Game prop generation method based on story text and related equipment

Abstract

The invention provides a game prop generation method based on a story text and related equipment, in the method, a game prop is generated in an interaction process that a player character and a non-player character tell a story in turn, and since the player character does not input the same story every time the story is narrated, the game prop is generated in the interaction process; the stories output by the non-player character when the stories are continued each time are not the same, so that for the target prop keywords, the target story background data and the target prop attribute data generated based on the story texts are different, and even if the target prop template is the same, the target props can be continuously stored in the target props. In addition, the target game prop generated after the data and the target prop template are bound has uniqueness and uniqueness, the prop itself and the use effect of the prop are all extremely personalized, and the game experience of generating the entity game prop by a virtual story can be brought, so that the requirements of players can be met.

Description

TECHNICAL FIELD

[0001] The present application relates to the game technical field, and particularly to a game prop generation method based on story text and related equipment. BACKGROUND

[0002] At present, when obtaining game props, the commonly used method is that the player first completes a specific task in the game, and then the system settles the task completion, and according to the settlement, the game props are issued to the player. However, in this method, the game props are pre-uniformly set, regardless of who the player is or how the player performs in the game process, the same game props are issued to the player after completing the same task, and the same game props are the same from the display effect to the use effect, which is difficult to meet the personalized needs of the player.

[0003] Therefore, in the current game scene, there is a technical problem that game props are difficult to meet the personalized needs of the player, which needs to be improved. SUMMARY

[0004] The embodiments of the present application provide a game prop generation method based on story text and related equipment to alleviate the technical problem that game props are difficult to meet the personalized needs of the player in the current game scene.

[0005] To solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0006] The present application provides a game prop generation method based on story text, the method comprising:

[0007] In response to a trigger instruction of a target prop keyword, a historical story text and a current story text are obtained, the historical story text includes a historical player story text input by a player character and a historical continuation story text output by a non-player character, the current story text includes a current player story text input by the player character and a current continuation story text output by the non-player character, and the current continuation story text includes at least one prop keyword;

[0008] A target prop template corresponding to the target prop keyword is determined from a preset prop template library, and target story background data and target prop attribute data corresponding to the target prop keyword are generated according to the historical story text and the current story text;

[0009] The target story background data and the target prop attribute data are bound to the target prop template, and a target game prop corresponding to the target prop keyword is generated and displayed.

[0010] In one embodiment, the step of determining the target prop template corresponding to the target prop keyword from the preset prop template library comprises:

[0011] obtaining a preset prop template library, the preset prop template library comprising a plurality of preset prop templates, each of the preset prop templates comprising a corresponding preset prop name;

[0012] determining a target preset prop name identical to the target prop keyword from the preset prop names, and determining a preset prop template corresponding to the target preset prop name as a target prop template.

[0013] In another embodiment, the step of determining the target prop template corresponding to the target prop keyword from the preset prop template library comprises:

[0014] obtaining a preset prop template library, the preset prop template library comprising a plurality of preset prop templates, each of the preset prop templates comprising a corresponding preset prop category name;

[0015] calling a large language model to recognize a target semantic of the target prop keyword;

[0016] determining a target preset prop category name closest to the target semantic from the preset prop category names, and determining a preset prop template corresponding to the target preset prop category name as a target prop template.

[0017] In an embodiment, the target prop template comprises a target static template, the target static template comprising a target prop image, after the step of determining the target preset prop category closest to the target semantic from the preset prop categories, and determining a preset prop template corresponding to the target preset prop category as a target prop template, the method further comprises:

[0018] obtaining a variable image parameter of the target prop image;

[0019] updating the variable image parameter based on the target semantic to obtain an updated variable image parameter;

[0020] updating the target prop image based on the updated variable image parameter to obtain an updated target prop template.

[0021] In an embodiment, the step of generating target story background data and target prop attribute data corresponding to the target prop keyword according to the historical story text and the current story text comprises:

[0022] calling a large language model to extract target story background description information and target prop description information from the historical story text and the current story text;

[0023] Based on the target story background description information, generate a target prop background image, and based on the target prop description information, generate target prop basic attribute data and target prop usage attribute data.

[0024] In one embodiment, the target item template includes a target dynamic template and a target static template. The step of binding the target story background data and the target item attribute data to the target item template, and generating and displaying the target game item corresponding to the target item keyword, includes:

[0025] Bind the target story background data and the target item attribute data to the target static template to generate static target game items;

[0026] Based on the target dynamic template, generate and display the transformation animation from the target item keyword to the static target game item;

[0027] After the transformation animation finishes playing, the static target game item is displayed.

[0028] In one embodiment, after generating and displaying the target game item corresponding to the target item keyword, the method further includes:

[0029] In response to a command to use the target game item, the attribute data of the target item is obtained;

[0030] Based on the target item attribute data, generate and display the player character's first battle lines, the target game item's battle effect lines, and the non-player character's second battle lines.

[0031] Meanwhile, this application also provides a game item generation device based on story text, the device comprising:

[0032] The first response module is used to respond to the trigger command of the target item keyword, and obtain the historical story text and the current story text. The historical story text includes the historical player story text input by the player character and the historical continuation story text output by the non-player character. The current story text includes the current player story text input by the player character and the current continuation story text output by the non-player character. The current continuation story text includes at least one item keyword.

[0033] The first generation module is used to determine the target item template corresponding to the target item keyword from the preset item template library, and generate the target story background data and target item attribute data corresponding to the target item keyword based on the historical story text and the current story text;

[0034] The second generation module is used to bind the target story background data and the target item attribute data with the target item template to generate and display the target game item corresponding to the target item keyword.

[0035] This application also provides an electronic device, including a memory and a processor; the memory stores an application program, and the processor is configured to run the application program within the memory to perform the steps in the story-text-based game item generation method described above.

[0036] This application provides a computer-readable storage medium storing multiple instructions adapted for loading by a processor to execute the steps in the above-described method for generating game props based on story text.

