CN116492685B - Path planning method - Google Patents
Path planning method Download PDFInfo
- Publication number
- CN116492685B CN116492685B CN202310785126.3A CN202310785126A CN116492685B CN 116492685 B CN116492685 B CN 116492685B CN 202310785126 A CN202310785126 A CN 202310785126A CN 116492685 B CN116492685 B CN 116492685B
- Authority
- CN
- China
- Prior art keywords
- node
- path
- data
- current
- preference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000010845 search algorithm Methods 0.000 claims abstract description 4
- 238000012790 confirmation Methods 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000006399 behavior Effects 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 230000000694 effects Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 239000000758 substrate Substances 0.000 claims 5
- 239000000523 sample Substances 0.000 claims 1
- 230000009471 action Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000005291 magnetic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000003936 working memory Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/55—Controlling game characters or game objects based on the game progress
- A63F13/56—Computing the motion of game characters with respect to other game characters, game objects or elements of the game scene, e.g. for simulating the behaviour of a group of virtual soldiers or for path finding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Multimedia (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Human Computer Interaction (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a path planning method, which comprises the following steps: obtaining a starting point position and an end point position; acquiring a map array of the game map, and if the map array does not exist, creating the map array according to the game map; calculating the preference degree of all key positions in the estimated feasible region of the map array according to the user preference model, and screening out the preference positions; the estimated feasible region refers to a possible path existence region from a starting point position to an end point position; initializing a search algorithm; searching paths to obtain planning path data; by the method, path planning according to the user characteristics can be realized, and the game experience of a game player is improved.
Description
Technical Field
The application relates to the technical field of computers, in particular to a path planning method.
Background
The role playing game has complete environment, scene, characters, scenario and other factors, and has good game experience, high playability and wide popularity among players. The path planning of role actions in the game is an important direction for improving the experience of a player currently in a role playing game, and particularly for the game with complex scene, huge map area and complicated task scenario, the game experience of the player can be greatly improved by helping the player to perform the path planning.
Current ways of path planning in games include path planning by planarizing a three-dimensional map into a two-dimensional map, path planning by introducing altitude difference data into the three-dimensional map, and the like. However, the current path planning method can only meet the basic requirement that the character moves from the starting point to the end point, ignores the position with unique design in the game, cannot meet the requirement for exploring the game scene, easily loses the game interest by the player, and reduces the overall game experience. Moreover, current game path planning does not take into account the personalized needs of different players, resulting in poor game experience.
Disclosure of Invention
Aiming at the limitation of the existence, the application provides a path planning method, which carries out path searching by determining a predicted feasible region and screening a preference position, fully considers the preference characteristics of players and improves the efficiency of path searching.
In order to achieve the above purpose, the present application adopts the following technical scheme:
a method of path planning, the method comprising the steps of:
step 1, obtaining a starting point position and an end point position;
the starting point position and the end point position are coordinate values of a starting point and an end point respectively;
step 2, acquiring a map array of the game map, and if the map array does not exist, creating the map array according to the game map;
the map array is a two-dimensional array and is used for storing game map data;
step 3, calculating the preference degree of all key positions in the estimated feasible region of the map array according to the user preference model, and screening out the preference positions;
the estimated feasible region refers to a possible path existence region from a starting point position to an end point position;
step 4, initializing a search algorithm;
and 5, searching paths to obtain planning path data.
Compared with the prior art, the application has the following advantages:
(1) The key positions and the user preference are taken as consideration factors of game path planning, so that the requirement of character movement is met, meanwhile, the personalized exploration requirement of a player is fully considered, path planning is carried out according to the user characteristics, and the game experience of the game player is improved.
(2) Before formal path searching is carried out, the estimated feasible region is determined, and the preference position screening and path planning are carried out in the estimated feasible region, so that the path searching efficiency can be effectively improved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application, as well as the preferred embodiments thereof, together with the following detailed description of the application, given by way of illustration only, together with the accompanying drawings.
Drawings
Fig. 1 is a step diagram of a path planning method according to an embodiment of the present application.
