Role recommendation method and system for multiplayer online competitive game role conflicts

The method and system address character position conflicts in multiplayer online competitive games by identifying, dividing, and correcting recommendation scores for conflicting roles, ensuring effective character recommendations and improved user experience.

CN115228089BActive Publication Date: 2024-12-06QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202210961199.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-08-11
Publication Date
2024-12-06
Estimated Expiration
2042-08-11

AI Technical Summary

Technical Problem

The existing character recommendation systems in multiplayer online competitive games fail to consider the impact of players' subjective selections, leading to character position conflicts that deteriorate the recommendation effect and affect user experience.

Method used

A method and system that identifies conflicting roles, divides them into non-conflicting lists, calculates and corrects recommendation scores, and sorts them to ensure effective character recommendations despite position conflicts.

Benefits of technology

Maintains a good recommendation effect by resolving character position conflicts, enhancing the overall gaming experience by providing accurate and relevant character suggestions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115228089B_ABST
    Figure CN115228089B_ABST
Patent Text Reader

Abstract

The present invention discloses a role recommendation method and system for role conflicts in multiplayer online competitive games; wherein the method obtains a selected role list and round information in response to a role recommendation request instruction; identifies conflicting roles in a currently recommended player's friendly lineup according to the selected role list and the round information; divides all conflicting roles into different non-conflicting role ID lists; calculates recommendation scores for all roles to be recommended in each non-conflicting role ID list; corrects the scores; sorts the recommendation scores of all roles to be recommended in each non-conflicting role ID list from large to small, and selects the top M roles for each non-conflicting role ID list; and then sorts the roles selected from all non-conflicting role ID lists in descending order according to the corrected recommendation scores, and selects the top N roles as recommendation results for output.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of role recommendation, and in particular to a role recommendation method and system for multiplayer online competitive game role conflicts. Background Art

[0002] The statements in this section merely mention background art related to the present invention and do not necessarily constitute prior art.

[0003] When recommending corresponding characters to players, the character recommendation system of multiplayer online competitive games does not consider the impact of the player's subjective selection on the system. In detail, the character recommended by the recommendation system to the current player depends on the characters currently selected by both parties. In other words, the character currently selected by the friendly player will affect the recommendation effect of the recommendation system on subsequent friendly players. Because the input of the recommendation system is the ID of the characters selected by all players before the recommended player, the recommendation system generates the lineup score based on the ID and makes subsequent recommendations.

[0004] In theory, the corresponding roles of characters in an excellent lineup should not be repeated. However, when a friendly player makes a choice based on his personal wishes and causes a conflict in the role positions of the friendly lineup, the recommendation system will have a poor recommendation effect, which will affect the system's subsequent recommendations for other friendly players and ultimately affect the user's experience of the game. Summary of the invention

[0005] In order to solve the shortcomings of the prior art, the present invention provides a method and system for recommending characters for multiplayer online competitive games with character conflicts; through a series of correction methods, the problem that the original recommendation system is deteriorated due to the subjective selectivity of players causing character position conflicts is well solved. The introduction of the correction method makes it possible to maintain a good recommendation effect when recommending characters to subsequent players even if there are characters with position conflicts on our side.

[0006] In a first aspect, the present invention provides a role recommendation method for multiplayer online competitive game role conflicts;

[0007] A role recommendation method for role conflicts in multiplayer online competitive games, applied to servers, including:

[0008] In response to the role recommendation request instruction, obtain a selected role list and round information; identify conflicting roles in the currently recommended player's friendly lineup according to the selected role list and round information;

[0009] All conflicting roles are divided into different non-conflicting role ID lists. A non-conflicting role ID list only retains one conflicting role. Each non-conflicting role ID list contains not only one conflicting role but also all selected non-conflicting roles.

[0010] Calculate the recommendation scores for all the roles to be recommended in each non-conflicting role ID list;

[0011] Correct the recommendation scores of all the roles to be recommended in each non-conflicting role ID list;

[0012] The recommendation scores of all the roles to be recommended in each non-conflicting role ID list are sorted in descending order, and the top M roles are selected for each non-conflicting role ID list; then the roles selected from all non-conflicting role ID lists are sorted in descending order according to the corrected recommendation scores, and the top N roles are selected as the recommendation result output, where M and N are both positive integers.

