Information processing method and device in game, electronic equipment and readable storage medium

Abstract

The invention discloses an information processing method and device in a game, electronic equipment and a readable storage medium. The method comprises the steps that session information input by a player character for a non-player character in a game task is acquired; determining a first credibility of the non-player character on the session information; and determining reply information of the non-player character for the session information according to the first credibility. According to the method, the dialogue ability of the non-player character and the player character can be improved, the interaction richness of the player character and the non-player character is improved, and the game experience of players is improved.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a method, device, electronic device and computer-readable storage medium for processing information in a game. Background Art

[0002] In some games, players can obtain game information, participate in specific activities, hand over tasks, etc. by controlling player characters to communicate with non-player characters.

[0003] In the related art, non-player characters usually follow preset scripts to communicate with player characters, that is, the non-player characters communicate based on preset judgment conditions, response texts, etc. However, this method of following preset scripts makes the interaction process between player characters and non-player characters relatively rigid and repetitive, lacking personalized features, limiting the playability of the game. Players will quickly become familiar with the behavior patterns of non-player characters, reducing the challenge and fun of the game.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] In view of this, the present application provides an information processing method, device, electronic device and computer-readable storage medium in a game, which can improve the dialogue ability between non-player characters and player characters, improve the richness of interaction between player characters and non-player characters, and improve the player's gaming experience.

[0006] In a first aspect, an embodiment of the present application provides a method for processing information in a game, the method comprising:

[0007] Get the conversation information entered by the player character for the non-player character in the game task;

[0008] determining a first trust level of the non-player character for the session information;

[0009] Determine reply information of the non-player character to the conversation information according to the first trust level.

[0010] In a second aspect, an embodiment of the present application provides an information processing device in a game, the device comprising: an acquisition unit and a determination unit;

[0011] The acquisition unit is used to acquire the session information input by the player character for the non-player character in the game task;

[0012] The determining unit is used to determine a first trust level of the non-player character with respect to the session information;

[0013] The determining unit is further configured to determine, according to the first trust level, reply information of the non-player character to the conversation information.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0015] Processor; and

[0016] The memory is used to store a data processing program. After the electronic device is powered on and the program is run by the processor, the method of the first aspect is executed.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a data processing program, which is executed by a processor to perform the method of the first aspect.

[0018] The information processing method in the game provided by the present application obtains the session information input by the player character for the non-player character in the game task; based on the input session information, determines the first trust degree of the non-player character for the session information, that is, determines the trust degree of the non-player character for the input session information; further, determines the reply information of the non-player character for the session information according to the trust degree.

[0019] It can be seen that the non-player character can determine whether to trust the conversation information input by the player character, and use this to determine different reply information, so that the non-player character can dynamically adjust the reply information based on the player character's conversation information without following a preset script; in addition, when the reply information is determined according to the first trust level, the player character and the non-player character can conduct in-depth psychological games and strategy applications, which increases the challenge and fun of the game.

[0020] The above description is only an overview of the information processing method provided by the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0022] Figure 1 A system schematic diagram of a game system for implementing an information processing method in a game provided by an embodiment of the present application;

[0023] Figure 2 A flowchart of an example of an information processing method in a game provided in an embodiment of the present application;

[0024] Figure 3 A flowchart for determining reply information is provided for an embodiment of the present application;

[0025] Figure 4 A schematic diagram of an interface display of an example of an information processing method in a game provided in an embodiment of the present application;

[0026] Figure 5 A schematic diagram of another example of an interface display of the information processing method in a game provided in an embodiment of the present application;

[0027] Figure 6 A schematic diagram of the structure of an information processing device in a game provided by an embodiment of the present application;

[0028] Figure 7 A structural block diagram of an electronic device for implementing an information processing method in a game is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0029] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0030] It should be noted that the terms "first", "second", "third", etc. in the claims, description and drawings of the present application are used to distinguish similar objects and are not used to describe a specific order or sequence. The data used in this way are interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including", "having" and their variants are intended to cover non-exclusive inclusions, 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 clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] It should be understood that in the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" is merely a way to describe the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. "Including A, B and / or C" means including any one, any two, or any three of A, B, and C.

[0032] It should be understood that in the embodiments of the present application, "B corresponding to A", "B corresponding to A", "A corresponds to B", or "B corresponds to A" means that B is associated with A, and B can be determined according to A. Determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0033] Before describing the implementation methods of the present application in detail, the related technologies are first further introduced.

[0034] In some related technologies, non-player characters usually follow preset scripts to communicate with player characters, that is, the non-player characters communicate based on preset judgment conditions, response texts, etc. However, this method of following preset scripts does not have dynamic and real-time flexibility, which limits the adaptability of non-player characters to the behavior of player characters and changes in the game environment, making the interaction process between player characters and non-player characters relatively rigid and repetitive, lacking personalized characteristics, limiting the playability of the game, and players will quickly become familiar with the behavior patterns of non-player characters, reducing the challenge and fun of the game.

[0035] Alternatively, some games provide non-player characters with fixed personalities, which usually provide a more reasonable interaction between player characters and non-player characters. However, in this way, non-player characters can only interact with non-player characters with fixed personalities, lacking deep emotional understanding and feedback capabilities. The interaction mode is single and deep emotional communication is impossible. The interaction between players and non-player characters is usually mechanical, lacking fun and immersion. Players have no expectations for the current progress of the gameplay, and non-player characters cannot give personalized feedback based on the current status of the player characters.

[0036] Based on the above-mentioned problems, the embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for processing information in a game.

[0037] The information processing method in the game provided by the embodiment of the present application can be performed by an electronic device, which can be a terminal or a server. The terminal can be a terminal device such as a smart phone, a tablet computer, or a laptop computer. The server can be an independent physical server, or a server cluster or a 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 storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (such as software or software modules for providing distributed services), or it can be implemented as a single software or software module. The embodiment of the present application does not specifically limit this.

[0038] In an optional embodiment, when the information processing method in the game is run on a terminal device, the terminal device stores a game application and a game virtual scene. The terminal device interacts with the player through a graphical user interface. The terminal device may provide the graphical user interface to the player in a variety of ways, for example, it may be rendered and displayed on a display screen of the terminal device, or the graphical user interface may be presented through holographic projection.

[0039] In an optional embodiment, when the information processing method in the game runs on the server, the method can be implemented and executed based on the cloud game system. The cloud game system refers to a game method based on cloud computing. The cloud game system includes a server and a client device. The running body of the game application and the game screen presentation body are separated, and the storage and operation of the information processing method in the game are completed on the server. The game screen presentation is completed on the client, and the client is mainly used for receiving and sending game data and presenting the game screen. For example, the client can be a display device with data transmission function close to the player side, such as a mobile terminal, a TV, a computer, a handheld computer, a personal digital assistant, a head-mounted display device, etc., but the terminal device for processing game data is a server in the cloud. When playing the game, the player operates the client to send instructions to the server, and the server controls the running of the game according to the instructions, encodes and compresses the game screen and other data, and returns it to the client through the network. Finally, the client decodes and outputs the game screen.

[0040] It should be noted that in the embodiments of the present application, the execution subject of the information processing method in the game can be a terminal device or a server, wherein the terminal device can be a local terminal device or a client device in the aforementioned cloud game. The embodiments of the present application do not limit the type of the execution subject.

[0041] For example, in combination with the above introduction, Figure 1 A game system 1000 for implementing an information processing method in a game provided by an embodiment of the present application is shown. The game system 1000 may include at least one terminal 1001, at least one server 1002, at least one database 1003, and a network. The terminal 1001 held by the player can be connected to servers of different games through the network. The terminal is any device with computing hardware that can support and execute software application tools corresponding to the game.

[0042] In the above-mentioned game system 1000, the terminal 1001 is used to install and run the game application. In some cases, the game application may not be installed in advance in the terminal 1001, and the player can directly access the game through a client such as a browser. The player uses the registered game account to log in to the game application, and can manipulate the virtual character corresponding to the game account to participate in the game. When the player logs in to the game application, the terminal 1001 sends a login request to the server 1002, and the server 1002 verifies the game account used by the player. At the same time, the server 1002 determines the game mechanism corresponding to the game account according to the login request, and the verification returns a successful login notification to the terminal 1001. In the process of the player participating in the game through the game application, the terminal 1001 and the server 1002 interact with each other, and the terminal 1001 sends various information to the server 1002. The server 1002 determines the display data of the terminal 1001 according to the stored game mechanism (such as the information processing method in the game provided by this application) and the received information, and sends the display data to the terminal 1001, so as to display the display data sent by the server 1002 to the player through the terminal 1001.

[0043] 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 first and second methods will be used for description when involved in the embodiments of the present application. In fact, the servers 1002 corresponding to different game terminals 1001 may be the same server 1002. Therefore, without distinguishing between the first and the second, it can be understood that the terminals 1001 corresponding to the virtual characters in the same game scene are served by the same server 1002.

