High-value IP positioning acquisition geographic grid target evaluation method

Abstract

The invention provides a high-value IP positioning acquisition geographic grid target evaluation method, and relates to the technical field of network security, and the method comprises the steps: constructing a comprehensive evaluation index system of a multi-dimensional index high-value IP positioning acquisition geographic grid target; according to the comprehensive evaluation index system, constructing a comprehensive weight of a high-value IP positioning collection geographic grid target; according to the comprehensive evaluation index system and the comprehensive weight, each geographic grid is comprehensively evaluated, each geographic grid serves as a particle, the position of the particle represents the position of the grid, and the fitness value of the particle represents the comprehensive evaluation score of the grid; by iteratively updating the speed and the position of the particle, determining an initial fitness particle, and taking the fitness particle as a high-value target geographic grid; and correcting the high-value target geographic grids to obtain a final high-value target geographic grid list. According to the invention, the quality of the IP positioning reference data is improved, and the data acquisition cost is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of network security, and in particular to a method for evaluating a high-value IP location acquisition geographic grid target. Background Art

[0002] The existing high-value target grid assessment methods mainly include density method, heat map method, cluster analysis method, and feature-based assessment method, all of which have certain limitations. The density method is prone to over-sampling in some dense areas and missing important information in low-density areas. The heat map method cannot reflect the actual situation well when the target distribution is irregular or there are isolated high-value points.

[0003] Cluster analysis requires adjusting clustering parameters for targets of different scales, which increases the complexity of the method. Feature-based evaluation methods are highly dependent on the accuracy of feature extraction and are difficult to fully capture complex and changing target features. The above four evaluation methods only consider single-dimensional features and cannot comprehensively utilize the multi-faceted features of the target. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method for evaluating high-value IP positioning and acquisition geographic grid targets, thereby improving the evaluation accuracy and practicality of high-value IP positioning and acquisition geographic grid targets.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, a method for evaluating a high-value IP location collection geographic grid target is provided, the method comprising:

[0007] Construct a comprehensive evaluation index system for high-value IP location acquisition geographic grid targets with multi-dimensional indicators;

[0008] Based on the comprehensive evaluation index system, the comprehensive weight of high-value IP positioning and collection geographic grid targets is constructed;

[0009] According to the comprehensive evaluation index system and comprehensive weight, each geographic grid is comprehensively evaluated, and each geographic grid is regarded as a particle. The position of the particle represents the position of the grid, and the fitness value of the particle represents the comprehensive evaluation score of the grid.

[0010] By iteratively updating the speed and position of particles, preliminary fitness particles are determined, and the fitness particles are used as high-value target geographic grids;

[0011] The high-value target geographic grids are modified to obtain a final high-value target geographic grid list.

[0012] Furthermore, based on the comprehensive evaluation index system, the comprehensive weight of high-value IP location collection geographic grid targets is constructed, including:

[0013] Compare the elements in the same level to obtain the comparison result;

[0014] According to the comparison results, a matrix is ​​constructed, where each element in the matrix represents the relative importance between two indicators, and the diagonal elements of the matrix are 1, indicating that the indicator is equally important compared to itself;

[0015] Calculate the maximum eigenvalue and corresponding eigenvector of the matrix to obtain the subjective weight value of each indicator;

[0016] Obtain historical data related to the comprehensive evaluation indicator system;

[0017] Preprocessing the historical data to obtain preprocessed data;

[0018] The information entropy of each evaluation index is calculated based on the distribution of preprocessed data;

[0019] According to the information entropy, the difference coefficient of each indicator is calculated, and the difference coefficient of each indicator is normalized to obtain the objective weight value of each indicator;

[0020] Based on the subjective weight value and the objective weight value, the comprehensive weight of the high-value IP positioning and collection geographic grid target is calculated.

[0021] Furthermore, the calculation formula of the comprehensive weight is:

[0022]

[0023] Among them, ω i represents the comprehensive weight of the i-th geographic grid target; δ i represents the subjective weight value of the i-th geographic grid target; ζ i Represents the objective weight value of the i-th geographic grid target; ∑ i represents the sum over all i.

