Skill release method, skill determination method, skill release device, skill determination device, storage medium and product

Abstract

The invention provides a skill release method and device, a skill determination method and device, a storage medium and a product, and belongs to the technical field of artificial intelligence. The method comprises the following steps: displaying a game interface of a virtual game, wherein a first virtual object participating in the virtual game is displayed in the game interface; and in response to a trigger operation on a skill release function, the first virtual object is controlled to continuously release a plurality of skills, and the plurality of skills are determined based on at least one of the game state information of the virtual game and the historical release skills of the first virtual object. According to the method, the interaction efficiency is improved on the basis of ensuring the accuracy of the recommended skills.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a skill releasing method, a skill determining method, a device, a storage medium and a product. BACKGROUND

[0002] In a virtual scene, a virtual object can be controlled to release multiple skills at a time, that is, through one interaction, the virtual object can be controlled to release multiple skills continuously. However, the multiple skills need to be set in advance in a setting interface. Among them, multiple skills are displayed on the setting interface, the player selects the desired skill, and long-presses and drags to the assembly area on the setting interface, and the multiple skills are assembled in the assembly area, thereby obtaining multiple skills that can be released at a time.

[0003] The method sets multiple skills, which requires the player to frequently click, drag and other operations on the setting interface, and the whole process is relatively cumbersome, thereby reducing the interaction efficiency. SUMMARY

[0004] Embodiments of the present application provide a skill releasing method, a skill determining method, a device, a storage medium and a product, which improve the interaction efficiency on the basis of ensuring the accuracy of recommended skills. The technical solution is as follows:

[0005] On the one hand, a skill releasing method is provided, and the method comprises:

[0006] displaying a game interface of a virtual game, wherein the game interface displays a first virtual object participating in the virtual game;

[0007] in response to a triggering operation of a skill releasing function, controlling the first virtual object to release multiple skills continuously, wherein the multiple skills are determined based on at least one of game state information of the virtual game and historical released skills of the first virtual object.

[0008] On the other hand, a skill determining method is provided, and the method comprises:

[0009] acquiring at least one of game state information of a virtual game and historical released skills of a first virtual object participating in the virtual game during a process in which a terminal performs the virtual game;

[0010] determining multiple skills for the first virtual object based on at least one of the game state information and the historical released skills, wherein the multiple skills are used to be released continuously in a case where a skill releasing function is triggered.

[0011] On the other hand, a skill releasing device is provided, and the device comprises:

[0012] The display module is configured to display a game interface of a virtual game, and the game interface displays a first virtual object participating in the virtual game.

[0013] The release module is configured to, in response to a trigger operation on a skill release function, control the first virtual object to continuously release a plurality of skills, and the plurality of skills are determined based on at least one of game state information of the virtual game and historical released skills of the first virtual object.

[0014] In some embodiments, the display module is further configured to:

[0015] display at least one skill combination on the game interface based on at least one of the game state information and the historical released skills, and each skill combination includes a plurality of skills;

[0016] The release module is configured to:

[0017] In response to a trigger operation on any skill combination of the at least one skill combination, control the first virtual object to continuously release a plurality of skills in the any skill combination.

[0018] In some embodiments, the display module is further configured to:

[0019] display skill effects of each skill combination of the at least one skill combination on the game interface, and the skill effects of any skill combination are used to indicate effects that can be achieved by the plurality of skills in the any skill combination.

[0020] In some embodiments, the display module is further configured to:

[0021] In response to a modification operation on any skill in any skill combination, display the modified any skill combination and a changed skill effect of the modified any skill combination;

[0022] The release module is further configured to:

[0023] In response to a trigger operation on the modified any skill combination, control the first virtual object to continuously release a plurality of skills in the modified any skill combination.

[0024] In some embodiments, the plurality of skills in any skill combination are arranged in a release order on the game interface, and the modification operation includes a sequence adjustment operation on the any skill.

[0025] In some embodiments, the skill effect is a dynamic demonstration effect, and the dynamic demonstration effect is used to demonstrate a process of continuously releasing the plurality of skills by the first virtual object and effects that can be achieved.

[0026] In some embodiments, the display module is further configured to perform at least one of:

[0027] in response to any skill in the plurality of skills being released, a change in appearance of the any skill is displayed, the changed appearance being used to indicate that the any skill has been released;

[0028] in response to any skill in the plurality of skills being released, the any skill in the plurality of skills is highlighted.

[0029] In some embodiments, the release module is further configured to:

[0030] in response to a triggering operation on any skill in the plurality of skills, the first virtual object is controlled to release the any skill.

[0031] In some embodiments, the display module is further configured to perform at least one of:

[0032] a first combo control is displayed in the game interface, in response to a triggering operation on the first combo control, a combo function is enabled, the combo function being used to control the first virtual object to release a plurality of skills in succession in response to a triggering operation on the skill release function;

[0033] a second combo control is displayed on the setting interface of the virtual game, in response to a triggering operation on the second combo control, the combo function is enabled.

[0034] In some embodiments, the game state information includes at least one of a type of a level in which the first virtual object is located, a difficulty value of the level in which the first virtual object is located, a type of the first virtual object, a virtual prop used by the first virtual object, a skill released by the first virtual object, a type of a second virtual object, a virtual prop used by the second virtual object, and a skill released by the second virtual object, the second virtual object being a virtual object that is in a battle with the first virtual object.

[0035] In some embodiments, the historical release skill includes at least one of a plurality of skills released in succession by the virtual object in a target time period and a single skill released once, an end point of the target time period being a start point of the virtual game.

[0036] In another aspect, a skill determination apparatus is provided, the apparatus comprising:

[0037] an acquisition module configured to acquire at least one of game state information of a virtual game and a historical release skill of a first virtual object participating in the virtual game in a process in which a terminal plays the virtual game;

[0038] determining a plurality of skills for the first virtual object based on at least one of the game state information and the historical released skills, the plurality of skills being used for continuous release in case that the skill release function is triggered.

[0039] In some embodiments, the obtaining module is further configured to:

[0040] obtaining updated game state information of the virtual game in case that a current time reaches an update time point of the skill;

[0041] The apparatus further includes:

[0042] a first updating module configured to update the plurality of skills based on at least one of the updated game state information and the historical released skills;

[0043] a returning module configured to return the updated plurality of skills to a terminal, the terminal being configured to control the first virtual object to continuously release the updated plurality of skills in response to a triggering operation on the skill release function.

[0044] In some embodiments, the determining module is configured to:

[0045] inputting at least one of the game state information and the historical released skills into a long short-term memory network, and outputting the plurality of skills through the long short-term memory network, the long short-term memory network being configured to determine a plurality of skills for the virtual object based on at least one of game state information and historical released skills of the virtual object.

[0046] In some embodiments, the apparatus further includes a second updating module configured to:

[0047] updating the long short-term memory network based on game state information of the virtual game and a plurality of skills released by the first virtual object in the virtual game after the virtual game ends.

[0048] In some embodiments, the apparatus further includes a training module configured to:

[0049] obtaining a plurality of groups of samples, each group of samples including a sample skill combination of a sample virtual object and at least one of sample game state information and historical released skills of the sample virtual object, the sample skill combination including a plurality of sample skills continuously released by the sample virtual object, and the sample game state information being game state information corresponding to a case that the sample virtual object releases the plurality of sample skills;

[0050] For each group of sample groups, at least one of the sample pair state information and the historical release skills in the sample groups is input into the long short-term memory network, and the long short-term memory network is used for prediction to obtain a predicted skill combination, the predicted skill combination including a plurality of skills released continuously;

[0051] Based on the respective sample skill combinations and the predicted skill combinations of the plurality of groups of sample groups, the long short-term memory network is trained.

[0052] In some embodiments, the game state information includes at least one of a type of a level in which the first virtual object is located, a difficulty value of the level in which the first virtual object is located, a type of the first virtual object, a virtual prop used by the first virtual object, a skill released by the first virtual object, a type of a second virtual object, a virtual prop used by the second virtual object, and a skill released by the second virtual object, the second virtual object being a virtual object that is in a battle with the first virtual object.

[0053] In some embodiments, the historical release skills include at least one of a plurality of skills released continuously by the virtual object in a target time period and a single skill released once, an end point of the target time period being a start point of the virtual game.

[0054] In another aspect, a computer device is provided, the computer device including a processor and a memory, the memory being configured to store at least one program, the at least one program being loaded and executed by the processor to implement the skill release method or the skill determination method in the embodiments of the present application.

[0055] In another aspect, a computer readable storage medium is provided, the computer readable storage medium storing at least one program, the at least one program being loaded and executed by a processor to implement the skill release method or the skill determination method in the embodiments of the present application.

[0056] In another aspect, a computer program product is provided, the computer program product including at least one program, the at least one program being stored in a computer readable storage medium, a processor of a computer device reading the at least one program from the computer readable storage medium, and the processor executing the at least one program to cause the computer device to perform the skill release method or the skill determination method according to any of the implementation manners described above.

[0057] The embodiment of the present application provides a skill release method, which can control a first virtual object to continuously release a plurality of skills in response to a trigger operation of a skill release function, that is, realizes the function of one-key release of continuous skills; and since the plurality of skills are determined based on at least one of game state information and historical released skills, that is, the skills in the continuous skills are intelligently recommended for the player, so that the player does not need to configure the plurality of skills in the continuous skills in advance, the interactive operation is reduced, and the interactive efficiency is improved. Further, since the plurality of skills are determined based on at least one of the game state information and the historical released skills, the plurality of skills are matched with the current game state of the virtual game and / or the skill use habit of the player, and the accuracy of the recommended skills is ensured, that is, the method improves the interactive efficiency on the basis of ensuring the accuracy of the recommended skills. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0059] Figure 1 is a schematic diagram of an implementation environment provided by the embodiment of the present application;

[0060] Figure 2 is a flowchart of a skill release method provided by the embodiment of the present application;

[0061] Figure 3 is a flowchart of another skill release method provided by the embodiment of the present application;

[0062] Figure 4 is a schematic diagram of a game interface provided by the embodiment of the present application;

[0063] Figure 5 is a flowchart of a training method of a long short-term memory network provided by the embodiment of the present application;

[0064] Figure 6 is a schematic diagram of a long short-term memory network provided by the embodiment of the present application;

[0065] Figure 7 is a schematic diagram of another game interface provided by the embodiment of the present application;

[0066] Figure 8 is a schematic diagram of still another game interface provided by the embodiment of the present application;

[0067] Figure 9 is a flowchart of still another skill release method provided by the embodiment of the present application;

[0068] Figure 10 is a flowchart of another skill releasing method provided by an embodiment of the present application;

[0069] Figure 11 is a block diagram of a skill releasing apparatus provided by an embodiment of the present application;

[0070] Figure 12 is a block diagram of a skill determining apparatus provided by an embodiment of the present application;

[0071] Figure 13 is a block diagram of a terminal provided by an embodiment of the present application;

[0072] Figure 14 is a block diagram of a server provided by an embodiment of the present application. DETAILED DESCRIPTION

[0073] In order to make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0074] In the present application, the terms "first", "second", and the like are used to distinguish the same or similar items with substantially the same function and action, and it should be understood that there is no logical or time sequence dependency between "first", "second", and "nth", and the number and execution order are not limited.