Fig. 2 is a step chart of screening preferred locations according to an embodiment of the present application.
Fig. 3 is a flowchart of a neighboring node traversing operation according to an embodiment of the present application.
Fig. 4 is a flowchart of a node search according to an embodiment of the present application.
Detailed Description
Other advantages and advantages of the present application will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. For a further understanding of the present application, the present application will be described in further detail with reference to the following preferred embodiments.
The application provides a path planning method, which plans a path from a starting point to an end point according to the preference characteristics of a user path, and fully meets the personalized requirements of different players.
An aspect of the present application is a path planning method, referring to fig. 1, the method comprising the steps of:
step 1, obtaining a starting point position and an end point position;
the starting point position and the end point position are coordinate values of a starting point and an end point respectively;
step 2, acquiring a map array of the game map, and if the map array does not exist, creating the map array according to the game map;
the map array is a two-dimensional array and is used for storing game map data;
step 3, calculating the preference degree of all key positions in the estimated feasible region of the map array according to the user preference model, and screening out the preference positions;
the estimated feasible region refers to a possible path existence region from a starting point position to an end point position;
step 4, initializing a search algorithm;
and 5, searching paths to obtain planning path data.
As an embodiment, in step 2, the specific way of creating the map array includes the following steps:
step 221, obtaining a game map and determining a feasible region; the feasible area is a map area which can move freely;
step 222, converting the game map into a map array according to the game map form, wherein the specific mode is as follows:
if the game map is a grid-based map, creating a two-dimensional array and mapping the state of each grid into elements of coordinates corresponding to the two-dimensional array;
if the game data is based on polygons, converting the game map into grid areas by adopting a gridding method, and mapping each grid in the grid areas into elements of coordinates corresponding to the two-dimensional array;
step 223, marking the obstacle position and the key position in the map array.
As an embodiment, referring to fig. 2, step 3 specifically includes the following steps:
step 31, determining an estimated feasible region according to the map array, the starting point position and the end point position;
step 32, if the estimated feasible region is empty, ending the whole path planning step; if the estimated feasible region is not empty, inputting the position feature data of all the key positions in the estimated feasible region into a user preference model to obtain preference degrees of all the key positions;
the user preference model is a machine learning model for predicting user preference according to user characteristic data and position characteristic data;
and 33, screening out the key position nodes with the preference degree larger than a preset preference value as the preference positions, and setting the preference degree of the rest key positions to 0.
It can be understood that for a relatively complex game map with a huge area in the game, the estimated feasible region is determined first, and then the path planning is performed in the estimated feasible region, so that compared with the direct path planning on the whole map, the calculation resource consumption can be remarkably reduced, and the path planning efficiency is improved.
As an embodiment, the estimated feasible region in step 31 is obtained by:
step 311a, creating a node queue, a node access dictionary, a node path dictionary, a node depth dictionary and a feasible path list, and initializing;
the node queue is used for storing the nodes to be searched, and the starting point node is stored in the node queue during initialization;
the node access dictionary is used for recording access states of all nodes, and the access states of the starting point nodes are set to be accessed during initialization;
the node path dictionary is used for recording access paths from the starting point node to each node, and the access paths of the nodes are set as the starting point node itself during initialization;
the node depth dictionary is used for recording the depth level of each node, and the depth level of the initial node is set to be 0 during initialization;
the feasible path list is used for storing the feasible paths from the starting point to the end point, and is an empty list during initialization;
step 312a, if the current node queue is empty, go to step 313a; otherwise, performing the cyclic search, which specifically includes:
step 312a1, a node is taken out from the node queue, and the taken node is used as a current searching node;
step 312a2, determining a depth level of the current search node, and if the depth level exceeds a preset search depth threshold, entering step 313a; otherwise, go to step 312a3;
step 312a3, judging whether the current searching node is an end node, if so, storing the access path of the end node in a feasible path list; otherwise go to step 312a4;
step 312a4, traversing the neighbor nodes of the current search node until all neighbor nodes are traversed;
referring to fig. 3, the traversal operation is: acquiring a current neighbor node, and judging whether the neighbor node is accessed; if the neighbor node is not accessed, adding the neighbor node into a node queue, setting the access state of the neighbor node as accessed, setting the depth level of the neighbor node as the current search node depth level plus 1, and setting the access path of the neighbor node as the current search node access path plus the neighbor node; if the neighbor node is accessed, skipping the neighbor node and entering the next neighbor node;
step 313a, if the feasible path list is empty, estimating that the feasible region is empty; if the feasible paths are not empty at this time, the estimated feasible region is the region surrounded by all the feasible paths.
