Story retouching method and device

Abstract

The invention provides a story retouching method and device. The method comprises the following steps: determining original story data of a target user; according to a retouching dimension matched with the target user, retouching the original story data to obtain retouching story data corresponding to the original story data; and displaying the retouching story data. After the original story data is polished according to the polishing dimension, the obtained polished story data can be accurately in butt joint with the cognitive level of the target user, so that the target user can more easily and pleasantly understand and accept the story content, and the reading interest and participation degree of the target user are improved. Besides, personalized story retouching customization can be carried out for different users by flexibly deploying a retouching dimension strategy, and the general applicability and flexibility of the story retouching method are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of natural language processing, and in particular to a story polishing method and device. Background Art

[0002] Story polishing refers to modifying, improving and optimizing the original story text to enhance the story's appeal, readability and educational value. The polishing process may include adjusting the language style, enhancing the coherence of the plot, enriching the character description, optimizing the language expression and other aspects, aiming to make the story more vivid, interesting and easy to understand. For different types of articles, the focus of polishing will also be different. For example, for stories for young children, the polishing process focuses more on the simplicity and understandability of the language, the interest of the plot and the integration of educational significance.

[0003] Existing story polishing solutions mainly rely on powerful natural language processing large models. Although they can meet the basic needs of general text polishing, the generated content is too professional and lacks interest for young children, and is not conducive to their understanding. Summary of the invention

[0004] The present invention provides a story polishing method and device to solve the defects in the prior art.

[0005] The present invention provides a story polishing method, comprising the following steps: Determine the original story data of target users; polishing the original story data according to the polishing dimension matching the target user to obtain polished story data corresponding to the original story data; The polished story data is displayed.

[0006] According to a story polishing method provided by the present invention, the polishing dimension includes at least one of a sound effect dimension, a picture dimension, a virtual image dimension, and an expansion dimension; The polishing of the original story data according to the polishing dimension matching the target user includes: In the sound effect dimension, based on the attribute characteristics of each story element in the original story data, the music of each story element is determined, and the original story data is polished based on the music of each story element; In the dimension of illustration, based on the appearance characteristics of each story element, the illustration of each story element is determined, and the original story data is polished based on the illustration of each story element; In the virtual image dimension, based on the image of the target user and the voice data of the target user, a virtual image of the target user is generated, and the original story data is polished based on the virtual image; In the expansion dimension, the expansion content is determined based on the logical relationship between the story elements, and the original story data is polished based on the expansion content.

[0007] According to a story polishing method provided by the present invention, the step of determining the expanded content based on the logical relationship between the story elements includes: Determine missing elements in the original story data based on the logical relationship between the story elements and the semantic information of the original story data; Based on the age level of the target users, the expanded content for describing the missing element is determined.

[0008] According to a story polishing method provided by the present invention, generating a virtual image of the target user based on the image of the target user and the voice data of the target user includes: Extracting the voice features of the target user from the voice data; Based on the speech features, performing speech synthesis on the expanded story data to obtain synthesized speech, wherein the expanded story data is story data obtained by integrating the expanded content into the original story data; A virtual image of the target user is generated based on the image of the target user and the synthesized voice.

[0009] According to a story polishing method provided by the present invention, the image and the voice data are collected when the target user tells a story; The step of generating a virtual image of the target user based on the image of the target user and the synthesized voice includes: Based on the image of the target user, identifying the expression of the target user when telling a story; Based on the voice data, extracting environmental features of the target user when telling a story; A virtual image of the target user is generated based on the expression, the synthesized voice and the environmental characteristics.

[0010] According to a story polishing method provided by the present invention, the polished story data includes first polishing data and second polishing data, the first polishing data is obtained by polishing the original story data according to at least one of the sound effect dimension, the picture dimension and the virtual image dimension, and the second polishing data is obtained by polishing the original story data according to the expansion dimension; The presenting of the polished story data includes: The first polishing data and the second polishing data are displayed.

[0011] The present invention also provides a story polishing device, comprising the following modules: A determination unit, used for determining original story data of a target user; A polishing unit, configured to polish the original story data according to a polishing dimension matching the target user, to obtain polished story data corresponding to the original story data; A display unit is used to display the polished story data.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the story polishing methods described above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the story polishing method described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for polishing a story as described above is implemented.