[0075] In the present application, the term "at least one" means one or more, and the term "multiple" means two or more.

[0076] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.) and signals involved in the present application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions. For example, the game state information and historical skill releasing involved in the present application are obtained under sufficient authorization.

[0077] In the following, the professional terms involved in the present application are introduced:

[0078] Artificial Intelligence (AI) is the theory, method, technology and application system of using digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology of computer science, which attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that machines have the functions of perception, reasoning and decision making. Artificial intelligence technology is a comprehensive discipline, involving a wide range of fields, both hardware and software technologies. Artificial intelligence basic technologies generally include sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, pre-training model technology, operation / interaction system, mechatronics, etc. Among them, the pre-training model is also called large model, basic model, which can be widely applied to downstream tasks in various directions of artificial intelligence after fine tuning. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology and machine learning / deep learning, etc.

[0079] Machine Learning (ML) is a multi-disciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, etc. It is a subject that studies how computers simulate or implement human learning behavior to acquire new knowledge or skills, and reorganize existing knowledge structure to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental approach to making computers intelligent, and its applications are widespread in various fields of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching-based learning. Pre-training model is the latest development of deep learning, which integrates the above technologies.

[0080] Long Short Term Memory (LSTM) is a kind of time recurrent neural network, which can learn and remember long-term dependencies and can process time series and long-range context information in time series, suitable for processing and predicting important events with relatively long interval or delay in time series, and belongs to a kind of recurrent neural network. LSTM neural network has a "gate" structure (including input gate, forget gate and output gate), which can eliminate or increase the ability of information to cell state, so that LSTM neural network can remember long-term information, and solve the problem of gradient disappearance or explosion in the training process of traditional recurrent neural network.

[0081] Virtual scene: a virtual scene displayed (or provided) by an application when running on a terminal. The virtual scene can be a simulated environment of the real world, a semi-simulated and semi-fictitious virtual environment, or a purely fictitious virtual environment. The virtual scene can be any one of a two-dimensional virtual scene, a 2.5-dimensional virtual scene, or a three-dimensional virtual scene, and the embodiments of the present application do not limit the dimension of the virtual scene. For example, the virtual scene can include a sky, a land, an ocean, etc., the land can include desert, city, and other environmental elements, and a terminal user can control a virtual object to move in the virtual scene.

[0082] Virtual object: a movable object in a virtual world. The movable object can be at least one of a virtual person, a virtual animal, an animation character, and a virtual vehicle. Alternatively, when the virtual world is a three-dimensional virtual world, the virtual object can be a three-dimensional model, each virtual object has its own shape and volume in the three-dimensional virtual world, and occupies a part of the space in the three-dimensional virtual world. Alternatively, the virtual object is a three-dimensional character constructed based on three-dimensional human skeleton technology, and the virtual object realizes different external images by wearing different skins. In some implementations, the virtual object can also be implemented in a 2.5-dimensional or 2-dimensional model, and the embodiments of the present application do not limit this.

[0083] Chained skill: in a virtual scene, chained skill usually refers to a series of actions or skills executed in a specific order, which can continuously cause damage to an enemy without being interrupted.

[0084] In the following, the implementation environment related to the present application is introduced:

[0085] The skill release method provided by the embodiments of the present application can be executed by a computer device, which can be provided as a server or a terminal. The implementation environment schematic diagram of the skill release method provided by the embodiments of the present application is introduced as follows.

[0086] Referring to Figure 1 , Figure 1A schematic diagram of an implementation environment of a skill release method provided by an embodiment of the present application is shown, which includes a terminal 101 and a server 102. The terminal 101 and the server 102 can be directly or indirectly connected through wired or wireless communication, which is not limited in the present application. In some embodiments, the terminal 101 is installed with a target application, and a virtual scene is run in the target application, and a plurality of virtual objects in the virtual scene can participate in the same virtual match. During the process of the virtual match, the terminal can control the virtual objects to release a plurality of skills in succession by one key. The plurality of skills are determined based on at least one of match state information of the virtual objects in the virtual match and historical released skills. Alternatively, the terminal 101 determines a plurality of skills recommended for the virtual objects through the server 102. The server 102 is a background server of the target application. Further, the server 102 is used to train a long short-term memory network, and the long short-term memory network obtained by training is used to recommend a plurality of skills for the virtual objects based on at least one of the match state information and the historical released skills.

[0087] In some embodiments, the terminal 101 can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart voice interaction device, a smart home appliance, a vehicle-mounted terminal, a flying device, a VR (Virtual Reality) device, an AR (Augmented Reality) device, etc., but is not limited thereto. In some embodiments, the server 102 is an independent server, and can also be a server cluster composed of a plurality of servers or a distributed system, and can also be a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network) services, and basic cloud computing services such as big data and artificial intelligence platforms. In some embodiments, the server 102 mainly undertakes the computing work, and the terminal 101 undertakes the secondary computing work; or the server 102 undertakes the secondary computing service, and the terminal 101 undertakes the main computing work; or the server 102 and the terminal 101 cooperatively compute in a distributed computing architecture.

[0088] Referring to Figure 2 , Figure 2 A flowchart of a skill release method provided by an embodiment of the present application is shown, which includes the following steps.

[0089] 201, the terminal displays a match interface of a virtual match, and the match interface displays a first virtual object participating in the virtual match.

[0090] In the embodiments of the present application, multiple virtual objects can participate in the virtual game, and the multiple virtual objects can fight in the virtual game. The first virtual object is a virtual object controlled by the terminal among the multiple virtual objects. Any virtual object can release a skill to attack other virtual objects.

[0091] 202. The terminal controls the first virtual object to continuously release multiple skills in response to the triggering operation of the skill release function, and the multiple skills are determined based on at least one of game state information of the virtual game and historical released skills of the first virtual object.

[0092] In the embodiments of the present application, the game state information is used to indicate a game state of the virtual game when the skill release function is triggered. The game state information includes state information of the first virtual object and state information of the second virtual object, and the second virtual object is a virtual object fighting with the first virtual object, and the second virtual object can be one or more. The state information of the first virtual object includes but is not limited to the type of the first virtual object, the virtual props used, the skills released, the level in which the first virtual object is located, and the like. The state information of the second virtual object includes but is not limited to the type of the second virtual object, the virtual props used, the skills released, and the like.

[0093] Optionally, the game state information is a game state of the virtual game at a first time, and the first time is a time when the skill release function is triggered. Alternatively, the game state information is a game state of the virtual game in a first time period, and the first time period is a time period before the first time and ending at the first time, such as the preset time period can be 3 seconds. Alternatively, the game state information is a game state of the virtual game at a second time, and the second time is a time when the terminal acquires the game state information before the first time; optionally, the terminal acquires the game state information at a regular time to update the multiple skills at a regular time, so that the multiple skills determined in advance can be released immediately when the skill release function is triggered, thereby improving the interaction efficiency. Alternatively, the game state information is a game state of the virtual game in a second time period, and the second time period is a time period before the second time and ending at the second time.

[0094] In the embodiments of the present application, the historical released skill is used to indicate a skill use habit of the first virtual object, and the historical released skill includes at least one of multiple skills historically continuously released by the first virtual object and a single skill released at a single time; further, the historical released skill can include only the skills released by the first virtual object in the historical virtual game, or can include the skills released by the first virtual object in the historical virtual game and the skills already released in the current virtual game.

[0095] It should be noted that in the embodiments of the present application, the terminal obtains the game state information and the historical released skills of the player with the authorization permission of the player. The authorization interface is displayed on the terminal used by the player, and the authorization interface displays prompt information, an agree control and a disagree control. The prompt information is used to prompt the obtaining of the game state information and the historical released skills of the player. The agree control is used to indicate that the player agrees that the terminal obtains the game state information and the historical released skills of the player. In response to a triggering operation on the agree control, the terminal obtains the game state information and the historical released skills of the player.

[0096] The embodiments of the present application provide a skill releasing method, which can control a first virtual object to continuously release a plurality of skills in response to a triggering operation on a skill releasing function, that is, realizes the function of one-key release of continuous skills. Since the plurality of skills are determined based on at least one of the game state information and the historical released skills, that is, the skills in the continuous skills are intelligently recommended for the player, the player does not need to configure the plurality of skills in the continuous skills in advance, the interactive operation is reduced, and the interactive efficiency is improved. Further, since the plurality of skills are determined based on at least one of the game state information and the historical released skills, the plurality of skills are matched with the current game state of the virtual game and / or the skill use habit of the player, and the accuracy of the recommended skills is ensured, that is, the method improves the interactive efficiency on the basis of ensuring the accuracy of the recommended skills.

[0097] The above Figure 2 The basic flow of the skill releasing method is described below. Figure 3 The skill releasing method is further introduced. Referring to Figure 3 Figure 3 A flowchart of a skill releasing method provided by the embodiments of the present application is shown in FIG. 6, and the embodiments take recommending a skill combination as an example for description. The method comprises the following steps.

[0098] 301. The terminal displays a game interface of a virtual game, and the game interface displays a first virtual object participating in the virtual game. A first continuous skill control is displayed on the game interface, and the first continuous skill control is used to start a continuous skill function. The continuous skill function is used to control the first virtual object to continuously release a plurality of skills in response to a triggering operation on a skill releasing function.

[0099] The game interface is an interface in a virtual scene, and the virtual scene comprises a plurality of virtual objects and at least one virtual game. The virtual objects participating in the same virtual game are multiple. The plurality of virtual objects comprise a first virtual object controlled by the terminal, a virtual object controlled by another terminal, and a virtual object of an NPC (Non-Player Character) type, etc. The plurality of virtual objects participating in the virtual game fight with each other. Each virtual object can attack other virtual objects by releasing a skill or using a virtual prop.​

[0100] In the embodiments of the present application, under the continuous skill function, a plurality of skills to be continuously released can be intelligently recommended for the first virtual object, that is, the continuous skill function is also called intelligent continuous skill function, and the plurality of skills recommended under the continuous skill function can also be called continuous skill.

[0101] In the embodiments of the present application, the display position of the first continuous skill control on the game interface can be set as needed. Optionally, the first continuous skill control is displayed in the vicinity of the skill control to display the same type of function in the same area, thereby facilitating function linkage and interaction, and the skill control is used to release skills. For example, the skill control is displayed in the right area of the game interface, and the first continuous skill control can be displayed in the lower right corner or the upper right corner of the game interface.

