Electronic picture book generation method and device, electronic equipment and storage medium

Abstract

The invention relates to an electronic picture book generation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a basic keyword set, and enabling each basic keyword in the basic keyword set to be related to a picture book story text; traversing basic keywords in the basic keyword set, determining key texts corresponding to the basic keywords, and forming a key text set by the key texts; and generating a picture book story text of the electronic picture book according to the key text set, and generating a picture book illustration of the electronic picture book according to the picture book story text. In this way, the basic keyword set related to the picture book story is given, the picture book story text of the electronic picture book is generated, then the picture book illustration of the electronic picture book is generated, work of a picture book author and an illustrator can be replaced, the design difficulty of the electronic picture book is reduced, time and money input is reduced, and the design cost of the electronic picture book is reduced.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to an electronic picture book generation method, device, electronic device and storage medium. Background Art

[0002] Picture books are mainly paintings with a small amount of articles. In many countries around the world, picture books are the first choice for children's books. Picture book reading can effectively promote children's language development, cultivate children's artistic sentiments, and cultivate children's interest in reading. With the continuous development of science and technology and the changes in people's lifestyles, children's electronic picture books under the digital background are gradually integrated into people's lives. The use of digital technology to design children's electronic picture books can make reading electronic picture books like watching movies, which makes children remember deeply and feel the same.

[0003] Currently, the design of electronic picture books is difficult, requiring the author to have high professional quality and artistic talent, and then manually input the complete picture book story. The electronic painting illustrations are inserted into the electronic picture book through hand-drawn pictures by illustrators with professional art skills who fully understand the picture book story. Secondly, the design cost is high. From the conception of the picture book story, illustration design, to the final conversion into an electronic picture book, the entire production chain is cumbersome and requires a large investment of time and money. Summary of the invention

[0004] In order to solve the above-mentioned current problems in the design of electronic picture books, first of all, the design is difficult, requiring the picture book author to have high professional qualities and artistic talent, and then manually enter the complete picture book story. The electronic painting illustrations are inserted into the electronic picture book through hand-drawn pictures by illustrators with professional art skills on the premise of fully understanding the picture book story. Secondly, the design cost is high. From the conception of the picture book story, illustration design, to the final conversion into an electronic picture book, the entire production chain is cumbersome, and the investment of time and money is large. Technical problems, this application provides a method, device, electronic device and storage medium for generating an electronic picture book. The specific technical solution is as follows:

[0005] In a first aspect, the present application provides a method for generating an electronic picture book, the method comprising:

[0006] Acquire a basic keyword set, wherein each basic keyword in the basic keyword set is related to the story text of the picture book;

[0007] Traversing the basic keywords in the basic keyword set, determining key texts corresponding to the basic keywords, and forming a key text set with the key texts;

[0008] A picture book story text of the electronic picture book is generated according to the key text set, and a picture book illustration of the electronic picture book is generated according to the picture book story text.

[0009] In an optional implementation, obtaining the basic keyword set includes:

[0010] In response to the arrangement instruction for the basic keywords, displaying the multiple basic keywords through the operation view;

[0011] In response to a selection operation on a basic keyword, the selected basic keyword is determined, and the selected basic keywords are sequentially constituted into a basic keyword set.

[0012] In an optional implementation, the basic keywords in the basic keyword set are stored in order;

[0013] The traversing the basic keywords in the basic keyword set to determine the key texts corresponding to the basic keywords includes:

[0014] Traversing the basic keywords in the basic keyword set, converting the basic keywords into question voices for playback;

[0015] A response voice issued by the electronic picture book creator in response to the question voice is received, and voice recognition is performed on the response voice to obtain key texts corresponding to the basic keywords.

[0016] In an optional implementation, generating a picture book story text of the electronic picture book according to the key text set includes:

[0017] Performing semantic recognition on the key text in the key text set to obtain a semantic recognition result, wherein the semantic recognition result represents the intention of the creator of the electronic picture book;

[0018] Obtaining picture book story constraint keywords, wherein the picture book story constraint keywords are used to constrain the picture book story text output by the Wenshengwen model;

[0019] The semantic recognition result and the picture book story constraint keywords are provided to the Wenshengwen model to generate the picture book story text of the electronic picture book.