[0015] The story polishing method and device provided by the present invention, because the polishing dimensions are highly consistent with the cognitive characteristics and interest tendencies of the target users, after the original story data is polished according to the polishing dimensions, the polished story data obtained can accurately match the cognitive level of the target users, so that the target users can more easily and happily understand and accept the story content, thereby enhancing their reading interest and participation. In addition, the present invention can customize personalized story polishing for different users by flexibly deploying polishing dimension strategies, which significantly improves the universal applicability and flexibility of the story polishing method. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the story polishing method provided by the present invention.

[0018] Figure 2 It is a flowchart diagram of an implementation of step 120 in the story polishing method provided by the present invention.

[0019] Figure 3 It is a structural schematic diagram of the story polishing device provided by the present invention.

[0020] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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 are within the scope of protection of the present invention.

[0022] When big models are polishing stories, they usually use natural language processing (NLP) technology, including text analysis, language generation, and semantic understanding. Big models can identify key information in the original story, such as characters, plots, and themes, and generate polished stories based on this information.

[0023] Although large models excel in general story polishing, they often lack dedicated applicability for specific user groups, such as young children. Among them, young children have the richest imagination. They are able to create highly creative paintings and bring various characters to life with the help of simple toys, thereby weaving a series of wonderful storylines. However, compared with paintings that are easy to preserve as a form of expression, children's self-created stories are more difficult to record and are often difficult to be effectively captured and preserved by parents or teachers. In addition, stories of young children often have unique language styles and plot structures, and large models may not be able to fully capture these characteristics, resulting in the polished stories still tending to be adult or professional.

[0024] In addition, when polishing stories, large models tend to focus more on the accuracy and coherence of the language, while ignoring the fun of the content, which may make the polished stories unattractive and difficult to arouse the interest of young children. The content generated by large models may also be too complex or abstract, which is not conducive to the understanding of young children.

[0025] In this regard, the present invention provides a story polishing method, which aims to perform targeted polishing on the original story data of the target user through the polishing dimensions matching the target user, thereby ensuring that the generated polished story data not only retains the core requirements of the original story data, but also is close to the cognitive characteristics of the target user, thereby achieving personalized and customized story polishing for different user groups.

[0026] That is to say, the story polishing method provided by the present invention can be applied to different user groups, such as young children, school-age children, and adults. In order to facilitate understanding of the technical solution of the present invention, the following embodiments are all described by taking young children as the target users. Figure 1 is a flow chart of the story polishing method provided by the present invention, such as Figure 1 As shown, the method includes step 110 , step 120 and step 130 .

[0027] Step 110: Determine the original story data of the target user.

[0028] Specifically, the original story data refers to story data that is directly derived from the target user without any modification or polishing. The original story data can be audio data when the target user tells the story, or it can be video data when the target user tells the story. The embodiment of the present invention does not specifically limit this.

[0029] In addition, in order to provide more comprehensive and rich data support for the subsequent polishing process, the collection scope of the original story data can be further expanded to include facial images and environmental sounds of the target user when telling the story. Among them, facial images can directly reflect the changes in the target user's expression during the storytelling process. These changes in expression contain the emotional fluctuations of the narrator and the creation of the story atmosphere, so that the emotional expression and appeal of the story can be enhanced during polishing. At the same time, environmental sounds such as applause, cheers, and cheers, as a direct reflection of the audience's reaction, can reflect the appeal of the story to the audience and the audience's emotional feedback. These sound elements can be reasonably incorporated during polishing to further enhance the story atmosphere and enhance the interactivity and appeal of the story.

[0030] Step 120: polish the original story data according to the polishing dimension matching the target user to obtain polished story data corresponding to the original story data.

