Infrared pair tube layout optimization method, system and storage medium of touch screen

Abstract

The application provides an infrared touch screen infrared pair tube layout optimization method, which comprises the following steps: acquiring an edge light signal distribution curve of the infrared touch screen and determining an edge to be optimized which needs to be optimized in edge light signal distribution; designing a first optimization model for optimizing infrared pair tube coordinates of the edge to be optimized, introducing a genetic algorithm to solve the first optimization model, and obtaining optimized coordinates of the edge to be optimized; and designing a second optimization model for optimizing infrared line spacing of the infrared touch screen, introducing a genetic algorithm to solve the second optimization model, and obtaining optimized coordinate layout of the infrared pair tube from a Pareto optimal solution of the second optimization model. The application designs an infrared touch screen infrared pair tube layout optimization model and introduces a genetic algorithm to solve the optimization model, gives one or more reasonable infrared pair tube layouts, improves uniformity of infrared line distribution in the touch screen, and improves working performance of the touch screen.

Description

Technical Field

[0001] This application belongs to the field of touch technology, specifically relating to a method, system, and storage medium for optimizing the layout of infrared photocells in a touch screen. Background Technology

[0002] An infrared touchscreen is an electronic device that uses a dense matrix of infrared rays to detect and locate human touch gestures. It consists of a circuit board frame mounted in front of the screen, on which infrared emitters and receivers are arranged. These emitters and receivers are interconnected, forming a complex infrared detection network. Traditional infrared touchscreens use an orthogonal layout, which, limited by the size of the infrared emitters and receivers, cannot generate a high-density infrared detection network, resulting in low touchscreen resolution and low touch point positioning accuracy. Modern infrared touchscreens widely use wide-angle infrared diodes. The infrared emitters emit a fan-shaped infrared beam, and multiple infrared receivers are installed within this fan-shaped area. The photosensitive elements inside the receivers convert the infrared signal into an electrical signal, thus forming a straight infrared light path between the emitters and receivers. When an object blocks this light path, the receiver cannot receive a signal. This characteristic is the basis for touch point positioning in infrared touchscreens. The main control unit analyzes the blocked infrared information and converts it into touch point coordinates, thereby enabling the touchscreen's functionality. The layout of the infrared photocells at the edge of the infrared touchscreen directly determines the shape of the infrared detection network, and thus has a direct impact on the performance of the touchscreen.

[0003] Several indicators can be used to evaluate the shape of an infrared detection network, including: the number of infrared rays, the number of intersections generated by the infrared rays, and the uniformity of the intersection distribution. A reasonable layout of infrared photocells is needed to comprehensively optimize the infrared detection network shape. Summary of the Invention

[0004] To address the aforementioned problems, the first aspect of this application proposes a method for optimizing the layout of infrared photocells in an infrared touchscreen, comprising:

[0005] Obtain the edge light signal distribution curve of the infrared touch screen and identify the edges that need to be optimized to improve their edge light signal distribution;

[0006] The first optimization model is designed to optimize the infrared phototransistor coordinates of the edge to be optimized. A genetic algorithm is introduced to solve the first optimization model to obtain the optimized coordinates of the edge to be optimized.

[0007] as well as,

[0008] A second optimization model is designed to optimize the infrared spacing of the infrared touch screen. A genetic algorithm is introduced to solve the second optimization model, and the optimized coordinate layout of the infrared tubes is obtained from the Pareto optimal solution of the second optimization model.

[0009] Furthermore, the edge light signal distribution curve is the distribution curve of infrared signal value on the edge of the infrared touch screen. The infrared signal value is the infrared signal value received at the edge of the touch screen at each unit distance, provided that there is one infrared emitting tube and one infrared receiving tube at each unit distance of the touch screen edge.

[0010] Furthermore, the optimization objective of the first optimization model is the variance of the set of differences in infrared signal values ​​corresponding to the infrared pairs of the edge to be optimized.

[0011] Furthermore, the optimization objective of the second optimization model includes the infrared spacing in the diagonal region of the infrared touchscreen.

