Prompt content generation method and device, storage medium, equipment and program product

Abstract

The present disclosure discloses a generation method of prompt content, a prompt content generation device, a computer readable storage medium, a computer device and a computer program product. The generation method comprises: displaying a current game picture corresponding to a game video on a game client; receiving a constraint condition set through the game client, the constraint condition at least including selection of an active role, selection of a passive role and selection of a backtracking round in the game video, the backtracking round being used to determine N historical rounds backtracking from a current time, N being an integer greater than or equal to 1; analyzing original video data corresponding to the N historical rounds in the game video to obtain analysis data, wherein the analysis data at least includes behavior data of the active role in the N historical rounds; and generating prompt content corresponding to the current game picture according to the analysis data.

Description

Technical Field

[0001] This disclosure relates to the field of prompt content generation technology, specifically to a method for generating prompt content, a prompt content generation apparatus, a computer-readable storage medium, a computer device, and a computer program product. Background Technology

[0002] In the process of data processing of game videos on game clients, it is usually necessary to parse massive amounts of raw video data to generate prompts for review or auxiliary analysis. Because the raw video data corresponding to game videos is enormous and contains complex information dimensions, existing technologies often require parsing and processing the entire dataset, leading to a significant increase in the computational load on the client or server. Furthermore, the generated prompts are prone to containing a large amount of redundant data irrelevant to the current analysis needs, further exacerbating storage resource consumption and data processing pressure. Summary of the Invention

[0003] This disclosure provides a method for generating prompt content, a prompt content generation apparatus, a computer-readable storage medium, a computer device, and a computer program product. It acquires raw video data in response to constraints, parses the raw video data to obtain parsed data, and generates prompt content, which is then displayed alongside the current game screen. This targeted approach generates meaningful prompt content to help users review content and improve the user experience.

[0004] On one hand, this disclosure provides a method for generating prompt content. Applied to a game client, the method includes: displaying the current game screen corresponding to a game video on the game client; receiving constraints set by the game client, the constraints including at least the selection of an active character, a passive character, and a backtracking round in the game video, wherein the backtracking round is used to determine N historical rounds back from the current moment, where N is an integer greater than or equal to 1; parsing the original video data corresponding to the N historical rounds in the game video to obtain parsed data, wherein the parsed data includes at least the behavior data of the active character in the N historical rounds; and generating prompt content corresponding to the current game screen based on the parsed data.

[0005] On the other hand, this disclosure provides a prompt content generation device. The prompt content generation device includes a display unit and a control unit. The display unit provides a graphical user interface (GUI), which at least displays the current game screen. The control unit is connected to the display unit. The control unit is configured to: control the display unit to display the current game screen corresponding to a game video; receive constraints set by the game client, the constraints including at least the selection of an active character, a passive character, and a backtracking round in the game video, wherein the backtracking round is used to determine N historical rounds backward from the current moment, where N is an integer greater than or equal to 1; parse the original video data corresponding to the N historical rounds in the game video to obtain parsed data, wherein the parsed data includes at least the behavioral data of the active character within the N historical rounds; and generate prompt content corresponding to the current game screen based on the parsed data.

[0006] On the other hand, embodiments of this disclosure provide a computer-readable storage medium storing a computer program adapted for loading by a processor to execute a generation method. The generation method includes: displaying a current game screen corresponding to a game video on a game client; receiving constraints set through the game client, the constraints including at least the selection of an active character, a passive character, and a backtracking round in the game video, wherein the backtracking round is used to determine N historical rounds retracing backward from the current moment, where N is an integer greater than or equal to 1; parsing the original video data corresponding to the N historical rounds in the game video to obtain parsed data, wherein the parsed data includes at least the behavioral data of the active character within the N historical rounds; and generating prompt content corresponding to the current game screen based on the parsed data.

[0007] On the other hand, this disclosure provides a computer device including a processor and a memory. The memory stores a computer program, and the processor executes a generation method by calling the computer program stored in the memory. The generation method includes: displaying the current game screen corresponding to a game video on a game client; receiving constraints set through the game client, the constraints including at least the selection of an active character, a passive character, and a backtracking round in the game video, wherein the backtracking round is used to determine N historical rounds back from the current moment, where N is an integer greater than or equal to 1; parsing the original video data corresponding to the N historical rounds in the game video to obtain parsed data, wherein the parsed data includes at least the behavior data of the active character in the N historical rounds; and generating prompt content corresponding to the current game screen based on the parsed data.

[0008] On the other hand, this disclosure provides a computer program product, including computer instructions, which, when executed by a processor, implement a generation method. The generation method includes: displaying a current game screen corresponding to a game video on a game client; receiving constraints set through the game client, the constraints including at least the selection of an active character, a passive character, and a backtracking round in the game video, wherein the backtracking round is used to determine N historical rounds retracing backward from the current moment, where N is an integer greater than or equal to 1; parsing the original video data corresponding to the N historical rounds in the game video to obtain parsed data, wherein the parsed data includes at least the behavioral data of the active character within the N historical rounds; and generating prompt content corresponding to the current game screen based on the parsed data.

[0009] In the prompt content generation method, prompt content generation apparatus, computer-readable storage medium, computer device, and computer program product provided in this disclosure, by responding to three key constraints—the selection of the active role, the selection of the passive role, and the selection of the rewind round—the acquired original video data is ensured to be associated with the constraints, reflecting the user's true intention in generating the prompt content. Furthermore, parsing the original video data yields parsed data, and this parsed data is used to generate prompt content corresponding to the current game screen within the rewind round. The prompt content and the current game screen are then displayed together. In this case, the proportion of redundant data in the generated prompt content is low, reducing storage resource overhead and data processing pressure. Moreover, the prompt content has a high degree of matching with the user's immediate information needs, reflecting the user's true generation intention. This facilitates the user's ability to analyze, trace, and review the battle process through prompt content, significantly improving the user experience. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram of an example prompt content generation system provided in an embodiment of this disclosure.

[0012] Figure 2 This is a schematic flowchart of the generation method provided in the embodiments of this disclosure.

[0013] Figure 3 This is a schematic diagram illustrating an application scenario of a generation method provided in an embodiment of this disclosure.

[0014] Figure 4 This is a schematic diagram illustrating another application scenario of the generation method provided in this embodiment of the disclosure.

[0015] Figure 5 This is a schematic flowchart of the generation method provided in the embodiments of this disclosure.

[0016] Figure 6 This is a schematic flowchart of the generation method provided in the embodiments of this disclosure.

[0017] Figure 7 This is a schematic flowchart of the generation method provided in the embodiments of this disclosure.

[0018] Figure 8 This is a schematic flowchart of the generation method provided in the embodiments of this disclosure.

[0019] Figure 9 This is a schematic flowchart of the generation method provided in the embodiments of this disclosure.

[0020] Figure 10 This is a schematic diagram of the structure of the prompt content generation device provided in the embodiments of this disclosure.

[0021] Figure 11 A schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. Detailed Implementation

[0022] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0023] It should be noted that the terms "first," "second," and "third," etc., used in various parts of the embodiments and drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. These terms can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in a sequence other than that illustrated or described herein. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0024] The insufficient intelligence in the prompt content generation process makes it difficult to accurately identify user focus points, resulting in low information matching and potentially excessive redundant information. This prevents the prompt content from providing effective tactical breakdown, fails to meet user traceability needs, and has limited value in assisting understanding combat logic and improving skills. To address this issue, this disclosure provides a method for generating prompt content, a prompt content generation apparatus, a computer-readable storage medium, a computer device, and a computer program product.

