离散的色阶来标识，可以将某一变量在二维空间的分布及变化规律自然生动的展示出来，因此，热力图被应用于各种场景中以呈现密度数据，反应区域的特征。比如，用热力图在电子地图中以色阶呈现不同区域的密度数据，可以清楚的在地图上呈现数据密集的“热区”以及数据稀疏的“冷区”，从而展示诸如人口分布的重要统计信息。采用热力图体现网页中区域与用户点击数量的对应关系，便于网站管理人员确定用户经常点击但不是链接的区域，考虑在该区域放置资源链接。
目前，通常在比例尺适合的图像中，根据密度数据采用描点法绘制热力图。常用的绘制方法是一个数据点绘制一个热力点，或者，一个区域内的数据总和绘制一个热力点。在此基础的热力图上，一旦图像比例尺变化，热力图将不能连续且准确的反应区域的特征。
以电子地图中应用热力图为例，电子地图的特点是对于地理位置信息完整且连续，但现有的热力图技术生成的热力图，当用户放大地图，热力图的呈现效果为散点图，整体不能反映密度数据在不同区域内的分布规律。当地图被缩小到一定等级，热力图的呈现为一个大热力点，该点的覆盖区域甚至超过实际数据的覆盖区域，无实际意义。
由此可知，现有的热力图技术生成的热力图，在调整图像的缩放比例时，热力图无法准确的体现图像的实际分布特征及区域的特征。并且热力图连续性差。
发明内容
本发明实施例提供一种生成热力图的方法及装置，实现热力图连续准确的反应区域的特征，图像缩放比例的变化不影响热力图的连续性及准确性。
为达到上述目的，本申请采用如下技术方案：
第一方面，提供一种生成热力图的方法，所述方法包括：先将原始图像在屏幕中的当前显示区域划分为边长为r＝α*r1的方形单元格；然后根据原始图像的包括至少一个用于反映原始图像区域特征的数据点的统计数据及本次生成热力图的热力权重w＝β*w1，分别计算每个单元格内，以单元格中心点为圆心以x为半径的热力点区域的基本热力H，x小于或等于
Figure PCTCN2017077942-appb-000001
一个热力点区域中每个像素点的基本热力为H；再分别根据每个单元格的热力点区域的基本热力，计算当前显示区域中每个像素点受到的扩散热力，处于至少一个单元格的扩散热力区域中的一个像素点受到的扩散热力由所述至少一个单元格中每个单元格的热力点区域产生；在此基础上，根据当前显示区域中每个像素点的基本热力及受到的扩散热力，分别获取当前显示区域中每个像素点的总热力；最后按照预设的热力呈现对应关系，在原始图像的当前显示区域中，呈现当前显示区域中每个像素点的总热力对应的颜色，得到当前显示区域的热力图。
其中，r1为对原始图像前一次生成热力图时划分的单元格的边长；α是与缩放比例相关的单元格变化函数。w1为原始图像前一次生成热力图时的热力权重；β是与缩放比例相关的热力权重变化函数。原始图像的统计数据包括至少一个用于反映原始图像区域特征的数据点。一个单元格的扩散热力区域为，以所述一个单元格的中心为圆心，以R为半径的圆中除所述一个单元格的热力点区域之外的区域；所述R大于r。热力呈现对应关系包括了热力区间及与每个热力区间一一对应的颜色。
通过本申请提供的生成热力图的方法，首先，在每次生成热力图时，每个单元格的热力点区域及扩散热力区域可以包括原始图像的当前显示区域中每个位置及细节，无论用户对原始图像的缩放比例如何调整，每一次生成的热力图都是连续的，保证了热力图的连续性，使得热力图可以反映区域的特征；其次，在本地生成热力图时，单元格的边长r及热力权重w，分别通过单元格变化函数α、热力权重变化函数β，与上次生成热力图时的单元格的边长r1及热力权重w1相关，在此基础上，通过合理设置单元格变化函数α、热力权重变化函数β，可以保证每次生成热力图时一个单元格在原始图像中对应的区域面积相近、每次生成热力图时原始图像中同一个区域内热力相近，无论用户对原始图像的缩放比例如何调整，对于原始图像中的同一位置，每次生成 的热力图中该位置的热力值均接近，保证了热力图的准确性。
进一步的，本申请采用划分单元格后生成热力图的方法，在数据量庞大时，相比与现有技术中的描点法，大大提高了处理效率，节约了处理时间，减少了生成热力图时用户的等待时间。
其中，原始图像是生成热力图的基础，生成的热力图即反应原始图像的区域特征。原始图像在屏幕中的当前显示区域，为用户在当前缩放比例下在终端屏幕中看到的原始图像中的区域，即原始图像在终端界面上显示的区域。
一个单元格的热力点区域，是指这个单元格内预定的以单元格中心点为圆心以x为半径的区域。单元格的热力点区域用于在热力图中，向用户呈现原始图像的统计数据中，坐标位于该单元格在原始图像中对应的区域内的数据点的产生的热力，该热力称之为该单元内的热力点区域的基本热力。在通过单元格的热力点区域呈现基本热力时，通过单元格的热力点区域中每个像素点的基本热力来呈现，单元格的热力点区域中每个像素点的基本热力与单元格的热力点区域相等。
一个单元格的扩散热力区域，是指单元格的热力点区域向外辐射的热力到达的区域。一个单元格的扩散热力区域定义为以该单元格中心为圆心，以R为半径的区域中，除去该单元格热力点区域之外的区域。一个单元格的热力点区域向该单元格的扩散热力区域中每个像素点产生扩散热力。处于至少一个单元格的扩散热力区域的像素点，受到至少一个单元格中每个单元格的扩散热力分量。根据像素点受到的所有扩散热力分量计算得到像素点受到的扩散热力。
其中，x可以为
Figure PCTCN2017077942-appb-000002
结合第一方面，在一种可能的实现方式中，为了获取更精细的热力图，准确的反应区域内统计对象的特征，可以对统计对象或者数据点配置权值，以使得获取的热力值产生尽可能大的差值可以用不同的颜色体现。在生成热力图时，对于根据原始图像的统计数据及本次生成热力图的热力权重w，分别计算每个单元格内，以单元格中心点为圆心以x为半径的热力点区域的基本热力H的过程，每个单元格的处理方式相同，此处以原始图像当前显示区域中的任一个单元格(称为第一单元格)为例，描述根据原始图像的统计数据及本次生成热力图的热力权重w，计算第一单元格内，以第一单元格中心点为圆心以x为半径的热力点区域的基本热力H的具体过程为：计算第一单元格的热力点区域的基本热力H＝N*w。其中，N为原始图像的统计数据中，坐标位于第一单元格在原始图像中对应的区域内的数据点或统计对象的总数量。
其中，统计对象是在原始图像中获取用于数据分析的数据点时的目标个体，数据点是指原始图像中对于统计对象进行数据统计后，生成的包括位置与统计参数的二元组数据。