As an embodiment, the estimated feasible region in step 31 is obtained by:
step 311b, compressing the map array to obtain a compressed map array, and determining the positions of the start point position and the end point position in the compressed map array;
the compression mode of the map array is as follows:
compressing the map array according to a preset feature extraction step length by adopting a sliding window with a preset window size, comparing window data with a preset window template in each window, if the window data is the same as the preset window template, compressing the data in the window to be 1 (representing that a map in the window can pass), otherwise, compressing the data in the window to be 0 (representing that the map in the window can not pass);
the preset window template is a plurality of preset map block arrays with passable characteristics; the size of the preset window template is consistent with the size of the preset window;
step 312b, obtaining the shortest path from the start point to the end point in the compressed map array by using Dijkstra algorithm;
step 313b, using the areas in the preset expansion ranges at the two sides of each node in the shortest path as the feasible areas of the compressed map;
step 314b, restoring the estimated feasible region in the original map array according to the compressed map feasible region.
As an embodiment, the user preference model is obtained by:
collecting user characteristic data, position characteristic data and user preference data, and performing data processing to obtain an original data set; splitting the original data set into a training set and a testing set, and training a model by means of a machine learning algorithm based on the training set; and evaluating the model by means of the test set and adjusting the optimization model until the preset model effect is met, so that the user preference model is obtained.
The original data set consists of input data and output data, each element in the input data consists of user characteristic data and position characteristic data, and each element in the output data is preference corresponding to the input data.
For example, the ith element in the input data may be expressed as [ ]U i ,L i ) Wherein the method comprises the steps ofU i Representing a useruIs provided with a set of user characteristic data,L i representing the positionlIs provided; the ith element in the output data may be expressed asP i ,P i Representing a useruTo the positionlIs a preference degree of (2).
The preference is used for describing the preference condition of a user for a specific geographic position in the game, and the preference data of the user is obtained through the following steps:
s1, acquiring historical behavior data of a user and preprocessing the data, wherein the historical behavior data is movement track data of the user in a game process;
s2, extracting characteristics of historical behavior data of a user to obtain a user path characteristic value, wherein the path characteristic value comprises access frequency, residence time, access time period distribution, access duration distribution, path distance, position type and operation equipment;
s3, carrying out characteristic value normalization to obtain a standard path characteristic value;
s4, calculating the user preference according to the weighted summation of the standard path characteristic values, wherein the calculation mode of the user preference is as follows:
wherein mu (x,y) For preference of the (x, y) position in coordinates,w j (x,y) the weight of the eigenvalue numbered j,f j (x,y) is the value of the j-th eigenvalue of the coordinate (x, y) position.
The machine learning algorithm can be any one algorithm selected from linear regression, decision trees, random forests, support vector machines and neural networks. The above algorithms are all currently mature algorithms, and can be easily implemented by those skilled in the art based on the description of the foregoing embodiments, and are not described herein again.
As an embodiment, step 4 specifically includes the following steps:
step 41, initializing a starting node and an end node, which specifically includes:
creating a starting point node object and an ending point node object; coordinate data of a starting point node object and an ending point node object correspond to the starting point position and the ending point position; step number cost (g_cost), distance cost (h_cost) and node cost (cost) of the starting point node object and the end point node object are all set to 0; parent nodes of the starting point node object and the ending point node object are None;
and step 42, initializing an open list and a closed list, and storing the starting point node into the open list, wherein the closed list is an empty list.