[0025] Specifically, the generation method of this disclosure embodiment can be executed by a computer device, which can be a terminal or a server. The terminal can be a terminal device such as a smartphone, tablet, laptop, smart TV, wearable smart device, or smart vehicle terminal. The terminal can also include a client, which can be a game client, browser client, instant messaging client, or mini-program. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0026] For example, when the generation method runs on a terminal device, the terminal device may include a display screen and a processor. The display screen is used to present a graphical user interface (GUI) and receive user commands to the GUI. The processor is used to store programs applied by the prompt content generation method (e.g., game applications used by the prompt content generation method), run the generation method, generate the GUI, and control the display of the GUI on the display screen. The GUI may be used to display game visuals, which may include portions of a virtual game scene, a virtual world where virtual characters move. The processor is also used to store game applications, run the game, generate game visuals, respond to commands, and control the display of the game visuals on the display screen. When a user operates the GUI through the display screen, the GUI can control local content on the terminal device in response to received operation commands. The terminal device may provide the GUI to the user in various ways, such as rendering it on the terminal device's display screen or presenting the GUI through holographic projection.

[0027] For example, when this generation method runs on a server, it can be implemented and executed based on a cloud generation system. A cloud generation system refers to a generation method based on cloud computing. A cloud generation system includes servers and client devices. The program running the prompt content generation method and the graphical user interface (GUI) presentation are separate; the storage and execution of the generation method are completed on the server. The GUI presentation is completed on the client, which is mainly used for receiving and sending data for the GUI presentation. For example, the client can be a display device with data transmission capabilities located close to the user, such as a mobile terminal, television, computer, PDA, personal digital assistant, or head-mounted display device. However, the terminal device for data processing is the server in the cloud. During prompt content generation, the user operates the client to send instructions to the server. The server controls the execution of the generation method according to the instructions, encodes and compresses the GUI data, returns it to the client via the network, and finally, the client decodes and outputs the GUI.

[0028] It should be noted that in this embodiment of the disclosure, the executing entity of the generation method can be a terminal device or a server. The terminal device can be a local terminal device or a client device in the aforementioned cloud generation system. This embodiment of the disclosure does not limit the type of executing entity.

[0029] It is understood that in the specific embodiments of this disclosure, user object data, context data and other related data are involved. When the embodiments of this disclosure are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0030] For example, in conjunction with the above description, Figure 1 This disclosure illustrates a prompt content generation system 1000 for implementing a generation method, which may include at least one terminal 1001, at least one server 1002, at least one database 1003, and a network. The user-held terminal 1001 can connect to different servers via the network. The terminal can be any device with computing hardware capable of supporting and executing software application tools corresponding to the generation method.

[0031] In the aforementioned prompt content generation system 1000, terminal 1001 is used to install and run the program for the prompt content generation method. In some cases, the game application may not need to be pre-installed on terminal 1001, and users can directly access and enter the game through a browser or other client. Players can log in to the game application using their registered game account to control the virtual character corresponding to that game account and participate in the game. When a user logs in to the game application, terminal 1001 sends a login request to server 1002. Server 1002 verifies the game account used by the user and determines the game mechanism corresponding to the game account based on the login request. If the verification is successful, a login success notification is returned to terminal 1001. During the process of the user generating prompt content through the game application, terminal 1001 and server 1002 exchange data. Terminal 1001 sends various information to server 1002. Server 1002 determines the display data of terminal 1001 based on the storage mechanism and the received information, and sends the display data to terminal 1001 so that terminal 1001 can display the display data sent by server 1002 to the user.

[0032] In possible application scenarios, different terminals 1001 may be served by different servers 1002. Therefore, in order to distinguish the servers 1002 corresponding to different game terminals 1001, the embodiments of this disclosure will use a first and a second approach for description. In fact, the servers 1002 corresponding to different game terminals 1001 can be the same server 1002. Therefore, without distinguishing between the first and second approaches, it can be understood that the terminals 1001 corresponding to virtual characters in the same game scene are served by the same server 1002.

[0033] Furthermore, when the game system 1000 includes multiple terminals, multiple servers, and multiple networks, different terminals can connect to each other through different networks and different servers. The network can be a wireless network or a wired network; for example, wireless networks include Wi-Fi, LAN, cellular networks, 2G networks, 3G networks, 4G networks, 5G networks, etc. Additionally, terminals can also use their own Bluetooth network or hotspot network to connect to other terminals or to the server. Furthermore, the prompt content generation system 1000 can include multiple databases, which are coupled to different servers.

[0034] It should be noted that in this embodiment, multiple terminal devices are running the same virtual game. Therefore, data interaction between the multiple terminal devices can be achieved through the virtual game's server. Thus, sending data from terminal device 1 to terminal device 2 can be understood as: terminal device 1 sends data to the virtual game's server, and the server sends the data to terminal device 2. Receiving data from terminal device 2 can be understood as: terminal device 1 receives data sent by the virtual game's server, which is the data sent by terminal device 2 to the server. Alternatively, there may be no game server, and terminal device 1 directly sends game data to terminal device 2.

[0035] It should be noted that, Figure 1 The schematic diagram of the prompt content generation system shown is merely an example. The prompt content generation system 1000 described in this disclosure is intended to more clearly illustrate the technical solutions of this disclosure and does not constitute a limitation on the technical solutions provided in this disclosure. As those skilled in the art will know, with the evolution of the prompt content generation system 1000 and the emergence of new business scenarios, the technical solutions provided in this disclosure are also applicable to similar technical problems.

[0036] It should be noted that the triggering operations mentioned in the subsequent detailed description of the generation method provided in the embodiments of this disclosure can all be regarded as triggering operations performed by the user through a finger or by controlling a medium such as a mouse, keyboard, or stylus. The specific medium used can be determined according to the type of computer device. For example, when the computer device is a touchscreen device such as a mobile phone, tablet computer, or game console, the user can operate on the touchscreen using any suitable object or accessory such as a finger or stylus. When the terminal device is a non-touchscreen terminal device such as a desktop computer or laptop computer, the user can operate using an external device such as a mouse or keyboard.

[0037] The technical solutions of this disclosure will be described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0038] Please combine Figure 3 and Figure 4 This disclosure uses the method for generating prompt content applied to a game client as an example. In this case, the game client provides at least a graphical user interface (GUI) to display the current game screen, and the prompt content is generated within the GUI. The GUI displays at least a portion of the game scene of a virtual game, including at least one virtual character. In some embodiments, the game scene also includes a non-player character controlled by the game server. The virtual scene can be a game scene, which can be understood as a simulation of the real world within the game, a semi-simulated / semi-fictional virtual environment, or a purely fictional virtual environment. The game scene can be any one of a two-dimensional virtual scene, a two-and-a-half-dimensional virtual scene, or a three-dimensional virtual scene. A virtual scene typically includes multiple scene elements, which refer to the various elements required to constitute the virtual scene. For example, these may include, but are not limited to, at least one of the following: virtual character elements, virtual item elements, virtual building elements, virtual terrain elements, virtual vegetation elements, etc. Virtual terrain elements may include, but are not limited to, natural landform elements such as land, ocean, lakes, and rivers. The virtual scene is the scene in which the player controls the virtual character to complete the game logic.

[0039] As can be understood, a virtual character is a game character controlled by the player in the game. The player operates this virtual character to perform various game activities in the game scene, such as picking up items, fighting, exploring, or solving puzzles. This virtual character can represent the player's image, and each virtual character can be implemented using a 3D virtual model or a 2D virtual model; this embodiment is not specifically limited. Virtual characters include, but are not limited to, at least one of virtual human characters, virtual animals, and virtual machines. A non-player character is a game character controlled by the server in the game. The server operates this non-player character to perform various game activities in the game scene, such as picking up items, fighting, or talking; this non-player character can interact with the virtual character. Each non-player character can be implemented using a 3D virtual model or a 2D virtual model; this embodiment is not specifically limited. Non-player characters include, but are not limited to, at least one of non-player human characters, non-player animals, and non-player machines.