[0024] Furthermore, the fitness value calculation formula of the particle is:

[0025]

[0026] Where F(x) represents the fitness value of the geographic grid particle x; n represents the total number of evaluation indicators; w c represents the weight of the cth evaluation indicator; m c Indicates the number of sub-indicators under the cth evaluation indicator; a cj represents the weight coefficient of the jth sub-indicator under the cth evaluation indicator; f cj(x) represents the original score of geographic grid particle x on the jth sub-index under the cth evaluation index; It represents the minimum value of the jth sub-indicator under the cth evaluation indicator in all geographic grids; represents the maximum value of the jth sub-indicator under the cth evaluation indicator in all geographic grids; b cj It represents the benchmark value of the jth sub-indicator under the cth evaluation indicator.

[0027] Furthermore, the particle velocity update formula is:

[0028]

[0029] Among them, v b (t+1) represents the velocity of the bth particle at time t+1; w(t) represents the inertia weight; c1 represents the individual learning factor; r1 represents the individual random number; r2 represents the global random coefficient; r3 represents the local random coefficient; p b represents the individual optimal position of the bth particle; g represents the global optimal position; l b represents the local optimal position of the neighborhood where the bth particle is located; c2 represents the global learning factor; c3 represents the local learning factor; α represents the boundary effect coefficient; x b (t) represents the current position of particle b; x max represents the maximum position explored by particle b; β represents the fitness adjustment coefficient; Indicates that particle b is at position x b (t) fitness function value; x b (t) represents the position of the bth particle at time t.

[0030] Furthermore, the particle position update formula is:

[0031]

[0032] Among them, x b (t+1) represents the position of particle b at time t+1; x b (t) represents the position of the bth particle at time t; v b (t+1) represents the velocity of the bth particle at time t+1; γ1 represents the momentum coefficient; x b (t)-x b (t-1) represents the difference between the position of the b-th particle at the current moment and the previous moment; represents the disturbance amplitude coefficient; ω represents the angular frequency of the disturbance; represents the initial phase of the bth particle; δ represents the amplitude coefficient of the adaptive adjustment term; represents the adaptive adjustment term; f(x b(t)) indicates that the bth particle is at position x b (t) represents the fitness function value; T represents the fitness threshold; k represents the slope of the logistic function.

[0033] In the second aspect, a high-value IP location collection geographic grid target assessment system includes:

[0034] The acquisition module is used to construct a comprehensive evaluation index system of high-value IP positioning and collection geographic grid targets with multi-dimensional indicators; based on the comprehensive evaluation index system, the comprehensive weight of high-value IP positioning and collection geographic grid targets is constructed; based on the comprehensive evaluation index system and the comprehensive weight, each geographic grid is comprehensively evaluated, and each geographic grid is regarded as a particle, the position of the particle represents the position of the grid, and the fitness value of the particle represents the comprehensive evaluation score of the grid;

[0035] The processing module is used to iteratively update the speed and position of the particles, determine the preliminary fitness particles, and use the fitness particles as high-value target geographic grids; correct the high-value target geographic grids to obtain a final high-value target geographic grid list.

[0036] According to a third aspect, a computing device includes:

[0037] one or more processors;

[0038] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0039] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0040] The above solution of the present invention includes at least the following beneficial effects:

[0041] By building a comprehensive evaluation index system, high-value target geographic grids can be identified more accurately. This helps optimize data collection strategies and focus resources on the most valuable areas, thereby improving the efficiency and accuracy of data collection. By assigning a comprehensive evaluation score to each geographic grid and sorting them according to the score, limited resources can be allocated more reasonably. For example, in network monitoring or market research, priority can be given to geographic grids with higher scores to maximize resource utilization.

