Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a combined path optimization method and a combined path optimization system considering group heterogeneity, which are used for determining the heterogeneity characteristics of group members, dividing the group members into heterogeneous characteristic group combinations according to the heterogeneity characteristics, generating a delivery initial path when delivering goods for each heterogeneous characteristic group combination, optimizing the delivery initial path, searching for a delivery optimal path, evaluating the effect of the optimal path, outputting an optimal path result, searching for the shortest path through searching and iterating the path, combining the time required from a starting point to a terminal point, and selecting the optimal path by considering the heterogeneity characteristic factors of obstacles, road conditions, gate barriers and heterogeneous group members, thereby greatly improving the delivery efficiency and having great significance for delivery of takeaway.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the combined path optimization method considering the group heterogeneity comprises the following steps:
step S1: determining the heterogeneity characteristics of the population members, and dividing the population members into heterogeneous characteristic population combinations according to the heterogeneity characteristics;
step S2: when each heterogeneous characteristic group is combined for delivery, generating a delivery initial path;
step S3: optimizing the initial delivery path, and searching an optimal delivery path;
step S4: and evaluating the effect of the optimal path and outputting the optimal path result.
Specifically, the heterogeneity of the step S1 includes: differences in personality, psychological needs, and social context.
Specifically, the specific steps of the step S2 are as follows:
step S201: the set of group members is set to Q,,/>representing an nth heterogeneous population of combinations of features;
step S202: and setting the departure point as A and the destination point as B when delivering goods, and automatically planning and generating an initial path by map software when heterogeneous characteristic group members deliver goods from the point A to the point B.
Specifically, the map software in step S202 includes: a Goldmap, a Tencel map, and a hundred degree map.
Specifically, the specific steps of the step S3 include:
step S301: setting the motion step length of the heterogeneous characteristic group members in unit time as d, dividing a map in a grid shape, setting the side length of a square grid as d, and setting a rectangular coordinate system by taking a square starting point A as an origin;
step S302: the heterogeneous characteristic group members send out from the starting point A, find paths leading to the grid of the end point B, generate M paths, and iterate and preferential the generated M paths;
step S303: and gradually iterating to obtain the optimal delivery path.
Specifically, the specific steps of step S302 include:
step S3021: searching paths A to B, wherein a search calculation formula is as follows:
,
wherein,representing the probability of the next waypoint searched by heterogeneous feature population member k at time t,representing the amount of information on the path-grid point (i, j), for example>Represents a path information quantity heuristic, ++>Representing the desirability of the current path-grid point to transition to path-grid point (i, j), +.>Representing the desired heuristic->Indicating obstacle avoidance factors, < >>Represents grid points in a square area connected by AB lines as diagonals, +.>Representing an obstacle factor;
step S3022: obstacle avoidance factorThe calculation formula of (2) is as follows: />WhereinRepresents the total number of grids adjacent to grid point (i, j), +.>Representing the total number of grids adjacent to grid point (i, j) and having obstacles, +.>Representing the total number of meshes adjacent to the mesh point (i, j), having an obstacle and passing through;
step S3023: iterating according to the searched paths until grid points passing through the paths from A to B are connected, and calculating the time required from A to B,/>The calculation formula of (2) is as follows:
wherein->Represents the path distance from A to B, +.>Representing the movement speed of members of the heterogeneous characteristic population, < ->Representing road condition influence factors->Representing the door barrier influencing factor->A heterogeneity influencing factor representing members of a heterogeneous characteristic population;
step S3024: selectingFor an optimized delivery optimal path, wherein +.>Represents path optimization weights, ++>Representing time optimized weights.
A combined path optimization system that accounts for group heterogeneity, comprising: the system comprises a heterogeneous population screening module, a path optimizing module and a path evaluating module;
the heterogeneous population screening module is used for dividing population members into heterogeneous characteristic population combinations according to the heterogeneous characteristics of the heterogeneous population screening module;
the path optimization module is used for searching a delivery path from a starting point to a destination point, optimizing the delivery path and selecting an optimal path;
and the path evaluation module is used for evaluating the optimal path.
