Data display device, data display method, and program

By dividing axes into sections and plotting symbols representing data density, the technique allows for the display of data trends while maintaining individual data secrecy, effectively addressing the challenge of data privacy in scatter plots.

WO2024246984A1PCT designated stage expired Publication Date: 2024-12-05NIPPON TELEGRAPH & TELEPHONE CORP
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2023/019695
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-26
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

Conventional scatter plots reveal individual data points, making it impossible to display data while maintaining secrecy, which is essential for understanding correlations without compromising data privacy.

Method used

The technique involves dividing the x-axis and y-axis into sections, generating squares or circles representing the number of data points within each section, and plotting these symbols to show data distribution trends without exposing individual data points, using methods that adjust section divisions based on data density to ensure privacy.

Benefits of technology

This method effectively displays the distribution trend of entire data sets while keeping individual data secret, addressing the challenge of data privacy in data analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2023019695_05122024_PF_FP_ABST
    Figure JP2023019695_05122024_PF_FP_ABST
Patent Text Reader

Abstract

Provided is a data display technology for showing a distribution trend of entire pieces of data while concealing each piece of the data. The present invention includes: an interval generation unit that uses N pieces of data (xn, yn) to generate a first interval [a1, a2] and a second interval [b1, b2]; a cell generation unit that uses an integer L larger than or equal to 1 as the number of divisions of the interval to divide the first interval [a1, a2] and the second interval [b1, b2] into L equal parts where L satisfies L2≤αN<(L+1)2 and α is a real number satisfying 0<α<1, to thereby generate a (p, q)-th cell [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)]; a count unit that counts the number Np,q of pieces of data included in the (p, q)-th cell from among the N pieces of data (xn, yn); and a plotting unit that plots a (p, q)-th circle representing the number Np,q of pieces of data included in the (p, q)-th cell.
Need to check novelty before this filing date? Find Prior Art

Description

Data display device, data display method, and program

[0001] The present invention relates to a technique for displaying a plurality of pieces of data while concealing each piece of data.

[0002] When performing data analysis, it is sometimes desirable to understand whether or not there is a correlation between two data items. A scatter plot is a diagram suitable for understanding the correlation between two data items (see Non-Patent Document 1). In a scatter plot, different data items are plotted on the horizontal x-axis and the vertical y-axis, and points are plotted where the data to be displayed corresponds.

[0003] Naruhodo Statistics Academy: Scatter Plot, [online], [Retrieved May 8, 2023], Internet<URL: https: / / www.stat.go.jp / naruhodo / 9_graph / jyokyu / sanpu.html>

[0004] However, because scatter plots plot individual data directly as points, they cannot be used when data confidentiality is desired.

[0005] Therefore, an object of the present invention is to provide a data display technique that shows the distribution trend of the entire data while concealing the confidentiality of individual data.

[0006] One aspect of the present invention is a method for producing a compound comprising: n , y n )(n=1, …, N) is N pieces of data (where N is an integer greater than or equal to 2), and the N pieces of data (x n , y n ) (n=1, …, N) to find the first interval [a1, a2] (where a1 is a1≦min(x n ) and a2 is max(x n )≦a2) and the second interval [b1, b2] (where b1 satisfies b1≦min(y n ) and b2 is max(y n )≦b2), and an interval generator that generates a real number satisfying 0<α<1, L 2 ≦αN<(L+1) 2The first section [a1, a2] and the second section [b1, b2] are each divided into L equal parts, with L being an integer equal to or greater than 1 that satisfies the above, and a cell generator generates the (p, q)-th cell [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)](p=0, …, L-1, q=0, …, L-1). N data (x n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q A counting section counts (p=0, …, L-1, q=0, …, L-1) and the number of data contained in the (p, q)th square, N p,q The (p, q)th circle represents the (p, q)th data (however, the size of the circle is N, the number of data contained in the (p, q)th data block). p,q The plotting section plots the points (p=0, ..., L-1, q=0, ..., L-1) corresponding to the circle whose center is a point included in the (p, q)th square.

[0007] One aspect of the present invention is a method for producing a compound comprising: n , y n )(n=1, …, N) is N pieces of data (where N is an integer greater than or equal to 2), and the N pieces of data (x n , y n ) (n=1, …, N) to find the first interval [a1, a2] (where a1 is a1≦min(x n ) and a2 is max(x n )≦a2) and the second interval [b1, b2] (where b1 satisfies b1≦min(y n ) and b2 is max(y n where K is an integer between 2 and N, and β is a real number that satisfies 0<β≦1. The λ-th mass generation method (where λ is an integer between 1 and N) divides the first mass [a1, a2] and the second mass [b1, b2] into λ equal parts, with λ being the number of mass divisions. 2The method is to generate squares [a1+p / λ×(a2-a1), a1+(p+1) / λ×(a2-a1)]×[b1+q / λ×(b2-b1), b1+(q+1) / λ×(b2-b1)](p=0, …, λ-1, q=0, …, λ-1), and W λ (λ=1, …, N) is the λ generated by the λ-th mass generation method. 2 The number of squares that contain K or more data is defined as λ 2 Divided by μ λ (λ=1, …, N) is the average number of data contained in the cells generated by the λ-th cell generation method, N / ν λ (However, ν λ is the λ generated by the λth mass generation method 2 (the number of cells that contain one or more data points among the cells), and W1 ≥ β, W2 ≥ β, …, W L ≧β, W L+1 <β, μ1>μ2> … >μ L or W1 ≥ β, W2 ≥ β, …, W L ≧β, μ1>μ2> … >μ L , μ L ≦μ L+1 The first section [a1, a2] and the second section [b1, b2] are each divided into L equal parts, with L being an integer equal to or greater than 1 that satisfies the above, and a cell generator generates the (p, q)-th cell [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)](p=0, …, L-1, q=0, …, L-1). N data (x n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q A counting section counts (p=0, …, L-1, q=0, …, L-1) and the number of data contained in the (p, q)th square, N p,q If is greater than or equal to K, the number of data contained in the (p, q)th square is N p,q The (p, q)th circle represents the (p, q)th data (however, the size of the circle is N, the number of data contained in the (p, q)th data block). p,qThe plotting section plots the points (p=0, ..., L-1, q=0, ..., L-1) corresponding to the circle whose center is a point included in the (p, q)th square.