[0013] In a second aspect, the present invention provides a role recommendation system for role conflicts in multiplayer online competitive games;

[0014] A role recommendation system for multiplayer online competitive games with role conflicts, applied to servers, including:

[0015] The conflicting role identification module is configured to: in response to the role recommendation request instruction, obtain a selected role list and round information; and identify the conflicting roles in the currently recommended player's friendly lineup according to the selected role list and round information;

[0016] The conflicting role division module is configured to: divide all conflicting roles into different non-conflicting role ID lists, and each non-conflicting role ID list only retains one conflicting role; each non-conflicting role ID list contains not only one conflicting role but also all selected non-conflicting roles;

[0017] The recommendation score calculation module is configured to: calculate the recommendation scores for all roles to be recommended in each non-conflicting role ID list;

[0018] A recommendation score correction module is configured to: correct the recommendation scores of all roles to be recommended in each non-conflicting role ID list;

[0019] The recommendation score sorting module is configured as follows: the recommendation scores of all the roles to be recommended in each non-conflicting role ID list are sorted in descending order, and the top M roles are screened out for each non-conflicting role ID list; and then the roles screened out from all the non-conflicting role ID lists are sorted in descending order according to the corrected recommendation scores, and the top N roles are screened out as the recommendation result output, where M and N are both positive integers.

[0020] In a third aspect, the present invention further provides an electronic device, comprising:

[0021] a memory for non-transitory storage of computer-readable instructions; and

[0022] a processor for executing the computer readable instructions,

[0023] When the computer-readable instructions are executed by the processor, the method described in the first aspect is executed.

[0024] In a fourth aspect, the present invention further provides a storage medium that non-temporarily stores computer-readable instructions, wherein when the non-temporary computer-readable instructions are executed by a computer, the instructions of the method described in the first aspect are executed.

[0025] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, wherein the computer program is used to implement the method described in the first aspect when running on one or more processors.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The present invention uses a novel system to overcome the problem that the subjective selectivity of players leads to the poor effect of the recommendation system. The method is mainly composed of multiple modules: a conflict detection module, a conflict grouping module, a group recommendation module, an association fusion module, and a recommendation module. In the conflict detection module, before the system recommends a role to a player, the system will detect whether there is a position conflict between the characters in the current lineup. If there is no conflict, the original system will recommend normally; if there is, the conflict grouping module will be entered. In this stage, the system will first divide the conflicting characters into two groups, and each group will be combined with other selected characters to form a new selected character id list, and then enter the group recommendation stage. In this stage, the system will construct two root nodes, and input the two groups of selected character ids and round information into these two different root nodes respectively, and construct two Monte Carlo search trees to search for alternative characters, and perform role relevance and player interest fusion. Through these three stages, the problem caused by the subjective selectivity of players is well solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0029] Figure 1 This is a flow chart of the method of embodiment 1. DETAILED DESCRIPTION

[0030] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0031] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0033] In this embodiment, all data is obtained in compliance with laws and regulations and based on the user's consent, and is used legally.

[0034] Embodiment 1

[0035] This embodiment provides a role recommendation method for multiplayer online competitive game role conflicts;

[0036] like Figure 1 As shown, the role recommendation method for multiplayer online competitive game role conflicts is applied to the server, including:

[0037] S101: In response to a role recommendation request instruction, obtain a selected role list and round information; and identify conflicting roles in the currently recommended player's friendly lineup according to the selected role list and round information;

[0038] S102: All conflicting roles are divided into different non-conflicting role ID lists, and each non-conflicting role ID list only retains one conflicting role; each non-conflicting role ID list contains not only one conflicting role but also all selected non-conflicting roles;

[0039] S103: Calculate the recommendation scores for all the roles to be recommended in each non-conflicting role ID list;

[0040] S104: Modifying the recommendation scores of all roles to be recommended in each non-conflicting role ID list;

[0041] S105: Sort the recommendation scores of all the roles to be recommended in each non-conflicting role ID list in descending order, and select the top M roles for each non-conflicting role ID list; then sort the roles selected from all the non-conflicting role ID lists in descending order according to the corrected recommendation scores, and select the top N roles as the recommendation results for output, where M and N are both positive integers.