具体的，对于N的类型，取决于w的定义。若w定义为数据点的热力值 权重，则N为原始图像的统计数据中，坐标位于第一单元格在原始图像中对应的区域内的数据点的总数量；若w定义为统计对象的热力值权重，则N为原始图像的统计数据中，坐标位于第一单元格在原始图像中对应的区域内的统计对象的总数量。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，为了准确并精细的将原始图像当前显示区域中每个位置热力准确反应在在热力图中，当前显示区域中的像素点会受到其周围单元格中热力点区域产生的扩散热力的影响。一个单元格的热力点区域对距离其中心点越近的像素点产生的扩散热力越大。因此，根据像素点位置到单元格中心的距离计算的扩散热力可以更准确的体现实际数据分布。具体的，在生成热力图时，对于计算当前显示区域中每个像素点受到的扩散热力的过程相同，本实现方式中，以当前显示区域中处于至少一个单元格的扩散热力区域的任一个像素点(称为第一像素点)为例，描述计算第一像素点受到的扩散热力的具体过程。具体实现为：先根据每个单元格的热力点区域的基本热力，计算第一像素点受到每个单元格的热力点区域的扩散热力分量，然后将第一像素点受到的至少一个扩散热力分量的加权和，作为第一像素点受到的扩散热力；其中，第一像素点受到的至少一个扩散热力分量，为第一像素点所处的至少一个扩散热力区域所属的每个单元格产生。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，对于计算第一像素点受到每个单元格的热力点区域的扩散热力分量的过程相同，此处描述计算第一像素点受到第二单元格的热力点区域的扩散热力分量的过程：计算第一像素点受到第二单元格的扩散热力分量
Figure PCTCN2017077942-appb-000003
其中，第二单元格为第一像素点所处的至少一个扩散热力区域所属的单元格中任一个单元格；d为第一像素点位置到第二单元格中心的距离；H为第二单元格的热力点区域的基本热力。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，当前显示区域中处于一个单元格的热力点区域中，但不处于任一个单元格的扩散热力区域中的像素点受到的扩散热力，为该像素点的基本热力。
其中，像素点位置到单元格中心的距离是指当前显示区域中显示的距离d，与r相同的单位。或者，像素点位置到单元格中心的距离是指在原始图像中对应的实际距离，r也为单元格的边长在原始图像中对应的实际距离，只要d和r的单位距离表示的内容相同即可。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，为了实现不同缩放比例下，每次生成热力图时，单元格的边长r在原始图像中对应的距离相近，原始图像中同一区域内热力值相近，可以将α、β定 义为缩放比例的变化量ΔZ的相关函数。具体的，α＝aΔZ，a为预设的单元格变化参数，a大于或等于1，小于或等于2；β＝bΔZ，b为预设的热力权重变化参数，b大于或等于1，小于或等于4；ΔZ为本次生成热力图时对原始图像的缩放比例减去上次生成热力图时对原始图像的缩放比例。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，若在第一方面的方案执行时，即本次生成当前显示区域的热力图，是对原始图像首次生成热力图，不存在前一次生成热力图的情况，此时r1为单元格边长初始值r0，w1为热力权重初始值w0。r0及w0为预先设定值。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，为了使得定义的α实现在不同的缩放比例下，每次生成热力图时，单元格的边长r在原始图像中对应的距离相近，具体定义为：α用于控制r与r1在原始图像中对应的实际长度差值的绝对值小于或等于第一预设门限。为了使得定义的β实现在不同的缩放比例下，每次生成热力图时，原始图像中同一区域的热力值相近，具体定义为：β用于控制原始图像中同一区域在每次生成热力图时得到的总热力值的差值的绝对值小于或等于第二预设门限。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，在计算扩散热力时，需要合理定义扩散区域范围，以实现热力图既准确体现每个位置的热力，又节约运算资源，即需要设定合理的R。在本实现方式中，R小于或等于2r。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，对于原始图像当前显示区域中处于某个单元格的扩散热力区域的像素点，可能也处于一个单元的热力点区域，该像素点既有基本热力，还会受到其他单元格的扩散热力。具体的，对于原始图像当前显示区域中处于单元格的热力点区域的每个像素点，计算其总热力的过程相同，在本实现方式中，以原始图像当前显示区域中处于单元格的热力点区域的任一像素点(称为第二像素点)为例，描述根据基本热力及扩散热力，获取第二像素点的总热力具体实现为：将第二像素点受到的扩散热力及第二像素点的基本热力相加，得到第二像素点的总热力；或者，将第二像素点受到的扩散热力及第二像素点的基本热力加权相加，得到第二像素点的总热力。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，对于原始图像当前显示区域中处于某个单元格的热力点区域的像素点，可能不处于任一个单元的扩散热力区域，该像素点则只有基本热力，其总热力则为像素点的基本热力。
结合第一方面或上述任一种可能的实现方式，在另一种可能的实现方式中，对于原始图像当前显示区域中仅处于至少一个单元格的扩散热力区域但未处于任一单元格的热力点区域的像素点，该像素点的总热力则为受到扩散热力。具体的，对于原始图像当前显示区域中处于单元格扩散热力区域且不处于任一单元格的热力点区域的任一像素点，计算其总热力的过程相同。在本实现方式中，以原始图像当前显示区域中处于单元格扩散热力区域且不处 于任一单元格的热力点区域的任一像素点(称为第三像素点)为例，获取第三像素点的总热力具体实现为：所述第三像素点受到的扩散热力为所述第三像素点的总热力。
第二方面，本发明实施例提供了一种生成热力图的装置，该装置可以实现上述方法，所述装置的功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多个上述功能相应的模块。
结合第二方面，在一种可能的实现方式中，该装置的结构中包括处理器和收发器，该处理器被配置为支持该装置执行上述方法。该收发器用于支持该装置与其他网元之间的通信。该装置还可以包括存储器，该存储器用于与处理器耦合，其保存该装置必要的程序指令和数据。
第三方面，本发明实施例提供了一种计算机存储介质，用于储存为上述装置所用的计算机软件指令，其包含用于执行上述方面所设计的程序。
上述第二方面或第三方面提供的方案，用于实现上述第一方面提供的生成热力图的方法，因此可以与第一方面达到相同的有益效果，此处不再进行赘述。
附图说明
图1为现有技术中的一种互联网架构的结构示意图；
图2为本发明实施例提供的一种生成热力图的装置20的结构示意图；
图3为本发明实施例提供的一种生成热力图的方法的流程示意图；
图4为本发明实施例提供的一种单元格与热力点区域的位置示意图；
图5为本发明实施例提供的一种单元格与热力点区域及扩散热力区域的位置示意图；
图6为本发明实施例提供的一种像素点位置示意图；
图7为本发明实施例提供的另一种像素点位置示意图；
图8为本发明实施例提供的再一种像素点位置示意图；
图9为本发明实施例提供的另一种生成热力图的装置20的结构示意图；
图10为本发明实施例提供的再一种生成热力图的装置20的结构示意图。
具体实施方式
当前，通过采用描点法在固定缩放比例下生成热力图。当用户调整图像缩放比例时，热力图会随着缩放比例的变化而离散或者汇聚。导致热力图不能准确的反映区域的特征。