[0037] Beneficial Effects: This application provides a method and related equipment for generating game props based on story text. The method first responds to a trigger command for a target prop keyword, and obtains historical story text and current story text. The historical story text includes historical player story text input by the player character and historical continuation story text output by non-player characters. The current story text includes current player story text input by the player character and current continuation story text output by non-player characters. The current continuation story text includes at least one prop keyword. Then, the method determines the target prop template corresponding to the target prop keyword from a preset prop template library, and generates target story background data and target prop attribute data corresponding to the target prop keyword based on the historical story text and current story text. Finally, the method binds the target story background data and target prop attribute data to the target prop template to generate and display the target game prop corresponding to the target prop keyword. In this application, game items are generated during the interactive process of player characters and non-player characters taking turns telling stories. Since the player character does not input the same story each time he tells the story, and the non-player character does not output the same story each time he continues the story, the target story background data and target item attribute data generated based on these story texts are also different for the target item keywords. Even if the same target item template is used, the target game item generated after binding these data with the target item template is unique and one-of-a-kind. Both the item itself and its usage effect are highly personalized, and it can bring the game experience of generating physical game items from virtual stories, thus meeting the needs of players. Attached Figure Description

[0038] The technical solution and other beneficial effects of this application will become apparent from the following detailed description of specific embodiments in conjunction with the accompanying drawings.

[0039] Figure 1 A schematic diagram of a game item generation method provided in this application embodiment.

[0040] Figure 2 This is a flowchart illustrating the game item generation method based on item keywords provided in this application embodiment.

[0041] Figure 3 This is a schematic diagram of the game dialogue interface in an embodiment of this application.

[0042] Figure 4 This is a first schematic diagram of the game item generation interface in the embodiments of this application.

[0043] Figure 5 This is a schematic diagram of the target static template of the "sword" card in the embodiments of this application.

[0044] Figure 6 This is a second schematic diagram of the game item generation interface in the embodiments of this application.

[0045] Figure 7 This is a third schematic diagram of the game item generation interface in the embodiments of this application.

[0046] Figure 8 This is a fourth schematic diagram of the game item generation interface in the embodiments of this application.

[0047] Figure 9 This is the fifth schematic diagram of the game item generation interface in the embodiments of this application.

[0048] Figure 10 This is the sixth schematic diagram of the game item generation interface in the embodiments of this application.

[0049] Figure 11 This is a schematic diagram of the static target game item of the "sword" card in the embodiments of this application.

[0050] Figure 12 This is a first schematic diagram of the game item usage interface in the first battle mode of this application embodiment.

[0051] Figure 13 This is a second schematic diagram of the game item usage interface in the first battle mode of this application embodiment.

[0052] Figure 14 This is a third schematic diagram of the game item usage interface in the first battle mode of the embodiments of this application.

[0053] Figure 15 This is a fourth schematic diagram of the game item usage interface in the first battle mode of the embodiments of this application.

[0054] Figure 16 This is the fifth schematic diagram of the game item usage interface in the first battle mode of this application embodiment.

[0055] Figure 17 This is a first schematic diagram of the game item usage interface in the second battle mode of this application embodiment.

[0056] Figure 18 This is a second schematic diagram of the game item usage interface in the second battle mode of this application embodiment.

[0057] Figure 19 This is a third schematic diagram of the game item usage interface in the second battle mode of this application embodiment.

[0058] Figure 20 This is a fourth schematic diagram of the game item usage interface in the second battle mode of this application embodiment.

[0059] Figure 21 This is the fifth schematic diagram of the game item usage interface in the second battle mode of this application embodiment.

[0060] Figure 22 This is the sixth schematic diagram of the game item usage interface in the second battle mode of this application embodiment.

[0061] Figure 23 This is the seventh schematic diagram of the game item usage interface in the second battle mode of this application embodiment.

[0062] Figure 24 This is a schematic diagram of the structure for generating game props provided in the embodiments of this application.

[0063] Figure 25 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0064] Explanation of reference numerals in the attached figures:

[0065] Game client 11; Game server 12; Large language model 13; Player character 1; Non-player character 2; First dialog box 3; Second dialog box 4; Text input box 5; First strength value display area 6; Second strength value display area 7; Game item display area 8; Indicator bar 9; Background image display area 501; Text display area 502; Flower model 110; Sword model 120; Card 130; First battle lines 200; Battle effect lines 300; Second battle lines 400; Action lines 500; Twisted lines 600; First position A; Second position B; First response module 10; First generation module 20; Second generation module 30; Radio frequency circuit 101; Memory 102; Input unit 103; Display unit 104; Sensor 105; Audio circuit 106; WiFi module 107; Processor 108. Detailed Implementation

[0066] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0067] Please see Figure 1 , Figure 1 This is a schematic diagram of a scenario in which the game prop generation method provided in this application embodiment is applied. The scenario includes a game client 11, a game server 12, and a large language model 13. The game client 11 has human-computer interaction functions and is used to run the game and display the game interface. Players can perform interactive operations on the game interface. The game server 12 is a local / remote server and is used to receive the interactive instructions generated after the player performs interactive operations on the game interface. When necessary, it calls the large language model 13 to process the interactive instructions and finally displays the processing results on the game client 11.

[0068] The game item generation method in this application is applied to a game server 12. During generation, a player triggers a target item keyword on the game device 11. The trigger command generated by this operation is received by the game server 12. In response to this trigger command, the game server 12 first obtains the historical story text and the current story text. The historical story text includes the historical player story text input by the player character and the historical continuation story text output by the non-player character. The current story text includes the current player story text input by the player character and the current continuation story text output by the non-player character. The current continuation story text includes at least one item keyword, and the target item keyword is any one of these item keywords. Then, the game server 12 determines the target item template corresponding to the target item keyword from a preset item template library, and generates the target story background data and target item attribute data corresponding to the target item keyword based on the historical story text and the current story text. During this process, the game server 12 may call the large language model 13 for processing as needed. Finally, the game server 12 binds the target story background data and target item attribute data to the target item template, generates and displays the target game item corresponding to the target item keyword on the game-related interface. The generation process of the above-mentioned game props will be described in detail in the following embodiments.

[0069] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for generating game items based on story text, as provided in an embodiment of this application. The method specifically includes:

[0070] S1: In response to the trigger command for the target item keyword, obtain the historical story text and the current story text. The historical story text includes the historical player story text input by the player character and the historical continuation story text output by the non-player character. The current story text includes the current player story text input by the player character and the current continuation story text output by the non-player character. The current continuation story text includes at least one item keyword.