Specifically, the heterogeneous population screening module comprises a heterogeneous population characteristic identification unit, a heterogeneous population characteristic screening unit and a heterogeneous population member combination unit;
the heterogeneous group feature recognition unit is used for recognizing heterogeneous features of heterogeneous group members;
the heterogeneous population characteristic screening unit is used for screening heterogeneous characteristics in heterogeneous population members;
the heterogeneous group member combination unit is used for combining heterogeneous group members subjected to heterogeneous characteristic screening, and the same heterogeneous characteristics are a group.
Specifically, the path optimization module comprises a path searching unit and a path optimization unit;
the path searching unit is used for searching paths from the starting point to the end point;
the path optimization unit is used for optimizing the searched path in consideration of relevant factors influencing path optimization, and the characteristics of heterogeneity of barriers, road conditions, barriers and heterogeneous population members.
Specifically, the relevant factors of the path optimization include obstacle factors, road condition factors, door obstacle factors and heterogeneous group member heterogeneous characteristic factors.
An electronic device comprising a memory storing a computer program and a processor implementing the steps of a combined path optimization method taking account of group heterogeneity when executing the computer program.
A computer readable storage medium having stored thereon computer instructions which, when executed, perform the steps of a combined path optimization method that takes into account group heterogeneity.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention provides a combined path optimization system considering group heterogeneity, and performs optimization and improvement on architecture, operation steps and flow, and the system has the advantages of simple flow, low investment and operation cost and low production and working costs.
2. The invention provides a combined path optimization method considering group heterogeneity, which is characterized in that the heterogeneity characteristics of group members are determined, the group members are divided into heterogeneous characteristic group combinations according to the heterogeneity characteristics, when each heterogeneous characteristic group combination is used for delivering goods, a delivery initial path is generated, the delivery initial path is optimized, the optimal delivery path is searched, the effect of the optimal path is evaluated, the optimal path result is output, the shortest path is searched through searching and iterating the paths, the time required from the starting point to the end point is combined, and the heterogeneous characteristic factors of barriers, road conditions, barriers and heterogeneous group members are considered, so that the optimal path is selected, the delivery efficiency is greatly improved, and the method has great significance for delivery of takeaway.
3. The invention provides a combination path optimization method considering group heterogeneity, which can pertinently plan the combination of heterogeneous groups by considering obstacle factors, road condition factors, gate obstacle factors and heterogeneous group member heterogeneity characteristic factors, thereby improving the goods delivery and take-out efficiency of the heterogeneous group combination and saving a great deal of time and cost.
Detailed Description
In order that the technical means, the creation characteristics, the achievement of the objects and the effects of the present invention may be easily understood, it should be noted that in the description of the present invention, the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements to be referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "a", "an", "the" and "the" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The invention is further described below in conjunction with the detailed description.
Example 1
Referring to fig. 1-3, an embodiment of the present invention is provided: gait recognition correction method based on deep learning comprises the following steps:
the combined path optimization method considering the group heterogeneity comprises the following steps:
step S1: determining the heterogeneity characteristics of the population members, and dividing the population members into heterogeneous characteristic population combinations according to the heterogeneity characteristics;
heterogeneity refers to the differences in personality, psychological needs, social context, etc. among members. This can lead to heterogeneous populations where feelings of identity and affiliation have not been established (long term and psychological communication is required), and the bruise of population emotion, especially in the middle of heterogeneous populations, can be intensified by the complete disappearance of the sense of responsibility. The storm is conducted from one part of the people A to the other part of the people B, the group B conducts the emotion progress one step to the group C, and the group C conducts the emotion enhancement to the group A.
Step S2: when each heterogeneous characteristic group is combined for delivery, generating a delivery initial path;
step S3: optimizing the initial delivery path, and searching an optimal delivery path;
step S4: and evaluating the effect of the optimal path and outputting the optimal path result.
The heterogeneity of step S1 includes: differences in personality, psychological needs, and social context.
The specific steps of the step S2 are as follows:
step S201: the set of group members is set to Q,,/>representing an nth heterogeneous population of combinations of features;
step S202: and setting the departure point as A and the destination point as B when delivering goods, and automatically planning and generating an initial path by map software when heterogeneous characteristic group members deliver goods from the point A to the point B.
