Terrain solving method and device for improving weed optimization, equipment and medium

Abstract

The invention discloses a terrain solving method and device for improving weed optimization, equipment and a medium, and the method comprises the steps: initializing solving parameters, and obtaining a weed population; traversing the weed population to carry out terrain solution and fitness evaluation to obtain a fitness value of each weed individual; when the fitness value is smaller than the optimal iteration threshold value, taking the corresponding weed individual as a target individual; otherwise, taking the weed individual with the minimum fitness value as a candidate individual, and carrying out self-adaptive updating on the weed population; adding 1 to the number of iterations, and returning to execute the step of traversing the weed population to perform terrain solution and fitness evaluation until the fitness value is smaller than a preset optimal iteration threshold value, or the number of iterations reaches a preset maximum number of iterations; when the number of iterations reaches the maximum number of iterations, taking the candidate individual as a target individual; and taking a terrain solving result of the target individual as a final result. The method can accurately realize terrain solving, and can be widely applied to the technical field of data evolution analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of data evolution analysis, and particularly to an improved weed optimization-based terrain solving method, device, equipment and medium. Background Art

[0002] In the field of terrain solving, traditional technical solutions usually set the solving parameters as constants. Although this method simplifies the calculation process, it often results in low solving accuracy. In addition, some studies rely on experience to set these parameters, which not only lacks a scientific basis, but also due to the subjectivity and differences of experience, even in the same geographical area, multiple different Mohorovicic discontinuity models may be generated. This inconsistency makes it difficult to guarantee the quality of the model, and at the same time brings challenges to the management and unified application of the model. Summary of the Invention

[0003] The present invention aims to solve the problems of related technical limitations to at least a certain extent. For this purpose, the present invention provides an improved weed optimization-based terrain solving method, device, equipment and medium, which can efficiently and accurately perform terrain solving with improved weed optimization.

[0004] On the one hand, an embodiment of the present invention provides an improved weed optimization-based terrain solving method, including the following steps:

[0005] Initialize the solving parameters for terrain solving to obtain a weed population; the weed population includes weed individuals containing the solving parameters with a preset number of population individuals;

[0006] Traverse each weed individual in the weed population for terrain solving and fitness evaluation to obtain the fitness value corresponding to each weed individual;

[0007] When there is a fitness value less than a preset optimal iteration threshold, take the corresponding weed individual as the target individual; otherwise, take the weed individual with the smallest fitness value as the candidate individual and perform adaptive update on the weed population;

[0008] Increment the iteration count by 1, and return to execute the step of traversing each weed individual in the weed population for terrain solving and fitness evaluation until there is a fitness value less than the preset optimal iteration threshold, or the iteration count reaches the preset maximum iteration count; when the iteration count reaches the maximum iteration count, take the candidate individual as the target individual;

[0009] Wherein, in the process of adaptive update, the number of seeds generated by each weed individual for the next generation of individuals is positively correlated with the fitness value of the corresponding weed individual, and the search range applied by each weed individual for the next generation of individuals is negatively correlated with the iteration count;

[0010] Take the result of the terrain solving of the target individual as the final result.

[0011] Optionally, each weed individual in the weed population is traversed for terrain solution and fitness evaluation to obtain the fitness value corresponding to each weed individual, including the following steps:

[0012] Traverse each weed individual in the weed population for terrain solution to obtain the terrain data corresponding to each weed individual;

[0013] Perform fitness evaluation on the terrain data to obtain the fitness value corresponding to each weed individual.

[0014] Optionally, each weed individual in the weed population is traversed for terrain solution to obtain the terrain data corresponding to each weed individual, including the following steps:

[0015] Traverse to obtain the solution parameters corresponding to each weed individual in the weed population;

[0016] Based on the solution parameters corresponding to each weed individual, process them one by one through the Parker - Oldenburg inversion method to obtain the Mohorovicic discontinuity data corresponding to each weed individual.

[0017] Optionally, perform fitness evaluation on the terrain data to obtain the fitness value corresponding to each weed individual, including the following steps:

[0018] According to the terrain data corresponding to the weed individual, perform root - mean - square operation in combination with the preset seismic depth matrix;

[0019] Take the result of the root - mean - square operation as the fitness value corresponding to the weed individual.

[0020] Optionally, the method further includes the following steps:

[0021] Calculate the search range based on the number of iterations in combination with a preset constant;

[0022] Among them, the preset constant includes the maximum number of iterations, the starting iteration threshold, the optimal iteration threshold, and the nonlinear adjustment factor; the expression of the search range is:

[0023]

[0024] In the formula, sigma represents the search range; maxGenCnt represents the maximum number of iterations; initIterDelt represents the starting iteration threshold; minIterDelt represents the optimal iteration threshold; nonlinearFactor represents the nonlinear adjustment factor; iterCnt represents the number of iterations;

[0025] Based on the fitness value corresponding to each weed individual, the number of seeds for the corresponding weed individual to generate the next generation of individuals is calculated by combining the preset maximum number of seeds and minimum number of seeds, as well as the maximum fitness value and minimum fitness value corresponding to the current weed population; the expression for the number of seeds is:

[0026]

[0027] In the formula, seedNum i represents the number of seeds for the i-th weed individual to generate the next generation of individuals; minSeedNum represents the minimum number of seeds; maxSeedNum represents the maximum number of seeds; curRms i represents the fitness value of the i-th weed individual; minRms iter represents the minimum fitness value of the current weed population; maxRms iter represents the maximum fitness value of the current weed population.

[0028] Optionally, adaptively updating the weed population includes the following steps:

[0029] Traverse each weed individual in the weed population one by one, and use the traversed weed individual as the processing individual;

[0030] Based on the number of seeds corresponding to the processing individual, generate the corresponding number of adjustment parameters that conform to the normal distribution according to the search range;

[0031] Generate the next generation of individuals for the processing individual by combining the adjustment parameters with the solution parameters corresponding to the processing individual.

[0032] Optionally, before the steps of adaptively updating the weed population, the method further includes the following steps:

[0033] Obtain the number of individuals in the weed population;

[0034] When the number of individuals is greater than the number of population individuals, sort the weed individuals in the weed population from smallest to largest based on the fitness value, and then retain the weed individuals with the smallest number of population individuals in the weed population with the smallest fitness value, and eliminate the other weed individuals.

[0035] On the other hand, an embodiment of the present invention provides an improved terrain solving device for weed optimization, including:

[0036] The first module is used to initialize the solution parameters for terrain solving to obtain a weed population; the weed population includes weed individuals containing solution parameters with a preset number of population individuals;

[0037] The second module is used to traverse each weed individual in the weed population for terrain solving and fitness evaluation to obtain the fitness value corresponding to each weed individual;

[0038] The third module is used to take the corresponding weed individual as the target individual when there is a fitness value less than the preset optimal iteration threshold; otherwise, take the weed individual with the minimum fitness value as the candidate individual and perform adaptive update on the weed population;

[0039] The fourth module is used to increment the iteration count by 1, return to execute the second module until there is a fitness value less than the preset optimal iteration threshold, or the iteration count reaches the preset maximum iteration count; when the iteration count reaches the maximum iteration count, take the candidate individual as the target individual;

[0040] Wherein, in the process of adaptive update, the number of seeds generated by each weed individual for the next generation of individuals is positively correlated with the fitness value of the corresponding weed individual, and the search range applied by each weed individual to generate the next generation of individuals is negatively correlated with the iteration count;

[0041] The fifth module is used to take the result of terrain solution of the target individual as the final result.