[0044] In addition, when the game system 1000 includes multiple terminals, multiple servers, and multiple networks, different terminals can be connected to each other through different networks and different servers. The network can be a wireless network or a wired network, such as a wireless network such as a wireless local area network (WLAN), a local area network (LAN), a cellular network, a 2G network, a 3G network, a 4G network, a 5G network, etc. In addition, different terminals can also use their own Bluetooth network or hotspot network to connect to other terminals or to servers, etc. In addition, the game system 1000 may include multiple databases, multiple databases are coupled to different servers, and game-related information can be continuously stored in the database when different players play multi-player games online.

[0045] It should be noted that Figure 1 The game system diagram shown is only an example. The game system 1000 described in the embodiment of the present application is to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can know that with the evolution of the game system and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

[0046] The technical solution of the present application is 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 in detail in some embodiments.

[0047] like Figure 2 As shown, Figure 2 This is a flowchart of an example of data processing in a game provided by an embodiment of the present application. It should be noted that the steps shown can be performed in a logical order different from that shown in the flowchart of the method. The method may include the following steps S210 to S230.

[0048] Step S210: Acquire the conversation information input by the player character for the non-player character in the game task.

[0049] Step S220: Determine a first degree of trust of the non-player character in the session information.

[0050] Step S230: Determine the response information of the non-player character to the conversation information according to the first trust level.

[0051] Next, the above steps S210 to S230 are described in detail.

[0052] For the above step S210, the conversation information input by the player character for the non-player character in the game task is obtained. The player character (PC) and the non-player character (NPC) are used to distinguish between the characters controlled by real players and the characters controlled by the game system in the game;

[0053] The player character is usually used to represent the image of a real player in the game world. The player character can be a three-dimensional virtual model or a two-dimensional virtual model, which is not specifically limited in this embodiment. The player character includes but is not limited to at least one of a virtual person, a virtual animal, a virtual machine, a virtual building, and a virtual plant.

[0054] Non-player characters refer to characters in the game that are not directly controlled by the player. They can be virtual characters controlled by the game's artificial intelligence. NPCs can play a variety of roles in the game, such as issuing quests, selling items, providing story clues, and serving as targets for game quests. The existence of NPCs enriches the game's worldview and increases the complexity and immersion of the game.

[0055] The above-mentioned game tasks refer to the gameplay mechanism in the game, which can promote the development of the game's storyline, help players improve their character abilities and obtain rewards. A variety of game tasks can be set in a game for players to perform. For example, the game task can be a dialogue between a player character and a non-player character to increase the trust of the non-player character in the player character, and when the trust of the non-player character in the player character reaches a threshold, a certain reward is given to the player character; or, the game task can also be to solve a puzzle in a fixed area of ​​the game map, and give the player a certain reward after the puzzle is successfully solved, etc. This embodiment does not specifically limit the type of game tasks.

[0056] It can be understood that the non-player characters in the above-mentioned game tasks can be key characters in the game tasks, used to interact with the player characters.

[0057] The above-mentioned session information refers to the chat text, images, emoticons, animated images, videos, audio and other information input by the player when the player character communicates with the non-player character, or it can be called dialogue information.

[0058] The purpose of this step S210 is to obtain the session information input by the player to facilitate the subsequent generation of reply information for the session information.

[0059] With respect to the above step S220, the first trust level of the non-player character in the session information refers to the trust level of the non-player character in the session information currently input by the player. The trust level of the non-player character in the session information can affect the interaction mode between the non-player character and the player character and the progress of the game. The first trust level is usually determined by the emotions and behaviors expressed by the player, the design of the game task, the personality of the player character or the personality of the non-player character, etc., which will not be described here, and can be referred to the detailed description below.

[0060] With respect to the above step S230, the reply information of the non-player character to the conversation information is determined according to the first trust level. That is, the non-player character can determine whether to trust the conversation information input by the player character, and determine different reply information accordingly, so that the non-player character can dynamically adjust the reply information based on the conversation information of the player character without following a preset script.

[0061] In addition, when the reply information is determined according to the first trust level, the player character and the non-player character can conduct in-depth psychological games and apply strategies, which increases the challenge and fun of the game. For example, according to the trust level of the non-player character for the session information, a personalized response can be provided for the session information, making the player feel that the interaction with the NPC is more real. In addition, the non-player character determines the reply information according to the change in the trust level of the session information, which allows the player to experience the evolution of the relationship with the NPC, increase the player's emotional investment, and gain a sense of accomplishment. At the same time, in this case, the player can try to explore different trust paths and results by entering different session information, so that the player's exploration space can be increased.

[0062] Next, the information processing method in the game provided by this application is further introduced in detail.

[0063] In some optional embodiments, the “determining the first trust level of the non-player character for the session information” in the above step S210 can be specifically implemented through the following steps S211 to S212.

[0064] Step S211: Generate strategy prompt words according to the session information, the task description information of the game task, the player character's personality information, and the non-player character's non-player personality information.

[0065] Step S212: inputting the strategy prompt word into the pre-trained reply information generation model, and outputting the first trust level through the pre-trained reply information generation model.

[0066] In the above step S211, the above session information can refer to the above description and will not be repeated here.

[0067] The task description information of the game task is used to convey the task background, task objectives, task requirements and other information of the game task to the player, guide the player to complete the game task, and stimulate the player's interest. It is understandable that the task description information of the game task may include but is not limited to: task name, background story, task objectives, reward information, restrictions, task clues, interaction methods and other information, and there is no specific limitation on this.

[0068] The player character information of the above-mentioned player characters includes, but is not limited to, information describing the basic information, appearance characteristics, personality traits, background story, skills and abilities, interpersonal relationships, goals and pursuits, interaction habits, etc. of the virtual model controlled by the player.

[0069] Similarly, the personality information of the above-mentioned non-player characters includes but is not limited to: information describing the NPC's basic information, appearance characteristics, personality traits, background stories, skills and abilities, interpersonal relationships, goals and pursuits, interaction habits, etc.

[0070] The player character's personality information and the non-player character's non-player personality information may be in the form of text, images, etc., without limitation.

[0071] Among them, the above basic information may include but is not limited to: name, gender, age, occupation, etc.; appearance characteristics may include but are not limited to: height, weight, hairstyle, clothing style, facial features, etc.; personality traits may include but are not limited to: the character's personality traits, such as bravery, cunning, kindness, etc., the character's emotional reflection, values, etc.; the background story may include but is not limited to: the enemy of the character's birth, growth energy, family background, past experiences, etc.

[0072] For example, the character information of the player character controlled by player A may be: his name is Zhang San, he is a male, dressed in rags, has a handsome appearance but a gloomy expression, looks less than 30 years old, has confused eyes, and does not seem to pay attention to what is happening around him.

[0073] The character information of NPC can be: Your name is Li Si, and you play a girl. You were born in a village called Y Village in Country X. You are thoughtful, gentle and delicate, and can keenly perceive the mood changes of people around you. Your friends are Li Yi, Li Er, Li Wu, Li Liu, etc. Your biggest wish at present is to return to your family in Y Village as soon as possible. In the conversation with Zhang San, you need to call yourself "I" and call Zhang San "Brother Zhang". Please generate reply information based on the above settings during the role-playing process.

[0074] In the embodiment of the present application, the above-mentioned session information, the task description information of the game task, the player character's player character information, and the non-player character's non-player character information can be spliced ​​together, and the spliced ​​information can be used as a strategy prompt. It can be seen that in a specific embodiment, the strategy prompt can be a large paragraph of text information.

[0075] The above-mentioned pre-trained reply information generation model is used to generate a model for the reply information of the non-player character. The model can be a large language model (LLM). In a specific embodiment, the LLM model can be a large-scale pre-trained language model based on the transformer architecture. The above-mentioned spliced ​​strategic prompt words are input into the pre-trained reply information generation model, and the pre-trained reply information generation model can output the first trust of the non-player character for the input session information based on the strategic prompt words. Among them, the transformer architecture is a neural network architecture, and the neural network architecture attention mechanism, especially the multi-head attention mechanism, can make the model pay attention to different parts of the input data, so as to better capture the dependency between different parts of the input data, and each head can process the characteristic parts of the input data concerned separately; for example, in an embodiment of the present application, the pre-trained reply information generation model can process the influence of different information in the strategic prompt words on the trust of the non-player character for the session information separately based on the multi-head attention mechanism.

[0076] In some optional specific embodiments, in the above step S212, "inputting the strategy prompt word into a pre-trained reply information generation model, and outputting the first trust through the pre-trained reply information generation model" can be specifically implemented through the following steps S2120 to S2121.

[0077] Step S2120: inputting the strategy prompt words into the pre-trained reply information generation model, and determining the emotion type corresponding to the conversation information in the strategy prompt words and the behavior attribute of the corresponding player character in the conversation information through the pre-trained reply information generation model.

[0078] Step S2121: Determine and output a first degree of trust of the non-player character to the conversation information according to the emotion type and the behavior attribute of the player character.

[0079] In this optional embodiment, steps S2120 and S2121 mainly focus on the influence of the pre-trained reply information generation model on the emotional tendencies and behavioral patterns of the player characters in the conversation information on the first trust level of the non-player characters when generating reply information.

