18 results about "Non-player character" patented technology

The disclosed systems and methods track and continuously monitor data about a player or a multiple players and create a non-playing character (NPC) and / or modify an existing NPC that replicates the player(s) play style. The disclosed systems implement an artificial intelligence engine that monitors how a real player responds to one or more events in a game and correlates game outcomes with real player actions, with the actions or reactions of third players, and / or with an amount or extent of engagement. The engine may be used to generate, host, or otherwise provide data representative of one or more NPCs to multiple different games, being hosted by one or more servers, concurrently.

The present application relates to the technical field of computers. Disclosed are a virtual character control method and apparatus, and a device and a storage medium. The method comprises: displaying a player-controlled virtual character and a non-player character that are located in a virtual environment; in response to a first attack operation on the non-player character, controlling the player-controlled virtual character to attack the non-player character; when an element display condition is met, displaying at least one virtual interaction element, wherein the element display condition is related to at least one of the following: the first attack operation, the player-controlled virtual character and the non-player character; and in response to an interaction operation on the at least one virtual interaction element, on the basis of an interaction result of the at least one virtual interaction element, changing an attack effect of the player-controlled virtual character on the non-player character. The method enriches the forms of human-computer interaction.

This application discloses a method, apparatus, device, medium, and program product for controlling virtual objects, belonging to the field of computer technology. The method includes: controlling a first virtual object, which is a non-player character (NPC), through a first row tree; obtaining a first distance between the first virtual object and a second virtual object, which is a player-controlled virtual object, in a virtual environment; and determining, based on the first distance, to control the first virtual object through a second row tree, which is obtained by replacing or adjusting the first row tree. This solution ensures that NPCs can achieve rich expressive forms even with limited computer equipment resources.

The embodiment of the application relates to the computer technical field, especially to the artificial intelligence technical field, and provides a game task generation method and device, electronic equipment and a storage medium, so as to improve the diversity of the game task. The method comprises the following steps: obtaining operation behavior information generated by a target object in a target game, obtaining role setting information of a non-player character specified by the target object, determining a task framework of a game task allocated to the target object by the non-player character, obtaining operation complexity of the game task according to a behavior matching degree between the operation behavior information and the role setting information, and generating the game task meeting the operation behavior information under the task framework according to the operation behavior information and the operation complexity. According to the different operation behavior information of different objects, different game tasks can be generated for different objects, and the diversity of the game task is improved.

The present disclosure provides a non-player character control method, a non-player character control device, a computer storage medium and an electronic device, and relates to the technical field of games. The non-player character control method comprises: in response to the distance between the current position of the non-player character and the target virtual cover in the game scene being less than a first preset distance, generating a plurality of preset movement directions corresponding to the current position according to the edge profile of the target virtual cover; determining a first movement direction of the target virtual character at the current time according to the historical movement direction of the target virtual character in pursuit of the non-player character; in response to the non-player character being located within the field of view range of the target virtual character, determining the movement direction with the smallest included angle with the first movement direction among the plurality of preset movement directions as a second movement direction of the non-player character; and controlling the non-player character to move according to the second movement direction. The present disclosure can improve the intelligence and personification of non-player character control.

The invention relates to determining activities to be performed by non-player characters (NPC) in an interactive experience, e.g. video game. Activities, e.g. dialogue, are generated using generative machine learning models using a received input activity from a player, an entire established context / lore within the experience, and a set of activity history within the experience, as input. The invention involves updating the entire established context / lore based on a comparison of semantic content of the entire established context and semantic content of the generated activity of the NPC. The invention involves determining subsequent activities to be performed by NPCs based on the updated entire established context / lore, thereby providing consistency within the experience.

This application provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for controlling a non-player character, comprising: displaying a non-player character in a first scene area of ​​a virtual scene; wherein the first scene area has multiple adjacent second scene areas; controlling the non-player character to select a third scene area from the multiple second scene areas; wherein the probability of the second scene area being selected by the non-player character is related to the interaction parameters of the scene area; controlling the non-player character to move from the first scene area to the third scene area; and during the movement of the non-player character, in response to the presence of a player character in the non-player character's sensing area, controlling the non-player character to interact with the player character. This application can improve the diversity of the interaction process between the non-player character and the player character, as well as the probability of interaction with the player character.

Non-player characters (NPC) in a computer game may be controlled using context in the form of player statements from the game engine to an LLM to drive NPC dialog and control NPC actions. Imperative statements are executed by game engine, and the result of this execution plus the original player request are converted to plain text description and injected back into the NPC dialog to ensure the NPC remains within defined bounds.