[0008] One aspect of the present invention is a method for producing a compound comprising: n , y n )(n=1, …, N) is N pieces of data (where N is an integer greater than or equal to 2), and the N pieces of data (x n , y n ) (n=1, …, N) to find the first interval [a1, a2] (where a1 is a1≦min(x n ) and a2 is max(x n )≦a2) and the second interval [b1, b2] (where b1 satisfies b1≦min(y n ) and b2 is max(y n )≦b2), and the λ-th mass generation method (where λ is an integer between 1 and N) divides the first mass [a1, a2] and the second mass [b1, b2] into λ equal parts, with λ being the number of mass divisions. 2 The method is to generate squares [a1+p / λ×(a2-a1), a1+(p+1) / λ×(a2-a1)]×[b1+q / λ×(b2-b1), b1+(q+1) / λ×(b2-b1)](p=0, …, λ-1, q=0, …, λ-1), and W λ (λ=1, …, N) is the λ generated by the λ-th mass generation method. 2 The number of squares that contain less than K data points is defined as λ. 2 Divided by μ λ (λ=1, …, N) is the average number of data contained in the cells generated by the λ-th cell generation method, N / ν λ (However, ν λ is the λ generated by the λth mass generation method 2 (the number of cells that contain one or more data points among the cells), and W1<β, W2<β, …, W L <β, W L+1 ≧β,μ1>μ2> … >μ L or W1<β, W2<β, …, W L <β,μ1>μ2> … >μL , μ L ≦μ L+1 The first section [a1, a2] and the second section [b1, b2] are each divided into L equal parts, with L being an integer equal to or greater than 1 that satisfies the above, and a cell generator generates the (p, q)-th cell [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)](p=0, …, L-1, q=0, …, L-1). N data (x n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q A counting section counts (p=0, …, L-1, q=0, …, L-1) and the number of data contained in the (p, q)th square, N p,q If is greater than or equal to K, the number of data contained in the (p, q)th square is N p,q The (p, q)th circle represents the (p, q)th data (however, the size of the circle is N, the number of data contained in the (p, q)th data block). p,q The plotting section plots the points (p=0, ..., L-1, q=0, ..., L-1) corresponding to the circle whose center is a point included in the (p, q)th square.

[0009] According to the present invention, it is possible to show the distribution trend of the entire data while keeping each piece of data confidential.

[0010] 1 is an example of a normal scatter plot; FIG. 2 is an example of a scatter plot by display method 1; FIG. 3 is an example of a scatter plot by display method 2; FIG. 4 is an example of a scatter plot by display method 3; and FIG. 5 is an example of a scatter plot by display method 4. A block diagram showing the configuration of a data display device 100 / 200. A flowchart showing the operation of the data display device 100 / 200. A block diagram showing the configuration of a grid generation unit 220. A flowchart showing the operation of the grid generation unit 220. A diagram showing an example of the functional configuration of a computer that realizes each device in an embodiment of the present invention.

[0011] Hereinafter, embodiments of the present invention will be described in detail. Components having the same functions are given the same numbers, and duplicated explanations will be omitted.

[0012] Before describing each embodiment, the notation used in this specification will be explained.

[0013] ^ (caret) represents a superscript, e.g., x y^z Yes z is a superscript to x, and x y^z Yes z is a subscript to x. Also, _ (underscore) represents a subscript. For example, x y_z Yes z is a superscript to x, and x y_z Yes z is a subscript to x.

[0014] The superscripts "^" and "~" such as ^x and ~x for a certain letter x should be written directly above the "x", but due to restrictions on the notation in the specification, they are written as ^x and ~x.

[0015] <Technical Background> In an embodiment of the present invention, in order to conceal individual data, statistical values ​​of multiple data are plotted and displayed instead of plotting individual data. The display method in an embodiment of the present invention will be described below.

[0016] [Display Method 1] In display method 1, the x-axis and y-axis are each divided into multiple intervals, the intersection of these intervals (hereinafter referred to as "cells") is generated, and the number of data points included in each cell is plotted. Specifically, this is as follows:

[0017] (1) The number of intervals into which the x-axis is divided and the number of intervals into which the y-axis is divided are the same, and the number of intervals into which the x-axis and y-axis are divided is determined so that the number of squares generated is a maximum value that is less than a predetermined percentage (e.g., 10%) of the number of data to be displayed.

[0018] (2) The data may be displayed as a circle having a size corresponding to the number of data items contained in the square, or a circle having a color or pattern corresponding to the number of data items contained in the square.

[0019] Fig. 1 is an example of a normal scatter diagram. In Fig. 1, the data to be displayed is displayed without any concealment. Fig. 2 is an example of a scatter diagram using display method 1, in which the data in Fig. 1 is displayed according to display method 1. Note that the center of the circle representing the number of data points included in the square is aligned with the center of the square.

[0020] [Display Method 2] Display Method 2 is a variation of Display Method 1, in which the center of the circle representing the number of data points contained in a cell is set to the average value of the x-coordinate and the average value of the y-coordinate of the data points contained in that cell. This allows for a more accurate visual understanding.

[0021] FIG. 3 is an example of a scatter diagram according to display method 2, which displays the data of FIG. 1 according to display method 2.