[0031] Considering that stories about young children usually have unique language expressions and narrative structures, and large-scale language models are often trained on extensive and general data sets, it may be difficult to accurately grasp the unique elements of young children's stories, such as vivid and concrete vocabulary, repetitive narrative patterns, and plots rich in creativity and imagination, resulting in the generated story content being biased towards adult logic or professional contexts. If a corresponding large-scale model is customized for young children, the primary difficulty is that the limited expression ability and reading experience of young children will greatly restrict the collection of high-quality training data; secondly, training exclusive models for different age groups or specific groups will undoubtedly greatly increase economic costs and technical investment. In view of this, an embodiment of the present invention proposes a story polishing method, which aims to polish and adjust story data from a perspective that is consistent with the target user (i.e., young children). The specific scheme is as follows: In order to ensure that the polishing of the original story data can be highly consistent with the needs of the target users, the first step of the embodiment of the present invention is to define the polishing dimensions suitable for the target users. The polishing dimensions refer to a series of specific and targeted standards and directions based on which the original story data is polished. These standards and directions make the polished stories more consistent with the needs and preferences of the target users.

[0032] For example, given that young children have limited cognitive levels and relatively weak abilities to understand and accept, stories can be polished for young children from the dimensions of sound effects (such as adding vivid and interesting sound effects), illustrations (such as adding colorful and vivid illustrations), and virtual images (such as designing cute and recognizable cartoon characters). This can match the cognitive characteristics and interest preferences of young children and enhance their reading experience and participation.

[0033] In addition, given that the original story data of young children is usually chaotic and disordered, some key plots may be missing from the original story data, resulting in a loose and incoherent story structure. In order to solve this problem, the story can be polished from the perspective of expansion, that is, according to the development and logical needs of the story, appropriate details can be added or expanded, and the plot content can be enriched to ensure the integrity and logical coherence of the story, making the story more vivid, interesting and easy to understand.

[0034] It can be seen that the setting of the polishing dimensions is highly consistent with the cognitive characteristics and interest tendencies of the target users. After the original story data is polished according to these polishing dimensions, the polished story data obtained can accurately match the cognitive level of the target users, so that the target users can more easily and happily understand and accept the story content, thereby increasing their reading interest and participation. In addition, the implementation of the present invention can avoid the need to train special models for different age groups or specific user groups by flexibly deploying polishing dimension strategies, effectively reducing training costs, and improving story polishing efficiency and wide applicability.

[0035] For example, the original story data can be polished according to the polishing dimension matching the target user based on the story polishing model to obtain polished story data corresponding to the original story data. The story polishing model can be a large model or a pre-trained model, which is not specifically limited in the embodiment of the present invention.

[0036] Step 130: Display the polished story data.

[0037] Specifically, the polished story data can be in various forms, such as video data or audio data. For example, after adding music to the original story data for polishing, the polished story data obtained is audio data; if the original story data is animated, the polished story data generated is video data.

[0038] In addition, after displaying the polished story data, since it is usually highly matched with the cognitive level of the target users, it can help the target users to understand the story content more deeply, thereby promoting their comprehensive development in cognitive fields such as language, thinking, and imagination. Among them, the polished story data can be uploaded to the online story platform and displayed and shared through the web page or mobile application.

[0039] The story polishing method provided by the embodiment of the present invention, because the polishing dimension is highly consistent with the cognitive characteristics and interest tendencies of the target user, after the original story data is polished according to the polishing dimension, the polished story data obtained can accurately match the cognitive level of the target user, so that the target user can more easily and happily understand and accept the story content, thereby enhancing their reading interest and participation. In addition, the present invention can customize personalized story polishing for different users by flexibly deploying the polishing dimension strategy, which significantly improves the universal applicability and flexibility of the story polishing method.

[0040] Based on the above embodiment, the polishing dimension includes at least one of a sound effect dimension, a picture dimension, a virtual image dimension, and an expansion dimension; Figure 2 is a flow chart of an implementation of step 120 in the story polishing method provided by the present invention, such as Figure 2 As shown, step 120 polishes the original story data according to the polishing dimension matching the target user, including: Step 121: Under the sound effect dimension, based on the attribute characteristics of each story element in the original story data, determine the music of each story element, and polish the original story data based on the music of each story element; Step 122: Under the dimension of illustration, based on the appearance characteristics of each story element, determine the illustration of each story element, and polish the original story data based on the illustration of each story element; Step 123: Under the virtual image dimension, based on the image of the target user and the voice data of the target user, generate a virtual image of the target user, and polish the original story data based on the virtual image; Step 124: Under the expansion dimension, based on the logical relationship between the story elements, determine the expansion content, and polish the original story data based on the expansion content.