[0012] Furthermore, the optimization objective of the second optimization model also includes the distance distribution between adjacent infrared pairs on the edge.

[0013] Furthermore, the genetic algorithm employs floating-point encoding, introduces a proportional selection operator for population selection, an arithmetic crossover operator for chromosome crossover, and a non-uniform mutation operator for gene value perturbation.

[0014] Furthermore, in the genetic algorithm for solving the first optimization model, an initial coordinate layout is generated based on the light signal distribution curve of the edge to be optimized. The initial coordinate layout satisfies that the infrared tubes are more densely distributed in areas with sparse light signal distribution, and a partial initial population is generated based on the initial coordinate layout.

[0015] Furthermore, the spacing between adjacent infrared pairs at the optimized edges of the first and / or second models is adjusted proportionally to separate the overlapping infrared intersections. The adjusted spacing between adjacent infrared pairs satisfies d1 / d2 > 1.2, where d1 is the distance between the transmitter and receiver tubes and d2 is the distance between the receiver and transmitter tubes.

[0016] The second aspect of this application proposes an infrared photocell layout optimization system for an infrared touchscreen, comprising:

[0017] The edge ray signal distribution curve generation module is configured to acquire the edge ray signal distribution curve of the infrared touch screen and determine the edges that need to be optimized in order to optimize the edge ray signal distribution.

[0018] The edge layout optimization module is configured to design the infrared photocell coordinates of the edge to be optimized using the first optimization model. A genetic algorithm is introduced to solve the first optimization model to obtain the optimized coordinates of the edge to be optimized.

[0019] as well as,

[0020] The infrared photocell layout optimization module is configured to design a second optimization model to optimize the infrared line spacing of the infrared touch screen. A genetic algorithm is introduced to solve the second optimization model, and the optimized coordinate layout of the infrared photocells is obtained from the Pareto optimal solution of the second optimization model.

[0021] A third aspect of this application provides a computer-readable storage medium for optimizing the layout of infrared photocells in an infrared touchscreen, having stored thereon one or more computer programs that, when executed by a computer processor, implement the method described in any of the first aspects.

[0022] This application designs an infrared photocell layout optimization model for infrared touch screens, introduces a genetic algorithm to solve the optimization model, optimizes the coordinates of infrared photocells at the edges of the infrared touch screen, and provides one or more reasonable infrared photocell layouts. It focuses on solving the problem of touch screen performance loss caused by the concentration of infrared light in the central area of ​​the touch screen and the relative sparseness of infrared light in the edge area, improves the uniformity of infrared light distribution inside the touch screen, and enhances the working performance of the touch screen. Attached Figure Description

[0023] The accompanying drawings are provided to aid in further understanding of this application. The elements in the drawings are not necessarily to scale. For ease of description, only the parts relevant to the invention are shown in the drawings.

[0024] Figure 1 This is a flowchart illustrating the infrared photocell layout optimization method for an infrared touchscreen in one embodiment of this application.

[0025] Figure 2 This is a light signal distribution curve of the upper / lower edge of the infrared touch screen in one embodiment of this application;

[0026] Figure 3 This is a light signal distribution curve of the left / right edge of the infrared touch screen in one embodiment of this application;

[0027] Figure 4 This is a schematic diagram illustrating the meaning of mathematical symbols for the first optimization model in one embodiment of this application;

[0028] Figure 5 This is the optimization function value curve of the first optimization model in one embodiment of this application;

[0029] Figure 6 This is a schematic diagram of the spacing between adjacent infrared pairs in one embodiment of this application;

[0030] Figure 7 This is a schematic diagram of an infrared detection network in one embodiment of this application when d1 / d2>1;

[0031] Figure 8This is a schematic diagram of an infrared detection network in one embodiment of this application when d1 / d2>2;

[0032] Figure 9 This is a schematic diagram of an infrared detection network when d1 / d2 = 3 in one embodiment of this application;

[0033] Figure 10 This is a schematic diagram of a half-infrared detection network with infrared pairs uniformly distributed in one embodiment of this application;

[0034] Figure 11 It is the Pareto front-end after the second optimization model iteration is completed in one embodiment of this application;

[0035] Figure 12 This is a description of the statistical region for the number of non-repeating intersections in one embodiment of this application;

[0036] Figure 13 This is a comparison of the number of non-repeating intersections between the optimized layout and the traditional layout in one embodiment of this application. Detailed Implementation

[0037] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention.