[0042] Optionally, the device further includes:

[0043] The sixth module is used to calculate the search range based on the iteration count in combination with a preset constant;

[0044] Wherein, the preset constant includes the maximum iteration count, the starting iteration threshold, the optimal iteration threshold, and the non-linear adjustment factor; the expression of the search range is:

[0045]

[0046] In the formula, sigma represents the search range; maxGenCnt represents the maximum iteration count; initIterDelt represents the starting iteration threshold; minIterDelt represents the optimal iteration threshold; nonlinearFactor represents the non-linear adjustment factor; iterCnt represents the iteration count;

[0047] The seventh module is used to calculate the number of seeds generated by the corresponding weed individual for the next generation of individuals based on the fitness value of the weed individual, in combination with the preset maximum number of seeds and minimum number of seeds, and the maximum fitness value and minimum fitness value of the current weed population; the expression of the number of seeds is:

[0048]

[0049] In the formula, seedNum i represents the number of seeds generated by the i-th weed individual for the next generation of individuals; minSeedNum represents the minimum number of seeds; maxSeedNum represents the maximum number of seeds; curRms iRepresents the fitness value of the i-th weed individual; minRms iter Represents the minimum fitness value of the current weed population; maxRms iter Represents the maximum fitness value of the current weed population.

[0050] Optionally, the device further includes an eighth module, which is executed before adaptively updating the weed population. The eighth module is used for:

[0051] Obtain the number of individuals in the weed population;

[0052] When the number of individuals is greater than the number of population individuals, sort the weed individuals in the weed population from smallest to largest based on the fitness value, and then retain the weed individuals with the smallest fitness value in the number of population individuals in the weed population, and eliminate other weed individuals.

[0053] On the other hand, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used to store a program; the processor executes the program to implement the above-mentioned terrain solving method for improving weed optimization.

[0054] On the other hand, an embodiment of the present invention provides a computer storage medium, in which a program executable by a processor is stored. The program executable by the processor is used to implement the above-mentioned terrain solving method for improving weed optimization when executed by the processor.

[0055] In the embodiment of the present invention, by initializing the solution parameters of terrain solving, a weed population is obtained; the weed population includes weed individuals containing solution parameters with a preset number of population individuals; each weed individual in the weed population is traversed for terrain solving and fitness evaluation to obtain the fitness value corresponding to each weed individual; when there is a fitness value less than a preset optimal iteration threshold, the corresponding weed individual is used as the target individual; otherwise, the weed individual with the smallest fitness value is used as the candidate individual, and the weed population is adaptively updated; the iteration count is incremented by 1, and the step of traversing each weed individual in the weed population for terrain solving and fitness evaluation is returned until there is a fitness value less than a preset optimal iteration threshold, or the iteration count reaches a preset maximum iteration count; when the iteration count reaches the maximum iteration count, the candidate individual is used as the target individual; wherein, in the process of adaptive update, the number of seeds generated by each weed individual for the next generation of individuals is positively correlated with the fitness value of the corresponding weed individual, and the search range applied by each weed individual for the next generation of individuals is negatively correlated with the iteration count; the result of terrain solving of the target individual is used as the final result. The embodiments of the present invention have the following beneficial effects:

[0056] 1. Improve the solution accuracy: By optimizing the solution parameters as variables instead of fixing them as constants, the present invention can more precisely adapt to the characteristics of different terrains, thereby improving the accuracy of terrain solving.

[0057] 2. Enhance model consistency: Through a unified optimization process and an adaptive update mechanism, the present invention reduces model inconsistencies caused by experience differences, making the terrain solution results in the same area more consistent and reliable.

[0058] 3. Adaptive optimization: The weed population in the present invention can be updated adaptively according to fitness values. The number of seeds generated by each weed individual and the search range for the next generation are both related to the current iteration state. This mechanism effectively balances global search and local search, improving the efficiency and effectiveness of optimization.

[0059] 4. Iteration control: By presetting the optimal iteration threshold and the maximum number of iterations, the present invention can effectively control the computational cost while ensuring the solution quality, avoiding unrestricted consumption of computing resources.

[0060] 5. Easy to manage and apply: Due to the improved model consistency and solution accuracy, the Moho model generated by the present invention is easier to manage and apply in actual geological exploration and engineering design.

[0061] In summary, by introducing an adaptive optimization mechanism, the present invention not only improves the accuracy of terrain solution and the consistency of the model, but also optimizes the utilization of computing resources, providing an efficient and reliable solution for the field of terrain solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The drawings are used to provide a further understanding of the technical solution of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation to the technical solution of the present invention.

[0063] Figure 1 is a schematic diagram of an implementation environment of a terrain solution method for improved weed optimization provided by an embodiment of the present invention;

[0064] Figure 2 is a schematic flowchart of a terrain solution method for improved weed optimization provided by an embodiment of the present invention;

[0065] Figure 3 is an expanded flowchart of step S200 provided by an embodiment of the present invention;

[0066] Figure 4 is an expanded flowchart of step S201 provided by an embodiment of the present invention;

[0067] Figure 5 is an expanded flowchart of step S202 provided by an embodiment of the present invention;

[0068] Figure 6Schematic diagram of an extended process for terrain solution with improved weed optimization provided by an embodiment of the present invention;

[0069] Figure 7 Schematic diagram of the expanded process of step S300 provided by an embodiment of the present invention;

[0070] Figure 8 Schematic diagram of the overall process of the terrain solution method with improved weed optimization provided by an embodiment of the present invention;

[0071] Figure 9 Schematic diagram of the structure of a terrain solution device with improved weed optimization provided by an embodiment of the present invention;

[0072] Figure 10 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0073] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0074] It should be noted that although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the system or the order in the flowchart. The terms "first / S100", "second / S200", etc. in the specification, claims and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0075] Referring to "embodiment" herein means that the specific features, structures or characteristics described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0076] For the convenience of understanding the technical solution of the present invention, first, the technical terms that may appear in the technical solution of the present invention will be explained:

[0077] Mohorovicic discontinuity: The surface form of the solid earth under water coverage. Due to the covering of seawater, the undulation of the Mohorovicic discontinuity is difficult to observe directly. The early plumb sounding method was time-consuming and had low accuracy. Since the 1920s, echo sounders have been used on ships during navigation, which can quickly measure the seabed depth. Combining with precise positioning, the truth of the Mohorovicic discontinuity has been revealed. In this invention, the Mohorovicic discontinuity refers to the seawater depth at each longitude and latitude of the ocean.

[0078] Heuristically Search, also known as informed search, uses the heuristic information of the problem to guide the search, aiming to reduce the search scope and the complexity of the problem. This search process using heuristic information is called heuristic search. For example, the invasive weed optimization algorithm is a classic heuristic search algorithm.

