WO2025189355A1 - 推荐方法、装置、计算机可读存储介质和计算机程序产品 - Google Patents

推荐方法、装置、计算机可读存储介质和计算机程序产品

Info

Publication number
WO2025189355A1
WO2025189355A1 PCT/CN2024/081223 CN2024081223W WO2025189355A1 WO 2025189355 A1 WO2025189355 A1 WO 2025189355A1 CN 2024081223 W CN2024081223 W CN 2024081223W WO 2025189355 A1 WO2025189355 A1 WO 2025189355A1
Authority
WO
WIPO (PCT)
Prior art keywords
book
recommended
user
multimedia content
books
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/081223
Other languages
English (en)
French (fr)
Inventor
刘建诚
龚宁
黄荣强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Zitiao Network Technology Co Ltd
Original Assignee
Beijing Zitiao Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Zitiao Network Technology Co Ltd filed Critical Beijing Zitiao Network Technology Co Ltd
Priority to CN202480003554.9A priority Critical patent/CN120981800A/zh
Priority to PCT/CN2024/081223 priority patent/WO2025189355A1/zh
Publication of WO2025189355A1 publication Critical patent/WO2025189355A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43—Querying
    • G06F16/435—Filtering based on additional data, e.g. user or group profiles

Definitions

  • the present disclosure relates to the field of multimedia technology, and in particular to a recommendation method, device, computer-readable storage medium, and computer program product.
  • apps Users can read books through apps. Some apps push other information during reading, such as advertisements and recommendations for other services within the app. If the user is interested in the pushed information, they can learn more about it. After understanding the pushed information, or if the user skips or closes the pushed information because they are not interested, the user can continue reading.
  • a recommendation method comprising: determining an object to be recommended that matches a reference object in a reference book; generating multimedia content for introducing the object to be recommended using a description text of the reference object in the reference book and the object to be recommended; and displaying the multimedia content during a user's reading process.
  • a recommendation device including: a determination module configured to determine an object to be recommended that matches a reference object in a reference book; a generation module configured to generate multimedia content for introducing the object to be recommended using a description text of the reference object in the reference book and the object to be recommended; and a display module configured to display the multimedia content during a user's reading process.
  • a recommendation device including: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the recommendation method of any one embodiment of the present disclosure based on instructions stored in the memory.
  • a computer-readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the recommendation method of any embodiment of the present disclosure is performed.
  • a computer program product is provided.
  • the computer When the computer is run on the computer, the computer implements the recommended method of any embodiment of the present disclosure.
  • a computer program comprising: instructions, which, when executed by a processor, cause the processor to perform the recommended method of any one of the embodiments of the present disclosure.
  • FIG1 shows a schematic flow chart of a recommendation method according to some embodiments of the present disclosure.
  • FIG2 shows a schematic flow chart of a method for generating multimedia content according to some embodiments of the present disclosure.
  • FIG3A shows a schematic flow chart of a method for generating multimedia content according to other embodiments of the present disclosure.
  • FIG3B shows a schematic flow chart of a method for generating multimedia content according to yet other embodiments of the present disclosure.
  • FIG3C shows a schematic flow chart of a method for generating multimedia content according to still other embodiments of the present disclosure.
  • FIG4A exemplarily shows a book page in some embodiments of the present disclosure.
  • FIG4B shows a schematic diagram of a multimedia content display interface according to some embodiments of the present disclosure.
  • FIG4C shows a schematic diagram of an intelligent dialogue interface according to some embodiments of the present disclosure.
  • FIG5 shows a schematic flow chart of an information determination method according to some embodiments of the present disclosure.
  • FIG6 shows a schematic structural diagram of a recommendation device according to some embodiments of the present disclosure.
  • FIG7 shows a schematic structural diagram of an electronic device according to some embodiments of the present disclosure.
  • FIG8 shows a schematic structural diagram of a computer system according to some embodiments of the present disclosure.
  • the term “include” and its variations are intended to be open-ended terms that include at least the following elements/features but do not exclude other elements/features, i.e., “including but not limited to.”
  • the term “comprise” and its variations are intended to be open-ended terms that include at least the following elements/features but do not exclude other elements/features, i.e., “including but not limited to.” Therefore, “include” and “include” are synonymous.
  • the term “based on” means “based, at least in part, on.”
  • references throughout this specification to "one embodiment,” “some embodiments,” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention.
  • the term “one embodiment” means “at least one embodiment”
  • the term “another embodiment” means “at least one additional embodiment”
  • the term “some embodiments” means “at least some embodiments.”
  • the appearances of the phrases “in one embodiment,” “in some embodiments,” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment, but may.
  • the present disclosure provides a recommendation method that utilizes the content in a book to generate multimedia content for introducing the recommended object, and displays the multimedia content during the user's reading process to reduce the disturbance to the user when information is pushed during the user's reading process.
  • An embodiment of the recommendation method disclosed herein is described below with reference to FIG1 . This embodiment can be executed by an electronic device, for example, an application (Application) or application program in the electronic device.
  • the electronic device can be a tablet computer, a mobile phone (such as a foldable screen mobile phone, a large screen mobile phone, etc.), a wearable device, an in-vehicle device, an augmented reality (AR)/virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a smart TV, a smart screen, a high-definition TV, a 4K TV, a smart speaker, a smart projector, or other Internet of Things (IoT) devices.
  • the present disclosure does not impose any restrictions on the specific type of electronic device.
  • the present disclosure does not limit the type of operating system of the electronic device. For example, Android system, Linux system, Windows system, iOS system, etc.
  • Figure 1 shows a schematic flow chart of a recommendation method according to some embodiments of the present disclosure. As shown in Figure 1 , the recommendation method of this embodiment includes steps S102 to S106.
  • step S102 objects to be recommended that match reference objects in reference books are determined.
  • Reference books refer to books provided in the application and can be browsed on electronic devices, such as e-books, audio books, etc. They can be books associated with the user, such as those owned by the user (for example, added to the user's bookshelf), read by the user (for example, currently being read or read in the past), and books that the user is interested in (for example, listed in the user's book list, collected by the user, discussed by the user in a topic post, recommended by the user), or books that are not associated with the user, such as popular books in the application.
  • Popular books can be determined based on click-through rate, related discussion, and user evaluation. Reference books are used to provide a basis for the generation of multimedia content. The degree of discussion can be determined based on the frequency of appearance or the amount of information in the comments or topic posts of the book.
  • Reference objects are objects described in reference books, such as characters, places, objects, etc. Reference objects can be objects that appear in the paragraphs adjacent to the current reading progress, or key objects in the book (such as the protagonist, iconic places, iconic objects), or the most discussed objects.
  • the object to be recommended refers to the object to be recommended to the current user, which can be a product, a function in an application, or a service, etc.
  • the reference object may have a certain correlation with the object to be recommended, and this correlation can be further mined through the description of the reference object in reference books.
  • the object to be recommended that matches the reference object is an object that is associated with the reference object.
  • the description text of the reference object can be semantically analyzed to extract named entities, subject terms, keywords, etc., and the extracted information can be matched with multiple alternative objects to determine the object to be recommended from the multiple alternative objects.
  • step S104 multimedia content for introducing the object to be recommended is generated using the description text of the reference object in the reference book and the object to be recommended.
  • the descriptive text of the reference object can be a paragraph in the book where the reference object appears, such as a direct description of the appearance and characteristics of the reference object, or a plot text that includes the reference object. Or, when the reference object is a character, the descriptive text can also be the text of the character's speech content.
  • the generated multimedia content includes, for example, images, videos, and the like. These can be multimedia files themselves, such as images and videos, or other types of files or objects, including images, videos, and games.
  • the multimedia content includes at least one of images, videos, intelligent conversation pages, graphic links, and live broadcasts.
  • the process of generating multimedia content using descriptive text and recommended objects can be implemented using a generative model, thereby improving the efficiency of multimedia content generation.
  • the generative model is used to output target content based on the input information.
  • the input information includes the processing basis of the generative model during the generation process, such as which information is referenced to perform the generation process, the requirements of the output multimedia content, etc.
  • An example of the input content to the generative model includes a description text of the reference object, information of the object to be recommended, and a generation instruction, the generation instruction being, for example, "based on the content in the description text of the reference object and the object to be recommended, generate a multimedia content that uses the style/plot/object of the content in the description text to introduce the object to be recommended.”
  • the generation instruction can be expressed in the form of natural language or in other forms, which will not be repeated here.
  • multimedia content can also be generated in stages, for example, using one or more generative models to sequentially generate various parts of the multimedia content, and then synthesizing these parts to obtain the multimedia content.
  • the generative model used in the present disclosure includes, for example, a model generated based on text, and the output of the generative model may include text, multimedia content, or a combination of the two.
  • the input or output of the generative model may also include data of other modalities, such as audio, image, video, or a combination of multiple types of data.
  • the generative model is, for example, based on a large language model (LLM) or a basic model. (Foundation Model) implementation.
  • step S106 the multimedia content is displayed during the user's reading process.
  • the user's reading process may refer to the process of the user reading a book (hereinafter referred to as the "current book") in an application, that is, the multimedia content is displayed during the display of the book.
  • the multimedia content may be displayed on a page of the book, or the multimedia content may be displayed as a supplementary page between two pages of the book, before the first page, or after the last page of the book, or displayed on top of the book page in a floating window or other manner.
  • a link to the recommended object may also be displayed. After triggering the link, the user may enter the details interface, purchase interface, customer service interface, etc. of the recommended object.
  • multimedia content is generated based on the content in the book
  • the multimedia content contains elements from the book. Therefore, when introducing the recommended object to the user, it can improve the immersiveness of the pushed information and the continuity of the user's reading, thereby improving the user's reading experience and the efficiency of information transmission.
  • Some embodiments of the present disclosure can utilize a generative model to generate images and recommendation information, and then further generate multimedia content based on the two.
  • An embodiment of a method for generating multimedia content of the present disclosure will be described below with reference to FIG2 .
  • Figure 2 shows a schematic flow chart of a method for generating multimedia content according to some embodiments of the present disclosure. As shown in Figure 2 , the method of this embodiment includes steps S202 to S206.
  • step S202 the first generation model is used to process the description text of the reference object in the reference book to generate an image resource corresponding to the reference object.
  • the first generative model is a generative model.
  • the first generative model can be, for example, a text-image model (a model that generates images based on text), or other types of models whose input includes text and whose output includes images.
  • the input of the first generative model includes a descriptive text of a reference object and a first generation instruction.
  • the first generation instruction is, for example, "Based on the descriptive text of the reference object, generate an image resource including the reference object, and the image resource needs to meet the requirements of"
  • the first generation instruction can be in natural language or other forms, which will not be described in detail here.
  • the image resource corresponding to the reference object can be an image resource that includes the reference object, or an image resource that indirectly reflects the reference object, such as by using an object in the image resource to describe the reference object.
  • the image resource can be a static image, a dynamic image, or one or more video clips.
  • the first generation model is used to process the descriptive text of the reference object in the reference book and the picture corresponding to the reference object to generate an image resource corresponding to the reference object, wherein the picture corresponding to the reference object is a picture in the reference book, or a picture in a book with illustrations associated with the reference book.
  • Books with illustrations are, for example, comics, picture books, and art settings of film and television works related to the reference book.
  • the input data can be expanded to make the generated image resources more effective.
  • searching for pictures corresponding to the reference image for example, the legend of the picture in the book, or the name of the reference object in the context of the picture, etc. can be searched to more accurately obtain the picture corresponding to the reference image.
  • step S204 the second generation model is used to process the description text of the reference object and the object to be recommended to generate recommendation information of the object to be recommended.
  • the second generation model is a generative model.
  • the second generation model can be, for example, a text-generating model (a model that generates text based on text), or other types of models whose input includes text and whose output includes text.
  • the second generation model can be the same as or different from the first generation model.
  • steps S202 and S204 can be performed by the same agent (e.g., a client) of the model, or by different agents.
  • the input to the second generation model includes a description of a reference object, the object to be recommended, and a second generation instruction.
  • the second generation instruction may be, "Based on the description of the reference object and the object to be recommended, generate recommendation information for the object to be recommended, where the recommendation information must be consistent with the characteristics of the reference object.”
  • the second generation instruction may be in natural language or other forms, which will not be further elaborated here.
  • Recommendation information can be text-based, such as the text itself or a text-generated voice.
  • the text can include one or more paragraphs.
  • recommendation information can be understood as a recommendation or advertising slogan for the recommended object.
  • the generation of recommendation information refers to both the descriptive text of the reference object and the recommended object, so that the recommendation information can take into account the characteristics of both, combining the relevant context in the reference book to recommend the recommended object more naturally.
  • step S206 multimedia content for introducing the object to be recommended is generated based on the image resources and the recommendation information.
  • the two can be synthesized to generate multimedia content.
  • the recommendation information can be displayed in the multimedia content in the form of text, or the image resource and the recommendation information can be displayed side by side in the multimedia content.
  • Steps S202 and S204 may be executed sequentially or in parallel, and their execution may be associated or independent of each other.
