A drawing path optimization system and method based on AI

Abstract

The present invention belongs to the field of drawing path optimization, relates to data analysis technology, and is used to solve the problem that the prior art cannot optimize the generated path information. Specifically, it is an Ai-based drawing path optimization system and method, including a server, wherein the server is communicatively connected with a path generation module, a necessary analysis module, an optimization analysis module, an optimization evaluation module, and a database; the path generation module is used to generate drawing path information according to imported pictures or texts, and the path information includes several groups, each of which includes several anchor points; the optimization analysis module is used to optimize and analyze the path information and obtain several benchmark groups and unified merged groups; the present invention can eliminate the benchmark group and then form a unified merged group through optimization processing, so that the task allocation amount of the execution components of the unified merged group and the benchmark group in the optimization path reaches a balanced state, saving drawing task execution resources while improving drawing efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of drawing path optimization and relates to data analysis technology, and specifically is a drawing path optimization system and method based on Ai. Background Art

[0002] AI technology automatically converts images into vector paths through artificial intelligence technology. This type of function not only improves design efficiency, but also makes design works more creative and flexible.

[0003] The drawing path optimization system in the prior art can only perform image drawing according to the path information generated by the shape generator, but cannot optimize the generated path information. In particular, when the number of anchor points of each group in the path information deviates greatly, the amount of tasks allocated to the drawing components corresponding to each group is uneven, resulting in low overall drawing efficiency.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a drawing path optimization system and method based on Ai, which is used to solve the problem that the prior art cannot optimize the generated path information;

[0006] The technical problem to be solved by the present invention is: how to provide an Ai-based drawing path optimization system and method that can optimize the generated path information.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An Ai-based drawing path optimization system includes a server, wherein the server is communicatively connected with a path generation module, a necessary analysis module, an optimization analysis module, an optimization evaluation module, and a database;

[0009] The path generation module is used to generate drawing path information according to the imported pictures or texts, and the path information includes a number of groups, each of which includes a number of anchor points;

[0010] The necessary analysis module is used to perform optimization necessity analysis on the path information: obtain the optimization necessary value YB of the drawing task; determine the necessity of optimizing the path information of the drawing task by optimizing the necessary value YB;

[0011] The optimization analysis module is used to optimize and analyze the path information and obtain a number of benchmark groups and unified merged groups; all unified merged groups and benchmark groups constitute an optimized path, and the optimized path is sent to the server;

[0012] The optimization evaluation module is used to evaluate and analyze the optimization effect of the drawing path.

[0013] Furthermore, the process of obtaining the optimized necessary value YB of the drawing task includes: obtaining the number of groups in the drawing task and marking it as the processing value CL, obtaining the number of anchor points in each group and marking it as the group's anchor point value; performing variance calculation on the anchor point values ​​of all groups to obtain the centralized value JZ of the drawing task; and obtaining the optimized necessary value YB of the drawing task through the formula YB=k1*CL+k2*JZ, wherein k1 and k2 are both proportional coefficients, and k1>k2>1.

[0014] Furthermore, the specific process of determining the necessity of optimizing the path information of the drawing task includes: retrieving the necessary optimization threshold value YBmax through the database, and comparing the necessary optimization value YB with the necessary optimization threshold value YBmax: if the necessary optimization value YB is less than the necessary optimization threshold value YBmax; then it is determined that the path information of the drawing task does not need to be optimized, a drawing execution signal is generated and the drawing execution signal is sent to the server; if the necessary optimization value YB is greater than or equal to the necessary optimization threshold value YBmax, then it is determined that the path information of the drawing task needs to be optimized, an optimization analysis signal is generated and the optimization analysis signal is sent to the optimization analysis module through the server.

[0015] Furthermore, the process of obtaining the benchmark group includes: obtaining the concentration threshold JZmax through the storage module, comparing the concentration coefficient JZ of the drawing task path information with the concentration threshold JZmax: if the concentration coefficient JZ is greater than or equal to the concentration threshold JZmax, then eliminating the grouping with the largest numerical value of the drawing point in the path information, and then recalculating the concentration coefficient JZ until the concentration coefficient JZ is less than the concentration threshold JZmax; if the concentration coefficient JZ is less than the concentration threshold JZmax, then marking all eliminated groups as benchmark groups, and optimizing the path information.