[0022] [Display Method 3] In Display Method 1 and Display Method 2, the number of intervals to be divided is determined without considering the number of data contained in the squares, which may result in an output privacy problem (see Reference Non-Patent Document 1). Therefore, in Display Method 3, for squares where the number of data contained in the squares is less than K, the number of data contained in the squares is not plotted, while the number of intervals to be divided is adjusted so that the number of data not plotted is minimized.

[0023] (Reference Non-Patent Document 1: Igarashi Dai, Takahashi Katsumi, "Differential Privacy," Computer Software, Vol. 29, No. 4, pp. 40-49, 2012.) Specifically, a desired minimum value K is set as the number of data contained in a cell. Furthermore, a desired minimum value β is set as the ratio of the number of cells containing K or more pieces of data to the number of cells generated by a predetermined method described later. Then, an integer L of 1 or more that satisfies a predetermined condition is divided into L intervals (hereinafter referred to as the number of interval divisions), and cells are generated. Here, the predetermined condition is to use a λth cell generation method (where λ is an integer between 1 and N, and N is the number of data to be displayed) to divide the x-axis and y-axis into λ intervals, respectively, with the integer λ being the number of interval divisions. 2Method for generating individual cells, W λ (λ = 1, …, N) is the λ generated by the λ-th cell generation method 2 Among the λ cells generated, the number of cells containing K or more data is λ 2 Divided by the value, μ λ (λ = 1, …, N) is the average value N / ν of the number of data contained in the cells generated by the λ-th cell generation method λ However, ν λ is the number of cells containing one or more data among the λ cells generated by the λ-th cell generation method, and W1 ≥ β, W2 ≥ β, …, W 2 ≥ β, W L ≥ β, W L+1 < β, μ1 > μ2 > … > μ L Or W1 ≥ β, W2 ≥ β, …, W L ≥ β, μ1 > μ2 > … > μ L , μ L ≤ μ L+1 This is the condition.

[0024] The integer L that satisfies the above predetermined condition can be obtained using the following algorithm. [[Algorithm for obtaining the number of interval divisions L]] ------------------------------------------------------------------ 1: for (λ = 1; λ < N; λ++){ 2: if (f1(λ) ≠ 0) 3: M = f1(λ) 4: else 5: return λ 6:} ------------------------------------------------------------------ Here, M is a variable that stores the average value of the number of data contained in the cells generated by the λ-th cell generation method, and the initial value of M may be, for example, an integer larger than N.

[0025] The function f1(λ) is a value μ smaller than the average value of the number of data contained in the cell when the value f2(λ) of the function f2 satisfies f2(λ) ≥ β λ is obtained, then the value μ λThe function f2(λ) returns the λ generated by the λ-th mass generation method. 2 The number of squares that contain K or more data is defined as λ 2 W divided by λ The algorithm for function f1 and the algorithm for function f2 are as follows. [[Algorithm for function f1]] ------------------------------------------------------------------ f1(λ) { 1: if (f2(λ)≧β) 2: if (average number of data contained in the square μ λ is smaller than M) 3: return (the average value μ of the number of data contained in the square λ ) 4: else 5: return 0 6: else 7: return 0} ------------------------------------------------------------------ [[Algorithm for function f2]] ------------------------------------------------------------------ f2(λ) { 1: for (λ generated by the λ-th mass generation method 2 each cell of the cells) { 2: if (the number of data contained in the cell generated by the λ-th cell generation method is K or more) 3: λ generated by the λ-th cell generation method 2 Increment the number of cells that contain K or more data by 1. 4:} 5: return W λ} ------------------------------------------------------------------ Instead of setting β as the desired minimum value as the ratio of the number of squares containing K or more pieces of data to the number of squares generated by the λ-th square generation method, it may be set as the maximum value allowed as the ratio of the number of squares containing less than K pieces of data to the number of squares generated by the λ-th square generation method. In this case, the predetermined condition is to use the λ-th square generation method (where λ is an integer between 1 and N) to divide the x-axis and y-axis into λ sections, with λ being the number of section divisions, and 2 How to generate W squares λ (λ=1, …, N) is the λ generated by the λ-th mass generation method. 2 The number of squares that contain less than K data points is defined as λ. 2 Divided by μ λ (λ=1, …, N) is the average number of data contained in the cells generated by the λ-th cell generation method, N / ν λ (However, ν λ is the λ generated by the λth mass generation method 2 (the number of cells that contain one or more data points among the cells), and W1<β, W2<β, …, W L <β, W L+1 ≧β,μ1>μ2> … >μ L or W1<β, W2<β, …, W L <β,μ1>μ2> … >μ L , μ L ≦μ L+1 The conditions are as follows. The algorithms for function f1 and function f2 are as follows:

[0026] [Algorithm for function f1] ------------------------------------------------------------------ f1(λ) { 1: if (f2(λ)<β) 2: if (average number of data contained in the square μ λ is smaller than M) 3: return (the average value μ of the number of data contained in the square λ) 4: else 5: return 0 6: else 7: return 0} ------------------------------------------------------------------ [[Algorithm for function f2]] ------------------------------------------------------------------ f2(λ) { 1: for (λ generated by the λ-th mass generation method 2 each cell of the cells) { 2: if (the number of data contained in the cell generated by the λ-th cell generation method is less than K) 3: λ generated by the λ-th cell generation method 2 Increment the number of cells that contain less than K data by 1. 4:} 5: return W λ} ------------------------------------------------------------------ FIG. 4 is an example of a scatter diagram according to display method 3, and is a diagram in which the data of FIG. 1 is displayed according to display method 3.

[0027] [Display Method 4] In Display Method 3, data is lost because the number of data points contained in a cell is not plotted for cells that contain less than K. Therefore, in Display Method 4, to avoid this data loss, cells that contain less than K data points are merged with neighboring cells that contain data, so that a single cell contains K or more data points.

[0028] FIG. 5 is an example of a scatter diagram according to Display Method 4, which displays the data of FIG. 1 according to Display Method 4.