[0020] In an optional implementation, generating the picture book illustration of the electronic picture book according to the picture book story text includes:

[0021] Obtaining picture book illustration constraint keywords, wherein the picture book illustration constraint keywords are used to constrain the picture book illustration output by the literary figure model;

[0022] The picture book story text and the picture book illustration constraint keywords are provided to the text-based picture model to generate the picture book illustrations of the electronic picture book.

[0023] In an optional implementation, providing the picture book story text and the picture book illustration constraint keywords to the text-based image model to generate the picture book illustration of the electronic picture book includes:

[0024] In response to an editing operation on the picture book story text, acquiring the edited picture book story text;

[0025] The edited picture book story text and the picture book illustration constraint keywords are provided to the text-based picture model to generate picture book illustrations of the electronic picture book.

[0026] In an optional embodiment, the method further comprises:

[0027] In response to a voice playback instruction for the picture book story text of the electronic picture book, the following processing is performed:

[0028] Converting the picture book story text of the electronic picture book into a target voice of a target character, and playing the target voice;

[0029] or,

[0030] Acquire the original voice of a specific character, and preprocess the original voice to obtain the preprocessed original voice;

[0031] Extracting features from the preprocessed original speech to obtain speech features, and converting the speech features into spectral features;

[0032] In response to a voice playback instruction for the picture book story text of the electronic picture book, the following processing is performed:

[0033] A timbre synthesis is performed according to the pronunciation sequence of the picture book story text of the electronic picture book and the frequency spectrum feature to obtain a synthesized voice, and the synthesized voice is played.

[0034] In a second aspect, the present application provides an electronic picture book generating device, the device comprising:

[0035] A keyword set acquisition module, used to acquire a basic keyword set, wherein each basic keyword in the basic keyword set is related to the story text of the picture book;

[0036] A text determination module, used for traversing the basic keywords in the basic keyword set, determining key texts corresponding to the basic keywords, and forming a key text set from the key texts;

[0037] A story generation module, used to generate a picture book story text of the electronic picture book according to the key text set;

[0038] The illustration generation module is used to generate picture book illustrations for the electronic picture book based on the picture book story text.

[0039] In a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0040] Memory, used to store computer programs;

[0041] The processor is used to implement any electronic picture book generation method described in the first aspect when executing the program stored in the memory.

[0042] In a fourth aspect, a storage medium is further provided, wherein instructions are stored in the storage medium, and when the storage medium is run on a computer, the computer executes any of the electronic picture book generation methods described in the first aspect.

[0043] In a fifth aspect, a computer program product comprising instructions is also provided, which, when executed on a computer, enables the computer to execute any of the above-mentioned electronic picture book generation methods.

[0044] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application obtains a basic keyword set, wherein each basic keyword in the basic keyword set is related to a picture book story text, traverses the basic keywords in the basic keyword set, determines the key texts corresponding to the basic keywords, and forms a key text set with the key texts, generates a picture book story text of an electronic picture book based on the key text set, and generates picture book illustrations of the electronic picture book based on the picture book story text.

[0045] By obtaining a basic keyword set, generating a key text set based on the basic keyword set, generating a picture book story text for an electronic picture book based on the key text set, and then generating picture book illustrations for the electronic picture book based on the picture book story text, a basic keyword set related to a picture book story is given, thereby generating a picture book story text for an electronic picture book, and then generating picture book illustrations for the electronic picture book, which can replace the work of picture book authors and illustrators, reduce the difficulty of electronic picture book design, and reduce the investment of time and money, thereby reducing the cost of electronic picture book design. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0049] Figure 1 A schematic diagram of an implementation flow of an electronic picture book generation method provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of an implementation flow of another electronic picture book generation method provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a voice interaction provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of the structure of an electronic picture book generating device provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution 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 part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0055] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0056] like Figure 1FIG. 1 is a schematic diagram of an implementation flow of a method for generating an electronic picture book provided in an embodiment of the present application. The method is applied to an electronic device and may specifically include the following steps:

[0057] S101, obtaining a basic keyword set, wherein each basic keyword in the basic keyword set is related to the story text of the picture book.