[0016] Furthermore, the specific process of optimizing the path information includes: summing and averaging the point values ​​of all benchmark groups to obtain a combined evaluation value ZP, arranging the remaining groups in order of the point values ​​from small to large to obtain a unified sequence, marking the first-ranked group as a processing object, summing and averaging the point values ​​of all eliminated groups to obtain a combined evaluation value ZP, and obtaining a combined evaluation low value ZPmin and a combined evaluation high value ZPmax through the formulas ZPmin=t1*ZP and ZPmax=t2*ZP, where t1 and t2 are both proportional coefficients, and 0.92≤t1≤0.95, 1.05≤t 2≤1.08; the combined evaluation range is formed by the combined evaluation low value ZPmin and the combined evaluation high value ZPmax, and the grouping whose sum of the tracing point value and the processing object tracing point value is within the combined evaluation range is marked as the associated object of the processing object; the straight-line distance between the central tracing point of the processing object and the central tracing points of all associated objects is calculated and marked as the preferred value of the associated object relative to the processing object, and the associated object with the smallest preferred value and the processing object form the first unified merged group; then the second ranked grouping is marked as the processing object and the second unified merged group is formed, and so on, until all the groups in the unified sequence are divided into the corresponding unified merged groups.

[0017] Furthermore, the specific process of the optimization evaluation module evaluating and analyzing the optimization effect of the drawing path includes: generating an evaluation cycle, obtaining the optimization effect coefficient of the evaluation cycle, obtaining the optimization effect threshold through the database, and comparing the optimization effect coefficient of the evaluation cycle with the optimization effect threshold: if the optimization effect coefficient is less than the optimization effect threshold, the necessary optimization threshold YBmax is adjusted upward: the necessary optimization update value YBn is obtained by the formula YBn=t3*YBmax, where t3 is the proportional coefficient, and 1.05≤t3≤1.15; the necessary optimization update value YBn is used to replace the necessary optimization threshold YBmax; if the optimization effect coefficient is greater than or equal to the optimization effect threshold, no processing is performed.

[0018] Furthermore, the process of obtaining the optimization effect coefficient of the evaluation cycle includes: calling several drawing tasks that execute the optimized path in the evaluation cycle and marking them as evaluation objects, obtaining the time difference between the evaluation object when the path information is generated and the drawing is completed and marking it as the optimization duration value of the evaluation object, then executing the drawing task according to the generated path information, recording the drawing duration and marking it as the basic duration value, marking the difference between the basic duration value and the optimized duration value as the optimization effect value of the evaluation object, and summing and averaging the optimization effect values ​​of all evaluation objects to obtain the optimization effect coefficient.

[0019] A drawing path optimization method based on AI, comprising the following steps:

[0020] Step 1: Generate drawing path information based on the imported picture or text;

[0021] Step 2: Analyze the necessity of optimizing the path information and obtain the necessary optimization value YB of the path information. Determine whether the path information of the drawing task needs to be optimized by using the necessary optimization value YB. If optimization is required, execute step 3.

[0022] Step 3: Analyze the necessity of optimizing the path information and obtain several benchmark groups and unified merged groups, which constitute the optimized path;

[0023] Step 4: Evaluate and analyze the optimization effect of the drawing path: generate an evaluation cycle, obtain the optimization effect coefficient of the evaluation cycle, and evaluate the optimization effect of the drawing path within the evaluation cycle through the optimization effect coefficient.

[0024] The present invention has the following beneficial effects:

[0025] 1. The necessary analysis module can be used to analyze the necessity of optimizing the path information. The number of groups in the drawing task and the discrete degree of the number of anchor points in all groups can be comprehensively analyzed and calculated to obtain the necessary optimization value. According to the necessary optimization value, the necessary degree of optimization of the path information of the drawing task can be evaluated, and the path information can be optimized and screened. The path information that does not need to be optimized can directly execute the drawing task, thereby improving the overall Ai drawing efficiency;

[0026] 2. The optimization analysis module can be used to optimize and analyze the path information. After eliminating the benchmark group, the unified merged group is formed through optimization processing, and then a new optimization path is formed, so that the task allocation of the execution components of the unified merged group and the benchmark group in the optimization path reaches a balanced state, saving drawing task execution resources while improving drawing efficiency;

[0027] 3. The optimization evaluation module can be used to evaluate and analyze the optimization effect of the drawing path. The execution efficiency of the drawing task of the optimized path can be analyzed in a periodic evaluation manner, and then the drawing efficiency of the original path information can be compared. The optimization effect of the drawing path can be evaluated based on the comparison results. When the optimization effect is not obvious, the optimization necessity analysis link can be optimized to further improve the drawing efficiency as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 is a system block diagram of Embodiment 1 of the present invention;

[0030] Figure 2 This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0031] The technical scheme of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Embodiment 1: Figure 1 As shown, an Ai-based drawing path optimization system includes a server, and the server is communicatively connected to a path generation module, a necessary analysis module, an optimization analysis module, an optimization evaluation module and a database.

[0033] The path generation module is used to generate drawing path information based on imported pictures or texts. The path information includes several groups, each of which contains several anchor points. This process is mainly completed through the shape generator. The shape generator is a graphic creation and editing tool that can automatically generate various shapes according to user needs. It can help designers quickly create and edit complex shapes and enhance design efficiency. The required shapes can be quickly generated through operations such as dragging, merging, and splitting. The generated shapes have vector characteristics, which are convenient for subsequent editing and adjustment.

[0034] The necessity analysis module is used to perform necessity analysis on the optimization of the path information: obtain the number of groups in the drawing task and mark it as the processing value CL, obtain the number of anchor points in each group and mark it as the group's plotting value; perform variance calculation on the plotting values ​​of all groups to obtain the centralized value JZ of the drawing task; obtain the optimization necessary value YB of the drawing task through the formula YB=k1*CL+k2*JZ, where k1 and k2 are both proportional coefficients, and k1>k2>1; retrieve the optimization necessary threshold YBmax through the database, and compare the optimization necessary value YB with the optimization necessary threshold YBmax: if the optimization necessary value YB is less than the optimization necessary threshold YBmax; then determine that the drawing task The path information does not need to be optimized, a drawing execution signal is generated and sent to the server; if the necessary optimization value YB is greater than or equal to the necessary optimization threshold YBmax, it is determined that the path information of the drawing task needs to be optimized, an optimization analysis signal is generated and the optimization analysis signal is sent to the optimization analysis module through the server; the discrete degree of the number of groups in the drawing task and the number of anchor points in all groups is comprehensively analyzed and calculated to obtain the necessary optimization value, and the necessary degree of optimization of the path information of the drawing task is evaluated according to the necessary optimization value, and the path information is optimized and screened. The path information that does not need to be optimized can directly execute the drawing task, thereby improving the overall Ai drawing efficiency.

[0035] The optimization analysis module is used to optimize and analyze the path information: obtain the concentration threshold JZmax through the storage module, and compare the concentration coefficient JZ of the drawing task path information with the concentration threshold JZmax: if the concentration coefficient JZ is greater than or equal to the concentration threshold JZmax, the group with the largest point value in the path information is eliminated, and then the concentration coefficient JZ is recalculated until the concentration coefficient JZ is less than the concentration threshold JZmax; if the concentration coefficient JZ is less than the concentration threshold JZmax, the path information is optimized: all eliminated groups are marked as benchmark groups, the point values ​​of all benchmark groups are summed and averaged to obtain the combined evaluation value ZP, the remaining groups are arranged in order from small to large in the order of the point values ​​to obtain a unified sequence, the first ranked group is marked as the processing object, the point values ​​of all eliminated groups are summed and averaged to obtain the combined evaluation value ZP, and the combined evaluation low value ZPmin and the combined evaluation high value ZPmax are obtained by the formula ZPmin=t1*ZP and ZPmax=t2*ZP, where t1 and t2 are both ratios. Example coefficient, and 0.92≤t1≤0.95, 1.05≤t2≤1.08; the combined evaluation range is formed by the combined evaluation low value ZPmin and the combined evaluation high value ZPmax, and the group whose sum of the plotted point value and the processed object plotted point value is within the combined evaluation range is marked as the associated object of the processed object; the straight-line distance between the central plotted point of the processed object and the central plotted points of all associated objects is calculated and marked as the preferred value of the associated object relative to the processed object, and the associated object with the smallest preferred value and the processed object form the first unified merged group; then the group ranked second is marked as the processed object and the second unified merged group is formed, and so on, until all the groups in the unified sequence are divided into the corresponding unified merged groups; all the unified merged groups and the benchmark group form an optimization path, and the optimization path is sent to the server; after the benchmark group is eliminated, the unified merged group is formed through optimization processing, and then a new optimization path is formed, so that the task allocation amount of the execution components of the unified merged group and the benchmark group in the optimization path reaches a balanced state, saving drawing task execution resources while improving drawing efficiency.