[0042] Furthermore, the step of identifying conflicting characters in the currently recommended player's friendly lineup specifically includes:

[0043] S101-1: Classify the selected characters in the selected character list into friendly characters and enemy characters according to the round information;

[0044] S101-2: extract the ID of the friendly character into a friendly character list;

[0045] S101-3: extracting the role information corresponding to the role ID from the existing role information list according to all the role IDs in the friendly role list; the role information includes: role ID, role name and role position;

[0046] S101-4: Determine whether there is a situation in the extracted character information where the character IDs are different but the character positions are the same. If so, it means that the two current characters are conflicting characters, and output the ID of the conflicting character and the IDs of all selected characters in the lineup where the conflicting character is located.

[0047] It should be understood that, in S101: in the role information list, the role information is stored in the data form of a Python dictionary. Each role is an independent dictionary, and the dictionary stores role information such as "role id", "role name", and "role position".

[0048] The attribute value of "role id" is one of the numbers from 0 to 108, representing 109 characters respectively.

[0049] "Character position" represents the position of the character in the game, which is divided into five categories: assassin, mage, shooter, warrior and support, represented by the numbers 1, 2, 3, 5 and 6 respectively. For a good character lineup, the positions of the five characters should not be repeated.

[0050] After the system obtains the friendly character ID list mentioned above, it will establish two layers of for loops. Then, according to the character ID, it uses the character information list to retrieve the position information of the character in the friendly character list. If it is found that the "character position" attribute value of two friendly characters is the same, it is considered that there is a conflict in the character position. When a conflict is detected, the system will output the ID list of all previously selected characters and the ID of the conflicting character detected by the friendly party.

[0051] It should be understood that, in S102, to solve the position conflict problem, the most critical point should be to separate the detected conflicting roles. After receiving the ID list of the selected role and the conflicting friendly role, the ID list of the selected role is removed from one of the two conflicting roles according to the ID of the conflicting role, and two new non-conflicting role ID lists are constructed.

[0052] For example: recommending to player 5, the current character has selected the role id list of [11,22,33,44]. Assuming that at this time the role positions of player 5's teammates 1 and 4 conflict, the module should process the id list into two new id lists [11,22,33] and [22,33,44].

[0053] Furthermore, the step S103: calculating the recommendation scores for all the roles to be recommended in each non-conflicting role ID list; specifically includes:

[0054] S103-1: Construct a root node; the attributes of the root node include: the currently selected character of the lineup to be formed, the currently selected character of the opponent player, and the turn information of the selected character;

[0055] S103-2: Expand a child node or select a child node for the root node;

[0056] S103-3: Visit the child node expanded or selected in the previous step;

[0057] When the jth child node is visited, it is assumed that the role represented by the jth child node is the role to be recommended;

[0058] For the remaining characters in the lineup to be formed, randomly select characters to set up to complete the lineup to be formed;

[0059] For the remaining characters of the opposing player, randomly select characters to set up to complete the opposing player's lineup;

[0060] S103-4: Rearrange the roles of the completed lineup to be formed and the completed lineup of opposing players;

[0061] S103-5: inputting the lineup to be formed after the role rearrangement into the trained neural network, and outputting the predicted score of the lineup to be formed after the completion;

[0062] Input the completed lineup of players into the trained neural network, and output the predicted score of the completed lineup of players;

[0063] When the predicted score of the completed lineup to be formed is greater than the predicted score of the opposing player lineup and greater than the set threshold, the feedback value of the current child node is increased by 1; otherwise, the feedback value of the current child node is increased by 0; return to S103-2;

[0064] S103-6: After visiting the M child nodes a set number of times, calculate the ratio of the feedback value of the current child node to the number of times the current child node has been visited, and use the ratio as the first recommendation index of the role corresponding to the current child node.