[0042] The comprehensive evaluation index system and comprehensive weights provide decision makers with a comprehensive data analysis basis, which helps to make more scientific and reasonable decisions. Whether in urban planning, market layout, or network security management, this system can provide strong data support. The particle swarm optimization algorithm (assuming that this is a method of iteratively updating particle speed and position) is used to dynamically adjust the selection of geographic grids, so that the system can quickly adapt to changing environments and needs. This flexibility enables the system to cope with a variety of complex and changing application scenarios. By correcting the high-value target geographic grid, the accuracy of positioning can be further improved. This is of great significance for applications that require precise geographic information, such as navigation, logistics, etc. By accurately identifying high-value target geographic grids and concentrating resources for collection and processing, the cost of data collection and processing in unnecessary or low-value areas can be reduced, thereby improving the efficiency and economic benefits of overall operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of a method for evaluating a high-value IP location collection geographic grid target provided by an embodiment of the present invention.

[0044] Figure 2 It is a schematic diagram of a high-value IP positioning and collection geographic grid target evaluation system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] like Figure 1 As shown, an embodiment of the present invention provides a method for evaluating a high-value IP location collection geographic grid target, the method comprising the following steps:

[0047] Step 1: Construct a comprehensive evaluation index system of high-value IP location acquisition geographic grid targets with multi-dimensional indicators;

[0048] Step 2: Based on the comprehensive evaluation index system, the comprehensive weight of high-value IP location collection geographic grid targets is constructed;

[0049] Step 3: Based on the comprehensive evaluation index system and comprehensive weight, each geographic grid is comprehensively evaluated, and each geographic grid is regarded as a particle. The position of the particle represents the position of the grid, and the fitness value of the particle represents the comprehensive evaluation score of the grid.

[0050] Step 4, by iteratively updating the speed and position of the particles, determine the preliminary fitness particles, and use the fitness particles as high-value target geographic grids;

[0051] Step 5, correct the high-value target geographic grids to obtain a final high-value target geographic grid list.

[0052] In an embodiment of the present invention, multiple dimensions for evaluating the value of a geographic grid are determined, such as population density, economic activity, network facility perfection, information transmission efficiency, etc. Each indicator is carefully selected to ensure that they can fully reflect the potential value of the geographic grid in IP positioning data collection. Based on the established indicator system, a weight is assigned to each indicator, which reflects the importance of the indicator in the overall evaluation. The weight allocation is based on expert judgment, historical data analysis or machine learning methods to ensure the accuracy and fairness of the evaluation. Using the established indicator system and weights, each geographic grid is scored. Each geographic grid is regarded as a "particle", whose position represents the actual geographical location of the grid, and the fitness value of the particle represents its comprehensive evaluation score. The speed and position of the particle are continuously adjusted through an iterative process to find the best fitness particle. In this process, the speed and position of the particle are updated according to its own historical best position and the global best position in the group. After multiple iterations, the particles with the highest fitness value are selected as preliminary fitness particles, which represent high-value geographic grid targets. After the high-value geographic grid is initially determined, further verification and correction are performed to ensure the accuracy of the results. It includes steps such as field investigation, data comparison, and expert review, and ultimately generates a list of high-value target geographic grids.

[0053] By locating high-value geographic grids, resources can be deployed more accurately, thereby improving the efficiency of IP location data collection. The comprehensive evaluation system helps to allocate resources reasonably, invest limited resources in the most potential geographic grids, and maximize the use of resources. Through accurate evaluation, it is possible to avoid wasting resources on unnecessary or inefficient geographic grids, thereby reducing overall operating costs. Based on a comprehensive evaluation of multiple dimensions, decision makers can make more informed and comprehensive decisions and improve overall operational results. With the help of the idea of ​​particle swarm optimization algorithm, the system can flexibly respond to environmental changes and dynamically adjust the positioning of high-value geographic grids. Through the correction steps, the accuracy of high-value geographic grid positioning is improved to ensure the reliability of the final list.

