Book reading method, device and equipment, medium and product

Abstract

The invention discloses a book reading method, device and equipment, a medium and a product. The method comprises the steps of determining a target book in response to a book reading request sent by a target user, and performing analysis processing on the target book based on a preset large language model to obtain target text roles contained in the target book and target role lines corresponding to the target text roles; determining role feature information corresponding to the target text role, and determining a target timbre template corresponding to the target text role from a preset timbre library according to the role feature information to generate a target audio; and determining a paraphrasing audio corresponding to the paraphrasing lines in the target book, and according to the target audio and the paraphrasing audio, generating a reading audio according to the text structure of the target book, so as to respond to the book reading request. According to the method, the roles and lines in the book can be analyzed by utilizing the large language model, and the tone templates are adaptively selected to generate the personalized audio, so that the use experience of a user is improved.

Description

Technical Field

[0001] The present invention relates to the field of speech synthesis technology, and in particular to a book reading method, device, equipment, medium and product. Background Art

[0002] With the continuous development of audio synthesis technology, the technology of converting books into audio for display has been widely used in many fields, such as audio book systems. However, for books with long content and many characters, the direct conversion into audio is not intelligent enough and difficult to meet user needs.

[0003] Therefore, how to use a large language model to analyze the characters and lines in the book, adaptively select the timbre template to generate personalized audio, so as to better read aloud to the user and improve the user experience is a problem that needs to be solved urgently. Summary of the invention

[0004] The present invention provides a book reading method, device, equipment, medium and product, so as to better read aloud to users and improve the user experience.

[0005] According to one aspect of the present invention, there is provided a method for reading aloud a book, comprising:

[0006] In response to a book reading request sent by a target user, a target book is determined, and the target book is analyzed and processed based on a preset large language model to obtain target text characters contained in the target book and target character lines corresponding to each target text character;

[0007] Determine the role characteristic information corresponding to the target text role, and determine the target timbre template corresponding to the target text role from a preset timbre library according to the role characteristic information to generate the target audio;

[0008] The narration audio corresponding to the narration lines in the target book is determined, and the reading audio is generated according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request.

[0009] According to another aspect of the present invention, there is provided a book reading device, comprising:

[0010] An analysis module, for responding to a book reading request sent by a target user, determining a target book, and analyzing and processing the target book based on a preset large language model to obtain target text characters contained in the target book and target character lines corresponding to each target text character;

[0011] A generation module, used to determine the role characteristic information corresponding to the target text role, and determine the target timbre template corresponding to the target text role from a preset timbre library according to the role characteristic information, so as to generate the target audio;

[0012] The response module is used to determine the narration audio corresponding to the narration lines in the target book, and generate the reading audio according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the book reading method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the book reading method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the book reading method according to any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention responds to the book reading request sent by the target user, determines the target book, and analyzes and processes the target book based on the preset large language model to obtain the target text roles and target role lines corresponding to each target text role contained in the target book; determines the role feature information corresponding to the target text role, and determines the target timbre template corresponding to the target text role from the preset timbre library according to the role feature information to generate the target audio; determines the narration audio corresponding to the narration lines in the target book, and generates the reading audio according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request. By using the large language model to analyze the roles and lines in the book, and adaptively selecting the timbre template to generate personalized audio, it is possible to better read to the user and improve the user experience.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0022] Figure 1 is a flow chart of a book reading method provided by Embodiment 1 of the present invention;

[0023] Figure 2 is a flow chart of a book reading method provided by Embodiment 2 of the present invention;

[0024] Figure 3 This is a structural block diagram of a book reading device provided by Embodiment 3 of the present invention;

[0025] Figure 4 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", "target", "candidate", "alternative", etc. in the specification and claims of the present invention 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 of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof 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 acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0028] Embodiment 1

[0029] Figure 11 is a flow chart of a method for reading aloud a book provided in the first embodiment of the present invention; this embodiment is applicable to the case where an audio book system performs character analysis and timbre matching on a book sent by a user to provide personalized audio for reading aloud the book, and the method can be executed by a book reading aloud device, which can be implemented in the form of hardware and / or software, and the book reading aloud device can be configured in an electronic device, such as an audio book system, such as Figure 1 As shown, the book reading method includes:

[0030] S101. In response to a book reading request sent by a target user, a target book is determined, and the target book is analyzed and processed based on a preset large language model to obtain target text characters contained in the target book and target character lines corresponding to each target text character.