[0065] Furthermore, the S103-2: expanding a child node or selecting a child node for the root node specifically includes:

[0066] Assuming that the number of all candidate roles is M, generate a random number, which is greater than 0 and less than 1; determine whether the random number is greater than 0.5;

[0067] If the random number is less than 0.5, continue to determine whether the number of child nodes of the current root node is less than M. If so, expand a new child node for the root node and proceed to S103-3. If greater than or equal to M, select a child node.

[0068] If the random number is greater than 0.5, a child node is selected;

[0069] The process of selecting a child node includes:

[0070] The child node score calculation formula of the Monte Carlo search tree algorithm is used to calculate the scores of all child nodes under the current root node, and the child node corresponding to the highest score is selected, and then the process proceeds to S103-3;

[0071] Each child node represents an alternative role; different child nodes represent different alternative roles; where M is a positive integer; the initial feedback value of each child node is 0.

[0072] Furthermore, the scores of all child nodes of the root node are calculated according to the child node score calculation formula, and the child node with the highest score is selected:

[0073]

[0074] Among them, R c Represents the number of times the node receives feedback of 1, V c Represents the number of times the node is visited, V pRepresents the number of visits to the node's parent node, S is a constant, and UTC represents the score corresponding to the child node.

[0075] Furthermore, the training process of the trained neural network includes:

[0076] Constructing a training set; the training set includes positive samples and negative samples; using the lineup data of the winners of several tens of thousands of games of several players before the current game as positive samples, and using several tens of thousands of lineup data of the conflicting roles in the current game as negative samples;

[0077] Constructing a neural network; the neural network is a shallow neural network; the shallow neural network includes an input layer, a hidden layer and an output layer connected in sequence;

[0078] The training set is input into the shallow neural network for training to obtain the trained shallow neural network.

[0079] S103-1, S103-2, S103-3, S103-5, S103-6 are the same as the application number 202210852217X, application date 2022-07-20, patent name: Game role recommendation method and system, the specific steps of the first embodiment of the specification are the same as the current selected role of the lineup to be formed, the current selected role of the opponent player, the round information of the selected role, and all the candidate roles. What is different is that this application adds S103-4. S103-4 is a role re-arrangement for role conflicts.

[0080] Furthermore, the step S103-4: rearranging the roles of the completed lineup to be formed and the completed lineup of opposing players specifically includes:

[0081] S103-41: Obtain a list of selected roles, a list of removed conflicting roles, and a list of roles to be rearranged;

[0082] S103-42: Calculating the role positions to be filled based on the selected role list and the removed conflicting roles;

[0083] S103-43: Calculate the position of the role to be recommended;

[0084] S103-44: saving the recommended role information corresponding to the position of the role to be recommended in the role list to be rearranged; and shifting each role information in the role list to be rearranged backward one position in sequence starting from the position of the role to be filled;

[0085] S103-45: deleting the recommended role information in the role list to be rearranged; and moving the subsequent roles of the deleted role forward one position in sequence;

[0086] S103-46: Fill the saved information of the role to be recommended into the position of the role to be filled, complete the role rearrangement, and obtain the rearranged role list.

[0087] The selected role list refers to a list sorted by the rounds of the selected roles;

[0088] The list of characters to be rearranged refers to a list sorted according to the turns of the characters based on the completed lineup to be formed and the completed lineup of opposing players.

[0089] Exemplarily, S103-4, 10 characters are input into a rearrangement module. The function of the rearrangement module is to allocate the 10 characters to the correct camp (left side or red side).

[0090] In detail: As mentioned above, the role id list [11,22,33,44] is grouped into [11,22,33] and [22,33,44] after detecting the conflict.

[0091] For the first group, after the group is filled with 10 heroes, the camp to which each hero belongs is no different than before the grouping.

[0092] However, for the second group, after it was filled with 10 heroes, according to the round information, the character with ID 22 who originally belonged to the right camp was now equivalent to a character in the left camp, and there was confusion as to the camps to which the characters after that belonged.

[0093] Therefore, if the order of role IDs is not adjusted, the recommendation effect will be affected.

[0094] Therefore, it is necessary to introduce the rearrangement module.