The map software in step S202 includes: a Goldmap, a Tencel map, and a hundred degree map.
Drawbacks of map software planning: 1) The combination of a recommended route and a small route cannot be accurate because many small routes have special cases, such as: lane paths with insufficient vehicle spacing; 2) The route cannot be planned according to the characteristics of heterogeneous group members, and the path selection is different because the heterogeneous group members can affect each other; 3) Walking in a cell and a campus cannot be recommended, and due to the fact that the factors considered in walking in the cell and the campus are more, the cell and the campus door are not necessarily opened, verification and the like are needed.
The specific steps of the step S3 include:
step S301: setting the motion step length of the heterogeneous characteristic group members in unit time as d, dividing a map in a grid shape, setting the side length of a square grid as d, and setting a rectangular coordinate system by taking a square starting point A as an origin;
step S302: the heterogeneous characteristic group members send out from the starting point A, find paths leading to the grid of the end point B, generate M paths, and iterate and preferential the generated M paths;
step S303: and gradually iterating to obtain the optimal delivery path.
The specific steps of step S302 include:
step S3021: searching paths A to B, wherein a search calculation formula is as follows:
,
wherein,representing the probability of the next waypoint searched by heterogeneous feature population member k at time t,representing the amount of information on the path-grid point (i, j), for example>Represents a path information quantity heuristic, ++>Representing the desirability of the current path-grid point to transition to path-grid point (i, j), +.>Representing the desired heuristic->Indicating obstacle avoidance factors, < >>Represents grid points in a square area connected by AB lines as diagonals, +.>Representing an obstacle factor;
common path search algorithms: 1) The ant colony algorithm uses the form of the path pheromone to communicate due to the information exchange in the ant colony, so that when an ant walks through a path, the pheromone is left on the path, and other ants can judge whether the path is good or bad by sensing the pheromone, thereby guiding the advancing direction of the ant. The pheromone forms positive feedback phenomenon in the process of releasing and path optimizing, namely, the more ants walk in the path, the better the optimizing path is, the more the ants are likely to select a better path, and therefore, the target path is obtained. The ant colony algorithm has the characteristic of distributed computation, because each ant can only see the surrounding information, and the ants can jointly decide the optimal path through the transmission and perception of pheromones, thereby realizing the distributed computation. The ant colony algorithm has good expandability and adaptability, and can solve the problem of large-scale and complex optimization. The ant colony algorithm is used for the path optimizing problem and can be divided into two stages of path construction and pheromone updating. In the path construction, the probability of the lower node is calculated according to the pheromone concentration and the distance from the current node to other nodes, and in the selected path, ants have a high probability of selecting the direction with the closer distance and the larger pheromone concentration, because the direction is the direction of the optimal path. The updating of the pheromone is to update the concentration of the pheromone on the path according to the quality and importance of a certain node after the ant accesses the node, so as to lead the ant to be more likely to select the node in the next path construction. This update process can be expressed in terms of a pheromone concentration differential equation. Through the alternate iteration of the two stages, the ant population can continuously optimize the global optimal solution of the path, thereby solving the path optimizing problem; 2) The genetic algorithm converts the solving process of the problem into processes like crossing, mutation and the like of chromosome genes in the biological evolution by using a computer simulation operation in a mathematical mode. When solving the complex combined optimization problem, a better optimization result can be obtained faster than that of some conventional optimization algorithms.
Two algorithms suffer from the disadvantages: the ant colony algorithm is based on simulating the food searching behavior of ants, and utilizes pheromones and heuristic function values to guide ants to select paths. However, since the heuristic function value only considers the reciprocal of the distance of the node to the target point, the effect of avoiding the obstacle is poor. In addition, in a complex path planning environment, the ant colony algorithm needs to be optimized in a huge search space, and because the concentration of pheromones on an initial path is small, forward feedback information is not obvious enough, blind search is easy to fall into, a large number of local cross paths are caused, and algorithm efficiency is reduced. In addition, the ant colony algorithm is easy to fall into local optimum, and searches to a certain extent, a dead point phenomenon possibly occurs, and as all individuals cannot obtain better solutions, better solutions cannot be searched further.