[0102] In some embodiments, the first continuous skill control displays a selection button and prompt information of the continuous skill function. In response to a triggering operation on the selection button, the selection button is displayed in a selected state, and the terminal starts the continuous skill function. Similarly, in response to a re-triggering operation on the selection button, the selection button is displayed in a non-selected state, and the terminal exits the continuous skill function. For example, see Figure 4 , Figure 4 is a schematic diagram of a game interface provided by the embodiments of the present application. The first continuous skill control 401 is displayed on the game interface. The first continuous skill control 401 displays a selection button 4011.

[0103] 302, the terminal starts the continuous skill function in response to a triggering operation on the first continuous skill control, and sends a continuous skill request to the server, the continuous skill request being used to request to determine a plurality of skills.

[0104] The triggering operation on the first continuous skill control can be a click operation, a long press operation, a double-click operation, etc., which is not limited here. Optionally, after the terminal starts the continuous skill function, the first continuous skill control is displayed in a changed state, and the changed first continuous skill control is used to indicate that the terminal has started the continuous skill function. For example, the selection button of the first continuous skill control is changed to a selected state.

[0105] In some embodiments, the continuous skill request carries identification information, which is used to indicate at least one of the virtual game and the first virtual object, such as at least one of the game identification of the virtual game and the account information corresponding to the first virtual object, so that the server obtains at least one of the game state information of the virtual game and the historical released skills of the first virtual object based on the identification information.

[0106] The first virtual object is a virtual object controlled by the terminal, i.e., a virtual object controlled by an account logged in by the terminal. A player can control different virtual objects to participate in different virtual matches through the same account. In some embodiments, different virtual objects use different skills, and accordingly, the history released skills only include the skills released by the account when the account historically controls the first virtual object. In other embodiments, different virtual objects can use the same skill, and the history released skills include the skills released by the account when the account historically controls multiple virtual objects.

[0107] In other embodiments, the combo request carries at least one of the match state information and the history released skills, so that the server directly obtains at least one of the match state information and the history released skills based on the combo request.

[0108] In this embodiment, the first combo control is displayed on the match interface, which enables the player to flexibly control whether to use the combo function during the match, i.e., the combo function can be quickly interacted through the match interface, and the player does not need to enter other interfaces to realize the combo function, thereby improving the convenience and efficiency of the interaction.

[0109] In other embodiments, the terminal displays the second combo control on the setting interface of the virtual match, and in response to a triggering operation on the second combo control, the terminal starts the combo function and sends a combo request to the server, or after starting the combo function, the terminal sends a combo request to the server in response to entering the match interface. Further, the terminal sets the combo control on both the match interface and the setting interface, so that the player can flexibly set the combo function as needed, further improving the diversity and flexibility of the interaction.

[0110] It should be noted that before starting the combo function, multiple individual skills can be displayed on the match interface, and in response to a triggering operation on any skill, the terminal controls the first virtual object to release the individual skill. Further, after starting the combo function, multiple individual skills can also be displayed on the match interface, and in response to a triggering operation on any skill, the terminal controls the first virtual object to release the individual skill.

[0111] 303. The server obtains at least one of the match state information of the virtual match and the history released skills of the first virtual object based on the combo request.

[0112] It should be noted that if the server determines multiple skills based on the match state information, the server only obtains the match state information. If the server determines multiple skills based on the history released skills, the server only obtains the history released skills. If the server determines multiple skills based on the match state information and the history released skills, the server obtains the match state information and the history released skills.

[0113] In some embodiments, the match state information includes at least one of a type of a level in which the first virtual object is located, a difficulty value of the level in which the first virtual object is located, a type of the first virtual object, a virtual prop used by the first virtual object, a skill released by the first virtual object, a type of a second virtual object, a virtual prop used by the second virtual object, and a skill released by the second virtual object, the second virtual object being a virtual object that is in a battle with the first virtual object.

[0114] In this embodiment, the match state information includes not only various information of the first virtual object, but also various information of the second virtual object, and the various information can effectively and accurately represent the current match state, and the release of the skill has an important reference effect, and then the multiple skills recommended based on the information are matched with the current match state, and then the first virtual object can effectively cope with the current match state based on the recommended multiple skills, thereby improving the accuracy of skill recommendation.

[0115] Further, the match state information further includes a distance between the first virtual object and the second virtual object, so as to recommend a skill that can cause damage to the second virtual object within the distance for the first virtual object.

[0116] In some embodiments, the historical released skill includes at least one of multiple skills continuously released by the virtual object in a target time period and a single skill released by the virtual object in a single time, and an end point of the target time period is a start point of the virtual match. In this embodiment, the historical released skill includes the multiple skills continuously released and the single skill released in a single time, and the skills can all represent the skill use habit of the player, and then the multiple skills determined based on the historical released skill are in line with the skill use habit of the player, that is, the player has a high degree of interest in the recommended multiple skills and a large use probability, that is, the recommendation effect of the skill is improved, thereby improving the use rate of the player on the intelligent combo function.

[0117] The target time period can be set and changed as needed. Alternatively, the target time period is a fixed time period, such as 1 week. Alternatively, the target time period can be determined from multiple levels of time periods, and the multiple levels of time periods correspond to different lengths of time. For example, the multiple levels of time periods are half a year, one month, one week, or three days, etc.

[0118] Further, the server determines the target time period from the multiple levels of time periods based on the number of times that the first virtual object participates in the virtual match. Wherein, the target time period is determined as a time period with the shortest length from the multiple levels of time periods when the number of times that the first virtual object participates in the virtual match is not less than a preset number of times.

[0119] 304、The server determines the plurality of skills for the first virtual object based on at least one of the game state information and the historical released skills, the plurality of skills being used for continuous release in a case where the skill release function is triggered.

[0120] In some embodiments, the server determines the plurality of skills through a long short-term memory network. In this case, the server inputs at least one of the game state information and the historical released skills into the long short-term memory network, and outputs the plurality of skills through the long short-term memory network, the long short-term memory network being used for determining the plurality of skills for the virtual object based on at least one of the game state information and the historical released skills of the virtual object. The training process of the long short-term memory network can refer to the embodiments of Figure 5 , which will not be described herein again.

[0121] In this case, the plurality of skills are released continuously, and the server also determines the release order of the plurality of skills.

[0122] In this embodiment, the plurality of skills are determined through the long short-term memory network. Since the long short-term memory network is trained based on at least one of the game state information and the historical released skills and the corresponding real skills, the plurality of skills predicted through the long short-term memory network meet the skill use habits of the player and / or can effectively cope with the current game state, thereby improving the accuracy of skill recommendation. In addition, since the long short-term memory network can learn and remember long-term dependencies, the next moment skills having a time sequence relationship with the current game state can be accurately predicted based on the current game state. Further, since the long short-term memory network can learn and remember long-term dependencies, the plurality of skills having a release time sequence relationship can also be determined through the network, thereby ensuring the accuracy of the recommended plurality of skills. In addition, the long short-term memory network can also be used for skill recommendation, thereby improving the convenience and efficiency of skill recommendation.

[0123] In some embodiments, the server determines the plurality of skills based on the game state information, and then inputs the game state information into the long short-term memory network to output the plurality of skills through the long short-term memory network. In other embodiments, the server determines the plurality of skills based on the historical released skills, and then inputs the historical released skills into the long short-term memory network to output the plurality of skills through the long short-term memory network. In other embodiments, the server determines the plurality of skills based on the game state information and the historical released skills, and then inputs the game state information and the historical released skills into the long short-term memory network to output the plurality of skills through the long short-term memory network.

[0124] Optionally, the server converts the input into a feature vector before inputting at least one of the game state information and the historical released skills into the long short-term memory network, thereby facilitating subsequent processing of the long short-term memory network.

[0125] In this embodiment, the skill recommendation by the long short-term memory network is taken as an example for illustration. In other embodiments, the server can also perform skill recommendation in other manners, such as skill recommendation by other deep learning networks.

[0126] In some embodiments, the server also limits the number of recommended skills. For example, the number of skills does not exceed 5, that is, the number of skills is 2-5. Among them, for any skill without a cooling time limit, the skill can appear repeatedly in the skills.

[0127] 305、The server returns the skills to the terminal.

[0128] It should be noted that the recommended skills are released in sequence, and accordingly, the skills returned by the server to the terminal carry release order information, which is used to indicate the release order of the skills.

[0129] In some embodiments, the server also determines a skill effect corresponding to the skills, which is used to indicate the effect that can be achieved by the skills. Accordingly, the server also returns the skill effect to the terminal.

[0130] In this embodiment, the server determining the skills is taken as an example for illustration, and in other embodiments, the terminal itself determines the skills based on at least one of the game state information and the historical released skills. Optionally, the terminal is embedded with a long short-term memory network, and the terminal determines the skills by the long short-term memory network. The process is the same as that of the server determining the skills by the long short-term memory network, and will not be described here.

[0131] 306、The terminal displays the skills on the game interface.

[0132] Among them, the terminal displays the skills arranged on the game interface in the release order.

[0133] Optionally, the skills are arranged in the release order in a clockwise direction around the skill release control; or the skills are arranged in the release order from left to right, and the skills with earlier release order are arranged on the left; or the skills are arranged in the release order from top to bottom, and the skills with earlier release order are arranged on the top.

[0134] In this embodiment, since the skills are released in sequence, the skills are arranged on the game interface in the release order, which further transmits the information of the recommended skills, enables the player to obtain more skill information, improves the richness of information display, and thus can further improve the player's interest in the recommended skills, and promotes the player to use the combo function.

[0135] In this embodiment, the multiple skills of one-key release are displayed on the game interface, which improves the information output richness of the recommended skills and enables the player to know the combo skills in advance. Further, the recommended skills are displayed on the game interface after the combo function is enabled, which enables the player to fully understand the recommended skills, and the player can decide whether to trigger the one-key combo according to the displayed multiple skills, that is, the completeness of the interaction is improved, and the player experience is improved. For example, continuing to refer to Figure 4 In this embodiment, the multiple skills are arranged in the skill release control as the center in the clockwise direction on the game interface according to the release order.

[0136] In some embodiments, the terminal also displays the skill effect of the skill combination formed by the multiple skills on the game interface. In this embodiment, the skill effect of the recommended skills is prompted, which enables the player to further understand the recommended skills, and the one-key combo can be further promoted based on the technical effect guaranteed by the multiple skills, and the probability of the player using the recommended skills is improved.

[0137] Optionally, the skill effect is text information, which is used to describe the effect that can be achieved by the multiple skills, that is, the advantage of the multiple skills. For example, the text information can be “quickly knock down the opponent” and “minimum loss”.