[0095] The rearrangement module has three input parameters: the selected role ID list (that is, the list before grouping, i.e. [11,22,33,44]), the removed conflicting roles (that is, the roles removed when the list is grouped. If the grouped list is [22,33,44], then 11 is the removed conflicting role of the grouped list) and the above-mentioned list of 10 roles that need to be rearranged (here it can be understood as a list consisting of [22,33,44] + roles to be selected + random roles).

[0096] As for the problem of disordered faction order mentioned above, a deeper analysis shows that the disordered order is caused by the reduction of a character in the original list. Therefore, if we can find a character to fill the reduced position, the order problem will not occur afterwards (it can be understood as: the original list is [11, 22, 33, 44], and a group is [22, 33, 44]. At this time, we need to find a filling character id to change [22, 33, 44] to [filling id, 22, 33, 44]).

[0097] Based on this idea, after experiments, the rearrangement module chooses the ID of the hero to be recommended as the filler ID and adjusts the order of the remaining characters, which can solve the above-mentioned problems.

[0098] The details of the module algorithm are:

[0099] First, based on the selected character ID list and the removed conflicting character IDs in the three input parameters, calculate the role position that needs to be filled (the list subscript index of the removed character in the original selected characters) and the hero position to be recommended (the length of the original recommendation list - 1).

[0100] Then process the list of 10 characters that need to be rearranged: starting from the position that needs to be filled, each character ID position is moved back one unit in turn, and after deleting the ID of the hero to be recommended in the list, the recommended hero ID is filled in the fill position.

[0101] The detailed process is as follows:

[0102] Suppose the group [22,33,44] generates a list of 10 characters [22,33,44,5,6,7,8,9,10,13] after the simulation stage, the selected hero list is [11,22,33,44], and the conflicting character id that has been removed is 11.

[0103] Step 1: Calculate the filling position;

[0104] 11 is in the first position in [11,22,33,44], and the corresponding character list subscript value is 0.

[0105] Step 2: Calculate the position of the hero to be recommended;

[0106] The length of [11,22,33,44] - 1 = 4 - 1 = 3;

[0107] The corresponding index value of the 10-character list is 3, the fourth position. (That is, the position of id 5)

[0108] Step 3: Save the id information of the role to be recommended, and move back from the filled position id in sequence.

[0109] Set variable temp = 5

[0110] [22,33,44,5,6,7,8,9,10,13]=>[fill id,22,33,44,5,6,7,8,9,10,13]

[0111] Step 4: Delete the recommended character IDs from the 10 hero list

[0112] [fill id, 22, 33, 44, 5, 6, 7, 8, 9, 10, 13] => [fill id, 22, 33, 44, 6, 7, 8, 9, 10, 13]

[0113] Step 5: Enter the recommended role ID information saved in temp into the fill position

[0114] [fill id,22,33,44,6,7,8,9,10,13]=>[5,22,33,44,6,7,8,9,10,13]

[0115] At this point, the list of 10 heroes has been re-arranged, and you can see that the camp chaos problem has been solved.

[0116] Furthermore, the S104: corrects the recommendation scores of all characters to be recommended in each non-conflicting character ID list; for the specific calculation process, refer to application number 202210852217X, application date 2022-07-20, patent name: Game character recommendation method and system, and the specification of the specific embodiment 1 of the knowledge graph based on the role, constructing a different team association matrix and a same team association matrix; based on the different team association matrix and the same team association matrix, correcting the first recommendation index of each alternative character to obtain the second recommendation index of each alternative character; based on the historical role usage record of the current player, correcting the second recommendation index of each alternative character to obtain a third recommendation index for each alternative character.

[0117] Further, the step S105: sorting the recommendation scores of all the roles to be recommended in each non-conflicting role ID list in descending order, and selecting the top M roles for each non-conflicting role ID list; and then sorting the roles selected from all the non-conflicting role ID lists in descending order according to the corrected recommendation scores, and selecting the top N roles as the recommendation results for output, where both M and N are positive integers; specifically includes:

[0118] After receiving the two root nodes, first sort the recommendation scores of the candidate character nodes in each root node from large to small according to the recommendation score, and construct two lists. Note that the candidate character nodes belonging to the same root node are in the same list. After that, take out the first three candidate character nodes in the two lists, sort them again, construct a new list containing 6 recommended character IDs, and return it to the front end. After that, the front end renders the character ID in the list and displays the corresponding character avatar for recommendation to the player.