[0054] In a preferred embodiment of the present invention, a comprehensive weight of high-value IP location collection geographic grid targets is constructed based on a comprehensive evaluation index system, including:

[0055] Compare the elements in the same level to obtain the comparison result;

[0056] According to the comparison results, a matrix is ​​constructed, where each element in the matrix represents the relative importance between two indicators, and the diagonal elements of the matrix are 1, indicating that the indicator is equally important compared to itself;

[0057] Calculate the maximum eigenvalue and corresponding eigenvector of the matrix to obtain the subjective weight value of each indicator;

[0058] Obtain historical data related to the comprehensive evaluation indicator system;

[0059] Preprocessing the historical data to obtain preprocessed data;

[0060] The information entropy of each evaluation index is calculated based on the distribution of preprocessed data;

[0061] According to the information entropy, the difference coefficient of each indicator is calculated, and the difference coefficient of each indicator is normalized to obtain the objective weight value of each indicator;

[0062] Based on the subjective weight value and the objective weight value, the comprehensive weight of the high-value IP positioning and collection geographic grid target is calculated.

[0063] In an embodiment of the present invention, when constructing a comprehensive evaluation index system, it is necessary to compare each evaluation index at the same level in pairs to determine the relative importance between them. Based on the above comparison results, a matrix is ​​constructed, in which each element of the matrix represents the relative importance between the two indicators. For example, if indicator A is twice as important as indicator B, the corresponding element in the matrix is ​​2, and vice versa. The diagonal elements of the matrix are set to 1, because any indicator is equally important compared to itself. The maximum eigenvalue of the matrix and its corresponding eigenvector are calculated by mathematical methods (such as power method, QR algorithm, etc.). This eigenvector represents the subjective weight value of each indicator, which reflects the decision maker's subjective judgment on the importance of each indicator. Collect historical data related to the evaluation index, which will be used to calculate the objective weight value. The collected historical data is preprocessed by cleaning, conversion and standardization to ensure the accuracy and comparability of the data. Based on the distribution of the preprocessed data, the information entropy of each evaluation indicator is calculated. The information entropy reflects the degree of confusion or uncertainty of the data. The more uniform the data distribution of the indicator, the greater its information entropy. Information entropy is used to calculate the difference coefficient of each indicator. The difference coefficient is inversely proportional to information entropy, that is, the smaller the information entropy, the larger the difference coefficient, indicating that the indicator has a higher degree of discrimination in the evaluation. The difference coefficient of each indicator is normalized to obtain the objective weight value of each indicator. Combining the subjective weight value and the objective weight value, the comprehensive weight of the high-value IP positioning and collection geographic grid target is calculated. This comprehensive weight takes into account both the subjective preferences of decision makers and the objective characteristics of the actual data.

[0064] By combining subjective weights and objective weights, the comprehensive weights reflect the decision maker's experience and judgment, and make full use of the information of historical data, making the evaluation results more comprehensive and accurate. The qualitative indicators are converted into quantitative weights through mathematical methods, making the evaluation process more scientific and operational. Subjective weights can be adjusted according to actual conditions, while objective weights change dynamically according to historical data, so the comprehensive weights have high flexibility and adaptability. Clear weight allocation helps decision makers quickly identify key factors, thereby improving decision efficiency and accuracy.

[0065] In a preferred embodiment of the present invention, the calculation formula of the comprehensive weight is:

[0066]

[0067] Among them, ω i represents the comprehensive weight of the i-th geographic grid target; δ i represents the subjective weight value of the i-th geographic grid target; ζ i Represents the objective weight value of the i-th geographic grid target; ∑ i represents the sum over all i.

[0068] In the embodiment of the present invention, the subjective weight values ​​are determined based on expert evaluation, empirical judgment or policy guidance. These weights reflect the subjective cognition of decision makers or experts on the importance of each geographic grid target. The objective weight values ​​are determined by data analysis, statistical methods or other quantitative techniques. They reflect the importance of the target based on actual data or observable indicators. For each geographic grid target, the subjective weight value δ i and objective weight value ζ i Add or subtract (whether to use addition or subtraction depends on the actual situation and evaluation requirements). The purpose is to combine the two weights to form a weighted value. Use the summation symbol ∑ i The weighted sum of all geographic grid targets is summed. This sum is used as a normalization factor to ensure that the combined weights of all targets sum to 1. The weighted sum of each target is divided by this sum to obtain the combined weight of each geographic grid target ω i Ultimately, each geographic grid target is assigned a composite weight value between 0 and 1, which reflects the relative importance of the target in the overall assessment.