本申请的基本原理是：在生成热力图时，参考前一次生成热力图时的参数，以保证对于原始图像中的同一区域的面积及热力在不同缩放比例下相近，达到生成的热力图可以准确且连续的体现图像的区域特征。
本发明实施例提供的生成热力图的方法，应用于如图1所示的互联网架构中。该互联网架构中包括网络服务器101及至少一个终端102。
在图1所示的架构中，本发明实施例提供的生成热力图的方法具体应用于终端102上。网络服务器101通过统计每个终端102的用户数据，得到统计数据，提供给每一个终端102用于进行数据分析。终端102通过与网络服 务器101的通过互联网交互，获取到网络服务器101统计得到的统计数据以进行数据分析。
进一步的，终端102进行的数据分析可以包括生成热力图，供用户直观查看统计数据。
本发明实施例提供的生成热力图的方法，由本发明实施例提供的生成热力图的装置20实现，本发明实施例提供的生成热力图的装置20可以为图1所示的架构中终端102的部分或全部。
可选的，所述终端102可以为手机、平板电脑、笔记本电脑、个人计算机(英文全称：personal computer，PC)、超级移动个人计算机(英文全称：Ultra-mobile Personal Computer，UMPC)、上网本、个人数字助理(英文全称：Personal Digital Assistant，PDA)、车载设备等终端设备。
图2示出的是与本申请各实施例相关的一种生成热力图的装置20的结构示意图。
如图2所示，生成热力图的装置20可以包括：处理器201、存储器202、通信总线203及显示器204。
存储器202，用于存储程序代码，并将该程序代码传输给该处理器201，以便处理器201执行程序代码实现生成热力图的装置20的各种功能。存储器202可以是易失性存储器(volatile memory)，例如随机存取存储器(英文全称：random-access memory，RAM)；或者非易失性存储器(英文全称：non-volatile memory)，例如只读存储器(英文全称：read-only memory，ROM)，快闪存储器(英文全称：flash memory)，硬盘(英文全称：hard disk drive，HDD)或固态硬盘(英文全称：solid-state drive，SSD)；或者上述种类的存储器的组合。
处理器201是生成热力图的装置20的控制中心，可以是一个中央处理器(英文全称：central processing unit，CPU)，也可以是特定集成电路(英文全称：Application Specific Integrated Circuit，ASIC)，或者是被配置成实施本发明实施例的一个或多个集成电路，例如：一个或多个微处理器(英文全称：digital singnal processor，DSP)，或，一个或者多个现场可编程门阵列(英文全称：Field Programmable Gate Array，FPGA)。处理器201可以通过运行或执行存储在存储器202内的程序代码，以及调用存储在存储器202内的数据，实现生成热力图的装置20的各种功能。
其中，通信总线203可以是工业标准体系结构(英文全称：Industry Standard Architecture，ISA)总线、外部设备互连(英文全称：Peripheral Component，PCI)总线或扩展工业标准体系结构(英文全称：Extended Industry Standard Architecture，EISA)总线等。该总线203可以分为地址总线、数据总线、控制总线等。为便于表示，图2中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
显示器204可以为终端102的屏幕，用于向用户呈现热力图。
下面结合附图，对本申请的实施例进行具体阐述。
在描述之前，先对一些基础概念进行解释。
一个单元格的热力点区域，是指这个单元格内预定的以单元格中心点为圆心以x为半径的区域。单元格的热力点区域用于在热力图中，向用户呈现原始图像的统计数据中，坐标位于该单元格在原始图像中对应的区域内的数据点的产生的热力，该热力称之为该单元内的热力点区域的基本热力。在通过单元格的热力点区域呈现基本热力时，通过单元格的热力点区域中每个像素点的基本热力来呈现，单元格的热力点区域中每个像素点的基本热力与单元格的热力点区域相等。
一个单元格的扩散热力区域，是指单元格的热力点区域向外辐射的热力到达的区域。一个单元格的扩散热力区域定义为以该单元格中心为圆心，以R为半径的区域中，除去该单元格热力点区域之外的区域。一个单元格的热力点区域向该单元格的扩散热力区域中每个像素点产生扩散热力。处于至少一个单元格的扩散热力区域的像素点，受到至少一个单元格中每个单元格的扩散热力分量。根据像素点受到的所有扩散热力分量计算得到像素点受到的扩散热力。
一方面，本发明实施例提供一种生成热力图的方法，如图3所示，所述方法可以包括：
S301、将原始图像在屏幕中的当前显示区域划分为边长为r的方形单元格。
其中，原始图像在屏幕中的当前显示区域，是指原始图像在当前缩放比例下，在终端的屏幕中可以被用户看到的区域。
其中，r＝α*r1，r1为原始图像前一次生成热力图时划分的单元格的边长。所述*为乘法计算。
需要说明的是，在执行S301时，若在划分单元格时，原始图像的当前显示区域的边界处剩余区域的边长不足r，则将不足r的部分作为一个单元格，即在划分边长为r的方形单元格时，最大限度保证单元格的边长为r。具体的，在执行S301时，划分单元格时边长不足r的剩余区域是在当前显示区域的上边界还是下边界，或者在左边界还是右边界，可以根据实际需求设定，本发明实施例对此不进行具体限定。只需要在每一次生成热力图时采用相同的方式处理边长不足r的剩余区域。
进一步的，若执行S301时，是对原始图像首次生成热力图，即若本次生成热力图为对原始图像首次生成热力图，则r1为单元格边长初始值r0。
需要说明的是，对于r0的取值，可以根据实际需求或者经验值设定，本发明实施例对此不进行具体限定。
其中，α是与缩放比例相关的单元格变化函数，用来控制热力图离散化的速度，通过设定合适的α函数，可以控制连续两次对原始图像生成热力图时划分的单元格的边长满足一定的关系。
进一步的，所述α用于控制r与r1在原始图像中对应的实际长度差值的绝对值小于或等于第一预设门限。
需要说明的是，对于第一预设门限的取值，可以根据实际需求设定，本申请对此不进行具体限定。具体的，第一预设门限设定的越小，热力图在缩放比例大的情况下呈现效果则更稳定，但难以对于图像细节做足够补充；第一预设门限设定的越大，生成的热力图将会显示额外细节信息，但图像整体的稳定性及连续性较差。在实际应用中，可以根据实际需求，折中设定第一预设门限的取值。
可选的，对于α与缩放比例的函数关系，可以有多种形式的幂函数。
可选的，此处示例一种α与缩放比例的幂函数关系，具体包括：α＝aΔZ。
其中，a为预设的单元格变化参数，a大于或等于1，小于或等于2；ΔZ为本次生成热力图时对原始图像的缩放比例减去上次生成热力图时对原始图像的缩放比例。