[0029] First Embodiment A data display device 100 displays N pieces of data (x) (where N is an integer equal to or greater than 2) in a manner that allows the distribution trend of the entire data to be known while keeping each piece of data confidential. n , y n )(n=1, …, N) as a scatter plot, where xn (n=1, …, N), y n (n=1, …, N) is a real number. Also, the N pieces of data to be displayed (x n , y n ) (n=1, . . . , N) is, for example, a set of two attribute values ​​obtained as a result of searching a database.

[0030] The data display device 100 will be described below with reference to Figs. 6 and 7. Fig. 6 is a block diagram showing the configuration of the data display device 100. Fig. 7 is a flowchart showing the operation of the data display device 100. As shown in Fig. 6, the data display device 100 includes a section generation unit 110, a grid generation unit 120, a counting unit 130, a plotting unit 140, and a recording unit 190. The recording unit 190 is a component that appropriately records information required for the processing of the data display device 100. The recording unit 190 records, for example, N pieces of data (x n , y n ) (n=1, ..., N) may be recorded in advance instead of being input to the data display device 100. The recording unit 190 may also record a real number α that satisfies 0<α<1, for example. The real number α is the number of N pieces of data (x n , y n ) (n=1, …, N) indicates the maximum allowable ratio of the number of squares generated to display the

[0031] The operation of the data display device 100 will be described with reference to FIG.

[0032] In S110, the section generation unit 110 generates N pieces of data (x n , y n ) (n=1, …, N) as input, and n , y n ) (n=1, …, N) to find the first interval [a1, a2] (where a1 is a1≦min(x n ) and a2 is max(x n )≦a2) and the second interval [b1, b2] (where b1 satisfies b1≦min(y n ) and b2 is max(y n)≦b2) is generated and output. n ) is the set {x1, x2, …, x n}, max(x n ) is the set {x1, x2, …, x n Similarly, min(y n ) is the set {y1, y2, …, y n}, max(y n ) is the set {y1, y2, …, y n} represents the maximum value.

[0033] In S120, the grid generation unit 120 receives the first section [a1, a2] and the second section [b1, b2] generated in S110 as input, and calculates L 2 ≦αN<(L+1) 2 The first interval [a1, a2] and the second interval [b1, b2] are each divided into L equal parts, where L is an integer greater than or equal to 1 that satisfies the above, and the (p, q)th square [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)](p=0, …, L-1, q=0, …, L-1) is generated and output.

[0034] In S130, the counting unit 130 counts N pieces of data (x n , y n ) (n=1, ..., N) and the (p, q)th mass [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)](p=0, ..., L-1, q=0, ..., L-1) generated in S120 are input, and N pieces of data (x n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q Count and output (p=0, …, L-1, q=0, …, L-1).

[0035] In S140, the plotting unit 140 calculates the number N of data included in the (p, q)-th cell [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)] (p=0, ..., L-1, q=0, ..., L-1) generated in S120 and the number N of data included in the (p, q)-th cell generated in S130. p,q (p=0, …, L-1, q=0, …, L-1) is the input, and the number of data contained in the (p, q)th square is N p,q The (p, q)th circle represents the (p, q)th data (however, the size of the circle is N, the number of data contained in the (p, q)th data block). p,q The center of the circle is the point included in the (p, q)th square (p=0, …, L-1, q=0, …, L-1). The size of the (p, q)th circle is determined by the radius of the circle being the number of data points included in the (p, q)th square, N. p,q The area of ​​the circle may be proportional to the number of data N included in the (p, q)th cell. p,q The center of the (p, q)th circle may be the center of the (p, q)th cell, that is, the point expressed by (a1+(2p+1) / 2L×(a2-a1), b1+(2q+1) / 2L×(b2-b1)), or may be a point whose x-coordinate and y-coordinate values ​​are the average values ​​of the x-coordinate and y-coordinate of the data contained in the (p, q)th cell, respectively. Furthermore, the (p, q)th circle may be represented by a color or pattern according to the number of data contained in the cell.

[0036] <<Modification>> In the above explanation, the first interval [a1, a2] and the second interval [b1, b2] are divided into the same number of intervals, but they may be different. In this case, the processing from S120 onwards is as follows.

[0037] In S120, the grid generation unit 120 receives the first interval [a1, a2] and the second interval [b1, b2] generated in S110 as input, and divides the first interval [a1, a2] into L1 equal parts and the second interval [b1, b2] into L2 equal parts, using L1 (where L1 is an integer greater than or equal to 1) as the number of interval divisions for the first interval [a1, a2] and L2 (where L2 is an integer greater than or equal to 1) as the number of interval divisions for the second interval [b1, b2]. The grid generation unit 120 then generates and outputs the (p, q) grid [a1+p / L1×(a2-a1), a1+(p+1) / L1×(a2-a1)]×[b1+q / L2×(b2-b1), b1+(q+1) / L2×(b2-b1)](p=0, ..., L1-1, q=0, ..., L2-1).

[0038] In S130, the counting unit 130 counts N pieces of data (x n , y n ) (n=1, ..., N) and the (p, q)th mass [a1+p / L1×(a2-a1), a1+(p+1) / L1×(a2-a1)]×[b1+q / L2×(b2-b1), b1+(q+1) / L2×(b2-b1)](p=0, ..., L1-1, q=0, ..., L2-1) generated in S120 are input, and N pieces of data (x n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q Count and output (p=0, …, L1-1, q=0, …, L2-1).