[0069] By comprehensively considering the weight information of both subjective and objective aspects, a more comprehensive and accurate comprehensive weight value can be obtained. It helps to avoid the bias of relying solely on subjective judgment or objective data. By combining expert knowledge and actual data analysis, the scientificity and rationality of decision-making can be improved. The comprehensive weight can provide decision makers with a clear and quantitative evaluation indicator to help them make trade-offs and choices between multiple geographic grid goals. The + operator allows flexible adjustment of the combination of subjective and objective weights according to actual conditions. This flexibility allows the formula to adapt to different decision-making scenarios and needs. Using clear mathematical formulas to calculate comprehensive weights can enhance the transparency and traceability of the decision-making process. This helps to build trust and acceptance, especially when multiple stakeholders are involved. For complex decision-making problems involving multiple geographic grid goals, it can provide a systematic approach to determine the relative importance of each goal. This helps decision makers better understand the overall structure of the problem.

[0070] In a preferred embodiment of the present invention, the fitness value calculation formula of the particle is:

[0071]

[0072] Where F(x) represents the fitness value of the geographic grid particle x; n represents the total number of evaluation indicators; w c represents the weight of the cth evaluation indicator; m c represents the number of sub-indicators under the c-th evaluation indicator; acj represents the weight coefficient of the j-th sub-indicator under the c-th evaluation indicator; f cj (x) represents the original score of geographic grid particle x on the jth sub-index under the cth evaluation index; It represents the minimum value of the jth sub-indicator under the cth evaluation indicator in all geographic grids; represents the maximum value of the jth sub-indicator under the cth evaluation indicator in all geographic grids; b cj It represents the benchmark value of the jth sub-indicator under the cth evaluation indicator.

[0073] In the embodiment of the present invention, there are n evaluation indicators, each of which is further divided into m c sub-indicators, which can more comprehensively reflect the characteristics or values ​​of geographic grids in different aspects. Standardization is performed. The raw score is converted into a relative value between 0 and 1, so that different indicators can be compared and weighted. Each sub-indicator is multiplied by a weight coefficient a cj , to reflect its importance in the comprehensive evaluation. At the same time, each evaluation indicator also has a weight w c , used to further adjust the contribution of each indicator to the final fitness value. b cjAs the benchmark value of each sub-indicator, it is used to adjust the score range or balance point of the sub-indicator. This increases the flexibility of the model and makes the evaluation process more in line with actual needs. Through the above steps, a quantitative fitness value F(x) is calculated by comprehensively considering multiple evaluation indicators and sub-indicators. This value can be used as a measure of the value of the geographic grid and used to compare the advantages and disadvantages of different geographic grids.

[0074] By considering multiple evaluation indicators and sub-indicators, the model can comprehensively and multi-angle evaluate the value of the geographic grid, avoiding the one-sidedness of a single indicator. The weight coefficients and benchmark values ​​in the model can be adjusted according to actual conditions, making the evaluation process more flexible and adaptable to different application scenarios and needs. Through standardization, the scores between different indicators are comparable, which facilitates weighted summation and comprehensive evaluation. Based on simple mathematical operations and weighted average ideas, it is easy to program and calculate, and is easy to promote and use in practical applications. It provides decision makers with a quantitative and objective evaluation result as a basis or reference for decision-making, which helps to improve the scientificity and accuracy of decision-making.

[0075] In a preferred embodiment of the present invention, the particle velocity update formula is:

[0076]

[0077] Among them, v b (t+1) represents the velocity of the bth particle at time t+1; w(t) represents the inertia weight; c1 represents the individual learning factor; r1 represents the individual random number; r2 represents the global random coefficient; r3 represents the local random coefficient; p b represents the individual optimal position of the bth particle; g represents the global optimal position; l b represents the local optimal position of the neighborhood where the bth particle is located; c2 represents the global learning factor; c3 represents the local learning factor; α represents the boundary effect coefficient; x b (t) represents the current position of particle b; x max represents the maximum position explored by particle b; β represents the fitness adjustment coefficient; Indicates that particle b is at position x b (t) fitness function value; x b (t) represents the position of the bth particle at time t.