[0071] In this embodiment, game items are generated during the process of players and non-player characters taking turns telling stories, and the storytelling process needs to take place in the game dialogue interface. For example... Figure 3 As shown, the game dialogue interface includes player character 1, non-player character 2, a first dialog box 3, a second dialog box 4, and a text input box 5. Player character 1 is a virtual character controlled by the player. The player can enter text in the text input box 5 and send it. This text will be displayed in the first dialog box 3 as input for player character 1. Non-player character 2 is a virtual character controlled by the game server and the large language model. Text output by non-player character 2 will be displayed in the second dialog box 4. The first dialog box 3 and the second dialog box 4 are not displayed when the player is not inputting text. The first dialog box 3 will only appear after the player enters and sends text, and the second dialog box 4 will only appear when non-player character 2 outputs text.

[0072] For ease of explanation, in this embodiment, the input text of player character 1 is defined as player story text. After the game starts, the player first performs the input operation of player story text in text input box 5. This operation will generate a corresponding input command, which the game server can receive through the game dialogue interface. The input operation is considered complete after the player inputs and sends the input. When performing the input operation, the operation is not limited to various input methods such as keyboard input, voice input, copy and paste input, etc., that is, this application does not limit the specific method of input operation.

[0073] like Figure 4 As shown, in response to the input command, the game server displays the player's story text in the first dialog box 3, and simultaneously calls the large language model to process the player's story text, displaying the processed text in the second dialog box 4. The processed text is regenerated by the large language model in combination with the game background and the ongoing storyline. The text content is a continuation of the story described in the player's story text. For ease of explanation, in this embodiment, the output text of the non-player character 2 is defined as the continuation story text.

[0074] For example, such as Figure 4As shown, if the player's story text is "Once upon a time, there was an old mage in a mountain. The old mage had a magical sword to offer to a dragon far away," the generated continuation story text could be "The dragon angrily breathed out flames, and the sword bathed in the fire, radiating endless light!" For example... Figure 6 As shown, if the player's story text is "There was once a kingdom where there was a mysterious moonflower that could bring wealth", the generated continuation story text could be "The king ordered his men to wipe out the garden so that he could have the moonflower for himself. Broken vines were scattered all over the ground, and thorn flowers wept softly in the wind."

[0075] The input from player character 1 and the output from non-player character 2 alternate in multiple rounds. In each round, when non-player character 2 outputs the continued story text, the game server first checks if the continued story text contains item keywords before deciding how to display it. Item keywords refer to words related to game items that player character 1 can obtain. For example, if the game item is a sword, the item keyword could be "sword"; if the game item is a plant, the item keyword could be "grass," "moonlight grass," "silver leaf," "thorn flower," etc.

[0076] When generating continuation story text, the large language model generates it based on input prompts. These prompts can indicate whether non-player character 2 should output item keywords. For example, it might instruct, "When my story fits certain elements, non-player character 2 needs to find a way to integrate at least one of these elements into the story; if they don't fit, they won't be integrated." The words describing these elements are the item keywords. Based on this condition, the large language model autonomously determines whether the text is suitable and generates continuation story text with item keywords; otherwise, it generates text without them. Alternatively, the large language model can generate continuation story text based on prompts without item keyword introductory conditions. In this case, whether the model includes item keywords is uncertain. This uncertainty increases the difficulty of obtaining game items, encouraging player creativity and enhancing the overall experience. Those skilled in the art can choose to add or omit item keyword introductory conditions to the prompts as needed to achieve the desired game effect.

[0077] If the item keyword is not present in the continuation story text, the continuation story text will be displayed directly in the second dialog box 4, and the player will proceed directly to the next round of input.

[0078] If the continuation story text contains item keywords, the continuation story text will be displayed in the second dialog box 4, highlighting the item keywords. Then, the player can proceed to the item generation step. Highlighting can include, but is not limited to, various display methods such as increasing font size / boldness / italicization, highlighting the font / its area, and adding identifiers before and after the font, as long as it allows the player to intuitively discover the existence of the item keywords. For example, such as... Figure 4 As shown, if the keyword "sword" appears in the story text, identifiers such as "[ ]" can be added before and after "sword" to highlight it. For example... Figure 6 As shown, if the story text contains the keywords "moonlight grass", "vines" and "thorn flowers", then identifiers such as "[ ]" can be added before and after "moonlight grass", "vines" and "thorn flowers" to highlight them.

[0079] When item keywords exist in the continuation story text, the current player story text and the continuation story text are defined as the current player story text and the current continuation story text, collectively referred to as the current story text. The player story texts and continuation story texts from previous rounds are defined as the historical player story text and the historical continuation story text, collectively referred to as the historical story text. The target item keyword is any item keyword in the currently displayed continuation story text. In addition to being highlighted, each item keyword will have its trigger function activated by the game server. Players can perform trigger operations on the target item keyword, and the game server can receive the trigger commands generated by these operations. Trigger operations include, but are not limited to, mouse clicks and finger touches. Figure 4 and Figure 6 The diagram illustrates the mouse click mechanism. In response to this trigger, the game server retrieves the aforementioned story text.

[0080] S2: Determine the target item template corresponding to the target item keyword from the preset item template library, and generate the target story background data and target item attribute data corresponding to the target item keyword based on the historical story text and the current story text.

[0081] In response to the trigger command, the game server determines the target item template corresponding to the target item keyword from the preset item template library. The item template is the basic framework for generating game items, including pre-set visual elements. For example, when the game item is a card, the item template can include the card's appearance and the images and / or text elements displayed on the card. Since there are multiple item keywords, and therefore multiple possible target game items generated based on them, multiple item templates are pre-made and stored in the preset item template library to quickly generate and display the required game items. After determining the target item keyword, the template that best matches that keyword is selected and designated as the target item template.

[0082] The historical story text and the current story text together constitute the complete narrative of the entire story, containing a relatively rich amount of information. This story is a personalized product created through interaction between player character 1 and non-player character 2. The most relevant and personalized parts related to game items are mainly reflected in two aspects: the story background of the item's creation and the item's own characteristics and usage effects. To obtain personalized game items, this step, while determining the target item template, also needs to generate target story background data and target item attribute data corresponding to the target item keywords based on the historical story text and the current story text. The target story background data describes the story background of the target game item, while the target item attribute data describes the target game item's own characteristics and usage features. Both of these data are obtained by the game server processing the historical story text and the current story text using a large language model.