[0038] Figure 1 This is a flowchart illustrating a method for optimizing the infrared transistor layout of an infrared touchscreen according to an embodiment of the first aspect of this application. This embodiment designs an optimization model for the infrared transistor layout and introduces a genetic algorithm to solve the optimization model, thereby obtaining an optimized layout of one or a group of infrared transistors. Specifically, it includes the following steps:

[0039] S1, acquire the edge light signal distribution curve of the infrared touch screen and determine the edge to be optimized that needs to optimize the edge light signal distribution.

[0040] Specifically, obtain the relevant basic information of the infrared touch screen, including the touch screen length, touch screen width, number of infrared photocells, and diffraction angle of the infrared photocells. Assuming there is one infrared emitter and one infrared receiver at each unit distance of the touch screen edge, the edge light signal distribution curve of the infrared touch screen can be obtained by counting the infrared signal value received at each unit distance.

[0041] In this embodiment, the infrared touchscreen is 197.7 cm long and 116 cm wide, with an infrared tube diffraction angle of 120°. Using 1 mm as the unit distance, the upper and lower edges can be divided into 1977 segments, and the left and right edges into 1160 segments. Ignoring the actual size of the infrared tubes, assuming each segment contains one infrared emitter and one receiver, the light signal distribution curves of the upper and lower edges of the infrared touchscreen are obtained as follows: Figure 2 As shown, the light signal distribution curves at the left and right edges are as follows: Figure 3 As shown. Reference Figure 2 and Figure 3 As can be seen, the light signal distribution curves on the left and right edges of the touchscreen can be almost regarded as horizontal line segments, so there is no need to adjust the coordinates of the infrared photodiode to improve the light signal distribution. However, the light signal distribution curves on the top and bottom edges of the touchscreen show a phenomenon that remains unchanged from the center to both sides and then gradually decreases, thus determining that the top or bottom edge of the touchscreen is the edge where the edge light signal distribution needs to be optimized.

[0042] Touchscreens with different aspect ratios have different edge light signal distribution curves. In other embodiments, the aspect ratio of the touchscreen approaches 1:1, and the edge light signal distribution curves of the left and right edges are also curves rather than horizontal line segments, so the left and right edges also need to be optimized.

[0043] S2, Design a first optimization model to optimize the infrared phototransistor coordinates of the edge to be optimized, and introduce a genetic algorithm to solve the first optimization model to obtain the optimized coordinates of the edge to be optimized.

[0044] Specifically, each infrared pair on the upper and lower edges has a corresponding light signal value. The infrared pair includes an infrared emitter and an infrared receiver. The difference between the infrared signal values ​​corresponding to every two adjacent infrared pairs is calculated. The variance of the set of differences is used as the optimization objective of the first optimization model. The optimization model is designed as follows:

[0045]

[0046] Among them, reference Figure 4 x i Let m be the horizontal coordinate value of the i-th infrared pair. i Let Δ be the light signal value of the i-th infrared pair. i is the overlapping area of ​​the light signal coverage area of ​​the i-th infrared pair and the (i+1)-th infrared pair, that is, the difference in infrared signal values ​​corresponding to adjacent infrared pairs; n is the number of infrared pairs arranged on the upper or lower edge of the touch screen. In this embodiment, the value of n is 80.

[0047] A genetic algorithm is introduced to solve the above optimization model. In the genetic algorithm, the chromosome of an individual represents the coordinates of the infrared photocells on the edge to be optimized, and the gene represents the coordinates of each infrared photocell. The encoding length of the chromosome is equal to the number of its decision variables, i.e., the number of infrared photocells deployed on the edge to be optimized. In this embodiment, the encoding method used by the genetic algorithm is floating-point encoding, which uses a floating-point number limited to the length range of the touchscreen. Using floating-point encoding is suitable for representing the coordinates of infrared photocells distributed over a large area, suitable for solving for higher precision infrared photocell coordinates, and can also improve the computational complexity and efficiency of the genetic algorithm.