[0078] In the embodiment of the present invention, v b (t+1) represents the velocity vector of the bth particle at time t+1. The velocity vector determines the direction and distance of the particle's next move. b(t) retains part of the particle's current velocity, giving the particle a kind of "inertia" that helps the particle maintain a certain momentum in the search space. w is the inertia weight, which can be a constant or a function that changes with time and is used to control the degree to which the particle retains its current velocity. c1·r1·(p b -x b (t)) reflects the particle's best historical position p b memory and tendency. c1 is the individual cognitive coefficient r1 is a random number used to increase the randomness of the search. Through this part, the particle will tend to move towards its own historical best position. c2·r2·(gx b (t)) represents the tendency of particles to move toward the optimal solution g in the group. c2 is the global learning factor, and r2 is another random number. Particles are encouraged to move toward the optimal position of the entire group, reflecting information sharing and cooperation in the group. b -x b (t)) the particle considers the best solution l in its neighborhood b c3 is the local learning factor, r3 is a random number, which makes the particle affected by the optimal solution in its neighborhood, which helps to conduct a more refined search in the local area, and α·(x max -x b (t)) 2 is an optional item used to guide particles to move to a specific area of ​​the search space, such as the upper bound x max α is a coefficient that controls this attraction and can help prevent particles from converging to a local optimum too early in some cases. According to the current fitness value of the particle (through the fitness function f(x b (t)) is calculated to adjust the speed of the particle. β is the adjustment coefficient, which is used to dynamically adjust the search behavior of the particle according to its performance, so that particles with poor performance can change their search direction more quickly.

[0079] By combining individual best, global best and local best information, it is possible to strike a balance between exploration (finding new search areas) and utilization (fine searching in currently known good areas) to maintain the diversity of the population. By adjusting the learning factor and inertia weight, the search strategy can be adaptively adjusted according to different optimization problems and stages to improve the optimization efficiency. The introduction of fitness-related adjustment items and random components helps prevent the algorithm from falling into the local optimum too early and increases the possibility of finding the global optimal solution. It can adapt to different types of optimization problems, including unimodal and multimodal function optimization, by adjusting parameters, showing good flexibility and versatility. By setting parameters reasonably, the convergence speed of the algorithm can be accelerated and the computing time and resource consumption can be reduced.

[0080] In a preferred embodiment of the present invention, the particle position update formula is:

[0081]

[0082] Among them, x b (t+1) represents the position of particle b at time t+1; v b (t+1) represents the velocity of the bth particle at time t+1; γ1 represents the momentum coefficient; x b (t)-x b (t-1) represents the difference between the position of the bth particle at the current moment and the previous moment; r2 represents the disturbance amplitude coefficient; ω represents the angular frequency of the disturbance; represents the initial phase of the bth particle; δ represents the amplitude coefficient of the adaptive adjustment term; represents the adaptive adjustment term; T represents the fitness threshold; k represents the slope of the logistic function.

[0083] In the embodiment of the present invention, x b (t+1) indicates the particle moves from the current position x b (t) Start at the updated speed v b (t+1) moves to a new position, γ1·(x b (t)-x b (t-1)) takes into account the difference between the current position of the particle and the position at the previous moment. The momentum coefficient β1 simulates the inertia of the particle during movement, which helps the particle maintain a certain movement trend, so that it may cross the local optimal area. A periodic disturbance is introduced. This disturbance is realized by a sine function, where ω controls the frequency of the disturbance, is the initial phase of each particle, ensuring that the particles are subjected to different perturbations. This perturbation increases the diversity of the search, helps particles jump out of the current search area, and avoids premature convergence to the local optimal solution. Adaptive adjustment based on logical function. According to the fitness function value f(x b (t)) is compared with the set threshold T, and the position of the particle is adjusted nonlinearly accordingly. If the fitness of the particle is better than the threshold T, the value of the logic function will increase, thereby increasing the amplitude of the position adjustment. On the contrary, if the fitness is poor, the adjustment amplitude will be reduced. This mechanism enables the algorithm to adaptively adjust the search strategy according to the performance of the particle.