[0079] Invasive Weed Optimization (IWO) is a heuristic optimization algorithm based on the reproduction of weed populations. Its inspiration comes from the mechanism by which weeds achieve efficient survival through reproduction, diffusion, and competition in nature. The algorithm simulates four core processes of the weed population: initialization (randomly generating initial solutions), growth (selecting by fitness), reproduction (higher fitness individuals producing more seeds), and competition (eliminating lower fitness individuals). Its feature is to achieve a smooth transition from global exploration to local exploitation by dynamically adjusting the standard deviation of the normal distribution of seed diffusion: the standard deviation is larger in the initial stage to cover a wide area, and gradually shrinks in the later stage to finely search for the optimal solution. This algorithm has few parameters and strong robustness, and is widely used in engineering design, machine learning, data clustering and other fields.

[0080] The Parker-Oldenburg inversion method is a frequency-domain density interface iterative inversion method proposed by Oldenburg based on the Parker formula. Due to the advantage of fast calculation of this method, its application has developed rapidly. However, there is a downward continuation factor in the formula, which causes the oscillation phenomenon of high-frequency signals in the inversion iteration process, and this phenomenon becomes more obvious as the inversion depth increases, seriously affecting the convergence of the inversion result. To solve this situation, a low-pass filter is usually applied in the inversion process to eliminate the high-frequency oscillation phenomenon. The Parker-Oldenburg inversion method is one of the important methods for calculating the Mohorovicic discontinuity and is also the core starting point of this invention. Currently, the input parameters (filtering-related parameters, density difference, depth, etc.) of this method are designed according to experience as constants, but in fact, there is still room for optimization and exploration of these parameters.

[0081] RMS: The abbreviation of Root Mean Square, which is the result of taking the square root after dividing the sum of the squares of N terms by N, that is, the result of the root mean square.

[0082] It can be understood that the improved terrain solving method for weed optimization provided by the embodiments of the present invention can be applied to any computer device with data processing and computing capabilities, and this computer device can be various types of terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the terminal is a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto.

[0083] For the convenience of understanding the technical solutions of the present invention, first, the technical feature proper nouns that may appear in the embodiments of the present invention are explained:

[0084] As Figure 1 shown, it is a schematic diagram of an implementation environment provided by the embodiments of the present invention. Referring to Figure 1 , this implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be network-connected by wireless or wired means to complete data transmission and exchange.

[0085] The server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0086] In addition, the server 101 can also be a node server in a blockchain network. Among them, the blockchain is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm.

[0087] The terminal 102 can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal 102 and the server 101 can be directly or indirectly connected by wired or wireless communication means, and the embodiments of the present invention do not limit this here.

[0088] Exemplarily based on Figure 1In the implementation environment shown, an embodiment of the present invention provides an improved terrain solving method for weed optimization. Taking the application of this improved terrain solving method for weed optimization to server 101 as an example for illustration, it can be understood that this improved terrain solving method for weed optimization can also be applied to terminal 102.

[0089] Referring to Figure 2 , Figure 2 is a flowchart of the improved terrain solving method for weed optimization applied to a server provided by an embodiment of the present invention. The execution subject of this improved terrain solving method for weed optimization can be any of the aforementioned computer devices (including servers or terminals). Referring to Figure 2 , this method includes the following steps:

[0090] S100. Initialize the solution parameters for terrain solving to obtain a weed population;

[0091] Among them, the weed population includes weed individuals containing solution parameters with a preset number of population individuals;

[0092] Exemplarily, in some specific embodiments, the weed population is composed of a large number of individuals. Each individual has two parameter information (i.e., solution parameters), representing the density difference contrast and the average depth depth. The core of population initialization is to generate maxWeedSize individuals, and initialize the corresponding parameters for each individual. The formula is as follows:

[0093] contrast = minContrast + (maxContrast - minContrast) × random()

[0094] depth = minDepth + (maxDepth - minDepth) × random()

[0095] Execute maxWeedSize (i.e., the number of population individuals) times to obtain a population composed of maxWeedSize weeds. random() represents a random number from 0 to 1.

[0096] Among them, it should be noted that the parameters applied in the embodiments of the present invention mainly include two parts: parameters based on the improved weed optimization algorithm and parameters of the Parker - Oldenburg inversion method, etc. The following is an example description of the parameters that may be applied in the specific application scenarios of the embodiments of the present invention:

[0097] There are a total of 2 target search parameters (i.e., solution parameters), which are contrast (density difference, unit: g / cm3) and depth (depth, unit: km). The input parameters of the improved weed optimization algorithm are respectively:

[0098] Density difference maximum value maxContrast: The maximum value of contrast, which is determined by the average value of the target search area, is generally obtained based on experience and meets minContrast<maxContrast。大多数情况下,满足maxContrast-minContrast> =0.4 is sufficient and can be set according to actual conditions.

[0099] Minimum density difference minContrast: The minimum value of contrast, which is determined by the average value of the target search area. It is generally obtained based on experience and meets minContrast.<maxContrast。大多数情况下,满足maxContrast-minContrast> =0.4 is sufficient and can be set according to actual conditions.

[0100] MaxDepth: The maximum value of depth, which is determined by the average value of the target search area. It is usually obtained based on experience and satisfies maxDepth.<minDepth。大多数情况下,满足maxDepth-minDepth> =10, which can be set according to actual conditions.

[0101] Minimum depth minDepth: The minimum value of depth, which is determined by the average value of the target search area, is generally obtained based on experience and satisfies maxDepth<minDepth。大多数情况下,满足maxDepth-minDepth> =10, which can be set according to actual conditions.

[0102] The maximum number of weed individuals in the population is maxWeedSize, which is the maximum number of weed populations. The value is determined based on demand and the default value is 50.

[0103] The maximum number of iterations of the population, maxGenCnt, is the maximum number of reproduction times of the weed population. The value is determined according to demand and the default value is 10.

[0104] Nonlinear adjustment factor nonlinearFactor is used to adjust the search accuracy. The value range is [1,5]. The default value is 3. It is generally a constant. The larger the value, the larger the search range and the worse the search accuracy, and vice versa.

[0105] The maximum number of seeds maxSeedNum, the maximum number of seeds generated by a weed individual, is used to adjust the scale of newly generated seeds in each generation. The value is determined according to demand and the default value is 6.

[0106] The minimum number of seeds, minSeedNum, is the minimum number of seeds generated by a weed individual and is used to adjust the scale of newly generated seeds in each generation. It is valued according to requirements, with a default value of 2, and satisfies minSeedNum < maxSeedNum.

[0107] The initial iteration threshold, initIterDelt, is used to adjust the search accuracy. Its physical meaning is the error of the Mohorovicic discontinuity model (unit: km), with a value range of [10, 20] and a default value of 10, satisfying initDelt > minIterDelt. The larger this value, the larger the search range and the worse the search accuracy, and vice versa.

[0108] The optimal iteration threshold, minIterDelt. If a weed smaller than or equal to minIterDelt is found, it means the optimal solution has been found and the entire search process ends directly.

[0109] The parameters of the Parker - Oldenburg inversion method are mainly as follows:

[0110] The density contrast, contrast, with the unit g / cm3, is one of the variables searched by the improved weed optimization algorithm, that is, this variable is obtained by the improved weed optimization algorithm and is one of the two search directions mentioned in the present invention.

[0111] The depth, depth, with the unit km, is one of the variables searched by the improved weed optimization algorithm, that is, this variable is obtained by the improved weed optimization algorithm and is one of the two search directions mentioned in the present invention.