[0083] There are two ways to determine the target item template corresponding to the target item keyword from the preset item template library. The two methods are explained below.

[0084] In one embodiment, S2 specifically includes:

[0085] S211: Obtain the preset item template library. The preset item template library includes multiple preset item templates, and each preset item template includes a corresponding preset item name.

[0086] S212: Determine the target preset item name that is the same as the target item keyword from the preset item names, and determine the preset item template corresponding to the target preset item name as the target item template.

[0087] In some levels, words in the current story text must match any preset keyword in the preset item vocabulary to be recognized as item keywords. This means item keywords are limited to a few selectable words. To address this, multiple preset item templates can be created and stored in a preset item template library, each with its own corresponding preset item name. When a target item template is needed, the preset item template library is called directly, and the target item keyword is compared with each preset item name. If a preset item name matches the target item keyword, that preset item name is identified as the target preset item name, and the template to which that name belongs is the target item template.

[0088] For example, taking a game item corresponding to a certain level as a weapon, the preset item template library can include multiple preset item templates such as sword template, armor template, shield template, knife template, dagger template, blade template, magic wand template, staff template, axe template, spear template, and long spear template. "Sword," "Armor," "Shield," "Knife," "Dagger," "Blade," "Magic Wand," "Staff," "Axe," "Spear," and "Long Spear" are the preset item names for each preset item template. If the target item keyword is "sword," then the sword template is the target item template.

[0089] The method of determining the target item template by using a pre-set item template library can be achieved without calling a large language model, thus reducing computational resources and improving processing speed.

[0090] In another embodiment, S2 specifically includes:

[0091] S221: Obtain the preset item template library. The preset item template library includes multiple preset item templates, and each preset item template includes the corresponding preset item category name.

[0092] S222: Call the large language model to identify the target semantics of the target prop keywords.

[0093] S223: Determine the target preset item category name that is closest to the target semantics from the preset item category names, and determine the preset item template corresponding to the target preset item category name as the target item template.

[0094] In some levels, the words in the current story text do not need to strictly match the preset keywords. Instead, only the semantics of a word need to fall within the preset item category; that is, it needs to be identified as an item keyword. In other words, item keywords have a degree of openness. In this case, setting a corresponding item template for each item keyword would be too labor-intensive and difficult to cover all possible scenarios. For this situation, multiple preset item templates can be created and stored as a preset item template library. Each preset item template has its own corresponding preset item category name. When the target item template is needed, the large language model is first used to identify the target semantics of the target item keyword. Then, the preset item template library is called to compare the target semantics with the names of each preset item category, determining the target preset item category name that is closest to the target semantics. The template to which this name belongs is the target item template.

[0095] For example, taking a level where the corresponding game item category is "plant," the preset item module library can include flower templates, grass templates, tree templates, vine templates, etc., where "flower," "grass," "tree," and "vine" are the preset item category names for each preset item template. If the target item keyword is "thorn flower," and the large language model identifies that "thorn flower" is closest to the flower category, then the flower template is the target item template. If the target item keyword is "king's rose," and the large language model identifies that "king's rose" is also closest to the flower category, then the flower template is also the target item template. If the target item keyword is "moonlight grass," and the large language model identifies that "moonlight grass" is closest to the grass category, then the grass template is the target item template.

[0096] The method of determining the target item template by semantic recognition can not increase the workload of developing preset item templates, but can meet the personalized needs of generating different game items for different game keywords.

[0097] In one embodiment, the target prop template includes a target static template, which includes a target prop image. Following S223, the following is also included:

[0098] S224: Obtain the variable image parameters of the target prop image.

[0099] S225: Update the variable image parameters based on the target semantics to obtain the updated variable image parameters.

[0100] S226: Update the target prop image based on the updated variable image parameters to obtain the updated target prop template.

[0101] The target item template can include a target static template. In this embodiment, taking cards as an example, each item template includes a static template, and each static template has the appearance of a card. The card will have an image of the game item. For example, if the game item is a "sword", the corresponding card will display an image of a sword; if the game item is a "flower", the corresponding card will display an image of a flower. Figure 5 The illustration shows a "Sword" card, which includes an image of a sword. Each item image has basic image parameters and variable image parameters. The basic image parameters are those that do not change with the semantic changes of the target item's keywords. These parameters control a portion of the item image to remain unchanged. The variable image parameters are those that change with the semantic changes of the target item's keywords. These parameters control another portion of the item image to produce different visual effects.

[0102] After determining the target item template, we can first obtain the variable image parameters of the template, then update the variable image parameters using the target semantics, and finally maintain this part of the original image based on the basic image parameters. Based on the updated variable image parameters, we update the variable content in the original image. The updated target item image will present different visual effects depending on the target semantics, thereby further satisfying the player's personalized needs.

[0103] For example, taking the game item "flower" as an example, the target item image is an image of a flower. The basic image parameters can be the shape of the flower and the flower branch in the image of "flower". Regardless of whether the target item keyword is "flame flower" or "snow lotus", as long as it is the same target static template, the shape of the flower and the flower branch in the target item image will not change. The variable image parameter can be the color of the flower. If the target item keyword is "flame flower", after semantic recognition, the color of the flower in the target item image can be updated to red, and finally an image of a red flower can be generated. If the target item keyword is "snow lotus", after semantic recognition, the color of the flower in the target item image can be updated to white, and finally an image of a white flower can be generated.

[0104] When generating target story background data and target item attribute data, the following methods are used.

[0105] In one embodiment, S2 further includes:

[0106] S231: Invoke the large language model to extract target story background description information and target prop description information from historical story text and current story text.

[0107] S232: Generate the background image of the target item based on the background description information of the target story, and generate the basic attribute data and usage attribute data of the target item based on the description information of the target item.