[0138] Optionally, the skill effect is a dynamic demonstration effect, which is used to demonstrate the process of the first virtual object continuously releasing the multiple skills and the effect that can be achieved. In this embodiment, the dynamic demonstration effect is displayed, which enables the player to further understand the recommended skills, and the skill effect is displayed after the demonstration of the skills, which realizes more vivid and smooth output of the skill effect, the player has a deeper understanding of the skill effect based on the demonstrated process, and the player uses the recommended skills is promoted, and the probability of the player using the recommended skills is improved.

[0139] In some embodiments, any of the multiple skills can be modified. In response to the modification operation on any of the multiple skills, the terminal displays the modified multiple skills and the changed skill effect of the modified multiple skills, and the any of the multiple skills is a modified skill. Correspondingly, in response to the trigger operation on the modified multiple skills, the terminal controls the first virtual object to continuously release the modified multiple skills. In this embodiment, the player can manually modify the multiple skills recommended by the intelligent recommendation, so that the modified skills are more in line with the player's wishes, the diversity and flexibility of the interaction are improved, and the completeness of the interaction and the completeness of the information display are improved, and the interaction efficiency is further improved.

[0140] Optionally, the plurality of skills in any skill combination are arranged in a release order on the game interface, and the modifying operation comprises a sequence adjustment operation on any skill. In this embodiment, the player can freely adjust the release order of the plurality of skills, so that the plurality of skills after the release order is modified are more in line with the player's wishes, and the diversity and convenience of the interaction are improved.

[0141] In this embodiment, the modifying operation on any skill further comprises a removal operation, a replacement operation, etc. The removal operation means that the skill is removed from the plurality of skills. The replacement operation means that the skill is replaced by another skill. For example, in response to a trigger operation on the skill, the terminal displays a removal option and a replacement option, and the trigger operation can be a long press operation, a double-click operation, etc. In response to a trigger operation on the removal option, the terminal removes the skill from the plurality of skills. In response to a trigger operation on the replacement option, the terminal displays a plurality of candidate skills, and replaces the skill with the selected candidate skill.

[0142] In the embodiments of the present application, the process of displaying the plurality of skills on the game interface by the terminal based on at least one of the game state information and the historical released skills is realized through the above steps 302-306. In this embodiment, the terminal determines the plurality of skills through the server, so that the powerful computing power of the server is utilized to determine the plurality of skills, which can improve the computing efficiency; and the terminal displays the recommended plurality of skills on the game interface, which increases the amount of information transmission, so that the player can decide whether to use the recommended skills according to the displayed plurality of skills, thereby improving the completeness of the interaction and the player experience.

[0143] 307. The terminal displays a skill release control on the game interface, and in response to a trigger operation on the skill release control, the terminal controls the first virtual object to continuously release the plurality of skills.

[0144] In this embodiment, the skill release control can be a main skill control. In the case where the combo function is not started, the main skill control is used to release the main skill after being triggered, and the main skill is a single skill which can be set as needed, such as a punch skill.

[0145] In some embodiments, the process of releasing the skill further comprises at least one of the following implementation manners. In response to any skill in the plurality of skills being released, the terminal displays a changed appearance of the any skill, and the changed appearance is used to indicate that the any skill has been released. In response to any skill in the plurality of skills being released, the terminal highlights the any skill in the plurality of skills.

[0146] The terminal displays the skill by displaying an identifier of the skill, the identifier being used to indicate the skill. An appearance of the skill, i.e. a display appearance of the identifier, includes at least one of a pattern, a text, etc. The pattern has certain color, shape, etc. Optionally, the appearance of the skill changes, which means at least one of the color, the shape, or the text in the appearance changes. For example, the skill is displayed in a first color before being released, and is changed to a second color after being released, the second color being different from the first color. For example, the skill is displayed in a first shape before being released, and is changed to a second shape after being released, the second shape being different from the first shape. For example, the skill is displayed with a first text before being released, and is changed to a second text after being released, the second text being different from the first text, e.g. the first text is "not released", and the second text is "released".

[0147] The highlighted skill can be at least one of a color, a shape, a text, etc. in the appearance. For example, the color of the skill is displayed in bright color to highlight the skill. Or, the shape of the skill is displayed in a target shape, which is different from the shapes of other skills, to highlight the skill. Or, a text indicating that the skill is being released is displayed on the skill, e.g. the text can be "being released", to highlight the skill. Or, a dynamic effect of the skill is displayed to highlight the skill, e.g. the skill is displayed to shake.

[0148] In this embodiment, the appearance of the skill is changed when the skill has been released, so that the player can know which skills have been released, and the diversity of information display and the integrity of interaction are improved, thereby improving the player experience. The skill being released is highlighted, so that the player can know which skill is being released, and the diversity of information display and the integrity of interaction are improved. Moreover, since the skill being released is highlighted, i.e. the skill being released is intuitively explained, the player's impression of the skill is deepened, the player's interest in the recommended skill is improved, and the player is encouraged to use the recommended skill.

[0149] For example, refer to Figure 7 , Figure 7 is a schematic diagram of a game interface provided in an embodiment of the present application. The skill is displayed by an identifier 701, which includes at least one of a pattern, a text, etc. For the skill being released 702, a changed color is displayed to highlight the skill.

[0150] In this embodiment, the process of controlling the first virtual object to continuously release multiple skills in response to the triggering operation of the skill release function is achieved through the above steps. In other embodiments, the process includes the following steps: in response to a target operation on the game interface, the terminal controls the first virtual object to continuously release multiple skills. The target operation can be set and changed as needed. For example, the target operation can be a long press operation, a sliding operation, or the like. Further, the target operation can also be a composite gesture operation, such as a long press plus sliding continuous gesture operation. In other embodiments, both of the above two implementation manners can achieve the release of multiple skills, thereby improving the diversity and flexibility of the interaction.

[0151] 308、In a case where the server reaches the update time point of the skill at the current time, the server acquires the updated game state information of the virtual game; and based on at least one of the updated game state information and the historical released skill, the server updates the multiple skills.

[0152] In some embodiments, the update time point of the skill is multiple, and the multiple update time points have a preset time gap, such as a time gap of 1 minute between the multiple update time points, that is, the server periodically updates the recommended multiple skills.

[0153] In this embodiment, as the game state in the virtual game changes over time, that is, is updated, in this embodiment, the server periodically acquires the latest game state information in the virtual game, and then re-recommends the multiple skills based on the latest game state information, so that the recommended multiple skills always match the current game state, that is, the timeliness and accuracy of the recommended skills are ensured.

[0154] The process of determining the updated multiple skills by the server based on at least one of the updated game state information and the historical released skill is the same as the process of determining the multiple skills by the server based on at least one of the game state information and the historical released skill in step 304, and will not be described here.

[0155] It should be noted that in a case where the server determines the multiple skills based only on the historical released skill, steps 308-310 are no longer performed, that is, the multiple skills do not need to be updated.

[0156] 309、The server returns the updated multiple skills to the terminal.

[0157] The process of returning the updated multiple skills by the server to the terminal is the same as the process of returning the multiple skills by the server to the terminal in step 305, and will not be described here.

[0158] 310、The terminal displays the updated multiple skills on the game interface.

[0159] The terminal displays the updated plurality of skills, i.e., no longer displays the plurality of skills displayed before. The process of displaying the updated plurality of skills on the game interface by the terminal is the same as the process of displaying the plurality of skills on the game interface by the terminal in step 306, and will not be repeated here.

[0160] 311. The terminal controls the first virtual object to continuously release the updated plurality of skills in response to the triggering operation of the skill release function.

[0161] The process of controlling the first virtual object to release the updated plurality of skills by the terminal is the same as the process of controlling the first virtual object to release the plurality of skills in step 307, and will not be repeated here.

[0162] In some embodiments, the terminal controls the first virtual object to release any skill in the plurality of skills in response to the triggering operation of the any skill. The release operation of the any skill can be a click operation, a double-click operation, a long-press operation, etc., which will not be specifically limited here.

[0163] In this embodiment, the plurality of skills can be released by one key in response to the triggering operation of the skill release control, and the single skill can be triggered in response to the triggering operation of the single skill, so that the displayed plurality of skills not only can play an indicating role, but also can be interacted, thereby the one-key release of the plurality of skills and the single release of the single skill do not conflict, and the flexibility and diversity of the interaction are improved.

[0164] In some embodiments, the server also updates the long short-term memory network in real time. Wherein, after the virtual game ends, the server updates the long short-term memory network based on the game state information of the virtual game and the plurality of skills released by the first virtual object in the virtual game.

[0165] In this embodiment, the data of the virtual game is acquired in real time to update the long short-term memory network, i.e., the parameters of the long short-term memory network are updated online by continuously collecting new data, so that the accuracy of the long short-term memory network is higher.

[0166] In other embodiments, the server acquires the data in the virtual game periodically to update the long short-term memory network. For example, the terminal acquires the data in the virtual game in a week to update the long short-term memory network, which will not be specifically limited here.

[0167] The server updates the historical release skills of the first virtual object based on the multiple skills released by the first virtual object in the virtual match. When there are multiple time points at which the first virtual object continuously releases the multiple skills in the virtual match, a sample skill combination is determined based on the multiple skills continuously released by the first virtual object at each time point, a sample match state information is determined based on the match state information corresponding to each time point, and multiple new sample groups are obtained by combining the updated historical release skills.

[0168] The server updates the long short-term memory network based on the multiple new sample groups, that is, continues to train the long short-term memory network based on the multiple new sample groups. The training process is the same as that of the embodiment of the server based on the multiple sample groups, which will not be described herein again. Figure 4 The embodiment of the server based on the multiple new sample groups is the same as that of the embodiment of the server based on the multiple sample groups, which will not be described herein again.

[0169] In some embodiments, when the terminal does not start the combo function, multiple skills are displayed on the match interface, and in response to a trigger operation on any skill, the terminal controls the first virtual object to release the skill. Optionally, when the terminal does not start the combo function, the selection button on the first combo control is in an unselected state, to indicate that the terminal does not start the combo function. For example, see Figure 8 , Figure 8 is a schematic diagram of a match interface provided by an embodiment of the present application. In the match interface, the selection button of the first combo control 801 is in an unselected state, and multiple skills 802 are displayed on the match interface.