  • the above embodiment generates image resources of the reference object and recommendation information of the object to be recommended, and generates multimedia content based on the two, so that the generated multimedia content includes visualization information of the content of the reference book and recommendation information of the object to be recommended, so that the multimedia content can take into account both the immersive feeling of the reference book and the transmission of information about the recommended object.
  • the following describes the method for generating multimedia content by taking reference objects including reference characters, reference objects, and reference locations as examples.
  • FIG3A shows a flow chart of a method for generating multimedia content according to some other embodiments of the present disclosure.
  • the reference object includes a reference character.
  • the generation method of this embodiment includes steps S202a to S206a.
  • step S202a the first generation model is used to process the description text of the reference character in the reference book to generate a virtual image of the reference character.
  • Reference characters can be people, animals, or any other type of character.
  • the descriptive text for a reference character can include a direct or indirect description of the reference character's basic familiarity, occupation, appearance, clothing, image, actions, personality, language, and other aspects.
  • the descriptive text may also include a brief introduction to the character provided by the book.
  • Reference characters can be main characters in the reference book, characters that are popular among readers of the reference book, characters that the user is interested in, or characters mentioned in a passage the user has recently read.
  • the avatar of the reference character can be a full-length portrait, a half-length portrait, a head portrait, etc. of the reference character, or in multiple forms, the character's clothing, expression, etc. in the avatar can match the relevant description in the book.
  • step S204a the second generative model processes the description text of the reference character in the reference book and the recommended object to generate a recommendation for the virtual character. This allows recommendations to be made using the virtual character's characteristics. For example, the recommendation can be generated by mimicking the virtual character's speaking style, achieving an effect similar to advertising through the virtual character.
  • step S206a multimedia content for introducing the object to be recommended is generated based on the virtual image and the recommendation words.
  • the voice of the virtual character can also be automatically generated.
  • the voice of the reference character is generated based on at least one of the description text of the reference character in the reference book and the setting information of the reference character; based on the virtual character, the recommendation and the voice, multimedia content for introducing the recommended object is generated.
  • the voice content can be the recommendation, or the text in the reference book, or the multimedia content based on the reference book.
  • the text-generated sentences can also be voice responses generated in response to user interactions. This allows the avatar to have a voice that matches the description in the reference book.
  • the generated multimedia content can shape the reference character through multiple aspects, including image, sound, and text, improving the recommendation effect of the multimedia content.
  • the above embodiment uses characters in books for recommendation, which can achieve the effect of using the virtual images of the characters for recommendation, making the recommended objects more easily accepted by readers and improving the efficiency of information push.
  • FIG3B shows a flow chart of a method for generating multimedia content according to yet another embodiment of the present disclosure.
  • the reference object includes a reference item.
  • the generation method of this embodiment includes steps S202b to S206b.
  • step S202b the first generation model is used to process the description text of the reference item in the reference book to generate an image resource of the reference item, for example, an image resource of the usage scene of the reference item in the reference book.
  • the descriptive text of the reference item includes, for example, a direct or indirect description of the item's name, appearance, and purpose.
  • the reference item can be an important item in the reference book, a popular item among readers of the reference book, an item of interest to the user, or an item mentioned in a passage the user recently read.
  • a reference item can be of the same category or have similar attributes to the object to be recommended. For example, if a protagonist in a reference book wears a red coat, the object to be recommended can also be a red coat.
  • the generated image resource can include the usage scenario of the reference item in the reference book. For example, if the reference item is a red coat, and the reference book describes a protagonist running in the sun wearing the red coat, the image resource can include this scene. If the reference item is a tent, and the reference book describes a character camping on a mountaintop, the image resource can include, for example, a mountaintop at night with a tent on top.
  • the second generation model processes the description text of the reference item in the reference book and the object to be recommended to generate recommendation information for the object to be recommended.
  • the recommendation information may be, for example, an introduction to the object to be recommended. This recommendation information can thus integrate both the description of the reference item in the reference book and the description of the object to be recommended, making the recommendation information an extension of the description of the reference item in the reference book.
  • the second generation model can be instructed to generate recommendation information using the commonalities or similarities between the reference item and the object to be recommended, so that the recommendation information naturally transitions from the description of the reference item in the reference book to the introduction to the recommended object, thereby improving the readability of the recommendation information.
  • step S206b multimedia content for introducing the object to be recommended is generated based on the image resources of the usage scenario and the recommendation information.
  • the above embodiment makes recommendations based on the items in the book and the items to be recommended. Recommendations are made based on the correlation between objects, making the recommended objects more easily accepted by readers and improving the efficiency of information push.
  • FIG3C shows a flow chart of a method for generating multimedia content according to yet another embodiment of the present disclosure.
  • the reference object includes a reference item.
  • the generation method of this embodiment includes steps S202c to S206c.
  • step S202c the first generation model is used to process the description text of the reference location in the reference book to generate an image resource of the reference location.
  • the reference place can be a real place or a fictional place in a book.
  • the descriptive text of the reference place includes, for example, direct or indirect descriptions of the location, climate characteristics, local customs, and key events.
  • the reference place can be an important place in a reference book, a place that is popular among readers of the reference book, a place that the user is interested in, or a place mentioned in a paragraph that the user has recently read.
  • the reference place is, for example, a place that is associated with the object to be recommended. For example, if the object to be recommended is tropical fruit, the reference place may be a place in the tropics.
  • the object to be recommended may be a travel product or service, such as a flight booking service, a hotel booking service, a travel application, and the like.
  • the second generation model is used to process the description text of the reference location in the reference book and the object to be recommended to generate recommendation information for the object to be recommended.
  • the recommendation information may include, for example, an introduction to the object to be recommended.
  • the recommendation information for the object to be recommended can simultaneously integrate the description of the reference location in the reference book with the description of the object to be recommended, making the recommendation information an extension of the description of the reference location in the reference book.
  • the second generation model can be instructed to leverage the content of reference books to identify characteristics of the reference location. If the reference location is a real-world location, additional information about the location can be extracted from other sources. This allows the recommendation information to reflect the relevance of the reference location to the recommended item, resulting in better recommendations.
  • step S206c multimedia content for introducing the object to be recommended is generated based on the image resources and recommendation information of the reference location.
  • the above embodiment makes recommendations by using places in books. It can recommend objects to be recommended based on the association between the characteristics of the places in the book and the objects to be recommended, making the recommended objects more easily accepted by readers and improving the efficiency of information push.
  • FIG4A exemplarily shows a book page in some embodiments of the present disclosure, where the book is AAAA being read by the user, and the current reading is chapter BBBB.
  • a page of the book is displayed, including text 411 "It is a sunny day. In place c, a young man D is climbing a mountain, wearing a jacket with a badge of the XX team pinned on the jacket."
  • interface 41 may also include recommendation prompts 412, such as "You are about to enter the recommendation page" or "You are about to enter the advertisement page", etc.
  • the generated multimedia content can be triggered for display.
  • multimedia content is displayed in response to the user reaching a designated point in the current book.
  • the designated point can be the end of a chapter or the end of a key plot point. This minimizes interruptions to the user's reading flow.
  • the multimedia content can be pre-generated and displayed after the designated point, or it can be generated in real time as the user approaches the designated point.
  • 4B and 4C respectively show two different interfaces for displaying multimedia content, which are described below.
  • Figure 4B shows a schematic diagram of a display interface for multimedia content according to some embodiments of the present disclosure.
  • an image is displayed in the interface 42, and the image includes a full-length image 421 of the character D in the book AAAA (which is also used as a reference book in this embodiment) that the user is reading.
  • the full-length image 421 is generated, for example, based on the descriptive text of the character D in Figure 4A.
  • the image may also include a recommendation 422 for the character D, "Hey! I didn't expect to meet you here. Team XX is in urgent need of new members. Do you want to join Team XX? You can buy the same equipment to join us. I look forward to fighting together!
  • the recommendation can be generated based on the jacket and team logo to be recommended and the descriptive text of the character D in the book AAAA.
  • interface 42 may also include a link 423 for the recommended jacket and a link 424 for the team logo.
  • link 423 for the recommended jacket
  • link 424 for the team logo.
  • the name of the object in the link can be its original name or a new name generated by processing the description text in the reference book and the original name. For example, if the recommended jacket is originally a jacket of a certain brand, a new name "XX Team Jacket” can be generated here based on the description in the reference book.
  • the multimedia content may be an intelligent dialogue page.
  • an intelligent dialogue page of the virtual image corresponding to the reference character is generated, and the recommendation is a dialogue sent by the virtual image.
  • FIG4C shows a schematic diagram of an intelligent dialogue interface according to some embodiments of the present disclosure.
  • the dialogue interface 43 is a dialogue interface between the user and the virtual image of the reference character D. Based on the description of the character D in the reference book, an avatar 431 of the character D may be generated.
  • the character D may send information to describe the recommended object, or respond to the recommendation. User questions about the recommended object.
  • Interface 43 can be displayed after the reading page of the book. For example, after the page switching operation is triggered in interface 41, interface 43 can be displayed. At this time, character D can send a recommendation in interface 43. Interface 43 can also be displayed after the display interface of other multimedia content. For example, in response to triggering the link of the object to be recommended in interface 42, interface 43 is displayed. At this time, the recommendation can be displayed again in interface 43, or information related to the object to be recommended can be directly displayed, such as the inquiry prompt associated with the object to be recommended shown in the dialogue control 432.
  • Multimedia content can also be live broadcasts.
  • a live broadcast with the virtual image as the host is generated, and the recommendation is the description of the recommended object in the live broadcast.
  • a real host can be replaced with a virtual image in real time, or live broadcast content with the virtual image as the host can be generated in real time.
  • the generated recommendation can be displayed in the live broadcast interface, or the host can also verbally recite the recommendation.
  • the live broadcast can be carried after the reading page of a book, or it can be carried after the display interface of other multimedia content. I will not go into details here.
  • the above embodiments describe the generation and display of multimedia content, wherein the reference books and reference objects utilized in the generation process can be determined based on the user's authorized reading history.
  • the following describes an embodiment of the disclosed method for determining information such as reference books, reference objects, and objects to be recommended, with reference to FIG5 .
  • Figure 5 shows a flow chart of an information determination method according to some embodiments of the present disclosure. As shown in Figure 5 , the information determination method of this embodiment includes steps S502 to S106.
  • step S502 reference books and reference objects in the reference books are determined based on the user's reading records authorized by the user.
  • the user's reading record includes the books the user has read. If needed, it can also include the reading time of each book, reading progress (such as which chapter, paragraph, page, etc. read), the time when the reading started, the time when the reading was last done, etc.
  • a user's reading history includes at least one of the book the user is currently reading and the books they have read, as well as their reading progress.
  • the reference book can be the book the user is currently reading, so that the multimedia content generated can better match the current reading content, thereby improving the user's reading experience and improving recommendation efficiency.
  • the reference book can be a book the user has read before, so that the multimedia content generated is familiar to the user. Although it may not completely match the content of the current book, it is also generated based on the book, has a reading atmosphere, and can also reduce interference with the user's reading rhythm to a certain extent, thereby improving recommendation efficiency.
  • reference objects can be extracted from at least one of the content corresponding to the user's reading progress in the reference book, the abstract of the reference book, the key plot of the reference book, the main character of the reference book, and the posts published by the user.
  • the content corresponding to the user's reading progress can be the chapter where the user's current reading progress is located, or the specified number of paragraphs, words, pages, etc. before the current reading progress.
  • the key plot of the reference book can be pre-marked in the book, or it can be determined based on the reader's marking information and reading situation, for example, based on the number of times it is marked, the number of reading users, etc.
  • the main character of the reference book can not only provide information about the character, but also determine key events, key items, key locations, etc. associated with the main character as reference information.
  • the posts published by the user may involve discussions on the characters, plots, etc. in the book, from which reference information of interest to the user can be mined.
  • reference books are determined based on one or more books mentioned in user posts and books the user has read. This means that reference books can be selected from books the user has read, or books of interest to the user can be determined from books mentioned in user posts. Books of interest to the user may or may not be books the user has read. This allows the elements involved in multimedia content to be familiar to the user or potentially interesting to the user, thereby improving recommendation effectiveness.
  • a candidate book is determined based on at least one of the book's frequency of appearance in the post and the amount of information related to the book in the post.
  • the frequency of appearance of a book in a post published by a user can be determined based on the ratio of the number of posts in which the book appears to the total number of posts published by the user.
  • semantic analysis can be performed to determine the content in the post related to the book, and then the length of this content can be calculated as the amount of information.