[0080] The emotion type corresponding to the above-mentioned session information refers to the emotional color or emotional attitude of the player expressed in the session information, and the emotion type may include but is not limited to: positive emotion, negative emotion, neutral emotion, etc. Among them, positive emotion is used to express positive emotions such as happiness, satisfaction, and love; negative emotion is used to express negative emotions such as sadness, anger, and disgust; neutral emotion is used to express emotions without obvious emotional color when objectively describing or stating facts. In an embodiment of the present application, if the tone of the player in the session information is a positive emotion, the NPC may be more willing to trust the player, that is, the NPC's first trust in the session information will be relatively high; if the tone of the emotion is a negative emotion, the NPC may be more suspicious of the player, that is, the NPC's first trust in the session information will be reduced.

[0081] The behavior attribute of the player character corresponding to the above session information refers to the behavior pattern of the player character expressed in the session information, which can be used to help non-player characters understand the player character's motivation, decision-making, personality, attitude, etc. For example, there are real clues and false clues in the character clues of the game task. The player's behavior of choosing a false clue can reflect the player character's attitude of deceiving the non-player character; the player's behavior of choosing a real clue can reflect the player character's sincere attitude.

[0082] It should be noted that based on the multi-head attention mechanism, such as Figure 3 As shown, the pre-trained reply information generation model may include a sentiment analysis module, a behavior analysis module, a task description information and a character setting information analysis module, etc. In a specific embodiment, when the strategy prompt words are input into the pre-trained reply information generation model, the sentiment analysis module in the pre-trained reply information generation model may analyze the current sentiment tendency of the player character expressed by the conversation information in the strategy prompt words, that is, the sentiment type described above; the behavior analysis module in the pre-trained reply information generation model may analyze the current behavior attributes of the player character expressed in the conversation information, and the task description information and the character setting information analysis module are used to analyze the background story of the game task, the character setting requirements and other dependent information.

[0083] In some optional specific embodiments, on the basis of the pre-trained response information generation model being provided with a behavior analysis module, if the task description information of the game task includes several task clues with different degrees of authenticity, the degree of authenticity is used to indicate the degree of trust of the non-player character in the task clue; in layman's terms, when the degree of authenticity of a task clue is low, it indicates that the non-player character has low trust in the task clue, and the task clue with a degree of authenticity less than or equal to the preset degree of authenticity can be regarded as a false clue; when the degree of authenticity of a task clue is high, it indicates that the non-player character has high trust in the task clue, and the task clue with a degree of authenticity greater than the preset degree of authenticity can be regarded as a real clue. In the game task, several task clues with different degrees of authenticity are provided to the player, and the player can interact with the non-player based on the several character clues with different degrees of authenticity provided to complete the task goal of the game task.

[0084] Based on the game task, the step S2120 described above of "determining the behavior attributes of the player character corresponding to the conversation information through a pre-trained response information generation model" can be specifically implemented through the following step S01.

[0085] Step S01: The behavior analysis module of the pre-trained response information generation model determines the behavior attributes of the player character corresponding to the conversation information according to the authenticity corresponding to the task clues contained in the conversation information.

[0086] In some specific embodiments, when the degree of authenticity corresponding to the task clues contained in the session information is less than or equal to the preset degree of authenticity, the behavior attribute of the player character corresponding to the session information is determined to be a deceptive behavior, that is, the player chooses false clues to deceive the NPC; when the degree of authenticity corresponding to the character clues contained in the session information is greater than the preset degree of authenticity, the behavior attribute of the player character corresponding to the session information is determined to be an honest behavior, that is, the player adopts a sincere attitude to communicate with the NPC.

[0087] That is, if the conversation information expresses the player's behavior of choosing false clues, the NPC can determine that the player character has cheated, thereby reducing the first trust in the conversation information input by the player character; if the conversation information expresses the player's behavior of choosing real clues, the NPC can determine that the player character has not cheated and the conversation attitude is relatively sincere, thereby increasing the first trust in the conversation information input by the player character.

[0088] Alternatively, in some games, the authenticity of each task clue can be divided into intervals, and the non-player character will determine different behavioral attributes of the player character for task clues in different authenticity intervals. For example, the authenticity interval can be divided into: completely true, partially true, completely false, etc. When the player character chooses a partially true task clue, the non-player character can determine the player character's behavioral attribute as neutral behavior, and the first trust in the session information is to remain neutral; when the player character chooses a completely true task clue, the non-player character can determine the player character's behavioral attribute as honest behavior, and increase the first trust in the session information; when the player character chooses a completely false task clue, the non-player character can determine the player character's behavioral attribute as deceptive behavior, and reduce the first trust in the session information.

[0089] In the embodiment of the present application, after parsing the emotional tendency and behavioral attributes of the player character, the pre-trained reply information generation model can determine and output the first trust of the non-player character for the conversation information described above based on the emotional tendency and behavioral attributes and the rest of the content in the strategy prompt words, in addition to considering the influence of the emotional tendency and behavioral attributes of the player character on the first trust. For example, considering the personality information of the non-player character itself, when the NPC is suspicious, the first trust of the conversation information is relatively low. Figure 3 As shown, the above contents can be fused through the feature fusion module in the pre-trained reply information generation model.

[0090] In this way, while considering factors such as the player's emotional tendencies, behavioral attributes, player character information, non-player character information, and task description information expressed in the conversation information input by the player character, the reply information of the non-player character can be made more in line with the current emotional environment, story environment, character personality, etc., increasing the authenticity and diversity of the NPC's reply information, avoiding repetitive and monotonous reply information, and allowing players to feel that the NPC is an emotional and responsive entity, rather than a simple, fixed, mechanical preset script, thereby enhancing the player's gaming experience.

[0091] Based on any of the above implementations, further, in some optional embodiments, such as Figure 3 As shown, the above-mentioned pre-trained reply information generation model may also include a prediction classification module; based on this, the "determining and outputting the first trust degree of the non-player character for the conversation information through the pre-trained reply information generation model" in the step S2121 described above can be specifically implemented through the following steps T01 to T02.

[0092] Step T01: Determine, through a prediction classification module of a pre-trained reply information generation model, that the first trust level of the non-player for the conversation information is a predicted probability value of each reference trust level.

[0093] Step T02: determining the reference trust level whose predicted probability value exceeds a preset threshold as the first trust level of the non-player character for the session information and outputting the first trust level of the non-player character for the session information.

[0094] The reference trust level can be understood as a plurality of trust levels preset to indicate the trust level that the non-player character can have in the session information input by the player character. For example, the reference trust level can include but is not limited to: full trust, partial trust, neutral, slight suspicion, strong suspicion, direct insight, etc.

[0095] That is, when the player inputs the strategy prompt words into the pre-trained response information generation model, such as Figure 3 As shown, the information fused by the feature fusion module can be input into the prediction and classification module, and the prediction and classification module will give a probability value for each reference trust level for the first trust level of the session information, and each probability value can be used to represent the confidence of the reply information generation model in each reference trust level as the first trust level of the non-player character for the session information. It should be noted that the sum of each probability value is usually 1.

[0096] In a specific embodiment, as shown in the above step T02, the reference trust level with a predicted probability value exceeding a preset threshold is determined as the first trust level of the non-player character for the session information and the first trust level of the non-player character for the session information is output. For example, the reference trust level with the highest probability value is determined as the first trust level output, and outputting the reference trust level with the highest probability value indicates that the model is most confident in using the reference trust level as the first trust level.

[0097] For example, when the reference trust level includes but is not limited to: full trust, partial trust, neutral, slight suspicion, strong suspicion, and direct insight, the prediction and classification module gives a probability value of 0.6 when the first trust level of a certain session information input is full trust; a probability value of 0.2 when the first trust level of a certain session information input is partial trust; a probability value of 0.1 when the first trust level of a certain session information input is neutral; a probability value of 0.05 when the first trust level of a certain session information input is slight suspicion; a probability value of 0.05 when the first trust level of a certain session information input is strong suspicion; a probability value of 0 when the first trust level of a certain session information input is direct insight; then, the reference trust level of full trust can be output, and full trust is determined as the first trust level. This means that the non-player character fully trusts the session information input by the player character.

[0098] In some optional embodiments, such as Figure 3 As shown, the pre-trained reply information generation model provided in the embodiment of the present application may also include an information generation module. Based on this, the step S230 described above "determining the reply information of the non-player character to the conversation information according to the first trust degree" can be specifically implemented through the following steps S231 to S232.

[0099] Step S231: generating a reply prompt word according to the guidance information and the strategy prompt word corresponding to the first trust level.

[0100] Step S232: inputting the reply prompt word into the pre-trained reply information generation model, and outputting the reply information of the non-player character to the conversation information through the information generation module in the pre-trained reply information generation model.

[0101] In this embodiment, the above-mentioned guidance information refers to information set for each reference trust level to guide the pre-trained reply information generation model to generate reply information matching each reference trust level. The guidance information can be text information, picture information, video information, etc., and this embodiment does not make specific restrictions.

[0102] For example, as shown in Table 1, Table 1 provides examples of guidance information corresponding to each first trust level.

[0103] Table 1 Examples of guidance information corresponding to each first degree of trust

[0104]

[0105] That is, as shown in Table 1, when the first trust level is full trust, the guidance information corresponding to full trust may be "You completely believe what the person in front of you said, without any doubt, please output a sentence as a reply"; when the first trust level is partial trust, the guidance information corresponding to partial trust may be "What the person in front of you said is mostly credible, but further confirmation is needed, please output a sentence as a reply"; when the first trust level is neutral, the guidance information corresponding to neutral may be "What the person in front of you said is neither completely credible nor completely uncredible, you can maintain a neutral attitude, please output a sentence as a reply"; when the first trust level is slight suspicion, the guidance information corresponding to slight suspicion may be "What the person in front of you said is mostly uncredible, please output a sentence as a reply"; when the first trust level is strong suspicion, the guidance information corresponding to strong suspicion may be "What the person in front of you said is completely uncredible, please output a sentence as a reply"; when the first trust level is direct recognition, the guidance information corresponding to direct recognition may be "According to the information, you have completely recognized the person in front of you and confirmed that he is a liar, please output a sentence as a reply";

[0106] That is, Figure 3As shown, after determining the first trust level of the non-player character in the conversation information input by the player character, the guidance information corresponding to the first trust level can be determined, and the guidance information and the strategy prompt words described above can be spliced ​​to generate the reply prompt words; in a specific embodiment, the guidance information is spliced ​​at the end of the strategy prompt words.

[0107] After obtaining the reply prompt word, the reply prompt word is input into the pre-trained reply information generation model, and the information generation module in the pre-trained reply information generation model generates and outputs the reply information of the non-player character to the conversation information based on the reply prompt word. It should be noted that the pre-trained reply information generation model can distinguish whether the input is a strategy prompt word or a reply prompt word based on whether the guidance information is included.

[0108] When generating reply information, not only the direct input of the player is considered, but also the story background, task clues, etc. of the current game task are considered, so that the generated reply information is consistent with the game situation, and the NPC can show a variety of different dialogue paths and behavior patterns based on different first trust levels, avoiding repetition and monotony of interactions between player characters and non-player characters.

[0109] The following is a detailed introduction to the training process of the above-mentioned pre-trained reply information generation model.

[0110] In some embodiments, the pre-trained reply information generation model is trained through the following steps R1 and R2.

[0111] Step R1: Obtain several preset pairs of training samples, the training sample pairs include a first training sample and a second training sample, the first training sample includes: a sample corpus associated with a game task and a target trust; the second training sample includes: a sample corpus and target response information; the target response information matches the target trust.

[0112] Step R2: According to each pair of the first training sample and the second training sample, the reply information generation model to be trained is trained until a preset training end condition is reached to obtain a pre-trained reply information generation model.

[0113] The above-mentioned training sample pairs refer to the training samples used to train the reply information generation model to be trained, which appear in pairs. In this embodiment, a pair of training sample pairs may include a first training sample and a second training sample; wherein the first training sample is used to train the reply information generation model to be trained to learn how to predict the target trust from the input first training sample; the second training sample is used to train the reply information generation model to be trained to learn how to predict the target reply information from the input second training sample.

[0114] As described above, the first training sample may include a sample corpus associated with a game task and a target trust; wherein the sample corpus associated with the game task may include but is not limited to: historical session information of a sample player character, task description information of the game task, player personality information of the sample player character, non-player personality information of a sample non-player character, etc.; the target trust is a real trust pre-set for the sample corpus.

[0115] The difference between the second training sample and the first training sample is that the second training sample does not include target trust in addition to the sample corpus, but also includes target response information, which can be understood as a response template set for the sample corpus, that is, a series of dialogue information prepared in advance for the sample corpus.

[0116] It should be noted that in the embodiment of the present application, the target reply information matches the target trust, that is, the target reply information takes into account the influence of the target trust. For example, when the target trust is full trust, the semantics expressed by the target reply information is to believe what the person in front of you says.

[0117] The above-mentioned preset training end conditions may include but are not limited to: the loss value of the loss function of the reply information generation model to be trained is less than or equal to the preset loss value, the number of training times reaches the preset number of times; the reply information output by the reply information generation model to be trained meets the requirements, etc. This embodiment does not specifically limit this.

[0118] Further, in some optional specific embodiments, the above step R2 can be implemented by the following steps R20 to R22. That is, in this specific embodiment, the training end condition is that the loss value of the loss function of the reply information generation model to be trained is less than or equal to the preset loss value.

[0119] Step R20: Input any training sample pair into the reply information generation model to be trained, and the reply information generation model to be trained determines the predicted trust according to the first training sample in the input training sample pair, and determines the first difference between the reference trust and the target trust.

[0120] Step R21: The reply information generation model to be trained determines the predicted reply information according to the second training sample in the input training sample pair, and determines the second difference between the predicted reply information and the target reply information.

[0121] Step R22: Determine the loss value of the loss function corresponding to the reply information generation model to be trained based on the first difference and the second difference, and update and adjust the parameters of the reply information generation model to be trained based on the principle of making the loss value less than the preset loss value to obtain a pre-trained reply information generation model.

[0122] It should be noted that the above training process is an iterative training process, that is, after inputting a pair of training sample pairs, if the loss value of the loss function of the reply information generation model to be trained is not less than the preset loss value, then a training sample pair is randomly selected from several pairs of training sample pairs to retrain the reply information generation model to be trained after parameter adjustment until the loss value of the loss function is less than the preset loss value.

[0123] The above-mentioned predicted trust is the trust of the non-player character in the historical conversation information contained in the training sample determined by the reply information generation model to be trained based on the first training sample in the input training sample pair. Further, the first difference between the predicted trust and the preset target trust is calculated, that is, the gap between the trust predicted by the reply information generation model to be trained and the preset target trust; the first difference is a part of the loss value of the loss function of the reply information generation model to be trained.

[0124] Similarly, the above-mentioned predicted reply information is the reply information of the non-player character predicted by the reply information generation model to be trained based on the input second training sample for the conversation information in the second training sample; further, the second difference between the predicted reply information and the target reply information is calculated, that is, the semantic gap between the reply information predicted by the reply information generation model to be trained and the preset target reply information, and the second difference is part of the loss value of the loss function of the reply information generation model to be trained.

[0125] It should be noted that the loss value of the loss function of the reply information generation model to be trained includes the first difference and the second difference. Specifically, the first difference and the second difference can be weighted and summed to obtain the total loss value of the loss function of the reply information generation model to be trained. In this embodiment, the parameters of the reply information generation model to be trained are adjusted based on the principle of making the total loss value less than the preset loss value to obtain a pre-trained reply information generation model.

[0126] After obtaining the pre-trained reply information generation model, the pre-trained reply information generation model can be used through the various embodiments described above to determine the reply information of the non-player character to the conversation information input by the player character.

[0127] So far, the introduction to the content used to determine the reply information in the information processing method in the game provided by the present application is completed. Next, the display content of the reply information involved in the information processing method in the game is introduced.

[0128] In some optional embodiments, the information processing method in the game provided by the present application provides a graphical user interface through a terminal device. Based on this, the information processing method in the game provided by the present application may also include the following steps S240 to S250.

[0129] Step S240: Displaying the player character and at least one non-player character controlled by the terminal device through a graphical user interface.

[0130] Step S250: In response to a conversation event being triggered between the player character and the non-player character, a conversation panel is displayed; the conversation panel is used to receive conversation information input by the player character.

[0131] In an embodiment of the present application, the above-mentioned terminal device is any terminal device that displays a graphical user interface of a virtual game. The graphical user interface is a visual representation and operation interface for players to interact with the virtual game, which includes the game scene of the virtual game, as well as control components, social elements, etc. for displaying the style of the game world and information for guiding user operations.

[0132] In a graphical user interface, multiple interface contents to be displayed are usually presented in layers. Layers refer to a layered display method in a graphical user interface. Different interface contents can be placed on different layers to better control the display and hiding of each interface content. For example, the game scene can be placed on the scene layer, that is, the scene layer is mainly used to render the game world and the objects therein, including characters, environments, dynamic elements, etc. The display of various UI (User Interface) elements is placed on the UI layer. For example, UI elements can include but are not limited to various operation controls, information panels for displaying various game information (such as chat interfaces, character status panels, etc.), game thumbnail maps, and other elements. Since UI elements are interface elements for players to interact with games, generally, the display level of the UI layer where UI elements are placed is higher than the scene layer of the game scene. That is, the display level of each UI element is higher than the display level of the scene screen.

[0133] It should be noted that in the embodiments of the present application, there is no restriction on whether the terminal device providing the graphical user interface is placed horizontally or vertically, that is, there is no specific restriction on whether the virtual game is a horizontal screen game or a vertical screen game. In this embodiment, the virtual game is a horizontal screen game, and the terminal device is placed horizontally as an example to introduce the solution. However, it does not mean that the interactive control method of the game provided by this application is not applicable to vertical screen games. The information processing method in the game provided by this application can be applied to horizontal screen games and vertical screen games, that is, the operation mode set in the virtual game and the corresponding game logic are consistent in horizontal screen games and vertical screen games, and there are only slight differences in the layout of the interface elements in the graphical user interface.

[0134] In the embodiment of the present application, the graphical user interface at least displays a player character and at least one non-player character controlled by a terminal device. When a conversation event is triggered between the player character and the non-player character in the game task, a conversation panel is displayed; the conversation panel is used to receive conversation information input by the player character. That is, the conversation panel is a UI element displayed on the UI graphical user interface, which is generally understood as a dialog box, through which the player can communicate with the non-player character.

[0135] In an optional specific embodiment, the triggering of the conversation event between the player character and the non-player character may be implemented in any exemplary manner.

[0136] Example 1: In response to a distance between the player character and the non-player character being less than or equal to a preset distance, triggering a conversation event between the player character and the non-player character;

[0137] The above preset distance is a pre-set interactive distance for non-player characters, that is, when the player character is within the interactive distance of the non-player character, the dialogue interaction function with the non-player character can be performed, that is, when the player character is within the interactive distance of the non-player character, a conversation event between the two is triggered.

[0138] Example 2: In response to a selection operation on a non-player character, a conversation event is triggered between the player character and the non-player character;

[0139] In this example, the selection operation for the non-player character may include but is not limited to: a touch operation for the non-player character, a hover operation at the location of the non-player character, a specific air gesture operation, a shortcut key operation or a voice command operation, etc. Among them, the touch operation for the non-player character may include but is not limited to: a click operation, a press operation, a slide operation, etc. for the non-player character. No specific limitation is made in this example.

[0140] That is, in this example, when the player applies a selection operation to the non-player character, a corresponding session event may be triggered, and in response to the session event, a session panel may be displayed in the graphical user interface.

[0141] Example 3: Displaying a session control at a position corresponding to a non-player character; in response to a trigger operation on the session control, triggering a session event between the player character and the non-player character corresponding to the session control.

[0142] In this example, a corresponding session control can be set for each non-player character, and the session control is pre-set with a game logic for triggering a session event between the player character and the non-player character. When the player applies a corresponding trigger operation to the session control, the electronic device executes the game logic for triggering the session event. That is, after the session control is triggered by the corresponding trigger operation, the session event between the player character and the corresponding non-player character is triggered, so that the session panel is displayed in the graphical user interface.

[0143] In this example, the triggering operation for the session control may include, but is not limited to: a touch operation on the session control, a hover operation on the session control, a specific air gesture operation, a shortcut key operation, or a voice command operation, etc. Among them, the touch operation on the session control may include, but is not limited to: a click operation, a press operation, a slide operation, etc. on the session control. This example is not specifically limited.

[0144] Based on the above steps S240 and S250, in some embodiments, the above step S210 can be implemented through the following step S211.

[0145] Step S211: in response to the input completion instruction of the session information of the player character in the session panel, the session information input by the player character for the non-player character in the game task is obtained.

[0146] The input completion instruction is an instruction for notifying the electronic device that the player has completed inputting the session information. The input completion instruction may be generated in the following exemplary manner.

[0147] Example 1: In response to not performing an input operation within a preset time range, an input completion instruction is generated.

[0148] The input operation can be understood as the operation of the player inputting text, video, picture and other information through the session panel. The preset duration is a pre-set time setting for judging whether the player has completed the input. For example, the preset duration can be 3 seconds, 10 seconds, etc., without specific restrictions; for example, when the player does not input content within 10 seconds, the input can be judged to be complete, and the content that has been input can be submitted as session information.

[0149] Example 2: In response to an input completion operation, an input completion instruction is generated.

[0150] The input completion operation may include but is not limited to: triggering operations on the publishing controls displayed in the session panel, shortcut key operations, voice command operations, air gesture operations, etc.; among which, the triggering operations on the publishing controls may include but are not limited to: clicking operations, pressing operations, sliding operations, etc.

[0151] It should be noted that the operations that occur during the detailed introduction of the information processing method in the game provided in the embodiment of the present application can all be regarded as operations performed by the player through fingers or controlling a medium such as a mouse, keyboard, or stylus. The specific medium to be used can be determined according to the type of electronic device. For example, when the electronic device is a touch screen device such as a mobile phone, a tablet computer, or a game console, the player can operate on the touch screen through any suitable object or accessory such as a finger or stylus. When the terminal device is a non-touch screen terminal device such as a desktop computer or a laptop computer, the player can operate through an external device such as a mouse or keyboard.

[0152] Based on the above embodiments, the information processing method in the game provided by the present application may further include the following step S260.

[0153] Step S260: After determining the reply information, displaying the reply information through the graphical user interface, and / or voice broadcasting the reply information.

[0154] That is, after the reply information is determined, the reply information may be notified to the player in the following exemplary manner.

[0155] Example 1: Displaying the reply information in a graphical user interface. In a specific embodiment, the reply information may be displayed in the conversation panel described above or near the conversation panel; or displayed in other fixed areas in the graphical user interface, such as the upper right corner or upper left corner of the graphical user interface; this embodiment does not limit the display area of ​​the reply information in the graphical user interface.

[0156] Example 2: The reply information is announced by a non-player character. In this way, the player does not need to visually check the reply information, which reduces the player's visual pressure.

[0157] Example 3: When the non-player voice broadcasts the reply information, the reply information is displayed on the graphical user interface. In this way, the needs of different players can be met and the game experience of the players can be improved.

[0158] In some optional embodiments, in addition to displaying the above-mentioned session panel, the graphical user interface provided by the present application can also execute the following step S270.

[0159] Step S270: Displaying an information panel through the graphical user interface, wherein the information panel is used to display the second trust level of the non-player character toward the player character.

[0160] That is, in addition to displaying the above-mentioned conversation panel and reply information, the graphical user interface also displays an information panel, and the information panel is used to display the second trust level of the non-player character towards the player character.

[0161] The second trust level refers to the current trust level of the non-player character in the player character. It should be noted that the difference between the first trust level described above and the second trust level is that the first trust level refers to the trust level of the non-player character in the current session information input by the player; the second trust level refers to the current trust level of the non-player character in the player character; that is, the trust objects of the two are different.

[0162] In this embodiment, the trust value of the second trust level of the non-player character for the player character can be set with an upper and lower limit to indicate the range of the trust level of the non-player character for the player character, such as the lower limit value is used to indicate that the non-player character does not trust the player character at all, and the upper limit value is used to indicate that the non-player character fully trusts the player character. The upper limit value can be 100, and the lower limit value can be 0, which can be determined according to actual conditions and is not specifically limited.

[0163] Optionally, when the second trust level is displayed in the information panel, it can be displayed through graphics and / or numbers. The graphical display method is more intuitive, which is convenient for players to roughly estimate the current proportion of the second trust level relative to the reference trust level, for example, it can be displayed in the style of a progress bar, a heart-shaped fill method, or a five-pointed star fill method; while the digital display of the second trust level can be more accurate. For example, assuming that the current second trust level of the non-player character in the player character is 50, and the reference trust level is 100, the player can accurately understand the changes in the non-player character's trust level in himself.

[0164] In some optional implementations, the information processing method in the game provided by the present application may also include the following steps S280 to S290.

[0165] Step S280: when the first trust level is determined, determining a trust score of the non-player character corresponding to the first trust level for the session information.

[0166] Step S290: updating the second trust level displayed in the information panel according to the trust score.

[0167] In this embodiment, the non-player character is provided with corresponding trust scores for different first trust levels of the session information input by the player, respectively, and the trust scores are used to quantify the first trust levels.

[0168] Furthermore, in this embodiment, after determining the trust score corresponding to the first trust level, the second trust level of the non-player character to the player character may be updated based on the trust score of the non-player character to the current session information.

[0169] The specific updating and displaying process may be: calculating the sum of the trust value corresponding to the current second trust of the non-player character to the player character and the trust score, taking the sum as the updated second trust, and displaying the updated second trust in the information panel.

[0170] It should be noted that, in this embodiment, an initial value can be set for the second trust of the non-player character to the player character, that is, the initial trust of the non-player character to the player character. In the game task, the initial value of the second trust of the non-player character to each player character can be a preset fixed value, or it can be a value determined according to the personality information of the player character. For example, the initial value of the second trust of the non-player character to each player character is 30; or, if the appearance of player character 1 is neat, clean, and smiling, the initial value of the second trust of the non-player character to player character 1 is 40; if the appearance of player character 2 is sloppy and gloomy, the initial value of the second trust of the non-player character to player character 2 is 20; this embodiment is not specifically limited and can be set according to actual needs.

[0171] Based on the initial value of the second trust level, when the reply information is determined for the first time, the trust score corresponding to the first trust level corresponding to the first time the reply information is determined is added to the initial value to obtain the second trust level.

[0172] As shown in Table 2, Table 2 is an example of the correspondence between the first trust level and the trust score provided in an embodiment of the present application.

[0173] Table 2 Example of the correspondence between the first trust level and the trust score

[0174] First Trust Trust Score Complete trust +20 Partial Trust +10 neutral 0 Slightly doubtful -10 Strong suspicion -20 Directly see through Clear

[0175] It should be noted that in different game tasks, the trust score can be set to different specific values, and the specific values ​​of the above trust scores are only examples. Among them, when the first trust is directly seen through, the second trust currently possessed by the player character is cleared, that is, the trust score corresponding to the first trust when it is directly seen through is the opposite value of the second trust currently possessed by the player character, and it changes dynamically.

[0176] As shown in Table 2, when it is determined that the first trust is full trust, the corresponding trust score can be queried as +20 points, which adds 20 points to the current second trust of the player character, indicating that the non-player character has increased the trust in the player character through the current session information; when it is determined that the first trust is partial trust, the corresponding trust score can be queried as +10 points, which adds 10 points to the current second trust of the player character; when it is determined that the first trust is neutral, the corresponding trust score can be queried as 0 points, which adds 10 points to the current second trust of the player character. There is no addition or subtraction on the basis; when it is determined that the first trust level is a slight suspicion, the corresponding trust score can be queried and is -10 points, then 10 points are reduced on the basis of the current second trust level of the player character; when it is determined that the first trust level is a strong suspicion, the corresponding trust score can be queried and is -20 points, then 20 points are reduced on the basis of the current second trust level of the player character; when it is determined that the first trust level is directly seen through, if the current second trust level of the player character is 60, then the trust score corresponding to the first trust level is -60, that is, the current second trust level of the player character is cleared.

[0177] In some optional embodiments, the information processing method in the game provided by the present application may also include the following step S2100.

[0178] Step S2100: Displaying the remaining number of speeches for the player character to have a conversation with the non-player character through the conversation panel through the graphical user interface; the remaining number of speeches is the difference between the preset number of speeches set for the game task and the number of speeches already made.

[0179] The preset number of speeches set in the above game task refers to the number of times the player character and the non-player character can interact in the game task. For example, in the game task, it can be set that the player can only speak 10 times when interacting with the NPC through the conversation panel.

[0180] The above-mentioned number of times the player character has spoken can be determined by the number of input completion instructions described above. For example, when an input completion instruction is generated once, the number of times the player character has spoken increases once.

[0181] The remaining number of speeches for the player character to have a conversation with the non-player character through the conversation panel can be determined based on the difference between the preset number of speeches and the number of speeches that have been spoken. For example, when the preset number of speeches set for the game task is 10 times and the player has currently spoken 5 times, the remaining number of speeches for the player is 5 times.

[0182] It should be noted that this embodiment does not specifically limit the display position of the above-mentioned remaining number of speeches in the graphical user interface, and it can be displayed at any position in the graphical user interface. Preferably, it can be displayed near the session panel, such as below or above the session panel.

[0183] In some optional embodiments, the information processing method in the game provided by the present application may also include the following steps S2110 to S2120.

[0184] Step S2110: When the remaining number of speeches is equal to or greater than 0, if the updated second trust level satisfies the first preset trust level, it is determined that the game task is successfully executed.

[0185] Step S2120: When the specified condition is met, determining that the game task execution fails;

[0186] The specified conditions include: the remaining number of speeches is less than 0 and the updated second trust does not meet the first preset trust; or the remaining number of speeches is equal to or greater than 0 and the updated second trust meets the second preset trust.

[0187] The purpose of step S2110 and step S2120 is to determine whether the game task is successfully executed based on the remaining number of speeches and the second trust level.

[0188] The first preset trust and the second preset trust can be set according to the gameplay mechanism of the game task. Usually, the first preset trust and the second preset trust are respectively the highest trust and the lowest trust that the non-player character can give to the player character.

[0189] For example, when the task goal of a game task is to make the non-player character completely trust the player character, the first preset trust level may be the highest trust level that the non-player character can have based on the player character, and the second trust level may be the lowest trust level that the non-player character can give to the player character. The trust value of the highest trust level may be 100, indicating that the non-player character completely trusts the player character, and the trust value of the lowest trust level may be 0, indicating that the non-player character completely sees through the player character and believes that the player character is a liar.

[0190] When the task goal of the game task is to make the non-player character completely doubt the player character, that is, the game task needs to reduce the trust level of the non-player character in the player character; then the first preset trust level can be the lowest trust level that the non-player character can have based on the player character, and the second trust level can be the highest trust level that the non-player character can give to the player character; the trust value of the highest trust level can be 100, indicating that the non-player character completely trusts the player character, and the trust value of the lowest trust level can be 0, indicating that the non-player character completely sees through the player character and believes that the player character is a liar.

[0191] Based on this, in this embodiment, when the player's remaining number of speeches is equal to or greater than 0, that is, the player character can interact with the non-player character, if the updated second trust level meets the first preset trust level, it can be determined that the game task is successfully executed.

[0192] On the contrary, if the player's remaining number of speeches is equal to or greater than 0, that is, the player character can interact with non-player characters, and the updated second trust level meets the second preset trust level, it can be determined that the game task has failed; or, when the remaining number of speeches is less than 0 and the updated second trust level does not meet the first preset trust level, it is determined that the game task has failed; that is, when the player character can interact with non-player characters, and the level of trust between the player character and the non-player character has not reached specific requirements, it is determined that the game task has failed.

[0193] In some optional embodiments, the information processing method in the game provided by the present application may also include the following step S2120.

[0194] Step S2120: determining the execution progress of the game task according to the second trust level, and displaying a progress indicator for representing the execution progress of the game task in the information panel.

[0195] In this embodiment, the execution progress of the game task refers to the degree reached by the player in the process of completing the game task. The progress mark used to characterize the execution progress can help players more intuitively understand their current status and goals to be completed. The progress mark may include but is not limited to: a progress bar mark, an icon change mark, a text description mark, a numerical mark, etc., without specific limitation.

[0196] Next, combine Figure 4 And a specific example is provided to describe in detail the information processing method in the game provided by this application.

[0197] like Figure 4As shown, in the graphical user interface 2000, player characters, non-player characters and the task objective of the current game task "Make Zhang San believe that you are his brother Li Si, and you can get 100 gold coins" are displayed; among them, Zhang San is the name of the non-player character in the current game task, that is, the non-player character displayed in the graphical user interface 2000.

[0198] Based on the graphical user interface 2000, if the player character finds the non-player character "Zhang San" and moves to the interactive range of the non-player character "Zhang San" (such as a distance of 1 meter), the graphical user interface 2000 is switched to the graphical user interface 2001, and the distance between the player character and the non-player character "Zhang San" is 1 meter, then the graphical user interface 2001 can be further switched to the graphical user interface 2002, in which the conversation panel for the dialogue interaction between the player character and the non-player character "Zhang San" is displayed, as well as the task clues of the game task are displayed; wherein, the publishing control of the conversation information is displayed in the conversation panel; the task clues of the game task are true and false, for example, the first clue "Zhang San and Li Si met when they were 4 years old" and the second clue "Zhang San has a son, nicknamed Goudan" are true clues; the third clue "Zhang San fell down from a tree when he was a child" is a false clue. In addition, when the player character enters the interactive range with the non-player character, the non-player character can have a conversation with the player character to advance the game process. Specifically, the speech information of the non-player character "Excuse me, are you...? What do you want to talk to me about?" can be displayed in the graphical user interface. In this specific example, the reply information of the non-player character and the conversation information of the player character are displayed in the upper right corner of the graphical user interface.

[0199] Based on the graphical user interface 2002, the player controlling the player character can input corresponding session information in the session panel, such as "I am Li Si, don't you recognize me?", and the graphical user interface 2002 is switched to the graphical user interface 2003. Based on the graphical user interface 2003, when the player clicks the release control (the release control is displayed in a gray filled state, indicating that the release control is clicked), the session information "I am Li Si, don't you recognize me?" input by the player can be displayed in the graphical user interface, that is, the graphical user interface 2003 is switched to the graphical user interface 2004, and the session information input by the player is displayed in the dialogue record in the upper right corner of the graphical user interface 2004.

[0200] Based on the conversation information input by my family, the electronic device can obtain the conversation information and generate corresponding reply information. After the reply information is generated, it is displayed in the graphical user interface. That is, assuming that the generated reply information is "Are you Li Si? Do you know how we met?", after the reply information is generated, the graphical user interface 2004 is switched to the graphical user interface 2005, and the reply information is displayed in the graphical user interface 2005.

[0201] Next, combine Figure 5 And a specific example, the information processing method in the game provided by this application is further described in detail.

[0202] For more information about GUI 2000 and GUI 2001, please refer to Figure 4 The introduction of will not be repeated here.

[0203] Based on the graphical user interface 2001, when the player character is within the interactive distance of the non-player character, the graphical user interface 2001 is switched to the graphical user interface 2006, and an information panel is displayed in the graphical user interface 2006. The information panel displays the second trust of the non-player character "Zhang San" to the current player character and a progress indicator (such as a progress bar indicator) used to represent the character progress of the current game task; for example, the information panel displays an initial trust value of 20 for the second trust, and a first preset trust of 100 set in the game task; in addition, the remaining number of speeches of the player character is also displayed: 10 times; for the rest of the content displayed in the graphical user interface 2006, please refer to Figure 4 The description of graphical user interface 2002 in will not be repeated here.

[0204] Based on the graphical user interface 2006, if the player Figure 4 As described, the session information "I am Li Si, don't you recognize me?" is input in the session panel, and the graphical user interface 2006 is switched to the graphical user interface 2007, and the publishing control displayed in the graphical user interface 2007 is clicked to publish the session information "I am Li Si, don't you recognize me?", and the graphical user interface 2007 is switched to the graphical user interface 2008.

[0205] At this time, based on the graphical user interface 2008, the game system can generate a reply message "Are you Li Si? Do you know how we met?" Figure 5In the specific example shown, in addition to generating the reply information, a trust score can be given to the session information "I am Li Si, don't you recognize me?" Assuming that the first trust level of the currently determined non-player character "Zhang San" for the session information is "slightly suspicious", that is, combined with the corresponding relationship example shown in Table 2 above, the trust score of the session information can be -10 points; based on this, after generating the reply information and determining the trust score, the graphical user interface 2008 can be switched to the graphical user interface 2009, and in the graphical user interface 2009, the current second trust level of the player character is updated from the trust value 20 corresponding to the initial trust level to 10, that is, the trust level of the non-player character "Zhang San" for the player character has decreased. At the same time, the filling degree of the progress bar mark used to represent the game task is synchronously reduced.

[0206] Based on the graphical user interface 2009, if the player selects the first clue "Zhang San and Li Si knew each other when they were 4 years old" and organizes it into the conversation information "We knew each other when you were 4 years old, have you really forgotten it", and publishes it on the graphical user interface, the graphical user interface 2009 can be switched to the graphical user interface 2010, and the conversation information "We knew each other when you were 4 years old, have you really forgotten it" is displayed in the dialogue record displayed in the upper right corner of the graphical user interface 2010. At this time, the second trust level of the player character is: 10.

[0207] Based on the graphical user interface 2010, the non-player character "Zhang San" can generate corresponding reply information and trust score for the currently input conversation information "We met when you were 4 years old, have you really forgotten?" Since the clue "Zhang San and Li Si met when they were 4 years old" selected by the player is a true clue, the trust level of the non-player character in the conversation information can be improved; assuming that the first trust level of the non-player character "Zhang San" in the conversation information is partial trust, the corresponding trust score is +10 points; in addition, when the first trust level is partial trust, the reply information generated by the non-player character will have the semantics and tone of trust, such as the generated reply information "

Surprise

[0208] It should be noted that Figure 4 and Figure 5 The dotted lines in the figure are fictitious lines for the sake of ease of understanding and do not exist on the graphical user interface displayed on the terminal device.

[0209] So far, the method provided in this embodiment has been described. The non-player character can determine whether to trust the conversation information input by the player character, and use this to determine different reply information, so that the non-player character can dynamically adjust the reply information based on the conversation information of the player character without following a preset script.

[0210] In addition, when the reply information is determined according to the first trust level, the player character and the non-player character can conduct in-depth psychological games and apply strategies, which increases the challenge and fun of the game. For example, according to the trust level of the non-player character for the session information, a personalized response can be provided for the session information, making the player feel that the interaction with the NPC is more real. In addition, the non-player character determines the reply information according to the change in the trust level of the session information, which allows the player to experience the evolution of the relationship with the NPC, increase the player's emotional investment, and gain a sense of accomplishment. At the same time, in this case, the player can try to explore different trust paths and results by entering different session information, so that the player's exploration space can be increased.

[0211] Corresponding to the information processing method in the game provided by the embodiment of the present application, the embodiment of the present application also provides an information processing device 3000 in the game, such as Figure 6 As shown, the device 3000 includes: an acquisition unit 3001 and a determination unit 3002;

[0212] The acquisition unit 3001 is used to acquire the session information input by the player character for the non-player character in the game task;

[0213] The determining unit 3002 is used to determine a first trust level of the non-player character to the session information;

[0214] The determining unit 3002 is further configured to determine, according to the first trust level, reply information of the non-player character to the conversation information.

[0215] The determination unit 3002 is specifically used to generate a strategy prompt word based on the session information, the task description information of the game task, the player personality information of the player character, and the non-player personality information of the non-player character; input the strategy prompt word into a pre-trained response information generation model, and output the first trust through the pre-trained response information generation model.

[0216] The determination unit 3002 is further specifically used to input the strategy prompt word into a pre-trained response information generation model, and determine the emotion type corresponding to the session information in the strategy prompt word and the behavior attribute of the player character corresponding to the session information through the pre-trained response information generation model; and determine and output the first trust degree of the non-player character for the session information based on the emotion type and the behavior attribute of the player character.

[0217] Optionally, the pre-trained response information generation model includes a behavior analysis module; the task description information of the game task includes a plurality of task clues with different degrees of authenticity, and the degree of authenticity is used to indicate the degree of trust of the non-player character in the task clue;

[0218] The determining unit 3002 is specifically further used for the behavior analysis module of the pre-trained response information generation model to determine the behavior attribute of the player character corresponding to the session information according to the authenticity corresponding to the task clue contained in the session information.

[0219] The determination unit 3002 is further specifically used to determine that the behavior attribute of the player character corresponding to the session information is a deceptive behavior when the authenticity corresponding to the task clue contained in the session information is less than or equal to the preset authenticity; and to determine that the behavior attribute of the player character corresponding to the session information is an honest behavior when the authenticity corresponding to the character clue contained in the session information is greater than the preset authenticity.

[0220] Optionally, the pre-trained reply information generation model includes a sentiment analysis module;

[0221] The determining unit 3002 is further specifically configured to parse the emotion type corresponding to the conversation information in the strategy prompt word through the emotion analysis module of the pre-trained response information generation model.

[0222] Optionally, the pre-trained reply information generation model includes a prediction classification module;

[0223] The determination unit 3002 is further specifically used to determine the predicted probability values ​​of the first trust of the non-player character for the session information corresponding to each reference trust through the prediction classification module of the pre-trained reply information generation model; determine the reference trust whose predicted probability value exceeds a preset threshold as the first trust of the non-player character for the session information and output the first trust of the non-player character for the session information.

[0224] Optionally, the pre-trained reply information generation model includes an information generation module;

[0225] The determination unit 3002 is further specifically used to generate a reply prompt word according to the guidance information corresponding to the first trust level and the strategy prompt word; input the reply prompt word into the pre-trained reply information generation model, and output the reply information of the non-player character to the conversation information through the information generation module in the pre-trained reply information generation model.

[0226] Optionally, the information processing device 3000 in the game further includes a training unit 3003;

[0227] The training unit 3003 is used to obtain a plurality of preset pairs of training sample pairs, wherein the training sample pairs include a first training sample and a second training sample, wherein the first training sample includes: a sample corpus associated with the game task and a target trust; the second training sample includes: the sample corpus and target reply information; the target reply information matches the target trust; and according to each pair of the first training sample and the second training sample, the reply information generation model to be trained is trained until a preset training end condition is reached, thereby obtaining the pre-trained reply information generation model.

[0228] Optionally, the training unit 3003 is specifically used to input any training sample pair into the reply information generation model to be trained, the reply information generation model to be trained outputs a predicted trust according to the first training sample in the input training sample pair, and determines a first difference between the reference trust and the target trust; the reply information generation model to be trained outputs predicted reply information according to the second training sample in the input training sample pair, and determines a second difference between the predicted reply information and the target reply information; the loss value of the loss function corresponding to the reply information generation model to be trained is determined according to the first difference and the second difference, and the parameters of the reply information generation model to be trained are updated and adjusted based on the principle of making the loss value less than a preset loss value to obtain the pre-trained reply information generation model.

[0229] Optionally, the information processing device 3000 in the game also includes a display unit 3005; the display unit 3005 provides a graphical user interface through a terminal device; the player character and at least one non-player character controlled by the terminal device are displayed through the graphical user interface; in response to a session event being triggered between the player character and the non-player character, a session panel is displayed; the session panel is used to receive session information input by the player character.

[0230] Optionally, the acquisition unit 3001 is specifically configured to acquire the session information input by the player character for the non-player character in the game task in response to an input completion instruction of the session information by the player character in the session panel.

[0231] Optionally, the display unit 3004 is further used to display the reply information through the graphical user interface after determining the reply information, and / or voice broadcast the reply information.

[0232] Optionally, the display unit 3004 is further configured to display an information panel through the graphical user interface, wherein the information panel is configured to display a second trust level of the non-player character toward the player character;

[0233] Optionally, the display unit 3004 is further configured to determine, when determining the first trust level, a trust score of the non-player character corresponding to the first trust level for the session information; and update a second trust level displayed in the information panel according to the trust score.