[0112] The gravity anomaly value matrix, GravityMat, is a matrix composed of (longitude, latitude, gravity anomaly value) triples, generally data observed by seismic surveys, satellite surveys or other means, and is a constant in the present invention.

[0113] The seismic depth matrix, SemisMat, is a matrix composed of (longitude, latitude, depth) triples, generally data observed by seismic surveys, satellite surveys or other means, and is a constant in the present invention.

[0114] The iteration threshold, criterio, that is, the rms threshold for the Parker - Oldenburg inversion method iteration. Generally speaking, this is a constant, with a default value of 0.1, and is a constant in the present invention.

[0115] The frequency threshold WH: the low - pass filtering threshold, with the initial value obtained according to experience, defaulting to 0.1, and is a constant in the present invention.

[0116] The frequency threshold SH: the high - pass filtering threshold, with the initial value obtained according to experience, defaulting to 0.12, and is a constant in the present invention.

[0117] Window function threshold truncation: It is a signal sampling weighting function in signal processing. The initial value is obtained based on experience and the default value is 0.1, which is a constant in the present invention.

[0118] It should be understood that the set values or default values of the various parameters applied in the embodiments of the present invention can be adjusted according to the requirements of actual applications. The above specific parameter values are only for illustrative purposes and should not be regarded as a limitation to the implementation scheme of the present invention.

[0119] S200. Traverse each weed individual in the weed population to solve the terrain and evaluate the fitness, and obtain the fitness value corresponding to each weed individual;

[0120] It should be noted that in some embodiments, such as Figure 3 shown, step S200 may include the following steps: S201. Traverse each weed individual in the weed population to solve the terrain and obtain the terrain data corresponding to each weed individual; S202. Evaluate the fitness of the terrain data to obtain the fitness value corresponding to each weed individual.

[0121] Among them, in some embodiments, such as Figure 4 shown, step S201 may include the following steps: S2011. Traverse and obtain the solution parameters corresponding to each weed individual in the weed population; S2012. Based on the solution parameters corresponding to each weed individual, process them one by one through the Parker - Oldenburg inversion method to obtain the Mohorovicic discontinuity data corresponding to each weed individual.

[0122] Exemplarily, in some specific embodiments, traverse the current weed population to calculate the Mohorovicic discontinuity respectively: For the current population, traverse the information contrast and depth of each individual one by one, and then calculate the corresponding Mohorovicic discontinuity data based on the Parker - Oldenburg inversion method.

[0123] Among them, in some embodiments, such as Figure 5 shown, step S202 may include the following steps: S2021. According to the terrain data corresponding to the weed individual, perform root - mean - square operation in combination with the preset seismic depth matrix; S2022. Use the result of the root - mean - square operation as the fitness value corresponding to the weed individual.

[0124] Exemplarily, in some specific embodiments, traverse the current weed population to calculate the fitness function value respectively: At this time, the Mohorovicic discontinuity data corresponding to each individual in the population has been calculated, and then in combination with the seismic depth matrix SemisMat, the corresponding RMS is calculated. Each individual will calculate its own RMS, and finally an array with a size of maxWeedSize is obtained.

[0125] S300. When there is a fitness value less than the preset optimal iteration threshold, the corresponding weed individual is used as the target individual; otherwise, the weed individual with the minimum fitness value is used as the candidate individual, and the weed population is adaptively updated;

[0126] Among them, in the process of adaptive update, the number of seeds generated by each weed individual for the next generation of individuals is positively correlated with the fitness value of the corresponding weed individual, and the search range applied by each weed individual to generate the next generation of individuals is negatively correlated with the number of iterations;

[0127] Among them, in some embodiments, such as Figure 6 shown, the method may further include the following steps:

[0128] T100. Calculate the search range based on the number of iterations combined with a preset constant;

[0129] Among them, the preset constant includes the maximum number of iterations, the starting iteration threshold, the optimal iteration threshold, and the non-linear adjustment factor; the expression of the search range is:

[0130]

[0131] In the formula, sigma represents the search range; maxGenCnt represents the maximum number of iterations; initIterDelt represents the starting iteration threshold; minIterDelt represents the optimal iteration threshold; nonlinearFactor represents the non-linear adjustment factor; iterCnt represents the number of iterations;

[0132] Exemplarily, in some specific embodiments, update the value of the sigma (i.e., the search range) variable, and the calculation formula is as follows:

[0133]

[0134] Among them, maxGenCnt represents the maximum number of iterations, initIterDelt represents the starting iteration threshold, minIterDelt represents the optimal iteration threshold, nonlinearFactor is the non-linear adjustment factor, the above several belong to constants, iterCnt is the current number of iterations, and the value range is [1, maxGenCnt]. Each time an iteration is performed, iterCnt is incremented by one.

[0135] Sigma is used to dynamically adjust the standard deviation of the normal distribution for seed diffusion, which can be understood as the search range. As the iteration of iterCnt progresses, iterCnt gradually increases while sigma gradually decreases, indicating that the search range gradually shrinks. At the same time, in each generation of the population, individuals with poor performance are eliminated and the most excellent individuals are retained. As sigma gradually decreases, it means that the search starts with a relatively large standard deviation in the initial stage to cover a wide area and gradually narrows down in the later stage for a fine search of the optimal solution, making the whole search increasingly refined.

[0136] Among them, in some specific application scenarios, the decreasing rate of sigma can also be adjusted by nonlinearFactor. The larger the nonlinearFactor, the faster the decreasing rate of sigma. That is, in each iteration, the value of sigma is decreased by nonlinearFactor.

[0137] T200. Based on the fitness value corresponding to the weed individual, combined with the preset maximum seed number, minimum seed number, and the maximum fitness value and minimum fitness value corresponding to the current weed population, calculate the seed number for the corresponding weed individual to generate the next-generation individuals; the expression of the seed number is:

[0138]

[0139] In the formula, seedNum i represents the seed number for the i-th weed individual to generate the next-generation individuals; minSeedNum represents the minimum seed number; maxSeedNum represents the maximum seed number; curRms i represents the fitness value of the i-th weed individual; minRms iter represents the minimum fitness value of the current weed population; maxRms iter represents the maximum fitness value of the current weed population.

[0140] Exemplarily, in some specific embodiments, traverse the entire weed population and calculate the seed number seedNum i of the next-generation seeds for each weed weed i , and the formula is as follows:

[0141]

[0142] where curRms i represents the RMS of the weed weed i , maxRms iter represents the maximum value of the RMS of the current iteration iterCnt population, and minRms iterRepresents the minimum value of the RMS of the current iteration iterCnt population. The subscript iter represents the number of iterations of the current population. Each time the population reproduces, the iteration count iterCnt is incremented by one.

[0143] curRms i The larger, the seedNum i The larger, and vice versa. This means that when the population is farther from the optimal solution, more seeds need to be generated for searching. When the population is closer to the optimal solution, at least each weed can ensure minSeedNum seeds for searching, that is, all weeds participating in reproduction have the opportunity to leave seeds.

[0144] Among them, in some embodiments, before the step of adaptively updating the weed population, the method may further include the following steps: obtaining the number of individuals in the weed population; when the number of individuals is greater than the number of population individuals, sorting the weed individuals in the weed population from smallest to largest based on the fitness value, and then retaining the weed individuals with the smallest number of population individuals in the weed population with the smallest fitness value, and eliminating other weed individuals.