  • those skilled in the art can adjust the method for calculating the frequency of appearance and the amount of information, which will not be repeated here.
  • the above embodiment can first identify books with certain reference value based on the breadth of coverage or depth of discussion of the books in the posts. Then, reference books are determined based on the books that have been read and the candidate books. Thus, if a book that appears in a post is not a book that the user has read, but the user frequently mentions it or discusses it in depth, it is likely that the user has read the book in other applications or has a strong interest in it. In this case, the book can be used as a reference book, so that the generated multimedia content is content that the user is relatively familiar with, improving the effectiveness of the recommendation.
  • reference books can be determined from popular books.
  • reference books are determined from popular books. The total reading volume is based on the first threshold. It is determined based on the user's reading records authorized by the user; the reference object is extracted from at least one of the abstracts of the reference books, the key plots of the reference books, the main characters of the reference books, and the posts published by the user.
  • the total amount of reading by the user can be determined by one or more of any indicators such as the number of words, the number of books, the reading time, etc.
  • Popular books are determined based on the number of discussions, clicks, or the number of reading users of each book in the application or platform.
  • the reference objects can be extracted from those that can reflect the main content of the reference books. Therefore, when the total amount of reading by the user is small, in addition to generating multimedia content directly based on the books the user is reading, multimedia content can also be generated based on popular books, which improves the diversity of multimedia content generation.
  • Steps S102 to S106 refer to the above embodiment and are not described in detail here.
  • reference books can be determined based on the user's reading situation, and then reference objects can be determined from the reference books. Therefore, the generated multimedia content can be made closer to the user and the recommendation efficiency can be improved.
  • a prompt message is sent to the user to clearly inform the user that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operation of the disclosed technical solution based on the prompt message.
  • the prompt information in response to a user's active request, may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form.
  • the pop-up window may also contain a selection control for the user to select "agree” or “disagree” to provide personal information to the electronic device.
  • Figure 6 illustrates a schematic diagram of a recommendation device according to some embodiments of the present disclosure.
  • the recommendation device 60 of this embodiment includes: a determination module 602 configured to determine an object to be recommended that matches a reference object in a reference book; a generation module 604 configured to generate multimedia content introducing the object to be recommended using the descriptive text of the reference object in the reference book and the object to be recommended; and a display module 606 configured to display the multimedia content while the user is reading.
  • the generation module 604 is further configured to: generate the reference book using the first generation model
  • the description text of the reference object is processed to generate image resources corresponding to the reference object; the description text of the reference object and the object to be recommended are processed using the second generation model to generate recommendation information of the object to be recommended; based on the image resources and the recommendation information, multimedia content for introducing the object to be recommended is generated.
  • the generation module 604 is further configured to: use the first generation model to process the descriptive text of the reference object in the reference book and the picture corresponding to the reference object to generate an image resource corresponding to the reference object, wherein the picture corresponding to the reference object is a picture in the reference book, or a picture in a book with illustrations associated with the reference book.
  • the reference object includes a reference character
  • the generation module 604 is further configured to: utilize a first generation model to process the description text of the reference character in the reference book to generate a virtual image of the reference character; utilize a second generation model to process the description text of the reference character in the reference book and the object to be recommended to generate a recommendation statement by the virtual character for the object to be recommended; and generate multimedia content for introducing the object to be recommended based on the virtual image and the recommendation statement.
  • the generation module 604 is further configured to: generate the voice of the reference character based on at least one of the description text of the reference character in the reference book and the setting information of the reference character; and generate multimedia content for introducing the object to be recommended based on the virtual image, recommendation words and voice.
  • the generation module 604 is further configured to: generate an intelligent dialogue page for the virtual image corresponding to the reference character, and the recommendation is the dialogue sent by the virtual image; or, generate a live broadcast with the virtual image as the anchor, and the recommendation is the description information of the recommended object in the live broadcast.
  • the reference object includes a reference item
  • the generation module 604 is further configured to: utilize a first generation model to process the description text of the reference item in the reference book to generate image resources of the usage scenario of the reference item in the reference book; utilize a second generation model to process the description text of the reference item and the object to be recommended in the reference book to generate recommendation information of the object to be recommended; and generate multimedia content for introducing the object to be recommended based on the image resources of the usage scenario and the recommendation information.
  • the reference object includes a reference location
  • the generation module 604 is further configured to: utilize a first generation model to process the descriptive text of the reference location in the reference book to generate an image resource of the reference location; utilize a second generation model to process the descriptive text of the reference location and the object to be recommended in the reference book to generate recommendation information of the object to be recommended; and generate multimedia content for introducing the object to be recommended based on the image resource and recommendation information of the reference location.
  • the display module 606 is further configured to: in response to the user reading a Specify a node to display multimedia content.
  • the specified node is the end of a chapter or the end of a key plot.
  • the determination module 602 is further configured to: determine reference books and reference objects in the reference books based on the user's reading records authorized by the user; and determine objects to be recommended that match the reference objects.
  • the user's reading record includes the book the user is reading, at least one of the books the user has read, and the reading progress
  • the determination module 602 is further configured to: determine the book the user is reading as a reference book, or, based on the user's reading progress in one or more books that have been read, determine the reference book from the books that have been read; extract the reference object from at least one of the content in the reference book corresponding to the user's reading progress, the summary of the reference book, the key plot of the reference book, the main character of the reference book, and the post published by the user.
  • the determination module 602 is further configured to determine reference books based on one or more books related to posts published by the user and books that the user has read.
  • the determination module 602 is further configured to: for each of the one or more books involved in the post published by the user, determine a candidate book based on at least one of the frequency of appearance of the book in the post and the amount of information involved in the book in the post; and determine a reference book based on the read books and the candidate books.
  • the determination module 602 is further configured to: determine reference books from popular books when the user's total reading volume is less than a first threshold, and the total reading volume is determined based on the user's reading records authorized by the user; extract reference objects from at least one of the abstract of the reference book, the key plot of the reference book, the main character of the reference book, and the post published by the user.
  • the multimedia content includes at least one of images, videos, smart dialogue pages, graphic links, and live broadcasts.
  • the above-mentioned units are merely logical modules divided according to the specific functions they implement, and are not intended to limit specific implementation methods. For example, they can be implemented in software, hardware, or a combination of software and hardware. In actual implementation, the above-mentioned units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, the above-mentioned units are shown with dotted lines in the accompanying drawings to indicate that these units may not actually exist, and the operations/functions they implement can be implemented by the processing circuit itself.
  • the device may also include a memory, which can store various information generated by the device and the various units contained in the device during operation, programs and data used for operation, data to be sent by the communication unit, etc.
  • the memory can be a volatile memory and/or a non-volatile memory.
  • the memory can include but is not limited to a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a read-only memory (ROM), and a flash memory.
  • the memory can also be located outside the device.
  • the device may also include a communication unit that can be used to communicate with other devices.
  • the communication unit can be implemented in an appropriate manner known in the art, for example, including communication components such as an antenna array and/or a radio frequency link, various types of interfaces, communication units, etc., which will not be described in detail here.
  • the device may also include other components not shown, such as a radio frequency link, a baseband processing unit, a network interface, a processor, a controller, etc., which will not be described in detail here.
  • FIG. 7 shows a schematic structural diagram of an electronic device according to some embodiments of the present disclosure.
  • the electronic device 7 can be various types of devices, for example, including but not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device 7 may include a display panel for displaying data and/or execution results utilized in the scheme of the present disclosure.
  • the display panel can be of various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel.
  • the display panel can be not only a flat panel, but also a curved panel or even a spherical panel.
  • the electronic device 7 of this embodiment includes a memory 71 and a processor 72 coupled to the memory 71. It should be noted that the components of the electronic device 7 shown in FIG7 are merely exemplary and non-limiting. The electronic device 7 may also include other components as required by actual applications. The processor 72 may control the other components in the electronic device 7 to perform desired functions.
  • the memory 71 is configured to store one or more computer-readable instructions.
  • the processor 72 is configured to execute the computer-readable instructions
  • the computer-readable instructions when executed by the processor 72, implement a method according to any of the above-described embodiments.
  • the specific implementation and related explanations of each step of the method can be found in the above-described embodiments, and any repetitions are omitted here.
  • the processor 72 and the memory 71 may communicate with each other directly or indirectly.
  • the processor 72 and the memory 71 may communicate with each other via a network.
  • the network may include a wireless network, a wired network, and/or any combination of wireless networks and wired networks.
  • the processor 72 and the memory 71 may also communicate with each other via a system bus, which is not limited in this disclosure.
  • the processor 72 may be embodied as various appropriate processors, processing devices, etc., such as a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc.; it may 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.
  • the central processing unit (CPU) may be X86 or ARM architecture, etc.
  • the memory 71 may include any combination of various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • the memory 71 may include, for example, system memory, which stores, for example, an operating system, application programs, a boot loader, a database, and other programs. Various applications and various data may also be stored in the storage medium.
  • the programs constituting the software can be installed from a storage medium or a network to a computer system having a dedicated hardware structure, such as the computer system 80 shown in Figure 8.
  • the computer system can perform various functions, including the functions described above.
  • Figure 8 shows a schematic structural diagram of a computer system according to some embodiments of the present disclosure.
  • a central processing unit (CPU) 801 performs various processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage portion 808 to a random access memory (RAM) 803.
  • ROM 802 read-only memory
  • RAM 803 data required when the CPU 801 performs various processes, etc., is also stored as needed.
  • the central processing unit is merely exemplary, and it may also be other types of processors, such as the various processors described above.
  • ROM 802, RAM 803, and storage portion 808 may be various forms of computer-readable storage media, as described below. It should be noted that although ROM 802, RAM 803, and storage device 808 are shown separately in FIG8 , one or more of them may be combined or located in the same or different memory or storage modules.
  • the CPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804.
  • An input/output interface 805 is also connected to the bus 804.
  • the following components are connected to the input/output interface 805: an input portion 806, such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output portion 807, including a display, such as a cathode ray tube (CRT), liquid crystal display (LCD), speaker, vibrator, etc.; a storage portion 808, including a hard disk, magnetic tape, etc.; and a communication portion 809, including a network interface card, such as a LAN card, modem, etc.
  • the communication portion 809 allows communication processing to be performed via a network, such as the Internet.
  • FIG8 shows that the various devices or modules in the computer system 80 communicate via the bus 804, they may also communicate via a network or other means, where the network may include a wireless network, a wired network, and/or any combination of wireless and wired networks.
  • a drive 810 is also connected to the input/output interface 805 as needed.
  • a removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 810 as needed so that a computer program read therefrom is installed in the storage section 808 as needed.
  • the removable medium 811 installs the programs constituting the software.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart.
  • the computer program can be downloaded and installed from the network through the communication device 809, or installed from the storage device 808, or installed from the ROM 802.
  • the computer program is executed by the CPU 801, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.
  • a computer-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof.
  • a computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.
  • Computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • the program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.
  • the computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
  • a computer program comprising: instructions, which, when executed by a processor, cause the processor to perform any of the methods of the above embodiments.
  • the instructions may be embodied as computer program codes.
  • the programs for executing the present invention may be written in one or more programming languages or a combination thereof.
  • the disclosed computer program code for operation the programming language includes but is not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and also includes conventional procedural programming languages, such as "C" language or similar programming languages.
  • the program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).
  • LAN local area network
  • WAN wide area network
  • Internet Internet service provider
  • each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function.
  • the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.
  • each box in the block diagram and/or flowchart, and the combination of the boxes in the block diagram and/or flowchart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
  • the modules, components, or units described in the embodiments of the present disclosure may be implemented in software or hardware.
  • the names of the modules, components, or units do not necessarily limit the modules, components, or units themselves.
  • exemplary hardware logic components include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOCs systems on chip
  • CPLDs complex programmable logic devices