It should be noted that, the data structure of the node object is composed of six attributes, namely, coordinate data, step cost, distance cost, node cost, father node, preference position and preference degree. And the starting point node object and the ending point node object both belong to node objects.
As an embodiment, step 5 specifically includes the steps of:
step 51, when the open list is not empty, selecting the node with the lowest node cost in the open list as the current confirmation node, storing the current confirmation node into the closed list, and removing the current confirmation node from the open list;
step 52, if the current confirmation node is not the destination node, performing node search on all neighbor nodes of the current confirmation node, updating the open list, and returning to step 51; if the current confirmation node is the terminal node, ending the searching path;
the node searching refers to updating node cost of the neighbor node and updating an open list according to the characteristics of the neighbor node;
step 53, creating a path list and storing the end node into the path list;
step 54, finding out a corresponding node according to the father node and storing the corresponding node into a path list until the father node backtracks to the starting point node;
and step 55, performing reverse order on the path list to obtain planning path data.
Referring to fig. 4 as an embodiment, in step 52, the node searching specifically includes:
(1) Acquiring current neighbor node data, judging whether to skip the current neighbor node, and judging the current neighbor node data by the following method: if the current neighbor node is an obstacle node or is in the existing and closed list, skipping the current neighbor node;
(2) Calculating node cost of the current neighbor node; the node cost is calculated in the following way:
the cost is the node cost of the current neighbor node, gcest is the step number cost of the current neighbor node, hcest is the distance cost of the current neighbor node, and alpha is the preference weight of the current neighbor node;
the step number cost refers to the distance between the current neighbor node and the starting point node; the distance cost refers to the distance between the current neighbor node and the destination node; the distance can be calculated by any one of Manhattan distance and Euclidean distance;
the calculation method of the preference degree weight comprises the following steps:
wherein alpha is preference weight, beta is preference of the current neighbor node, and the preference is calculated in the step 32;
(3) Updating the node cost of the current neighbor node and setting the current confirmation node as the father node of the current neighbor node;
(4) Judging whether the current neighbor node exists in the open list, and if not, storing the current neighbor node into the open list; and if the current neighbor node exists in the open list, updating the corresponding node in the open list.
As an embodiment, in addition to steps 1-5, the method further comprises:
step 6, obtaining the actual path of the user, calculating the path similarity of the actual path and the planned path, and recording the actual path data of the user and increasing the number of times of planning failure when the path similarity is smaller than a preset similarity threshold value; and calculating a planning failure ratio in a preset optimization period, and if the planning failure ratio is larger than a preset failure threshold, performing user preference model adjustment optimization.
Specifically, the method for calculating the path similarity is as follows:
selecting nodes with the same ordinate as each node in the planned path from the actual path, and calculating the standard deviation of the abscissa among all corresponding nodes, wherein the calculation formula is as follows:
wherein issThe degree of similarity of the paths is determined,p i the abscissa of the node numbered i in the actual path,q i as the abscissa of the node numbered i in the planned path,Nis the total number of nodes.
The calculation method of the planning failure ratio is the ratio of the number of planning failures to the number of planning failures.
Another aspect of the application is a path planning system comprising a data collection module, a data processing module, a model training module, a path analysis module, and a system optimization module.
The data collection module is used for collecting game map data, user characteristic data, position characteristic data and user preference data.
The data processing module is used for carrying out data cleaning and data processing on the data collected by the data collecting module, and storing the processed data into a database.
The model training module is used for training and optimizing the user preference model by means of a machine learning algorithm by using the data processed by the data processing module.
The path analysis module realizes path planning through the method of the steps 1-6.
And the system optimization module performs model optimization according to the step 7 according to the actual moving path and the planned path data of the user.
As one example, the methods of the present application may be implemented in software and/or a combination of software and hardware, e.g., using an Application Specific Integrated Circuit (ASIC), a general purpose computer, or any other similar hardware device.
The method of the present application may be implemented in the form of a software program that is executable by a processor to perform the steps or functions described above. Likewise, the software programs (including associated data structures) may be stored on a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like.