[0031] Among them, the target user refers to a user who uses the audio book system to select a book or a chapter of a book and requests it to be read aloud. The book reading request may include user identity information and the target book that the target user requests to be read aloud. The target book refers to the book uploaded or selected by the target user through the audio book system interface. The target book can be a book or a chapter of a book. The preset large language model refers to a pre-trained model that can perform text segmentation, character recognition, and text extraction on the target book. The target text role refers to the character role contained in the target book, and the number of target text roles can be at least one. The target character lines refer to all the lines spoken by the target text character recorded in the target book.

[0032] Optionally, the target user can issue an instruction to read the entire book or a specific chapter in the audio book system. If the audio book system detects the instruction issued by the target user, it determines that the book reading request issued by the target user is detected, and can perform automated operations in response to the book reading request issued by the target user to achieve the generation of reading audio.

[0033] Optionally, in response to a book reading request sent by a target user, a preset regular expression may be used to match the request content of the book reading request to obtain the content of the book requested to be read by the target user, that is, to determine the target book.

[0034] Optionally, based on a preset large language model, the target book is analyzed and processed to obtain target text roles contained in the target book and target role lines corresponding to each target text role, including: based on the preset large language model, text segmentation, role recognition and text extraction are performed on the target book to implement text parsing of the target book to obtain candidate text roles contained in the target book and candidate role lines corresponding to each candidate text role; the role names of the candidate text roles are analyzed to merge candidate text roles belonging to the same role with different titles to obtain the target text roles, and determine the target role lines corresponding to each target text role.

[0035] Among them, the preset large language model refers to a preset model for processing text of the target book to generate audio. The candidate text roles refer to all text roles contained in the target book, specifically all text roles with lines listed in double quotes. The candidate text roles may have different titles but are essentially the same role. The target text role refers to a truly independent text role among the candidate text roles. The candidate role lines may be the lines of the candidate text role listed in double quotes in the target book. The target role lines consist of the collection of the candidate role lines of each corresponding merged candidate text role.

[0036] Optionally, the audio book system can be based on a preset large language model. It can first use a preset regular expression, such as the noun say +: + "" regular expression, to perform text segmentation on the target book, perform matching in the target book, obtain the candidate text roles contained in the target book, implement role recognition, and determine the lines of the candidate text role obtained by matching the regular expression and stated in double quotes as the candidate role lines corresponding to the candidate text object, that is, perform text extraction, obtain the target text roles contained in the target book and the target role lines corresponding to each target text role. Among them, the text that conforms to the noun +: + "" regular expression can be: A said: "xxx".

[0037] Optionally, the audio book system can determine whether there are other titles for the character names of each candidate text character based on a preset library of classic character names. For example, "Lu Xun" and "Zhou Shuren" are the same character with different titles. If so, it is determined whether the other titles appear in the target book. If so, the two different titles need to be unified to achieve a merge process to obtain the target text character.

[0038] It should be noted that by clustering different titles of the same role, the uniformity of the role can be effectively guaranteed and the intelligent level of reading aloud can be improved.

[0039] S102, determining role characteristic information corresponding to the target text role, and determining a target timbre template corresponding to the target text role from a preset timbre library according to the role characteristic information, so as to generate a target audio.

[0040] The character feature information may include at least one of the following: the character type, behavioral characteristics, identity category, and emotional change information of the target text character. The preset sound library stores at least two sound templates suitable for different characters. The target audio refers to the audio corresponding to the target character's lines in the target book. The character type can be introverted or extroverted. The behavioral characteristics can be decisive or hesitant. The emotional tendency can be irritable, gentle, angry, sad, or excited.

[0041] Optionally, the character feature information may also include dialogue scenes, character participation and influence. Accordingly, the dialogue scenes may be determined based on the target character's dialogue and the corresponding target text character, and the main and secondary characters in the target text character may be determined to obtain the influence and participation of the main character.

[0042] Optionally, determining role characteristic information corresponding to the target text role includes: analyzing the target role lines corresponding to each target text role to obtain the personality type, behavioral characteristics and emotional tendencies corresponding to each target text role; determining the emotional change information of the target text role based on the emotional tendencies of each line in the target role lines and the position information of each line in the target role lines; obtaining the identity category of the target text role based on the role relationship between the target text roles, and determining the role characteristic information based on the personality type, behavioral characteristics, identity category and emotional change information of the target text role.