[0170] In some embodiments, the skill release method is implemented through a data collection module, a feature conversion module, a model training and updating module, an action recommendation module, an online adjustment and feedback module, and the like. For example, see Figure 9 , Figure 9is a flowchart of a skill release method provided by an embodiment of the present application. Among them, the controller of the virtual scene obtains the input multiple groups of sample groups, which are collected by the data collection module. The data collection module is the basis of all decisions. This module will regularly or as needed extract important information from the virtual scene. These information includes but is not limited to what skill combination the player used in the past, what skills or equipment the enemy currently uses, the type and difficulty of the current level, etc. Specifically, it includes level information, prop information, skill information, player character information, player operation information, enemy information, etc. The player character information is the type of the sample virtual object, the player operation information is the skill released by the sample virtual object, and the enemy information is the information of the virtual object fighting with the sample virtual object. Then the above data is preprocessed by the feature conversion module, that is, converted into a feature vector. The feature vector can be a numerical vector or a binary vector. Then through the model training and updating module, the LSTM network is trained based on the above feature vector to obtain the action recommendation module, which includes the trained long short-term memory network. In the process of virtual match, in response to the continuous attack request of the terminal one-key continuous attack, the match state information and the history release skill are input into the action recommendation module, and a plurality of skills are output, which are the best action sequence. Finally, after the virtual match ends, through the online adjustment and feedback module, based on the data in the virtual match, the network parameters of the long short-term memory network are updated to perform online adjustment and feedback of the long short-term memory network. With the increase of collected virtual match data, the parameters of the long short-term memory network will also be continuously online adjusted and updated. While continuously collecting new data during system operation, online updating machine learning model parameters, and adjusting the continuous attack recommendation strategy accordingly, the accuracy and satisfaction of skill recommendation can be improved.

[0171] The method provided by the embodiments of the present application is applicable to a virtual scene of a virtual fighting type, a virtual fighting type and a virtual adventure type, and uses current game state information and player habit preferences to realize intelligent continuous attack recommendation in a game process. In the virtual game process, the player can quickly select to manually start or close the one-key continuous attack function in the game interface. In the case of starting the one-key continuous attack function, the background algorithm will recommend a continuous attack operation that meets the current scene for the player according to the current game state information and in combination with machine learning data. The product mainly displays the skills and the number of skills included in the intelligent continuous attack. The number of skills included can be limited according to the scene characteristics, for example, the number of skills included in a skill combination is 2-5, and the same skill can appear repeatedly in a skill combination without a cooling time limit. The player only needs to click the skill release control to use the current intelligent recommended continuous attack. If the player does not need the intelligent continuous attack operation temporarily, the intelligent continuous attack function can be quickly closed, and the conventional manual operation mode can be entered. The switching between the two operation modes is very convenient and smooth, which improves the convenience of interaction.

[0172] In the embodiments of the present application, the current game state information and the personal habits of the player are used to intelligently predict the series of operations that the player is expected to perform, to form intelligent continuous attack recommendation, to facilitate the player to use the continuous attack with one key, to improve the interaction efficiency and to reduce the continuous attack operation threshold.

[0173] Referring to Figure 5 , Figure 5 A flowchart of a training method of a long short-term memory network provided by the embodiments of the present application. The method includes the following steps.

[0174] 501, the server acquires a plurality of sample groups, each sample group including a sample skill combination of a sample virtual object and at least one of sample game state information and a history of released skills of the sample virtual object, the sample skill combination including a plurality of sample skills continuously released by the sample virtual object, and the sample game state information being game state information corresponding to the sample virtual object releasing the plurality of sample skills.

[0175] In some embodiments, the plurality of sample groups includes sample groups with a game result of victory and sample groups with a game result of failure. The sample groups with the game result of victory are positive samples, and the sample groups with the game result of failure are negative samples. In this embodiment, the sample groups with the game result of victory are used as positive samples, and the sample groups with the game result of failure are used as negative samples, which improves the richness of the samples, and the plurality of skills recommended by the trained long short-term memory network can make the game result as victory as possible, thereby improving the player experience, promoting the player to use the continuous attack function, and increasing the use rate of the function.

[0176] 502、The server inputs at least one of the sample pair game state information and the historical release skill in the sample group into the long short-term memory network for each sample group, performs prediction through the long short-term memory network, and obtains a predicted skill combination, the predicted skill combination including a plurality of skills released in succession.

[0177] In some embodiments, the computer device pre-processes the plurality of sample groups, and converts data of the plurality of sample groups into feature vectors through feature engineering, so as to adapt to the long short-term memory network for training and prediction. For example, the data of the distance is converted into a numerical feature vector, and the data of the skill or the prop is converted into a binary feature vector through one-hot encoding.

[0178] After the plurality of sample groups are respectively converted into the feature vectors, the long short-term memory network is trained through the feature vectors. This method is very effective for solving problems with sequential attributes. Since the long short-term memory network can learn and remember long-term dependencies, the next moment skill with a time sequence relationship with the current game state can be accurately predicted. Further, since the long short-term memory network can learn and remember long-term dependencies, a plurality of skills with release time sequences are determined through the network, which can ensure the accuracy of the recommended plurality of skills.

[0179] In other embodiments, after the computer device inputs the sample game state information and the historical skill release features into the long short-term memory network, the long short-term memory network converts these information into feature vectors, which facilitates subsequent processing.

[0180] For example, referring to Figure 6 , Figure 6 is a schematic diagram of a long short-term memory network provided by an embodiment of the present application. The LSTM network includes cell state (Ct), forget gate, input gate, and output gate. The connection between Ct-1 and Ct represents the cell state for storing the memory information at time t (t>0), the circle represents the operation, and the arrow represents the transmission direction of the vector. The various "gate" structures can selectively pass information, and are used to remove or add information in the cell state.

[0181] The forget gate Ft is used to determine which information needs to be forgotten from the cell state. The forget gate takes the output vector Ht-1 of the previous layer and the vector Xt to be input this time as input, obtains an output result through a logistic regression function (sigmoid), and the output result has a value in the interval [0, 1], which represents the probability of forgetting the cell state of the previous layer (i.e., the cell state corresponding to the output vector Ht-1). "1" represents complete retention, and "0" represents complete discard.

[0182] The input gate It includes two parts. First, a part using a sigmoid function; second, a part using a hyperbolic tangent (tanh) function. The first part is used to determine which new information should be added to the cell state. After determining which information to add, the new information needs to be converted into a form that can be added to the cell state by using the tanh function. Illustratively, the cell state is updated from Ct-1 to Ct.

[0183] The output gate Ot determines the output vector Ht based on the content saved by the cell state, i.e., selectively outputs the content saved by the cell state. The output gate also needs to use the sigmoid function to determine which part of the content needs to be output, and then use the tanh function to convert the form of the output content.

[0184] 503、The server trains the long short-term memory network based on the sample skill combination and the predicted skill combination of each of the plurality of sample groups.

[0185] The server determines, for each sample group, a loss value between the sample skill combination and the predicted skill combination of the sample group, and adjusts the parameters of the long short-term memory network based on the loss value.

[0186] In the embodiments of the present application, the server iteratively trains the long short-term memory network based on the sample skill combination and the predicted skill combination of each of the plurality of sample groups until a preset requirement is reached. The preset requirement can be that the loss reaches convergence, or the loss value reaches a preset threshold, or the number of iterations reaches a preset number, which is not limited here.

[0187] In some embodiments, the long short-term memory network is trained based on the sample skill combination and the sample game state information. The server obtains a plurality of sample groups, each of which includes a sample skill combination and sample game state information. For each sample group, the sample game state information in the sample group is input into the long short-term memory network, and a predicted skill combination is obtained by prediction through the long short-term memory network. The long short-term memory network is trained based on the sample skill combination and the predicted skill combination of each of the plurality of sample groups.

[0188] In other embodiments, the long short-term memory network is trained based on the sample skill combination and the historical released skill. The server obtains a plurality of sample groups, each of which includes a sample skill combination and a historical released skill. For each sample group, the historical released skill in the sample group is input into the long short-term memory network, and a predicted skill combination is obtained by prediction through the long short-term memory network. The long short-term memory network is trained based on the sample skill combination and the predicted skill combination of each of the plurality of sample groups.

[0189] In some embodiments, the server obtains a plurality of sample sets, each sample set including a sample skill combination, sample game state information and historical released skills; for each sample set, the sample game state information and the historical released skills in the sample set are input into the long short-term memory network, and the long short-term memory network is used for prediction to obtain a predicted skill combination; and the long short-term memory network is trained based on the sample skill combination and the predicted skill combination of each sample set.

[0190] In the embodiments of the present application, the long short-term memory network is trained based on the sample skill combination and the sample game state information, and the recommended combo skills of the trained long short-term memory network can meet the current game state, thereby improving the accuracy of the recommended skills. The long short-term memory network is trained based on the sample skill combination and the historical released skills, and the recommended combo skills of the trained long short-term memory network meet the skill use habits of the player, thereby improving the accuracy of the recommended skills. The long short-term memory network is trained based on the sample skill combination, the sample game state information and the historical released skills, and the recommended combo skills of the trained long short-term memory network can meet the current game state and the skill use habits of the player, thereby further improving the accuracy of the recommended skills.

[0191] In the embodiments of the present application, the above Figure 3 embodiments are described by taking recommending a skill combination as an example, and the following Figure 10 embodiments are described by taking recommending a plurality of skill combinations as an example. Referring to Figure 10 , Figure 10 is a flowchart of a skill releasing method provided by an embodiment of the present application. The method includes the following steps.

[0192] 1001, the terminal displays a game interface of a virtual game, and the game interface displays a first virtual object participating in the virtual game; a first combo control is displayed on the game interface, and the first combo control is used to start a combo function. The combo function is used to control the first virtual object to continuously release a plurality of skills in response to a trigger operation of a skill releasing function.

[0193] In the embodiments of the present application, step 1001 is the same as step 301, and thus is not described herein.

[0194] 1002, the terminal starts the combo function in response to the trigger operation of the first combo control, and sends a combo request to the server. The combo request is used to request to determine the plurality of skills.

[0195] In the embodiments of the present application, step 1002 is the same as step 302, and thus is not described here again.

[0196] 1003. The server acquires at least one of the game state information of the virtual game and the historical released skills of the first virtual object based on the continuous recruitment request.

[0197] In the embodiments of the present application, step 1003 is the same as step 303, and thus is not described here again.

[0198] 1004. The server determines a plurality of skill combinations for the first virtual object based on at least one of the game state information and the historical released skills, each of the plurality of skill combinations including a plurality of skills for being released continuously in the case that the skill release function is triggered.

[0199] In some embodiments, the server determines the plurality of skill combinations through a long short-term memory network. Wherein, the server inputs at least one of the game state information and the historical released skills into the long short-term memory network, and outputs the plurality of skill combinations through the long short-term memory network.

[0200] Optionally, the long short-term memory network determines a plurality of candidate skill combinations based on at least one of the game state information and the historical released skills, the plurality of candidate skill combinations respectively have a probability value, and the plurality of candidate skill combinations with the probability values ranked in the front of a preset bit are output as the plurality of skill combinations. Wherein, the probability value of each candidate skill combination is used to indicate the probability of the candidate skill combination being recommended. Further, since the skills are recommended based on the skill use habits of the player, the probability value also indicates the probability of the candidate skill combination being used after being recommended to the player.

[0201] In this embodiment, since the plurality of skills in each skill combination are released continuously, correspondingly, the server also determines the release order of the plurality of skills in each skill combination.