[0108] The target story background data is specifically presented as a background image of the target item, which visually reflects the story background in which the target game item originates. The target item attribute data includes basic attribute data and usage attribute data. Basic attribute data may include the item name, story origin, etc., while usage attribute data may include the power value and power description when using the item in combat. To obtain the target story background data and target item attribute data, the game server first needs to concatenate the above two types of story text with system prompts. Then, the concatenated whole is input into a large language model, instructing the large language model to first extract the target story background description information related to the story background and the target item description information related to the item itself from the historical story text and the current story text. Finally, based on these two types of information, the required target story background data and target item attribute data are generated.

[0109] After extracting the background description information of the target story, the large language model can first generate background feature words, and then generate the corresponding image based on these background feature words. For example, if the background description information of the target story extracted by the large language model is "There was once an old mage in a mountain, and the old mage had a magical sword to offer to a dragon in the distance," the generated background feature words can include "mountain." After generation, the large language model can generate an image of a mountain based on these background feature words, and this image is the background image of the target prop.

[0110] After extracting the description information of the target item, the large language model can generate basic attribute data and usage attribute data of the target item based on the description. For example, if the description information of the target item is "The dragon angrily spews flames, and the sword is bathed in the fire, radiating endless light!", the generated basic attribute data of the target item includes the item name "Flame Sword" and the story source "The dragon angrily spews flames, and the sword is bathed in the fire, radiating endless light", and the usage attribute data of the target item includes the strength value "7" and the strength description "Contains the power of fire".

[0111] S3: Bind the target story background data and target item attribute data to the target item template to generate and display the target game item corresponding to the target item keyword.

[0112] After obtaining the above data, the target story background data and template item attribute data are bound to the target item template. After binding, the target game item corresponding to the target item keyword can be generated and displayed to the player through the relevant game interface. Since the target story background data and target item attribute data corresponding to each item keyword are different, even if it is the same target item template, the game item generated and displayed after binding is unique. Therefore, the personalized needs of players can be met through the display effect of the item.

[0113] In one embodiment, the target prop template includes a target dynamic template and a target static template, and S3 specifically includes:

[0114] S31: Bind the target story background data and target item attribute data to the target static template to generate static target game items;

[0115] S32: Based on the target dynamic template, display the transformation animation from target item keywords to static target game items;

[0116] S33: After the transition animation finishes playing, display the static target game item.

[0117] The target item template can include a target dynamic template and a target static template. The target static template is used to display the final generated target game item in a static way, while the target dynamic template is used to display the entire process of the target item keyword being transformed into a static target game item in a dynamic way. The two templates work together to create the visual effect of virtual target keywords falling into real personalized target game items.

[0118] Taking a game item type of card, and the target game item as the weapon card "sword" as an example, such as Figure 5 As shown, the target static template includes the appearance of a weapon card, which displays the target item image "a sword." The bottom layer of the target item image is the background image display area 501, and below that is the text display area 502. The target story background data generated in the above steps is bound to the background image display area 501, and the target item attribute data is bound to the text display area 502. For example, if the target story background image is an image of "a mountain," this image will be bound to the background image display area 501. The target item's basic attribute data includes the weapon name "Flame Blade," the story source "The dragon angrily spewed flames, and the sword bathed in the fire, radiating endless light!", and the target item's usage attribute data includes the strength value "7" and the strength description "Contains the power of flames." All of these contents will be bound to the text display area 502.

[0119] Before displaying the weapon card "Sword," the game server, in response to the trigger command for the target item keyword, will first display a transformation animation from the target item keyword to the static target game item based on the target dynamic template. The transformation animation needs to be pre-made and categorized for storage. The effect of the transformation animation matches the target semantics of the target item keyword to create a more realistic falling effect. For example, if the target item keyword is "Tree," since it belongs to the tree category and trees grow gradually from seeds, the transformation animation could be the target item keyword falling to the ground like a seed and then gradually growing into a tree. As another example, if the target item keyword is "Eagle," since it belongs to the bird category, the transformation animation could be the target item keyword flying away like a bird and then stopping at a certain location to spawn an eagle.

[0120] Furthermore, interactive features can be added to the transformation animation to enhance the player experience. For example, after the target item keyword falls to a certain position on the ground, it will still be displayed as the target item keyword. Players need to drag the target item keyword at that position from the current position to the target position, and then perform a placement operation at the target position to plant the seed and finally grow it into a tree at the target position.

[0121] For example, such as Figure 6 to Figure 9 As shown, after the player performs the trigger operation on the target item keyword "Thorn Flower", the generated transformation animation is as follows: "Thorn Flower" falls from the second dialog box 4 to the first position A. The player performs the drag operation to drag "Thorn Flower" from the first position A to the second position B, and performs the placement operation in the second position B. At this time, flower model 110 will gradually grow in the second position B.

[0122] It should be noted that the transition animation can also be pre-set uniformly. For example, for all weapons, the transition animation could be a 3D weapon model falling directly from the sky, with the specific type of the weapon model matching the target item's keywords, such as... Figure 10 As shown, when the target item keyword is "sword", the animation changes to a sword model 120 falling directly from the sky.

[0123] After the above transformation animation completes, static target game items can be displayed, such as... Figure 11 As shown, the weapon card "Sword" will display a complete image of "a sword existing in a mountain" in the image part, and the text part will display the weapon name as "Flame Blade", the story source as "the dragon angrily spewed flames, and [the sword] bathed in the fire, radiating endless light!", the power value is "7", and the power description is "containing the power of flames".

[0124] In one embodiment, the process further includes the following after S3:

[0125] S4: In response to the command to use the target game item, obtain the target item's attribute data.

[0126] S5: Based on the target item's attribute data, generate and display the player character's first battle lines, the target game item's battle effect lines, and the non-player character's second battle lines.

[0127] After a target game item is generated, the game server calculates the total number of generated game items. If the total number reaches a preset value, such as four, the game item can be used in a specific scenario. This application uses cards as an example, with the scenario being battle mode. In this mode, player character 1 will sequentially use four acquired cards to engage in four rounds of battle against a non-player character 2 until defeating them. There are various ways to display the game item usage interface in battle mode. Figure 12 to Figure 16 The first combat mode was shown. Figure 17 to Figure 23 The second battle mode is shown. The two modes will be explained separately below.