[0119] Embodiment 2

[0120] This embodiment provides a role recommendation system for multiplayer online competitive game role conflicts;

[0121] A role recommendation system for multiplayer online competitive games with role conflicts, applied to servers, including:

[0122] The conflicting role identification module is configured to: in response to the role recommendation request instruction, obtain a selected role list and round information; and identify the conflicting roles in the currently recommended player's friendly lineup according to the selected role list and round information;

[0123] The conflicting role division module is configured to: divide all conflicting roles into different non-conflicting role ID lists, and each non-conflicting role ID list only retains one conflicting role; each non-conflicting role ID list contains not only one conflicting role but also all selected non-conflicting roles;

[0124] The recommendation score calculation module is configured to: calculate the recommendation scores for all roles to be recommended in each non-conflicting role ID list;

[0125] A recommendation score correction module is configured to: correct the recommendation scores of all roles to be recommended in each non-conflicting role ID list;

[0126] The recommendation score sorting module is configured as follows: the recommendation scores of all the roles to be recommended in each non-conflicting role ID list are sorted in descending order, and the top M roles are screened out for each non-conflicting role ID list; and then the roles screened out from all the non-conflicting role ID lists are sorted in descending order according to the corrected recommendation scores, and the top N roles are screened out as the recommendation result output, where M and N are both positive integers.

[0127] Furthermore, the step of identifying conflicting characters in the currently recommended player's friendly lineup specifically includes:

[0128] According to the round information, the selected characters in the selected character list are divided into friendly characters and enemy characters;

[0129] Extract the ID of the friendly character into a friendly character list;

[0130] According to all the role IDs in the friendly role list, extract the role information corresponding to the role ID from the existing role information list; the role information includes: role ID, role name and role position;

[0131] Determine whether there is a situation in the extracted character information where the character IDs are different but the character positions are the same. If so, it means that the two current characters are conflicting characters. Output the ID of the conflicting character and the IDs of all selected characters in the lineup where the conflicting character is located.

[0132] It should be noted that the above-mentioned conflicting role identification module, conflicting role division module, recommendation score calculation module, recommendation score correction module and recommendation score ranking module correspond to steps S101 to S105 in Embodiment 1, and the examples and application scenarios implemented by the above-mentioned modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Embodiment 1. It should be noted that the above-mentioned modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0133] The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] The proposed system can be implemented in other ways. For example, the system embodiment described above is only illustrative, and the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0135] Embodiment 3

[0136] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein the processor is connected to the memory, and the one or more computer programs are stored in the memory. When the electronic device is running, the processor executes the one or more computer programs stored in the memory so that the electronic device executes the method described in the above embodiment one.

[0137] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0138] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0139] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.

[0140] The method in the first embodiment can be directly embodied as a hardware processor, or a combination of hardware and software modules in the 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, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0141] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0142] Embodiment 4

[0143] This embodiment further provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the method described in the first embodiment is completed.