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Transfer Between Computers (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本公开涉及一种推荐方法、装置、计算机可读存储介质和计算机程序产品，涉及多媒体技术领域。推荐方法包括：确定与参考书籍中的参考对象所匹配的待推荐对象；利用参考书籍中参考对象的描述文本、以及待推荐对象，生成用于介绍待推荐对象的多媒体内容；在用户的阅读过程中，显示多媒体内容。

Description

推荐方法、装置、计算机可读存储介质和计算机程序产品 技术领域
本公开涉及多媒体技术领域，特别涉及一种推荐方法、装置、计算机可读存储介质和计算机程序产品。
背景技术
用户可以通过应用来阅读书籍。部分应用在用户的阅读书籍过程中会推送其他信息，例如广告、应用中的其他服务推荐等等。用户如果对推送的信息感兴趣，可以进一步地了解。在了解推送的信息后、或者是用户对推送的信息不感兴趣而跳过或关闭该内容后，用户可以继续阅读书籍。
发明内容
提供该发明内容部分以便以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。该发明内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
根据本公开的一些实施例，提供了一种推荐方法，包括：确定与参考书籍中的参考对象所匹配的待推荐对象；利用参考书籍中参考对象的描述文本、以及待推荐对象，生成用于介绍待推荐对象的多媒体内容；在用户的阅读过程中，显示多媒体内容。
根据本公开的另一些实施例，提供了一种推荐装置，包括：确定模块，被配置为确定与参考书籍中的参考对象所匹配的待推荐对象；生成模块，被配置为利用参考书籍中参考对象的描述文本、以及待推荐对象，生成用于介绍待推荐对象的多媒体内容；显示模块，被配置为在用户的阅读过程中，显示多媒体内容。
根据本公开的一些实施例，提供一种推荐装置，包括：存储器；以及耦接至存储器的处理器，处理器被配置为基于存储在存储器中的指令，执行本公开任意一个实施例的推荐方法。
根据本公开的一些实施例，提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时执行本公开任意一个实施例的推荐方法。
根据本公开的一些实施例，提供一种计算机程序产品，当计算机程序产品在计算机 上运行时，使得计算机实现本公开任意一个实施例的推荐方法。
根据本公开的一些实施例，提供一种计算机程序，包括：指令，所述指令当由处理器执行时使所述处理器执行本公开任意一个实施例的推荐方法。
通过以下参照附图对本公开的示例性实施例的详细描述，本公开的其它特征、方面及其优点将会变得清楚。
附图说明
下面参照附图说明本公开的优选实施例。此处所说明的附图用来提供对本公开的进一步理解，各附图连同下面的具体描述一起包含在本说明书中并形成说明书的一部分，用于解释本公开。应当理解的是，下面描述中的附图仅仅涉及本公开的一些实施例，而非对本公开构成限制。在附图中：
图1示出了根据本公开一些实施例的推荐方法的流程示意图。
图2示出了根据本公开一些实施例的多媒体内容的生成方法的流程示意图。
图3A示出了根据本公开另一些实施例的多媒体内容的生成方法的流程示意图。
图3B示出了根据本公开又一些实施例的多媒体内容的生成方法的流程示意图。
图3C示出了根据本公开再一些实施例的多媒体内容的生成方法的流程示意图。
图4A示例性地示出了本公开一些实施例中的书籍页面。
图4B示出了根据本公开一些实施例的多媒体内容的展示界面的示意图。
图4C示出了根据本公开一些实施例的智能对话界面的示意图。
图5示出了根据本公开一些实施例的信息确定方法的流程示意图。
图6示出了根据本公开一些实施例的推荐装置的结构示意图。
图7示出了根据本公开一些实施例的的电子设备的结构示意图。
图8示出了根据本公开一些实施例的计算机系统的结构示意图。
应当明白，为了便于描述，附图中所示出的各个部分的尺寸并不一定是按照实际的比例关系绘制的。在各附图中使用了相同或相似的附图标记来表示相同或者相似的部件。因此，一旦某一项在一个附图中被定义，则在随后的附图中可能不再对其进行进一步讨论。
具体实施方式
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，但是显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。以下对实施例的描述实际上也仅仅是说明性的，决不作为对本公开及其应用或使用的任何限制。应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值应被解释为仅仅是示例性的，不限制本公开的范围。
本公开中使用的术语“包括”及其变型意指至少包括后面的元件/特征、但不排除其他元件/特征的开放性术语，即“包括但不限于”。此外，本公开使用的术语“包含”及其变型意指至少包含后面的元件/特征、但不排除其他元件/特征的开放性术语，即“包含但不限于”。因此，包括与包含是同义的。术语“基于”意指“至少部分地基于”。
整个说明书中所称“一个实施例”、“一些实施例”或“实施例”意味着与实施例结合描述的特定的特征、结构或特性被包括在本发明的至少一个实施例中。例如，术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。而且，短语“在一个实施例中”、“在一些实施例中”或“在实施例中”在整个说明书中各个地方的出现不一定全都指的是同一个实施例，但是也可以指同一个实施例。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。除非另有指定，否则“第一”、“第二”等概念并非意图暗示如此描述的对象必须按时间上、空间上、排名上的给定顺序或任何其他方式的给定顺序。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
下面结合附图对本公开的实施例进行详细说明，但是本公开并不限于这些具体的实施例。下面这些具体实施例可以相互结合，对于相同或者相似的概念或过程可能在某些 实施例不再赘述。此外，在一个或多个实施例中，特定的特征、结构或特性可以由本领域的普通技术人员从本公开将清楚的任何合适的方式组合。
在相关技术中，在用户阅读过程中推送的信息比较突兀和生硬。当用户沉浸在阅读的书籍中时，如果突然出现仅描述待推荐对象本身的推荐信息，会打断用户的阅读节奏和阅读沉浸感，并且对推送信息的信息传递有效性也造成了影响。
为了至少部分地解决上述问题，本公开提供了一种推荐方法，利用书籍中的内容生成用于介绍待推荐对象的多媒体内容，并在用户的阅读过程中显示该多媒体内容，以降低在用户阅读过程中推送信息时对用户的打扰。下面参考图1描述本公开推荐方法的实施例。该实施例可以由电子设备执行，例如，电子设备中的应用(Application)或应用程序执行。电子设备可以是平板电脑、手机(如折叠屏手机、大屏手机等)、可穿戴设备、车载设备、增强现实(augmented reality，AR)/虚拟现实(virtual reality，VR)设备、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本、个人数字助理(personal digital assistant，PDA)、智能电视、智慧屏、高清电视、4K电视、智能音箱、智能投影仪等物联网(the internet of things，IOT)设备，本公开对电子设备的具体类型不作任何限制。本公开对电子设备的操作系统的类型不做限定。例如，Android系统、Linux系统、Windows系统、iOS系统等。
图1示出了根据本公开一些实施例的推荐方法的流程示意图。如图1所示，该实施例的推荐方法包括步骤S102至S106。
在步骤S102中，确定与参考书籍中的参考对象所匹配的待推荐对象。
参考书籍是指应用中所提供的、可在电子设备中浏览的书籍，例如电子书、有声书等，其可以是与用户关联的书籍，诸如用户所有的(例如添加到用户书架上的)、用户阅读过的(例如当前正在阅读或者过去曾经阅读的)、用户感兴趣的(例如用户列举在用户的书单中的、用户收藏的、用户在话题贴中谈论的、用户推荐的)，或者也可以不是与用户关联的书籍，诸如应用中的热门书籍。热门书籍可以根据点击率、与之相关的讨论度、用户评价确定。参考书籍用于为多媒体内容的生成提供依据。讨论度可以根据书籍的评论或话题贴中的出现频率或信息量确定。
参考对象为参考书籍中描述过的对象，例如角色、地点、物品等等。参考对象可以是当前阅读进度邻近的段落中出现的对象，或者该书籍中的关键对象(例如主角、标志性地点、标志性物品)或者讨论度最高的对象。
待推荐对象是指待推荐给当前用户的对象，可以是商品、应用中的功能、或者服务等等。参考对象可以与待推荐对象具有一定的相关性，该相关性可以通过参考书籍中对参考对象的描述进一步挖掘。与参考对象匹配的待推荐对象为与参考对象存在关联的对象。例如，可以对参考对象的描述文本进行语义分析，从中提取命名实体、主题词、关键词等等，并将提取的信息与备选的多个对象进行匹配，以从备选的多个对象中确定出待推荐对象。
在步骤S104中，利用参考书籍中参考对象的描述文本、以及待推荐对象，生成用于介绍待推荐对象的多媒体内容。
参考对象的描述文本可以是书籍中出现了参考对象的段落，例如对参考对象的外观、特点的直接描述，或者是包括参考对象的某段情节文本，又或者，在参考对象为角色的情况下，描述文本也可以是该角色的说话内容文本。
生成的多媒体内容例如包括图像、视频等等，其可以是图像、视频等多媒体文件本身，也可以是包括图像、视频、游戏的其他类型文件或对象。在一些实施例中，多媒体内容包括图像、视频、智能对话页面、图文链接、直播中的至少一种。利用描述文本和待推荐对象生成多媒体内容的过程，可以通过生成式模型实现，从而能够提高多媒体内容的生成效率。
生成式模型用于基于输入的信息，输出目标内容。输入的信息包括生成式模型在生成过程中的处理依据，例如参考哪些信息执行生成过程、输出的多媒体内容的要求等等。向生成式模型的输入内容的一个示例中包括参考对象的描述文本、待推荐对象的信息、以及生成指示，生成指示例如为“基于参考对象的描述文本中的内容，以及待推荐对象，生成一个多媒体内容，该内容利用描述文本中的内容的风格/情节/对象，对待推荐对象进行介绍”。生成指示可以是以自然语言的形式表示的，也可以是利用其他形式表示的，这里不再赘述。在一些实施例中，也可以分阶段地生成多媒体内容，例如使用一个或多个生成式模型依次生成多媒体内容的各个部分，再合成这些部分以获得多媒体内容。