[0202] 1005. The server returns the plurality of skill combinations to the terminal.

[0203] It should be noted that the plurality of skills in each skill combination are released continuously, correspondingly, the plurality of skill combinations returned by the server to the terminal respectively carry release order information, and the release order information of each skill combination is used to indicate the release order of the plurality of skills in the skill combination.

[0204] In some embodiments, the server also determines the skill effects of the plurality of skill combinations respectively, and the skill effect of any of the plurality of skill combinations is used to indicate the effect that can be achieved by the plurality of skills in the any of the plurality of skill combinations. Correspondingly, the server also returns the skill effects of the plurality of skill combinations to the terminal.

[0205] 1006. The terminal displays the plurality of skill combinations on the game interface.

[0206] In some embodiments, the plurality of skills in any skill combination are arranged in sequence according to the release order on the game interface, which is the same as the arrangement in step 306, for example, the plurality of skills are arranged from left to right according to the release order, or the plurality of skills are arranged from top to bottom according to the release order, which will not be repeated here.

[0207] In some embodiments, the terminal also displays the skill effects of the plurality of skill combinations on the game interface. By displaying the skill effects of the plurality of skill combinations, the amount of information transmission of the plurality of skill combinations is increased, so that the player can further understand the plurality of skill combinations, and the player can freely select the skill combination according to the prompted skill effects, thereby improving the richness of information display and the diversity of interaction.

[0208] In this embodiment, the skill effects are the same as in step 306, which will not be repeated here.

[0209] In some embodiments, any skill in any skill combination can be modified. In response to a modification operation on any skill in any skill combination, the modified any skill combination and the skill effects of the modified any skill combination after the change are displayed; in response to a trigger operation on the modified any skill combination, the first virtual object is controlled to continuously release the plurality of skills in the modified any skill combination.

[0210] Optionally, the plurality of skills in any skill combination are arranged in sequence according to the release order on the game interface, and the modification operation includes a sequence adjustment operation on any skill.

[0211] In this embodiment, the modification operation on any skill also includes a removal operation, a replacement operation, etc. The removal operation means removing the skill from the skill combination. The replacement operation means replacing the skill with other skills. For example, in response to a trigger operation on the skill, the terminal displays a removal option and a replacement option. The trigger operation can be a long press operation, a double-click operation, etc.; in response to a trigger operation on the removal option, the terminal removes the skill from the skill combination. In response to a trigger operation on the replacement option, the terminal displays a plurality of candidate skills, and replaces the skill with the selected candidate skill.

[0212] 1007、In response to a trigger operation on any skill combination in the plurality of skill combinations, the terminal controls the first virtual object to continuously release the plurality of skills in the any skill combination.

[0213] In this embodiment, the trigger operation on any skill combination can be a trigger operation on the display area of the skill combination, which can be a single-click operation, a double-click operation, a long press operation, etc., which will not be specifically limited here.

[0214] In the embodiment of the present application, the process in which the terminal controls the first virtual object to continuously release the multiple skills in the any one skill combination is the same as the process in which the terminal controls the first virtual object to continuously release the multiple skills in step 307, and thus is not described herein again.

[0215] In the embodiment of the present application, by displaying the multiple skill combinations on the game interface, that is, recommending the multiple skill combinations to the player, the diversity of the player's selection can be improved, so that the player can select the most suitable skill combination according to the needs, and thus the probability that the recommended combo skills meet the player's preferences can be improved, which can promote the player to use the combo function, that is, improve the player's usage rate of the recommended skills.

[0216] 1008、In a case where the server determines that the current time reaches the update time point of the skill, the server acquires the updated game state information of the virtual game; and based on at least one of the updated game state information and the historical released skill, the server updates the multiple skills in the multiple skill combinations.

[0217] In the embodiment of the present application, the update time point of the skill is the same as the update time point in step 308, and thus is not described herein again. The process in which the server determines the updated multiple skill combinations based on at least one of the updated game state information and the historical released skill is the same as the process in which the server determines the multiple skill combinations based on at least one of the game state information and the historical released skill in step 1004, and thus is not described herein again.

[0218] It should be noted that, in a case where the server determines the multiple skill combinations based on only the historical released skill, steps 1008-1010 are no longer performed, that is, the multiple skill combinations do not need to be updated.

[0219] 1009、The server returns the updated multiple skill combinations to the terminal.

[0220] The process in which the server returns the updated multiple skill combinations to the terminal is the same as the process in which the server returns the multiple skill combinations to the terminal in step 1005, and thus is not described herein again.

[0221] 1010、The terminal displays the updated multiple skill combinations on the game interface.

[0222] The terminal displays the updated multiple skill combinations, that is, the previously displayed multiple skill combinations are no longer displayed. The process in which the terminal displays the updated multiple skill combinations on the game interface is the same as the process in which the terminal displays the multiple skill combinations on the game interface in step 1006, and thus is not described herein again.

[0223] 1011、The terminal controls the first virtual object to continuously release the multiple skills in the any one updated skill combination in response to a triggering operation on the any one updated skill combination.

[0224] In the process step 307, the terminal controls the first virtual object to continuously release a plurality of skills in any skill combination. The process of the terminal controlling the first virtual object to continuously release a plurality of skills in any skill combination is the same as that in the process step 307, and will not be described here.

[0225] In the related art, the one-key combo function is implemented, and the following problems exist. First, the setting operation is tedious. Among them, the player needs to define the combo sequence on the setting interface through frequent clicking, dragging and other operations, and the entire operation process is relatively tedious. Second, the threshold is high. Among them, the player needs to be familiar with each skill, and needs to know the influence effect of the function corresponding to each skill button and the release sequence, and needs the player to have a deep understanding of the virtual scene content, and the one-key combo function is originally to help the player to simplify the operation and reduce the difficulty, but in this way, the threshold of the function setting is relatively high. Third, the fixed skills lack flexibility. Once the plurality of skills in the combo are set, the player clicks to release the one-key combo in the virtual game, and the plurality of skills are fixedly released. However, the plurality of skills are not necessarily suitable for all game scenes, and the player often needs to use different combo skills in different levels. The fixed combo scheme lacks flexibility, and the player needs to repeatedly reset or frequently switch.

[0226] In the embodiments of the present application, there is no need for manual and tedious setting. The intelligent combo is automatically generated according to the use scene and recommended to the player, and the player does not need to set through tedious operation in advance, and can use the combo recommended by the system. Moreover, the threshold is greatly reduced. Among them, for novice players, there is no need to deeply understand the combination of each skill, and the combo skill recommended by the algorithm can be used one-key quickly, which greatly reduces the threshold of the combo, and everyone can use it. Moreover, it is flexibly matched with the current demand. Among them, the combo is intelligently recommended according to the game environment and habits of the player, so that the combo is more flexible and can cope with more rich, variable and complex game scenes.

[0227] The method provided by the embodiments of the present application has the following effects, but is not limited to the following. First, the operation is simplified. The most direct benefit of the method is that the operation process of the player executing a complex combo is greatly simplified, that is, the process of manually combining various skill keys is changed to releasing the combo combination for the game by only one key. Second, the threshold is lowered. For new players, it is usually difficult for them to effectively use the various attack modes provided by the virtual scene before they are familiar with the rules and master the skills. The function provided by the method can help them break through the level more efficiently during the learning process, and quickly understand and master how to play the role by observing the recommended combo. Third, the multi-environment adaptability. Since the online learning strategy is adopted, the system is not limited to fixed scenes, fixed enemy types or specific conditions to work well, but has the ability to analyze and generate corresponding guidance suggestions in any case. Fourth, the game experience is improved. For some elderly players or users with weak reaction ability, this function can help them maintain the upward progress rhythm, thereby feeling the satisfaction and achievement brought by the game; in addition, it also avoids frustration caused by long-term repeated trial and error, and improves the overall smoothness and tension of the game. Fifth, the participation and retention rate are increased. The role enhancement, new skill acquisition and the like may affect the attack mode judgment basis, at which time the player has the opportunity to re-enter the game and use the function, thereby improving the participation and prolonging the stay time in the virtual game. Sixth, the accuracy is high. By obtaining the data in the virtual game after the virtual game ends to update the long-term and short-term memory network, deep mining is realized in the subsequent to provide more accurate strategy improvement scheme, thereby improving the accuracy of the recommended skills.

[0228] Figure 11 is a block diagram of a skill release device according to an embodiment of the present application. Referring to Figure 11 , the device comprises:

[0229] The display module 1101 is configured to display a game interface of a virtual game, and the game interface displays a first virtual object participating in the virtual game.

[0230] The release module 1102 is configured to control the first virtual object to continuously release a plurality of skills in response to a triggering operation of a skill release function, and the plurality of skills are determined based on at least one of game state information of the virtual game and historical released skills of the first virtual object.

[0231] In some embodiments, the display module 1101 is further configured to:

[0232] display at least one skill combination on the game interface based on at least one of the game state information and the historical released skills, and each skill combination comprises a plurality of skills;

[0233] The releasing module 1102 is configured to:

[0234] In response to the triggering operation on any of the at least one skill combination, the first virtual object is controlled to successively release the multiple skills in any of the at least one skill combination.

[0235] In some embodiments, the display module 1101 is further configured to:

[0236] The skill effects of any of the at least one skill combination are displayed on the game interface, and the skill effect of any of the at least one skill combination is used to indicate the effects that can be achieved by the multiple skills in any of the at least one skill combination.

[0237] In some embodiments, the display module 1101 is further configured to:

[0238] In response to the modification operation on any of the skills in any of the at least one skill combination, the modified any of the at least one skill combination and the skill effect of the modified any of the at least one skill combination are displayed.

[0239] The releasing module 1102 is further configured to:

[0240] In response to the triggering operation on the modified any of the at least one skill combination, the first virtual object is controlled to successively release the multiple skills in the modified any of the at least one skill combination.

[0241] In some embodiments, the multiple skills in any of the at least one skill combination are arranged in the releasing order on the game interface, and the modification operation includes a sequence adjustment operation on any of the skills.

[0242] In some embodiments, the skill effect is a dynamic demonstration effect, and the dynamic demonstration effect is used to demonstrate the process of the first virtual object successively releasing the multiple skills and the effects that can be achieved.

[0243] In some embodiments, the display module 1101 is further configured to perform at least one of the following:

[0244] In response to any of the multiple skills being released, the appearance of any of the multiple skills is displayed as being changed, and the changed appearance is used to indicate that any of the multiple skills is released.

[0245] In response to any of the multiple skills being released, any of the multiple skills is highlighted.

[0246] In some embodiments, the releasing module 1102 is further configured to:

[0247] In response to the triggering operation on any of the multiple skills, the first virtual object is controlled to release any of the multiple skills.