[0145] Exemplarily, in some specific embodiments, all weeds can participate in the competition and eliminate the redundant weeds with poor performance. Specifically, it can be implemented as follows: counting the number of individuals curWeedSize in the current weed population. If it does not exceed maxWeedSize, it indicates that the current population size is stable and there is no need to eliminate redundant weeds. Otherwise, it is necessary to eliminate the weeds with poor performance to ensure that the population data does not exceed maxWeedSize. The elimination rule is as follows: all weeds are sorted from smallest to largest according to RMS, and the first maxWeedSize weeds are selected to enter the next generation of reproduction, and other weeds are all eliminated. Because the smaller the RMS, the better the performance of the weed, so the weeds with larger RMS are eliminated.

[0146] It should be noted that in some embodiments, as Figure 7 shown, the adaptive update of the weed population may include the following steps: S301, traversing the weed individuals in the weed population one by one, and taking the traversed weed individual as the processing individual; S302, generating the corresponding number of adjustment parameters that conform to the normal distribution according to the search range based on the number of seeds corresponding to the processing individual; S303, generating the next-generation individual of the processing individual by combining the adjustment parameters according to the solution parameters corresponding to the processing individual.

[0147] Exemplarily, in some specific embodiments, new weeds can be generated based on a dynamic random method. Specifically, it can be implemented as follows: traversing the entire weed population, the current weed weed i generates seedNum i seeds. Each time the following formula is executed, a new seed will be generated, and execute seedNumi Next, based on weed i seeds will be generated for seedNum i seeds. Until the traversal is completed, the next generation of seeds will be obtained.

[0148]

[0149] newDepth i = depth i + normal(0, sigma)

[0150] where normal represents the normal distribution, and newContrast i is calculated based on a distribution with a mean of 0 and a standard deviation of and newDepth i is calculated based on a distribution with a mean of 0 and a standard deviation of sigma. Regarding the calculation formula of newContrast i , an explanation is needed here as to why the standard deviation is instead of sigma. Because the search range of the density difference contrast is usually not less than 0.4 (maxContrast - minContrast >= 0.4), and the search range of the depth depth is usually not less than 10 (maxDepth - minDepth >= 10), that is, the search area of contrast is smaller. At the same time, in this paper, contrast and depth are not normalized, so the calculation of newContrast i requires a smaller standard deviation. Considering that through a large number of tests, here it means that the difference is taken as The 30 here is taken according to the test results and experience, and it can also be calculated through the following formula.

[0151]

[0152] S400. Increment the iteration count by 1, and return to the step of performing terrain solution and fitness evaluation for each weed individual in the weed population until there is a fitness value less than the preset optimal iteration threshold, or the iteration count reaches the preset maximum iteration count; when the iteration count reaches the maximum iteration count, use the candidate individual as the target individual;

[0153] Exemplarily, in some specific embodiments, after the operation of step S300, it indicates that the growth and reproduction of weeds have been completed once. At this time, the next generation of seeds has grown into weeds, and the population is composed of parent weeds and offspring weeds. Through the natural selection of survival of the fittest, it is determined whether the global optimal solution is searched based on the new population. Steps S200 to S300 are executed iteratively in a loop. Each execution represents one iteration of the growth and reproduction of weeds until the upper limit of the maximum population iteration times maxGenCnt is reached. If it does not exceed, it goes to step S200; otherwise, it goes to step S500.

[0154] S500. Use the result of the terrain solution of the target individual as the final result.

[0155] Exemplarily, in some specific embodiments, what is obtained in this step is the optimal solution of the entire search process. There are only two cases for the solution obtained here: the optimal vector that satisfies the optimal iteration threshold minIterDelt, or the optimal vector obtained by searching the entire space. At this time, the entire search process ends, and not only the search optimal solution is obtained, but also the corresponding Mohorovicic discontinuity model is obtained.

[0156] To explain the principle of the technical solution of the present invention in detail, the overall process of the present invention will be described below in conjunction with some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and should not be regarded as a limitation to the present invention.

[0157] First of all, it should be noted that in the calculation problem of Parker - Oldenburg optimal parameters, the existing research work mainly has the following deficiencies:

[0158] 1) Some research work treats the density difference and depth as a linear relationship, resulting in an inaccurate Mohorovicic discontinuity obtained by Parker - Oldenburg inversion. Different from the existing methods, the core idea of the present invention starts from the non - linear relationship between the density difference and depth.

[0159] 2) Some research work sets the density difference and depth based on experience, resulting in various different Mohorovicic discontinuity models in the same region due to different experiences, and the model quality is uneven and difficult to manage uniformly. Different from the existing methods, the core idea of the present invention is to calculate the optimal parameters by means of swarm intelligence, reducing the interference of individual experience.

[0160] 3) The overall calculation amount is large and there is no unified execution framework, resulting in difficulties in terrain inversion automation, etc., and ultimately the calculation result is rougher than the real result. Different from the existing methods, the present invention proposes an automated calculation process, which can realize the automated search for optimal parameters and the calculation of the optimal model, reducing the manual participation.

[0161] In view of this, the present invention proposes an improved terrain solution method for weed optimization, as Figure 8 shown, the present invention can achieve the following:

[0162] Step 1: Parameter initialization. The parameters mainly include two parts: the parameters of the improved weed optimization algorithm and the parameters of the Parker-Oldenburg inversion method, etc.

[0163] There are a total of 2 parameters for target search, namely contrast (density difference, unit: g / cm3) and depth (depth, unit: km). The input parameters of the improved weed optimization algorithm are respectively:

[0164] Maximum density difference maxContrast: the maximum value of contrast, which is determined by the average value of the target search area, generally obtained according to experience, and satisfies minContrast < maxContrast. In most cases, it is sufficient to satisfy maxContrast - minContrast >= 0.4, and it can be set according to the actual situation.

[0165] Minimum density difference minContrast: the minimum value of contrast, which is determined by the average value of the target search area, generally obtained according to experience, and satisfies minContrast < maxContrast. In most cases, it is sufficient to satisfy maxContrast - minContrast >= 0.4, and it can be set according to the actual situation.

[0166] Maximum depth maxDepth: the maximum value of depth, which is determined by the average value of the target search area, generally obtained according to experience, and satisfies maxDepth < minDepth. In most cases, it is sufficient to satisfy maxDepth - minDepth >= 10, and it can be set according to the actual situation.

[0167] Minimum depth minDepth: the minimum value of depth, which is determined by the average value of the target search area, generally obtained according to experience, and satisfies maxDepth < minDepth. In most cases, it is sufficient to satisfy maxDepth - minDepth >= 10, and it can be set according to the actual situation.

[0168] The maximum number of individuals in the population maxWeedSize, the maximum number of the weed population, is valued according to requirements, and the default is 50.

[0169] The maximum number of iterations of the population maxGenCnt, the maximum number of reproductions of the weed population, is valued according to requirements, and the default is 10.

[0170] The nonlinear adjustment factor, nonlinearFactor, is used to adjust the search accuracy. Its value range is [1, 5], and the default value is 3. Generally, it is a constant. The larger this value, the larger the search range and the worse the search accuracy, and vice versa.