[0039] In S140, the plotting unit 140 calculates the number N of data included in the (p, q)-th cell [a1+p / L1×(a2-a1), a1+(p+1) / L1×(a2-a1)]×[b1+q / L2×(b2-b1), b1+(q+1) / L2×(b2-b1)] (p=0, ..., L1-1, q=0, ..., L2-1) generated in S120 and the number N of data included in the (p, q)-th cell generated in S130. p,q (p=0, …, L1-1, q=0, …, L2-1) is the input, and the number of data contained in the (p, q)th square is N p,q The (p, q)th circle represents the (p, q)th data (however, the size of the circle is N, the number of data contained in the (p, q)th data block). p,qThe center of the circle is a point included in the (p, q)th square (p=0, …, L1-1, q=0, …, L2-1) is plotted.

[0040] According to an embodiment of the present invention, it is possible to show the distribution trend of the entire data while keeping each piece of data confidential.

[0041] Second Embodiment In this embodiment, a form that addresses the problem of output privacy, that is, a form in which the number of interval divisions is determined taking into consideration the number of data included in the squares, will be described. Similar to the data display device 100, the data display device 200 displays N pieces of data (x n , y n )(n=1, …, N) as a scatter plot.

[0042] The data display device 200 will be described below with reference to Figs. 6 and 7. Fig. 6 is a block diagram showing the configuration of the data display device 200. Fig. 7 is a flowchart showing the operation of the data display device 200. As shown in Fig. 6, the data display device 200 includes a section generation unit 110, a grid generation unit 220, a counting unit 130, a plotting unit 240, and a recording unit 190. The recording unit 190 is a component that appropriately records information required for the processing of the data display device 200. The recording unit 190 records, for example, N pieces of data (x n , y n ) (n=1, ..., N) may be recorded in advance instead of being input to the data display device 200. Furthermore, the recording unit 190 records, for example, an integer K between 2 and N inclusive. The integer K is the desired minimum value for the number of data items to be included in a square, and may be, for example, K=5. The recording unit 190 records, for example, a real number β that satisfies 0<β≦1. The real number β indicates the desired minimum value as the ratio of the number of squares containing K or more pieces of data to the number of generated squares.

[0043] The operation of the data display device 200 will be described with reference to FIG.

[0044] In S110, the section generation unit 110 generates N pieces of data (x n , y n) (n=1, …, N) as input, and n , y n ) (n=1, …, N) to find the first interval [a1, a2] (where a1 is a1≦min(x n ) and a2 is max(x n )≦a2) and the second interval [b1, b2] (where b1 satisfies b1≦min(y n ) and b2 is max(y n )≦b2) is generated and output.

[0045] In S220, the grid generation unit 220 generates N pieces of data (x n , y n ) (n=1, ..., N) and the first interval [a1, a2] and the second interval [b1, b2] generated in S110 are used as input, and the first interval [a1, a2] and the second interval [b1, b2] are each divided into L equal parts, with L being an integer greater than or equal to 1 that satisfies a predetermined condition and is used as the interval division number, to generate and output the (p, q)th square [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)](p=0, ..., L-1, q=0, ..., L-1). Here, the predetermined condition is that the λ-th mass generation method (where λ is an integer between 1 and N) is used to divide the first section [a1, a2] and the second section [b1, b2] into λ equal parts, with λ being the number of section divisions, and 2 A method for generating squares [a1+p / λ×(a2-a1), a1+(p+1) / λ×(a2-a1)]×[b1+q / λ×(b2-b1), b1+(q+1) / λ×(b2-b1)](p=0, …, λ-1, q=0, …, λ-1), W λ (λ=1, …, N) is the λ generated by the λ-th mass generation method. 2 The number of squares that contain K or more data is defined as λ 2 Divided by μ λ (λ=1, …, N) is the average number of data contained in the cells generated by the λ-th cell generation method, N / ν λ (However, ν λ is the λ generated by the λth mass generation method 2Let the number of cells containing data of one or more out of the cells be, and W1≥β, W2≥β, …, W L ≥β, W L+1 <β, μ1>μ2> … >μ L Or W1≥β, W2≥β, …, W L ≥β, μ1>μ2> … >μ L , μ L ≤μ L+1 is the condition.

[0046] Hereinafter, the cell generation unit 220 will be described with reference to FIGS. 8 to 9. FIG. 8 is a block diagram showing the configuration of the cell generation unit 220. FIG. 9 is a flowchart showing the operation of the cell generation unit 220. As shown in FIG. 8, the cell generation unit 220 includes an initialization unit 211, a first calculation unit 212, a second calculation unit 213, and an end condition determination unit 214.

[0047] The operation of the cell generation unit 220 will be described according to FIG. 9.

[0048] In S211, the initialization unit 211 sets 1 for λ and a predetermined value for M as initial values, respectively. The initial value of M may be, for example, an integer larger than N. Note that λ is a variable (also called a counter) for storing the number of interval divisions, and M is a variable for storing the average value of the number of data included in the cells generated by the λ-th cell generation method.

[0049] In S212, the first calculation unit 212 counts the number of cells containing K or more data out of the λ cells generated by the λ-th cell generation method, and divides the number of such cells by λ to calculate the value W 2 The first calculation unit 212 is a component that executes the algorithm of the function f2 in the display method 3 described in <Technical Background>. 2 to calculate. λ

[0050] In S213, the second calculation unit 213 calculates the average value μ λ of the number of data included in the cells generated by the λ-th cell generation method, and when W λ ≥β and μ λ <M holds, then S λ =μ λ , otherwise S λ= 0, the evaluation value S λ The second calculation unit 213 is a component that executes the algorithm of the function f1 in the display method 3 described in the <Technical Background> section.

[0051] In S214, the termination condition determination unit 214 determines whether S λ If =0 holds, output the value of λ as the number of interval divisions L; otherwise, increment λ by 1 and set M to M=μ λ The process returns to S212 and repeats the processes of S212 and S213. The termination condition determination unit 214 is a component that executes an algorithm for determining the number of section divisions L in display method 3 described in the <Technical Background> section.