[0040] Please see Figures 2 to 4 , Figure 2 This is a schematic flowchart of the generation method provided in the embodiments of this disclosure. Figure 3 This diagram illustrates the graphical user interface of a game client during the identification process of the generation method provided in this embodiment. It should be noted that the steps shown may be performed in a logical order different from that shown in the flowchart of this generation method. The generation method may include the following steps: Step 01: Display the current game screen corresponding to the game video in the game client; Step 03: Receive the constraints set through the game client. The constraints include at least the selection of active characters, passive characters and backtracking rounds in the game video. The backtracking round is used to determine the N historical rounds that are backtracked from the current moment, where N is an integer greater than or equal to 1. The graphical user interface is also used to display the current game screen within the backtracking round. Step 05: Analyze the raw video data corresponding to N historical rounds in the game video to obtain analyzed data. The analyzed data must include at least the behavioral data of the active character within those N historical rounds; and Step 07: Generate prompts corresponding to the current game screen based on the parsed data.

[0041] Specifically, the method for generating prompts disclosed herein is applied to games, such as competitive games. Competitive games are a type of video game involving one or more players. Their core mechanism involves players competing against each other, for example, belonging to opposing factions. Players control virtual characters in real-time, utilizing preset skill combinations, tactical strategies, and teamwork to engage in direct combat within specific rules and arenas. Victory is determined by defeating opponents, capturing objectives, or accumulating points. It should be noted that competitive games are not limited to games where only two players engage in combat; they can also include card games, board games, etc., with competitive elements. For ease of explanation, the following description uses combat games as an example; other games can be compared using similar analogies.

[0042] During gameplay, the system-generated bullet comments and other prompts suffer from insufficient intelligence. "Prompt content" refers to text or graphic information generated by the system and overlaid on the graphical user interface to assist users in understanding the battle situation. In some games, the generation of prompt content struggles to dynamically and accurately identify and model the user's focus of attention. The user's focus of attention refers to the subjective area of ​​attention formed by the user within a specific time window based on the current battle situation (such as friendly status, enemy skill releases, key target locations, etc.), typically manifested as a visual gaze point or the center of expected action.

[0043] Furthermore, the generated prompts often contain a large amount of redundant information. This "redundant information" refers to data fragments that have no direct causal relationship with the current battle progress or do not benefit the user's decision-making, such as repetitive low-damage hit prompts or movement warnings for non-critical areas. Due to the lack of a constraint mechanism on the generated prompts, the system's information extraction efficiency from the raw battle data stream is low, resulting in a low proportion of effective information per unit time. Users need to spend a lot of time and effort to sift through valuable content.

[0044] The aforementioned issues of difficulty in targeting user focus and insufficient information density further hinder the generated prompts from supporting structured post-battle analysis. "Structured post-battle analysis" requires decomposing and organizing continuous battle data along dimensions such as timeline, event type, and causal logic to form traceable, comparable, and attributable knowledge units. However, since the prompts are mostly isolated and disordered information fragments, they lack annotation of temporal relationships and causal chains between battle events. For example, if a user is hit twice consecutively by related skills in the game, and the system only provides an "attacked" prompt without linking the preceding actions to the subsequent actions, the user cannot effectively analyze tactics. This prevents the system from meeting the user's need to trace key operations (such as skill release timing), decision points (such as retreat or pursuit judgments), and reasons for errors (such as prediction errors or resource depletion), thus limiting its application value in helping users understand battle logic and improve game skills. To address this issue, this disclosure proposes a method for generating prompt content that highly matches the user's immediate information needs and reflects the user's true intention to generate the content.

[0045] More specifically, the current game screen is a game video of a certain duration displayed by the game client through the graphical user interface. It can be understood that the current game screen is a video recording of game actions performed by the user within a past period, often used for tactical replay, data management, etc.

[0046] Constraints refer to information or data input by the user in the game client that restricts and limits the generated prompts. In essence, constraints reflect the user's expectations and true intentions regarding the prompt generation process. Within the massive amount of data generated by the game, constraints limit at least a portion of the associated data, thus eliminating redundant data and ensuring that the original video data associated with the constraints reflects the user's true intentions. This helps increase the proportion of effective information in the subsequent prompts. It's important to note that "effective" here means that the information is relevant to the user's focus and can assist the user in reviewing gameplay.

[0047] In competitive games, users control a virtual character (e.g., virtual character A, e.g., ...). Figure 3 and Figure 4 As shown), and at least one other player-operated virtual character or system-controlled non-player character (e.g., virtual character B and virtual character C, such as...). Figure 3 and Figure 4As shown, virtual characters A, B, and C engage in multi-round battles, attacking, defending, or using skills or items on themselves or others. In some implementations, different virtual characters belong to different factions, and the operations that virtual characters in the same faction can perform may differ from those that virtual characters in different factions can perform. For example, attacks between virtual characters in the same faction will not be effective. For the sake of brevity, this disclosure does not consider faction issues, that is, it is assumed that the operations that virtual characters A, B, and C can perform in pairs are all the same.

[0048] It should be noted that a turn is the basic temporal unit in combat games. Within this unit, the participants (virtual character A, virtual character B, and virtual character C) can perform actions such as using skills, attacking, or defending according to predetermined rules (e.g., taking turns or simultaneously) (or they can choose not to perform any actions). After one turn ends, the next turn begins, and this cycle continues until the conditions for victory or defeat are met, or the battle is stopped (or terminated).

[0049] The selection of the active character refers to the user's choice of the virtual character they are most interested in. The character selected through this constraint is the active character. The active character can be a virtual character controlled by the user themselves, such as virtual character A, or a virtual character controlled by another player, or a non-player character controlled by the system, such as virtual character B or virtual character C. Players can flexibly select the active character based on the actual needs of the battle replay. For example, if a user wants to analyze and review the performance of their own virtual character A in the battle, they will select virtual character A as the active character; if a user wants to analyze and review the performance of their opponent's virtual character B in the battle and the battle process with their own virtual character A, they will select virtual character B as the active character.

[0050] The selection of a passive role refers to the user's choice of other roles that interact with the active role. The role selected through the "selection of a passive role" under certain constraints is the passive role. A passive role can be a virtual role controlled by the user, such as virtual role A, or a virtual role controlled by other players or a non-player role controlled by the system, such as virtual role B or virtual role C.

[0051] It's important to note that the focus for passive characters differs from that for active characters. The focus for active characters is on their actions, while the focus for passive characters is on information related to those actions. For example, when focusing on an attack performed by virtual character A in a particular round, the focus for virtual characters B and C is the damage inflicted on them, not the attacks or other actions performed by virtual characters B and C themselves.

[0052] The selection of the rewind rounds refers to the user's choice of the number of rounds to rewind for the generated prompt content. This can be understood as the prompt content being generated after the battle, during the rewind of the battle process. At this point, the user can select the number of rounds they want to rewind, i.e., the number of N historical rounds to trace back from the current moment (corresponding to different rewind durations, where N is an integer greater than or equal to 1). For example, if the user wants to focus on the continuous battle situation over multiple rounds, they can set the rewind rounds to a larger number at the corresponding moment, such as three, five, or seven; if the user wants to focus on the specific battle situation of a particular round, they can set the rewind rounds to one at the corresponding moment.