The embodiment of the application relates to the computer technical field, especially to the artificial intelligence technical field, and provides a game task generation method and device, electronic equipment and a storage medium, so as to improve the diversity of the game task. The method comprises the following steps: obtaining operation behavior information generated by a target object in a target game, obtaining role setting information of a non-player character specified by the target object, determining a task framework of a game task allocated to the target object by the non-player character, obtaining operation complexity of the game task according to a behavior matching degree between the operation behavior information and the role setting information, and generating the game task meeting the operation behavior information under the task framework according to the operation behavior information and the operation complexity. According to the different operation behavior information of different objects, different game tasks can be generated for different objects, and the diversity of the game task is improved.

This application provides a method for generating a schedule for a non-player character, comprising: obtaining scene information corresponding to the game map of the target game, including area information indicating multiple areas in the game map, atmosphere information indicating the environmental conditions of each area in different time periods of the target game, and point information indicating specific locations within each area; obtaining the identity information of the target non-player character, including at least the name information, occupation information, and character introduction of the target non-player character; and generating a schedule for the target non-player character using a trained first language model based at least on the scene information, identity information, and candidate game actions corresponding to the target non-player character. The candidate game actions are obtained by selecting corresponding game actions as candidate game actions from an entity knowledge base based on at least one of the scene and identity information. The entity knowledge base is pre-constructed based on at least a number of game actions pre-designed for the target game.

This application discloses a method, device, equipment, storage medium, and product for controlling a non-player character, belonging to the field of human-computer interaction. The method includes: displaying a non-player character in a virtual world; displaying the non-player character attacking a first virtual character, the first virtual character being one of at least two virtual characters within the non-player character's attack range; and changing the non-player character's attack target based on the damage value inflicted by the first virtual character, the attack target being at least one of the at least two virtual characters. By changing the non-player character's attack target in real-time according to the damage value inflicted by at least one virtual character, the flexibility of the non-player character is improved, allowing for more dynamic and varied reactions when fighting multiple opponents.

The present application belongs to the field of human-computer interaction. Disclosed are a method and apparatus for controlling a non-player character, and a device, a storage medium and a product. The method comprises: displaying a non-player character in a virtual world; displaying the non-player character attacking a first virtual character, wherein the first virtual character is one of at least two virtual characters located within an attack range of the non-player character; and on the basis of damage values dealt to the non-player character by the virtual characters, determining an attack target of the non-player character, wherein the attack target is at least one of the at least two virtual characters. On the basis of damage values dealt to a non-player character by at least one virtual character, an attack target of the non-player character is changed in real time, thereby improving the flexibility of the non-player character, and enabling the non-player character to exhibit more vivid and dynamic reactions when battling against multiple players.

Systems, processes, and device configurations are provided for dynamic chat translation and interactive game control. Methods can include receiving a communication for a user of an electronic game and converting the communication using localization settings and machine learning models for language processing to replace one or more segments of the communication. An updated communication with the replaced segments can be output to provide automatic conversion of information in the user's understanding. By automatically and adaptively outputting speech or text of a game chat and / or game output (e.g., non-player character (NPC) chat), a user can obtain improved understanding. Further, the systems and methods include detecting user reactions (including using eye tracking data) to evaluate the communication conversion and update the processes and models for communication conversion.

This application discloses a method, apparatus, device, and storage medium for controlling a virtual character, relating to the field of computer technology. The method includes: displaying a master virtual character and a non-player character located in a virtual environment; responding to a first attack operation against the non-player character, controlling the master virtual character to attack the non-player character; displaying at least one virtual interactive element when element display conditions are met, the element display conditions being related to at least one of the following: the first attack operation, the master virtual character, and the non-player character; and responding to an interaction operation against the at least one virtual interactive element, changing the attack effect of the master virtual character on the non-player character based on the interaction status of the at least one virtual interactive element. The above method enriches the forms of human-computer interaction.

The present invention relates to an English education system using virtual roleplay, comprising: a metaverse space providing device; a story providing device that generates a story, generates a Non-Player Character (NPC) that intervenes in the story, and generates an interaction scenario between the NPC and a user; and a Head Mounted Display (HMD) device that provides content according to the interaction scenario provided by the story providing device in the space provided by the metaverse space providing device and generates a user input signal corresponding to the content.

This information processing device comprises: a context acquisition unit that acquires, on the basis of the contents of a dialog between a user and a non-player character (NPC) in a virtual space, context information indicating the context of the dialog; and a generation unit that generates, on the basis of the context information and a sense-of-value segment that is information indicating the sense of value of the user, generation information for generating an utterance sentence by the NPC for recommending, to the user, a product and a service (product or the like) designated for recommendation to the user.

The invention relates to determining activities to be performed by non-player characters (NPC) in an interactive experience, e.g. video game. Activities, e.g. dialogue, are generated using generative machine learning models using a received input activity from a player, an entire established context / lore within the experience, and a set of activity history within the experience, as input. The invention involves updating the entire established context / lore based on a comparison of semantic content of the entire established context and semantic content of the generated activity of the NPC. The invention involves determining subsequent activities to be performed by NPCs based on the updated entire established context / lore, thereby providing consistency within the experience.