A personalized character generation control method and related equipment

Abstract

The present application discloses a personalized character generation control method and related equipment, which relate to the field of artificial intelligence. The method comprises: obtaining character description keywords input by a user; obtaining a target large language model selected by the user; generating character character continuous description information applicable to the target large language model according to the character description keywords, the target large language model and grammar generation rules; and sending the character character continuous description information to the target large language model to generate a personalized character.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and more specifically, to a personalized character generation control method and related equipment. Background Art

[0002] Current Large Language Model (LLM) services usually run on separate platforms and lack integrated management and operation tools. When users need to create a specific personalized character (Persona), they usually need to manually write a character description language from scratch to define the character's background, behavior rules, language style, etc. This method is very cumbersome and inefficient for users who need to create multiple characters. In addition, each character description language usually corresponds to only one character, and there is no unified storage and reuse mechanism, which makes it difficult for users to quickly switch or adjust characters.

[0003] Therefore, it is necessary to propose a personalized character generation control method and related equipment to at least solve some of the above problems. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] In a first aspect, the present application proposes a personalized character generation control method, comprising:

[0006] Get the character description keywords entered by the user;

[0007] Get the target large language model selected by the user;

[0008] Generate character role continuous description information applicable to the target large language model according to the character description keywords, the target large language model and grammar generation rules;

[0009] The above-mentioned character role continuous description information is sent to the above-mentioned target large language model to generate a personalized character.

[0010] In a feasible implementation manner, the above-mentioned character description keywords are based on the input information of the user in a preset input interface, and the above-mentioned preset input interface includes basic character information and personalized character information.

[0011] In a feasible implementation, it also includes:

[0012] Acquire input features of the input interface according to the target large language model;

[0013] Generate a corresponding preset input interface based on the above input features.

[0014] In a feasible implementation manner, the large language model selected by the user is determined based on a selection operation performed by the user on the large language model selection interface.

[0015] In a feasible implementation, it also includes:

[0016] The continuous description information of the characters applicable to the historically generated target large language model is stored in the personalized information storage module;

[0017] The user's selection operation in the above-mentioned personalized information storage module is obtained to determine the continuous description information of the target character.

[0018] In a feasible implementation, it also includes:

[0019] Obtain sample description information of the target large language model;

[0020] Extract description keywords and mapping relationships between keywords based on the above example description information;

[0021] Based on the above description keywords and the above mapping relationship, the above grammar generation rules are generated.

[0022] In a feasible implementation, it also includes:

[0023] Obtaining personalized role preference information input by the user;

[0024] Obtain characteristic information of large language models;

[0025] Based on the personalized role preference information and the characteristic information of the large language model, the target large language model is automatically determined.

[0026] In a second aspect, the present application proposes a personalized character generation control device, comprising:

[0027] A first acquisition unit, used to acquire a character description keyword input by a user;

[0028] A second acquisition unit, used to acquire a target large language model selected by a user;

[0029] A first generating unit is used to generate character role continuous description information applicable to the target large language model according to the character description keywords, the target large language model and grammar generation rules;

[0030] The second generating unit is used to send the above-mentioned character role continuous description information to the above-mentioned target large language model to generate a personalized character.

[0031] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the personalized character generation control method of any one of the above-mentioned first aspect when executing the computer program stored in the memory.

[0032] In a fourth aspect, the present application further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the personalized character generation control method of any one of the first aspects is implemented.

[0033] In summary, this method can automatically extract keywords from the information input by the user. These keywords cover the character's background (such as age, occupation), personality traits (such as humor, rationality), behavior patterns (such as quoting anecdotes), and language style (such as clarity and conciseness). The user only needs to enter a simple description, and the system can intelligently extract the core features of the character and generate complete character continuous description information, which greatly simplifies the operation of character definition. This method also supports users to freely choose between multiple large language models (such as GPT series, Claude, LLaMA, etc.). The system can dynamically adjust the character continuous description information generation rules according to the characteristics of the model selected by the user to ensure that the format of the generated character continuous description information is highly compatible with the target model. The system optimizes the grammar generation rules to make the generated character continuous description information more fluent and structured. The system can not only convert keywords into specific descriptions, but also refine and expand based on context. This method also provides a convenient role management function. Users can store the generated role description information in the system, which supports rapid reuse and adjustment of roles. The multi-role management mechanism enables users to easily switch roles or compare role performance in different scenarios. Compared with traditional methods, this method is more efficient, and users do not need to manually write continuous description information of the character from scratch. This method is more flexible and supports the adaptation of multiple models and multiple scenarios. The results of this method are more accurate, and the generated continuous description information of the character is natural and smooth, and fits the characteristics of the character. This method is more convenient to manage, and the storage and reuse of characters improves scalability and application efficiency. Through this improved method, users can more efficiently create personalized characters that meet their needs, improve the interactive experience with large language models, and provide strong support for a variety of scenarios such as education, entertainment, and customer service. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0035] Figure 1 A flowchart of a personalized character generation control method provided in an embodiment of the present application;