[0036] The optimization evaluation module is used to evaluate and analyze the optimization effect of the drawing path: generate an evaluation cycle, call several drawing tasks that execute the optimized path in the evaluation cycle and mark them as evaluation objects, obtain the time difference between the time when the path information is generated and the time when the drawing is completed and mark it as the optimization duration value of the evaluation object, then execute the drawing task according to the generated path information, record the drawing duration and mark it as the basic duration value, mark the difference between the basic duration value and the optimized duration value as the optimization effect value of the evaluation object, sum and average the optimization effect values ​​of all evaluation objects to obtain the optimization effect coefficient, obtain the optimization effect threshold through the database, and compare the optimization effect coefficient of the evaluation cycle with the optimization effect threshold: if the optimization effect coefficient If it is less than the optimization effect threshold, the necessary optimization threshold YBmax is adjusted upward: the necessary optimization update value YBn is obtained by the formula YBn=t3*YBmax, where t3 is the proportional coefficient, and 1.05≤t3≤1.15; the necessary optimization update value YBn is used to replace the necessary optimization threshold YBmax; if the optimization effect coefficient is greater than or equal to the optimization effect threshold, no processing is performed; the drawing task execution efficiency of the optimization path is analyzed in a periodic evaluation manner, and then the drawing efficiency of the original path information is compared, and the optimization effect of the drawing path is evaluated according to the comparison result. When the optimization effect is not obvious, the optimization necessity analysis link is optimized to further improve the drawing efficiency as a whole.

[0037] Embodiment 2: Figure 2 As shown, a drawing path optimization method of Ai includes the following steps:

[0038] Step 1: Generate drawing path information based on the imported picture or text;

[0039] Step 2: Analyze the necessity of optimizing the path information and obtain the necessary optimization value YB of the path information. Determine whether the path information of the drawing task needs to be optimized by using the necessary optimization value YB. If optimization is required, execute step 3.

[0040] Step 3: Analyze the necessity of optimizing the path information and obtain several benchmark groups and unified merged groups, which constitute the optimized path;

[0041] Step 4: Evaluate and analyze the optimization effect of the drawing path: generate an evaluation cycle, obtain the optimization effect coefficient of the evaluation cycle, and evaluate the optimization effect of the drawing path within the evaluation cycle through the optimization effect coefficient.

[0042] A drawing path optimization system and method based on Ai, when working, generates drawing path information according to imported pictures or texts; performs optimization necessity analysis on the path information and obtains the optimization necessary value YB of the path information, determines whether the path information of the drawing task needs to be optimized through the optimization necessary value YB, and performs optimization necessity analysis on the path information when optimization is needed and obtains several benchmark groups and unified merged groups, which constitute an optimization path; generates an evaluation cycle, obtains the optimization effect coefficient of the evaluation cycle, and evaluates the drawing path optimization effect within the evaluation cycle through the optimization effect coefficient.

[0043] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0044] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; such as: formula YB = k1*CL+k2*JZ; technicians in this field collect multiple groups of sample data and set corresponding optimization necessary values ​​for each group of sample data; substitute the set optimization necessary values ​​and the collected sample data into the formula, any two formulas constitute a set of two-variable linear equations, screen the calculated coefficients and take the average, and obtain the values ​​of k1 and k2 as 3.48 and 2.85 respectively;

[0045] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the initial setting of the corresponding optimization necessary value for each group of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the optimization necessary value is proportional to the value of the processed value.