[0128] exist Figure 12 to Figure 16 In the game, the specific process of each round of battle is as follows: Player character 1 selects a card to fight and will shout the first battle line when using it. The card will generate battle effect lines during use. After being hit by the card, non-player character 2 will shout the second battle line and then counterattack against player character 1.

[0129] Specifically, such as Figure 12 As shown, in this battle mode, the game interface displays player character 1 and non-player character 2. Below player character 1 is a first strength value display area 6, which shows the player character 1's total strength value and current remaining strength value during battle. For example, "24 / 24" indicates that the player's total strength value is 24 and the current remaining strength value is 24. A corresponding health bar is also displayed after "24 / 24" for a more intuitive display of these values. Similarly, below non-player character 2 is a second strength value display area 7, which shows the non-player character 2's total strength value and current remaining strength value during battle. For example, "26 / 26" indicates that the player's total strength value is 26 and the current remaining strength value is 26. A corresponding health bar is also displayed after "26 / 26" for a more intuitive display of these values. At the bottom of the game interface is a game item display area 8, which displays four generated cards 130. Each card 130 is displayed as a small icon. When the mouse pointer hovers over a card 130, that card 130 will display... Figure 11 The complete effect shown.

[0130] Assuming the first card from left to right, number 130, is the target game item, when a player clicks on it, the click action generates a use command. The game server responds to this command and retrieves the target item's attribute data. Let's assume the item's name is "Dragon-Slaying Sword - Blood Moon," its story origin is "Blood Moon Reflected in Blade Light! Sword Sect Slays the Dragon," its power value is 10, and its power description is "The Sword Sect tempers its blade with dragon bones; the Dragon-Slaying Blade reflects the cold light of the blood moon, and when it is drawn, the world changes color." After retrieving this data, the game server... Figure 13 As shown, first generate and display player character 1's first battle line 200: "With the hatred of a thousand men, I will slay you under the blood moon!", then... Figure 14 As shown, the animation of player character 1 attacking non-player character 2 is displayed, and the battle effect dialogue 300 "Blood moon reflects the sword, dragon's roar tears through the night sky" is generated and displayed. At this time, the non-player character 2's current remaining strength value will decrease to 16. Then as... Figure 15 As shown, the game generates and displays the second battle line (400) after the non-player character 2 is attacked: "Ah--! This dragon soul... Don't come near me!!" It also displays an animation of the non-player character 2 counterattacking the player character 1. At this point, the player character 1's remaining strength will decrease to 18. This concludes the current battle, and the game interface will then display... Figure 16 As shown, at this point, only the remaining three cards 130 are displayed in the game item display area 8. Repeat the above process until the non-player character 2 is defeated, and the battle ends.

[0131] exist Figure 17 to Figure 23 In the game, the specific process of each round of battle is as follows: First, the action lines and twisted lines of the non-player character 2 are displayed. Both the action lines and twisted lines contain information related to a certain card. Player character 1 selects a card from the 4 generated cards that matches the content of these lines to fight. When using the card, the first battle line will be shouted. During the use of the card, the battle effect lines will be generated. After being hit by the card, the non-player character 2 will shout the second battle line.

[0132] Specifically, such as Figure 17 As shown, in this combat mode, the game interface first displays the non-player character 2 and 500 action lines, then... Figure 18As shown, the non-player character 2's distorted dialogue 500, action dialogue 500, and distorted dialogue 600 are all generated based on the item attribute information of a certain generated card. Among them, action dialogue 500 is used to describe the attack action taken by the non-player character 2 on the card, and distorted dialogue 600 is used to describe the non-player character 2's misinterpretation of the card's attributes. For example, the four generated cards are "Throne of Thorns," "Moonlight Rose Blade," "Thorned Black Lotus," and "Black Lotus." The item attributes of "Throne of Thorns" include: "Grown from the blood of the Rose Princess, piercing the dreams and hearts of traitors." "Moonlight Rose Blade" includes: "Holded by a rose that takes form during a full moon, a dream-devouring dagger formed from silver light." "Thorned Black Lotus" includes: "Rising from the ashes of burned roses, each petal a pleading face, containing resentment and curses." "Black Lotus" includes: "A medicine rising from rose ashes, its petals are pleading faces; blooming means devouring its master." Based on the item attributes of "Throne of Thorns," the generated action line 500 could be "The king's scepter shatters the throne, releasing the imprisoned dream souls," and the generated twisted action line 600 could be: "This throne? It's nothing but a rack nailed to blood and mud with the wails of traitors!" Here, "King" refers to non-player character 2.

[0133] like Figure 19 As shown, the game interface displays Player Character 1, Non-Player Character 2, and Twisted Dialogue 600. Within Player Character 1's area, icons and names of four cards (130) are displayed. Similarly, when the mouse pointer hovers over a card (130), more information about that card is revealed. Additionally, a prompt is displayed within Player Character 1's area, advising Player Character 1 to observe the King's words and, combined with information about the plants, choose a card that can withstand the King's attack. Here, "King" refers to Non-Player Character 2, and "Plants" refers to plant cards. Player Character 1 can use the "Throne of Thorns" card (130) based on the aforementioned action dialogue 500 and Twisted Dialogue 600. To use it, simply drag it from Player Character 1's area to Non-Player Character 2's area and release it. (The text repeats itself here.) Figure 20 As shown, after use, the game interface will display player character 1 and the first battle line 200: "The throne does not bear power, but sacrifice and love! Throne of Thorns, answer my truth!" Figure 21 As shown, the game interface will simultaneously display player character 1, non-player character 2, the first battle dialogue 200, and the twisted dialogue 600. A bar 9 at the top of the interface will display the changes in power values ​​during combat. Figure 22 As shown, after the "Throne of Thorns" is used, it generates and displays the battle effect dialogue 300: "The Throne of Thorns rises with crimson glory, rose phantoms entwine the king, piercing the illusory dream." (Example:) Figure 23As shown, after non-player character 2 is hit, the second battle line 400 is generated and displayed: "Ah! What evil power is this! A mere story dares to shake the will of this king!" This ends the current round of battle, and the above process repeats until non-player character 2 is defeated, at which point the battle ends. Each round is won as long as player character 1 selects a matching card to launch an attack.