In addition, some steps or functions of the methods described herein may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.
Furthermore, parts of the methods of the present application may be applied as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide the methods and/or solutions according to the present application by way of operation of the computer. Program instructions for invoking the methods of the application may be stored in fixed or removable recording media and/or transmitted via a data stream in a broadcast or other signal bearing medium and/or stored within a working memory of a computer device operating according to the program instructions.
As an embodiment, the present application also provides an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to run a method and/or a solution according to the previous embodiments.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are alternative embodiments, and that the acts and modules referred to are not necessarily required for the present application.
Finally, it is pointed out that in the present document relational terms such as first and second, and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the scope of the application claimed.
The present application is not limited to the above-mentioned embodiments, but is intended to be limited to the following embodiments, and any modifications, equivalents and modifications can be made to the above-mentioned embodiments without departing from the scope of the application.
Claims (9)
1. A path planning method is characterized in that,
the method comprises the following steps:
step 1, obtaining a starting point position and an end point position;
step 2, acquiring a map array of the game map, and if the map array does not exist, creating the map array according to the game map;
step 3, calculating the preference degree of all key positions in the estimated feasible region of the map array according to the user preference model, and screening out the preference positions; the estimated feasible region refers to a possible path existence region from a starting point position to an end point position;
step 4, initializing a search algorithm;
step 5, searching paths to obtain planning path data;
step 6, obtaining the actual path of the user, calculating the path similarity of the actual path and the planned path, and recording the actual path data of the user and increasing the number of times of planning failure when the path similarity is smaller than a preset similarity threshold value; calculating a planning failure ratio in a preset optimization period, and if the planning failure ratio is larger than a preset failure threshold, performing user preference model adjustment optimization;
specifically, the method for calculating the path similarity is as follows:
selecting nodes with the same ordinate as each node in the planned path from the actual path, and calculating the standard deviation of the abscissa among all corresponding nodes, wherein the calculation formula is as follows:
；
wherein issThe degree of similarity of the paths is determined,p i the abscissa of the node numbered i in the actual path,q i as the abscissa of the node numbered i in the planned path,Nis the total number of nodes;
the calculation method of the planning failure ratio is the ratio of the number of planning failures to the number of planning failures;
wherein, the step 3 specifically comprises the following steps:
step 31, determining an estimated feasible region according to the map array, the starting point position and the end point position;
step 32, if the estimated feasible region is empty, ending the whole path planning step; if the estimated feasible region is not empty, inputting the position feature data of all the key positions in the estimated feasible region into a user preference model to obtain preference degrees of all the key positions;
step 33, screening out key position nodes with preference greater than a preset preference value as preference positions, and setting the preference degree of the rest key positions to be 0;
the step 5 specifically comprises the following steps:
step 51, when the open list is not empty, selecting the node with the lowest node cost in the open list as the current confirmation node, storing the current confirmation node into the closed list, and removing the current confirmation node from the open list;
step 52, if the current confirmation node is not the destination node, performing node search on all neighbor nodes of the current confirmation node, updating the open list, and returning to step 51; if the current confirmation node is the terminal node, ending the searching path;
the node searching refers to updating node cost of the neighbor node and updating an open list according to the characteristics of the neighbor node;
step 53, creating a path list and storing the end node into the path list;
step 54, finding out a corresponding node according to the father node and storing the corresponding node into a path list until the father node backtracks to the starting point node;
and step 55, performing reverse order on the path list to obtain planning path data.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises,
in step 2, the specific way of creating the map array includes the following steps:
step 221, obtaining a game map and determining a feasible region; the feasible area is a map area which can move freely;
step 222, converting the game map into a map array according to the game map form, wherein the specific mode is as follows:
if the game map is a grid-based map, creating a two-dimensional array and mapping the state of each grid into elements of coordinates corresponding to the two-dimensional array;
if the game data is based on polygons, converting the game map into grid areas by adopting a gridding method, and mapping each grid in the grid areas into elements of coordinates corresponding to the two-dimensional array;
step 223, marking the obstacle position and the key position in the map array.
3. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the user preference model is a machine learning model for predicting user preference based on user feature data and location feature data.
4. The method of claim 3, wherein the step of,
the estimated feasible region in step 31 is obtained by:
step 311a, creating a node queue, a node access dictionary, a node path dictionary, a node depth dictionary and a feasible path list, and initializing;
step 312a, if the current node queue is empty, go to step 313a; otherwise, performing the cyclic search, which specifically includes:
step 312a1, a node is taken out from the node queue, and the taken node is used as a current searching node;
step 312a2, determining a depth level of the current search node, and if the depth level exceeds a preset search depth threshold, entering step 313a; otherwise, go to step 312a3;
step 312a3, judging whether the current searching node is an end node, if so, storing the access path of the end node in a feasible path list; otherwise go to step 312a4;
step 312a4, traversing the neighbor nodes of the current search node until all neighbor nodes are traversed;
the traversing operation is as follows: if the neighbor node is not accessed, adding the neighbor node into a node queue, setting the access state of the neighbor node as accessed, setting the depth level of the neighbor node as the current search node depth level plus 1, and setting the access path of the neighbor node as the current search node access path plus the neighbor node; if the neighbor node is accessed, skipping the neighbor node and entering the next neighbor node;
step 313a, if the feasible path list is empty, estimating that the feasible region is empty; if the feasible paths are not empty at this time, the estimated feasible region is the region surrounded by all the feasible paths.
5. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the user preference model is obtained by:
collecting user characteristic data, position characteristic data and user preference data, and performing data processing to obtain an original data set; splitting the original data set into a training set and a testing set, and training a model by means of a machine learning algorithm based on the training set; evaluating the model by means of the test set and adjusting the optimization model until the preset model effect is met, so that a user preference model is obtained;
the original data set consists of input data and output data, each element in the input data consists of user characteristic data and position characteristic data, and each element in the output data is preference corresponding to the input data.
6. The method of claim 5, wherein the step of determining the position of the probe is performed,
the preference is used for describing the preference condition of a user for a specific geographic position in the game, and the preference data of the user is obtained through the following steps:
s1, acquiring historical behavior data of a user and preprocessing the data, wherein the historical behavior data is movement track data of the user in a game process;
s2, extracting characteristics of historical behavior data of a user to obtain a user path characteristic value, wherein the path characteristic value comprises access frequency, residence time, access time period distribution, access duration distribution, path distance, position type and operation equipment;
s3, carrying out characteristic value normalization to obtain a standard path characteristic value;
and S4, calculating the user preference according to the weighted summation of the standard path characteristic values.
7. The method of claim 1, wherein the step of determining the position of the substrate comprises,
step 41, initializing a starting node and an end node, which specifically includes:
creating a starting point node object and an ending point node object; coordinate data of a starting point node object and an ending point node object correspond to the starting point position and the ending point position; step number cost (g_cost), distance cost (h_cost) and node cost (cost) of the starting point node object and the end point node object are all set to 0; parent nodes of the starting point node object and the ending point node object are None;
and step 42, initializing an open list and a closed list, and storing the starting point node into the open list, wherein the closed list is an empty list.
8. The method of claim 1, wherein the step of determining the position of the substrate comprises,
in step 52, the node search specifically includes:
(1) Judging whether to skip the current neighbor node or not, wherein the judging mode is as follows: if the current neighbor node is an obstacle node or is in the existing and closed list, skipping the current neighbor node;
(2) Calculating node cost of the current neighbor node;
(3) Updating the node cost of the current neighbor node and setting the current confirmation node as the father node of the current neighbor node;
(4) Judging whether the current neighbor node exists in the open list, and if not, storing the current neighbor node into the open list; and if the current neighbor node exists in the open list, updating the corresponding node in the open list.