[0171] The maximum number of seeds, maxSeedNum, is the maximum number of seeds generated by a weed individual, which is used to adjust the scale of newly generated seeds in each generation. It is valued according to requirements, and the default value is 6.

[0172] The minimum number of seeds, minSeedNum, is the minimum number of seeds generated by a weed individual, which is used to adjust the scale of newly generated seeds in each generation. It is valued according to requirements, and the default value is 2, satisfying minSeedNum < maxSeedNum.

[0173] The initial iteration threshold, initIterDelt, is used to adjust the search accuracy. Its physical meaning is the error of the Mohorovicic discontinuity model (unit: km). Its value range is [10, 20], and the default value is 10, satisfying initDelt > minIterDelt. The larger this value, the larger the search range and the worse the search accuracy, and vice versa.

[0174] The optimal iteration threshold, minIterDelt. If weeds less than or equal to minIterDelt are found, it means the optimal solution has been found and the entire search process ends directly.

[0175] The parameters of the Parker - Oldenburg inversion method are mainly as follows:

[0176] The density contrast, contrast, in g / cm3, is one of the variables searched by means of the improved weed optimization algorithm, that is, this variable is obtained by the improved weed optimization algorithm and is one of the two search directions mentioned in the present invention.

[0177] The depth, depth, in km, is one of the variables searched by means of the improved weed optimization algorithm, that is, this variable is obtained by the improved weed optimization algorithm and is one of the two search directions mentioned in the present invention.

[0178] The gravity anomaly value matrix, GravityMat: It is a matrix composed of (longitude, latitude, gravity anomaly value) triples, generally data observed by means of seismic surveys, satellite surveys or other means, and is a constant in the present invention.

[0179] The seismic depth matrix, SemisMat: It is a matrix composed of (longitude, latitude, depth) triples, generally data observed by means of seismic surveys, satellite surveys or other means, and is a constant in the present invention.

[0180] Iterative threshold criterion, that is, the iterative rms threshold of the Parker-Oldenburg inversion method. Generally speaking, this is a constant, with a default value of 0.1, and it is a constant in the present invention.

[0181] Frequency threshold WH: The low-pass filtering threshold, the initial value is obtained based on experience, with a default value of 0.1, and it is a constant in the present invention.

[0182] Frequency threshold SH: The high-pass filtering threshold, the initial value is obtained based on experience, with a default value of 0.12, and it is a constant in the present invention.

[0183] Window function threshold truncation: It is a signal sampling weighting function in signal processing. The initial value is obtained based on experience, with a default value of 0.1, and it is a constant in the present invention.

[0184] Step 2: Initialize the weed population. The weed population is composed of a large number of individuals. Each individual has two parameter information, representing the density difference contrast and the average depth depth. The core of population initialization is to generate maxWeedSize individuals, and initialize the corresponding parameters for each individual. The formula is as follows:

[0185] contrast = minContrast + (maxContrast - minContrast) × random()

[0186] depth = minDepth + (maxDepth - minDepth) × random()

[0187] Execute maxWeedSize times to obtain a population composed of maxWeedSize weeds, and go to Step 3.

[0188] Step 3: Traverse the current weed population and calculate the Moho surface respectively. For the current population, traverse the information contrast and depth of each individual one by one, and then calculate the corresponding Moho surface data based on the Parker-Oldenburg inversion method. Go to Step 4.

[0189] Step 4: Traverse the current weed population and calculate the fitness function values respectively. At this time, each individual in the population has calculated the corresponding Moho surface data. Then, combined with the seismic depth matrix SemisMat, calculate the corresponding RMS. Each individual will calculate its own RMS, and finally obtain an array of size maxWeedSize. Go to Step 5.

[0190] Step 5: There are weeds smaller than the threshold. Traverse all weeds to determine if there is a weed with an RMS smaller than the optimal iteration threshold minIterDelt. If so, go to Step 12, indicating that the optimal individual (optimal solution) has been found. Otherwise, go to Step 6.

[0191] Step 6: All weeds participate in competition and eliminate the redundant weeds with poor performance. Count the number of individuals curWeedSize in the current weed population. If it does not exceed maxWeedSize, it means the current population size is stable and there is no need to eliminate redundant weeds. Otherwise, it is necessary to eliminate the weeds with poor performance to ensure that the population data does not exceed maxWeedSize. The elimination rule is as follows: all weeds are sorted in ascending order of RMS, and the first maxWeedSize weeds enter the next generation for reproduction, and all other weeds are eliminated. Since the smaller the RMS, the better the performance of the weed, the weeds with larger RMS are eliminated. Go to Step 5.

[0192] Step 7: Update the Sigma value. Update the value of the sigma variable. The calculation formula is as follows, where maxGenCnt represents the maximum number of iterations, initIterDelt represents the starting iteration threshold, minIterDelt represents the optimal iteration threshold, nonlinearFactor is the nonlinear adjustment factor, and the above several are constants. iterCnt is the current number of iterations, and its value range is [1, maxGenCnt]. Each time an iteration is performed, iterCnt is incremented by one.

[0193]

[0194] sigma is used to dynamically adjust the standard deviation of the normal distribution of seed diffusion, which can be understood as the search range. As iterCnt iterates, iterCnt gradually becomes larger and sigma gradually becomes smaller, indicating that the search range gradually shrinks. At the same time, each generation of the population will eliminate individuals with poor performance and retain the most excellent individuals. As sigma gradually becomes smaller, it means that the search starts from a larger standard deviation in the initial stage to cover a wide area and gradually shrinks in the later stage for fine search of the optimal solution, and the whole search becomes more and more refined.

[0195] The decreasing rate of sigma can also be adjusted by nonlinearFactor. The larger the nonlinearFactor, the faster the decreasing rate of sigma. From a large number of tests, nonlinearFactor = 3 performs better.

[0196] Step 8: Adaptively calculate the number of seeds in the next generation. Traverse the entire weed population and calculate the number of seeds seedNum i of the next generation for each weed weed i . Where curRmsi Denote the weed i RMS, maxRms iter Denote the maximum value of the RMS of the current iteration iterCnt population, minRms iter Denote the minimum value of the RMS of the current iteration iterCnt population. The subscript iter represents the number of times the current population is iterated. Each time the population reproduces, the iteration count iterCnt is incremented by one.

[0197] curRms i The larger it is, the larger seedNum i The larger it is, and vice versa. This means that when the population is farther from the optimal solution, more seeds need to be generated for searching. When the population is closer to the optimal solution, at least minSeedNum seeds can be guaranteed for each weed for searching, that is, all weeds participating in reproduction have the opportunity to leave seeds. Go to step 9.

[0198]

[0199] Step 9: Generate new weeds based on a dynamic random method. Traverse the entire weed population, the current weed i Generate seedNum i seeds. Each time the following formula is executed, a new seed is generated, and it is executed seedNum i times, based on weed i seedNum i seeds will be generated. Until the traversal is complete, the next generation of seeds will be obtained.

[0200]

[0201] newDepth i = depth i + normal(0, sigma)

[0202] where newContrast i is calculated according to a distribution with a mean of 0 and a standard deviation of , and newDepth i is calculated according to a distribution with a mean of 0 and a standard deviation of sigma. Regarding the calculation formula of newContrast i , an explanation is needed here as to why the standard deviation is Rather than sigma. Since the search range of the density difference contrast is usually not less than 0.4 (maxContrast - minContrast >= 0.4), and the search range of the depth is usually not less than 10 (maxDepth - minDepth >= 10), that is, the search area of contrast is smaller. At the same time, in this paper, contrast and depth are not normalized, so the calculation of newContrast i requires a smaller standard deviation. Considering through a large number of tests, here the difference is taken as The 30 here is taken according to the test results and experience, and can also be calculated by the following formula.