[0043] Among them, the emotional change information refers to the changes in the emotional tendency of the target text character in different lines. Specifically, the emotional change information can be, for example, Xiaohong's anger and tension in the plot of Chapter 10, or Zhang San's change from cowardice to bravery in the middle of the story. The identity category can be father, mother, old man, child, king or professor, etc.

[0044] Optionally, a comprehensive analysis can be performed on all target character lines corresponding to each target text character to obtain the personality type and behavioral characteristics corresponding to each target text character. Furthermore, an emotional tendency analysis can be performed on each paragraph of the target character lines to obtain the emotional tendency corresponding to each paragraph of the lines. Specifically, the keywords and high-frequency words in each paragraph of the lines can be matched with the preset correspondence between vocabulary and emotional orientation to determine the emotional tendency corresponding to each paragraph of the lines.

[0045] Optionally, after determining the emotional tendency corresponding to each line, the order of each line can be determined based on the position information of each line in the target character's lines, so as to obtain the emotional change information of the target text character based on the order and emotional tendency.

[0046] Optionally, based on the character characteristic information, a target timbre template corresponding to the target text character is determined from a preset timbre library, including: determining the timbre type and timbre parameters of the target text character based on the character characteristic information; based on the timbre type and timbre parameters, determining a timbre template that conforms to the character characteristic information from a preset timbre library as a target audio template.

[0047] Among them, the timbre type is deep, bright, gentle, majestic or mysterious; the timbre parameters include: speaking speed, pitch and emotional change information; the speaking speed can be fast or slow. The pitch can be high or low. The timbre template refers to a template pre-configured in the audiobook system for audio generation. Different timbre types and timbre parameters correspond to different timbre templates. The timbre template can generate different timbre audio based on age, gender, occupation, and personality. For example, the timbre template can include young men, older women, children, etc.

[0048] Optionally, the timbre type and timbre parameters corresponding to the character feature information of the target text character may be determined based on the correspondence between preset character feature information, timbre type and timbre parameters.

[0049] Exemplarily, if the personality type in the character characteristic information is introverted, the determined timbre type may be deep, and the timbre parameters may be slow speaking speed and low pitch; if the personality type in the character characteristic information is extroverted, the determined timbre type may be bright, and the timbre parameters may be fast speaking speed and high pitch.

[0050] For example, if the identity category in the character characteristic information is the protagonist, a confident and adventurous voice can be used, and correspondingly, a gentle or mysterious voice can be used for a supporting role; if the identity category in the character characteristic information is a mother, a gentle and caring voice can be used, and correspondingly, a father uses a steady and deep voice, and a child uses a lively and cheerful voice.

[0051] S103: Determine the narration audio corresponding to the narration lines in the target book, and generate a reading audio according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request.

[0052] The side lines refer to the text content in the target book other than the target character's lines. The side audio refers to the audio of the narration lines.

[0053] Optionally, determining the narration audio corresponding to the narration lines in the target book includes: determining the text content in the target book other than the target character's lines as the narration lines; and determining the tone template corresponding to the narration lines from a preset tone library according to default configuration information to generate the narration audio.

[0054] Optionally, an exclusive timbre template may be pre-configured for the narration portion of the book, such as a template corresponding to smooth, narrative timbre parameters, to generate narration audio.

[0055] Optionally, the order relationship between the character's lines and the narration lines can be determined according to the text structure of the target book, and the reading audio can be generated based on the order relationship, the target audio and the narration audio; ensuring the coherence and logic of the generated audio content.

[0056] Optionally, during the process of reading a book, based on the emotion change information, if it is detected that a target text character's emotion change is about to be read, the timbre template of the target text character is adjusted to use the adjusted timbre template to read the target dialogue paragraph; after the reading of the target dialogue paragraph is completed, the original timbre template continues to be used to read the target text character's dialogue paragraph.

[0057] Exemplarily, the audiobook system in the present invention can collaboratively generate the audio of the book through multiple agents (Agents), ensuring efficient and intelligent audio generation without manual intervention by the user. Independent agents work together with the large language model, which provides deep text understanding and semantic analysis support. Each agent performs specific tasks based on these analysis results, such as timbre matching, emotion regulation, and audio generation. The large model serves as a "think tank" for data analysis, and each agent performs specific task steps to ensure the automated operation of the entire system. Independent agents work together with the large language model, which provides deep text understanding and semantic analysis support. Each agent performs specific tasks based on these analysis results, such as timbre matching, emotion regulation, and audio generation. The large model serves as a "think tank" for data analysis, and each agent performs specific task steps to ensure the automated operation of the entire system.