本公开所使用的生成式模型例如包括基于文本进行生成的模型，生成式模型的输出可以包括文本、多媒体内容或二者的结合。当然，生成式模型的输入或输出也可以还包括其他模态的数据，如音频、图像、视频或者多种类型的数据的结合。生成式模型例如基于大语言模型(Large Language Model，简称：LLM)实现或者基础模型 (Foundation Model)实现。
在步骤S106中，在用户的阅读过程中，显示多媒体内容。
用户的阅读过程可以是指用户在应用中阅读某本书籍(后文可以简称为“当前书籍”)的过程，即在书籍的显示过程中，显示多媒体内容。例如，在书籍中某一页的页面中显示多媒体内容，或者将多媒体内容作为书籍的补充页面显示在书籍的两个页面之间、或首页之前、或尾页之后，或者以浮窗等方式显示在书籍的页面的上层。
在显示多媒体内容的同时、或者在多媒体内容中，还可以显示待推荐对象的链接，用户在触发链接后可以进入待推荐对象的详情界面、购买界面、客服界面等等。
由于多媒体内容是根据书籍中的内容生成的，因此在通过多媒体内容对待推荐对象进行介绍时，多媒体内容中包含了书籍中的元素，从而在向用户介绍待推荐对象时，能够提高推送信息的沉浸感和用户阅读的连贯性，因此提高了用户的阅读体验和信息传递的效率。
本公开的一些实施例可以利用生成式模型生成图像和推荐信息，再基于二者进一步生成多媒体内容。下面参考图2描述本公开多媒体内容的生成方法的实施例。
图2示出了根据本公开一些实施例的多媒体内容的生成方法的流程示意图。如图2所示，该实施例的生成方法包括步骤S202至S206。
在步骤S202中，利用第一生成模型，对参考书籍中参考对象的描述文本进行处理，生成与参考对象对应的图像资源。
第一生成模型为生成式模型，对生成式模型的描述可以参考图1实施例，这里不再赘述。第一生成模型例如可以是文生图模型(根据文本生成图像的模型)，或者输入包括文本、输出包括图像的其他类型的模型。在一个示例中，第一生成模型的输入包括参考对象的描述文本以及第一生成指令。第一生成指令例如为“根据参考对象的描述文本，生成包括参考对象的图像资源，该图像资源需要满足……要求”。第一生成指令可以是自然语言，也可以是其他形式，这里不再赘述。
与参考对象对应的图像资源可以是包括参考对象的图像资源，或者用于间接地反映参考对象的图像资源，例如借助图像资源中的对象对参考对象进行描述。图像资源可以是静态图像、动态图像或者一个或多个视频片段。通过生成与参考图像对应的图像资源，可以将书中的文字描述进行可视化处理，从而更加直观、生动地表示书籍中的内容。
部分书籍存在关联的、带有插图的书籍，在生成图像资源时，可以参考这类关联的书籍。在一些实施例中，利用第一生成模型，对参考书籍中参考对象的描述文本、以及与参考对象对应的图片进行处理，生成与参考对象对应的图像资源，其中，与参考对象对应的图片为参考书籍中的图片，或者与参考书籍关联的、带有插图的书籍中的图片。带有插图的书籍例如为参考书籍的相关漫画、绘本、影视化作品的美术设定等等。从而，可以扩展输入数据，使得生成的图像资源的效果更好。在搜索与参考图像对应的图片时，例如可以通过搜索书籍中的图片的图例、或者图片前后文的内容中的参考对象的名称等信息，以便更准确地获取与参考图像对应的图片。
在步骤S204中，利用第二生成模型，对参考对象的描述文本和待推荐对象进行处理，生成待推荐对象的推荐信息。
第二生成模型为生成式模型，对生成式模型的描述可以参考图1实施例，这里不再赘述。第二生成模型例如可以是文生文模型(根据文本生成文本的模型)，或者输入包括文本、输出包括文本的其他类型的模型。第二生成模型与第一生成模型可以相同、也可以不同。在第二生成模型与第一生成模型相同时，步骤S202和S204可以通过该模型的相同代理(例如客户端)执行，也可以通过不同的代理执行。
在一个示例中，第二生成模型的输入包括参考对象的描述文本、待推荐对象以及第二生成指令。第二生成指令例如为“根据参考对象的描述文本和待推荐对象，生成待推荐对象的推荐信息，推荐信息需要与参考对象的特点相符”。第二生成指令可以是自然语言，也可以是其他形式，这里不再赘述。
推荐信息可以是基于文本实现的信息，例如是文本本身，也可以是借助文本生成的语音。该文本可以包括一段或多段。在一些实施例中，推荐信息可以理解为是待推荐对象的推荐语、广告语。推荐信息的生成同时参考了参考对象的描述文本和待推荐对象，从而推荐信息能够兼顾二者的特点，以结合参考书籍中的相关情境，将待推荐对象更自然地进行推荐。
在步骤S206中，基于图像资源和推荐信息，生成用于介绍待推荐对象的多媒体内容。
在获得图像资源和推荐信息后，可以将二者进行合成以生成多媒体内容。例如，将推荐信息以文本的形式显示在多媒体内容中，或者将图像资源和推荐信息并列地显示在多媒体内容中。
步骤S202和S204可以先后执行、也可以并列执行，并且二者的执行可以是关联的、也可以是彼此独立的。
上述实施例通过生成参考对象的图像资源和待推荐对象的推荐信息，并基于二者生成多媒体内容，能够使得生成的多媒体内容中包括对参考书籍的内容的可视化信息和待推荐对象的推荐信息，从而多媒体内容能够兼顾参考书籍的沉浸感以及对待推荐对象的信息的传递。
下面分别以参考对象包括参考角色、参考物品、参考地点为例，示例性地描述多媒体内容的生成方法。
图3A示出了根据本公开另一些实施例的多媒体内容的生成方法的流程示意图。在该实施例中，参考对象包括参考角色。如图3A所示，该实施例的生成方法包括步骤S202a至S206a。
在步骤S202a中，利用第一生成模型，对参考书籍中参考角色的描述文本进行处理，生成参考角色的虚拟形象。
参考角色可以是人物、动物或其他任意类型的角色。参考角色的描述文本可以是对参考角色的基本熟悉、职业、外形、衣着、形象、动作、性格、语言等方面的直接或间接描述，并且除了书籍正文的内容以外，描述文本还可以包括书籍提供的人物简介。参考角色可以是参考书籍中的主要角色、在参考书籍的读者中热度较高的角色、用户感兴趣的角色或者用户最近读过的段落中提及的角色。
参考角色的虚拟形象可以是参考角色的全身像、半身像、头像等等，或者在多种，虚拟形象中的角色着装、表情等可以与书籍中的相关描述匹配。
在步骤S204a中，利用第二生成模型，对参考书籍中参考角色的描述文本和待推荐对象进行处理，生成虚拟角色对待推荐对象的推荐语。从而，可以借助虚拟角色的特点进行推荐。例如，可以模仿虚拟角色的说话特点生成推荐语，实现类似于通过虚拟角色做广告的效果。
在步骤S206a中，基于虚拟形象和推荐语，生成用于介绍待推荐对象的多媒体内容。
为了进一步丰富多媒体内容，还可以自动地生成虚拟形象的语音。在一些实施例中，基于参考书籍中参考角色的描述文本、参考角色的设定信息中的至少一种，生成参考角色的语音；基于虚拟形象、推荐语和语音，生成用于介绍待推荐对象的多媒体内容。语音的内容可以是推荐语，也可以是参考书籍中的文本、或根据参考书籍中的 文本生成的语句，还可以是针对用户的交互行为而生成的语音应答。从而，虚拟形象具有与参考书籍中的描述所匹配的语音，生成的多媒体内容能够从图像、声音、文本等多个方面塑造参考角色，提高了多媒体内容的推荐效果。
上述实施例通过利用书籍中的角色进行推荐，能够实现利用角色的虚拟形象进行推荐的效果，使得推荐的对象更容易被读者接受，提高了信息推送的效率。
图3B示出了根据本公开又一些实施例的多媒体内容的生成方法的流程示意图。在该实施例中，参考对象包括参考物品。如图3B所示，该实施例的生成方法包括步骤S202b至S206b。
在步骤S202b中，利用第一生成模型，对参考书籍中参考物品的描述文本进行处理，生成参考物品的图像资源。例如，生成参考物品在参考书籍中的使用场景的图像资源。
参考物品的描述文本例如包括物品的名称、外形、用途的文本的直接或间接描述，参考物品可以是参考书籍中的重要物品、在参考书籍的读者中热度较高的物品、用户感兴趣的物品或者用户最近读过的段落中提及的物品。参考物品例如为与待推荐对象类别相同或者属性相近的物品。例如，参考书籍中的某主角有一件红色外套，则待推荐对象也可以是一件红色外套。
生成的图像资源可以包括参考物品在参考书籍中的使用场景。例如，参考物品为红色外套，并且参考书籍中描写了主角穿着红色外套在阳光下奔跑的内容，则图像资源中可以包括该画面；参考物品为一个帐篷，并且参考书籍中描写了某角色在山顶搭帐篷过夜的内容，则图像资源中例如可以包括夜晚的山顶，并且山顶有一个帐篷。
在步骤S204b中，利用第二生成模型，对参考书籍中参考物品的描述文本和待推荐对象进行处理，生成待推荐对象的推荐信息。推荐信息例如为待推荐对象的介绍语。从而待推荐对象的推荐信息能够同时融合参考书籍中对参考物品的描述以及对待推荐对象的描述，使得推荐信息成为对参考书籍中的参考物品的描述的延展。
在生成推荐信息时，可以指示第二生成模型利用参考物品和待推荐对象的共同点或相似之处，生成推荐信息，使得推荐信息从参考书籍中对参考物品的描述自然地过渡到对待推荐对象的介绍，从而推荐信息的可读性会更好。
在步骤S206b中，基于使用场景的图像资源和推荐信息，生成用于介绍待推荐对象的多媒体内容。
上述实施例通过利用书籍中的物品进行推荐，能够基于书籍中的物品以及待推荐 对象之间的关联性进行推荐，使得推荐的对象更容易被读者接受，提高了信息推送的效率。
图3C示出了根据本公开再一些实施例的多媒体内容的生成方法的流程示意图。在该实施例中，参考对象包括参考物品。如图3C所示，该实施例的生成方法包括步骤S202c至S206c。
在步骤S202c中，利用第一生成模型，对参考书籍中参考地点的描述文本进行处理，生成参考地点的图像资源。
参考地点可以是真实地点，也可以是书籍中虚构的地点。参考地点的描述文本例如包括位置、气候特点、风土人情、关键事件的直接或间接描述。参考地点可以是参考书籍中的重要地点、在参考书籍的读者中热度较高的地点、用户感兴趣的地点或者用户最近读过的段落中提及的地点。参考地点例如为与待推荐对象具有关联性的地点。例如，待推荐对象为热带水果，则参考地点可以是位于热带的地点。或者，在使用参考地点生成多媒体内容的情况下，待推荐对象可以是出行类产品或服务，例如订机票服务、订酒店服务、旅行类应用等等。
在步骤S204c中，利用第二生成模型，对参考书籍中参考地点的描述文本和待推荐对象进行处理，生成待推荐对象的推荐信息。推荐信息例如为待推荐对象的介绍语。待推荐对象的推荐信息能够同时融合参考书籍中对参考地点的描述以及对待推荐对象的描述，使得推荐信息成为对参考书籍中的参考地点的描述的延展。
在生成推荐信息时，可以指示第二生成模型利用参考书籍中的内容挖掘参考地点的特点，如果参考地点是真实存在的地点，还可以从其他信息源中挖掘关于该地点的更多信息。从而，使得推荐信息能够体现参考地点与待推荐对象的关联性，从而推荐信息能够产生更好的推荐效果。
在步骤S206c中，基于参考地点的图像资源和推荐信息，生成用于介绍待推荐对象的多媒体内容。