[0036] Figure 2 A schematic diagram of a personalized character generation control principle provided in an embodiment of the present application;

[0037] Figure 3 A schematic diagram of an interface provided in an embodiment of the present application;

[0038] Figure 4 Another schematic diagram of the control principle of personalized character generation provided by the embodiment of the present application;

[0039] Figure 5 A schematic diagram of the structure of a personalized character generation control device provided in an embodiment of the present application;

[0040] Figure 6 A schematic diagram of the structure of a personalized character generation control electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0042] Figure 1 A flowchart of a personalized character generation control method provided in an embodiment of the present application is provided. Figure 2A schematic diagram of a personalized character generation control principle provided in an embodiment of the present application, the method may specifically include:

[0043] S110, obtaining character description keywords input by a user;

[0044] Exemplarily, keywords or phrases describing the core features of the character are extracted from the user input. Keywords may include the character's background (such as occupation, age), behavior patterns (such as personality traits), hobbies, language style, etc.

[0045] For example:

[0046] User input:

[0047] Age: 25

[0048] Occupation: Scientist

[0049] Hobbies: Astronomy, writing

[0050] Personality traits: rational, humorous

[0051] Language style: clear logic and concise

[0052] System extracts keywords:

[0053] [Age: 25], [Occupation: Scientist], [Interests: Astronomy, Writing], [Personality: Rational, Humorous], [Language style: Clear and concise]

[0054] S120, obtaining a target large language model selected by a user;

[0055] Exemplarily, the system supports selection of multiple large language models (LLMs), such as the GPT series, Claude, LLaMA, etc. Users select the most suitable model according to specific needs to generate responses that meet the target application scenario.

[0056] For example, if the user selects GPT-4 as the target model, the system will bind this information to the subsequent generation rules to ensure that the generated character continuous description information is compatible with the GPT-4 input specification.

[0057] S130, generating character role continuous description information applicable to the target large language model according to the character description keywords, the target large language model and grammar generation rules;

[0058] Exemplarily, the system uses grammar generation rules based on the keywords input by the user and the characteristics of the target model to convert the keywords into continuous and structured character descriptions (i.e., continuous description information of the character role). The basic structure includes the character's background information, behavioral norms, and language style. The refinement and expansion add contextual semantics to each keyword. The grammar optimization ensures that the generated description is fluent and meets the format requirements of the target model.

[0059] For example, if you enter keywords such as [age: 25], [occupation: scientist], [interests: astronomy, writing], [personality: rational, humorous], [language style: clear, concise]

[0060] Example of the generated character continuous description information: You are a 25-year-old scientist who focuses on astronomy research and loves writing. You are rational and humorous, and always express your opinions in clear and concise language. When communicating with people: You like to quote interesting anecdotes or stories related to astronomy. You use humor to resolve complex scientific concepts. You always keep your logic clear and don't be verbose.

[0061] Transform "rationality and humor" into behavioral norms (quote anecdotes, resolve complex concepts). Incorporate "clarity and conciseness" into language style, emphasizing clear logic and concise expression.

[0062] S140: Send the above-mentioned character role continuous description information to the above-mentioned target large language model to generate a personalized character.

[0063] Exemplarily, the generated character role continuous description information is submitted to the large language model selected by the user, and the model generates a response that conforms to the character characteristics based on the description information in the character role continuous description information. The generated content includes the character's specific answer style, behavioral habits, etc. to support the user's interaction needs.