[0058] In an embodiment of the present application, a basic keyword set can be obtained, wherein the basic keyword set includes at least one keyword, and each basic keyword is related to the picture book story text, so that the basic keywords in the basic keyword set can constitute the basic context of the picture book story text.

[0059] For example, a basic keyword set is obtained, wherein the basic keyword set includes the following basic keywords: character role, character name, character gender, story time, story plot, story meaning, story style, etc. Each basic keyword is related to the picture book story text and constitutes the basic context of the picture book story text.

[0060] S102, traversing the basic keywords in the basic keyword set, determining key texts corresponding to the basic keywords, and forming a key text set with the key texts.

[0061] In the embodiment of the present application, each basic keyword in the above basic keyword set can be regarded as a Key, and its corresponding Value needs to be determined. Therefore, the basic keywords in the basic keyword set are traversed to determine the key text corresponding to the basic keyword. The key text here can be regarded as a Value, and the key text set is composed of the key texts.

[0062] For example, the basic keyword "character role" can be regarded as a Key, and its corresponding Value needs to be determined. To this end, the basic keyword in the basic keyword set can be traversed to determine the key text "teacher" corresponding to the basic keyword, which means that "character role" is regarded as a Key, and "teacher" is regarded as a Value.

[0063] In this way, the basic keywords in the basic keyword set are traversed to determine the key texts corresponding to the basic keywords. Each basic keyword has a corresponding key text, and the key texts can constitute a key text set. The key text set can represent the basic content of the picture book story text, which is similar to the story introduction of the picture book story text.

[0064] S103, generating a picture book story text of the electronic picture book according to the key text set, and generating picture book illustrations of the electronic picture book according to the picture book story text.

[0065] In the embodiment of the present application, for the key text set obtained above, the picture book story text of the electronic picture book can be generated according to the key text set. Among them, the picture book story text of the electronic picture book can be generated by means of the Wenshengwen model of Wenshengwen (that is, the input of the Wenshengwen model is text and the output is text).

[0066] After the story text of the electronic picture book is generated, the illustrations of the electronic picture book can be generated according to the story text of the electronic picture book. The illustrations of the electronic picture book can be generated by using a text-based model (i.e., the input of the text-based model is text, and the output is a picture).

[0067] Through the above description of the technical solution provided in the embodiment of the present application, a basic keyword set is obtained, wherein each basic keyword in the basic keyword set is related to a picture book story text, the basic keywords in the basic keyword set are traversed, the key texts corresponding to the basic keywords are determined, a key text set is composed of the key texts, and based on the key text set, a picture book story text of an electronic picture book is generated, and based on the picture book story text, picture book illustrations of the electronic picture book are generated.

[0068] By obtaining a basic keyword set, generating a key text set based on the basic keyword set, generating a picture book story text for an electronic picture book based on the key text set, and then generating picture book illustrations for the electronic picture book based on the picture book story text, a basic keyword set related to a picture book story is given, thereby generating a picture book story text for an electronic picture book, and then generating picture book illustrations for the electronic picture book, which can replace the work of picture book authors and illustrators, reduce the difficulty of electronic picture book design, and reduce the investment of time and money, thereby reducing the cost of electronic picture book design.

[0069] like Figure 2 FIG. 1 is a schematic diagram of an implementation flow of another method for generating an electronic picture book provided in an embodiment of the present application. The method is applied to an electronic device and may specifically include the following steps:

[0070] S201 : In response to an arrangement instruction for a basic keyword, display a plurality of basic keywords through an operation view.

[0071] S202, in response to a selection operation on a basic keyword, determining the selected basic keyword, and sequentially forming a basic keyword set with the selected basic keywords, wherein each basic keyword in the basic keyword set is related to the story text of the picture book.