[0134] It should be noted that the display methods of animations and dialogue in the relevant game interfaces in the two methods mentioned above are not based on... Figure 12 to Figure 23 For the purposes of this study, those skilled in the art may make adaptive adjustments to the display methods of various elements in the game screen as needed, as long as the generation of each line of dialogue satisfies the same logic.

[0135] The dialogue generated using the methods described above can closely link the battle mode with the story narrative. Furthermore, since the item attribute data of each game item is different, the final generated dialogue is also unique. Therefore, the personalized needs of players can be met through the effects of using the items.

[0136] As can be seen from the above embodiments, the game prop generation method based on story text provided in this application generates game props during the interactive process of player characters and non-player characters taking turns telling stories. Since the player character will not input the same story each time he tells the story, and the non-player character will not output the same story each time he continues the story, the target story background data and target prop attribute data generated based on these story texts will also be different for the target prop keywords. The target game prop generated after binding these data with the target prop template also has uniqueness and exclusivity. Both the prop itself and its usage effect are highly personalized, and it can bring the game experience of generating physical game props from virtual stories, thus meeting the needs of players.

[0137] Based on the methods described in the above embodiments, this embodiment will further describe the method from the perspective of a game item generation device. Please refer to... Figure 24 The game item generation device based on story text may include:

[0138] The first response module 10 is used to respond to the trigger command of the target item keyword, and to obtain the historical story text and the current story text. The historical story text includes the historical player story text input by the player character and the historical continuation story text output by the non-player character. The current story text includes the current player story text input by the player character and the current continuation story text output by the non-player character. The current continuation story text includes at least one item keyword.

[0139] The first generation module 20 is used to determine the target item template corresponding to the target item keyword from the preset item template library, and generate the target story background data and target item attribute data corresponding to the target item keyword according to the historical story text and the current story text;

[0140] The second generation module 30 is used to bind the target story background data and the target item attribute data with the target item template to generate and display the target game item corresponding to the target item keyword.

[0141] In one embodiment, the first generation module 20 includes:

[0142] The first acquisition submodule is used to acquire a preset item template library, which includes multiple preset item templates, and each preset item template includes a corresponding preset item name.

[0143] The first determining submodule is used to determine the target preset item name that is the same as the target item keyword from each of the preset item names, and to determine the preset item template corresponding to the target preset item name as the target item template.

[0144] In another embodiment, the first generation module 20 includes:

[0145] The second acquisition submodule is used to acquire a preset item template library, which includes multiple preset item templates, and each preset item template includes a corresponding preset item category name.

[0146] The first calling submodule is used to call the large language model to identify the target semantics of the target prop keywords;

[0147] The second determining submodule is used to determine the target preset item category name that is closest to the target semantics from each of the preset item category names, and to determine the preset item template corresponding to the target preset item category name as the target item template.

[0148] In one embodiment, the target prop template includes a target static template, the target static template includes a target prop image, and the first generation module 20, in addition to the second determination submodule, further includes:

[0149] The third acquisition submodule is used to acquire the variable image parameters of the target prop image;

[0150] The first update submodule is used to update the variable image parameters based on the target semantics to obtain the updated variable image parameters;

[0151] The second update submodule updates the target prop image based on the updated variable image parameters to obtain the updated target prop template.

[0152] In one embodiment, the first generation module 20 further includes:

[0153] The second calling submodule is used to call the large language model to extract target story background description information and target prop description information from the historical story text and the current story text;

[0154] The first generation submodule is used to generate a background image of the target prop based on the target story background description information, and to generate basic attribute data and usage attribute data of the target prop based on the target prop description information.

[0155] In one embodiment, the target prop template includes a target dynamic template and a target static template, and the second generation module 30 includes:

[0156] The second generation submodule is used to bind the target story background data and the target prop attribute data with the target static template to generate static target game props;

[0157] The third generation submodule is used to generate and display the transformation animation from the target item keyword to the static target game item based on the target dynamic template;

[0158] The display submodule is used to display the static target game item after the transformation animation has finished playing.

[0159] In one embodiment, the game item generation device further includes, after the second generation module 30:

[0160] The second response module is used to obtain the target item attribute data in response to the instruction to use the target game item;

[0161] The third generation module is used to generate and display the first battle lines of the player character, the battle effect lines of the target game item, and the second battle lines of the non-player character based on the target item attribute data.

[0162] Unlike existing technologies, the game item generation device provided in this application generates game items during the interactive process of player characters and non-player characters taking turns telling stories. Since the player character does not input the same story each time he tells the story, and the non-player character does not output the same story each time he continues the story, the target story background data and target item attribute data generated based on these story texts are also different for the target item keywords. The target game item generated after binding these data with the target item template is also unique and distinctive. Both the item itself and its usage effect are highly personalized, and it can bring the game experience of generating physical game items from virtual stories, thus meeting the needs of players.

[0163] Accordingly, embodiments of this application also provide an electronic device, such as... Figure 25 As shown, the electronic device may include a radio frequency (RF) circuit 101, a memory 102 including one or more computer-readable storage media, an input unit 103, a display unit 104, a sensor 105, an audio circuit 106, a WiFi module 107, a processor 108 including one or more processing cores, and a power supply 109, among other components. Those skilled in the art will understand that... Figure 25 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0164] The radio frequency circuit 101 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and hands it over to one or more processors 108 for processing; additionally, it transmits uplink data to the base station. The memory 102 can be used to store software programs and modules. The processor 108 executes various functional applications and generates game props by running the software programs and modules stored in the memory 102. The input unit 103 can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical, or trackball signal inputs related to customer settings and function control.

[0165] Display unit 104 can be used to display information input by the customer or information provided to the customer, as well as various graphical client interfaces of the server. These graphical client interfaces can be composed of graphics, text, icons, videos, and any combination thereof.

[0166] The electronic device may also include at least one sensor 105, such as a light sensor, a motion sensor, and other sensors. Audio circuitry 106 includes a speaker that provides an audio interface between the client and the electronic device.

[0167] WiFi is a wireless transmission technology. Electronic devices using the WiFi module 107 can help customers send and receive emails, browse web pages, and access streaming media, providing customers with wireless broadband internet access. Although Figure 25 WiFi module 107 is shown, but it is understood that it is not a necessary component of the electronic device and can be omitted as needed without changing the nature of the application.