[0052] In S130, the counting unit 130 counts N pieces of data (x n , y n ) (n=1, ..., N) and the (p, q)th mass [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)](p=0, ..., L-1, q=0, ..., L-1) generated in S120 are input, and N pieces of data (x n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q Count and output (p=0, …, L-1, q=0, …, L-1).

[0053] In S240, the plotting unit 240 calculates the number N of data included in the (p, q)-th cell [a1+p / L×(a2-a1), a1+(p+1) / L×(a2-a1)]×[b1+q / L×(b2-b1), b1+(q+1) / L×(b2-b1)] (p=0, ..., L-1, q=0, ..., L-1) generated in S220 and the (p, q)-th cell generated in S130. p,q (p=0, …, L-1, q=0, …, L-1) is the input, and the number of data contained in the (p, q)th square is N p,q If is greater than or equal to K, the number of data contained in the (p, q)th square is N p,qThe (p, q)th circle represents the (p, q)th data (however, the size of the circle is N, the number of data contained in the (p, q)th data block). p,q The center of the circle is the point included in the (p, q)th square) (p=0, …, L-1, q=0, …, L-1) is plotted, and other cases are not plotted. The size of the (p, q)th circle is determined by the radius of the circle being the number of data included in the (p, q)th square, N p,q The area of ​​the circle may be proportional to the number of data N included in the (p, q)th cell. p,q The center of the (p, q)th circle may be the center of the (p, q)th cell, that is, the point expressed by (a1+(2p+1) / 2L×(a2-a1), b1+(2q+1) / 2L×(b2-b1)), or may be a point whose x-coordinate and y-coordinate values ​​are the average values ​​of the x-coordinate and y-coordinate of the data contained in the (p, q)th cell, respectively. Furthermore, the (p, q)th circle may be represented by a color or pattern according to the number of data contained in the cell.

[0054] <<Modifications>> As explained in <Technical Background>, β may be set to the maximum value allowed as the ratio of the number of squares containing less than K pieces of data to the number of squares generated by the λ-th square generation method. In this case, the recording unit 190 records, for example, a real number β that satisfies 0<β<1. Furthermore, the predetermined condition is that the λ-th square generation method (where λ is an integer between 1 and N) is used to divide the first section [a1, a2] and the second section [b1, b2] into λ equal sections, with the integer λ being the number of section divisions, and λ 2 A method for generating squares [a1+p / λ×(a2-a1), a1+(p+1) / λ×(a2-a1)]×[b1+q / λ×(b2-b1), b1+(q+1) / λ×(b2-b1)](p=0, …, λ-1, q=0, …, λ-1), W λ (λ=1, …, N) is the λ generated by the λ-th mass generation method. 2 The number of squares that contain less than K data points is defined as λ. 2 Divided by μ λ (λ=1, …, N) is the average number of data contained in the cells generated by the λ-th cell generation method, N / ν λ(However, ν λ is the number of cells containing one or more data among the λ 2 cells generated by the λ-th cell generation method), and W1 < β, W2 < β, …, W L <β, W L+1 ≧β, μ1 > μ2 > … > μ L Or W1 < β, W2 < β, …, W L <β, μ1 > μ2 > … > μ L , μ L ≦μ L+1 The condition is as follows.

[0055] Hereinafter, the operation of the cell generation unit 220 will be described according to FIG. 9. Here, only the processing of S212 and the processing of S213 different from those of the cell generation unit 220 in the first embodiment will be described.

[0056] In S212, the first calculation unit 212 counts the number of cells containing less than K data among the λ 2 cells generated by the λ-th cell generation method, and divides the number of these cells by λ 2 to calculate the value W λ .

[0057] In S213, the second calculation unit 213 calculates the average value μ λ of the number of data contained in the cells generated by the λ-th cell generation method, and when W λ <β and μ λ <M holds, S λ = μ λ , otherwise S λ = 0, and the evaluation value S λ is calculated.

[0058] << Modification Example >> When the number of data N p,q contained in the (p, q) cell is less than K, the plotting unit 240 does not plot a circle, so as described in <Technical Background>, the data will be lost. To avoid such a situation, when the number of data N p,q contained in the (p, q) cell is less than K, the plotting unit 240 uses the number of data contained in the cells adjacent to the (p, q) cell and the number of data N p,qWhen the sum of these is equal to or greater than K, a circle representing the number of data points contained in the two squares may be plotted (where the size of the circle corresponds to the sum of the number of data points contained in the two squares, and the center of the circle is a point contained in the two squares). Here, a square adjacent to the (p, q)th square is a square that shares one of the four sides that make up the (p, q)th square with the (p, q)th square.

[0059] According to the embodiment of the present invention, it is possible to show the distribution trend of the entire data while keeping each individual data confidential, and also to protect output privacy.

[0060] <Additional Note> The processing of each unit of each of the above-described devices may be realized by a computer, in which case the processing content of the functions to be possessed by each device is described by a program. Then, by loading this program into the recording unit 2020 of the computer 2000 shown in Fig. 10 and operating the arithmetic processing unit 2010, the input unit 2030, the output unit 2040, the auxiliary recording unit 2025, etc., the processing functions of each of the above-described devices are realized on the computer.

[0061] The device of the present invention may, for example, be a single hardware entity that includes an input unit capable of inputting signals from outside the hardware entity, an output unit capable of outputting signals to outside the hardware entity, a communication unit to which a communication device (e.g., a communication cable) can be connected for communication with outside the hardware entity, a CPU (Central Processing Unit) that serves as an arithmetic processing unit, which may also include cache memory and registers, RAM and ROM that serve as memory, an external storage device such as a hard disk, and buses that connect the input unit, output unit, communication unit, CPU, RAM, ROM, and external storage device so that data can be exchanged between them. If necessary, the hardware entity may also be provided with a device (drive) that can read and write recording media such as a CD-ROM. An example of a physical entity equipped with such hardware resources is a general-purpose computer.