[0072] In the embodiment of the present application, the arrangement capability is provided for the basic keywords, which means that the basic keywords can be arranged. Thus, the electronic picture book creator can execute the arrangement instruction for the basic keywords, and thus display multiple basic keywords through the operation view in response to the arrangement instruction for the basic keywords.

[0073] For multiple basic keywords displayed in the operation view, the electronic picture book creator can select corresponding basic keywords, thereby determining the selected basic keywords in response to the selection operation for the basic keywords, and sequentially forming a basic keyword set with the selected basic keywords, wherein each basic keyword in the basic keyword set is related to the picture book story text.

[0074] After the above operations, the basic keywords can be arranged, and the electronic picture book creator can arrange the basic keywords suitable for himself, thereby forming a basic keyword set in sequence. It should be noted that the electronic picture book creator can be an ordinary adult, of course, or a child, and the embodiment of the present application does not limit this.

[0075] S203, traversing the basic keywords in the basic keyword set, converting the basic keywords into question voices for playback.

[0076] S204, receiving a response voice issued by the electronic picture book creator in response to the question voice, performing voice recognition on the response voice, obtaining key texts corresponding to the basic keywords, and forming a key text set with the key texts.

[0077] In the embodiment of the present application, for the basic keywords in the basic keyword set, the key text corresponding to the basic keywords can be determined by voice interaction. Thus, the basic keywords in the basic keyword set are traversed, the basic keywords are converted into question voices for playback, the answer voice issued by the electronic picture book creator in response to the question voice is received, the answer voice is voice recognized, and the key text corresponding to the basic keyword is obtained, and the key text constitutes a key text set.

[0078] For example, the basic keyword set includes the following basic keywords: character role, character name, character gender, story age, story plot, story meaning, story style, etc. The basic keywords in the basic keyword set are traversed, the basic keywords are converted into question voices for playback, the answer voice issued by the electronic picture book creator in response to the question voice is received, the answer voice is recognized, and the key text corresponding to the basic keywords is obtained, such as Figure 3 As shown, the key text set is composed of key texts.

[0079] It should be noted that after traversing the basic keywords in the basic keyword set, for the key texts in the key text set, the electronic picture book creator can be uniformly confirmed whether the above key texts are correct. Specifically, the key texts can be played by voice, or displayed in the form of an operation view, to confirm whether the above key texts are correct with the electronic picture book creator. The embodiments of the present application are not limited to this.

[0080] S205, performing semantic recognition on the key texts in the key text set to obtain a semantic recognition result, which represents the intention of the creator of the electronic picture book.

[0081] S206, obtaining picture book story constraint keywords, wherein the picture book story constraint keywords are used to constrain the picture book story text output by the Wenshengwen model.

[0082] S207, providing the semantic recognition results and picture book story constraint keywords to the Wenshengwen model to generate the picture book story text of the electronic picture book.

[0083] In an embodiment of the present application, for the key texts in the key text set, semantic recognition can be performed on the key texts in the key text set to obtain a semantic recognition result, which represents the intention of the creator of the electronic picture book.

[0084] Semantic recognition involves extracting meaning from natural language text so that computers can understand and process it. Semantic recognition can be divided into the following subtasks:

[0085] 1. Word meaning analysis: involves the study of the meaning and usage of words.

[0086] 2. Syntactic analysis: involves the study of sentence structure and grammatical rules.

[0087] 3. Semantic role labeling: involves labeling the semantic roles of each word in a sentence.

[0088] 4. Relationship extraction: involves the extraction and understanding of relationships between entities in the text.

[0089] 5. Sentiment analysis: involves the identification and analysis of emotional tendencies in text.

[0090] Among them, for word meaning analysis, the meaning and usage of words are mainly studied through vocabulary statistics, word meaning derivation, word meaning combination and other methods. In semantic recognition, the Naive Bayes algorithm can be used to perform word meaning analysis.