[0058] Optionally, the lines and narrations of each character can be sorted and output in the order of the book's plot, and the timbre, intonation and emotional changes of each character can be combined to generate the final immersive audio experience. The model analyzes the scene analysis results of the text, finds the appropriate background sound effects, and synchronizes the timeline. The large model is responsible for extracting scene keywords and understanding its emotional atmosphere, and the audio integration agent generates and matches appropriate sound effects based on this information. Automatically identify appropriate background sound effects and sounds in specific scenes based on the description of the book content, and combine these sound effects with the character's lines to further enhance the immersion and expressiveness of the audio. It not only includes basic background sound effects (such as wind, rain, and waves), but also covers specific sound effects mentioned in special scenes (such as battle sounds, footsteps, etc.). The type and volume of sound effects can be personalized according to user preferences to suit personal listening habits.

[0059] Exemplarily, the timeline synchronization and integration of scene sound effects can be achieved based on the following process: (1) Automatic timeline synchronization: The scene sound effects agent will integrate the sound effects with the character's lines and narration on the timeline to ensure that when the character speaks or important events occur, the background sound effects can be appropriately added and matched with the plot development. For example, when describing "a storm suddenly hits", the system will automatically adjust the volume and timing of the storm sound effect to make the audio performance more natural; (2) Multi-layer sound effect synthesis: In complex scenes (such as battle scenes), the system will synthesize multiple sound effect layers, such as background wind sounds, weapon collision sounds, and character shouts, to create a richer sound scene. (3) Emotion and plot perception: By collaborating with the large language model, the scene sound effects agent can perceive emotional changes in the plot and dynamically adjust the sound effects. For example, when describing a tense scene, the background sound effects can gradually increase the tension by adding low background music to create an atmosphere.

[0060] Optionally, the synthesized audio can be automatically analyzed to detect abnormal or incoherent timbre, and further adjust the timbre and audio parameters to ensure the quality of the final output. The agent covers multiple aspects such as text parsing, timbre configuration, and emotion adjustment to ensure the quality and consistency of the overall audio generation effect.

[0061] For example, in an adventure novel, the system identifies the content of the protagonist, supporting characters, and narration, and assigns a unique timbre to each character. The protagonist uses a confident and adventurous timbre, while the supporting characters use a gentle or mysterious timbre. At the same time, the system generates forest background sound effects and storm sound effects based on the scene description, adding thunder to the tense plot to create a tense atmosphere.

[0062] For example, in a family ethics drama, the system assigns a unique timbre to each family member by analyzing the emotional relationship between the characters, such as the mother uses a gentle and caring timbre, the father uses a calm and deep timbre, and the child uses a lively and cheerful timbre. At the same time, the system recognizes the environment in the family scene, such as the sound of pots and pans colliding in the kitchen and the background sound of the TV in the living room, so that the audience can feel the real family atmosphere.

[0063] The technical solution of the embodiment of the present invention responds to the book reading request sent by the target user, determines the target book, and analyzes and processes the target book based on the preset large language model to obtain the target text roles and target role lines corresponding to each target text role contained in the target book; determines the role feature information corresponding to the target text role, and determines the target timbre template corresponding to the target text role from the preset timbre library according to the role feature information to generate the target audio; determines the narration audio corresponding to the narration lines in the target book, and generates the reading audio according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request. By using the large language model to analyze the roles and lines in the book, and adaptively selecting the timbre template to generate personalized audio, it is possible to better read to the user and improve the user experience.

[0064] Embodiment 2

[0065] Figure 2 is a flow chart of a method for reading aloud a book provided in Embodiment 2 of the present invention; based on the above embodiments, this embodiment provides a preferred example of an audio book system performing character analysis and timbre matching on a book sent by a user to provide personalized audio for reading aloud a book, specifically, Figure 2 As shown, the method includes:

[0066] S201: In response to a book reading request sent by a target user, determine a target book.

[0067] S202: Based on a preset large language model, text segmentation, role recognition and text extraction are performed on the target book to implement text parsing of the target book, and candidate text roles included in the target book and candidate role lines corresponding to each candidate text role are obtained.

[0068] S203, analyzing the role names of the candidate text roles, merging the candidate text roles belonging to the same role with different titles to obtain target text roles, and determining the target role lines corresponding to each target text role.