[0041] Considering that young children are usually extremely sensitive and interested in sounds, sound effects can directly affect their auditory senses, attract their attention and stimulate their imagination. Therefore, polishing the original story data from the sound effect dimension can make the story more vivid and interesting, and satisfy children's curiosity and desire to explore novel sounds.

[0042] Among them, the sound effect dimension can be understood as selecting a matching music collection from the pre-stored music library based on the story elements in the original story data. Story elements refer to the characters in the story (including people, animals, objects, etc.), time, place, story climax nodes, story slow nodes, etc. For the scene (location) elements in the story, such as the gloomy and dim forest, you can choose darker and colder music at this time; for specific characters (characters) in the story, such as tigers, you can match the tiger's roar music; for the story plot to a funny plot, you can match the music of happy children's laughter or applause music; for the beginning of the story, which is a slow plot, you can match it with slow music; when the story advances to the climax, you can match it with passionate music.

[0043] The music selected from the pre-stored music database for the sound effect dimension includes but is not limited to pure music, songs, natural sounds (such as the calls of various animals, the collision and falling sounds of objects, etc.). For example, some stories are told live by young children, such as various story competitions, and may be accompanied by off-site sounds, such as cheers, applause, and encouragement. The pre-stored music database can also include off-site sounds, so that when polishing the story, the story can be polished based on the off-site sounds. For example, at the climax or key turning point of the story, the cheers or encouragement of the audience can be added in time to guide the emotional response of young children, so that they can find resonance in the story and participate more in the story telling and listening.

[0044] Specifically, in the sound effect dimension, the soundtrack of each story element can be determined based on the attribute characteristics of each story element in the original story data, and the original story data can be polished based on the soundtrack of each story element (such as inserting the corresponding soundtrack at the timestamp position of the story element). Among them, the data row features can cover multiple aspects such as the character's personality characteristics, emotional state, scene atmosphere, and plot development.

[0045] Taking into account that young children have strong visual cognitive abilities and that illustrations can provide intuitive visual information, the original story data is polished from the illustration dimension. Colorful and vivid illustrations can quickly attract the attention of young children and stimulate their interest in the story content.

[0046] Specifically, in the dimension of illustration, the illustration of each story element is determined based on its appearance characteristics, and the original story data is polished based on the illustration of each story element. The illustration refers to a picture that matches the appearance of each story element. In the dimension of illustrations, illustrations that match each story element are drawn based on the appearance features of each story element, such as the character's appearance, clothing, expressions, movements, and environmental background. The original story data can be polished by combining the illustrations with the original story data (such as inserting corresponding illustrations at the timestamp position of the story element), guiding young children to understand and feel the story through visual information.

[0047] For example, if a cat appears in the story, you can add a picture of a cat that fits the character in the story; if the story takes place in a forest, you can add a picture of a forest; if a red trolley suitcase appears in the story, you can add a picture of a suitcase of the same model.

[0048] Considering that young children are at a critical stage of self-cognition development and are eager to find their own shadows in the story and resonate with the characters, polishing the original story data from the virtual image dimension can integrate the image of young children into the story, so that young children can gain a stronger sense of participation and belonging. The virtual image dimension referred to here refers to the virtual character that matches the story narrative and appears on the screen synchronously to tell the story when presenting the polished story data. As the story timeline evolves, the virtual character can display corresponding illustrations and background music in a timely manner during the storytelling process to enrich the presentation of the story.

[0049] Considering that the original story data of young children are usually disorganized and lack certain detailed information, polishing the original story data from the expansion dimension can provide more details and background information to satisfy young children's curiosity and thirst for knowledge about the storyline.

[0050] In the dimension of expansion, based on the logical relationship between the story elements, such as cause and effect, time sequence, contrast, etc., the missing information in the original story data is determined, and based on the missing information, the expanded content that is closely connected with the original story data is determined. Then, the expanded content is integrated into the original story data to achieve polishing of the original story data.

[0051] It can be seen that the embodiment of the present invention polishes the original story data based on at least one of the sound effect dimension, the illustration dimension, the virtual image dimension, and the expansion dimension, fully considering the cognitive characteristics, interest preferences, and learning needs of young children, which not only enhances the attractiveness and appeal of the story, but also promotes the language development, emotional expression, and imagination and creativity of young children. Therefore, the embodiment of the present invention achieves refined processing in story polishing, providing young children with a better quality and more interesting reading experience.

[0052] Based on any of the above embodiments, the expanded content is determined based on the logical relationship between the story elements, including: Based on the logical relationship between the story elements and the semantic information of the original story data, the missing elements in the original story data are determined; Based on the age group of the target users, determine the expanded content used to describe the missing elements.

[0053] Considering that the original story data of young children are usually disorganized and incomplete, the original story data may lack some key information or plot details. Since the logical relationship between the story elements is used to characterize the interrelationship and dependence of these elements in the development of the story, it is an important part of the story structure, and the semantic information of the original story data is used to characterize the specific meaning and contextual relationship of each element in the story, which is the basis for understanding the story plot. Therefore, based on the logical relationship between the story elements and the semantic information of the original story data, the missing elements in the original story data can be analyzed and determined. Among them, the missing elements can be understood as information or plots that are crucial to the integrity, coherence or understanding of the story, but are not explicitly mentioned or described in the original data.

[0054] In addition, users of different age groups have different abilities to accept and understand stories. Therefore, when determining the expanded content used to describe the missing elements, it is necessary to consider the age level of the target users to ensure that the expanded content is both in line with the target users' cognitive level and can stimulate their interest. For example, for young children, the expanded content should be simple, easy to understand, and imaginative. For older users, the expanded content can be more complex, containing more details and profound meanings.

[0055] Based on any of the above embodiments, generating a virtual image of the target user based on the image of the target user and the voice data of the target user includes: Extract the voice features of the target user from the voice data; Based on the speech features, the expanded story data is subjected to speech synthesis to obtain synthesized speech, wherein the expanded story data is the story data obtained by integrating the expanded content into the original story data; Generate a virtual image of the target user based on the target user's image and synthesized voice.

[0056] Specifically, the voice data can be the voice data of the user telling a story, or the voice data of the user in a historical conversation. The voice data carries the acoustic information of the target user, such as pronunciation characteristics, intonation, and speech speed. The voice features of the target user can be extracted from the voice data, and the voice features are used to characterize the unique voice style and vocalization habits of the target user.

[0057] Based on the extracted speech features, the expanded story data is subjected to speech synthesis to obtain synthesized speech. The expanded data is the story data obtained by integrating the expanded content into the original story data, that is, the expanded data is the story data that has been enriched and improved and contains more plots and details.

[0058] In addition, the image of the target user can be a face image of the target user, and based on the face image, the target user's facial expression information can be captured, including rich expression details such as eyes, smiles, frowns, etc. Since the synthesized speech can simulate the voice characteristics of the target user, the generated speech sounds very similar to the voice of the target user, so based on the image of the target user and the synthesized speech, a highly realistic virtual image can be further generated, which can not only simulate the face of the target user, but also simulate the voice of the target user, increasing the immersion and realism of the storytelling.

[0059] Based on any of the above embodiments, the image and voice data are collected when the target user tells a story; Generate a virtual image of the target user based on the target user's image and synthesized voice, including: Based on the target user’s image, identify the target user’s facial expression when telling a story; Based on the voice data, extract the environmental characteristics of the target user when telling the story; Generate a virtual image of the target user based on facial expressions, synthesized speech and environmental features.

[0060] Specifically, image and voice data are collected when the target user tells a story, so that the image data can represent the facial expressions and body language of the target user when telling the story, and the voice data can represent the voice characteristics, intonation changes and emotional involvement of the target user when telling the story.

[0061] On this basis, based on the target user's image, the target user's facial expression when telling the story can be identified, which reflects his or her emotional state and level of involvement. Based on the voice data, the environmental features of the target user when telling the story can be extracted. The environmental features are used to characterize the physical environment background when the story is told, such as whether it is quiet, whether there are other sounds (such as applause, cheers), etc.

[0062] Since expressions are used to convey the target user's emotional state when telling a story and enhance the appeal of the story, synthetic speech is used to simulate the voice characteristics of the target user when telling a story and increase the realism of the story, and environmental features are used to create the atmosphere of storytelling so that the audience can feel the scene and environment where the story takes place, making it more immersive. Therefore, the virtual image generated based on expressions, synthetic speech and environmental features can fully simulate the state of the target user when telling a story, including his appearance, emotional expression, voice characteristics and the environment he is in.