9. The method of claim 8, wherein the step of determining the position of the first electrode is performed,
the node cost is calculated in the following way:
；
the cost is the node cost of the current neighbor node, gcest is the step number cost of the current neighbor node, hcest is the distance cost of the current neighbor node, and alpha is the preference weight of the current neighbor node;
the step number cost refers to the distance between the current neighbor node and the starting point node; the distance cost refers to the distance between the current neighbor node and the destination node; the distance is calculated by any one of Manhattan distance and Euclidean distance;
the calculation method of the preference degree weight comprises the following steps:
；
where α is a preference weight, β is a preference of the current neighboring node, and the preference is calculated in step 32.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310785126.3A CN116492685B (en) | 2023-06-29 | 2023-06-29 | Path planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310785126.3A CN116492685B (en) | 2023-06-29 | 2023-06-29 | Path planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116492685A CN116492685A (en) | 2023-07-28 |
| CN116492685B true CN116492685B (en) | 2023-09-19 |
Family
ID=87328901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310785126.3A Active CN116492685B (en) | 2023-06-29 | 2023-06-29 | Path planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116492685B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106197449A (en) * | 2016-06-30 | 2016-12-07 | 中国科学院计算技术研究所 | A kind of map path method and system for planning based on network path selection algorithm |
| CN116077942A (en) * | 2023-04-06 | 2023-05-09 | 深圳尚米网络技术有限公司 | Method for realizing interactive content recommendation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101901958B1 (en) * | 2012-03-26 | 2018-11-08 | 한국전자통신연구원 | Apparatus for fast path search by learning heuristic function and method thereof |
-
2023
- 2023-06-29 CN CN202310785126.3A patent/CN116492685B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106197449A (en) * | 2016-06-30 | 2016-12-07 | 中国科学院计算技术研究所 | A kind of map path method and system for planning based on network path selection algorithm |
| CN116077942A (en) * | 2023-04-06 | 2023-05-09 | 深圳尚米网络技术有限公司 | Method for realizing interactive content recommendation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116492685A (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yin et al. | Joint modeling of user check-in behaviors for real-time point-of-interest recommendation | |
| CN113190699B (en) | Remote sensing image retrieval method and device based on category-level semantic hash | |
| US11341424B2 (en) | Method, apparatus and system for estimating causality among observed variables | |
| CN107247961B (en) | Track prediction method applying fuzzy track sequence | |
| CN106714110A (en) | Auto building method and system of Wi-Fi position fingerprint map | |
| CN100383812C (en) | Information processing apparatus and method, and program | |
| US20110029475A1 (en) | Taxonomy-driven lumping for sequence mining | |
| CN111008337B (en) | Deep attention rumor identification method and device based on ternary characteristics | |
| CN112101430A (en) | Anchor frame generation method for image target detection processing and lightweight target detection method | |
| CN107194434B (en) | Moving object similarity calculation method and system based on space-time data | |
| McIntosh et al. | Assessing similarity of geographic processes and events | |
| CN113077097A (en) | Air quality prediction method based on deep space-time similarity | |
| CN112365708B (en) | Scenic spot traffic volume prediction model establishing and predicting method based on multi-graph convolution network | |
| CN112214689A (en) | Method and system for maximizing influence of group in social network | |
| CN110189362B (en) | Efficient target tracking method based on multi-branch self-coding countermeasure network | |
| CN112199600A (en) | Target object identification method and device | |
| CN113110507A (en) | Path planning method for autonomous obstacle avoidance | |
| KR20220017497A (en) | Methods, devices and devices for image feature extraction and training of networks | |
| CN110990678B (en) | Trajectory similarity calculation method based on enhanced recurrent neural network | |
| CN116492685B (en) | Path planning method | |
| CN113435101A (en) | Power failure prediction method for support vector machine based on particle swarm optimization | |
| CN112633389A (en) | Method for calculating trend of hurricane motion track based on MDL and speed direction | |
| CN115691140B (en) | Analysis and prediction method for space-time distribution of automobile charging demand | |
| Etemad et al. | On feature selection and evaluation of transportation mode prediction strategies | |
| CN115062708A (en) | Abnormal node detection method based on track deviation point embedding and depth clustering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |