Method, device and server for recommending virtual object landing point

Abstract

The present invention provides a method, device and server for recommending a virtual object landing point, including: obtaining a first player type of a player and scene information of a current game scene; wherein the first player type is used to characterize the game behavior preference of the player, and the scene information at least includes an alternative landing area included in the current game scene; and determining a recommended landing area from the alternative landing areas based on the first player type. The present invention can significantly improve the game experience of players.

Description

Technical Field

[0001] The present invention relates to the field of game technology, and in particular to a method, device and server for recommending a virtual object landing point. Background Art

[0002] In tactical competitive games, the landing point (or birth point) chosen by the player will affect the player's performance during the game. For example, some players are more suitable to land in resource-rich areas, while other players may be more suitable to land in resource-scarce areas. At present, in tactical competitive games provided by relevant technologies, players can only choose landing points based on their own game experience or randomly. Since the landing point selection process is somewhat blind, the landing point may limit the player's performance, thereby affecting the player's gaming experience. Summary of the invention

[0003] In view of this, an object of the present invention is to provide a method, device and server for recommending a virtual object landing point, which can significantly improve the game experience of players.

[0004] In a first aspect, an embodiment of the present invention provides a method for recommending a landing point of a virtual object, comprising: obtaining a first player type of a player and scene information of a current game scene; wherein the first player type is used to characterize the game behavior preference of the player, and the scene information at least includes alternative landing areas contained in the current game scene; and determining a recommended landing area from the alternative landing areas based on the first player type.

[0005] In one embodiment, the step of determining a recommended landing area from the alternative landing areas based on the first player type includes: based on the scene information, determining historical landing areas that match each of the alternative landing areas from historical game scenes; wherein each of the historical landing areas corresponds to historical performance data when the player selects the historical landing area; based on the first player type and the historical performance data corresponding to each of the historical landing areas, determining a recommended landing area from the alternative landing areas.

[0006] In one embodiment, the method includes: determining a recommended landing point for the virtual object from candidate landing points included in the recommended landing point area.

[0007] In one embodiment, before the step of obtaining the player's first player type and scene information of the current game scene, the method further includes: obtaining the player's historical game data; wherein the historical game data at least includes historical behavior data and historical record data; preprocessing the historical game data to obtain target feature values; wherein the preprocessing includes normalization processing and dimensionality reduction processing; clustering the target feature values ​​to determine the player's first player type.

[0008] In one embodiment, before the step of obtaining the player's first player type and scene information of the current game scene, the method further includes: obtaining a contact list of the player, and determining the player's first player type based on the second player type of each contact in the contact list.

[0009] In one embodiment, the step of determining historical landing areas that match each of the alternative landing areas from the historical game scenes based on the scene information includes: determining the historical game scene based on the scene type of the current game scene; calculating the similarity between each of the alternative landing areas and each historical landing area contained in the historical game scene; and determining the historical landing areas that match each of the alternative landing areas based on the similarity.

[0010] In one embodiment, the step of calculating the similarity between each of the alternative landing areas and each of the historical landing areas contained in the historical game scene includes: for each of the alternative landing areas, searching for coordinate points that match the alternative landing points contained in each of the historical landing areas contained in the historical game scene; obtaining the maximum distance of each of the historical landing areas; wherein the maximum distance is used to characterize the maximum distance between the historical landing points contained in the historical landing areas; based on the maximum distance of each of the historical landing areas, the alternative landing points contained in the alternative landing area, and the coordinate points that match the alternative landing points contained in the alternative landing area, determining the similarity between the alternative landing area and each of the historical landing areas.

[0011] In one embodiment, the step of searching, for each of the alternative landing areas, in each historical landing area contained in the historical game scene, for coordinate points that match the alternative landing points contained in the alternative landing area, comprises: determining, based on a pre-established virtual coordinate axis, first coordinate values ​​corresponding to each point in the alternative landing area, and determining second coordinate values ​​corresponding to each point in each historical landing area contained in the historical game scene; searching, in each of the historical landing areas, for coordinate points that match the alternative landing points contained in the alternative landing area, based on the first coordinate values ​​and the second coordinate values ​​using a propensity value matching algorithm.

[0012] In one embodiment, the step of determining the similarity of the alternative landing area with each of the historical landing areas based on the maximum distance of each of the historical landing areas, the alternative landing points contained in the alternative landing area, and the coordinate points that match the alternative landing points contained in the alternative landing area includes: for each alternative landing point contained in the alternative landing area, calculating the distance difference between the alternative landing point and the coordinate point that matches the alternative landing point; calculating the sum of the distance differences to obtain the sum of the distance differences; and calculating the ratio of the sum of the distance differences to the maximum distance of each of the historical landing areas to obtain the similarity of the alternative landing area with each of the historical landing areas.

[0013] In one embodiment, the step of determining the historical landing areas that match each of the alternative landing areas based on the similarity includes: judging whether the similarity between the historical landing area and the alternative landing area is greater than a preset threshold; if so, determining that the historical landing area matches the alternative landing area; if not, obtaining the area information of the alternative landing area; wherein the area information includes resource distribution information, sub-area distribution information, and distance information between each alternative landing point and the center point of the alternative landing area; clustering the historical landing areas based on the area information to obtain clustering results, and determining the historical landing area that matches the alternative landing area based on the clustering results.

[0014] In one embodiment, the step of determining a recommended landing area from the alternative landing areas based on the historical record data corresponding to the first player type and each of the historical landing areas includes: for each alternative landing area, estimating the first record probability when the player selects the alternative landing area based on the historical record data corresponding to the historical landing areas matching the first player type and the alternative landing area; and determining the recommended landing area according to the first record probability corresponding to each alternative landing area.

[0015] In one embodiment, the step of estimating the performance probability of the player selecting the alternative landing area based on the historical performance data corresponding to the historical landing area that matches the first player type and the alternative landing area includes: obtaining a third player type of the hostile player; based on the first player type and the third player type, filtering target performance data from the historical performance data corresponding to the historical landing area that matches the alternative landing area; and obtaining the performance probability of the player selecting the alternative landing area by counting the target performance data.

[0016] In one embodiment, the method further includes: searching for a target game match from the player's historical game matches according to the current game scene; based on the player's historical record data, separately counting the second record probability when the player selects each historical landing point in the historical game scene in the target game; and determining a recommended landing point for a virtual object from the alternative landing points in the current game scene according to the second record probability corresponding to each of the historical landing points.

[0017] In one embodiment, the method further includes: sending the recommended landing point and the second record probability corresponding to the recommended landing point to the player's terminal device, so as to display the second record probability corresponding to the recommended landing point through a graphical user interface provided by the terminal device.

[0018] In a second aspect, an embodiment of the present invention further provides a device for recommending a landing point of a virtual object, comprising: an acquisition module for acquiring a first player type of a player and scene information of a current game scene; wherein the first player type is used to characterize the game behavior preference of the player, and the scene information at least includes the alternative landing areas contained in the current game scene; a landing area determination module for determining a recommended landing area from the alternative landing areas based on the first player type.

[0019] In a third aspect, an embodiment of the present invention further provides a server, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement any one of the methods provided in the first aspect.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0021] The embodiments of the present invention provide a method, device and server for recommending a landing point of a virtual object. The method first obtains the first player type used to characterize the player's gaming behavior preference and the scene information of the current game scene (at least including the candidate landing areas included in the current game scene), and then determines the recommended landing area from the candidate landing areas based on the first player type. The above method can determine the recommended landing area for the player from the candidate landing areas included in the current game scene according to the player's first player type, thereby recommending a recommended landing area that is more suitable for the player's first player type. When the player controls the virtual character to land in the recommended landing area, it will be more conducive to the player to give full play to his strengths, thereby obtaining a better gaming experience.

[0022] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0023] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A flowchart of a method for recommending a virtual object landing point provided by an embodiment of the present invention;

[0026] Figure 2 A schematic diagram of a flow chart of another method for recommending a virtual object landing point provided by an embodiment of the present invention;

[0027] Figure 3 A schematic diagram of the structure of a device for recommending a virtual object landing point provided by an embodiment of the present invention;

[0028] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described in combination with the embodiments below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] At present, when players play tactical competitive games (such as chicken games), they usually choose landing points based on subjective ideas and random thoughts. Players cannot know how to choose a landing point to improve their winning rate. Blindly choosing a landing point may not be conducive to the player's performance, thereby affecting the player's gaming experience. Based on this, the present invention provides a method, device and server for recommending the landing point of a virtual object, which can significantly improve the player's gaming experience.

[0031] To facilitate understanding of this embodiment, a method for recommending a virtual object landing point disclosed in an embodiment of the present invention is first described in detail. This method can be applied to online games that involve selecting a birth place / landing place / teleportation place in a large map. The landing point may include a birth place, a landing place, a teleportation place, etc., including but not limited to a chicken-eating PC game or mobile game, see Figure 1 The flowchart of a method for recommending a virtual object landing point is shown in FIG. 1 , and the method mainly includes the following steps S102 to S104:

[0032] Step S102, obtain the first player type of the player and the scene information of the current game scene. Among them, the first player type is used to characterize the game behavior preference of the player. Exemplarily, the player type can be a snatch type, a wild type, a killing type or other types. The scene information at least includes the alternative landing area contained in the current game scene. The alternative landing area can be understood as the area that can be selected to land in the current game scene in this game match. The first information scene can also include the scene identification of the current game scene, such as a scene ID (Identity document, unique code), etc. In practical applications, the game scene can be divided into multiple areas, and the game scene used in each game match may be different, or the game scene used is the same but the alternative landing area is different. For example, a game scene is divided into area 1, area 2, area 3, and area 4. In one game match, the game scene is used, and the alternative landing area is area 1 and area 2 (that is, the player can only land in area 1 or area 2), and in another game match, the game scene is also used, and the alternative landing area is area 3 and area 4. In one implementation, the first player type of the player and scene information of the current game scene may be acquired during the game preparation phase.

[0033] Step S104, determining a recommended landing area from the candidate landing areas based on the first player type.

[0034] In one embodiment, a recommended landing area can be determined from the alternative landing areas in combination with the first player type, the current game scene, and the historical game scene. Specifically, historical landing areas that match each alternative landing area in the current game scene can be determined from the historical game scenes, and each historical landing area corresponds to historical performance data when the player selects the historical landing area. The recommended landing area is determined from the alternative landing areas based on the first player type and the historical performance data corresponding to each historical landing area, wherein the historical game scene can be understood as a game scene that the player has experienced in previous game matches, and the game scene has the same scene type as the current game scene, and the historical performance data may include the game score and / or score probability when the player selects the historical landing area.

[0035] In another embodiment, the historical record data corresponding to the players' selection of each landing area in a certain game scene is statistically processed, such as calculating the average record when the player selects each landing area, so as to pre-establish the correspondence between the first player type, the game scene, and the landing area according to the average record. In the current game, the first player type and the current game scene are directly used as search conditions to select the recommended landing area in the above correspondence. For example, a certain game scene is divided into area 1, area 2, area 3, and area 4. It is statistically determined that the average record when the player selects each landing area is in the order of area 3, area 4, area 1, and area 2 from high to low. Then the corresponding relationship can be determined as follows: in this game scene, the first player type corresponds to area 3, and area 3 is recommended to the player as the recommended landing area.

[0036] The above-mentioned method for recommending the landing point of a virtual character provided in an embodiment of the present invention can determine a recommended landing area for the player from the alternative landing areas included in the current game scene according to the player's first player type, thereby recommending a recommended landing area that is more suitable for the player's first player type. When the player controls the virtual character to land in the recommended landing area, it will be more conducive to the player's strengths, thereby obtaining a better gaming experience.

[0037] To facilitate understanding of the aforementioned player types, the embodiment of the present invention provides the following method for determining the first player type of a player:

[0038] Method 1: Determine the first player type based on historical game data, as shown in (1) to (3) below:

[0039] (1) Obtaining the player's historical game data. The historical game data includes at least historical behavior data and historical record data. The historical behavior data may include the number of kills, assists, blocks, etc. The historical record data may include the number of single-row games, the number of multi-row games, the number of wins, the top ten games, melee weapon damage, ranged weapon damage, etc. In one embodiment, to obtain the first player type of the player, the player's game log may be obtained, and the player's behavior, record, or other field information that is strongly related to the player type in each game may be extracted from the game log to obtain the historical game data.

[0040] (2) Preprocess the historical game data to obtain the target eigenvalue. Preprocessing includes normalization and dimensionality reduction. Normalization can include dimensionality standardization, unique hot encoding, etc. Dimensionality reduction can use PCA (Principal Component Analysis) etc. In practical applications, dimensionality standardization can be used to process continuous variables in historical game data. Dimensionality standardization can use min-max normalization method. Specifically, the maximum value max and minimum value min of the feature x in the continuous variable are determined, and then each eigenvalue is calculated according to the following formula to obtain the initial eigenvalue x* in the interval [0-1]:

[0041] In addition, the discrete variables in the historical game data can also be processed by one-hot encoding, and all the eigenvalues ​​of the feature x can be represented by one or more 0s and 1s. For example, the feature "killing weapon" has eigenvalues ​​"stick", "gun", and "bomb". The initial eigenvalues ​​"X1", "X2", and "X3" can be generated by one-hot encoding, where "stick" corresponds to 001, "gun" corresponds to 010, and "bomb" corresponds to 100.

[0042] Considering that too many dimensions of historical game data will affect computing efficiency, the embodiment of the present invention can use dimensionality reduction processing to process the above-mentioned initial eigenvalues, thereby reducing the number of features of the initial eigenvalues, and achieving the effects of noise reduction, alleviating dimensionality disaster, etc., to obtain target eigenvalues ​​that are convenient for subsequent calculations.

[0043] (3) Clustering the target feature values ​​to determine the first player type of the player. The cluster analysis may use algorithms such as K-means (K-means clustering algorithm) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise). In one embodiment, the target feature values ​​may be divided into different clusters, and the average kill value, the value of robbing other players' props, the average running distance, etc. of the player may be determined through clustering. For example, assuming that the average kill value of the player is higher than the first threshold, the average value of robbing other players' props is higher than the second threshold, and the average running distance is higher than the third threshold, it is auxiliary to determine that the player belongs to the robbing type player.

[0044] Method 2: Determine the first player type based on the player's contact list. Specifically, obtain the player's contact list, and determine the player's first player type based on the second player type of each contact in the contact list. In actual applications, for newly added players, since they have not yet played the game, it is impossible to obtain the player's historical game data. At this time, the player's contact list can be obtained. The contact list may contain the game ID of the player's sponsor or friend, so that the historical game data of each contact can be found based on the game ID, and the second player type of the contact can be determined based on the above method 1, and the first player type of the player can be inferred based on this. For example, if 80% of the player's contacts are snatch-type players, it can be inferred that the player is also a snatch-type player. In addition, since it is impossible to obtain the historical game map of the newly added player, a cold start method can be used.

[0045] For the aforementioned step S104, the embodiment of the present invention further provides an implementation method for determining a recommended landing area from candidate landing areas based on the first player type, see the following steps I to II:

[0046] Step I, based on the scene information, determine the historical landing areas that match each alternative landing area from the historical game scenes. For example, when a snatch-type player selects historical landing area n1, the probability that the game score is in the top ten is 50%, and when the historical landing area n2 is selected, the probability that the game score is in the top ten is 40%; when a wild player selects historical landing area n1, the probability that the game score is in the top ten is 40%, and when the historical landing area n2 is selected, the probability that the game score is in the top ten is 50%. In one embodiment, the historical game scenes of the same scene type can be determined based on the scene identifier of the current game scene, and then the similarity between the landing areas contained in the historical game scenes and the alternative landing areas contained in the current game scene is calculated, so as to determine the historical landing areas corresponding to each alternative landing area based on the similarity.

[0047] Step II, based on the historical record data corresponding to the first player type and each historical landing area, determine the recommended landing area from the alternative landing area. In one embodiment, the record probability of the user selecting each alternative landing area can be estimated based on the historical record data corresponding to the first player type and each historical landing area, so as to select the recommended landing area for the player from the alternative landing area and based on the high and low probability of the record. Exemplarily, assuming that the first player type is a grabbing player, the alternative landing area m1 corresponds to the historical landing area n1, and the alternative landing area m2 corresponds to the historical landing area n2, then it is necessary to combine the historical record data of the historical landing area n1 and the first player type (grabbing type) to determine the record probability when the player selects the alternative landing area m1 (for example, the probability of the top ten is 50%), and similarly determine the record probability when the player selects the alternative landing area m2 (for example, the probability of the top ten is 40%), and the alternative landing area with a higher record probability can be determined as the recommended landing area.

[0048] Considering that the game scene selected by the player in each round and the alternative landing areas provided by the game scene are uncertain, the embodiment of the present invention uses image recognition to determine similar game scenes that the player has played before, wherein the similar game scene actually refers to a game scene that is the same as the current game scene and has a similar alternative landing area. Specifically, for the aforementioned step I, the embodiment of the present invention provides an implementation method for determining historical landing areas that match each alternative landing area from historical game scenes, which can be seen in the following steps 1 to 3:

[0049] Step 1: Determine the historical game scene based on the scene type of the current game scene. In one embodiment, the scene type can be distinguished by the scene ID in the game log. For example, game scenes with the same scene ID belong to the same scene type. Specifically, the game scenes that the player has played before and have the same scene ID as the current game scene are determined as historical game scenes.

[0050] Step 2, calculating the similarity between each candidate landing area and each historical landing area included in the historical game scene. In one embodiment, the similarity between the candidate landing area and the historical landing area can be determined according to the following steps 2.1 to 2.3:

[0051] Step 2.1, for each candidate landing area, search for coordinate points that match the candidate landing points contained in the candidate landing area in each historical landing area contained in the historical game scene. In one embodiment, a PSM (Propensity Score Matching) algorithm can be used to search for coordinate points that match the candidate landing points contained in the candidate landing area. For ease of understanding, see the following steps a1 to a2:

[0052] Step a1, based on the pre-established virtual coordinate axis, respectively determine the first coordinate value corresponding to each point in the alternative landing area, and determine the second coordinate value corresponding to each point in each historical landing area contained in the historical game scene. Different from the traditional image recognition model importing pixel data, the embodiment of the present invention imports data as the coordinates (X, Y) of the game scene, defines the center coordinates (X0, Y0) of the game scene as (0, 0), and establishes a virtual coordinate axis with this as the origin. The virtual coordinate axis is a two-dimensional coordinate axis, so as to determine the coordinate value of each landing point in the game scene based on the virtual coordinate axis, that is, determine the first coordinate value corresponding to each alternative landing point in the alternative landing area, and determine the second coordinate value corresponding to each point in the historical landing area. The first coordinate value and the second coordinate value can be used for subsequent tendency matching analysis.

[0053] Step a2, using the propensity score matching algorithm based on the first coordinate value and the second coordinate value, in each historical landing area, search for coordinate points that match the alternative landing points contained in the alternative landing area. Assuming that the alternative landing area is α and the historical landing area is β, the PSM algorithm is used to search for the coordinate points closest to each alternative landing point in the alternative landing area α in the historical landing area β. In practical applications, the propensity score is a function of multiple covariates, which is used to deal with the problem of uneven distribution of covariates between groups in observational experiments, that is, the coordinate points in the alternative landing area α (which can be called the experimental group) and the historical landing area β (which can be called the control group) are not well randomly selected. The embodiment of the present invention uses the PSM algorithm to find the closest coordinate point in the historical landing area β for each alternative landing point in the alternative landing area α.

[0054] Step 2.2, obtain the maximum distance of each historical landing area. The maximum distance is used to characterize the maximum distance between the historical landing points contained in the historical landing area. For example, the historical landing area includes historical landing point 1, historical landing point 2, and historical landing point 3, among which the distance between historical landing point 1 and historical landing point 2 is the farthest, then the distance between historical landing point 1 and historical landing point 2 is the above maximum distance, and the maximum distance is recorded as DMax.

[0055] Step 2.3, based on the maximum distance of each historical landing area, the candidate landing points included in the candidate landing area, and the coordinate points that match the candidate landing points included in the candidate landing area, determine the similarity between the candidate landing area and each historical landing area. In one embodiment, the similarity between the candidate landing area and each historical landing area can be determined according to the following steps b1 to b3:

[0056] Step b1: for each candidate landing point included in the candidate landing area, calculate the distance difference between the candidate landing point and the coordinate point that matches the candidate landing point. For example, assuming that the candidate landing point (Xi, Yi) corresponds to the coordinate point (Xj, Yj), calculate the distance difference between the two and get Thus, the distance difference between each candidate landing point and its matching coordinate point is obtained.

[0057] Step b2, calculating the sum of the distance differences to obtain the sum of the distance differences. ij As shown below:

[0058] Step b3, respectively calculate the ratio of the sum of the distance differences to the maximum distance of each historical landing area, and obtain the similarity between the candidate landing area and each historical landing area. In one embodiment, the similarity Sim can be calculated according to the following formula: ij :

[0059] Step 3, determine the historical landing areas that match each alternative landing area based on similarity. Taking into account that in some cases, even if the similarity between the alternative landing area and the historical landing area is low, considering that the proportion of resource-rich locations P, the proportion of wild locations Q, and the distance R of each landing point from the center of the game scene are relatively close, the alternative landing area and the historical landing area can also be identified as similar. Based on this, after performing the above-mentioned image analysis, cluster analysis can be performed on the alternative landing areas and historical landing areas with low similarity to determine the historical landing areas that match the alternative landing areas again. Specifically, an embodiment of the present invention provides an implementation method for determining historical landing areas that match each alternative landing area based on similarity, see the following steps c1 to c4:

[0060] Step c1, determine whether the similarity between the historical landing area and the candidate landing area is greater than a preset threshold. If yes, execute step c2; if not, execute step c3.

[0061] Step c2, determining whether the historical landing area matches the candidate landing area. For example, when the similarity between the historical landing area n1 and the candidate landing area m1 is greater than a preset threshold (eg, 0.8), it can be directly determined that the candidate landing area m1 matches the historical landing area n1.

[0062] Step c3, obtaining the regional information of the candidate landing area. The regional information includes resource distribution information, sub-region distribution information, and distance information between each candidate landing point and the center point of the candidate landing area. The resource distribution information is the above-mentioned resource-rich location ratio P, the sub-region distribution information is the above-mentioned wild location ratio Q, and the distance information between each candidate landing point and the center point of the candidate landing area is the distance R between each landing point and the center of the game scene.

[0063] Step c4, cluster the historical landing areas based on the regional information to obtain clustering results, and determine the historical landing areas that match the candidate landing areas based on the clustering results. In one embodiment, the embodiment of the present invention assigns three dimensions (including the above-mentioned resource-rich location ratio P, and the sub-region distribution information is the above-mentioned wild location ratio Q) to each candidate landing area, and uses clustering algorithms such as Kmeans. In addition, the inflection point method or the contour method can also be used to determine the number of clustering categories K, thereby obtaining the range of the three dimensions of P, Q, and R of the candidate landing areas in the K categories, and then performing a second similarity judgment on the historical landing areas with low similarity.

[0064] To facilitate understanding of the aforementioned step II, the embodiment of the present invention further provides an implementation method for determining a recommended landing area from candidate landing areas based on the historical performance data corresponding to the first player type and each historical landing area, see the following steps (i) to (ii):

[0065] Step (a), for each alternative landing area, based on the historical record data corresponding to the first player type and the historical landing area that matches the alternative landing area, estimate the probability of the first record when the player selects the alternative landing area. In specific implementation, (1) obtain the third player type of the hostile player; (2) based on the first player type and the third player type, filter the target record data from the historical record data corresponding to the historical landing area that matches the alternative landing area; (3) count the target record data to obtain the record probability when the player selects the alternative landing area. Assuming that the first player type is B1, the proportion of players with the third player type of B1 is less than 50% of all players, use this as the search condition to search in the historical record data corresponding to the historical landing area that matches the alternative landing area, and obtain the probability of the player getting the top 10 when selecting the alternative landing area m1, the probability of getting the top 10 when selecting the alternative landing area m2, etc.

[0066] Step (ii), determining a recommended landing area according to the first performance probability corresponding to each candidate landing area. In one embodiment, the candidate landing area with the highest first performance probability can be determined as the recommended landing area.

[0067] In an optional implementation, the recommended landing point of the virtual object is also determined from the candidate landing points included in the recommended landing point area. For example, one or more candidate landing points in the recommended landing point area can be recommended to the player, so that the player can choose whether to control the virtual object to land according to the recommended landing point.

[0068] In another optional implementation, the recommended drop point may be determined for the player based on the player's historical performance data. In one implementation, see (a) to (c) below:

[0069] (a) Searching for a target game match from the player's historical game matches according to the current game scenario. In one embodiment, a historical game scenario similar to the current game scenario may be searched in the historical game matches, and the historical game match using the historical game scenario is determined as the target game match.

[0070] (b) Based on the player's historical record data, the second record probability of the player selecting each historical landing point in the historical game scene in the target game is calculated. Assume that the statistics show that the probability of the player getting the top 10 when selecting historical landing point t1 is 60%, and the probability of getting the top 10 when selecting historical landing point t2 is 60%.

[0071] (c) Determine a recommended landing point for the virtual object from the candidate landing points in the current game scene according to the second battle record probability corresponding to each historical landing point. In one embodiment, the historical landing point with the highest second battle record probability can be used as the recommended landing point.

[0072] In addition, the embodiment of the present invention can also send the second record probability corresponding to the above-mentioned recommended landing point to the player, so that the player can choose whether to choose the recommended landing point for landing. Specifically, the recommended landing point and the second record probability corresponding to the recommended landing point can be sent to the player's terminal device to display the second record probability corresponding to the recommended landing point through the graphical user interface provided by the terminal device. For example, based on the historical record data of this type of player, the graphical user interface displays "the probability of similar players choosing this landing point to enter the top ten is 70%."

[0073] In tactical competitive games, choosing a landing point is very important. In a certain map or an optional landing area, different types of players often have a landing point that allows them to best perform. The choice of a landing point can determine whether the player can enter the top ten in this game. For example, grabbing players may be more suitable for landing in resource-rich areas, players who tend to develop in the wild may have better performance in areas with sparse resources, and players who do not pursue rankings but only want to kill may be most suitable for areas with dense players. However, since players cannot know or cannot clearly know the resources and player density in the game scene, they cannot know which landing point to choose under the game scene, landing area, and teammate combination to increase the probability of winning, resulting in the inability to independently choose a landing point that is more conducive to performance. Therefore, this solution can recommend landing points to players in advance during the game preparation stage, which helps players to perform more comfortably and experience higher game fun, thereby achieving the effect of improving player retention.

[0074] The embodiment of the present invention provides an application example of a method for recommending a virtual object landing point. Figure 2 The flowchart of another method for recommending a virtual object landing point is shown in FIG. 1 , and the method mainly includes the following steps S202 to S208:

[0075] Step S202, obtaining a game log of the player, and determining a first player type of the player based on the game log.

[0076] Step S204, performing image recognition on the game map to determine the similarity between the candidate landing area in the current game scene and the historical landing area.

[0077] Step S206, determining a recommended drop point based on the first player type, the third player type of the opponent player, and the similarity.

[0078] Step S208, displaying the recommended landing point and the second battle record probability corresponding to the recommended landing point through the graphical user interface.

[0079] In summary, the embodiment of the present invention provides a method for recommending the landing point of a virtual object based on image recognition and similarity analysis. The embodiment of the present invention can provide a mechanism for recommending the birth point for players in tactical competitive games (such as online games like Chicken). It can also determine the recommended landing point by analyzing the alternative landing areas provided by the game, the player's historical behavior and record, so that the player can realize the game start method that he is good at, thereby improving the player's game experience and having a positive impact on the retention and payment of the game.

[0080] For the method for recommending a virtual object landing point provided in the above embodiment, the present invention provides a device for recommending a virtual object landing point, see Figure 3The schematic diagram of the structure of a device for recommending a virtual object landing point is shown in FIG. 1 , and the device mainly includes the following parts:

[0081] The acquisition module 302 is used to acquire the first player type of the player and the scene information of the current game scene; wherein the first player type is used to characterize the game behavior preference of the player, and the scene information at least includes the candidate landing area included in the current game scene;

[0082] The landing area determination module 304 is used to determine a recommended landing area from the candidate landing areas based on the first player type.

[0083] The device for recommending a virtual character's landing point provided in an embodiment of the present invention can determine a recommended landing area for the player from the alternative landing areas included in the current game scene according to the player's first player type, thereby recommending a recommended landing area that is more suitable for the player's first player type. When the player controls the virtual character to land in the recommended landing area, it will be more conducive to the player's strengths, thereby obtaining a better gaming experience.

[0084] In one embodiment, the landing area determination module 304 is also used to: based on the scene information, determine historical landing areas that match each of the alternative landing areas from the historical game scenes; wherein each of the historical landing areas corresponds to historical performance data when the player selects the historical landing area; based on the first player type and the historical performance data corresponding to each of the historical landing areas, determine a recommended landing area from the alternative landing areas.

[0085] In one embodiment, the above-mentioned device also includes a first landing point recommendation module, which is used to: determine a recommended landing point for the virtual object from the candidate landing points included in the recommended landing point area.

[0086] In one embodiment, the acquisition module 302 is also used to: obtain the player's historical game data; wherein the historical game data at least includes historical behavior data and historical performance data; pre-process the historical game data to obtain target feature values; wherein the pre-processing includes normalization processing and dimensionality reduction processing; cluster the target feature values ​​to determine the player's first player type.

[0087] In one implementation, the acquisition module 302 is further configured to: acquire a contact list of the player, and determine the first player type of the player based on the second player type of each contact in the contact list.

[0088] In one embodiment, the landing area determination module 304 is also used to: determine the historical game scene based on the scene type of the current game scene; calculate the similarity between each alternative landing area and each historical landing area contained in the historical game scene; and determine the historical landing area that matches each alternative landing area based on the similarity.

[0089] In one embodiment, the landing area determination module 304 is also used to: for each alternative landing area, search for coordinate points that match the alternative landing points contained in each historical landing area contained in the historical game scene; obtain the maximum distance of each historical landing area; wherein the maximum distance is used to characterize the maximum distance between the historical landing points contained in the historical landing area; based on the maximum distance of each historical landing area, the alternative landing points contained in the alternative landing area and the coordinate points that match the alternative landing points contained in the alternative landing area, determine the similarity between the alternative landing area and each historical landing area.

[0090] In one embodiment, the landing area determination module 304 is also used to: determine the first coordinate value corresponding to each point in the alternative landing area based on a pre-established virtual coordinate axis, and determine the second coordinate value corresponding to each point in each historical landing area contained in the historical game scene; use the tendency value matching algorithm based on the first coordinate value and the second coordinate value to search for coordinate points that match the alternative landing points contained in the alternative landing area in each historical landing area.

[0091] In one embodiment, the landing area determination module 304 is also used to: for each alternative landing point included in the alternative landing area, calculate the distance difference between the alternative landing point and the coordinate point that matches the alternative landing point; calculate the sum of the distance differences to obtain the sum of the distance differences; calculate the ratio of the sum of the distance differences to the maximum distance of each historical landing area, and obtain the similarity between the alternative landing area and each historical landing area.

[0092] In one embodiment, the landing area determination module 304 is also used to: determine whether the similarity between the historical landing area and the alternative landing area is greater than a preset threshold; if so, determine that the historical landing area matches the alternative landing area; if not, obtain the area information of the alternative landing area; wherein the area information includes resource distribution information, sub-area distribution information, and distance information between each alternative landing point and the center point of the alternative landing area; cluster the historical landing areas based on the area information to obtain clustering results, and determine the historical landing area that matches the alternative landing area based on the clustering results.

[0093] In one embodiment, the landing area determination module 304 is also used to: for each alternative landing area, estimate the first record probability when the player selects the alternative landing area based on the historical record data corresponding to the historical landing area that matches the first player type and the alternative landing area; determine the recommended landing area according to the first record probability corresponding to each alternative landing area.

[0094] In one embodiment, the landing area determination module 304 is also used to: obtain a third player type of the hostile player; based on the first player type and the third player type, filter target performance data from the historical performance data corresponding to the historical landing area that matches the alternative landing area; and statistically analyze the target performance data to obtain the performance probability when the player selects the alternative landing area.

[0095] In one embodiment, the above-mentioned device also includes a second landing point recommendation module, which is used to: search for a target game match from the player's historical game matches according to the current game scene; based on the player's historical record data, separately count the second record probability when the player selects each historical landing point in the historical game scene in the target game; and determine the recommended landing point of the virtual object from the alternative landing points in the current game scene according to the second record probability corresponding to each historical landing point.

[0096] In one embodiment, the sending module is used to send the recommended landing point and the second record probability corresponding to the recommended landing point to the player's terminal device, so as to display the second record probability corresponding to the recommended landing point through a graphical user interface provided by the terminal device.

[0097] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0098] An embodiment of the present invention provides a server. Specifically, the server includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0099] Figure 4 A structural diagram of a server provided in an embodiment of the present invention, the server 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0100] The memory 41 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 43 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0101] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0102] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0103] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 40. The above processor 40 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor to execute, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0104] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be referred to the previous method embodiments, which will not be repeated here.

[0105] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0106] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for recommending a virtual object landing point, characterized in that: include: Acquire a first player type of the player and scene information of a current game scene; wherein the first player type is used to characterize the game behavior preference of the player, and the scene information at least includes an alternative landing area included in the current game scene; determining a recommended landing area from the candidate landing areas based on the first player type; The first player type is determined by: Method 1: obtaining the historical game data of the player; wherein the historical game data at least includes historical behavior data and historical performance data; preprocessing the historical game data to obtain a target feature value; wherein the preprocessing includes normalization processing and dimensionality reduction processing; clustering processing is performed on the target feature value to determine the first player type of the player; Method 2: obtaining a contact list of the player, and determining the first player type of the player based on the second player type of each contact in the contact list; The step of determining a recommended landing area from the candidate landing areas based on the first player type includes: determining, from the historical game scenes, historical landing areas that match each of the candidate landing areas based on the scene information; wherein each of the historical landing areas corresponds to historical battle record data when the player selects the historical landing area; determining a recommended landing area from the candidate landing areas based on the first player type and the historical battle record data corresponding to each of the historical landing areas; The step of determining, from the historical game scenes, historical landing areas that match each of the alternative landing areas respectively based on the scene information, comprises: determining the historical game scene based on the scene type of the current game scene; calculating the similarity between each of the alternative landing areas and each historical landing area contained in the historical game scene; and determining the historical landing areas that match each of the alternative landing areas respectively based on the similarity.

2. The method according to claim 1, characterized in that The method comprises: A recommended landing point of the virtual object is determined from the candidate landing points included in the recommended landing point area.

3. The method according to claim 1, characterized in that The step of calculating the similarity between each candidate landing area and each historical landing area included in the historical game scene includes: For each candidate landing area, searching for a coordinate point matching the candidate landing point contained in each historical landing area contained in the historical game scene; Obtaining the maximum distance of each of the historical landing areas; wherein the maximum distance is used to characterize the maximum distance between the historical landing points contained in the historical landing area; Based on the maximum distance of each of the historical landing areas, the candidate landing points included in the candidate landing area and the coordinate points that match the candidate landing points included in the candidate landing area, the similarity between the candidate landing area and each of the historical landing areas is determined.

4. The method according to claim 3, characterized in that The step of searching, for each candidate landing area, in each historical landing area contained in the historical game scene, for a coordinate point matching the candidate landing point contained in the candidate landing area comprises: Based on a pre-established virtual coordinate axis, respectively determine a first coordinate value corresponding to each point in the candidate landing area, and determine a second coordinate value corresponding to each point in each historical landing area included in the historical game scene; Using a propensity value matching algorithm based on the first coordinate value and the second coordinate value, in each of the historical landing areas, a coordinate point matching the candidate landing point included in the candidate landing area is searched.

5. The method according to claim 3, characterized in that: The step of determining the similarity between the candidate landing area and each of the historical landing areas based on the maximum distance of each of the historical landing areas, the candidate landing points included in the candidate landing area, and the coordinate points matching the candidate landing points included in the candidate landing area, comprises: For each candidate landing point included in the candidate landing area, calculate the distance difference between the candidate landing point and the coordinate point that matches the candidate landing point; Calculate the sum of the distance differences to obtain the sum of the distance differences; The ratio of the sum of the distance differences to the maximum distance of each of the historical landing areas is calculated respectively to obtain the similarity between the candidate landing area and each of the historical landing areas.

6. The method according to claim 1, characterized in that The step of determining the historical landing areas that match each of the candidate landing areas based on the similarity comprises: Determine whether the similarity between the historical landing area and the candidate landing area is greater than a preset threshold; If yes, determining that the historical landing area matches the candidate landing area; If not, obtain the area information of the candidate landing area; wherein the area information includes resource distribution information, sub-area distribution information, and distance information between each candidate landing point and the center point of the candidate landing area; The historical landing areas are clustered based on the area information to obtain a clustering result, and a historical landing area matching the candidate landing area is determined according to the clustering result.

7. The method according to claim 1, characterized in that The step of determining a recommended landing area from the candidate landing areas based on the first player type and the historical battle record data corresponding to each of the historical landing areas comprises: For each candidate landing area, based on the historical battle record data corresponding to the historical landing area matching the first player type and the candidate landing area, estimate the first battle record probability when the player selects the candidate landing area; The recommended landing area is determined based on the first battle record probability corresponding to each alternative landing area.

8. The method according to claim 7, characterized in that The step of estimating the probability of the player's performance when selecting the alternative landing area based on the historical performance data corresponding to the historical landing area matching the first player type and the alternative landing area comprises: Get the third player type of the hostile player; Based on the first player type and the third player type, selecting target performance data from historical performance data corresponding to historical landing areas matched by candidate landing areas; The target battle record data is counted to obtain the battle record probability when the player selects the alternative landing area.

9. The method according to claim 1, characterized in that: The method further comprises: Searching for a target game match from the player's historical game matches according to the current game scenario; Based on the historical battle record data of the player, respectively counting the second battle record probability when the player selects each historical landing point in the historical game scene in the target game match; According to the second battle record probability corresponding to each of the historical landing points, a recommended landing point of the virtual object is determined from the candidate landing points in the current game scene.

10. The method according to claim 9, characterized in that The method further comprises: The recommended landing point and the second victory probability corresponding to the recommended landing point are sent to the terminal device of the player, so that the recommended landing point and the second victory probability corresponding to the recommended landing point are displayed through a graphical user interface provided by the terminal device.

11. A device for recommending a virtual object landing point, characterized in that: include: An acquisition module, used to acquire a first player type of a player and scene information of a current game scene; wherein the first player type is used to characterize the game behavior preference of the player, and the scene information at least includes an alternative landing area included in the current game scene; A landing area determination module, configured to determine a recommended landing area from the candidate landing areas based on the first player type; The first player type is determined by: Method 1: obtaining the historical game data of the player; wherein the historical game data at least includes historical behavior data and historical performance data; preprocessing the historical game data to obtain a target feature value; wherein the preprocessing includes normalization processing and dimensionality reduction processing; clustering processing is performed on the target feature value to determine the first player type of the player; Method 2: obtaining a contact list of the player, and determining the first player type of the player based on the second player type of each contact in the contact list; The landing area determination module is specifically used to: determine, based on the scene information, historical landing areas that match each of the candidate landing areas from the historical game scenes; wherein each of the historical landing areas corresponds to historical performance data when the player selects the historical landing area; based on the first player type and the historical performance data corresponding to each of the historical landing areas, determine a recommended landing area from the candidate landing areas; The landing area determination module is specifically used to: determine the historical game scene based on the scene type of the current game scene; calculate the similarity between each of the alternative landing areas and each historical landing area contained in the historical game scene; and determine the historical landing areas that match each of the alternative landing areas based on the similarity.

12. A server, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 10.

Images