[0046] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0047] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A drawing path optimization system based on Ai, characterized in that: The server comprises a path generation module, a necessary analysis module, an optimization analysis module, an optimization evaluation module and a database; The path generation module is used to generate drawing path information according to the imported pictures or texts, and the path information includes a number of groups, each of which includes a number of anchor points; The necessary analysis module is used to perform optimization necessity analysis on the path information: obtain the optimization necessary value YB of the drawing task; determine the necessity of optimizing the path information of the drawing task by optimizing the necessary value YB; The optimization analysis module is used to optimize and analyze the path information and obtain a number of benchmark groups and unified merged groups; all unified merged groups and benchmark groups constitute an optimized path, and the optimized path is sent to the server; The optimization evaluation module is used to evaluate and analyze the optimization effect of the drawing path; The process of obtaining the optimization necessary value YB of the drawing task includes: obtaining the number of groups in the drawing task and marking it as the processing value CL, obtaining the number of anchor points in each group and marking it as the group's plotting point value; performing variance calculation on the plotting point values ​​of all groups to obtain the central value JZ of the drawing task; obtaining the optimization necessary value YB of the drawing task by the formula YB=k1*CL+k2*JZ, where k1 and k2 are both proportional coefficients, and k1>k2>1; The specific process of determining the necessity of optimizing the path information of the drawing task includes: retrieving the necessary optimization threshold value YBmax through the database, and comparing the necessary optimization value YB with the necessary optimization threshold value YBmax: if the necessary optimization value YB is less than the necessary optimization threshold value YBmax; it is determined that the path information of the drawing task does not need to be optimized, and a drawing execution signal is generated and sent to the server; if the necessary optimization value YB is greater than or equal to the necessary optimization threshold value YBmax, it is determined that the path information of the drawing task needs to be optimized, and an optimization analysis signal is generated and sent to the optimization analysis module through the server; The process of obtaining the benchmark group includes: obtaining the concentration threshold JZmax through the storage module, comparing the concentration value JZ of the drawing task path information with the concentration threshold JZmax: if the concentration value JZ is greater than or equal to the concentration threshold JZmax, then eliminating the group with the largest value of the drawing point value in the path information, and then recalculating the concentration value JZ until the concentration value JZ is less than the concentration threshold JZmax; if the concentration value JZ is less than the concentration threshold JZmax, then marking all the eliminated groups as benchmark groups, and optimizing the path information; The specific process of optimizing the path information includes: summing and averaging the point values ​​of all benchmark groups to obtain the combined evaluation value ZP, arranging the remaining groups in order of the point values ​​from small to large to obtain a unified sequence, marking the first-ranked group as the processing object, summing and averaging the point values ​​of all eliminated groups to obtain the combined evaluation value ZP, and obtaining the combined evaluation low value ZPmin and the combined evaluation high value ZPmax through the formula ZPmin=t1*ZP and ZPmax=t2*ZP, where t1 and t2 are both proportional coefficients, and 0.92≤t1≤0.95, 1.05≤t2≤1.0 8. The combined evaluation range is formed by the combined evaluation low value ZPmin and the combined evaluation high value ZPmax, and the groups whose sum of the plotted point value and the processed object plotted point value in the remaining groups is within the combined evaluation range are marked as associated objects of the processed object; the straight-line distance between the central plotted point of the processed object and the central plotted points of all associated objects is calculated and marked as the preferred value of the associated object relative to the processed object, and the associated object with the smallest preferred value and the processed object form the first unified merged group; then the second ranked group is marked as the processed object and the second unified merged group is formed, and so on, until all the groups in the unified sequence are divided into the corresponding unified merged groups.

2. The drawing path optimization system based on Ai according to claim 1, characterized in that: The specific process of the optimization evaluation module evaluating and analyzing the optimization effect of the drawing path includes: generating an evaluation cycle, obtaining the optimization effect coefficient of the evaluation cycle, obtaining the optimization effect threshold through the database, and comparing the optimization effect coefficient of the evaluation cycle with the optimization effect threshold: if the optimization effect coefficient is less than the optimization effect threshold, the necessary optimization threshold YBmax is adjusted upward: the necessary optimization update value YBn is obtained by the formula YBn=t3*YBmax, where t3 is the proportional coefficient, and 1.05≤t3≤1.15; the necessary optimization update value YBn is used to replace the necessary optimization threshold YBmax; if the optimization effect coefficient is greater than or equal to the optimization effect threshold, no processing is performed.

3. The Ai-based drawing path optimization system according to claim 2, characterized in that: The process of obtaining the optimization effect coefficient of the evaluation cycle includes: calling several drawing tasks that execute the optimized path in the evaluation cycle and marking them as evaluation objects, obtaining the time difference between the evaluation object when the path information is generated and the drawing is completed and marking it as the optimization duration value of the evaluation object, then executing the drawing task according to the generated path information, recording the drawing duration and marking it as the basic duration value, marking the difference between the basic duration value and the optimized duration value as the optimization effect value of the evaluation object, and summing and averaging the optimization effect values ​​of all evaluation objects to obtain the optimization effect coefficient.

Images