[0048] The selection operation in genetic algorithms is used to select superior individuals from the current population, giving them the opportunity to serve as parents and reproduce for the next generation, thus increasing the probability that highly adaptable individuals will contribute to the next generation. The selection operation is based on the evaluation of an individual's fitness. In this embodiment, a proportional selection operator and an optimal preservation strategy are used to screen the population through proportional selection. The reciprocal of the objective function value in the above optimization model is taken as the fitness value of the genotype individual. The fitness evaluation function used by the genetic algorithm is:

[0049] f(x) = 1 / Var(Δ i ), i∈[1,m-1],i∈N

[0050] Proportional selection ensures that the probability of each individual being selected is proportional to its fitness, and the probability of an individual being selected is:

[0051]

[0052] Among them, F i Let be the fitness value of individual i, and N be the number of individuals in the population, i.e., the number of infrared pairs on the edge to be optimized.

[0053] In this embodiment, the crossover operation of the genetic algorithm uses the arithmetic crossover operator. Specifically, the k-th chromosome a k and the l-th chromosome a l The method for crossover at position j is as follows:

[0054] a kj =a kj (1-b)+a lj b

[0055] a lj =a lj (1-b)+a kj b

[0056] Where b is a random number in the interval [0,1].

[0057] In this embodiment, a non-uniform mutation operator is introduced. A random perturbation is input based on the original gene values, and the result of the perturbation is used as the new gene value, which facilitates focused local searches. Specifically, the mutation operation for the j-th gene 'a' of the i-th individual is as follows:

[0058]

[0059] Among them, a max It is gene a ij The upper bound; a min It is gene a ij The lower bound; r2 is a random number, g is the current iteration number, and G... max is the maximum number of evolutions, and r is a random number in the interval [0,1].

[0060] In this embodiment, a portion of the initial population is generated based on the light signal distribution curve. Specifically, a coordinate layout is derived according to the principle that the difference in coordinates between infrared photocells is proportional to the corresponding value on their light signal distribution curves. Thus, infrared photocells are placed more densely in areas where the light signal distribution is sparse. Subsequently, each photocell is randomly varied within the constraints between its coordinates and those of its left and right counterparts, based on the obtained coordinates, to generate a coordinate layout that roughly conforms to the light signal distribution pattern.

[0061] Figure 5 This is the optimization function value curve of the first optimization model in this embodiment. In this embodiment, the genetic algorithm has 200 generations, a population size of 500, a crossover probability of 0.8, a mutation probability of 0.1, and 10% of the initial population consists of 50 coordinate layouts generated based on the light signal distribution curve, while the rest are randomly generated. Figure 5 It is evident that the objective function converges rapidly during the iteration process, demonstrating the effectiveness of the encoding method, the selection of selection, crossover, and mutation operators, and the initial population generation scheme.

[0062] After optimizing the layout of the infrared photocells at the top and bottom edges, connecting the infrared photocells to the touchscreen at that edge and proportionally adjusting the distance between adjacent infrared photocells can achieve a more uniform infrared detection network within the touchscreen area. Specifically, refer to... Figure 6 The distance between adjacent infrared pairs is shown in the figure. The distance between the transmitting tube and the receiving tube is denoted as d1, and the distance between the receiving tube and the transmitting tube is denoted as d2. Gradually increase d1 / d2 and record the infrared detection network and the corresponding repeated infrared intersections. For specific testing methods, please refer to US Patent No. 10001881B2. Figures 7-9 This is a schematic diagram of an infrared detection network with different ratios of adjacent infrared tube spacing. In this embodiment, after multiple experiments, such as... Figure 7As shown, when d1 / d2>1, repeating infrared intersections begin to separate within the touchscreen area, and a large hole exists in the central area of ​​the touchscreen; as... Figure 8 As shown, when d1 / d2>2, the infrared pairs connected at the top and bottom edges within the touchscreen area diffuse outwards to the left and right edges, creating a dense area of ​​intersection points. Figure 9 As shown, when d1 / d2 = 3, the infrared pairs connecting the upper and lower edges within the touchscreen area are covered by the intersection of diffused infrared rays.

[0063] S3. Design a second optimization model to optimize the infrared spacing of the infrared touch screen. Introduce a genetic algorithm to solve the second optimization model and obtain the Pareto optimal solution for the infrared pair layout.

[0064] With equidistant distribution on the left and right edges and an optimized coordinate layout on the top and bottom edges, the infrared photocells at the bottom and left edges of the touchscreen are connected separately to generate a partial infrared detection network, such as... Figure 10 As shown. Reference Figure 10 It can be observed that as the infrared detection network extends diagonally from the center of the touchscreen towards the four corners, it gradually becomes sparser. This negatively impacts the touch point positioning performance of the infrared touchscreen. Therefore, the distance between infrared rays in the infrared detection network formed by connecting the infrared pairs at the bottom and left edges is converted into an observable, calculable, and modifiable value. The spacing between infrared rays in the diagonal region is used as one of the optimization objectives of the second optimization model. Simultaneously, to avoid the infrared pairs at the left and right edges of the touchscreen gradually becoming extremely irregular and disordered during the optimization algorithm iteration process, the distance distribution between every two adjacent infrared pairs at the left and right edges of the touchscreen is also used as one of the optimization objectives of the second optimization model. In this embodiment, the second optimization model is designed as follows:

[0065]

[0066] In A·x + B·y + C = 0, A = [a1, a2, ..., a m ] T B = [b1, b2, ..., b m ] T C = [c1, c2, ..., c m ] T , is the mathematical expression for the infrared lines generated after connecting the lower half of the infrared phototransistor on the left edge of the touchscreen to the lower half of the infrared phototransistor on the left edge of the touchscreen, with a total of m infrared lines; D is a 1*m one-dimensional matrix, except for the i-th position which is 1, all others are 0; In this context, w represents the width of the touchscreen, l represents the length of the touchscreen, and h represents the width of the touchscreen's border. Coordinates within the border area cannot be touched by the user and are invalid coordinates. Therefore, the border width is introduced to restrict the coordinates of the infrared photodiode, preventing coordinates from being generated within the border edge area; (x i ,y i The infrared light and straight line generated by connecting the infrared phototransistors at the left and bottom edges of the touchscreen. The coordinates of the i-th intersection point generated by the intersection; s j is the ordinate of the j-th infrared pair on the left edge of the touchscreen; m is half the number of infrared pairs on the left edge of the touchscreen; in this embodiment, w is 116, l is 197.7, h is 0.8, and m is 30.

[0067] A genetic algorithm is introduced to solve the second optimization model of the design. Specifically, the encoding method and selection, crossover, and mutation operators of the genetic algorithm are selected with reference to the method in S2. In this embodiment, the number of iteration rounds is set to 200, and the population size is 1000. During each iteration, the Pareto front is obtained, and its distribution is updated once with each generation of algorithm evolution. After the iteration is completed, the Pareto front is plotted as follows: Figure 11 As shown, the solution numbers are also given in the figure. Considering the two objective functions of multi-objective optimization according to the principle of equal weight, in this embodiment, one selected layout coordinate set is... Figure 11 The solution with index 12 in the list.