[0053] It should be noted that when a user executes the above-mentioned prompt content generation method to enable the function of generating prompt content in the game, it is usually accompanied by locating the initial moment of the intention to rewind the battle, and using this initial moment as a reference to rewind forward, so as to ensure that in a long battle, at least part of the battle process that you want to rewind can be quickly locked.

[0054] Furthermore, based on the acquired raw video data, the raw video data is parsed. This parsing can include, but is not limited to, data filtering, data removal, data interpretation, and data analysis. The aim is to better analyze and extract data from the raw video data that clearly illustrates the specific battle situation in the replay round, assisting users in replaying battles. The data obtained after this step is called parsed data. It can be understood that parsed data is the final data directly used to generate prompts. It should be noted that parsed data includes at least the behavioral data of the active character within N historical rounds corresponding to the replay round. Behavioral data refers to the data corresponding to the specific actions of the virtual character in that round.

[0055] Therefore, based on the acquired and analyzed data, and through a pre-defined method for generating prompts, prompts can be generated that reflect the specific battle situation within the rewind round, and these prompts correspond to the current game screen. The prompts are typically presented in a floating or dynamically moving manner on the graphical user interface. The prompts can include text, symbols, or images, used to convey data related to the battle process to the player, such as damage values, skill effects, or status changes. In this case, the prompts and the corresponding current game screen are displayed together on the graphical user interface. For example, the prompts can be, but are not limited to, floating numbers, scrolling bar prompts, icon bubbles, and warning text with color or effects, and are displayed floating on top of the corresponding current game screen without being obscured by the current game screen.

[0056] In the generation method provided in this embodiment, by responding to three key constraints—the selection of the active role, the selection of the passive role, and the selection of the backtracking round—the acquired original video data is ensured to be associated with the constraints, reflecting the user's true intention in generating the prompt content. Furthermore, parsing the original video data yields parsed data, which is then used to generate prompt content corresponding to the current game screen within the backtracking round. This results in the simultaneous display of the prompt content and the current game screen. In this case, the proportion of redundant data in the generated prompt content is low, reducing storage resource overhead and data processing pressure. Moreover, the prompt content has a high degree of matching with the user's immediate information needs, reflecting the user's true generation intention. This facilitates the user's ability to analyze, trace, and review the battle process through the prompt content, significantly improving the user experience.

[0057] Please see Figures 2 to 4 In some implementations, the selection of the active role is performed in the following manner: In response to performing the first selection operation on the active character through the game client, the active character is selected.

[0058] Specifically, in the current game screen displayed by the graphical user interface, multiple virtual characters are simultaneously displayed on the game screen, for example... Figure 3 and Figure 4 The virtual characters shown are A, B, C, and others. The first selection operation is the specific operation of inputting the constraint of selecting the active character; that is, the user performs the first selection operation in the graphical user interface to uniquely determine a certain virtual character as the active character.

[0059] In this disclosure, the first selection operation may include clicking on the active character (a virtual character, for example) in the graphical user interface provided by the client. Figure 3 or Figure 4 The virtual character A shown is an example. For instance, a user can use the left or right mouse button, or long-press the virtual character A, to select it by highlighting it or indicating it has a border, thus making it the active character. Alternatively, the first selection can be achieved using keyboard shortcuts, touchscreen taps, or gamepad focus switching.

[0060] Therefore, in the generation method provided in this embodiment, the selection of the active character can be quickly input by performing the first selection operation through the game client. The user operation process is simple and fast, which simplifies the input method of constraints, improves the generation efficiency of prompt content, and helps to improve the user experience and the sense of interaction with the game.

[0061] Please see Figures 2 to 4 In some implementations, the selection of the passive role is performed in the following manner: In response to performing a second selection operation on the passive character via the game client, the passive character is selected. Specifically, in the current game screen displayed in the graphical user interface, multiple virtual characters are simultaneously displayed on the game screen, for example... Figure 3 and Figure 4 The virtual characters shown are A, B, C, and others. The second selection operation is the specific operation of inputting the constraint of selecting a passive character; that is, the user performs the second selection operation in the graphical user interface to determine at least one virtual character as a passive character.

[0062] In this disclosure, the second selection operation may include clicking on a passive character (a virtual character, for example) in a graphical user interface provided by the client. Figure 3 or Figure 4 (As shown in the example, virtual character B and / or virtual character C). For instance, a user can use the left or right mouse button, or long-press virtual character B and / or virtual character C, to select them by highlighting or marking them with a border, thus designating them as a passive character. Alternatively, a second selection operation can be achieved using keyboard shortcuts, touchscreen taps, or gamepad focus switching.

[0063] Therefore, in the generation method provided in this embodiment, the selection of a passive character can be quickly input by performing the second selection operation through the game client. The user operation process is simple and fast, which simplifies the input method of constraints, improves the generation efficiency of prompt content, and helps to improve the user experience and the sense of interaction with the game.

[0064] Please see Figures 2 to 4 In some implementations, the selection of the backtracking round is performed in the following manner: In response to a third selection operation performed through the game client, a backtracking turn is selected, the third selection operation including at least one of adjusting the step control to increase or decrease the backtracking turn, typing the backtracking turn, and clicking a button to generate prompt content.

[0065] Specifically, while displaying the current game screen, the game client's graphical user interface can also display icons related to the prompts, such as a "Generate Prompt Button" and a "Step Control." It should be noted that these icons can always be displayed in the graphical user interface, or they can be hidden by default and invoked by the player through mouse clicks, keyboard shortcuts, or voice commands.

[0066] In some implementations, selecting the backtracking round includes clicking a button to generate a prompt message; please refer to [link / reference]. Figure 3 At this point, the user can use the left or right mouse button or long press the "Generate Prompt" button to select the "Rewind Round" as the default value, for example, round one. The prompt content is generated based on the battle situation of the previous round at the current moment.

[0067] In other implementations, selecting the backtracking round includes adjusting a step control to increase or decrease the backtracking round. The step control is used to increment or decrement the value of the historical round N corresponding to the backtracking round in a step-by-step manner. Please refer to [reference needed]. Figure 4 At this point, the user can use the left or right mouse button in the step control to indicate adding or removing at least part of the backtracking rounds, such as the plus or minus signs on both sides, to select a specific value for the backtracking rounds, such as three. The prompt content is generated based on the battle situation of the previous three rounds at the current moment.

[0068] In some other implementations, selecting the backtracking round includes typing the backtracking round; please refer to [reference needed]. Figure 4 At this point, the user can use the left or right mouse button to select at least a portion of the step control that represents the round to be rolled back, such as the area displaying numbers, to further input a specific value as the round to be rolled back, such as three. The prompt content is then generated based on the battle situation of the previous three rounds at the current moment.

[0069] Therefore, in the generation method provided in this embodiment, the input methods for selecting the backtracking round are relatively rich and diverse, allowing users to easily and quickly select the backtracking round. This effectively simplifies the input methods for constraints, improves the efficiency of generating prompts, and helps enhance user experience and the interactivity with the game.

[0070] Please see Figures 2 to 5 In some implementations, the raw video data includes the status data of the active character at the current moment; step 05 can be implemented through steps 051 and 053, specifically as follows: Step 051: From the behavioral data related to the active and passive roles within the backtracking round, filter out behavioral data that has a causal relationship with the state data, and use this as the target behavioral data; and, Step 053: Analyze the target behavior data using a preset logic parser to identify the interaction intent corresponding to at least a portion of the target behavior data, and use the target behavior data and / or the interaction intent as parsed data.

[0071] Specifically, status data represents the active character's current state, such as their current health, mana, and skill buffs. It can be understood that the active character's status data is related to their actions (such as using skills or items) or their combat interactions with passive or other virtual characters during at least some of the previous turns.