[0064] In summary, this method can automatically extract keywords from the information input by the user. These keywords cover the character's background (such as age, occupation), personality traits (such as humor, rationality), behavior patterns (such as quoting anecdotes), and language style (such as clarity and conciseness). The user only needs to enter a simple description, and the system can intelligently extract the core features of the character and generate complete character continuous description information, which greatly simplifies the operation of character definition. This method also supports users to freely choose between multiple large language models (such as GPT series, Claude, LLaMA, etc.). The system can dynamically adjust the character continuous description information generation rules according to the characteristics of the model selected by the user to ensure that the format of the generated character continuous description information is highly compatible with the target model. The system optimizes the grammar generation rules to make the generated character continuous description information more fluent and structured. The system can not only convert keywords into specific descriptions, but also refine and expand based on context. This method also provides a convenient role management function. Users can store the generated role description information in the system, which supports rapid reuse and adjustment of roles. The multi-role management mechanism enables users to easily switch roles or compare role performance in different scenarios. Compared with traditional methods, this method is more efficient, and users do not need to manually write continuous description information of the character from scratch. This method is more flexible and supports the adaptation of multiple models and multiple scenarios. The results of this method are more accurate, and the generated continuous description information of the character is natural and smooth, and fits the characteristics of the character. This method is more convenient to manage, and the storage and reuse of characters improves scalability and application efficiency. Through this improved method, users can more efficiently create personalized characters that meet their needs, improve the interactive experience with large language models, and provide strong support for a variety of scenarios such as education, entertainment, and customer service.

[0065] In some examples, the above-mentioned character description keywords are based on the user's input information in a preset input interface, and the above-mentioned preset input interface includes basic character information and personalized character information.

[0066] Exemplarily, the preset input interface is designed to help users quickly define the basic information and personalized characteristics of a character in a modular and intuitive manner. Figure 3 This is a possible interface, and the main components of the interface include basic character information and personalized character information. The basic character information is used to collect the basic background information of the character, which includes but is not limited to: name (optional), age, occupation, gender, place of residence and educational background.

[0067] Personalized character information is used to describe the character's personality traits and behavior patterns. Personalized character information includes but is not limited to:

[0068] Personality traits: such as rationality, humor, rigor, enthusiasm, etc.

[0069] Hobbies and interests: such as technology, art, sports, etc.

[0070] Language style: such as humor, elegance, strong logic, etc.

[0071] Behavioral habits: such as quoting literary works and using specific terminology in conversations.

[0072] Input guidance prompts: Provide user-friendly prompt information, such as placeholder text or drop-down menu options, to help users understand how to fill in each information.

[0073] The placeholder in the personality trait input box reads "Please enter the character's personality traits, for example: rational, humorous."

[0074] In some examples, this also includes:

[0075] Acquire input features of the input interface according to the target large language model;

[0076] Generate a corresponding preset input interface based on the above input features.

[0077] Exemplarily, this solution proposes a mechanism for dynamically generating an input interface, which adjusts the layout and content of a preset input interface according to the characteristics and functional requirements of a target large language model (LLM) selected by the user, thereby optimizing the user experience.

[0078] The characteristics of the target large language model are obtained. The characteristics of the target large language model mainly include input content characteristics, application scenario characteristics, and model function limitations.

[0079] Input content features include the input formats supported by the model (such as text keywords, structured descriptions, natural language paragraphs, etc.) and the requirements for the input, such as the number of keywords and the level of detail of the description.

[0080] Application scenario characteristics include the application capabilities of the target model in specific fields (such as education, entertainment, customer service, etc.).

[0081] Model function restrictions include the maximum number of tokens, that is, the length limit of input content. The character continuous description information structure requirements are whether it needs to be clearly divided into blocks (such as instruction part, background part).

[0082] The system automatically generates or adjusts the input interface based on the characteristics of the target LLM. Add or reduce input fields based on model requirements, such as character background information, personality traits, etc. Provide guidance related to model characteristics, such as text length limits or format requirements. Adjust the order or hierarchy of fields to facilitate quick filling by users.

[0083] If the target model is suitable for short text generation (such as GPT-3.5-turbo), the interface may prioritize the input box of brief keywords. If the target model supports complex context analysis (such as GPT-4), the interface may provide richer input options (such as paragraph input area).

[0084] In some examples, the large language model selected by the user is determined based on a selection operation performed by the user on a large language model selection interface.

[0085] Exemplarily, the user enters the model selection interface, and is presented with a list of available large language models based on the user's needs. The interface displays the key features and applicable scenarios of each model.

[0086] Users can filter and select models by browsing the model list, understanding the characteristics of each model, or using the search function to find a model that meets their needs.

[0087] The user completes the selection operation by clicking the "Select" button of the corresponding model. The system records the model selected by the user and marks it as the "current target large language model". The subsequent input interface (such as field settings, text length limit) is adjusted based on the characteristics of the model. Generate continuous description information of the character role suitable for the model.

[0088] In some examples, this also includes:

[0089] The continuous description information of the characters applicable to the historically generated target large language model is stored in the personalized information storage module;

[0090] The user's selection operation in the above-mentioned personalized information storage module is obtained to determine the continuous description information of the target character.