[0091] For syntactic analysis, sentence structure and grammatical rules are mainly studied through methods such as dependency napsing and syntax rule parsing. Dependency napsing can use algorithms based on conditional random fields (CRF).

[0092] Semantic role labeling is mainly achieved through rule-based methods and model-based methods. The model-based methods mainly include methods based on Hidden Markov Model (HMM) and methods based on Recurrent Neural Network (RNN).

[0093] Relation extraction is mainly achieved through rule engines, machine learning, deep learning, etc. Relation extraction can use a tree-based model (Tree-LSTM).

[0094] Sentiment analysis is mainly achieved through machine learning and deep learning. Sentiment analysis can be performed using a method based on a recurrent neural network (RNN).

[0095] Therefore, the above-mentioned semantic recognition of the key texts in the key text set can be specifically performed on the key texts in the key text set through word meaning analysis, syntactic analysis, semantic role labeling, relationship extraction, sentiment analysis, etc., and then the word meaning results, syntactic results, semantic role results, relationship results, sentiment results, etc. are obtained respectively.

[0096] In addition, in the embodiment of the present application, a prompt arrangement capability is provided, corresponding to the instructions and constraints of the AI's reply. For this purpose, picture book story constraint keywords (for example, prohibiting stories that are not suitable for children) can be obtained, wherein the picture book story constraint keywords are used to constrain the picture book story text output by the Vincent model, and the semantic recognition result and the picture book story constraint keywords are provided to the Vincent model to generate the picture book story text of the electronic picture book.

[0097] It should be noted that the Vincent model can be any large language model currently available on the market that can perform Vincent, and the present application embodiment does not limit this. In addition, the parameters of the Vincent model can be adjusted at any time as needed, and the source of the Vincent model can be switched, that is, a locally deployed Vincent model can be selected, or other Vincent models can be selected.

[0098] In addition, the picture book story constraint keywords may be related to the electronic picture book creator. For example, if the electronic picture book creator is an ordinary adult, then the picture book story constraint keywords may be ordinary constraint keywords adapted to the electronic picture book creator. If the electronic picture book creator is a child, then the picture book story constraint keywords may be special constraint keywords adapted to the electronic picture book creator, such as prohibiting stories that are not suitable for children. The embodiments of the present application do not limit this.

[0099] S208, obtaining picture book illustration constraint keywords, wherein the picture book illustration constraint keywords are used to constrain the picture book illustration output by the literary image model.

[0100] S209, providing the picture book story text and picture book illustration constraint keywords to the Wenshengtu model to generate picture book illustrations of the electronic picture book.

[0101] In the embodiment of the present application, a prompt editing capability is provided, corresponding to the instructions and constraints of the AI's reply. For this purpose, picture book illustration constraint keywords (for example, prohibiting illustrations that are not suitable for children) can be obtained, wherein the picture book illustration constraint keywords are used to constrain the picture book illustrations output by the Wenshengtu model, and the picture book story text and picture book illustration constraint keywords are provided to the Wenshengtu model to generate the picture book illustrations of the electronic picture book.

[0102] Among them, the picture book story text of the electronic picture book output by the Wenshengwen model supports manual secondary editing, so that the Wenshengtu model can generate picture book illustrations for the electronic picture book based on the picture book story text of the electronic picture book output by the Wenshengwen model and the results of manual secondary editing.

[0103] To this end, the creator of an electronic picture book can perform editing operations on the picture book story text of the electronic picture book output by the Wenshengwen model, thereby obtaining the edited picture book story text in response to the editing operation on the picture book story text, and providing the edited picture book story text and the picture book illustration constraint keywords to the Wenshengtu model to generate the picture book illustrations of the electronic picture book.

[0104] It should be noted that the text graph model can be any large language model that can perform text graphs on the market, and the embodiments of the present application do not limit this. In addition, the parameters of the text graph model can be adjusted at any time as needed, and the source of the text graph model can be switched, that is, a locally deployed text graph model can be selected, or other text graph models can be selected.