需要说明的是，对于a的取值，可以根据实际需求设定。
具体的，当a＝1时，单元格边长没有变化，单元格在原始图像中对应的面积大小不随缩放比例的变化而变化，热力图将会显示额外细节信息，但图像整体的稳定性及连续性较差；当a＝2时，单元格的边长随着缩放比例的变化而变化，单元格在原始图像中对应的面积大小不随缩放比例的变化而变化，即单元格表示的图像中的实际区域一定，热力图在放大操作下呈现效果稳定，但难以对于细节做足够补充或忽略。
示例性的，以原始图像为电子地图，假设用户将地图放大一级(ΔZ则为1)，地图上同样大小的单元格所表示的实际面积仅为原来的1/4。如果数据点分布均匀，单元格内的数据总量会相应的变为原来的约1/4。为适应这一变化，保证本地生成热力图时，单元格内的数据总量与上一次生成热力图时一个单元格内的数据总量相近，单元格的边长r则需要做出相应改变。若r＝aΔZ*r1，ΔZ则＝1，即单元格的边长变为上一次的a倍，地图上同样大小的单元格所表示的实际面积则为原来的
Figure PCTCN2017077942-appb-000004
倍。此时，若a取1，则地图上同样大小的单元格所表示的实际面积则为原来的1/4；若a取2，地图上同样大小的单元格所表示的实际面积则为原来的1倍，即两次生成热力图时划分的单元格在电子地图中对应的实际面积相等。
优选的，所述a为1.6。
进一步的，对于α与ΔZ的幂函数的关系，还可以根据实际需求在幂函数的部分之外，添加常数或者关于Z的指数函数来进行变形。
示例性的，α＝aΔZ+c。
其中，c可以为常数，也可以用关于Z的指数函数。
S302、根据原始图像的统计数据及本次生成热力图的热力权重w＝β*w1， 分别计算每个单元格内，以单元格中心点为圆心以x为半径的热力点区域的基本热力H。
其中，一个热力点区域中每个像素点的基本热力为H。
具体的，原始图像的统计数据包括至少一个用于反映原始图像区域特征的数据点。原始图像的统计数据可以由执行本申请生成热力图的方法的装置与网络服务器通过互联网交互获取，统计数据中网络服务器原始图像监控后生成的至少一个数据点。本申请对于原始图像的统计数据的内容及获取过程不再进行赘述。可选的，数据点可以为区域的统计对象密度。
其中，x小于或等于
Figure PCTCN2017077942-appb-000005
对于x的取值，可以根据实际需求设定。优选x等于
Figure PCTCN2017077942-appb-000006
当然，x也可以为接近
Figure PCTCN2017077942-appb-000007
且小于
Figure PCTCN2017077942-appb-000008
的值。本申请实施例对于x的取值不进行具体限定。
具体的，w1为原始图像前一次生成热力图时的热力权重。
其中，热力权重是在生成热力图时，为了在计算热力时方便，以及让计算出的热力值拉开距离以便于用不同的颜色示意，而为数据点(二元组数据)或者统计对象设置的权重系数。
进一步的，若执行S302时，是对原始图像首次生成热力图，若本次生成热力图为对原始图像首次生成热力图，则w1为热力权重初始值w0。
需要说明的是，对于w0的取值，可以根据实际需求或者经验值设定，本发明实施例对此不进行具体限定。
其中，β是与缩放比例相关的热力权重变化函数，用来维持热力图的稳定性，通过设定合适的β函数，可以控制连续两次原始图像中同一区域内的热力满足一定的关系。
进一步的，所述β用于控制原始图像中同一区域在每次生成热力图时得到的总热力值的差值的绝对值小于或等于第二预设门限。
需要说明的是，对于第二预设门限的取值，可以根据实际需求设定，本申请对此不进行具体限定。第二预设门限设定的越小，则生成的热力图连续性越好，原始图像中同一区域在缩放比例不同的热力图中呈现的颜色相同或接近。
具体的，若α已选定，原始图像放大一级后，每个单元格所代表的实际面积将变为原来的
Figure PCTCN2017077942-appb-000009
倍，单元格中的数据点数量以及热力值也会随之变化，必须计算相应的β以确保在不同缩放比例下的热力图的稳定。此稳定性定义如下：在理想情况下，若数据点在某一单元格所代表的实际区域内的分布均匀， 则无论地图放大或缩小，该实际区域的热力值应保持不变。
可选的，对于β与缩放比例的函数关系，可以有多种形式，比如可以为线性函数、幂函数或者其他。
可选的，此处示例一种β与缩放比例的幂函数关系，具体包括：β＝bΔZ。
其中，b为预设的热力权重变化参数，b大于或等于1，小于或等于4。
需要说明的是，对于b的取值，可以根据实际需求确定。具体的，b的作用是使热力图的热力变得稳定，因此b的取值与a的取值相关。若原始图像放大一级，也就值Z增加1的情况，当a＝2时，每个单元格代表的实际面积不变，每个数据点的权重w也不用变化，b＝1即可；当a＝1时，每个单元格代表的面积变为之前的
Figure PCTCN2017077942-appb-000010
如果不考虑扩散热力的影响，应该使得w也变为之前的4倍才能使热力稳定，即b＝4。
可选的，对于b的确定方法可以如下：比较两级缩放比例i与(i+1)，若i级中某一个窗格的热力值为H，所代表的地理区域为A。那么在(i+1)级中，A的热力将会由
Figure PCTCN2017077942-appb-000011
个小单元格的基本热力以及作于用A之内的扩散热力构成，同时每个数据点的热力贡献值会变成原来的b倍，最终得出的(i+1)级中A的热力值H’可以用积分得出并且符合H＝H’的关系，由此可以计算出b的取值。
需要说明的是，在确定b时，这一数值的取得可以通过计算或根据经验，反复测试和调整得到。
上述确定b的方法，只是一种实现形式，并不是对于b的取值的具体限定，还可以有其他确定b的取值的方法，只需要保证确定出的b的取值可以实现β的功能即可。
优选的，所述b为1.3。
具体的，定义一个单元格的热力点区域为单元格内，以单元格中心点为圆心以x为半径的区域，该区域中每个像素点的基本热力值相等，均为该单元格热力点区域的基本热力。
如图4所示，示意了单元格的热力点区域，图中方形区域为单元格，圆形区域为该单元格的热力点区域。在该示例中，x为
Figure PCTCN2017077942-appb-000012
具体的，对于S301中划分的每一个单元格，在S302中的执行过程是相 同的，此处以S301中划分的任一个单元格(称为第一单元格)为例，描述在S302中，根据原始图像的统计数据及本次生成热力图的热力权重w，计算第一单元格内，以第一单元格中心点为圆心以x为半径的热力点区域的基本热力的过程。
可选的，一种根据原始图像的统计数据及本次生成热力图的热力权重w，计算第一单元格内，以第一单元格中心点为圆心以x为半径的热力点区域的基本热力的过程具体可以包括：
计算第一单元格的热力点区域的基本热力H＝N*w。
其中，N为原始图像的统计数据中，坐标位于第一单元格在原始图像中对应的区域内的数据点或统计对象的总数量。
示例性的，以原始图像为电子地图为例，假设某一个单元格覆盖了整个天安门区域，这个范围内有两个数据点，天安门城楼附近有5个人(统计对象)，广场附近有20个人，每一个人的热力权重是w′，那这个单元格的热力点区域的基本热力H为5w′+20w′＝25w′。