[0069] S204, analyzing the target character lines corresponding to each target text character to obtain the personality type, behavioral characteristics and emotional tendency corresponding to each target text character.

[0070] S205, determining the emotion change information of the target text character according to the emotional tendency of each paragraph of the target character's lines and the position information of each paragraph of the lines in the target character's lines.

[0071] S206. Obtain the identity category of the target text role based on the role relationship between the target text roles, and determine the role characteristic information based on the personality type, behavior characteristics, identity category and emotion change information of the target text role.

[0072] S207: Determine the timbre type and timbre parameters of the target text character according to the character feature information.

[0073] S208. According to the timbre type and timbre parameters, determine a timbre template that meets the character characteristic information from a preset timbre library as a target audio template to generate a target audio.

[0074] S209: Determine the narration audio corresponding to the narration lines in the target book, and generate a reading audio according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request.

[0075] The present invention imports the book content into a large language model, analyzes all the characters and their lines in the book, and assigns a personalized timbre to each character, thereby solving the problems of monotonous character timbre, unintelligent narration generation, and insufficient timbre correction in the prior art. Users only need to import the book content, and the system can automatically complete character analysis, timbre assignment, emotional expression adjustment, and audio synthesis, providing an immersive auditory experience.

[0076] Embodiment 3

[0077] Figure 3 : is a structural block diagram of a book reading device provided in the third embodiment of the present invention; this embodiment can be applied to the case where an audio book system performs character analysis and timbre matching on a book sent by a user to provide personalized audio for book reading; the book reading device provided in the embodiment of the present invention can execute the book reading method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method; the book reading device can be implemented in the form of hardware and / or software, and configured in an electronic device with a book reading function, such as an audio book system, such as Figure 3 As shown, the book reading device specifically includes:

[0078] The analysis module 301 is used to respond to the book reading request sent by the target user, determine the target book, and analyze the target book based on the preset large language model to obtain the target text characters contained in the target book and the target character lines corresponding to each target text character;

[0079] A generating module 302 is used to determine the role characteristic information corresponding to the target text role, and determine the target timbre template corresponding to the target text role from a preset timbre library according to the role characteristic information to generate the target audio;

[0080] The response module 303 is used to determine the narration audio corresponding to the narration lines in the target book, and generate the reading audio according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request.

[0081] The technical solution of the embodiment of the present invention responds to the book reading request sent by the target user, determines the target book, and analyzes and processes the target book based on the preset large language model to obtain the target text roles and target role lines corresponding to each target text role contained in the target book; determines the role feature information corresponding to the target text role, and determines the target timbre template corresponding to the target text role from the preset timbre library according to the role feature information to generate the target audio; determines the narration audio corresponding to the narration lines in the target book, and generates the reading audio according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request. By using the large language model to analyze the roles and lines in the book, and adaptively selecting the timbre template to generate personalized audio, it is possible to better read to the user and improve the user experience.

[0082] Furthermore, the analysis module 301 is specifically used for:

[0083] Based on the preset large language model, the target book is subjected to text segmentation, role recognition and text extraction to achieve text parsing of the target book, and the candidate text roles contained in the target book and the candidate role lines corresponding to each candidate text role are obtained;

[0084] The role names of the candidate text roles are analyzed to merge the candidate text roles belonging to the same role with different titles to obtain the target text roles, and the target role lines corresponding to each target text role are determined.

[0085] Furthermore, the response module 303 is specifically used for:

[0086] The textual content in the target book other than the target character’s lines is identified as the narration lines;

[0087] According to the default configuration information, the timbre template corresponding to the voice-over lines is determined from the preset timbre library to generate the narration audio.

[0088] Furthermore, the generating module 302 is specifically used for:

[0089] Determine the timbre type and timbre parameters of the target text character according to the character feature information; the timbre type is deep, bright, gentle, majestic or mysterious; the timbre parameters include: speech speed, pitch and emotion change information;

[0090] According to the timbre type and timbre parameters, a timbre template that meets the character characteristic information is determined from a preset timbre library as a target audio template.

[0091] Furthermore, the generating module 302 is also used for:

[0092] Analyze the target character lines corresponding to each target text character to obtain the personality type, behavioral characteristics and emotional tendencies corresponding to each target text character;

[0093] Determine the emotional change information of the target text character according to the emotional tendency of each paragraph of the target character's lines and the position information of each paragraph of the lines in the target character's lines;

[0094] According to the role relationship between the characters in the target text, the identity category of the target text role is obtained, and according to the personality type, behavior characteristics, identity category and emotional change information of the target text role, the role characteristic information is determined.