[0105] In addition, for picture book illustration constraint keywords, they may be related to the electronic picture book creator. For example, if the electronic picture book creator is an ordinary adult, then the picture book illustration constraint keywords may be ordinary constraint keywords adapted to the electronic picture book creator. If the electronic picture book creator is a child, then the picture book illustration constraint keywords may be special constraint keywords adapted to the electronic picture book creator, such as prohibiting illustrations that are not suitable for children. The embodiments of the present application do not limit this.

[0106] In addition, in the embodiment of the present application, the electronic picture book can be an audio electronic picture book. For this reason, the picture book story text of the electronic picture book output by the Wenshengwen model can be played by voice, which can be characterized by providing the voice of a given IP character, or by voice playback according to the preferred IP character through voice timbre replication technology. The voice timbre replication technology mainly uploads a piece of original voice of the IP character, pre-processes and extracts features of the original voice, and performs timbre synthesis based on the pronunciation sequence of the text plus the features of the original voice.

[0107] Based on this, the creator of the electronic picture book can execute a voice playback instruction for the picture book story text of the electronic picture book output by the Wenshengwen model, and thus, in response to the voice playback instruction for the picture book story text of the electronic picture book, perform the following processing: convert the picture book story text of the electronic picture book into the target voice of the target character (for example, an anime character), and play the target voice.

[0108] Alternatively, the original voice of a specific character (such as an ordinary adult or child) is obtained, and the original voice is preprocessed to obtain the preprocessed original voice; feature extraction is performed on the preprocessed original voice to obtain voice features, and the voice features are converted into spectral features; in response to a voice playback instruction for the picture book story text of the electronic picture book, the following processing is performed: timbre synthesis is performed according to the pronunciation sequence of the picture book story text of the electronic picture book and the spectral features to obtain synthesized voice, and the synthesized voice is played.

[0109] It should be noted that preprocessing includes noise reduction and noise removal to ensure that the extracted speech features are clear and discernible. The speech features can be converted into spectral features by using a technology based on digital signal processing, and the speech features are analyzed in the frequency domain to extract spectral features such as frequency, amplitude and phase. In addition, timbre synthesis includes rule-based synthesis and statistical modeling methods. The rule-based synthesis method is to analyze and reconstruct spectral features according to existing models and rules, and the embodiments of the present application are not limited to this.

[0110] Corresponding to the above method embodiment, the present application embodiment also provides an electronic picture book generating device, such as Figure 4 As shown, the device may include: a keyword set acquisition module 410 , a text determination module 420 , a story generation module 430 , and an illustration generation module 440 .

[0111] A keyword set acquisition module 410 is used to acquire a basic keyword set, wherein each basic keyword in the basic keyword set is related to the story text of the picture book;

[0112] A text determination module 420 is used to traverse the basic keywords in the basic keyword set, determine the key texts corresponding to the basic keywords, and form a key text set with the key texts;

[0113] A story generating module 430 is used to generate a picture book story text of the electronic picture book according to the key text set;

[0114] The illustration generation module 440 is used to generate picture book illustrations of the electronic picture book according to the picture book story text.

[0115] The present application also provides an electronic device, such as Figure 5 As shown, it includes a processor 51, a communication interface 52, a memory 53 and a communication bus 54, wherein the processor 51, the communication interface 52, and the memory 53 communicate with each other through the communication bus 54.

[0116] A memory 53, for storing computer programs;

[0117] The processor 51 is used to execute the program stored in the memory 53 to implement the following steps:

[0118] Obtain a basic keyword set, wherein each basic keyword in the basic keyword set is related to a picture book story text; traverse the basic keywords in the basic keyword set, determine the key texts corresponding to the basic keywords, and form a key text set with the key texts; generate a picture book story text of an electronic picture book according to the key text set, and generate a picture book illustration of the electronic picture book according to the picture book story text.

[0119] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0120] The communication interface is used for communication between the above electronic device and other devices.

[0121] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0122] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0123] In another embodiment provided in the present application, a storage medium is further provided. The storage medium stores instructions. When the storage medium is executed on a computer, the computer executes the electronic picture book generation method described in any one of the above embodiments.