示例性的，以原始图像为电子地图为例，假设某一个单元格覆盖了整个天安门区域，这个范围内有两个数据点，每个数据点的热力权重是w″，那这个单元格的热力点区域的基本热力H为2w″。
可选的，另一种根据原始图像的统计数据及本次生成热力图的热力权重w，计算第一单元格的热力点区域的基本热力的过程具体可以包括：
计算第一单元格的热力点区域的基本热力H＝N*w+q。
其中，q为预设的常数，可以根据实际需求设定，本发明实施例对此不进行具体限定。
需要说明的是，计算单元格的热力点区域的基本热力的方法，还可以通过上述两种方法之外的其他方法实现，本发明实施例对此不进行具体限定。
S303、分别根据每个单元格的热力点区域的基本热力H，计算当前显示区域中每个像素点受到的扩散热力。
其中，一个单元格的扩散热力区域为，以这个单元格的中心为圆心，以R为半径的圆中除该单元格的热力点区域之外的区域；R大于r。
具体的，处于至少一个单元格的扩散热力区域中的一个像素点受到的扩散热力由所述至少一个单元格中每个单元格的热力点区域产生。
示例性的，如图5所示，示意了单元格、热力点区域及扩散热力区域之间的关系。
优选的，为了有效的计算，可以限制定义单元格的扩散热力区域的R小于或等于2r。
具体的，对于当前显示区域中任一个像素点，若处于至少一个单元格的扩散热力区域中，则会受到该至少一个单元格中每个单元格的扩散热力分量。对于当前显示区域中任一个像素点，若不处于任一单元格的扩散热力区域中，则不会受到任一个单元格的扩散热力分量，这一类像素点受到的扩散热力则为零。
可选的，计算当前显示区域中每一个像素点受到的扩散热力的过程中，不处于任一单元格的扩散热力区域中的像素点受到的扩散热力则为零。处于至少一个单元格的扩散热力区域中的像素点受到的扩散热力计算得到。
可选的，计算当前显示区域中每一个像素点受到的扩散热力的过程中，可以仅计算处于至少一个单元格的扩散热力区域中的像素点受到的扩散热力。
具体的，计算当前显示区域中处于至少一个单元格的扩散热力区域中每一个像素点受到的扩散热力的过程相同，此处不在一一赘述，此处仅以当前显示区域中处于至少一个单元格的扩散热力区域中任一个像素点(称为第一像素点)为例，描述在S303中，根据每个单元格的热力点区域的基本热力，计算第一像素点受到的扩散热力的过程。
进一步的，计算第一像素点受到的扩散热力的过程具体可以包括：先计算第一像素点受到每个单元格的扩散热力分量；将第一像素点受到的至少一个扩散热力分量的加权和，作为第一像素点受到的扩散热力。
需要说明的是，对于计算第一像素点受到的扩散热力时，加权时的权值，可以根据实际需求设定，本发明实施例对此不进行具体限定。
示例性的，计算第一像素点受到的扩散热力时，加权时的权值可以与像素点离单元格中心的距离成正比。
可选的，对于计算第一像素点受到的扩散热力时，加权时的权值，可以为1，使得第一像素点受到的扩散热力为第一像素点受到的至少一个扩散热力分量的和。
其中，第一像素点受到的至少一个扩散热力分量，为第一像素点所处的至少一个扩散热力区域所属每个单元格产生。
需要说明的是，计算第一像素点受到每个单元格的扩散热力分量的过程相同，此处不再进行一一赘述。仅以计算第一像素点受到第二单元格的扩散热力分量的过程示例说明。第二单元格为第一像素点所处的至少一个扩散热力区域所属的单元格中任一个单元格。
可选的，一种计算第一像素点受到第二单元格的扩散热力分量的方法，具体可以包括：
计算第一像素点受到第二单元格的扩散热力分量
Figure PCTCN2017077942-appb-000013
其中，d为第一像素点位置到第二单元格中心的距离。H为第二单元格的热力点区域的基本热力。
具体的，d为像素点的位置在当前显示区域中，与单元格中心的距离，与单元格边长r的单位一致。d也可以为像素点的位置在原始图像中，与单元格中心的实际距离，只要与r的内容一致即可。
需要说明的是，对于H的计算方式，已经在S302中进行了详细描述，此处不再进行赘述。
可选的，一种计算第一像素点受到第二单元格的扩散热力分量的方法，具体可以包括：
计算第一像素点受到第二单元格的扩散热力分量
Figure PCTCN2017077942-appb-000014
其中，π可以为3.14。
需要说明的是，计算第一像素点受到第二单元格的扩散热力分量的函数，可以根据实际需求设定，该函数只要保证从1到0的单调减即可。
进一步的，对于处于多个单元格的扩散热力区域的像素点，会受到这些单元格中每个单元格的扩散热力分量，则需要一一计算。
需要说明的是，计算像素点受到单元格的扩散热力分量，还可以通过上述两种方法之外的其他方法实现，本发明实施例对此不进行具体限定。
S304、根据当前显示区域中每个像素点的基本热力及受到的扩散热力，分别获取当前显示区域中每个像素点的总热力。
具体的，对于当前显示区域中处于单元格的热力点区域中的像素点，既有基本热力，也可能会受到其他单元格的扩散热力，这一类像素点的总热力与基本热力及受到的扩散热力相关。
进一步的，对于处于单元格的热力点区域中的每个像素点，在S304中获取其总热力的执行过程是相同的。此处以处于单元格的热力点区域中的任一个像素点(称为第二像素点)为例，描述在S304中，获取第二像素点的总热力的过程。
可选的，获取第二像素点的总热力的具体实现方式，可以包括但不限于下述两种方式：
方式1：
将第二像素点受到的扩散热力及第二像素点的基本热力相加，得到第二像素点的总热力。
示例性的，如图6所示，假设像素点A处于1个单元格的热力点区域，其基本热力为H，像素点A还处于4个单元格的扩散热力区域中，像素点A将会受到这4个单元格的热力点区域对其的扩散热力分量，分别记录为h1、h2、h3、h4，像素点A受到的扩散热力为h1+h2+h3+h4，那么像素点A的总热力则为H+h1+h2+h3+h4。
方式2：
将第二像素点受到的扩散热力及第二像素点的基本热力加权相加，得到第二像素点的总热力。
需要说明的是，方式2与方式1具体实现相似，此处不再详细描述。对于上述方式2中加权时的权值，可以根据实际需求设定，本发明实施例对此不进行具体限定。
需要说明的是，在上述获取第二像素点的总热力时，若第二像素点不处于任一单元格的扩散热力区域中，第二像素点的总热力则为第二像素点的基 本热力。
具体的，对于当前显示区域中的另一类像素点，可能处于至少一个单元格的扩散热力区域且不处于任一单元格的热力点区域。对于这一类像素点，只会受到其他单元格的扩散热力，其总热力与受到的扩散热力相关。
进一步的，对于处于单元格扩散热力区域且不处于任一单元格的热力点区域的每个像素点，在S304中获取其总热力的执行过程是相同的。此处以处于单元格扩散热力区域且不处于任一单元格的热力点区域的任一个像素点(称为第三像素点)为例，描述在S304中，获取第三像素点的总热力的过程。
具体的，获取第三像素点的总热力的具体实现，可以包括：第三像素点受到的扩散热力为第三像素点的总热力。
示例性的，如图7所示，假设像素点B位于4个单元格的扩散热力区域中且不处于任一单元格的热力点区域，像素点B将会受到这4个单元格的热力点区域对其的扩散热力分量，分别记录为h1、h2、h3、h4，像素点B受到的扩散热力为h1+h2+h3+h4，那么像素点B的总热力则为h1+h2+h3+h4。