[0203]

[0204] There are two places in the present invention where the data changes dynamically. (1) In step 7, as the iteration progresses, the standard deviation of the normal distribution used later gradually becomes smaller, and the entire search process becomes more and more refined. (2) In step 8, in each iteration process, each weed dynamically calculates seedNum according to its distance from the optimal solution i , which improves the search efficiency for long and short distances. These two points are the core points of the innovation of the present invention. Go to step 10.

[0205] Step 10: Obtain the next generation of weed population. After the operations in steps 6 to 9, it means that the growth and reproduction of a generation of weeds are completed. At this time, the next generation of seeds has grown into weeds, and the population is composed of parent weeds and offspring weeds. Through the natural selection of survival of the fittest, it is judged whether the global optimal solution is searched based on the new population. Go to step 11.

[0206] Step 11: Meet the maximum population iteration times. Steps 3 to 10 are executed in a loop. Each execution represents one iteration of the weed growth and reproduction until the upper limit of the maximum population iteration times maxGenCnt. If it has not exceeded, go to step 3, otherwise go to step 12.

[0207] Step 12: Find the optimal solution. The solution obtained in this step is the optimal solution of the entire search process. There are only two cases for the solution obtained here: the optimal vector that meets the optimal iteration threshold minIterDelt, or the optimal vector obtained by searching the entire space. At this time, the entire search process ends, and not only the search optimal solution is obtained, but also the corresponding Mohorovicic discontinuity model is obtained.

[0208] In summary, the present invention proposes a terrain solution method for improving weed optimization. By improving the weed optimization algorithm to find the optimal parameters and with the aid of the Parker-Oldenburg inversion method, a more accurate Mohorovicic discontinuity is obtained. The method includes:

[0209] 1) Propose to search for the optimal density contrast and depth based on the improved weed optimization algorithm. With the aid of the self-adaptive reproduction strategy of the weed population, the solution accuracy of the key parameters is improved;

[0210] 2) Propose an optimized population iterative update strategy to achieve rough search in the initial stage and precise search in the later stage, and improve the search efficiency of the key parameters;

[0211] 3) Combine the improved weed optimization algorithm and the Parker-Oldenburg inversion, and design an automated search for the optimal parameters and an optimal model solution process to improve the automation efficiency of data processing.

[0212] Specifically, the specific implementation manner of the present invention jointly solves a more accurate Mohorovicic discontinuity by searching for the optimal density contrast and depth based on the improved weed optimization algorithm and the Parker-Oldenburg inversion method.

[0213] On the other hand, as Figure 9 shown, the embodiment of the present invention provides a terrain solution device 900 for improving weed optimization, which may include:

[0214] A first module 901, configured to initialize the solution parameters for terrain solution to obtain a weed population; the weed population includes weed individuals containing solution parameters with a preset population individual quantity;

[0215] A second module 902, configured to traverse each weed individual in the weed population for terrain solution and fitness evaluation to obtain the fitness value corresponding to each weed individual;

[0216] A third module 903, configured to, when there is a fitness value less than a preset optimal iteration threshold, use the corresponding weed individual as the target individual; otherwise, use the weed individual with the smallest fitness value as the candidate individual and perform self-adaptive update on the weed population;

[0217] A fourth module 904, configured to increment the iteration number by 1, return to execute the second module until there is a fitness value less than a preset optimal iteration threshold, or the iteration number reaches a preset maximum iteration number; when the iteration number reaches the maximum iteration number, use the candidate individual as the target individual;

[0218] Among them, in the process of adaptive update, the number of seeds generated by each weed individual for the next generation of individuals is positively correlated with the fitness value of the corresponding weed individual, and the search range applied by each weed individual to generate the next generation of individuals is negatively correlated with the number of iterations;

[0219] The fifth module 905 is used to take the result of the terrain solution of the target individual as the final result.

[0220] In some embodiments, the device may further include:

[0221] The sixth module is used to calculate the search range based on the number of iterations in combination with a preset constant;

[0222] Among them, the preset constant includes the maximum number of iterations, the starting iteration threshold, the optimal iteration threshold, and the nonlinear adjustment factor; the expression of the search range is:

[0223]

[0224] In the formula, sigma represents the search range; maxGenCnt represents the maximum number of iterations; initIterDelt represents the starting iteration threshold; minIterDelt represents the optimal iteration threshold; nonlinearFactor represents the nonlinear adjustment factor; iterCnt represents the number of iterations;

[0225] The seventh module is used to calculate the number of seeds generated by the corresponding weed individual for the next generation of individuals based on the fitness value of the weed individual, in combination with the preset maximum number of seeds and minimum number of seeds, and the maximum fitness value and minimum fitness value of the current weed population; the expression of the number of seeds is:

[0226]

[0227] In the formula, seedNum i represents the number of seeds generated by the i-th weed individual for the next generation of individuals; minSeedNum represents the minimum number of seeds; maxSeedNum represents the maximum number of seeds; curRms i represents the fitness value of the i-th weed individual; minRms iter represents the minimum fitness value of the current weed population; maxRms iter represents the maximum fitness value of the current weed population.

[0228] In some embodiments, the device may further include an eighth module, which is executed before the adaptive update of the weed population. The eighth module is used to:

[0229] Obtain the number of individuals in the weed population;

[0230] When the number of individuals is greater than the population size, sort the weed individuals in the weed population from smallest to largest based on the fitness value, and then retain the number of weed individuals with the smallest fitness value in the weed population, and eliminate the other weed individuals.

[0231] The content of the method embodiments of the present invention is applicable to the device embodiments. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method.

[0232] On the other hand, the embodiments of the present invention also provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the above-mentioned terrain solving method for improving weed optimization. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0233] It can be understood that the content in the above method embodiments is applicable to the device embodiments of the present invention. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0234] As Figure 10 shown, Figure 10 schematically shows the hardware structure of an electronic device 1000 according to another embodiment. The electronic device 1000 includes:

[0235] A processor 1001, which can be implemented by using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present invention;

[0236] A memory 1002, which can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 1002 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1002 and are called by the processor 1001 to execute the network node population optimization method of the embodiments of the present invention;

[0237] An input / output interface 1003, which is used to implement information input and output;

[0238] A communication interface 1004, which is used to implement communication interaction between this device and other devices, can achieve communication through a wired method (such as USB, network cable, etc.), or can also achieve communication through a wireless method (such as mobile network, WIFI, Bluetooth, etc.);

[0239] A bus 1005, which transmits information between various components of the device (such as a processor 1001, a memory 1002, an input / output interface 1003, and a communication interface 1004);

[0240] Among them, the processor 1001, the memory 1002, the input / output interface 1003, and the communication interface 1004 achieve communication connections with each other inside the device through the bus 1005.

[0241] The electronic device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0242] The content of the method embodiments of the present invention is applicable to the electronic device embodiments of the present invention. The functions specifically implemented by the electronic device embodiments of the present invention are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above methods.