The programming implementation of the genetic algorithm is complex, firstly, the problem needs to be encoded, the problem needs to be decoded after the optimal solution is found, and in addition, the implementation of three operators also has a plurality of parameters, such as the crossover rate and the mutation rate, and the selection of the parameters seriously affects the quality of the solution, but most of the current selection of the parameters depends on experience and cannot timely utilize the feedback information of the network, so that the searching speed of the algorithm is slower, more training time is needed for the more accurate solution, the algorithm has certain dependence on the selection of the initial population, the improvement can be carried out by combining with some heuristic algorithms, and the potential capability of the parallel mechanism of the algorithm is not fully utilized, thus the method is a research hotspot direction of the current genetic algorithm.
Step S3022: obstacle avoidance factorThe calculation formula of (2) is as follows: />WhereinRepresents the total number of grids adjacent to grid point (i, j), +.>Representing the total number of grids adjacent to grid point (i, j) and having obstacles, +.>Representing the total number of meshes adjacent to the mesh point (i, j), having an obstacle and passing through;
step S3023: iterating according to the searched paths until grid points passing through the paths from A to B are connected, and calculating the time required from A to B,/>The calculation formula of (2) is as follows:
wherein->Represents the path distance from A to B, +.>Representing the movement speed of members of the heterogeneous characteristic population, < ->Representing road condition influence factors->Representing the door barrier influencing factor->A heterogeneity influencing factor representing members of a heterogeneous characteristic population;
step S3024: selectingFor an optimized delivery optimal path, wherein +.>Represents path optimization weights, ++>Representing time optimized weights.
The path is further optimized: because the algorithm is easy to stagnate when approaching the target position and the searching speed is slower, the adoption of the approach surrounding spiral predation strategy provides the algorithm with the advantages of accelerating the efficient and accurate searching in the later period of searching, and the searching calculation formula is as follows:
wherein (1)>Representing the close surrounding helical predation coefficient, +.>,/>The adjustment coefficient is represented, and the value range is (0).5,1),/>Represents the maximum number of iterations, +.>Representing the current iteration number, X (t+1) represents the next grid point of the close surrounding spiral predation search, +.>Represents the position of the currently best heterogeneous member, +.>The current position of the heterogenous member, C, D, E, is constant and has a value of [ -1,1]E represents a natural logarithm, b represents a logarithmic spiral shape constant, and r is a random number between-1 and 1. Judging whether the iteration times reach the set value, if not, continuing searching, otherwise, stopping searching, and storing path information.
The whale optimization algorithm (WOA, whaleOptimizationAlgorithm) is a group optimization algorithm based on meta-heuristics, and has been highly focused and pursued by a plurality of domestic and foreign researchers since 2016. The bubble network optimizing mode has strong local searching capability, but is easy to be trapped in local optimization and has weak exploratory property. In recent years, many students have improved whale optimization algorithms from different aspects, so that the whale optimization algorithms have better optimizing capability. Hybrid heuristics have proven to be more effective than single algorithm approaches as one of the most effective approaches to improving algorithm performance. The WOA has been widely popularized in various fields by combining with other algorithms since the proposal. One of the most common strategies for constructing hybrid WOA is to simply hybridize the two algorithms in a certain manner. Another strategy to construct hybrid WOA is to combine operators with complementary fusion features into WOA, forming a superior algorithm. In the prior art, a hybrid particle cluster optimization and whale optimization algorithm, called PSOWOA, processes global numerical function optimization. The main idea is to combine the optimal features of the two algorithms to form a new mutation operator. In the prior art, a whale optimization algorithm and a wolf optimization algorithm WOA-GWO are mixed to optimally coordinate the direction of the overcurrent relay. In the prior art, IWOA, they developed a nonlinear convergence factor that does not decrease in a linear fashion with iteration number, but instead uses a nonlinear function to adjust the value, thereby improving convergence speed and accuracy. Aiming at the problem of low convergence rate of the whale optimization algorithm, researchers introduce a chaos theory into the algorithm, and adjust algorithm parameters by using chaos mapping so as to improve the optimization performance of the algorithm. The chaotic map has certain randomness and nonlinear characteristics, so that the diversity and search space of the algorithm