上述实施例通过利用书籍中的地点进行推荐，能够基于书籍中的地点的特点中与待推荐对象的关联，对待推荐对象进行推荐，使得推荐的对象更容易被读者接受，提高了信息推送的效率。
上述利用参考角色、参考物品、参考地点进行推荐的方案可以单独使用，也可以进行任意组合，从而进一步提高推荐效果。具体的组合方式这里不再赘述。
下面示例性地描述本公开所涉及的界面示意图。
图4A示例性地示出了本公开一些实施例中的书籍页面，该书籍为用户阅读中的书籍AAAA，当前阅读到章节BBBB。在界面41中，显示了书中的某页内容，其中包括正文411“这是晴朗的一天。在c地，一个少年D正在爬山，身穿夹克，夹克上别着一枚XX小队的徽章……”。此外，界面41还可以包括推荐提示412，例如“即将进入推荐页”“即将进入广告页”等等。响应于用户触发翻页操作，可以触发展示生成的多媒体内容。
在一些实施例中，响应于用户阅读到当前书籍中的指定节点，显示多媒体内容。指定节点为章节的末尾、或者关键情节的结尾。从而可以尽量避免打断用户的阅读节奏。例如，可以预先生成好多媒体内容并在指定节点后显示，或者可以在用户阅读到临近指定节点时实时生成多媒体内容。
图4B和4C分别示出了两种不同的展示多媒体内容的界面。下面分别进行介绍。
图4B示出了根据本公开一些实施例的多媒体内容的展示界面的示意图。如图4B所示，界面42中展示了一张图像，图像中包括用户正在阅读的书籍AAAA(在该实施例中同时作为参考书籍)中的角色D的全身像421。全身像421例如根据图4A中的对角色D的描述文本生成。图像中还可以包括角色D的推荐语422“嘿！没想到在这里碰到你，XX小队急需要新成员，想加入XX小队吗？可以购买同款装备加入我们，期待一起战斗！”该推荐语可以根据待推荐的夹克和队徽以及书籍AAAA中对角色D的描述文本生成。
此外，界面42中还可以包括待推荐的夹克的链接423以及队徽的链接424，用户触发链接后可以进一步了解详情或购买。在链接中的对象的名称可以是其原本的名称，也可以是基于参考书籍中的描述文本以及原本的名称进行处理后生成的新名称。例如，待推荐的夹克原本是某品牌的夹克，这里可以基于参考书籍中的描述生成新的名称“XX小队夹克”。
多媒体内容可以为智能对话页面。在一些实施例中，基于参考角色的虚拟形象和推荐语，生成与参考角色对应的虚拟形象的智能对话页面，推荐语为虚拟形象发送的对话。图4C示出了根据本公开一些实施例的智能对话界面的示意图。对话界面43为用户和参考角色D的虚拟形象之间的对话界面。基于参考书籍中对角色D的描述，可以生成角色D的头像431。角色D可以发送信息以对待推荐对象进行描述，或者回应 用户关于待推荐对象的问题。
界面43可以承接在书籍的阅读页面之后，例如，在界面41中触发切换页面操作之后，可以显示界面43，此时界面43中，角色D可以发送推荐语；界面43也可以承接在其他多媒体内容的展示界面之后，例如响应于触发界面42中的待推荐对象的链接，显示界面43，此时界面43中可以再显示一次推荐语，也可以直接显示与待推荐对象相关的信息，例如对话控件432所示的、与待推荐对象关联的问询提示。
多媒体内容还可以为直播。在一些实施例中，基于参考角色的虚拟形象和推荐语，生成以虚拟形象作为主播的直播，推荐语为直播中被推荐对象的描述信息。例如，可以将真人主播实时替换为虚拟形象，或者实时生成以虚拟形象为主播的直播内容。直播界面中可以显示生成的推荐语，或者，主播也可以口述该推荐语。与智能对话界面类似地，直播可以承载在书籍的阅读页面之后，也可以承接在其他多媒体内容的展示界面之后，这里不再赘述。
上述各个实施例描述了多媒体内容的生成和显示，其中，在生成过程中所利用的参考书籍和参考对象可以根据用户授权的阅读记录确定。下面参考图5描述本公开对参考书籍、参考对象、待推荐对象等信息的确定方法的实施例。
图5示出了根据本公开一些实施例的信息确定方法的流程示意图。如图5所示，该实施例的信息确定方法包括步骤S502至S106。
在步骤S502中，根据经用户授权的、用户的阅读记录，确定参考书籍、以及参考书籍中的参考对象。
用户的阅读记录包括用户所阅读过的书籍，根据需要，还可以包括每本书的阅读时长、阅读进度(例如读到哪一章、哪一段、哪一页等)、开始阅读的时间、最后阅读的时间等等。
在一些实施例中，用户的阅读记录包括用户正在阅读的书籍、已阅读的书籍中的至少一个以及阅读进度。在这种情况下，参考书籍可以是用户正在阅读的书籍，这样生成的多媒体内容能够与当前的阅读内容更加匹配，从而提高了用户的阅读体验，也提高了推荐效率；或者，参考书籍可以是用户读过的书籍，这样生成的多媒体内容为用户熟悉的内容，虽然与当前阅读的书籍的内容不一定完全匹配，但是其同样是基于书籍生成的，也具有阅读氛围，也能够在一定程度上降低对用户阅读节奏的打扰，提高了推荐效率。
在一些实施例中，可以从参考书籍中与用户的阅读进度对应的内容、参考书籍的摘要、参考书籍的关键情节、参考书籍的主要角色、用户发布的帖子中的至少一项，提取参考对象。与用户的阅读进度对应的内容可以是用户当前阅读进度所在的章节，或当前阅读进度之前的指定段落数、字数、页数等等。参考书籍的关键情节可以是书籍中预先标注的，也可以根据读者的标记信息和阅读情况确定，例如根据被标记次数、阅读用户数等确定。参考书籍的主要角色不仅能够提供角色的信息，也能够确定与主要角色相关联的关键事件、关键物品、关键地点等信息，以作为参考信息。用户发布的帖子中可能涉及到对书籍中的角色、情节等讨论，从中可以挖掘出用户感兴趣的参考信息。
在一些实施例中，根据用户发布的帖子所涉及的一个或多个书籍、以及已阅读的书籍，确定参考书籍。即可以从已读书籍中选择参考书籍，也可以从用户发布的帖子中涉及的书籍中确定用户感兴趣的书籍、进而确定参考书籍，用户感兴趣的书籍可能是用户阅读过的、也可能是用户未阅读过的。从而，可以使得多媒体内容中所涉及的元素是用户熟悉的元素、或者用户可能感兴趣的元素，从而提高推荐的效果。
在一些实施例中，对于用户发布的帖子所涉及的一个或多个书籍中的每一个，根据书籍在帖子中的出现频率、书籍在帖子中所涉及的信息量中的至少一项，确定候选书籍。书籍在用户发布的帖子中的出现频率，可以根据出现该书籍的帖子数量与用户发布的帖子的总数量的比值确定。在确定书籍在帖子中涉及的信息量时，可以通过语义分析确定帖子中与该书籍相关的内容，再计算这部分内容的篇幅以作为信息量。当然，本领域技术人员可以对出现频率和信息量的计算方法进行调整，这里不再赘述。
上述实施例能够首先从书籍在帖子中的覆盖广度或讨论深度，首先确定出具有一定参考价值的书籍。然后，根据已阅读的书籍和候选书籍，确定参考书籍。从而，如果帖子中出现的书籍并不是用户已阅读的书籍，但是用户频繁提起、或者对其进行了深入的讨论，那么很有可能用户在其他应用中阅读过该书籍、或者对该书籍有非常浓厚的兴趣，在这种情况下，可以将其作为参考书籍，从而能够使得生成的多媒体内容是用户比较熟悉的内容，提高了推荐的效果。
如果用户的阅读量较小，例如是应用的新用户、或者不常登录的用户，其阅读记录难以带来更多的信息量，此时可以从热门书籍中确定参考书籍。在一些实施例中，在用户的阅读总量小于第一阈值的情况下，从热门书籍中确定参考书籍，阅读总量根 据经用户授权的、用户的阅读记录确定；从参考书籍的摘要、参考书籍的关键情节、参考书籍的主要角色、用户发布的帖子中的至少一项，提取参考对象。用户的阅读总量可以以字数、书籍数、阅读时长等任意指标中的一个或多个来确定。热门书籍根据应用或平台中各个书籍的讨论数、点击数或阅读用户数等确定。在确定参考书籍之后，可以从能够反映参考书籍的主要内容中提取参考对象。从而，在用户的阅读总量较小的情况下，除了直接根据用户阅读中的书籍生成多媒体内容，也可以根据热门书籍生成多媒体内容，提高了多媒体内容生成的多样性。
步骤S102至S106参考前述实施例，这里不再赘述。
通过上述实施例，可以基于用户的阅读情况确定参考书籍，进而从参考书籍中确定参考对象。从而，可以使得生成的多媒体内容更贴近用户，提高了推荐效率。
以上各个实施例描述了本公开所涉及的方法。可以理解的是，在使用本公开中各个实施例的技术方案之前，均会通过恰当的方式对所涉及的个人信息的类型、使用范围、使用场景等告知用户，并获得用户的授权。
例如，在响应于接收到用户的主动请求时，向用户发送提示信息，以明确的提示用户，其请求执行的操作将需要获取和使用到用户的个人信息。从而，使得用户可以根据提示信息来自主的选择是否向执行本公开技术方案的操作的电子设备、应用程序、服务器或存储介质等软件或硬件提供个人信息。
作为一种可选的但非限定的实现方式，响应于接受到用户的主动请求，向用户发送提示信息的方式例如可以是弹窗的方式，弹窗中可以以文字的方式呈现提示信息。此外，弹窗中还可以承载供用户选择“同意”或者“不同意”向电子设备提供个人信息的选择控件。
可以理解的是，上述通知和获取用户授权过程仅是示意性的，不对本公开的实现方式构成限定，其他满足相关法律法规的方式也可应用于本公开的实现方式中。
下面对本公开所涉及的装置、设备进行描述。
图6示出了根据本公开一些实施例的推荐装置的结构示意图。如图6所示，该实施例的推荐装置60包括：确定模块602，被配置为确定与参考书籍中的参考对象所匹配的待推荐对象；生成模块604，被配置为利用参考书籍中参考对象的描述文本、以及待推荐对象，生成用于介绍待推荐对象的多媒体内容；显示模块606，被配置为在用户的阅读过程中，显示多媒体内容。
在一些实施例中，生成模块604进一步被配置为：利用第一生成模型，对参考书籍 中参考对象的描述文本进行处理，生成与参考对象对应的图像资源；利用第二生成模型，对参考对象的描述文本和待推荐对象进行处理，生成待推荐对象的推荐信息；基于图像资源和推荐信息，生成用于介绍待推荐对象的多媒体内容。
在一些实施例中，生成模块604进一步被配置为：利用第一生成模型，对参考书籍中参考对象的描述文本、以及与参考对象对应的图片进行处理，生成与参考对象对应的图像资源，其中，与参考对象对应的图片为参考书籍中的图片，或者与参考书籍关联的、带有插图的书籍中的图片。
在一些实施例中，参考对象包括参考角色，生成模块604进一步被配置为：利用第一生成模型，对参考书籍中参考角色的描述文本进行处理，生成参考角色的虚拟形象；利用第二生成模型，对参考书籍中参考角色的描述文本和待推荐对象进行处理，生成虚拟角色对待推荐对象的推荐语；基于虚拟形象和推荐语，生成用于介绍待推荐对象的多媒体内容。
在一些实施例中，生成模块604进一步被配置为：基于参考书籍中参考角色的描述文本、参考角色的设定信息中的至少一种，生成参考角色的语音；基于虚拟形象、推荐语和语音，生成用于介绍待推荐对象的多媒体内容。
在一些实施例中，生成模块604进一步被配置为：生成与参考角色对应的虚拟形象的智能对话页面，推荐语为虚拟形象发送的对话；或者，生成以虚拟形象作为主播的直播，推荐语为直播中被推荐对象的描述信息。