[0095] Furthermore, the above device is also used for:

[0096] During the book reading process, if it is detected that a target dialogue section in which a target text character has an emotional change is to be read, the timbre template of the target text character is adjusted so that the target dialogue section is read using the adjusted timbre template;

[0097] After finishing reading the target dialogue paragraph, continue to use the original timbre template to read the dialogue paragraph of the target text character.

[0098] Embodiment 4

[0099] Figure 4 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0100] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0101] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0102] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a book reading method.

[0103] In some embodiments, the book reading method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the book reading method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the book reading method in any other appropriate manner (e.g., by means of firmware).

[0104] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0105] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0106] In the context of the present invention, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0107] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0108] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0109] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0110] In one embodiment, the present invention further includes a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, the book reading method of any embodiment of the present invention is implemented.

[0111] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0112] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0113] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for reading a book, characterized in that: include: In response to a book reading request sent by a target user, a target book is determined, and the target book is analyzed and processed based on a preset large language model to obtain target text characters contained in the target book and target character lines corresponding to each target text character; Determine the role characteristic information corresponding to the target text role, and determine the target timbre template corresponding to the target text role from a preset timbre library according to the role characteristic information to generate the target audio; The narration audio corresponding to the narration lines in the target book is determined, and the reading audio is generated according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request.

2. The method according to claim 1, characterized in that Based on the preset large language model, the target book is analyzed and processed to obtain the target text roles contained in the target book and the target role lines corresponding to each target text role, including: Based on the preset large language model, the target book is subjected to text segmentation, role recognition and text extraction to achieve text parsing of the target book, and the candidate text roles contained in the target book and the candidate role lines corresponding to each candidate text role are obtained; The role names of the candidate text roles are analyzed to merge the candidate text roles belonging to the same role with different titles to obtain the target text roles, and the target role lines corresponding to each target text role are determined.

3. The method according to claim 1, characterized in that Determine the narration audio corresponding to the narration lines in the target book, including: The textual content in the target book other than the target character’s lines is identified as the narration lines; According to the default configuration information, the timbre template corresponding to the voice-over lines is determined from the preset timbre library to generate the narration audio.

4. The method according to claim 1, characterized in that: According to the character feature information, a target timbre template corresponding to the target text character is determined from a preset timbre library, including: Determine the timbre type and timbre parameters of the target text character according to the character feature information; the timbre type is deep, bright, gentle, majestic or mysterious; the timbre parameters include: speech speed, pitch and emotion change information; According to the timbre type and timbre parameters, a timbre template that meets the character characteristic information is determined from a preset timbre library as a target audio template.

5. The method according to claim 1, characterized in that Determine the role characteristic information corresponding to the target text role, including: Analyze the target character lines corresponding to each target text character to obtain the personality type, behavioral characteristics and emotional tendencies corresponding to each target text character; Determine the emotional change information of the target text character according to the emotional tendency of each paragraph of the target character's lines and the position information of each paragraph of the lines in the target character's lines; According to the role relationship between the characters in the target text, the identity category of the target text role is obtained, and according to the personality type, behavior characteristics, identity category and emotional change information of the target text role, the role characteristic information is determined.

6. The method according to claim 1, characterized in that Also includes: During the book reading process, if it is detected that a target dialogue section in which a target text character has an emotional change is to be read, the timbre template of the target text character is adjusted so that the target dialogue section is read using the adjusted timbre template; After finishing reading the target dialogue paragraph, continue to use the original timbre template to read the dialogue paragraph of the target text character.

7. A book reading device, characterized in that: include: An analysis module, for responding to a book reading request sent by a target user, determining a target book, and analyzing and processing the target book based on a preset large language model to obtain target text characters contained in the target book and target character lines corresponding to each target text character; A generation module, used to determine the role characteristic information corresponding to the target text role, and determine the target timbre template corresponding to the target text role from a preset timbre library according to the role characteristic information, so as to generate the target audio; The response module is used to determine the narration audio corresponding to the narration lines in the target book, and generate the reading audio according to the target audio and the narration audio and the text structure of the target book to respond to the book reading request.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the book reading method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the book reading method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the book reading method according to any one of claims 1 to 6.

Images