[0068] The layout optimization effect of this embodiment can be illustrated by comparing the number of non-repeating intersections in a touchscreen with a traditional layout. For example... Figure 12 As shown, for a touchscreen with length l and width w, region A is a rectangle centered on the geometric center of the touchscreen, with length l1 and width w1, where l1 / l = w1 / w. Region B is a gray area, representing the outer edge of the touchscreen excluding rectangular region A. In this embodiment, the repetitive infrared intersections are separated when d1 / d2 = 1.2 at the top and bottom edges of the touchscreen. The area of ​​region A is gradually increased from 0 until it covers the entire touchscreen. The number of non-repetitive intersections in region B is counted. Figure 13 As shown, the horizontal x-axis represents the value of l1 / l*100%, the vertical y-axis represents the number of non-repeating intersections of coordinates in region B, the solid line represents the traditional equidistant layout, i.e., the infrared pairs are equidistantly distributed at the edges of the touchscreen, and the dashed line represents the optimized layout when d1 / d2 = 1.2. According to... Figure 13It can be seen that in the x-axis range of 0-30%, the number of non-repeating intersections in region B of the optimized layout is consistently greater than that of the traditional layout. As the x-axis increases, the difference in the number of non-repeating intersections in region B between the two layouts decreases. In the x-axis range of 30%-90%, as the x-axis increases, the number of non-repeating intersections in region B of the optimized layout is consistently greater than that of the traditional layout, and the difference in the number of non-repeating intersections in region B between the two layouts remains essentially constant. In the x-axis range of 90%-100%, since the areas of region B in both the optimized and traditional layouts gradually become 0, the number of non-repeating intersections gradually becomes 0. Through analysis... Figure 13 It can be seen that the density of intersection points in the center area of ​​the touch screen is greater than that in the edge area, and the probability of repeated intersection point coordinates is also the same. Compared with the traditional layout, the optimized layout can separate repeated intersection points in the touch screen area and increase the density of the infrared detection network. Since the density of intersection points in the center area is large, the effect of separating repeated intersection points is also obvious, and a stable and considerable separation effect can also be achieved in the edge area.

[0069] The following table shows the relevant data comparing the optimized layout with the traditional layout, using different ratios of d1 / d2 at the top and bottom edges of the touchscreen:

[0070] Table 1 Comparison of the number of intersection points between optimized and traditional layouts.

[0071]

[0072]

[0073] The calculation method for the percentage of intersection points is: corresponding intersection point number / total number of intersection points * 100%. The percentage of intersection points in region B is calculated by removing duplicate intersection points and using the number of non-duplicate intersection points as the total number of intersection points. Comparative data shows that the optimized layout has 2.38%-2.69% fewer intersection points than the traditional uniform layout, and the percentage of duplicate intersection points in the optimized layout is significantly lower than in the traditional layout. After removing duplicate intersection points, the optimized layout has 2.78%-3.06% more intersection points than the traditional layout, indicating that the optimized layout effectively separates duplicate intersection points within the touchscreen area. Simultaneously, observing and comparing different values ​​of l1 / l, when l1 / l = 0.1, the number of intersections in the optimized layout region B is greater than that in the traditional layout, but the proportion of intersections is smaller. As d1 / d2 is selected as 1.2, 2.0, and 3.0 respectively, the number of intersections in the optimized layout region B gradually increases. When l1 / l = 0.5, the number of intersections in the optimized layout region B is greater than that in the traditional layout, but the proportion of intersections is smaller. As d1 / d2 is selected as 1.2, 2.0, and 3.0 respectively, the number of intersections in the optimized layout region B gradually increases. When l1 / l = 0.9, the number of intersections in the optimized layout region B is greater than that in the traditional layout, but the proportion of intersections is greater than that in the traditional layout, indicating that the proportion of intersections in the edge region of the optimized layout is higher than that in the traditional layout. As the value of d1 / d2 is selected as 1.2, 2.0, and 3.0 respectively, the number of intersections in the optimized layout region B gradually increases.

[0074] Comparative experiments showed that the total number of non-repeating intersections in the optimized layout was significantly greater than that in the traditional layout, and the distribution of intersections in the area of ​​intersections achieved the effect of spreading from the central area to the edge area. As the value of d1 / d2 gradually increased, the number of intersections in the touch screen area was effectively improved, indicating that by selecting an appropriate value of d1 / d2 based on the optimized layout, the effect of separating repeating intersections can be further achieved, thereby increasing the density of the infrared detection network.