[0248] In some embodiments, the display module 1101 is further configured to perform at least one of the following:

[0249] The first combo control is displayed in the game interface, and in response to a triggering operation on the first combo control, a combo function is started, and the combo function is used to control the first virtual object to continuously release a plurality of skills in response to a triggering operation on a skill release function;

[0250] The second combo control is displayed on the setting interface of the virtual game, and in response to a triggering operation on the second combo control, the combo function is started.

[0251] In some embodiments, the game state information includes at least one of a type of a level in which the first virtual object is located, a difficulty value of the level in which the first virtual object is located, a type of the first virtual object, a virtual prop used by the first virtual object, a skill released by the first virtual object, a type of a second virtual object, a virtual prop used by the second virtual object, and a skill released by the second virtual object, the second virtual object being a virtual object that is in a battle with the first virtual object.

[0252] In some embodiments, the historical release skill includes at least one of a plurality of skills continuously released by the virtual object in a target time period and a single skill released by the virtual object in a single time.

[0253] The embodiments of the present application provide a skill release device, which can control the first virtual object to continuously release a plurality of skills in response to a triggering operation on a skill release function, that is, a one-key combo release function is realized; and since the plurality of skills are determined based on at least one of game state information and a historical release skill, that is, the skills in the combo are intelligently recommended to the player, the player does not need to configure the plurality of skills in the combo in advance, the interactive operation is reduced, and the interactive efficiency is improved. Further, since the plurality of skills are determined based on at least one of the game state information and the historical release skill, the plurality of skills are matched with a current game state of the virtual game and / or a skill use habit of the player, and the accuracy of the recommended skills is ensured, that is, the device improves the interactive efficiency on the basis of ensuring the accuracy of the recommended skills.

[0254] It should be noted that: the skill release device provided in the above embodiments is only exemplified by the division of the above functional modules during model training, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the skill release device and the skill release method provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0255] Figure 12 is a block diagram of a skill determination device according to an embodiment of the present application. Referring to Figure 12 , the device comprises:

[0256] The obtaining module 1201 is configured to obtain at least one of game state information of the virtual game and historical released skills of a first virtual object participating in the virtual game during the process in which the terminal plays the virtual game.

[0257] The determining module 1202 is configured to determine, based on at least one of the game state information and the historical released skills, a plurality of skills for the first virtual object, the plurality of skills being used for continuous release in a case where a skill release function is triggered.

[0258] In some embodiments, the obtaining module 1201 is further configured to:

[0259] In a case where the current time reaches an update time point of the skill, the obtaining module 1201 is further configured to obtain updated game state information of the virtual game.

[0260] The apparatus further includes:

[0261] The first updating module is configured to update the plurality of skills based on at least one of the updated game state information and the historical released skills.

[0262] The returning module is configured to return the updated plurality of skills to the terminal, and the terminal is configured to control the first virtual object to continuously release the updated plurality of skills in response to a triggering operation of the skill release function.

[0263] In some embodiments, the determining module 1202 is configured to:

[0264] The determining module 1202 is configured to input at least one of the game state information and the historical released skills into a long short-term memory network, and output the plurality of skills through the long short-term memory network, the long short-term memory network being configured to determine the plurality of skills for the virtual object based on at least one of the game state information and the historical released skills of the virtual object.

[0265] In some embodiments, the apparatus further includes a second updating module configured to:

[0266] After the virtual game ends, the second updating module is configured to update the long short-term memory network based on game state information of the virtual game and the plurality of skills released by the first virtual object in the virtual game.

[0267] In some embodiments, the apparatus further includes a training module configured to:

[0268] The training module is configured to obtain a plurality of groups of samples, each group of samples including at least one of sample game state information and historical released skills of a sample virtual object, and a sample skill combination of the sample virtual object, the sample skill combination including a plurality of sample skills continuously released by the sample virtual object, and the sample game state information being game state information corresponding to the release of the plurality of sample skills by the sample virtual object.

[0269] For each sample group, at least one of the game state information and the historical release skills of the samples in the sample group is input into the long short-term memory network, the long short-term memory network is used for prediction, and a predicted skill combination is obtained, the predicted skill combination including a plurality of skills released continuously.

[0270] The long short-term memory network is trained based on the sample skill combinations and the predicted skill combinations of the plurality of sample groups.

[0271] In some embodiments, the game state information includes at least one of a type of a level in which the first virtual object is located, a difficulty value of the level in which the first virtual object is located, a type of the first virtual object, a virtual prop used by the first virtual object, a skill released by the first virtual object, a type of a second virtual object, a virtual prop used by the second virtual object, and a skill released by the second virtual object, the second virtual object being a virtual object that is in a battle with the first virtual object.

[0272] In some embodiments, the historical release skills include at least one of a plurality of skills released continuously by the virtual object in a target time period and a single skill released once, an end point of the target time period being a start point of the virtual game.

[0273] It should be noted that the skill determination apparatus provided in the above embodiments is only used as an example to illustrate the division of the above functional modules in the model training, and in actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the functions described above. In addition, the skill determination apparatus and the skill determination method provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0274] In the embodiments of the present application, the computer device can be a terminal or a server. When the computer device is a terminal, the terminal is used as an execution subject to implement the technical solutions provided in the embodiments of the present application. When the computer device is a server, the server is used as an execution subject to implement the technical solutions provided in the embodiments of the present application. Alternatively, the technical solutions provided in the present application are implemented through the interaction between the terminal and the server, and the embodiments of the present application do not limit this.

[0275] Figure 13 A structural block diagram of a terminal 1300 provided in an example embodiment of the present application is shown.

[0276] Generally, the terminal 1300 includes a processor 1301 and a memory 1302.

[0277] The processor 1301 can include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 1301 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), a PLA (Programmable Logic Array). The processor 1301 can also include a main processor and a coprocessor, the main processor being a processor for processing data in an awake state, also known as a CPU (Central Processing Unit), and the coprocessor being a low-power processor for processing data in a standby state. In some embodiments, the processor 1301 can be integrated with a GPU (Graphics Processing Unit) for rendering and drawing content required to be displayed by the display screen. In some embodiments, the processor 1301 can also include an AI (Artificial Intelligence) processor for processing machine learning related computing operations.

[0278] The memory 1302 can include one or more computer-readable storage media that can be non-transitory. The memory 1302 can also include a high-speed random access memory, and a nonvolatile memory such as one or more disk storage devices, flash storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1302 is used to store at least one program code for being executed by the processor 1301 to implement the skill release method or the skill determination method provided by the method embodiments in the present application.

[0279] In some embodiments, the terminal 1300 can also optionally include a peripheral device interface 1303 and at least one peripheral device. The processor 1301, the memory 1302, and the peripheral device interface 1303 can be connected through a bus or a signal line. Each peripheral device can be connected to the peripheral device interface 1303 through a bus, a signal line, or a circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 1304, a display screen 1305, a camera assembly 1306, an audio circuit 1307, and a power supply 1308.

[0280] The peripheral interface 1303 can be used to connect at least one I / O (Input / Output) related peripheral device to the processor 1301 and the memory 1302. In some embodiments, the processor 1301, the memory 1302 and the peripheral interface 1303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1301, the memory 1302 and the peripheral interface 1303 can be implemented on a separate chip or circuit board, and the present embodiments are not limited in this regard.

[0281] The radio frequency circuit 1304 is configured to receive and send RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1304 communicates with communication networks and other communication devices through electromagnetic signals. The radio frequency circuit 1304 converts electric signals into electromagnetic signals for transmission, or converts electromagnetic signals received into electric signals. Optionally, the radio frequency circuit 1304 includes an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and the like. The radio frequency circuit 1304 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network, and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1304 can also include NFC (Near Field Communication) related circuitry, and the present application is not limited in this regard.

[0282] The display screen 1305 is configured to display a UI (User Interface). The UI can include graphics, text, icons, video, and any combination thereof. When the display screen 1305 is a touch display screen, the display screen 1305 is further configured to capture touch signals on or above the surface of the display screen 1305. The touch signals can be input to the processor 1301 as control signals for processing. In this case, the display screen 1305 can also be configured to provide virtual buttons and / or virtual keyboard, also known as soft buttons and / or soft keyboard. In some embodiments, the display screen 1305 can be one, disposed on the front panel of the terminal 1300; in other embodiments, the display screen 1305 can be at least two, respectively disposed on different surfaces of the terminal 1300 or in a folding design; in other embodiments, the display screen 1305 can be a flexible display screen, disposed on a curved surface or a folding surface of the terminal 1300. Even, the display screen 1305 can also be disposed in an irregular shape, i.e., a special-shaped screen. The display screen 1305 can be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc.

[0283] The camera assembly 1306 is configured to capture images or videos. Optionally, the camera assembly 1306 includes a front camera and a rear camera. Typically, the front camera is disposed on the front panel of the terminal, and the rear camera is disposed on the back of the terminal. In some embodiments, the rear camera is at least two, which are any one of a main camera, a depth-of-field camera, a wide-angle camera, and a telephoto camera, to realize the background blur function by fusing the main camera and the depth-of-field camera, the panoramic shooting and VR (Virtual Reality) shooting function by fusing the main camera and the wide-angle camera, or other fusion shooting functions. In some embodiments, the camera assembly 1306 can further include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. The dual-color temperature flash refers to the combination of a warm light flash and a cold light flash, which can be used for light compensation under different color temperatures.

[0284] The audio circuit 1307 can include a microphone and a speaker. The microphone is used to collect sound waves of the user and the environment, and convert the sound waves into an electrical signal input to the processor 1301 for processing, or input to the radio frequency circuit 1304 to realize voice communication. For the purpose of stereo sound collection or noise reduction, the microphone can be multiple, respectively arranged at different parts of the terminal 1300. The microphone can also be an array microphone or an omnidirectional collection type microphone. The speaker is used to convert the electrical signal from the processor 1301 or the radio frequency circuit 1304 into sound waves. The speaker can be a traditional diaphragm speaker, or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, not only can it convert electrical signals into sound waves that humans can hear, but it can also convert electrical signals into sound waves that humans cannot hear for ranging purposes. In some embodiments, the audio circuit 1307 can also include a headphone jack.

[0285] The power supply 1308 is used to supply power to each component in the terminal 1300. The power supply 1308 can be alternating current, direct current, disposable battery or rechargeable battery. When the power supply 1308 includes a rechargeable battery, the rechargeable battery can be a wired charging battery or a wireless charging battery. The wired charging battery is a battery charged through a wired line, and the wireless charging battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0286] In some embodiments, the terminal 1300 further includes one or more sensors 1309. The one or more sensors 1309 include, but are not limited to, an acceleration sensor 1310, a gyroscope sensor 1311, a pressure sensor 1312, an optical sensor 1313, and a proximity sensor 1314.