在一些实施例中，参考对象包括参考物品，生成模块604进一步被配置为：利用第一生成模型，对参考书籍中参考物品的描述文本进行处理，生成参考物品在参考书籍中的使用场景的图像资源；利用第二生成模型，对参考书籍中参考物品的描述文本和待推荐对象进行处理，生成待推荐对象的推荐信息；基于使用场景的图像资源和推荐信息，生成用于介绍待推荐对象的多媒体内容。
在一些实施例中，参考对象包括参考地点，生成模块604进一步被配置为：利用第一生成模型，对参考书籍中参考地点的描述文本进行处理，生成参考地点的图像资源；利用第二生成模型，对参考书籍中参考地点的描述文本和待推荐对象进行处理，生成待推荐对象的推荐信息；基于参考地点的图像资源和推荐信息，生成用于介绍待推荐对象的多媒体内容。
在一些实施例中，显示模块606进一步被配置为：响应于用户阅读到当前书籍中的 指定节点，显示多媒体内容，指定节点为章节的末尾、或者关键情节的结尾。
在一些实施例中，确定模块602进一步被配置为：根据经用户授权的、用户的阅读记录，确定参考书籍、以及参考书籍中的参考对象；确定与参考对象匹配的待推荐对象。
在一些实施例中，用户的阅读记录包括用户正在阅读的书籍、已阅读的书籍中的至少一个以及阅读进度，确定模块602进一步被配置为：将用户正在阅读的书籍确定为参考书籍，或者，基于用户在一本或多本已阅读的书籍中的阅读进度，从已阅读的书籍中确定参考书籍；从参考书籍中与用户的阅读进度对应的内容、参考书籍的摘要、参考书籍的关键情节、参考书籍的主要角色、用户发布的帖子中的至少一项，提取参考对象。
在一些实施例中，确定模块602进一步被配置为：根据用户发布的帖子所涉及的一个或多个书籍、以及已阅读的书籍，确定参考书籍。
在一些实施例中，确定模块602进一步被配置为：对于用户发布的帖子所涉及的一个或多个书籍中的每一个，根据书籍在帖子中的出现频率、书籍在帖子中所涉及的信息量中的至少一项，确定候选书籍；根据已阅读的书籍和候选书籍，确定参考书籍。
在一些实施例中，确定模块602进一步被配置为：在用户的阅读总量小于第一阈值的情况下，从热门书籍中确定参考书籍，阅读总量根据经用户授权的、用户的阅读记录确定；从参考书籍的摘要、参考书籍的关键情节、参考书籍的主要角色、用户发布的帖子中的至少一项，提取参考对象。
在一些实施例中，多媒体内容包括图像、视频、智能对话页面、图文链接、直播中的至少一种。
应注意，上述各个单元仅是根据其所实现的具体功能划分的逻辑模块，而不是用于限制具体的实现方式，例如可以以软件、硬件或者软硬件结合的方式来实现。在实际实现时，上述各个单元可被实现为独立的物理实体，或者也可由单个实体(例如，处理器(CPU或DSP等)、集成电路等)来实现。此外，上述各个单元在附图中用虚线示出指示这些单元可以并不实际存在，而它们所实现的操作/功能可由处理电路本身来实现。
此外，尽管未示出，该设备也可以包括存储器，其可以存储由设备、设备所包含的各个单元在操作中产生的各种信息、用于操作的程序和数据、将由通信单元发送的数据等。存储器可以是易失性存储器和/或非易失性存储器。例如，存储器可以包括但不限于随机存储存储器(RAM)、动态随机存储存储器(DRAM)、静态随机存取存储器(SRAM)、只读存储器(ROM)、闪存存储器。当然，存储器可也位于该设备之外。可选地，尽管 未示出，但是该设备也可以包括通信单元，其可用于与其它装置进行通信。在一个示例中，通信单元可以被按照本领域已知的适当方式来实现，例如包括天线阵列和/或射频链路等通信部件，各种类型的接口、通信单元等等。这里将不再详细描述。此外，设备还可以包括未示出的其它部件，诸如射频链路、基带处理单元、网络接口、处理器、控制器等。这里将不再详细描述。
本公开的一些实施例还提供一种电子设备。图7示出了根据本公开一些实施例的的电子设备的结构示意图。例如，在一些实施例中，电子设备7可以为各种类型的设备，例如可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。例如，电子设备7可以包括显示面板，以用于显示根据本公开的方案中所利用的数据和/或执行结果。例如，显示面板可以为各种形状，例如矩形面板、椭圆形面板或多边形面板等。另外，显示面板不仅可以为平面面板，也可以为曲面面板，甚至球面面板。
如图7所示，该实施例的电子设备7包括：存储器71以及耦接至该存储器71的处理器72。应当注意，图7所示的电子设备7的组件只是示例性的，而非限制性的，根据实际应用需要，该电子设备7还可以具有其他组件。处理器72可以控制电子设备7中的其它组件以执行期望的功能。
在一些实施例中，存储器71用于存储一个或多个计算机可读指令。处理器72用于运行计算机可读指令时，计算机可读指令被处理器72运行时实现根据上述任一实施例的方法。关于该方法的各个步骤的具体实现以及相关解释内容可以参见上述的实施例，重复之处在此不作赘述。
例如，处理器72和存储器71之间可以直接或间接地互相通信。例如，处理器72和存储器71可以通过网络进行通信。网络可以包括无线网络、有线网络、和/或无线网络和有线网络的任意组合。处理器72和存储器71之间也可以通过系统总线实现相互通信，本公开对此不作限制。
例如，处理器72可以体现为各种适当的处理器、处理装置等，诸如中央处理器(CPU)、图形处理器(Graphics Processing Unit，GPU)、网络处理器(NP)等；还可以是数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。中央处理元(CPU)可以为 X86或ARM架构等。例如，存储器71可以包括各种形式的计算机可读存储介质的任意组合，例如易失性存储器和/或非易失性存储器。存储器71例如可以包括系统存储器，系统存储器例如存储有操作系统、应用程序、引导装载程序(Boot Loader)、数据库以及其他程序等。在存储介质中还可以存储各种应用程序和各种数据等。
另外，根据本公开的一些实施例，根据本公开的各种操作/处理在通过软件和/或固件实现的情况下，可从存储介质或网络向具有专用硬件结构的计算机系统，例如图8所示的计算机系统80安装构成该软件的程序，该计算机系统在安装有各种程序时，能够执行各种功能，包括诸如前文的功能等等。图8示出了根据本公开一些实施例的计算机系统的结构示意图。
在图8中，中央处理单元(CPU)801根据只读存储器(ROM)802中存储的程序或从存储部分808加载到随机存取存储器(RAM)803的程序执行各种处理。在RAM 803中，也根据需要存储当CPU 801执行各种处理等时所需的数据。中央处理单元仅仅是示例性的，其也可以是其它类型的处理器，诸如前文所述的各种处理器。ROM 802、RAM803和存储部分808可以是各种形式的计算机可读存储介质，如下文所述。需要注意的是，虽然图8中分别示出了ROM 802、RAM 803和存储装置808，但是它们中的一个或多个可以合并或者位于相同或不同的存储器或存储模块中。
CPU 801、ROM 802和RAM 803经由总线804彼此连接。输入/输出接口805也连接到总线804。
下述部件连接到输入/输出接口805：输入部分806，诸如触摸屏、触摸板、键盘、鼠标、图像传感器、麦克风、加速度计、陀螺仪等；输出部分807，包括显示器，比如阴极射线管(CRT)、液晶显示器(LCD)，扬声器，振动器等；存储部分808，包括硬盘，磁带等；和通信部分809，包括网络接口卡比如LAN卡、调制解调器等。通信部分809允许经由网络比如因特网执行通信处理。容易理解的是，虽然图8中示出计算机系统80中的各个装置或模块是通过总线804来通信的，但它们也可以通过网络或其它方式进行通信，其中，网络可以包括无线网络、有线网络、和/或无线网络和有线网络的任意组合。
根据需要，驱动器810也连接到输入/输出接口805。可拆卸介质811比如磁盘、光盘、磁光盘、半导体存储器等等根据需要被安装在驱动器810上，使得从中读出的计算机程序根据需要被安装到存储部分808中。
在通过软件实现上述系列处理的情况下，可以从网络比如因特网或存储介质比如可 拆卸介质811安装构成软件的程序。
根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置809从网络上被下载和安装，或者从存储装置808被安装，或者从ROM 802被安装。在该计算机程序被CPU 801执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，在本公开的上下文中，计算机可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是，但不限于：电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
在一些实施例中，还提供了一种计算机程序，包括：指令，指令当由处理器执行时使处理器执行上述任一个实施例的方法。例如，指令可以体现为计算机程序代码。
在本公开的实施例中，可以以一种或多种程序设计语言或其组合来编写用于执行本 公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言，诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言，诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络(包括局域网(LAN)或广域网(WAN))连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的模块、部件或单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，模块、部件或单元的名称在某种情况下并不构成对该模块、部件或单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示例性的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
以上描述仅为本公开的一些实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
在本文提供的描述中，阐述了许多特定细节。然而，理解的是，可以在没有这些特 定细节的情况下实施本发明的实施例。在其他情况下，为了不模糊该描述的理解，没有对众所周知的方法、结构和技术进行详细展示。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
虽然已经通过示例对本公开的一些特定实施例进行了详细说明，但是本领域的技术人员应该理解，以上示例仅是为了进行说明，而不是为了限制本公开的范围。本领域的技术人员应该理解，可在不脱离本公开的范围和精神的情况下，对以上实施例进行修改。本公开的范围由所附权利要求来限定。