[0075] This embodiment establishes a layout optimization model for the touchscreen and solves the optimization model using a genetic algorithm. Specifically, it obtains the light signal distribution curve of the initial layout and establishes an optimization model for the infrared photocell layout of the upper and lower edges of the touchscreen based on the light signal distribution curve of the initial layout. The genetic algorithm is used to solve the optimal solution of the optimization model for the infrared photocell layout of the upper and lower edges of the touchscreen to determine the coordinates of the infrared photocells at the upper and lower edges of the touchscreen. Subsequently, a multi-objective optimization model for the infrared photocell layout of the lower and left edges is established. The genetic algorithm is used to solve the multi-objective optimization model to determine the coordinates of the infrared photocells at the left and right edges of the touchscreen.

[0076] Although the contents of this application have been specifically shown and described in conjunction with preferred embodiments, those skilled in the art should understand that any changes in form and detail made to this application without departing from the spirit and scope of this application as defined by the appended claims and without inventive effort are within the scope of protection of this application.

Claims

1. A method for optimizing the layout of infrared photocells in an infrared touchscreen, characterized in that, include: The edge light signal distribution curve of the infrared touch screen is obtained and the edge to be optimized is determined. The edge light signal distribution curve is the distribution curve of infrared signal value on the edge of the infrared touch screen. The infrared signal value is the infrared signal value received at the edge of the touch screen at a unit distance, under the condition that there is one infrared emitting tube and one infrared receiving tube at each unit distance of the touch screen edge. A first optimization model is designed to optimize the coordinates of the infrared phototransistors of the edge to be optimized. A genetic algorithm is introduced to solve the first optimization model to obtain the optimized coordinates of the edge to be optimized. The optimization objective of the first optimization model is the variance of the set of differences in infrared signal values ​​corresponding to the infrared phototransistors of the edge to be optimized. Furthermore, a second optimization model is designed to optimize the infrared spacing of the infrared touchscreen. A genetic algorithm is introduced to solve the second optimization model to obtain the Pareto optimal solution. The optimized coordinate layout of the infrared photocells is determined from the Pareto optimal solution of the second optimization model. The optimization objectives of the second optimization model include the infrared spacing in the diagonal region of the infrared touchscreen, as well as the distance distribution between adjacent infrared photocells on the edge. Finally, the spacing between adjacent infrared photocells on the edge after optimization by the first model and / or the second model is adjusted proportionally to separate the overlapping infrared intersections. The adjusted spacing between adjacent infrared photocells satisfies d1 / d2 > 1.2, where d1 is the distance between the transmitter and receiver, and d2 is the distance between the transmitter and receiver.

2. The infrared photocell layout optimization method for an infrared touchscreen according to claim 1, characterized in that, The genetic algorithm employs a floating-point encoding method, introduces a proportional selection operator for population selection, an arithmetic crossover operator for chromosome crossover, and a non-uniform mutation operator for gene value perturbation.

3. The infrared photocell layout optimization method for an infrared touchscreen according to claim 1, characterized in that, In the genetic algorithm for solving the first optimization model, an initial coordinate layout is generated based on the light signal distribution curve of the edge to be optimized. The initial coordinate layout satisfies that the infrared tubes are more densely distributed in areas with sparse light signal distribution. A partial initial population is generated based on the initial coordinate layout.

4. An infrared photocell layout optimization system for an infrared touchscreen, characterized in that, A method for optimizing the infrared photocell layout of an infrared touchscreen according to claim 1 includes: an edge light signal distribution curve generation module configured to acquire the edge light signal distribution curve of the infrared touchscreen and determine the edge to be optimized; an edge layout optimization module configured to design a first optimization model to optimize the infrared photocell coordinates of the edge to be optimized, and to introduce a genetic algorithm to solve the first optimization model to obtain the optimized coordinates of the edge to be optimized; and an infrared photocell layout optimization module configured to design a second optimization model to optimize the infrared spacing of the infrared touchscreen, and to introduce a genetic algorithm to solve the second optimization model to obtain the optimized coordinate layout of the infrared photocell from the Pareto optimal solution of the second optimization model.

5. A computer-readable storage medium for optimizing the layout of infrared photocells in an infrared touchscreen, wherein one or more computer programs are stored thereon, characterized in that, When the one or more computer programs are executed by a computer processor, they perform the method according to any one of claims 1-3.

Images