[0063] Taking young children as an example, if the target users are innocent, the synthesized voice is tender and crisp, and the environment is a warm and comfortable children's room, the generated virtual image can be a lively, cute and childlike image of a young child with a sweet and pleasant voice, and vivid expressions and body movements when telling stories. At the same time, the background environment creates a warm and harmonious atmosphere, making it easier for listeners (especially children of the same age) to be attracted into the story world and enjoy the fun of listening to stories.

[0064] Based on any of the above embodiments, the polished story data includes first polished data and second polished data, the first polished data is obtained by polishing the original story data according to at least one of a sound effect dimension, a picture dimension, and a virtual image dimension, and the second polished data is obtained by polishing the original story data according to an expansion dimension; Display polished story data, including: The first polished data and the second polished data are displayed.

[0065] Specifically, the polished story data includes first polished data and second polished data. The first polished data is obtained by polishing the original story data according to at least one of the sound effect dimension, the picture dimension, and the virtual image dimension. Therefore, the first polished data is based on the plot of the original story data, and enhances the audio-visual effect of the story by adding multimedia elements such as sound effects, pictures, and virtual images.

[0066] The second polishing data is obtained after polishing the original story data according to the expansion dimension. The polishing of this dimension mainly focuses on the detailed supplement and expansion of the storyline, character description, background setting, etc. Therefore, the second polishing data supplements and improves the original story data, making the story fuller and more three-dimensional by adding details and depth. Among them, in addition to polishing the original story data according to the expansion dimension, the second polishing data can also polish the original story data according to at least one of the sound effect dimension, the picture dimension, and the virtual image dimension. For example, the original story data can be first polished according to at least one of the sound effect dimension, the picture dimension, and the virtual image dimension to obtain the initial polished story data, and then the initial polished story data is polished based on the expansion dimension to obtain the second polished data.

[0067] When displaying the polished story data, the first polished story data and the second polished story data can be displayed at the same time, so as to provide the target user with a comparative perspective, so that the target user can clearly see the characteristics and advantages of the two polishing methods. By comparing the first polished story data and the second polished story data, the target user can find the possible deficiencies or defects in the story telling, and then learn how to tell the story completely.

[0068] The story polishing device provided by the present invention is described below. The story polishing device described below and the story polishing method described above can be referenced to each other.

[0069] Based on any of the above embodiments, Figure 3 is a structural schematic diagram of the story polishing device provided by the present invention, such as Figure 3 As shown, the device comprises: A determination unit 310, configured to determine the original story data of a target user; A polishing unit 320, configured to polish the original story data according to a polishing dimension matching the target user, to obtain polished story data corresponding to the original story data; The display unit 330 is used to display the polished story data.

[0070] Based on any of the above embodiments, the polishing dimension includes at least one of a sound effect dimension, a picture dimension, a virtual image dimension, and an expansion dimension; Polish the original story data according to the polishing dimensions that match the target users, including: In the sound effect dimension, based on the attribute characteristics of each story element in the original story data, the music of each story element is determined, and the original story data is polished based on the music of each story element; In the dimension of illustration, the illustration of each story element is determined based on its appearance characteristics, and the original story data is polished based on the illustration of each story element; In the virtual image dimension, a virtual image of the target user is generated based on the image of the target user and the voice data of the target user, and the original story data is polished based on the virtual image; In the expansion dimension, the expanded content is determined based on the logical relationship between the story elements, and the original story data is polished based on the expanded content.

[0071] Based on any of the above embodiments, the expanded content is determined based on the logical relationship between the story elements, including: Based on the logical relationship between the story elements and the semantic information of the original story data, the missing elements in the original story data are determined; Based on the age group of the target users, determine the expanded content used to describe the missing elements.

[0072] Based on any of the above embodiments, generating a virtual image of the target user based on the image of the target user and the voice data of the target user includes: Extract the voice features of the target user from the voice data; Based on the speech features, the expanded story data is subjected to speech synthesis to obtain synthesized speech, wherein the expanded story data is the story data obtained by integrating the expanded content into the original story data; Generate a virtual image of the target user based on the target user's image and synthesized voice.