[0234] Optionally, the display unit 3004 is further used to display, through the graphical user interface, the remaining number of speeches of the player character in conversation with the non-player character through the conversation panel; the remaining number of speeches is the difference between the preset number of speeches set for the game task and the number of speeches already made.

[0235] Optionally, the determination unit 3002 is also used to determine that the game task is successfully executed when the remaining number of speeches is equal to or greater than 0 and if the updated second trust level satisfies the first preset trust level; and to determine that the game task is failed when specified conditions are met; wherein the specified conditions include: the remaining number of speeches is less than 0 and the updated second trust level does not satisfy the first preset trust level; or, the remaining number of speeches is equal to or greater than 0 and the updated second trust level satisfies the second preset trust level.

[0236] Optionally, the display unit 3004 is further used to determine the execution progress of the game task according to the second trust level, and display a progress indicator used to represent the execution progress of the game task in the information panel.

[0237] Corresponding to the information processing method in a game provided in the embodiment of the present application, the embodiment of the present application also provides an electronic device 4000 for information processing in a game, such as Figure 7 As shown, the electronic device 4000 includes: a processor 4001; and a memory 4002, which is used to store the program of the information processing method in the game. After the device is powered on and runs the program of the information processing method in the game through the processor, the method steps described in any of the above embodiments are executed.

[0238] Corresponding to the information processing method in the game provided in the embodiments of the present application, the embodiments of the present application also provide a computer-readable storage medium storing a program of the information processing method in the game, which is run by a processor to execute the method steps described in any of the above embodiments.

[0239] It should be noted that for the detailed description of the device, electronic device and computer-readable storage medium provided in the embodiments of the present application, reference can be made to the relevant description of the information processing method embodiment in the game provided in the embodiments of the present application, which will not be repeated here.

[0240] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

[0241] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0242] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0243] 1. Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable operations, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0244] 2. Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0245] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. A method for processing information in a game, characterized in that: The method comprises: Get the conversation information entered by the player character for the non-player character in the game task; determining a first trust level of the non-player character for the session information; Determine reply information of the non-player character to the conversation information according to the first trust level.

2. The method according to claim 1, characterized in that The determining a first trust level of the non-player character for the session information includes: Generate a strategy prompt word according to the session information, the task description information of the game task, the player character's personality information, and the non-player character's non-player personality information; The strategy prompt word is input into a pre-trained reply information generation model, and the first trust degree is output through the pre-trained reply information generation model.

3. The method according to claim 2, characterized in that The step of inputting the strategy prompt word into a pre-trained response information generation model, and outputting the first trust level through the pre-trained response information generation model, includes: Inputting the strategy prompt word into a pre-trained response information generation model, and determining the emotion type corresponding to the conversation information in the strategy prompt word and the behavior attribute of the player character corresponding to the conversation information through the pre-trained response information generation model; According to the emotion type and the behavior attribute of the player character, a first trust degree of the non-player character to the session information is determined and output.

4. The method according to claim 3, characterized in that The pre-trained response information generation model includes a behavior analysis module; the task description information of the game task includes a plurality of task clues with different degrees of authenticity, and the degree of authenticity is used to indicate the degree of trust of the non-player character in the task clue; The step of determining the behavior attribute of the player character corresponding to the conversation information by using the pre-trained reply information generation model comprises: The behavior analysis module of the pre-trained response information generation model determines the behavior attribute of the player character corresponding to the session information according to the authenticity corresponding to the task clue contained in the session information.

5. The method according to claim 4, characterized in that The determining the behavior attribute of the player character corresponding to the session information according to the authenticity corresponding to the task clue contained in the session information includes: When the authenticity of the task clues included in the session information is less than or equal to the preset authenticity, determining that the behavior attribute of the player character corresponding to the session information is a cheating behavior; When the authenticity corresponding to the character clue contained in the session information is greater than the preset authenticity, it is determined that the behavior attribute of the player character corresponding to the session information is an honest behavior.

6. The method according to claim 3, characterized in that The pre-trained reply information generation model includes a sentiment analysis module; the step of determining the sentiment type corresponding to the conversation information in the strategy prompt word by using the pre-trained reply information generation model includes: The sentiment type corresponding to the conversation information in the strategy prompt word is analyzed by the sentiment analysis module of the pre-trained response information generation model.

7. The method according to claim 3, characterized in that The pre-trained reply information generation model includes a prediction classification module; the step of determining and outputting a first trust level of the non-player character for the conversation information through the pre-trained reply information generation model includes: Determining, by the prediction classification module of the pre-trained reply information generation model, predicted probability values ​​of the first trust of the non-player character for the conversation information corresponding to each reference trust respectively; The reference trust level whose predicted probability value exceeds a preset threshold is determined as a first trust level of the non-player character for the session information, and the first trust level of the non-player character for the session information is output.

8. The method according to claim 2, characterized in that: The pre-trained reply information generation model includes an information generation module; the determining, according to the first trust level, the reply information of the non-player character to the conversation information includes: generating a reply prompt word according to the guidance information corresponding to the first trust level and the strategy prompt word; The reply prompt word is input into the pre-trained reply information generation model, and the reply information of the non-player character to the conversation information is output through the information generation module in the pre-trained reply information generation model.

9. The method according to claim 2, characterized in that: The pre-trained reply information generation model is trained in the following manner: Acquire a plurality of preset training sample pairs, wherein the training sample pairs include a first training sample and a second training sample, wherein the first training sample includes: a sample corpus associated with the game task and a target confidence; the second training sample includes: the sample corpus and target answer information; the target answer information matches the target confidence; The reply information generation model to be trained is trained according to each pair of the first training samples and the second training samples until a preset training end condition is reached, thereby obtaining the pre-trained reply information generation model.

10. The method according to claim 9, characterized in that The step of training the reply information generation model to be trained according to each pair of the first training samples and the second training samples until a preset training end condition is reached to obtain the pre-trained reply information generation model comprises: Input any training sample pair to the answer information generation model to be trained, the answer information generation model to be trained outputs a predicted trust according to the first training sample in the input training sample pair, and determines a first difference between the reference trust and the target trust; The answer information generation model to be trained outputs predicted answer information according to the second training sample in the input training sample pair, and determines a second difference between the predicted answer information and the target answer information; The loss value of the loss function corresponding to the reply information generation model to be trained is determined according to the first difference and the second difference, and the parameters of the reply information generation model to be trained are updated and adjusted based on the principle of making the loss value less than the preset loss value to obtain the pre-trained reply information generation model.

11. The method according to claim 1, characterized in that: Providing a graphical user interface through a terminal device; the method further comprises: displaying the player character and at least one non-player character controlled by the terminal device through the graphical user interface; In response to a session event being triggered between the player character and the non-player character, a session panel is displayed; the session panel is used to receive session information input by the player character.

12. The method according to claim 11, characterized in that The obtaining of the session information input by the player character to the non-player character in the game task includes: In response to an instruction to complete inputting the session information of the player character in the session panel, the session information inputted by the player character for the non-player character in the game task is obtained.

13. The method according to claim 11, characterized in that The method further comprises: After the reply information is determined, the reply information is displayed through the graphical user interface, and / or the reply information is voice broadcasted.

14. The method according to claim 11, characterized in that The method further comprises: An information panel is displayed through the graphical user interface, wherein the information panel is used to display a second trust level of the non-player character toward the player character.

15. The method according to claim 14, characterized in that The method further comprises: When the first trust level is determined, determining a trust score of the non-player character for the session information corresponding to the first trust level; The second trust level in the information panel is updated and displayed according to the trust score.

16. The method according to claim 11, characterized in that The method further comprises: The remaining number of speeches for the player character to have a conversation with the non-player character through the conversation panel is displayed through the graphical user interface; the remaining number of speeches is the difference between the preset number of speeches set for the game task and the number of speeches already made.

17. The method according to claim 16, characterized in that The method further comprises: When the remaining number of speeches is equal to or greater than 0, if the updated second trust level meets the first preset trust level, it is determined that the game task is successfully executed; When a specified condition is met, determining that the game task execution fails; The specified conditions include: the remaining number of speeches is less than 0 and the updated second trust does not meet the first preset trust; or the remaining number of speeches is equal to or greater than 0 and the updated second trust meets the second preset trust.

18. The method according to claim 14, characterized in that The method further comprises: The execution progress of the game task is determined according to the second trust level, and a progress indicator for representing the execution progress of the game task is displayed in the information panel.

19. An information processing device in a game, characterized in that: The device comprises: an acquisition unit and a determination unit; The acquisition unit is used to acquire the session information input by the player character for the non-player character in the game task; The determining unit is configured to determine a first degree of trust of the non-player character in the session information; The determining unit is further configured to determine, according to the first trust level, reply information of the non-player character to the conversation information.

20. An electronic device, characterized in that: include: processor; as well as The memory is used to store a data processing program. After the electronic device is powered on and the program is run by the processor, the method according to any one of claims 1 to 18 is executed.

21. A computer-readable storage medium, characterized in that: A data processing program is stored, and the program is run by a processor to execute the method according to any one of claims 1 to 18.

Images