[0072] Within the rewind round, behavioral data comprises all data related to the combat process of both the active and passive characters. This means the behavioral data reflects all actions taken by both the active and passive characters within the rewind round. To better analyze the reasons behind the active character's current state and help users interpret and rewind the combat process, redundant parts need to be removed from the large amount of behavioral data, retaining only at least a portion of the behavioral data that has a causal relationship with the state data. This allows for the construction of a causal chain of behavior extending from the current moment back to previous rounds. Therefore, the behavioral data selected from the behavioral data that has a causal relationship with the state data is defined as the target behavioral data. In essence, the target behavioral data is the carefully selected data used to generate prompts.

[0073] A logic parser is a pre-defined analytical model used to analyze the tactical intentions and strategies implied in target behavior data. Based on the causal chain of a player's actions (target behavior data), the logic parser can infer the true purpose and overall tactical strategy behind each step of the player's action. The logic parser is a pre-defined, fixed model; it can be an unmodifiable fixed model stored in memory by the prompt content generation system 1000 before leaving the factory, or a model that can be written to, adjusted, or replaced by the operator in memory. When target behavior data is input into the logic parser, the parser analyzes the target behavior data, identifies and extracts the interaction intentions corresponding to at least a portion of the target behavior data. At this point, the logic parser optimizes the prompt content from "recording what happened" to "understanding what is wanted to be done," which helps users clearly understand the tactical logic.

[0074] In some implementations, the logic parser can identify preparatory behaviors from target behavior data and related follow-up behaviors, further locking in the entire tactical intent through the sequence and causal linkage of skills. For example, the logic parser might identify the preparatory behavior as stacking debuffs (causing debuffs such as reduced defense to the target, setting the stage for a powerful subsequent attack) and the follow-up behavior as detonation (detonating after stacking debuffs to unleash a high-damage burst attack). In this case, the logic parser can determine that the interaction intent is to achieve a powerful attack through the combination of stacking debuffs and detonation.

[0075] In some implementations, such as when the backtracking round is one, the target behavior data is used as parsed data to generate prompt content, such as... Figure 3 As shown. In other implementations, such as when there are more than one backtracking rounds, the target behavior data and interaction intent are used as parsed data to generate richer prompts, such as... Figure 4As shown. In some other implementations, such as when there are more than one rounds of backtracking, the interaction intent is used as parsed data to make the generated prompts more focused on tactical layout. (Not illustrated, but can be found in the references.) Figure 4 Inference, that is, this implementation method is Figure 4 The case where only the interactive intent is displayed.

[0076] Therefore, in the generation method provided in this embodiment, target behavior data that has a causal relationship with the state data, and / or interactive intents that reflect the overall tactical thinking obtained by the logic parser are used as parsing data to ensure the accuracy and effectiveness of the generated prompts. This effectively ensures that users can quickly learn about the battle situation in the recaptured round through the prompts, thereby improving the efficiency and experience of users in recapping battles.

[0077] Please see Figures 2 to 4 ,and Figure 6 In some implementations, step 07 can be achieved through steps 071 and 073, specifically as follows: Step 071: Divide the target behavior data into sub-analysis data based on the backtracking rounds. The sub-analysis data includes the target behavior data of the active character in the corresponding backtracking round, and the target behavior data of the passive character in the corresponding backtracking round; and... Step 073: Generate prompt content corresponding to the backtracking round based on all sub-parse data and / or interaction intents.

[0078] Specifically, the target behavior data is data associated with backtracking rounds. Therefore, the backtracking rounds can be used as the basis for division, dividing the target behavior data into sub-parse data corresponding to each backtracking round. It can be understood that when there is one backtracking round, the sub-parse data is the target behavior data. For example, when there are three backtracking rounds, the target behavior data can be divided into three sub-parse data based on the round: the sub-parse data of the round before the current time, the sub-parse data of the two rounds before the current time, and the sub-parse data of the three rounds before the current time.

[0079] It can be understood that each sub-parsed data includes both the target behavior data of the active character and the target behavior data of the passive character within the corresponding backtracking round. For example, using... Figure 4Taking the implementation with a 4-round rewind as an example, in the first round of the rewind, virtual character A uses a medicine item to replenish its health. In the second round, virtual character A uses skill A to apply debuffs to virtual characters B and C, with both virtual character B and C's debuffs reaching 50%. In the third round, virtual character A again uses skill A to apply debuffs to virtual characters B and C, with both virtual character B and C's debuffs reaching full stacks. In the fourth round, virtual character A uses skill B to detonate an attack, dealing 500 damage. Virtual character B, with its debuffs fully stacked, receives 200 damage from virtual character A, and virtual character C, with its debuffs fully stacked, receives 150 damage from virtual character A. At this point, each sub-parsed data includes the target behavior data of virtual character A in the corresponding rewind round, as well as the target behavior data of virtual characters B and C in the corresponding rewind round, as described above.

[0080] In some implementations, such as when the backtracking round is one, the prompt content is generated based on the sub-parsed data (parsed data), such as... Figure 3 As shown. In other implementations, such as when there are more than one backtracking rounds, prompts corresponding to each backtracking round are generated based on all the sub-parsed data, and prompts are also generated based on the interaction intent to supplement the overall battle strategy, such as... Figure 4 As shown in the diagram. In some other implementations, such as when the number of backtracking rounds is greater than one, prompts are generated based on the interaction intent to make the generated prompts more focused on tactical layout. (Not illustrated, but can be found in the references below.) Figure 4 Inference, that is, this implementation method is Figure 4 The case where only the interactive intent is displayed.

[0081] Therefore, in the generation method provided in this embodiment, by generating turn-based sub-parse data, the generated prompts can more clearly and explicitly display the battle situation of each turn. Furthermore, by generating prompts corresponding to the rewinding turns based on the interaction intent, the prompts can also effectively provide an overall battle strategy. At this point, the generated prompts have good accuracy and effectiveness, allowing users to obtain detailed battle information and overall battle strategies, thus ensuring the value of the prompts during the battle rewinding process.

[0082] Please see Figure 3 , Figure 4 , Figure 6 and Figure 7In some implementations, step 073 can be achieved through steps 0731, 07331, and 07333, specifically as follows: Step 0731: Match the corresponding prompt content template based on the backtracking round; Step 07331: When the backtracking round is one, the prompt content template is the first prompt content template. Sub-parse data is input into the first prompt content template to generate the prompt content corresponding to the backtracking round; and, Step 07333: When there is more than one backtracking round, the prompt content template is the second prompt content template. Input the sub-parse data and interaction intent into the second prompt content template to generate single-game prompt content corresponding to each round in the backtracking round, and comprehensive prompt content corresponding to all rounds, and use them together as prompt content.

[0083] Specifically, the prompt content template is a formatted structure used to generate prompt content based on parsed data. The prompt content template can quickly and accurately generate clear, well-formatted, and highly readable prompt content using the parsed data, improving the efficiency of users reading and extracting information from the prompt content. To ensure that the selected prompt content template matches the parsed data, the prompt content template corresponding to the specific value of the backtracking round must first be matched.

[0084] When the backtracking round is one, the first prompt content template is selected to generate the prompt content. This first prompt content template is the prompt content template corresponding to the case where the backtracking round is one. By embedding the sub-parsed data as input into the first prompt content template, the prompt content corresponding to this backtracking round can be generated and displayed on the game client along with the corresponding current game screen.