[0062] The external storage device of the hardware entity stores the programs required to realize the above-mentioned functions and the data required for processing these programs (the programs may be stored in a ROM, which is a read-only storage device, for example, instead of an external storage device). Data obtained by processing these programs is stored in RAM, the external storage device, etc. as appropriate.

[0063] In the hardware entity, each program stored in an external storage device (or ROM, etc.) and the data required to process each program are loaded into memory as needed, and interpreted, executed, and processed by the CPU as appropriate. As a result, the CPU realizes predetermined functions (each component represented as a "... unit," "... means," etc.). In other words, each component of the embodiments of the present invention may be configured by a processing circuitry.

[0064] As described above, when the processing functions of the hardware entities (apparatuses of the present invention) described in the above embodiments are realized by a computer, the processing contents of the functions that the hardware entities should have are described by a program. Then, by executing this program on a computer, the processing functions of the hardware entities are realized on the computer.

[0065] The program describing the processing contents can be recorded on a computer-readable recording medium, such as a non-transitory recording medium, specifically a magnetic recording device, an optical disk, or the like.

[0066] The program may be distributed, for example, by selling, transferring, lending, etc. a portable recording medium such as a DVD or CD-ROM on which the program is recorded. Furthermore, the program may be stored in a storage device of a server computer, and then transferred from the server computer to another computer via a network, thereby distributing the program.

[0067] A computer that executes such a program, for example, first stores the program recorded on a portable recording medium or transferred from a server computer in its own non-transitory storage device, the auxiliary storage unit 2025. Then, when executing a process, the computer loads the program stored in its own non-transitory storage device, the auxiliary storage unit 2025, into the storage unit 2020 and executes processing in accordance with the loaded program. Alternatively, as another execution mode of this program, the computer may load the program directly from a portable recording medium into the storage unit 2020 and execute processing in accordance with the program. Furthermore, the computer may execute processing in accordance with the received program each time a program is transferred from the server computer to the computer. Alternatively, the server computer may not transfer the program to the computer, but may instead execute the processing function by issuing an execution instruction and obtaining the results, thereby executing the above-described processing through a so-called ASP (Application Service Provider) type service. Note that the program in this embodiment includes information used for processing by a computer that is equivalent to a program (such as data that is not a direct instruction to the computer but has properties that define computer processing).

[0068] Furthermore, in this embodiment, the device is configured by executing a predetermined program on a computer, but at least a part of the processing contents may be realized by hardware.

[0069] The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit of the present invention.