[0287] The acceleration sensor 1310 can detect the acceleration magnitude in three coordinate axes of the coordinate system established by the terminal 1300. For example, the acceleration sensor 1310 can be used to detect the components of the gravitational acceleration in three coordinate axes. The processor 1301 can control the display screen 1305 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 1310. The acceleration sensor 1310 can also be used for game or user motion data collection.

[0288] The gyroscope sensor 1311 can detect the body direction and rotation angle of the terminal 1300, and the gyroscope sensor 1311 can collect 3D actions of the user on the terminal 1300 in cooperation with the acceleration sensor 1310. The processor 1301 can realize the following functions according to the data collected by the gyroscope sensor 1311: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization when shooting, game control, and inertial navigation.

[0289] The pressure sensor 1312 can be disposed on the side bezel of the terminal 1300 and / or on the lower layer of the display screen 1305. When the pressure sensor 1312 is disposed on the side bezel of the terminal 1300, it can detect the user's grip signal on the terminal 1300, and the processor 1301 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1312. When the pressure sensor 1312 is disposed on the lower layer of the display screen 1305, the processor 1301 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 1305. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0290] Optical sensor 1313 is used to collect ambient light intensity. In one embodiment, processor 1301 can control the display brightness of display screen 1305 based on the ambient light intensity collected by optical sensor 1313. Specifically, when the ambient light intensity is high, the display brightness of display screen 1305 is increased; when the ambient light intensity is low, the display brightness of display screen 1305 is decreased. In another embodiment, processor 1301 can also dynamically adjust the shooting parameters of camera assembly 1306 based on the ambient light intensity collected by optical sensor 1313.

[0291] The proximity sensor 1314, also known as a distance sensor, is typically located on the front panel of the terminal 1300. The proximity sensor 1314 is used to detect the distance between the user and the front of the terminal 1300. In one embodiment, when the proximity sensor 1314 detects that the distance between the user and the front of the terminal 1300 is gradually decreasing, the processor 1301 controls the display screen 1305 to switch from a screen-on state to a screen-off state; when the proximity sensor 1314 detects that the distance between the user and the front of the terminal 1300 is gradually increasing, the processor 1301 controls the display screen 1305 to switch from a screen-off state to a screen-on state.

[0292] Those skilled in the art will understand that Figure 13 The structure shown does not constitute a limitation on terminal 1300 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0293] Figure 14is a structural schematic diagram of a server provided by an embodiment of the present application. The server 1400 can have great differences due to different configurations or performances, and can include one or more processors (Central Processing Units, CPUs) 1401 and one or more memories 1402. The memory 1402 is configured to store executable program codes, and the processor 1401 is configured to execute the executable program codes to implement the skill release method or the skill determination method provided by the various method embodiments. Of course, the server can also have a wired or wireless network interface, a keyboard, an input and output interface, and other components for realizing the functions of the device, and details are not described herein.

[0294] The embodiment of the present application further provides a computer readable storage medium, and at least one program is stored in the computer readable storage medium. The at least one program is loaded and executed by a processor to implement the skill release method or the skill determination method in any of the implementation manners.

[0295] The embodiment of the present application further provides a computer program product, and the computer program product includes at least one program. The at least one program is stored in a computer readable storage medium. A processor of a computer device reads the at least one program from the computer readable storage medium. The processor executes the at least one program, so that the computer device executes the skill release method or the skill determination method in any of the implementation manners.

[0296] In some embodiments, the computer program product related to the embodiment of the present application can be deployed on one computer device for execution, or on multiple computer devices located in one place for execution, or on multiple computer devices distributed in multiple places and interconnected through a communication network for execution. The multiple computer devices distributed in multiple places and interconnected through a communication network can constitute a blockchain system.

[0297] All the optional technical solutions described above can be combined to form optional embodiments of the present application, and details are not described herein. The above is only an optional embodiment of the present application, and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A skill release method, characterized by, The method comprises: displaying a game interface of a virtual game, the game interface displaying a first virtual object participating in the virtual game; in response to a trigger operation on a skill release function, controlling the first virtual object to continuously release a plurality of skills, the plurality of skills being determined based on at least one of game state information of the virtual game and historical released skills of the first virtual object.

2. The method of claim 1, wherein, The method further comprises: based on at least one of the game state information and the historical released skills, displaying at least one skill combination on the game interface, each skill combination comprising a plurality of skills; the response to the trigger operation on the skill release function, controlling the first virtual object to continuously release a plurality of skills, comprises: in response to a trigger operation on any skill combination of the at least one skill combination, controlling the first virtual object to continuously release a plurality of skills in the any skill combination.

3. The method of claim 2, wherein, The method further comprises: displaying skill effects of the at least one skill combination respectively on the game interface, the skill effects of any skill combination being used to indicate effects that can be achieved by the plurality of skills in the any skill combination.

4. The method of claim 3, wherein, The method further comprises: in response to a modification operation on any skill in any skill combination, displaying the modified any skill combination and the skill effects of the modified any skill combination; in response to a trigger operation on the modified any skill combination, controlling the first virtual object to continuously release a plurality of skills in the modified any skill combination.

5. The method of claim 4, wherein, The plurality of skills in any skill combination are arranged in sequence according to a release order on the game interface, and the modification operation comprises an order adjustment operation on the any skill.

6. The method of claim 3, wherein, The skill effects are dynamic demonstration effects, which are used to demonstrate a process of continuously releasing a plurality of skills by the first virtual object and effects that can be achieved.

7. The method of claim 2, wherein, The method further comprises at least one of: in response to any skill of the plurality of skills being released, displaying a changed appearance of the any skill, the changed appearance being used to indicate that the any skill has been released; in response to any skill of the plurality of skills being released, highlighting the any skill of the plurality of skills.

8. The method of claim 2, wherein, The method further comprises: in response to a trigger operation on any skill of the plurality of skills, controlling the first virtual object to release the any skill.

9. The method of claim 1, wherein, The method further comprises at least one of: displaying a first combo control in the game interface, in response to a trigger operation on the first combo control, starting a combo function, the combo function being used to control the first virtual object to continuously release a plurality of skills in response to a trigger operation on the skill release function; displaying a second combo control on a setting interface of the virtual game, in response to a trigger operation on the second combo control, starting the combo function.

10. The method of claim 1, wherein, The game state information includes at least one of a type of a level in which the first virtual object is located, a difficulty value of the level in which the first virtual object is located, a type of the first virtual object, a virtual prop used by the first virtual object, a skill released by the first virtual object, a type of a second virtual object, a virtual prop used by the second virtual object, and a skill released by the second virtual object, the second virtual object being a virtual object that is in a battle with the first virtual object.

11. The method of claim 1, wherein, The historical released skill includes at least one of a plurality of skills that are continuously released by the virtual object in a target time period and a single skill that is released once, an end point of the target time period being a start point of the virtual game.

12. A skill determination method characterized by comprising: The method includes: During a process in which a terminal plays a virtual game, obtaining at least one of game state information of the virtual game and a historical released skill of a first virtual object participating in the virtual game; Based on the at least one of the game state information and the historical released skill, determining a plurality of skills for the first virtual object, the plurality of skills being used for continuous release in a case where a skill release function is triggered.

13. The method of claim 12, wherein, The method further includes: In a case where a current time reaches an update time point of a skill, obtaining updated game state information of the virtual game; Based on the updated game state information and the at least one of the historical released skill, updating the plurality of skills; Returning the updated plurality of skills to the terminal, the terminal being used to control the first virtual object to continuously release the updated plurality of skills in response to a triggering operation on the skill release function.

14. The method of claim 12, wherein, The method further includes: In a case where a current time reaches an update time point of a skill, obtaining updated game state information of the virtual game; 15. The method of claim 14, wherein, Based on the updated game state information and the at least one of the historical released skill, updating the plurality of skills; Returning the updated plurality of skills to the terminal, the terminal being used to control the first virtual object to continuously release the updated plurality of skills in response to a triggering operation on the skill release function.

16. The method of claim 14, wherein, The method further includes: After the virtual game ends, based on the game state information of the virtual game and a plurality of skills released by the first virtual object in the virtual game, updating the long short-term memory network. The training process of the long short-term memory network includes: Obtaining a plurality of sample groups, each sample group including a sample skill combination of a sample virtual object and at least one of sample game state information and a historical released skill of the sample virtual object, the sample skill combination including a plurality of sample skills that are continuously released by the sample virtual object, the sample game state information being game state information corresponding to a case where the plurality of sample skills are released by the sample virtual object; For each sample group, inputting the at least one of the sample game state information and the historical released skill in the sample group into the long short-term memory network, and performing prediction by the long short-term memory network to obtain a predicted skill combination, the predicted skill combination including a plurality of skills that are continuously released; The long short-term memory network is trained based on the respective sample skill combinations and the predicted skill combinations of the multiple groups of sample groups.

17. The method of claim 12, wherein, The game state information includes at least one of a type of a level in which the first virtual object is located, a difficulty value of the level in which the first virtual object is located, a type of the first virtual object, a virtual prop used by the first virtual object, a skill released by the first virtual object, a type of a second virtual object, a virtual prop used by the second virtual object, and a skill released by the second virtual object, the second virtual object being a virtual object that is in a battle with the first virtual object.

18. The method of claim 12, wherein, The historical released skills include at least one of a plurality of skills that are continuously released by the virtual object in a target time period and a single skill that is released once, an end point of the target time period being a start point of the virtual game.

19. A skill release device characterized by, The apparatus includes: a display module configured to display a game interface of a virtual game, the game interface displaying a first virtual object participating in the virtual game; a release module configured to, in response to a triggering operation of a skill release function, control the first virtual object to continuously release a plurality of skills, the plurality of skills being determined based on at least one of game state information of the virtual game and historical released skills of the first virtual object.

20. A skill determination apparatus characterized by comprising: The apparatus includes: an acquisition module configured to, in a process in which a terminal is playing a virtual game, acquire at least one of game state information of the virtual game and historical released skills of a first virtual object participating in the virtual game; a determination module configured to determine, based on the at least one of the game state information and the historical released skills, a plurality of skills for the first virtual object, the plurality of skills being used for continuous release in a case where a skill release function is triggered.

21. A computer device, comprising: The computer device includes a processor and a memory, the memory being used to store at least one program, the at least one program being loaded and executed by the processor to perform the skill release method of any one of claims 1-11 or the skill determination method of any one of claims 12-18.

22. A computer-readable storage medium, characterized in that, The computer readable storage medium is used to store at least one program, the at least one program being used to perform the skill release method of any one of claims 1-11 or the skill determination method of any one of claims 12-18.

23. A computer program product, characterised in that, The computer program product includes at least one program, the at least one program being stored in a computer readable storage medium, a processor of a computer device reading the at least one program from the computer readable storage medium, and the processor executing the at least one program to cause the computer device to perform the skill release method of any one of claims 1-11 or the skill determination method of any one of claims 12-18.

Images