[0168] The processor 108 is the control center of the electronic device. It connects various parts of the phone through various interfaces and lines. By running or executing software programs and / or modules stored in the memory 102, and calling data stored in the memory 102, it performs various functions of the electronic device and processes data, thereby monitoring the phone as a whole.

[0169] The electronic device also includes a power supply 109 (such as a battery) that supplies power to the various components. Preferably, the power supply can be logically connected to the processor 108 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system.

[0170] Although not shown, electronic devices may also include cameras, Bluetooth modules, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 108 in the server loads the executable files corresponding to the processes of one or more applications into the memory 102 according to the following instructions, and the processor 108 runs the applications stored in the memory 102 to achieve the following functions:

[0171] In response to a trigger command for a target item keyword, the historical story text and the current story text are obtained. The historical story text includes the historical player story text input by the player character and the historical continuation story text output by the non-player character. The current story text includes the current player story text input by the player character and the current continuation story text output by the non-player character. The current continuation story text includes at least one item keyword.

[0172] The target item template corresponding to the target item keyword is determined from the preset item template library, and the target story background data and target item attribute data corresponding to the target item keyword are generated based on the historical story text and the current story text.

[0173] The target story background data and the target item attribute data are bound to the target item template to generate and display the target game item corresponding to the target item keyword.

[0174] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed description above, which will not be repeated here.

[0175] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0176] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to perform the following functions:

[0177] In response to a trigger command for a target item keyword, the historical story text and the current story text are obtained. The historical story text includes the historical player story text input by the player character and the historical continuation story text output by the non-player character. The current story text includes the current player story text input by the player character and the current continuation story text output by the non-player character. The current continuation story text includes at least one item keyword.

[0178] The target item template corresponding to the target item keyword is determined from the preset item template library, and the target story background data and target item attribute data corresponding to the target item keyword are generated based on the historical story text and the current story text.

[0179] The target story background data and the target item attribute data are bound to the target item template to generate and display the target game item corresponding to the target item keyword.

[0180] The above provides a detailed description of a game prop generation method and related equipment based on story text provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the technical solutions and core ideas of this application. Those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for generating game props based on story text, characterized in that, The method includes: In response to a trigger command for a target item keyword, the historical story text and the current story text are obtained. The historical story text includes the historical player story text input by the player character and the historical continuation story text output by the non-player character. The current story text includes the current player story text input by the player character and the current continuation story text output by the non-player character. The current continuation story text includes at least one item keyword. The target item template corresponding to the target item keyword is determined from the preset item template library, and the target story background data and target item attribute data corresponding to the target item keyword are generated based on the historical story text and the current story text. The target story background data and the target item attribute data are bound to the target item template to generate and display the target game item corresponding to the target item keyword.

2. The method for generating game props based on story text according to claim 1, characterized in that, The step of determining the target item template corresponding to the target item keyword from the preset item template library includes: Obtain a preset item template library, which includes multiple preset item templates, and each preset item template includes a corresponding preset item name; From the preset item names, determine the target preset item name that is the same as the target item keyword, and determine the preset item template corresponding to the target preset item name as the target item template.

3. The method for generating game props based on story text according to claim 1, characterized in that, The step of determining the target item template corresponding to the target item keyword from the preset item template library includes: Obtain a preset item template library, which includes multiple preset item templates, each of which includes a corresponding preset item category name; The target semantics of the target prop keywords are identified by calling a large language model. From the names of the preset prop categories, determine the target preset prop category name that is closest to the target semantics, and determine the preset prop template corresponding to the target preset prop category name as the target prop template.

4. The game prop generation method based on story text according to claim 3, characterized in that, The target prop template includes a target static template, which includes a target prop image. After determining the target preset prop category that is closest to the target semantics from each of the preset prop categories, and determining the preset prop template corresponding to the target preset prop category as the target prop template, the method further includes: Obtain the variable image parameters of the target prop image; The variable image parameters are updated based on the target semantics to obtain the updated variable image parameters; The target prop image is updated based on the updated variable image parameters to obtain the updated target prop template.

5. The method for generating game props based on story text according to claim 1, characterized in that, The steps of generating target story background data and target item attribute data corresponding to the target item keywords based on the historical story text and the current story text include: The large language model is invoked to extract target story background description information and target prop description information from the historical story text and the current story text; Based on the target story background description information, generate a target prop background image, and based on the target prop description information, generate target prop basic attribute data and target prop usage attribute data.

6. The game prop generation method based on story text according to claim 1, characterized in that, The target item template includes a target dynamic template and a target static template. The steps of binding the target story background data and the target item attribute data to the target item template, and generating and displaying the target game item corresponding to the target item keyword, include: Bind the target story background data and the target item attribute data to the target static template to generate static target game items; Based on the target dynamic template, generate and display the transformation animation from the target item keyword to the static target game item; After the transformation animation finishes playing, the static target game item is displayed.

7. The method for generating game props based on story text according to claim 1, characterized in that, After generating and displaying the target game item corresponding to the target item keyword, the method further includes: In response to a command to use the target game item, the attribute data of the target item is obtained; Based on the target item attribute data, generate and display the player character's first battle lines, the target game item's battle effect lines, and the non-player character's second battle lines.

8. A game prop generation device based on story text, characterized in that, The device includes: The first response module is used to respond to the trigger command of the target item keyword, and obtain the historical story text and the current story text. The historical story text includes the historical player story text input by the player character and the historical continuation story text output by the non-player character. The current story text includes the current player story text input by the player character and the current continuation story text output by the non-player character. The current continuation story text includes at least one item keyword. The first generation module is used to determine the target item template corresponding to the target item keyword from the preset item template library, and generate the target story background data and target item attribute data corresponding to the target item keyword based on the historical story text and the current story text; The second generation module is used to bind the target story background data and the target item attribute data with the target item template to generate and display the target game item corresponding to the target item keyword.

9. An electronic device, characterized in that, It includes a memory and a processor; the memory stores an application program, and the processor is used to run the application program within the memory to perform the steps of the story text-based game item generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the steps of the story-text-based game item generation method according to any one of claims 1 to 7.

Images