[0084] By introducing the periodic perturbation function It can increase randomness and diversity in the search process, thus avoiding falling into the local optimal solution too early. This disturbance helps particles jump out of the current area and explore a wider search space, thus improving the global search ability of the algorithm. b (t)-x b The introduction of (t-1)) gives particles a certain inertia during the search process, allowing them to traverse the search space faster, thereby accelerating the convergence of the algorithm. This helps to find a better solution within a limited number of iterations. Adaptive adjustment items based on logical functions This enables the algorithm to dynamically adjust the search step size and direction according to the fitness function value of the particle. When the fitness of the particle is good, the adjustment term will increase, thereby accelerating the convergence to a better solution; conversely, when the fitness is poor, the adjustment term will decrease to avoid excessive deviation from the current area. This adaptive adjustment capability improves the flexibility and robustness of the algorithm. Through the integration of the above-mentioned multiple mechanisms, the algorithm can better balance the relationship between exploration and utilization during the search process. On the one hand, the exploration capability is increased through periodic perturbations and momentum effects; on the other hand, the utilization capability of the current high-quality area is improved through adaptive adjustment terms. This balance helps the algorithm find the global optimal solution in complex optimization problems. Because the algorithm combines multiple search strategies, it can be applied to different types of optimization problems, including continuous optimization, discrete optimization, and multimodal function optimization. This wide applicability gives the algorithm greater flexibility in practical applications.

[0085] like Figure 2 As shown, an embodiment of the present invention further provides a high-value IP location collection geographic grid target evaluation system 20, comprising:

[0086] Acquisition module 21 is used to construct a comprehensive evaluation index system of high-value IP location collection geographic grid targets of multi-dimensional indicators; based on the comprehensive evaluation index system, a comprehensive weight of high-value IP location collection geographic grid targets is constructed; based on the comprehensive evaluation index system and the comprehensive weight, each geographic grid is comprehensively evaluated, and each geographic grid is regarded as a particle, the position of the particle represents the position of the grid, and the fitness value of the particle represents the comprehensive evaluation score of the grid;

[0087] The processing module 22 is used to determine preliminary fitness particles by iteratively updating the speed and position of particles, and use the fitness particles as high-value target geographic grids; and modify the high-value target geographic grids to obtain a final high-value target geographic grid list.

[0088] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0089] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0090] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0091] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0092] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0093] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0094] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0096] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0097] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using basic programming skills after reading the description of the present invention.

[0098] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0099] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A high-value IP location collection geographic grid target assessment method, characterized in that: The method comprises: Construct a comprehensive evaluation index system for high-value IP location acquisition geographic grid targets with multi-dimensional indicators; Based on the comprehensive evaluation index system, the comprehensive weight of high-value IP positioning and collection geographic grid targets is constructed; According to the comprehensive evaluation index system and comprehensive weight, each geographic grid is comprehensively evaluated, and each geographic grid is regarded as a particle. The position of the particle represents the position of the grid, and the fitness value of the particle represents the comprehensive evaluation score of the grid. By iteratively updating the speed and position of particles, preliminary fitness particles are determined, and the fitness particles are used as high-value target geographic grids; The high-value target geographic grids are modified to obtain a final high-value target geographic grid list.

2. The high-value IP location collection geographic grid target evaluation method according to claim 1 is characterized in that: Based on the comprehensive evaluation index system, the comprehensive weight of high-value IP positioning and collection geographic grid targets is constructed, including: Compare the elements in the same level to obtain the comparison result; According to the comparison results, a matrix is ​​constructed; Calculate the maximum eigenvalue and corresponding eigenvector of the matrix to obtain the subjective weight value of each indicator; Obtain historical data related to the comprehensive evaluation indicator system; Preprocessing the historical data to obtain preprocessed data; The information entropy of each evaluation index is calculated based on the distribution of preprocessed data; According to the information entropy, the difference coefficient of each indicator is calculated, and the difference coefficient of each indicator is normalized to obtain the objective weight value of each indicator; Based on the subjective weight value and the objective weight value, the comprehensive weight of the high-value IP positioning and collection geographic grid target is calculated.