[0085] For example, please refer to Figure 3 The first prompt template is: "[Highlight Operation] [Active Player] uses [Skill Name] to deal [Damage Value] points of damage, causing [Passive Player] [Damage Value] points of damage." In the rewind round, virtual character A used skill X to attack, dealing 300 points of damage. Virtual character B received 100 points of damage from virtual character A, and virtual character C received 80 points of damage from virtual character A. Therefore, the generated prompt is: "[Highlight Operation] Virtual character A uses skill X to deal 300 points of damage, causing 100 points of damage to virtual character B and 80 points of damage to virtual character C."

[0086] If the number of rounds in the backtrack is greater than two, a second prompt template is selected to generate the prompt content. This second prompt template corresponds to the case where there are two backtrack rounds. By embedding the sub-parse data and interaction intent as input into the second prompt template, single-game prompt content corresponding to each round in the backtrack can be generated based on the sub-parse data, and comprehensive prompt content corresponding to all rounds can be generated based on the sub-parse data and interaction intent. At this point, the single-game prompt content and the comprehensive prompt content are displayed together as the prompt content on the game client along with the corresponding current game screen.

[0087] For example, please refer to Figure 4 The second prompt template is: "[Data on each combination][Combo Secrets] [Active Party] laid out their strategy [N] rounds in advance, ultimately unleashing a [total damage] burst." In the rewind rounds, the battle between virtual character A, virtual character B, and virtual character C is as described above, and will not be repeated here. Therefore, the generated prompt is: "Virtual character A used the item: Medicine; Virtual character A used skill A, causing virtual character B's debuff to stack by 50%, and virtual character C's debuff to stack by 50%; Virtual character A used skill A, causing virtual character B's debuff to reach its maximum stack, and virtual character C's debuff to reach its maximum stack; Virtual character A used skill B to deal 500 damage, dealing 200 damage to virtual character B, and dealing 150 damage to virtual character C; Virtual character A combined skill A and skill B for a powerful attack; laid out their strategy 3 rounds in advance, ultimately unleashing a 500-damage burst."

[0088] The four single-game hints are: "Virtual character A used the item: medicine; Virtual character A used skill A, causing virtual character B's debuff to stack by 50%, and virtual character C's debuff to stack by 50%; Virtual character A used skill A, causing virtual character B's debuff to stack to full, and virtual character C's debuff to stack to full; Virtual character A used skill B to deal 500 damage, dealing 200 damage to virtual character B, and dealing 150 damage to virtual character C." The comprehensive hint is: "Virtual character A combined skill A and skill B to achieve a powerful attack; the strategy was laid out 3 rounds in advance, ultimately resulting in a 500-damage burst."

[0089] Therefore, in the generation method provided in this embodiment, the corresponding prompt content template is selected according to the backtracking round to flexibly generate prompt content corresponding to the backtracking round. Especially in the process of backtracking multiple rounds, it can clearly show the battle situation of each round, and also reveal the overall battle strategy, providing users with a flexible and intelligent battle backtracking function, which significantly improves the convenience and practicality of users backtracking the battle process.

[0090] Please see Figure 4 and Figure 7 In some implementations, in the sub-parsed data, when there is no corresponding target behavior data for the passive character in the target behavior data of the active character, in the process of generating the prompt content corresponding to the backtracking round, and generating the single-game prompt content corresponding to each round in the backtracking round, only the prompt content associated with the active character and the single-game prompt content are generated.

[0091] Specifically, in the sub-parse data (if the backtracking round is one, the sub-parse data is the target behavior data), if the target behavior data of the active character does not have corresponding target behavior data of the passive character, for example, if the active character's operation in this round only affects itself, such as using an item that has a buff effect on itself, or the operation on the passive character hits the passive character, or the target hit by the operation is not the selected passive character but other unselected virtual characters, then in the process of generating prompt content or generating single-game prompt content, only the prompt content and single-game prompt content associated with that part of the active character's target behavior data are generated.

[0092] For example, please refer to Figure 4 In the first round of the rewind, virtual character A uses a medicine to replenish its health. The single-game prompt generated for this round is "Virtual character A used the item: medicine." This means that the single-game prompt for the first round of the rewind only contains the target behavior data associated with virtual character A. However, in the second to fourth rounds of the rewind, due to the existence of target behavior data for corresponding passive characters, it also includes target behavior data associated with virtual characters A, B, and C respectively.

[0093] Therefore, in the generation method provided in this embodiment, the generation of prompt content and single-round prompt content is more flexible and can cope with backtracking rounds with different actual operations, generating corresponding accurate prompt content or single-round prompt content without information matching errors or irrelevant content, thus ensuring the quality and effectiveness of the generated prompt content.

[0094] Please see Figures 2 to 4 ,and Figure 8 In some implementations, the generation method further includes: Step 091: Sort the prompts for each backtracking round according to the timeline; and, Step 093: Display the sorted prompts simultaneously on the top layer of the current game screen.

[0095] Specifically, to provide users with clear and easily readable prompts, when there is more than one backtracking round, the prompts for each backtracking round are sorted according to a timeline, that is, in chronological order, such as from bottom to top, top to bottom, right to left, or left to right. It should be noted that when there is only one backtracking round, displaying only that prompt can also be considered as sorting the prompts according to a timeline, placing that prompt first.

[0096] Furthermore, the sorted prompts are displayed together to ensure that users can simultaneously obtain comprehensive information about the battle process in the recap rounds. At this point, the prompts are positioned at the top of the current game screen, meaning they float above the current screen and may obscure at least part of it. This can be mitigated by reducing the transparency of the prompts or adjusting their relative position to the current game screen to avoid interfering with the user's view of the game.

[0097] In some implementations, before formally presenting the prompt content and the current game screen in the graphical user interface, the control method further includes: displaying a preview screen containing the prompt content and the current game screen in the graphical user interface, and, after receiving confirmation from the user, displaying the prompt content and the current game screen in the graphical user interface. Because there may be errors in selecting the active character, the passive character, or the backtracking turn, the generated prompt content may not provide effective information, such as mistakenly selecting another character as the active character, or setting the backtracking turn too short to effectively identify the interaction intent. To avoid this problem, this disclosure introduces a "preview-confirmation" step before formally presenting the prompt content and the current game screen.

[0098] After generating the prompt, the graphical user interface first creates a preview screen based on the prompt and the current game screen, giving the user time to make a decision. For example, please refer to... Figure 3 (A) and Figure 4 (A) The graphical user interface prompts the player through the text boxes "Confirm" and "Cancel" that the current screen is only a preview screen, and the player has the choice to decide whether to generate this prompt content.

[0099] Upon receiving a user's confirmation action on the preview screen, such as clicking the "Confirm" icon in the graphical user interface, the system determines that the user has confirmed the prompt content corresponding to the current preview screen and displays that prompt content along with the current game screen in the graphical user interface. Figure 3 (B) and Figure 4As shown in (B). When a user cancels the preview screen, such as clicking the "Cancel" icon in the text box of the graphical user interface, it is known that the user is not satisfied with the currently generated prompt. At this time, the process returns to the step of executing the input constraints to ensure that the generated prompt is more in line with the player's subjective intention and can help the player to better rewind the battle.

[0100] Therefore, in the generation method provided in this embodiment, the sorted prompts are displayed together with the current game screen, allowing users to quickly review the battle process using the prompts, thus enhancing the actual value of the prompts in improving user experience and assisting users in improving their skills. Simultaneously, the aforementioned "preview-confirm" steps empower users as "decision-makers" in the game, granting them final decision-making power. This ensures a sense of control over the user experience while effectively guaranteeing the validity of the generated prompts, significantly improving the user experience.

[0101] Please see Figures 2 to 4 ,and Figure 9 In some implementations, the generation method further includes: Step 095: Display timeline markers corresponding to N historical rounds on the current game screen. The timeline markers are used to highlight the moments when key actions occurred in the N historical rounds.