[0073] Based on any of the above embodiments, the image and voice data are collected when the target user tells a story; Generate a virtual image of the target user based on the target user's image and synthesized voice, including: Based on the target user’s image, identify the target user’s facial expression when telling a story; Based on the voice data, extract the environmental characteristics of the target user when telling the story; Generate a virtual image of the target user based on facial expressions, synthesized speech and environmental features.

[0074] Based on any of the above embodiments, the polished story data includes first polished data and second polished data, the first polished data is obtained by polishing the original story data according to at least one of a sound effect dimension, a picture dimension, and a virtual image dimension, and the second polished data is obtained by polishing the original story data according to an expansion dimension; Display polished story data, including: The first polished data and the second polished data are displayed.

[0075] Figure 4 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the story polishing method, which includes: determining the original story data of the target user; polishing the original story data according to the polishing dimension matching the target user to obtain the polished story data corresponding to the original story data; and displaying the polished story data.

[0076] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0077] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the story polishing method provided by the above methods, which includes: determining the original story data of the target user; polishing the original story data according to the polishing dimensions matching the target user to obtain polished story data corresponding to the original story data; and displaying the polished story data.

[0078] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for story polishing provided by the above methods is implemented, and the method includes: determining the original story data of a target user; polishing the original story data according to a polishing dimension matching the target user to obtain polished story data corresponding to the original story data; and displaying the polished story data.

[0079] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0080] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A story polishing method, characterized in that: include: Determine the original story data of target users; polishing the original story data according to the polishing dimension matching the target user to obtain polished story data corresponding to the original story data; The polished story data is displayed.

2. The story polishing method according to claim 1, characterized in that: The polishing dimension includes at least one of a sound effect dimension, a picture dimension, a virtual image dimension, and an expansion dimension; The polishing of the original story data according to the polishing dimension matching the target user includes: In the sound effect dimension, based on the attribute characteristics of each story element in the original story data, the music of each story element is determined, and the original story data is polished based on the music of each story element; In the dimension of illustration, based on the appearance characteristics of each story element, the illustration of each story element is determined, and the original story data is polished based on the illustration of each story element; In the virtual image dimension, based on the image of the target user and the voice data of the target user, a virtual image of the target user is generated, and the original story data is polished based on the virtual image; In the expansion dimension, the expansion content is determined based on the logical relationship between the story elements, and the original story data is polished based on the expansion content.

3. The story polishing method according to claim 2, characterized in that: The step of determining the expanded content based on the logical relationship between the story elements includes: Determine missing elements in the original story data based on the logical relationship between the story elements and the semantic information of the original story data; Based on the age level of the target users, the expanded content for describing the missing element is determined.

4. The story polishing method according to claim 3, characterized in that: The step of generating a virtual image of the target user based on the image of the target user and the voice data of the target user includes: Extracting the voice features of the target user from the voice data; Based on the speech features, performing speech synthesis on the expanded story data to obtain synthesized speech, wherein the expanded story data is story data obtained by integrating the expanded content into the original story data; A virtual image of the target user is generated based on the image of the target user and the synthesized voice.

5. The story polishing method according to claim 4, characterized in that: The image and the voice data are collected when the target user tells a story; The step of generating a virtual image of the target user based on the image of the target user and the synthesized voice includes: Based on the image of the target user, identifying the expression of the target user when telling a story; Based on the voice data, extracting environmental features of the target user when telling a story; A virtual image of the target user is generated based on the expression, the synthesized voice and the environmental characteristics.

6. The story polishing method according to claim 2, characterized in that: The polished story data includes first polished data and second polished data, wherein the first polished data is obtained by polishing the original story data according to at least one of the sound effect dimension, the illustration dimension, and the avatar dimension, and the second polished data is obtained by polishing the original story data according to the expansion dimension; The presenting of the polished story data includes: The first polishing data and the second polishing data are displayed.

7. A story polishing device, characterized in that: include: A determination unit, used for determining original story data of a target user; A polishing unit, configured to polish the original story data according to a polishing dimension matching the target user, to obtain polished story data corresponding to the original story data; A display unit is used to display the polished story data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the story polishing method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the story polishing method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the story polishing method according to any one of claims 1 to 6 is implemented.

Images