3. The high-value IP location collection geographic grid target evaluation method according to claim 2 is characterized in that: Each element in the matrix represents the relative importance between two indicators, and the diagonal elements of the matrix are 1, indicating that the indicator is equally important compared to itself.

4. The high-value IP location collection geographic grid target evaluation method according to claim 3 is characterized in that: The calculation formula of comprehensive weight is: Among them, ω i represents the comprehensive weight of the i-th geographic grid target; δ i represents the subjective weight value of the i-th geographic grid target; ζ i Represents the objective weight value of the i-th geographic grid target; ∑ i represents the sum over all i.

5. The high-value IP location collection geographic grid target evaluation method according to claim 4 is characterized in that: The fitness value calculation formula of a particle is: Where F(x) represents the fitness value of the geographic grid particle x; n represents the total number of evaluation indicators; w c represents the weight of the cth evaluation indicator; m c Indicates the number of sub-indicators under the cth evaluation indicator; a cj represents the weight coefficient of the jth sub-indicator under the cth evaluation indicator; f cj (x) represents the original score of geographic grid particle x on the jth sub-index under the cth evaluation index; It represents the minimum value of the jth sub-indicator under the cth evaluation indicator in all geographic grids; represents the maximum value of the jth sub-indicator under the cth evaluation indicator in all geographic grids; b cj It represents the benchmark value of the jth sub-indicator under the cth evaluation indicator.

6. The high-value IP location collection geographic grid target assessment method according to claim 5 is characterized in that: The particle velocity update formula is: Among them, v b (t+1) represents the velocity of the bth particle at time t+1; w represents the inertia weight; c1 represents the individual learning factor; r1 represents the individual random number; r2 represents the global random coefficient; r3 represents the local random coefficient; p b represents the individual optimal position of the bth particle; g represents the global optimal position; l b represents the local optimal position of the neighborhood where the bth particle is located; c2 represents the global learning factor; c3 represents the local learning factor; α represents the boundary effect coefficient; x b (t) represents the current position of particle b; x max represents the maximum position explored by particle b; β represents the fitness adjustment coefficient; Indicates that particle b is at position x b (t) fitness function value; x b (t) represents the position of the bth particle at time t.

7. The high-value IP location collection geographic grid target evaluation method according to claim 6 is characterized in that: The particle position update formula is: Among them, x b (t+1) represents the position of particle b at time t+1; x b (t) represents the position of the bth particle at time t; v b (t+1) represents the velocity of the bth particle at time t+1; γ1 represents the momentum coefficient; x b (t)-x b (t-1) represents the difference between the position of the bth particle at the current moment and the previous moment; r2 represents the disturbance amplitude coefficient; ω represents the angular frequency of the disturbance; represents the initial phase of the bth particle; δ represents the amplitude coefficient of the adaptive adjustment term; represents the adaptive adjustment term; f(x b (t)) indicates that the bth particle is at position x b (t) represents the fitness function value; T represents the fitness threshold; k represents the slope of the logistic function.

8. A high-value IP location collection geographic grid target assessment system, characterized in that: include: Acquisition module, used to build a comprehensive evaluation index system for high-value IP positioning and acquisition of geographic grid targets with multi-dimensional indicators; According to the comprehensive evaluation index system, the comprehensive weight of the high-value IP positioning and collection geographic grid targets is constructed; according to the comprehensive evaluation index system and comprehensive weight, each geographic grid is comprehensively evaluated, and each geographic grid is regarded as a particle, the position of the particle represents the position of the grid, and the fitness value of the particle represents the comprehensive evaluation score of the grid; A processing module is used to determine preliminary fitness particles by iteratively updating the speed and position of particles, and use the fitness particles as high-value target geographic grids; The high-value target geographic grids are modified to obtain a final high-value target geographic grid list.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images