[0144] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A role recommendation method for role conflicts in multiplayer online competitive games, characterized by: Applicable to servers, including: In response to the role recommendation request instruction, obtain a selected role list and round information; identify conflicting roles in the currently recommended player's friendly lineup according to the selected role list and round information; All conflicting roles are divided into different non-conflicting role ID lists. A non-conflicting role ID list only retains one conflicting role. Each non-conflicting role ID list contains not only one conflicting role but also all selected non-conflicting roles. For all the roles to be recommended in each non-conflicting role ID list, calculate the recommendation score, including: Construct a root node; the attributes of the root node include: the currently selected character of the lineup to be formed, the currently selected character of the opponent player, and the turn information of the selected character; Expand child nodes or select child nodes for the root node; Visit the child nodes expanded or selected in the previous step; when the j-th child node is visited, assume that the character represented by the j-th child node is the character to be recommended; for the remaining characters in the lineup to be formed, randomly select characters to set to complete the lineup to be formed; for the remaining characters of the opposing players, randomly select characters to set to complete the opposing player lineup; Rearrange the roles of the completed lineup to be formed and the completed lineup of opposing players; Input the lineup to be formed after the role rearrangement into the trained neural network, and output the predicted score of the completed lineup to be formed; input the completed opponent player lineup into the trained neural network, and output the predicted score of the completed opponent player lineup; when the predicted score of the completed lineup to be formed is greater than the predicted score of the opponent player lineup and greater than the set threshold, the feedback value of the current child node is increased by 1; otherwise, the feedback value of the current child node is increased by 0; return to expand the child node of the root node or select the child node; After visiting the M child nodes a set number of times, calculate the ratio of the feedback value of the current child node to the number of times the current child node has been visited, and use the ratio as the first recommendation index of the role corresponding to the current child node; The recommendation scores of all the characters to be recommended in each non-conflicting character ID list are corrected, specifically including: constructing a heterogeneous team association matrix and a same-team association matrix; based on the heterogeneous team association matrix and the same-team association matrix, the first recommendation index of each candidate character is corrected to obtain the second recommendation index of each candidate character; based on the historical character usage record of the current player, the second recommendation index of each candidate character is corrected to obtain the third recommendation index of each candidate character; The recommendation scores of all the roles to be recommended in each non-conflicting role ID list are sorted in descending order, and the top M roles are selected for each non-conflicting role ID list; then the roles selected from all the non-conflicting role ID lists are sorted in descending order according to the corrected recommendation scores, and the top N roles are selected as the recommendation results for output, where M and N are both positive integers; Rearrange the roles of the completed lineup to be formed and the completed lineup of players to be faced, including: Get the list of selected roles, the list of removed conflicting roles and the list of roles to be rearranged; Calculate the role positions to be filled based on the selected role list and the removed conflicting roles; Calculate the position of the role to be recommended; The recommended role information corresponding to the position of the recommended role in the role list to be rearranged is saved; each role information in the role list to be rearranged is shifted back one position in sequence starting from the position of the role to be filled; Delete the recommended role information in the role list to be rearranged; move the subsequent roles of the deleted role forward one position in sequence; The saved information of the roles to be recommended is filled into the roles to be filled, the roles are rearranged, and a rearranged role list is obtained.

2. The role recommendation method for multiplayer online competitive game role conflicts as claimed in claim 1, characterized in that: The step of identifying conflicting characters in the currently recommended player's friendly lineup specifically includes: According to the round information, the selected characters in the selected character list are divided into friendly characters and enemy characters; Extract the ID of the friendly character into a friendly character list; According to all the role IDs in the friendly role list, extract the role information corresponding to the role ID from the existing role information list; the role information includes: role ID, role name and role position; Determine whether there is a situation in the extracted character information where the character IDs are different but the character positions are the same. If so, it means that the two current characters are conflicting characters. Output the ID of the conflicting character and the IDs of all selected characters in the lineup where the conflicting character is located.

3. The role recommendation method for multiplayer online competitive game role conflicts as claimed in claim 1, characterized in that: The selected character list refers to a list sorted by the turns of the selected characters; the list of characters to be rearranged refers to a list sorted by the turns of the characters based on the completed lineup to be formed and the completed lineup of opposing players.