示例性的，如图8所示，假设像素点C只位于1个单元格的扩散热力区域中且不处于任一单元格的热力点区域，像素点C将会只受到这个单元格的热力点区域对其的扩散热力分量，那么像素点C的总热力则为受到的这个单元格的热力点区域对其的扩散热力分量。
S305、按照预设的热力呈现对应关系，在原始图像的当前显示区域中，呈现每个像素点的总热力对应的颜色，得到当前显示区域的热力图。
其中，预先设定的热力呈现对应关系中，包含了至少一个热力数值区间及与每一个热力数值区间一一对应的呈现颜色。
如表1所示，示意了一种预设的热力呈现对应关系。
表1
热力数值区间 呈现颜色
0≤H＜10 颜色1
10≤H＜20 颜色2
20≤H＜30 颜色3
30≤H＜40 颜色4
…… ……
其中，预设的热力呈现对应关系中的呈现颜色可以随着热力的增大而加深，呈现颜色可以通过色调、饱和度、亮度等来体现。
需要说明的是，表1只是通过举例的形式对预设的热力呈现对应关系的内容及形式进行说明，并不是对预设的热力呈现对应关系的内容及形式的具体限定。
具体的，在S305中，先查询在预设的热力呈现对应关系，获取原始图像当前显示区域中每个像素点的总热力对应的颜色，然后在原始图像的当前显 示区域中，显示每个像素点的总热力对应的颜色，得到当前显示区域的热力图。
进一步的，当用户调整原始图像的缩放比例后，原始图像的当前显示区域将发生变化，重新执行本申请提供的生成热力图的方法S301至S305，生成变化后的当前显示区域的热力图，两次生成的热力图显示连续无离散点，原始图像中的同一位置在两次生成的热力图中呈现相同或相近的颜色。
通过本申请提供的生成热力图的方法，首先，在每次生成热力图时，每个单元格的热力点区域及单元格的扩散热力区域可以包括原始图像的当前显示区域中每个位置及细节，无论用户对原始图像的缩放比例如何调整，每一次生成的热力图都是连续的，保证了热力图的连续性，使得热力图可以反映区域的特征；其次，在本地生成热力图时，单元格的边长r及热力权重w，分别通过单元格变化函数α、热力权重变化函数β，与上次生成热力图时的单元格的边长r1及热力权重w1相关，在此基础上，通过合理设置单元格变化函数α、热力权重变化函数β，可以保证每次生成热力图时一个单元格在原始图像中对应的区域面积相近、每次生成热力图时原始图像中同一个区域内热力相近，无论用户对原始图像的缩放比例如何调整，对于原始图像中的同一位置，每次生成的热力图中该位置的热力值均接近，保证了热力图的准确性。
上述主要从生成热力图的装置的工作过程的角度对本发明实施例提供的方案进行了介绍。可以理解的是，生成热力图的装置为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本发明实施例可以根据上述方法示例对生成热力图的装置进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本发明实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
在采用对应各个功能划分各个功能模块的情况下，图9示出了上述实施例中所涉及的生成热力图的装置20的一种可能的结构示意图，生成热力图的装置20包括：划分单元901，计算单元902，获取单元903，呈现单元904。划分单元901用于支持生成热力图的装置20执行图3中的过程S301，计算单元902用于支持生成热力图的装置20执行图3中的过程S302、S303；获取单元903用于支持生成热力图的装置20执行图3中的过程S304；呈现单元904用于支持生成热力图的装置20执行图3中的过程S305。其中，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描 述，在此不再赘述。
在采用集成的单元的情况下，图10示出了上述实施例中所涉及的生成热力图的装置20的一种可能的结构示意图。生成热力图的装置20可以包括：处理模块1001、通信模块1002和显示模块1003。处理模块1001用于对生成热力图的装置20的动作进行控制管理。例如，处理模块1001用于支持生成热力图的装置执行图3中的过程S301至S305，和/或用于本文所描述的技术的其它过程。通信模块1002用于支持生成热力图的装置20与其他网络实体的通信。显示模块1003用于支持生成热力图的装置执行图3中的过程S305。生成热力图的装置20还可以包括存储模块1004，用于存储生成热力图的装置20的程序代码和数据。
其中，处理模块1001可以为图2所示的生成热力图的装置20的实体结构中的处理器201，可以是处理器或控制器，例如可以是CPU，通用处理器，DSP，ASIC，FPGA或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合。其可以实现或执行结合本申请公开内容所描述的各种示例性的逻辑方框，模块和电路。所述处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和微处理器的组合等等。通信模块1002可以是通信端口，或者可以是收发器、收发电路或通信接口等。显示模块1003可以是图2所示的生成热力图的装置20的实体结构中的显示器204。存储模块1004可以是图2所示的生成热力图的装置20的实体结构中的存储器202。
当处理模块1001为处理器，显示模块1003为显示器204，存储模块1004为存储器时，本发明实施例图10所涉及的生成热力图的装置20可以为图2所示的生成热力图的装置20。
结合本申请公开内容所描述的方法或者算法的步骤可以硬件的方式来实现，也可以是由处理器执行软件指令的方式来实现。软件指令可以由相应的软件模块组成，软件模块可以被存放于RAM、闪存、ROM、可擦除可编程只读存储器(Erasable Programmable ROM，EPROM)、电可擦可编程只读存储器(Electrically EPROM，EEPROM)、寄存器、硬盘、移动硬盘、只读光盘(CD-ROM)或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可向该存储介质写入信息。当然，存储介质也可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。另外，该ASIC可以位于核心网接口设备中。当然，处理器和存储介质也可以作为分立组件存在于核心网接口设备中。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个 系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理包括，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，简称ROM)、随机存取存储器(Random Access Memory，简称RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (18)

  1. 一种生成热力图的方法，其特征在于，所述方法包括：
    将原始图像在屏幕中的当前显示区域划分为边长为r的方形单元格；其中，所述r＝α*r1；所述r1为所述原始图像前一次生成热力图时划分的单元格的边长；所述α是与缩放比例相关的单元格变化函数；
    根据所述原始图像的统计数据及本次生成热力图的热力权重w＝β*w1，分别计算每个单元格内，以单元格中心点为圆心以x为半径的热力点区域的基本热力H；其中，一个热力点区域中每个像素点的基本热力为H；所述统计数据包括至少一个用于反映所述原始图像区域特征的数据点；所述w1为所述原始图像前一次生成热力图时的热力权重；所述β是与缩放比例相关的热力权重变化函数；所述x小于或等于
    Figure PCTCN2017077942-appb-100001
    分别根据每个单元格的热力点区域的基本热力H，计算所述当前显示区域中每个像素点受到的扩散热力；其中，处于至少一个单元格的扩散热力区域中的一个像素点受到的扩散热力由所述至少一个单元格中每个单元格的热力点区域产生；一个单元格的扩散热力区域为，以所述一个单元格的中心为圆心，以R为半径的圆中除所述一个单元格的热力点区域之外的区域；所述R大于r；
    根据所述当前显示区域中每个像素点的基本热力及受到的扩散热力，分别获取所述当前显示区域中每个像素点的总热力；
    按照预设的热力呈现对应关系，在所述原始图像的当前显示区域中，呈现所述当前显示区域中每个像素点的总热力对应的颜色，得到所述当前显示区域的热力图。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述原始图像的统计数据及本次生成热力图的热力权重w＝β*w1，分别计算每个单元格内，以单元格中心点为圆心以x为半径的热力点区域的基本热力，包括：
    根据所述原始图像的统计数据及本次生成热力图的热力权重w，计算第一单元格内，以所述第一单元格中心点为圆心以x为半径的热力点区域的基本热力H＝N*w；其中，所述第一单元格为所述当前显示区域划分的单元格中的任一个单元格，所述N为所述原始图像的统计数据中，坐标位于所述第一单元格在所述原始图像中对应的区域内的数据点或统计对象的总数量。
  3. 根据权利要求1或2所述的方法，其特征在于，所述分别根据每个单元格的热力点区域的基本热力，计算所述当前显示区域中每个像素点受到的扩散热力，包括：
    根据每个单元格热力点区域的基本热力，计算第一像素点受到每个单元格的扩散热力分量；其中，所述第一像素点为所述当前显示区域中处于至少一个单元格的扩散热力区域的任一个像素点；
    将所述第一像素点受到的至少一个扩散热力分量的加权和，作为所述第一像素点受到的扩散热力；其中，所述第一像素点受到的至少一个扩散热力分量，为所述第一像素点所处的至少一个扩散热力区域所属每个单元格产生。
  4. 根据权利要求3所述的方法，其特征在于，所述根据每个单元格热力点区域的基本热力，计算第一像素点受到每个单元格的扩散热力分量，包括：
    根据第二单元格的热力点区域的基本热力，计算第一像素点受到所述第二单元格的扩散热力分量
    Figure PCTCN2017077942-appb-100002
    其中，所述第二单元格为所述第一像素点所处的至少一个扩散热力区域所属的单元格中任一个单元格；所述d为所述第一像素点位置到所述第二单元格中心的距离；所述H为所述第二单元格的热力点区域的基本热力。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，
    所述α＝aΔZ，所述a为预设的单元格变化参数，所述a大于或等于1，小于或等于2；所述ΔZ为本次生成热力图时对所述原始图像的缩放比例减去上次生成热力图时对所述原始图像的缩放比例；
    所述β＝bΔZ，所述b为预设的热力权重变化参数，所述b大于或等于1，小于或等于4。
  6. 根据权利要求1-5任一项所述的方法，其特征在于，
    若生成的所述当前显示区域的热力图为对所述原始图像首次生成热力图，则所述r1为单元格边长初始值r0，所述w1为热力权重初始值w0。
  7. 根据权利要求1-6任一项所述的方法，其特征在于，
    所述α用于控制所述r与r1在所述原始图像中对应的实际长度差值的绝对值小于或等于第一预设门限；
    所述β用于控制所述原始图像中同一区域在每次生成热力图时得到的总热力值的差值的绝对值小于或等于第二预设门限。
  8. 根据权利要求1-7任一项所述的方法，其特征在于，所述R小于或等于2r。
  9. 根据权利要求1-8任一项所述的方法，其特征在于，所述根据所述当前显示区域中每个像素点的基本热力及受到的扩散热力，分别获取所述当前显示区域中每个像素点的总热力，包括：
    将所述第二像素点受到的扩散热力及所述第二像素点的基本热力相加或者加权相加，得到所述第二像素点的总热力；所述第二像素点为处于单元格热力点区域中的任一像素点；
    或者，
    所述第三像素点受到的扩散热力为所述第三像素点的总热力；所述第三像素点为处于单元格扩散热力区域且不处于任一单元格的热力点区域的任一像素点。
  10. 一种生成热力图的装置，其特征在于，所述装置包括：
    划分单元，用于将原始图像在屏幕中的当前显示区域划分边长为r的方形单元格；其中，所述r＝α*r1；所述r1为所述原始图像前一次生成热力图时划分的单元格的边长；所述α是与缩放比例相关的单元格变化函数；
    计算单元，用于根据所述原始图像的统计数据及本次生成热力图的热力权重w＝β*w1，分别计算每个单元格内，以单元格中心点为圆心以x为半径的热力点区域的基本热力H；其中，一个热力点区域中每个像素点的基本热力为H；所述统计数据包括至少一个用于反映所述原始图像区域特征的数据点；所述w1为所述原始图像前一次生成热力图时的热力权重；所述β是与缩放比例相关的热力权重变化函数；所述x小于或等于
    Figure PCTCN2017077942-appb-100003
    所述计算单元还用于，分别根据每个单元格的热力点区域的基本热力H，计算所述当前显示区域中每个像素点受到的扩散热力；其中，处于至少一个单元格的扩散热力区域中的一个像素点受到的扩散热力由所述至少一个单元格中每个单元格的热力点区域产生；一个单元格的扩散热力区域为，以所述一个单元格的中心为圆心，以R为半径的圆中除所述一个单元格的热力点区域之外的区域；所述R大于r；
    获取单元，用于根据所述计算单元计算的所述当前显示区域中每个像素点的基本热力及受到的扩散热力，分别获取所述当前显示区域中每个像素点的总热力；
    呈现单元，用于按照预设的热力呈现对应关系，在所述原始图像的当前显示区域中，呈现所述当前显示区域中所述获取单元获取的每个像素点的总热力对应的颜色，得到所述当前显示区域的热力图。
  11. 根据权利要求10所述的装置，其特征在于，所述计算单元具体用于：
    计算第一单元格的热力点区域的基本热力H＝N*w；
    其中，所述第一单元格为所述当前显示区域划分的单元格中的任一个单元格，所述N为所述原始图像的统计数据中，坐标位于所述第一单元格在所述原始图像中对应的区域内的数据点或统计对象的总数量。
  12. 根据权利要求10或11所述的装置，其特征在于，所述计算单元具体用于：
    根据每个单元格热力点区域的基本热力，计算第一像素点受到每个单元格的扩散热力分量；其中，所述第一像素点为所述当前显示区域中处于至少一个单元格的扩散热力区域的任一个像素点；
    将所述第一像素点受到的至少一个扩散热力分量的加权和，作为所述第一像素点受到的扩散热力；其中，所述第一像素点受到的至少一个扩散热力分量，为所述第一像素点所处的至少一个扩散热力区域所属每个单元格产生。
  13. 根据权利要求12所述的装置，其特征在于，所述计算单元具体用于：
    根据第二单元格的热力点区域的基本热力，计算第一像素点受到所述第二单元格的扩散热力分量
    Figure PCTCN2017077942-appb-100004
    其中，所述第二单元格为所述第一像素点所处的至少一个扩散热力区域所属的单元格中任一个单元格；所述d为所述第一像素点位置到所述第二单元格中心的距离；所述H为所述第二单元格的热力点区域的基本热力。
  14. 根据权利要求10-13任一项所述的装置，其特征在于，
    所述α＝aΔZ，所述a为预设的单元格变化参数，所述a大于或等于1，小于或等于2；所述ΔZ为本次生成热力图时对所述原始图像的缩放比例减去上次生成热力图时对所述原始图像的缩放比例；
    所述β＝bΔZ，所述b为预设的热力权重变化参数，所述b大于或等于1，小于或等于4。
  15. 根据权利要求10-14任一项所述的装置，其特征在于，
    若生成的所述当前显示区域的热力图为对所述原始图像首次生成热力图，则所述r1为单元格边长初始值r0，所述w1为热力权重初始值w0。
  16. 根据权利要求10-15任一项所述的装置，其特征在于，
    所述α用于控制所述r与r1在所述原始图像中对应的实际长度差值的绝对值小于或等于第一预设门限；
    所述β用于控制所述原始图像中同一区域在每次生成热力图时得到的总热力值的差值的绝对值小于或等于第二预设门限。
  17. 根据权利要求10-16任一项所述的装置，其特征在于，所述R小于或等于2r。
  18. 根据权利要求10-17任一项所述的装置，其特征在于，所述获取单元具体用于：
    将所述第二像素点受到的扩散热力及所述第二像素点的基本热力相加或者加权相加，得到所述第二像素点的总热力；所述第二像素点为处于单元格热力点区域中的任一像素点；
    或者，
    所述第三像素点受到的扩散热力为所述第三像素点的总热力；所述第三像素点为处于单元格扩散热力区域且不处于任一单元格的热力点区域的任一像素点。
PCT/CN2017/077942 2016-08-19 2017-03-23 一种生成热力图的方法及装置 WO2018032763A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP17840740.9A EP3489904A1 (en) 2016-08-19 2017-03-23 Method and device for generating thermodynamic diagram
US16/279,622 US10783673B2 (en) 2016-08-19 2019-02-19 Method and apparatus for generating heatmap

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610697944.8 2016-08-19
CN201610697944.8A CN107766375B (zh) 2016-08-19 2016-08-19 一种生成热力图的方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/279,622 Continuation US10783673B2 (en) 2016-08-19 2019-02-19 Method and apparatus for generating heatmap

Publications (1)

Publication Number Publication Date
WO2018032763A1 true WO2018032763A1 (zh) 2018-02-22

Family

ID=61196409

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/077942 WO2018032763A1 (zh) 2016-08-19 2017-03-23 一种生成热力图的方法及装置

Country Status (4)

Country Link
US (1) US10783673B2 (zh)
EP (1) EP3489904A1 (zh)
CN (1) CN107766375B (zh)
WO (1) WO2018032763A1 (zh)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110390045B (zh) * 2018-04-12 2021-12-17 腾讯大地通途（北京）科技有限公司 基于位置服务的兴趣点推荐方法及装置
JP7168969B2 (ja) * 2018-06-06 2022-11-10 株式会社アルファコード ヒートマップ提示装置およびヒートマップ提示用プログラム
CN110675728B (zh) * 2018-07-03 2021-08-31 百度在线网络技术（北京）有限公司 热力图的生成方法、装置、设备及计算机可读存储介质
CN110673886B (zh) * 2018-07-03 2023-10-03 百度在线网络技术（北京）有限公司 用于生成热力图的方法和装置
CN109241466A (zh) * 2018-07-26 2019-01-18 威创软件南京有限公司 一种适用于小面积及少热点的热力图的全屏渲染方法
CN109726261A (zh) * 2019-01-07 2019-05-07 北京超图软件股份有限公司 一种热力图生成方法及装置
CN111695045B (zh) 2019-03-14 2023-08-11 北京嘀嘀无限科技发展有限公司 一种热力图展示、热力数据通知的方法及装置
CN110489508A (zh) * 2019-08-16 2019-11-22 北京百度网讯科技有限公司 热力图生成方法、装置、设备及计算机可读存储介质
CN110570491B (zh) * 2019-09-06 2020-08-28 广东省城乡规划设计研究院 热力图生成方法及装置
CN110717005B (zh) * 2019-10-10 2022-06-24 支付宝(杭州)信息技术有限公司 一种热力图纹理的生成方法、装置及设备
CN111538448B (zh) * 2020-04-28 2021-07-23 北京无限光场科技有限公司 图像显示的方法及装置、终端和存储介质
CN111754597A (zh) * 2020-06-24 2020-10-09 京东方科技集团股份有限公司 一种热力图生成的方法、服务端及可读存储介质
CN111861577B (zh) * 2020-07-28 2024-01-23 北京思特奇信息技术股份有限公司 产品办理热力图生成方法、装置、电子设备及存储介质
CN113657925B (zh) * 2021-07-28 2023-08-22 黄淮学院 基于人工智能的土木工程造价管理方法
CN115830178B (zh) * 2022-12-05 2023-09-08 珠海芯聚科技有限公司 一种集成电路热点图显示方法、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103605716A (zh) * 2013-11-14 2014-02-26 北京国双科技有限公司 用于网页页面点击展现的数据处理方法和装置
CN104199891A (zh) * 2014-08-25 2014-12-10 北京国双科技有限公司 用于热力图的数据处理方法及装置
CN104239617A (zh) * 2014-09-02 2014-12-24 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
US20160147789A1 (en) * 2012-03-12 2016-05-26 Google Inc. Dynamic display of content consumption by geographic location
CN105844681A (zh) * 2016-03-22 2016-08-10 北京建飞无限科技有限公司 热力图绘制方法及装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9727669B1 (en) * 2012-07-09 2017-08-08 Google Inc. Analyzing and interpreting user positioning data
US20140278802A1 (en) 2013-03-15 2014-09-18 Google Inc. Producing and providing data for rendering a travel cost heatmap
US8799799B1 (en) * 2013-05-07 2014-08-05 Palantir Technologies Inc. Interactive geospatial map
KR20150080863A (ko) 2014-01-02 2015-07-10 삼성테크윈 주식회사 히트맵 제공 장치 및 방법
US10163132B2 (en) 2014-02-19 2018-12-25 Ebay Inc. Systems and methods to create a geographic heatmap
CN104657417B (zh) * 2014-12-17 2018-07-13 东软集团股份有限公司 热力图的处理方法及系统
CN104731894B (zh) * 2015-03-18 2018-10-16 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

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160147789A1 (en) * 2012-03-12 2016-05-26 Google Inc. Dynamic display of content consumption by geographic location
CN103605716A (zh) * 2013-11-14 2014-02-26 北京国双科技有限公司 用于网页页面点击展现的数据处理方法和装置
CN104199891A (zh) * 2014-08-25 2014-12-10 北京国双科技有限公司 用于热力图的数据处理方法及装置
CN104239617A (zh) * 2014-09-02 2014-12-24 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
CN105844681A (zh) * 2016-03-22 2016-08-10 北京建飞无限科技有限公司 热力图绘制方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3489904A4 *

Also Published As

Publication number Publication date
EP3489904A4 (en) 2019-05-29
EP3489904A1 (en) 2019-05-29
CN107766375A (zh) 2018-03-06
US20190180480A1 (en) 2019-06-13
US10783673B2 (en) 2020-09-22
CN107766375B (zh) 2020-06-09

Similar Documents

Publication Publication Date Title
WO2018032763A1 (zh) 一种生成热力图的方法及装置
WO2021057848A1 (zh) 网络的训练方法、图像处理方法、网络、终端设备及介质
CN109903224B (zh) 图像缩放方法、装置、计算机设备和存储介质
WO2022199583A1 (zh) 图像处理方法、装置、计算机设备和存储介质
WO2021003921A1 (zh) 数据处理方法及终端设备
CN116108393B (zh) 电力敏感数据分类分级方法、装置、存储介质及电子设备
CN114548426B (zh) 异步联邦学习的方法、业务服务的预测方法、装置及系统
US11669566B2 (en) Multi-resolution color-based image search
CN115344692A (zh) 聚类方法、装置、计算机设备和存储介质
WO2018223724A1 (zh) 基于资源分布的地图缩放方法及系统、存储器和控制设备
Hsin Combination of saliency histogram equalisation and seam carving for image resizing
Dovoedo et al. Outlier detection for multivariate skew-normal data: a comparative study
CN117234712A (zh) 算力资源部署方法、装置、计算机设备以及存储介质
CN115935060A (zh) 网点布局位置筛选方法、装置和计算机设备
CN115330803A (zh) 一种表面缺陷数据增强方法、装置、电子设备及存储介质
CN114490719A (zh) 一种数据查询方法、装置、电子设备以及存储介质
CN112996011A (zh) 小区价值评估方法、装置、计算机设备和可读存储介质
CN111966262A (zh) 一种图片显示方法及计算设备
CN107679047B (zh) 展现滚动深度数据的方法及装置
CN108804435B (zh) 用于确定当前屏热度值的方法和装置
CN109324797B (zh) 一种桌面图标生成方法、计算机可读存储介质及终端设备
CN114186142A (zh) 基于多段线缓冲区的设备筛选方法及装置、介质
CN107735800A (zh) 一种图像处理方法以及相关装置
CN117634894A (zh) 生态环境风险评估方法、装置、电子设备及存储介质
Zhao et al. A class distribution learning method for few-shot remote sensing scene classification

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17840740

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2017840740

Country of ref document: EP

Effective date: 20190220