[0243] Another aspect of the embodiments of the present invention also provides a computer-readable storage medium. The storage medium stores a program, and the program is executed by a processor to implement the previous method.

[0244] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present invention, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0245] The content of the method embodiments of the present invention is applicable to this computer-readable storage medium embodiment. The functions specifically implemented by this computer-readable storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method.

[0246] The embodiments of the present invention also disclose a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the previous method.

[0247] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0248] It should be noted that although several modules of devices for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-described modules or units can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0249] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0250] In some alternative embodiments, the functions / operations mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously, or the blocks can sometimes be executed in the reverse order. In addition, the embodiments presented and described in the flowcharts of the present invention are provided by way of example for the purpose of providing a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated, in which the order of various operations is changed and the sub-operations described as part of a larger operation are executed independently.

[0251] In addition, although the present invention has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It should also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. Rather, considering the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the modules will be understood within the ordinary skills of an engineer. Thus, those skilled in the art can implement the present invention as set forth in the claims without undue experimentation. It should also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0252] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0253] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution device, apparatus, or equipment (such as a computer-based device, a device including a processor, or other devices that can fetch instructions from and execute instructions by the instruction execution device, apparatus, or equipment), or used in combination with these instruction execution devices, apparatuses, or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution device, apparatus, or equipment.

[0254] More specific examples (nonexhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0255] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0256] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do 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.

[0257] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the claims and their equivalents.

[0258] The above has specifically described the preferred embodiments of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present invention.

Claims

1. An improved terrain solving method for weed optimization, characterized in that, Including the following steps: Initialize the solution parameters for terrain solution to obtain a weed population; the weed population includes weed individuals containing the solution parameters with a preset population individual quantity; Traverse each weed individual in the weed population for terrain solution and fitness evaluation to obtain the fitness value corresponding to each weed individual; When there is a fitness value less than a preset optimal iteration threshold, use the corresponding weed individual as the target individual; Otherwise, use the weed individual with the smallest fitness value as the candidate individual and perform adaptive update on the weed population; Increment the iteration count by 1, and return to execute the step of traversing each weed individual in the weed population for terrain solution and fitness evaluation until there is a fitness value less than the preset optimal iteration threshold, or the iteration count reaches the preset maximum iteration count; When the iteration count reaches the maximum iteration count, use the candidate individual as the target individual; Wherein, in the process of the adaptive update, the number of seeds for each weed individual to generate the next-generation individuals is positively correlated with the fitness value of the corresponding weed individual, and the search range applied by each weed individual to generate the next-generation individuals is negatively correlated with the iteration count; Use the result of the terrain solution of the target individual as the final result.

2. The improved terrain solving method for optimizing weeds according to claim 1, wherein, The step of traversing each weed individual in the weed population for terrain solution and fitness evaluation to obtain the fitness value corresponding to each weed individual includes the following steps: Traverse each weed individual in the weed population for terrain solution to obtain the terrain data corresponding to each weed individual; Perform fitness evaluation on the terrain data to obtain the fitness value corresponding to each weed individual.

3. The improved terrain solving method for weed optimization according to claim 2, characterized in that, The step of traversing each weed individual in the weed population for terrain solution to obtain the terrain data corresponding to each weed individual includes the following steps: Traverse and obtain the solution parameters corresponding to each weed individual in the weed population; Based on the solution parameters corresponding to each weed individual, process them one by one through the Parker-Oldenburg inversion method to obtain the Moho data corresponding to each weed individual.

4. The improved terrain solving method for weed optimization according to claim 2, characterized in that, The step of performing fitness evaluation on the terrain data to obtain the fitness value corresponding to each weed individual includes the following steps: Perform root-mean-square operation according to the terrain data corresponding to the weed individual in combination with a preset seismic depth matrix; Use the result of the root-mean-square operation as the fitness value corresponding to the weed individual.

5. The improved weed optimization-based terrain solving method according to claim 1, wherein, The method further includes the following steps: Calculate the search range based on the iteration count in combination with a preset constant; Wherein, the preset constant includes the maximum iteration count, the starting iteration threshold, the optimal iteration threshold, and the nonlinear adjustment factor; the expression of the search range is: wherein, sigma represents the search range; maxGenCnt represents the maximum number of iterations; initIterDelt represents the starting iteration threshold; minIterDelt represents the optimal iteration threshold; nonlinearFactor represents the nonlinear adjustment factor; iterCnt represents the number of iterations; Based on the fitness value corresponding to the weed individual, and in combination with the preset maximum number of seeds and minimum number of seeds, as well as the maximum fitness value and minimum fitness value corresponding to the current weed population, calculate the number of seeds for the corresponding weed individual to generate the next-generation individuals; the expression of the number of seeds is: where seedNum i represents the number of seeds produced by the \(i\)-th weed individual to generate the next generation of individuals; minSeedNum represents the minimum number of seeds; maxSeedNum represents the maximum number of seeds; curRms i represents the fitness value of the \(i\)-th weed individual; minRms iter represents the minimum fitness value of the current weed population; maxRms iter represents the maximum fitness value of the current weed population.

6. The improved terrain solving method for weed optimization according to claim 1, characterized in that, The adaptive update of the weed population includes the following steps: Traverse each weed individual in the weed population one by one, and use the traversed weed individual as the processing individual; Based on the number of seeds corresponding to the processing individual, generate the corresponding number of adjustment parameters that conform to the normal distribution according to the search range; Generate the next-generation individual of the processing individual according to the solution parameters corresponding to the processing individual in combination with the adjustment parameters.

7. The improved terrain solving method for weed optimization according to claim 1, characterized in that, Before the step of adaptively updating the weed population, the method further includes the following steps: Obtain the number of individuals in the weed population; When the number of individuals is greater than the number of population individuals, sort the weed individuals in the weed population from small to large based on the fitness value, and then retain the weed individuals with the smallest fitness value in the number of population individuals in the weed population, and eliminate the other weed individuals.

8. An improved terrain solving device for weed optimization, characterized in that including: The first module is used to initialize the solution parameters for terrain solution to obtain a weed population; the weed population includes weed individuals containing the solution parameters with a preset number of population individuals; The second module is used to traverse each weed individual in the weed population for terrain solution and fitness evaluation to obtain the fitness value corresponding to each weed individual; The third module is used to, when there is a fitness value less than the preset optimal iteration threshold, use the corresponding weed individual as the target individual; Otherwise, use the weed individual with the smallest fitness value as the candidate individual, and perform adaptive update on the weed population; The fourth module is used to increment the number of iterations by 1, return to execute the second module until there is a fitness value less than the preset optimal iteration threshold, or the number of iterations reaches the preset maximum number of iterations; When the number of iterations reaches the maximum number of iterations, use the candidate individual as the target individual; wherein, in the process of the adaptive update, the number of seeds for each weed individual to generate the next-generation individual is positively correlated with the fitness value of the corresponding weed individual, and the search range applied by each weed individual to generate the next-generation individual is negatively correlated with the number of iterations; The fifth module is used to use the result of the terrain solution of the target individual as the final result.

9. An electronic device, characterized in that, including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer storage medium storing a program executable by a processor, characterized in that, The program executable by the processor, when executed by the processor, is used to implement the method according to any one of claims 1 to 7.

Images