4. A role recommendation system for role conflicts in multiplayer online competitive games, characterized by: Applicable to servers, including: The conflicting role identification module is configured to: in response to the role recommendation request instruction, obtain a selected role list and round information; and identify the conflicting roles in the currently recommended player's friendly lineup according to the selected role list and round information; The conflicting role division module is configured to: divide all conflicting roles into different non-conflicting role ID lists, and each non-conflicting role ID list only retains one conflicting role; each non-conflicting role ID list contains not only one conflicting role but also all selected non-conflicting roles; The recommendation score calculation module is configured to calculate the recommendation scores for all roles to be recommended in each non-conflicting role ID list, specifically including: Construct a root node; the attributes of the root node include: the currently selected character of the lineup to be formed, the currently selected character of the opponent player, and the turn information of the selected character; Expand child nodes or select child nodes for the root node; Visit the child nodes expanded or selected in the previous step; when the j-th child node is visited, assume that the character represented by the j-th child node is the character to be recommended; for the remaining characters in the lineup to be formed, randomly select characters to set to complete the lineup to be formed; for the remaining characters of the opposing players, randomly select characters to set to complete the opposing player lineup; Rearrange the roles of the completed lineup to be formed and the completed lineup of opposing players; Input the lineup to be formed after the role rearrangement into the trained neural network, and output the predicted score of the completed lineup to be formed; input the completed opponent player lineup into the trained neural network, and output the predicted score of the completed opponent player lineup; when the predicted score of the completed lineup to be formed is greater than the predicted score of the opponent player lineup and greater than the set threshold, the feedback value of the current child node is increased by 1; otherwise, the feedback value of the current child node is increased by 0; return to expand the child node of the root node or select the child node; After visiting the M child nodes a set number of times, calculate the ratio of the feedback value of the current child node to the number of times the current child node has been visited, and use the ratio as the first recommendation index of the role corresponding to the current child node; The recommendation score correction module is configured to correct the recommendation scores of all the characters to be recommended in each non-conflicting character ID list, specifically including: constructing a different team association matrix and a same team association matrix; based on the different team association matrix and the same team association matrix, correcting the first recommendation index of each candidate character to obtain the second recommendation index of each candidate character; based on the historical character usage record of the current player, correcting the second recommendation index of each candidate character to obtain the third recommendation index of each candidate character; The recommendation score sorting module is configured to: sort the recommendation scores of all roles to be recommended in each non-conflicting role ID list in descending order, and select the top M roles for each non-conflicting role ID list; then sort the roles selected from all non-conflicting role ID lists in descending order according to the revised recommendation scores, and select the top N roles as the recommendation results for output, where M and N are both positive integers; Rearrange the roles of the completed lineup to be formed and the completed lineup of players to be faced, including: Get the list of selected roles, the list of removed conflicting roles and the list of roles to be rearranged; Calculate the role positions to be filled based on the selected role list and the removed conflicting roles; Calculate the position of the role to be recommended; The recommended role information corresponding to the position of the recommended role in the role list to be rearranged is saved; each role information in the role list to be rearranged is shifted back one position in sequence starting from the position of the role to be filled; Delete the recommended role information in the role list to be rearranged; move the subsequent roles of the deleted role forward one position in sequence; The saved information of the roles to be recommended is filled into the roles to be filled, the roles are rearranged, and a rearranged role list is obtained.

5. The role recommendation system for multiplayer online competitive game role conflicts as claimed in claim 4, characterized in that: The step of identifying conflicting characters in the currently recommended player's friendly lineup specifically includes: According to the round information, the selected characters in the selected character list are divided into friendly characters and enemy characters; Extract the ID of the friendly character into a friendly character list; According to all the role IDs in the friendly role list, extract the role information corresponding to the role ID from the existing role information list; the role information includes: role ID, role name and role position; Determine whether there is a situation in the extracted character information where the character IDs are different but the character positions are the same. If so, it means that the two current characters are conflicting characters. Output the ID of the conflicting character and the IDs of all selected characters in the lineup where the conflicting character is located.

6. An electronic device, comprising: a memory for non-transitory storage of computer readable instructions; as well as a processor for executing the computer readable instructions, Wherein, when the computer-readable instructions are executed by the processor, the method described in any one of claims 1 to 3 is executed.

7. A storage medium, characterized in that it non-temporarily stores computer-readable instructions, wherein: When the computer-readable instructions are executed by a computer, the instructions of the method according to any one of claims 1 to 3 are executed.

8. A computer program product, characterized in that The invention comprises a computer program, which is used to implement the method according to any one of claims 1 to 3 when running on one or more processors.

Citation Information

Patent Citations

  • Game role recommendation, lineup establishment method and device, game method and device

    CN106919790A

  • An array volume determination method and device and an electronic device

    CN109814955A

  • Game character recommendation method and terminal

    CN110721475A

  • Recommendation method and device based on artificial intelligence, and electronic equipment

    CN112380430A

  • Program and server system

    JP2015126775A