[0102] Specifically, since the current game screen is a continuous screen consisting of multiple historical rounds over a long period of time in a single game, in order to improve the convenience of the backtracking process and help users quickly locate the moments of greater significance that occurred in the historical rounds, the generation method disclosed herein also displays timeline markers on the current game screen.

[0103] The timeline markers are used to indicate moments in N historical rounds where key actions occur. These key actions include, but are not limited to, the use of important skills by the active character, the active character dealing significant damage to the passive character, the active character using important items, the passive character deciding to use important skills, the passive character dealing significant damage to the active character, and the active character using a series of attacks. It should be noted that the definition of key actions is determined by preset fixed criteria in the prompt content generation system 1000.

[0104] At this point, the timeline markers are displaying the duration corresponding to the backtracking round (e.g., Figure 3 and Figure 4 (As shown by the straight line below) At the same time, the location of key actions within that duration was also determined by proportional scaling (e.g., Figure 3 and Figure 4(As shown by the dots on the straight line below), this allows users to quickly determine the specific battle situation in N historical rounds using the timeline markers, facilitating battle rewinding.

[0105] Therefore, in the generation method provided in this embodiment, by displaying timeline markers on the current game screen, users can quickly learn the moments when key actions occurred in N historical rounds. The timeline markers, together with the prompts, can further enhance the user experience and assist users in better retracing the battle.

[0106] All of the above technical solutions can be combined in any way to form optional embodiments of this disclosure, and will not be described in detail here.

[0107] In the generation method provided in this embodiment, by responding to three key constraints—the selection of the active role, the selection of the passive role, and the selection of the backtracking round—the acquired original video data is ensured to be associated with the constraints, reflecting the user's true intention in generating the prompt content. Furthermore, parsing the original video data yields parsed data, which is then used to generate prompt content corresponding to the current game screen within the backtracking round. This results in the simultaneous display of the prompt content and the current game screen. In this case, the proportion of redundant data in the generated prompt content is low, reducing storage resource overhead and data processing pressure. Moreover, the prompt content has a high degree of matching with the user's immediate information needs, reflecting the user's true generation intention. This facilitates the user's ability to analyze, trace, and review the battle process through the prompt content, significantly improving the user experience.

[0108] To facilitate better implementation of the generation method of the embodiments of this disclosure, the embodiments of this disclosure also provide a prompt content generation device 200. This prompt content generation device 200 can be applied to a server in a software or hardware manner to perform the prompt content generation task. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple. For details of the relevant technical features, please refer to the corresponding descriptions of the method embodiments provided above. The following description of the device embodiment is merely illustrative.

[0109] Please see Figure 10 Understanding this embodiment, the figure is a unit block diagram of the prompt content generation device 200 provided in this embodiment. As shown in the figure, the prompt content generation device 200 provided in this embodiment includes: Display unit 201 is used to provide a graphical user interface, which is used to display at least the current game screen.

[0110] The control unit 203, connected to the display unit 201, is used to: control the display unit 201 to display the current game screen corresponding to the game video; receive constraints set by the client, the constraints including at least the selection of the active character, the selection of the passive character, and the selection of the backtracking round in the game video, wherein the backtracking round is used to determine N historical rounds back from the current moment, where N is an integer greater than or equal to 1; parse the original video data corresponding to the N historical rounds in the game video to obtain parsed data, wherein the parsed data includes at least the behavior data of the active character in the N historical rounds; and generate prompt content corresponding to the current game screen based on the parsed data.

[0111] In some embodiments, the control unit 203 is configured to select an active character in response to performing a first selection operation on an active character via a game client.

[0112] In some embodiments, the control unit 203 is configured to select a passive character in response to performing a second selection operation on the passive character via the game client.

[0113] In some embodiments, the control unit 203 is configured to select a backtracking turn in response to a third selection operation performed via the game client, the third selection operation including at least one of adjusting a step control to increase or decrease backtracking turns, typing backtracking turns, and clicking a button to generate prompt content.

[0114] In some embodiments, the control unit 203 is used to filter out behavioral data that has a causal relationship with the state data from the behavioral data related to the active and passive roles in the backtracking round, and use it as target behavioral data; and to parse the target behavioral data through a preset logic parser to identify the interaction intent corresponding to at least part of the target behavioral data, and use the target behavioral data and / or the interaction intent in it as parsed data.

[0115] In some embodiments, the control unit 203 is configured to divide the target behavior data into sub-parse data according to the backtracking round, the sub-parse data including the target behavior data of the active character in the corresponding backtracking round and the target behavior data of the passive character in the corresponding backtracking round; and, based on all the sub-parse data and / or interaction intent, generate prompt content corresponding to the backtracking round.

[0116] In some embodiments, the control unit 203 is used to match a corresponding prompt content template according to the backtracking round; when there is one backtracking round, the prompt content template is a first prompt content template, and the sub-parse data is input into the first prompt content template to generate prompt content corresponding to the backtracking round; and when there is more than one backtracking round, the prompt content template is a second prompt content template, and the sub-parse data and interaction intent are input into the second prompt content template to generate single-round prompt content corresponding to each round in the backtracking round, and comprehensive prompt content corresponding to all rounds, which together serve as the prompt content.

[0117] In some embodiments, the control unit 203 is configured to, in the sub-parse data, when there is no corresponding target behavior data for the passive character in the target behavior data of the active character, generate only the prompt content associated with the active character and the single-game prompt content in the process of generating the prompt content corresponding to the backtracking round, and generating the single-game prompt content corresponding to each round in the backtracking round.

[0118] In some embodiments, the control unit 203 is used to sort the prompts corresponding to each backtracking round according to the timeline, and the display unit 201 is used to display the sorted prompts simultaneously on the top layer of the current game screen.

[0119] In some embodiments, the display unit 201 is used to display timeline markers corresponding to N historical rounds on the current game screen, and the timeline markers are used to highlight the moments when key actions occur in the N historical rounds.

[0120] Each unit in the aforementioned prompt content generation device 200 can be implemented entirely or partially through software, hardware, or a combination thereof. Each unit can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each unit.

[0121] The prompt content generation device 200 can be integrated into a terminal or server that has storage and a processor and thus computing power, or the prompt content generation device 200 can be the terminal or server.

[0122] Optionally, this disclosure also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0123] Figure 11 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. The computer device may be a terminal or a server. Figure 11As shown, the computer device 300 includes a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, and a program for a generation method stored in the memory 302 and executable on the processor. The processor 301 and the memory 302 are electrically connected. Those skilled in the art will understand that the computer device structure shown in the figures does not constitute a limitation on the computer device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0124] The processor 301 is the control center of the computer device 300. It connects various parts of the computer device 300 through various interfaces and lines. By running or loading software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it performs various functions of the computer device 300 and processes data, thereby performing overall processing of the computer device 300.

[0125] In this embodiment of the disclosure, the processor 301 in the computer device 300 loads the instructions corresponding to the process of one or more generation methods into the memory 302 according to the following steps, and the processor 301 runs the generation method program stored in the memory 302 to realize various functions: Display the current game screen corresponding to the game video in the game client; Receive constraints set through the game client. The constraints include at least the selection of active characters, passive characters, and backtracking rounds in the game video. The backtracking rounds are used to determine N historical rounds that are traced back from the current moment, where N is an integer greater than or equal to 1. The original video data corresponding to N historical rounds in the game video is analyzed to obtain analyzed data, wherein the analyzed data includes at least the behavioral data of the active character within N historical rounds; and, Based on the analyzed data, a prompt message corresponding to the current game screen is generated.