[0124] In another embodiment provided in the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the electronic picture book generating method described in any one of the above embodiments.

[0125] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a storage medium, or transmitted from one storage medium to another storage medium, for example, the computer instructions may 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 (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may 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 Solid State Disk (SSD)), etc.

[0126] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0127] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0128] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A method for generating an electronic picture book, characterized in that: The method comprises: Acquire a basic keyword set, wherein each basic keyword in the basic keyword set is related to the story text of the picture book; Traversing the basic keywords in the basic keyword set, determining key texts corresponding to the basic keywords, and forming a key text set with the key texts; A picture book story text of the electronic picture book is generated according to the key text set, and a picture book illustration of the electronic picture book is generated according to the picture book story text.

2. The method according to claim 1, characterized in that: The obtaining of the basic keyword set includes: In response to the arrangement instruction for the basic keywords, displaying the multiple basic keywords through the operation view; In response to a selection operation on a basic keyword, the selected basic keyword is determined, and the selected basic keywords are sequentially constituted into a basic keyword set.

3. The method according to claim 1, characterized in that In the basic keyword collection, basic keywords are stored in order; The traversing the basic keywords in the basic keyword set to determine the key texts corresponding to the basic keywords includes: Traversing the basic keywords in the basic keyword set, converting the basic keywords into question voices for playback; A response voice issued by the electronic picture book creator in response to the question voice is received, and voice recognition is performed on the response voice to obtain a key text corresponding to the basic keyword.

4. The method according to claim 1, characterized in that: Generating the picture book story text of the electronic picture book according to the key text set includes: Performing semantic recognition on the key text in the key text set to obtain a semantic recognition result, wherein the semantic recognition result represents the intention of the creator of the electronic picture book; Obtaining picture book story constraint keywords, wherein the picture book story constraint keywords are used to constrain the picture book story text output by the Wenshengwen model; The semantic recognition result and the picture book story constraint keywords are provided to the Wenshengwen model to generate the picture book story text of the electronic picture book.

5. The method according to claim 1, characterized in that Generating the picture book illustration of the electronic picture book according to the picture book story text includes: Obtaining picture book illustration constraint keywords, wherein the picture book illustration constraint keywords are used to constrain the picture book illustration output by the literary figure model; The picture book story text and the picture book illustration constraint keywords are provided to the text-based picture model to generate the picture book illustrations of the electronic picture book.

6. The method according to claim 5, characterized in that Providing the picture book story text and the picture book illustration constraint keywords to the literary figure model to generate the picture book illustration of the electronic picture book includes: In response to an editing operation on the picture book story text, acquiring the edited picture book story text; The edited picture book story text and the picture book illustration constraint keywords are provided to the text-based picture model to generate picture book illustrations of the electronic picture book.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: In response to a voice playback instruction for the picture book story text of the electronic picture book, the following processing is performed: Converting the picture book story text of the electronic picture book into a target voice of a target character, and playing the target voice; or, Acquire the original voice of a specific character, and preprocess the original voice to obtain the preprocessed original voice; Extracting features from the preprocessed original speech to obtain speech features, and converting the speech features into spectral features; In response to a voice playback instruction for the picture book story text of the electronic picture book, the following processing is performed: A timbre synthesis is performed according to the pronunciation sequence of the picture book story text of the electronic picture book and the frequency spectrum feature to obtain a synthesized voice, and the synthesized voice is played.

8. An electronic picture book generating device, characterized in that: The device comprises: A keyword set acquisition module, used to acquire a basic keyword set, wherein each basic keyword in the basic keyword set is related to the story text of the picture book; A text determination module, used for traversing the basic keywords in the basic keyword set, determining key texts corresponding to the basic keywords, and forming a key text set from the key texts; A story generation module, used to generate a picture book story text of the electronic picture book according to the key text set; The illustration generation module is used to generate picture book illustrations for the electronic picture book based on the picture book story text.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing any of the methods described in claims 1-7 when executing a program stored in a memory.

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

Images