[0091] For example, Figure 4 As shown, the storage, management and retrieval of historically generated continuous description information of human roles can be realized through the personalized information storage module, so that users can quickly reuse or adjust previously defined roles, reduce repetitive operations and improve efficiency. The continuous description information of the target human roles generated by users (including background information, personality traits, behavior patterns, etc.) is stored in the module. It supports classified storage of role information (such as classification by application scenario: education, entertainment, customer service). A labeling function can be provided to facilitate users to quickly retrieve roles based on keywords. This method supports versioned storage of role information, records the user's multiple modification history of role descriptions, and users can choose to restore to a specific version or make adjustments based on a certain version. Allow users to select the required role description information from the storage module for new sessions or model connections.

[0092] Users do not need to redefine roles every time, and can directly select previously created role description information from the storage module, which greatly reduces operation time. The system supports role classification, labeling, and version management, allowing users to quickly locate specific roles and flexibly adjust and expand role information. The stored role information can be reused across scenarios. For example, the same role can be switched in different applications such as education, entertainment, or customer service. Users can view and restore historical versions of roles at any time, and support iterative optimization of role description information. The system can automatically adapt the stored role description information to the target large language model to ensure that the generated results are consistent with the role characteristics.

[0093] In some examples, this also includes:

[0094] Obtain sample description information of the target large language model;

[0095] Extract description keywords and mapping relationships between keywords based on the above example description information;

[0096] Based on the above description keywords and the above mapping relationship, the above grammar generation rules are generated.

[0097] Exemplarily, by analyzing the example description information of the target large language model (LLM), extracting description keywords and their mapping relationships, and automatically generating grammar generation rules adapted to the LLM, the accuracy and efficiency of generating continuous description information of the character role are optimized.

[0098] The sample description information can come from official documents, historical data, or system built-in description text. Official documents are examples of continuous description information of reference personas provided by LLM. Historical data are effective interaction records when users use the target model. System built-in description texts are some standard descriptions generated by the system based on the characteristics of the target model.

[0099] Automatically extract keywords and mapping relationships from example description information, generate grammatical rules, and reduce manual intervention. The processing of a large amount of example data can quickly expand the grammatical rule library to adapt to the needs of different scenarios. Relying on NLP technology to accurately extract keywords, and generate reasonable mapping relationships based on the context, ensure the semantic integrity of the continuous description information of the character role. Adjust the grammatical rules according to the characteristics of the target model to adapt to the input requirements of different LLMs (such as short text, long text, structured description). The mapping relationship not only supports simple keyword classification, but also generates context-enhanced descriptions, making the continuous description information of the character role more vivid and personalized.

[0100] In some examples, this also includes:

[0101] Obtaining personalized role preference information input by the user;

[0102] Obtain characteristic information of large language models;

[0103] Based on the personalized role preference information and the characteristic information of the large language model, the target large language model is automatically determined.

[0104] Exemplarily, first, the user enters preference information through the role definition interface, which includes the role's background, personality traits, language style, application scenarios, and task types. For example, the user may want to create a 35-year-old history teacher role with a patient and humorous personality, used in educational scenarios, and supporting long text generation. The system extracts this preference information and structures it, such as role complexity (simple or complex), language style (humorous, professional, etc.), application scenario (education, entertainment, etc.), and task type (short text generation or long text processing).

[0105] At the same time, the system stores the characteristics of each language model, including model performance (such as computing power and generation quality), context processing capabilities (maximum input length), language style (supported expression types, such as humor, rigor, etc.), and typical scenarios for which the model is applicable (such as real-time conversations, educational scenarios, etc.). For example, GPT-3.5-turbo is suitable for short text generation and has high performance, while GPT-4 is good at complex tasks, supports longer input texts, and is suitable for education and multi-round deep conversation scenarios.

[0106] The system matches the role based on the user's role preference information and model feature information. For example, for the history teacher role in the above educational scenario, since the task requires long text generation, humorous language style, and high-complexity role description, the system will prioritize GPT-4 as the target large language model because it can meet these requirements. In contrast, if the user creates a simple real-time dialogue role, the system may recommend GPT-3.5-turbo to improve efficiency.

[0107] This automated matching method not only simplifies the decision-making process of users choosing models, but also ensures that the recommended model is highly adapted to user needs, improving the accuracy and experience of character generation and interaction. Through the dynamic recommendation model, users can easily achieve the best effect of character creation without having to understand complex technical details.