Claims

1. (x n , y n )(n=1, …, N) is N pieces of data (where N is an integer equal to or greater than 2), and the N pieces of data (x n , y n ) (n=1, …, N) to find the first interval [a 1 , a 2 ] (where a 1 is a 1 ≦min(x n ) and a 2 is max(x n )≦a 2 ) and the second interval [b 1 , b 2 ] (where b 1 HA 1 ≦min(y n ) and b 2 is max(y n )≦b 2 where α is a real number satisfying 0<α<1, and L 2 ≦αN<(L+1) 2 The first interval [a 1 , a 2 ] and the second section [b 1 , b 2 ] is divided into L equal parts, and the (p, q)th cell [a 1 +p / L×(a 2 -a 1 ), a 1 +(p+1) / L×(a 2 -a 1 )]×[b 1 +q / L×(b 2 -b 1 ), b 1 +(q+1) / L×(b 2 -b 1 )](p=0, …, L-1, q=0, …, L-1) and a mass generator that generates N data (x n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q A counting section that counts (p=0, …, L-1, q=0, …, L-1) and the number of data contained in the (p, q)th square, N p,q The (p, q)th circle represents the (p, q)th data (where the size of the circle is the number of data contained in the (p, q)th cell, N p,q A plot unit that plots (p=0, ..., L-1, q=0, ..., L-1) corresponding to the circle whose center is a point included in the (p, q)th square (p=0, ..., L-1, q=0, ..., L-1); and 2. (x n , y n )(n=1, …, N) is N pieces of data (where N is an integer equal to or greater than 2), and the N pieces of data (x n , y n ) (n=1, …, N) to find the first interval [a 1 , a 2 ] (where a 1 is a 1 ≦min(x n ) and a 2 is max(x n )≦a 2 ) and the second interval [b 1 , b 2 ] (where b 1 HA 1 ≦min(y n ) and b 2 is max(y n )≦b 2 where K is an integer between 2 and N, and β is a real number satisfying 0<β≦1. The λ-th mass generation method (where λ is an integer between 1 and N) is used to generate the first mass [a 1 , a 2 ] and the second section [b 1 , b 2 ] is divided into λ equal parts, 2 Pieces of squares [a 1 +p / λ×(a 2 -a 1 ), a 1 +(p+1) / λ×(a 2 -a 1 )]×[b 1 +q / λ×(b 2 -b 1 ), b 1 +(q+1) / λ×(b 2 -b 1 )](p=0, …, λ-1, q=0, …, λ-1), and W λ (λ=1, …, N) is the λ generated by the λ-th mass generation method. 2 The number of squares that contain K or more pieces of data is defined as λ 2 Divided by μ λ (λ=1, …, N) is the average number of data included in the masses generated by the λ-th mass generation method, N / ν λ (However, ν λ is the λ generated by the λ-th mass generation method. 2 The number of squares that contain at least one data point among the squares, W 1 ≧β, W 2 ≧β, …, W L ≧β, W L+1 <β, μ 1 >μ 2 > … >μ L or W 1 ≧β, W 2 ≧β, …, W L ≧β, μ 1 >μ 2 > … >μ L , μ L ≦μ L+1 The first interval [a 1 , a 2 ] and the second section [b 1 , b 2 ] is divided into L equal parts, and the (p, q)th cell [a 1 +p / L×(a 2 -a 1 ), a 1 +(p+1) / L×(a 2 -a 1 )]×[b 1 +q / L×(b 2 -b 1 ), b 1 +(q+1) / L×(b 2 -b 1 )](p=0, …, L-1, q=0, …, L-1) and a mass generator that generates N data (x n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q A counting section that counts (p=0, …, L-1, q=0, …, L-1) and the number of data contained in the (p, q)th square, N p,q If is K or more, the number of data in the (p, q)th cell is N p,q The (p, q)th circle represents the (p, q)th data (where the size of the circle is the number of data contained in the (p, q)th cell, N p,q A plot unit that plots (p=0, ..., L-1, q=0, ..., L-1) corresponding to the circle whose center is a point included in the (p, q)th square (p=0, ..., L-1, q=0, ..., L-1); and 3. (x n , y n )(n=1, …, N) is N pieces of data (where N is an integer equal to or greater than 2), and the N pieces of data (x n , y n ) (n=1, …, N) to find the first interval [a 1 , a 2 ] (where a 1 is a 1 ≦min(x n ) and a 2 is max(x n )≦a 2 ) and the second interval [b 1 , b 2 ] (where b 1 HA 1 ≦min(y n ) and b 2 is max(y n )≦b 2 where K is an integer between 2 and N, and β is a real number satisfying 0<β<1. The λ-th mass generation method (where λ is an integer between 1 and N) is used to generate the first mass [a 1 , a 2 ] and the second section [b 1 , b 2 ] is divided into λ equal parts, 2 Pieces of squares [a 1 +p / λ×(a 2 -a 1 ), a 1 +(p+1) / λ×(a 2 -a 1 )]×[b 1 +q / λ×(b 2 -b 1 ), b 1 +(q+1) / λ×(b 2 -b 1 )](p=0, …, λ-1, q=0, …, λ-1), and W λ (λ=1, …, N) is the λ generated by the λ-th mass generation method. 2 Let λ be the number of squares that contain less than K data points. 2 Divided by μ λ (λ=1, …, N) is the average number of data included in the masses generated by the λ-th mass generation method, N / ν λ (However, ν λ is the λ generated by the λ-th mass generation method. 2 The number of squares that contain at least one data point among the squares, W 1 <β, W 2 <β, …, W L <β, W L+1 ≧β,μ 1 >μ 2 > … >μ L or W 1 <β, W 2 <β, …, W L <β,μ 1 >μ 2 > … >μ L , μ L ≦μ L+1 The first interval [a 1 , a 2 ] and the second section [b 1 , b 2 ] is divided into L equal parts, and the (p, q)th cell [a 1 +p / L×(a 2 -a 1 ), a 1 +(p+1) / L×(a 2 -a 1 )]×[b 1 +q / L×(b 2 -b 1 ), b 1 +(q+1) / L×(b 2 -b 1 )](p=0, …, L-1, q=0, …, L-1) and a mass generator that generates N data (x n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q A counting section that counts (p=0, …, L-1, q=0, …, L-1) and the number of data contained in the (p, q)th square, N p,q If is K or more, the number of data in the (p, q)th cell is N p,q The (p, q)th circle represents the (p, q)th data (where the size of the circle is the number of data contained in the (p, q)th cell, N p,q A plot unit that plots (p=0, ..., L-1, q=0, ..., L-1) corresponding to the circle whose center is a point included in the (p, q)th square (p=0, ..., L-1, q=0, ..., L-1); and 4. The data display device according to any one of claims 1 to 3, wherein the center of the (p, q)th circle is (a 1 +(2p+1) / 2L×(a 2 -a 1 ), b 1 +(2q+1) / 2L×(b 2 -b 1 )) is a point represented by the data display device.

5. A data display device according to any one of claims 1 to 3, characterized in that the center of the (p, q)th circle is a point whose x-coordinate value and y-coordinate value are the average values ​​of the x-coordinate values ​​and the average values ​​of the y-coordinate values ​​of the data contained in the (p, q)th square, respectively.

6. A data display device according to any one of claims 1 to 3, characterized in that the (p, q)th circle is a circle represented by a color or pattern corresponding to the number of data contained in the square.

7. (x n , y n )(n=1, …, N) is N pieces of data (where N is an integer equal to or greater than 2), and the data display device displays the N pieces of data (x n , y n ) (n=1, …, N) to find the first interval [a 1 , a 2 ] (where a 1 is a 1 ≦min(x n ) and a 2 is max(x n )≦a 2 ) and the second interval [b 1 , b 2 ] (where b 1 HA 1 ≦min(y n ) and b 2 is max(y n )≦b 2 where α is a real number satisfying 0<α<1, and the data display device generates an interval L 2 ≦αN<(L+1) 2 The first interval [a 1 , a 2 ] and the second section [b 1 , b 2 ] is divided into L equal parts, and the (p, q)th cell [a 1 +p / L×(a 2 -a 1 ), a 1 +(p+1) / L×(a 2 -a 1 )]×[b 1 +q / L×(b 2 -b 1 ), b 1 +(q+1) / L×(b 2 -b 1 )](p=0, ..., L-1, q=0, ..., L-1) is generated by the data display device. n , y n ) (n=1, …, N) the number of data contained in the (p, q)th square, N p,q A counting step of counting (p=0, ..., L-1, q=0, ..., L-1); and the data display device counts the number of data N contained in the (p, q)th cell. p,q The (p, q)th circle represents the (p, q)th data (where the size of the circle is the number of data contained in the (p, q)th cell, N p,q a plotting step of plotting (p=0, ..., L-1, q=0, ..., L-1) corresponding to the circle whose center is a point included in the (p, q)th square (p, q=0, ..., L-1).

8. A program for causing a computer to function as the data display device according to any one of claims 1 to 6.

Citation Information

Patent Citations

  • Network anomaly detection method and device and network equipment

    CN114501520A

  • Ad hoc network topological graph layout method and device, computer equipment and storage medium

    CN115795750A