[0126] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0127] Optional, such as Figure 11 As shown, the computer device 300 also includes: a display screen 303, a radio frequency circuit 304, an audio circuit 305, an input unit 306, and a power supply 307. The processor 301 is electrically connected to the display screen 303, the radio frequency circuit 304, the audio circuit 305, the input unit 306, and the power supply 307. Those skilled in the art will understand that... Figure 11The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0128] The display screen 303 can be used for a graphical user interface (GUI) and to receive operation commands generated by the user interacting with the GUI. The display screen 303 may include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the computer device. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. The touch panel can be used to collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel), and generate corresponding operation commands, which then execute the corresponding program. Optionally, the touch panel may include a touch detection device and a touch controller. The touch detection device detects the user's touch location and the signal generated by the touch operation, transmitting the signal to the touch controller. The touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 301, and can also receive and execute commands from the processor 301. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it transmits the information to the processor 301 to determine the type of touch event. Subsequently, the processor 301 provides corresponding visual output on the display panel based on the type of touch event. In this embodiment, the touch panel and the display panel can be integrated into the display screen 303 to achieve input and output functions. However, in some embodiments, the touch panel and the display panel can be implemented as two independent components to achieve input and output functions. That is, the display screen 303 can also be used as part of the input unit 306 to achieve input functions.

[0129] The radio frequency circuit 304 can be used to transmit and receive radio frequency signals to establish wireless communication with network devices or other computer devices, and to transmit and receive signals with network devices or other computer devices.

[0130] Audio circuitry 305 can be used to provide an audio interface between a user and a computer device via a speaker and a microphone. Audio circuitry 305 converts received audio data into electrical signals, transmits them to the speaker, and the speaker converts them into sound signals for output. Conversely, the microphone converts collected sound signals into electrical signals, which are then received by audio circuitry 305, converted back into audio data, and output to processor 301 for processing. The audio data is then transmitted via radio frequency circuitry 304 to, for example, another computer device, or output to memory 302 for further processing. Audio circuitry 305 may also include an earphone jack to facilitate communication between peripheral headphones and the computer device.

[0131] The input unit 306 can be used to receive input numbers, characters, or object feature information (such as fingerprints, irises, facial information, etc.), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

[0132] Power supply 307 is used to supply power to various components of computer device 300. Optionally, power supply 307 can be logically connected to processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. Power supply 307 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0133] although Figure 11 As not shown in the diagram, computer equipment 300 may also include a camera, sensor, wireless fidelity module, Bluetooth module, etc., which will not be described in detail here.

[0134] This disclosure also provides a computer-readable storage medium for storing a computer program. This computer-readable storage medium can be applied to a computer device, and the computer program causes the computer device to execute corresponding processes in the display control method of the embodiments of this disclosure; for brevity, further details are omitted here.

[0135] This disclosure also provides a computer program product including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the corresponding processes in the generation method of the embodiments of this disclosure, such as executing the methods in steps 01, 03, 05, 051, 053, 07, 071, 073, 0731, 07331, 07333, 091, 093, and 095. For simplicity, these will not be elaborated further here.

[0136] It should be understood that the processor disclosed herein may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this disclosure can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0137] It is understood that the memory in the embodiments of this disclosure can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0138] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0139] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0140] In this disclosure, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0141] In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0142] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0143] In addition, the functional units in this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0144] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer or a server) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0145] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method for generating prompt content, characterized in that, Applied to game clients, the generation method includes: The game client displays the current game screen corresponding to the game video. The system receives constraints set through the game client. These constraints include at least the selection of active characters, passive characters, and backtracking rounds in the game video. The backtracking rounds are used to determine N historical rounds that are traced back from the current moment, where N is an integer greater than or equal to 1. The original video data corresponding to the N historical rounds in the game video is analyzed to obtain analyzed data, wherein the analyzed data includes at least the behavioral data of the active character within the N historical rounds; and, Based on the parsed data, a prompt message corresponding to the current game screen is generated.

2. The generation method according to claim 1, characterized in that, The selection of the active role, the passive role, and the selection of the rollback round are performed in the following manner: In response to performing a first selection operation on the active character through the game client, the active character is selected; In response to performing a second selection operation on the passive character through the game client, the passive character is selected; In response to a third selection operation performed through the game client, the rewind round is selected, the third selection operation including at least one of adjusting the step control to increase or decrease the rewind round, typing the rewind round, and clicking a button to generate prompt content.

3. The generation method according to claim 1, characterized in that, The original video data includes the status data of the active character at the current moment; parsing the original video data corresponding to the N historical rounds in the game video to obtain the parsed data includes: From the behavioral data related to the active and passive roles within the backtracking round, select the behavioral data that has a causal relationship with the state data and use it as the target behavioral data; and, The target behavior data is parsed by a preset logic parser to identify at least a portion of the interaction intent corresponding to the target behavior data, and the target behavior data and / or the interaction intent are used as the parsed data.

4. The generation method according to claim 3, characterized in that, The step of generating prompt content corresponding to the current game screen based on the parsed data includes: The target behavior data is divided into sub-analyzed data based on the backtracking round. The sub-analyzed data includes the target behavior data of the active character in the corresponding backtracking round, and the target behavior data of the passive character in the corresponding backtracking round; and... Based on all the sub-parsed data and / or the interaction intent, generate the prompt content corresponding to the backtracking round.

5. The generation method according to claim 4, characterized in that, The step of generating the prompt content corresponding to the backtracking round based on all the sub-parsed data and / or the interaction intent includes: Match the corresponding prompt content template based on the backtracking round; When the backtracking round is one, the prompt content template is a first prompt content template. The sub-parsed data is input into the first prompt content template to generate the prompt content corresponding to the backtracking round; and, When the number of backtracking rounds is greater than one, the prompt content template is a second prompt content template. The sub-parse data and the interaction intent are input into the second prompt content template to generate single-game prompt content corresponding to each round in the backtracking rounds, and comprehensive prompt content corresponding to all rounds, which together serve as the prompt content.

6. The generation method according to claim 5, characterized in that, In the sub-parsed data, if the target behavior data of the active role does not have corresponding target behavior data of the passive role, in the process of generating the prompt content corresponding to the backtracking round, and generating the single-game prompt content corresponding to each round in the backtracking round, only the prompt content associated with the active role and the single-game prompt content are generated.

7. The generation method according to claim 4, characterized in that, Also includes: The prompts corresponding to each of the backtracking rounds are sorted according to the timeline; and, The sorted prompts will be displayed simultaneously at the top of the current game screen.

8. The generation method according to claim 7, characterized in that, The method further includes: The timeline markers corresponding to the N historical rounds are displayed on the current game screen. The timeline markers are used to highlight the moments when key actions occur in the N historical rounds.

9. A device for generating prompt content, characterized in that, include: A display unit is used to provide a graphical user interface, which is at least used to display the current game screen; and The control unit, connected to the display unit, is used for: The display unit is controlled to display the current game screen corresponding to the game video; Receive constraints set through the client, the constraints including at least the selection of active characters, passive characters and backtracking rounds in the game video, wherein the backtracking rounds are used to determine N historical rounds back from the current moment, where N is an integer greater than or equal to 1; The original video data corresponding to the N historical rounds in the game video is analyzed to obtain analyzed data, wherein the analyzed data includes at least the behavioral data of the active character within the N historical rounds; and, Based on the parsed data, a prompt message corresponding to the current game screen is generated.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted for loading by a processor to execute the method for generating prompt content according to any one of claims 1-8.

11. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program, and the processor executing the method for generating prompt content according to any one of claims 1-8 by calling the computer program stored in the memory.

12. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the method for generating prompt content as described in any one of claims 1-8.

Images