[0108] like Figure 5 As shown, the present application proposes a personalized character generation control device, comprising:

[0109] A first acquisition unit 21 is used to acquire a character description keyword input by a user;

[0110] A second acquisition unit 22, used to acquire a target large language model selected by a user;

[0111] A first generating unit 23 is used to generate character role continuous description information applicable to the target large language model according to the character description keywords, the target large language model and grammar generation rules;

[0112] The second generating unit 24 is used to send the above-mentioned character role continuous description information to the above-mentioned target large language model to generate a personalized character.

[0113] The above-mentioned personalized character generation control device can also perform the following steps:

[0114] In some examples, the above-mentioned character description keywords are based on the user's input information in a preset input interface, and the above-mentioned preset input interface includes basic character information and personalized character information.

[0115] In some examples, this also includes:

[0116] Acquire input features of the input interface according to the target large language model;

[0117] Generate a corresponding preset input interface based on the above input features.

[0118] In some examples, the large language model selected by the user is determined based on a selection operation performed by the user on a large language model selection interface.

[0119] In some examples, this also includes:

[0120] The continuous description information of the characters applicable to the historically generated target large language model is stored in the personalized information storage module;

[0121] The user's selection operation in the above-mentioned personalized information storage module is obtained to determine the continuous description information of the target character.

[0122] In some examples, this also includes:

[0123] Obtain sample description information of the target large language model;

[0124] Extract description keywords and mapping relationships between keywords based on the above example description information;

[0125] Based on the above description keywords and the above mapping relationship, the above grammar generation rules are generated.

[0126] In some examples, this also includes:

[0127] Obtaining personalized role preference information input by the user;

[0128] Obtain characteristic information of large language models;

[0129] Based on the personalized role preference information and the characteristic information of the large language model, the target large language model is automatically determined.

[0130] like Figure 6 As shown, an embodiment of the present application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor, and when the processor 320 executes the computer program 311, the steps of any of the above-mentioned methods for controlling the generation of personalized characters are implemented.

[0131] Since the electronic device introduced in this embodiment is a device used to implement a personalized character generation control device in the embodiment of the present application, based on the method introduced in the embodiment of the present application, the technical personnel in this field can understand the specific implementation method of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by the technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0132] During the specific implementation process, when the computer program 311 is executed by a processor, any implementation method in the embodiments corresponding to the first aspect can be implemented.

[0133] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0135] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0136] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0138] The embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of personalized character generation control in the corresponding embodiment.

[0139] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0141] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

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

[0143] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0144] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0145] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A personalized character generation control method, characterized in that: include: Get the character description keywords entered by the user; Get the target large language model selected by the user; Generate character role continuous description information applicable to the target large language model according to the character description keywords, the target large language model and grammar generation rules; The character role continuous description information is sent to the target large language model to generate a personalized character.

2. The method for controlling the generation of a personalized character according to claim 1, characterized in that: The character description keywords are based on the user's input information in a preset input interface, and the preset input interface includes basic character information and personalized character information.

3. The method for controlling the generation of a personalized character according to claim 2, characterized in that: Also includes: Acquiring input features of the input interface according to the target large language model; A corresponding preset input interface is generated based on the input feature.

4. The method for controlling the generation of a personalized character according to claim 1, characterized in that: The large language model selected by the user is determined based on a selection operation of the user in the large language model selection interface.

5. The method for controlling the generation of a personalized character according to claim 1, characterized in that: Also includes: The continuous description information of the characters applicable to the historically generated target large language model is stored in the personalized information storage module; The user's selection operation in the personalized information storage module is obtained to determine the continuous description information of the target character.

6. The method for controlling the generation of a personalized character according to claim 1, characterized in that: Also includes: Obtain sample description information of the target large language model; Extracting description keywords and mapping relationships between keywords according to the example description information; The grammar generation rule is generated based on the description keywords and the mapping relationship.

7. The method for controlling the generation of a personalized character according to claim 1, characterized in that: Also includes: Obtaining personalized role preference information input by the user; Obtain characteristic information of large language models; Based on the personalized role preference information and the characteristic information of the large language model, a target large language model is automatically determined.

8. A personalized character generation control device, characterized in that: include: A first acquisition unit, used to acquire a character description keyword input by a user; A second acquisition unit, used to acquire a target large language model selected by a user; A first generating unit, configured to generate character role continuous description information applicable to the target large language model according to the character description keywords, the target large language model and grammar generation rules; The second generating unit is used to send the character role continuous description information to the target large language model to generate a personalized character.

9. An electronic device, comprising: A memory and a processor, wherein the processor is used to implement the steps of the personalized character generation control method according to any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the personalized character generation control method according to any one of claims 1 to 7 are implemented.

Images