can be increased, and the algorithm is more likely to find the globally optimal solution. Experimental results show that the convergence rate of the whale optimization algorithm is remarkably improved through the introduction of the chaos theory, and the algorithm has better robustness and global searching capability when processing complex problems. In the prior art, a chaotic search strategy is introduced into an original algorithm, and the chaotic search strategy updates individuals with poor adaptability in a population by using chaotic mapping to generate random numbers, so that new positions are given to the individuals, and the situation that the algorithm falls into a local optimal solution and cannot jump out is avoided. By the method, the population superiority can be guaranteed, the diversity of the algorithm and the global searching capability are increased, and therefore the optimization performance of the algorithm is improved. Experiments prove that the whale optimization algorithm after the chaotic search strategy is introduced can find out the global optimal solution more quickly, and has better robustness and stability when solving the complex problem. In the prior art, a positive and redundant chaotic double-string mechanism is introduced, so that the algorithm stability and optimizing capability of whale predation stage can be improved. Simulation experiment results show that the performance of the improved algorithm is excellent. In the prior art, a disturbance WOA (CWOA) refers to changing parameters of the WOA and accelerating convergence by using a disturbance map. In the prior art, WOA (MWOA) was improved using nonlinear power strategies, levy flight and quadratic interpolation to avoid the accuracy of local optimization and solution. In the prior art, levy flight and a chaotic local search mechanism are utilized in balancing WOA, so that precocity is avoided, and the superiority of understanding is improved. WOA is mixed with a particle swarm optimization algorithm, wherein the algorithm is named as HWPSO, and in the testing process, the stagnation of the optimization algorithm is effectively avoided. In the prior art, two WOA improvements: IWAA and IWAA+, and the differential supervised exploration capability is utilized to improve the optimizing exploration capability of WOA. In the prior art, the WOA algorithm is inspired by chaotic mapping and opposite learning, and differential evolution is used for improving the optimization speed of the WOA algorithm. These improved methods aim to enhance the search and optimization capabilities of the WOA algorithm. In the prior art, the WOAneller algorithm is mixed, which is a mixed design by means of the Nelder algorithm.
Example 2
Referring to fig. 4, another embodiment of the present invention is provided: a combined path optimization system that accounts for group heterogeneity, comprising:
the system comprises a heterogeneous population screening module, a path optimizing module and a path evaluating module;
the heterogeneous population screening module is used for dividing population members into heterogeneous characteristic population combinations according to the heterogeneous characteristics of the heterogeneous population screening module;
the path optimization module is used for searching a delivery path from a starting point to a destination point, optimizing the delivery path and selecting an optimal path;
and the path evaluation module is used for evaluating the optimal path.
The heterogeneous population screening module comprises a heterogeneous population characteristic identification unit, a heterogeneous population characteristic screening unit and a heterogeneous population member combination unit;
the heterogeneous group feature recognition unit is used for recognizing heterogeneous features of heterogeneous group members;
the heterogeneous population characteristic screening unit is used for screening heterogeneous characteristics in heterogeneous population members;
the heterogeneous group member combination unit is used for combining heterogeneous group members subjected to heterogeneous characteristic screening, and the same heterogeneous characteristics are a group.
The path optimization module comprises a path searching unit and a path optimization unit;
the path searching unit is used for searching paths from the starting point to the end point;
the path optimization unit is used for optimizing the searched path in consideration of relevant factors influencing path optimization, and the characteristics of heterogeneity of barriers, road conditions, barriers and heterogeneous population members.
Relevant factors of path optimization comprise obstacle factors, road condition factors, door obstacle factors and heterogeneous characteristic factors of heterogeneous group members.
Example 3
Referring to fig. 5, an electronic device includes a memory storing a computer program and a processor implementing steps of a combined path optimization method that take account of group heterogeneity when executing the computer program.
A computer readable storage medium having stored thereon computer instructions which, when executed, perform the steps of a combined path optimization method that takes into account group heterogeneity.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are all within the protection of the present invention.