Claims (20)

  1. 一种推荐方法，包括：
    确定与参考书籍中的参考对象所匹配的待推荐对象；
    利用所述参考书籍中所述参考对象的描述文本、以及所述待推荐对象，生成用于介绍所述待推荐对象的多媒体内容；
    在用户的阅读过程中，显示所述多媒体内容。
  2. 根据权利要求1所述的推荐方法，其中，所述利用所述参考书籍中所述参考对象的描述文本、以及所述待推荐对象，生成用于介绍所述待推荐对象的多媒体内容包括：
    利用第一生成模型，对所述参考书籍中所述参考对象的描述文本进行处理，生成与所述参考对象对应的图像资源；
    利用第二生成模型，对所述参考对象的描述文本和所述待推荐对象进行处理，生成所述待推荐对象的推荐信息；
    基于所述图像资源和所述推荐信息，生成所述用于介绍所述待推荐对象的多媒体内容。
  3. 根据权利要求2所述的推荐方法，其中，所述利用第一生成模型，对所述参考书籍中所述参考对象的描述文本进行处理，生成与所述参考对象对应的图像资源包括：
    利用所述第一生成模型，对所述参考书籍中所述参考对象的描述文本、以及与所述参考对象对应的图片进行处理，生成与所述参考对象对应的图像资源，其中，与所述参考对象对应的图片为所述参考书籍中的图片，或者与所述参考书籍关联的、带有插图的书籍中的图片。
  4. 根据权利要求2或3所述的推荐方法，其中，所述参考对象包括参考角色，所述利用所述参考书籍中所述参考对象的描述文本、以及所述待推荐对象，生成用于介绍所述待推荐对象的多媒体内容包括：
    利用所述第一生成模型，对所述参考书籍中所述参考角色的描述文本进行处理， 生成所述参考角色的虚拟形象；
    利用所述第二生成模型，对所述参考书籍中所述参考角色的描述文本和所述待推荐对象进行处理，生成所述虚拟角色对所述待推荐对象的推荐语；
    基于所述虚拟形象和所述推荐语，生成所述用于介绍所述待推荐对象的多媒体内容。
  5. 根据权利要求4所述的推荐方法，其中，所述基于所述虚拟形象和所述推荐语，生成所述用于介绍所述待推荐对象的多媒体内容包括：
    基于所述参考书籍中所述参考角色的描述文本、所述参考角色的设定信息中的至少一种，生成所述参考角色的语音；
    基于所述虚拟形象、所述推荐语和所述语音，生成所述用于介绍所述待推荐对象的多媒体内容。
  6. 根据权利要求4或5所述的推荐方法，其中，所述基于所述虚拟形象和所述推荐语，生成所述用于介绍所述待推荐对象的多媒体内容包括：
    生成与所述参考角色对应的虚拟形象的智能对话页面，所述推荐语为所述虚拟形象发送的对话；或者，
    生成以所述虚拟形象作为主播的直播，所述推荐语为所述直播中所述被推荐对象的描述信息。
  7. 根据权利要求2或3所述的推荐方法，其中，所述参考对象包括参考物品，所述利用所述参考书籍中所述参考对象的描述文本、以及所述待推荐对象，生成用于介绍所述待推荐对象的多媒体内容包括：
    利用所述第一生成模型，对所述参考书籍中所述参考物品的描述文本进行处理，生成所述参考物品在所述参考书籍中的使用场景的图像资源；
    利用所述第二生成模型，对所述参考书籍中所述参考物品的描述文本和所述待推荐对象进行处理，生成所述待推荐对象的推荐信息；
    基于所述使用场景的图像资源和所述推荐信息，生成所述用于介绍所述待推荐对象的多媒体内容。
  8. 根据权利要求2或3所述的推荐方法，其中，所述参考对象包括参考地点，所述利用所述参考书籍中所述参考对象的描述文本、以及所述待推荐对象，生成用于介绍所述待推荐对象的多媒体内容包括：
    利用所述第一生成模型，对所述参考书籍中所述参考地点的描述文本进行处理，生成所述参考地点的图像资源；
    利用所述第二生成模型，对所述参考书籍中所述参考地点的描述文本和所述待推荐对象进行处理，生成所述待推荐对象的推荐信息；
    基于所述参考地点的图像资源和所述推荐信息，生成所述用于介绍所述待推荐对象的多媒体内容。
  9. 根据权利要求1至8中任一项所述的推荐方法，其中，所述在用户的阅读过程中，显示所述多媒体内容包括：
    响应于所述用户阅读到当前书籍中的指定节点，显示所述多媒体内容，所述指定节点为章节的末尾、或者关键情节的结尾。
  10. 根据权利要求1至9中任一项所述的推荐方法，还包括：
    根据经所述用户授权的、所述用户的阅读记录，确定所述参考书籍、以及所述参考书籍中的所述参考对象。
  11. 根据权利要求10所述的推荐方法，其中，所述用户的阅读记录包括所述用户正在阅读的书籍、已阅读的书籍中的至少一个以及阅读进度，所述根据经所述用户授权的、所述用户的阅读记录，确定所述参考书籍、以及所述参考书籍中的所述参考对象包括：
    将所述用户正在阅读的书籍确定为所述参考书籍，或者，基于所述用户在一本或多本已阅读的书籍中的阅读进度，从所述已阅读的书籍中确定所述参考书籍；
    从所述参考书籍中与所述用户的阅读进度对应的内容、所述参考书籍的摘要、所述参考书籍的关键情节、所述参考书籍的主要角色、所述用户发布的帖子中的至少一项，提取所述参考对象。
  12. 根据权利要求11所述的推荐方法，其中，所述从所述已阅读的书籍中确定所述参考书籍包括：
    根据所述用户发布的帖子所涉及的一个或多个书籍、以及所述已阅读的书籍，确定所述参考书籍。
  13. 根据权利要求12所述的推荐方法，其中，所述根据所述用户发布的帖子所涉及的一个或多个书籍、以及所述已阅读的书籍，确定所述参考书籍包括：
    对于所述用户发布的帖子所涉及的一个或多个书籍中的每一个，根据所述书籍在所述帖子中的出现频率、所述书籍在所述帖子中所涉及的信息量中的至少一项，确定候选书籍；
    根据所述已阅读的书籍和所述候选书籍，确定所述参考书籍。
  14. 根据权利要求10至13中任一项所述的推荐方法，其中，所述根据经所述用户授权的、所述用户的阅读记录，确定所述参考书籍、以及所述参考书籍中的所述参考对象包括：
    在所述用户的阅读总量小于第一阈值的情况下，从热门书籍中确定所述参考书籍，所述阅读总量根据经所述用户授权的、所述用户的阅读记录确定；
    从所述参考书籍的摘要、所述参考书籍的关键情节、所述参考书籍的主要角色、所述用户发布的帖子中的至少一项，提取所述参考对象。
  15. 根据权利要求1至14中任一项所述的推荐方法，其中，所述多媒体内容包括图像、视频、智能对话页面、图文链接、直播中的至少一种。
  16. 一种推荐装置，包括：
    确定模块，被配置为确定与参考书籍中的参考对象所匹配的待推荐对象；
    生成模块，被配置为利用所述参考书籍中所述参考对象的描述文本、以及所述待推荐对象，生成用于介绍所述待推荐对象的多媒体内容；
    显示模块，被配置为在用户的阅读过程中，显示所述多媒体内容。
  17. 一种推荐装置，包括：
    存储器；以及
    耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器中的指令，执行如权利要求1至15中任一项所述的推荐方法。
  18. 一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现权利要求1至15中任一项所述的推荐方法。
  19. 一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机实现权利要求1至15中任一项所述的推荐方法。
  20. 一种计算机程序，包括：
    指令，所述指令当由处理器执行时使所述处理器执行根据权利要求1至15中任一项所述的推荐方法。
PCT/CN2024/081223 2024-03-12 2024-03-12 推荐方法、装置、计算机可读存储介质和计算机程序产品 Pending WO2025189355A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202480003554.9A CN120981800A (zh) 2024-03-12 2024-03-12 推荐方法、装置、计算机可读存储介质和计算机程序产品
PCT/CN2024/081223 WO2025189355A1 (zh) 2024-03-12 2024-03-12 推荐方法、装置、计算机可读存储介质和计算机程序产品

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2024/081223 WO2025189355A1 (zh) 2024-03-12 2024-03-12 推荐方法、装置、计算机可读存储介质和计算机程序产品

Publications (1)

Publication Number Publication Date
WO2025189355A1 true WO2025189355A1 (zh) 2025-09-18

Family

ID=97062747

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/081223 Pending WO2025189355A1 (zh) 2024-03-12 2024-03-12 推荐方法、装置、计算机可读存储介质和计算机程序产品

Country Status (2)

Country Link
CN (1) CN120981800A (zh)
WO (1) WO2025189355A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160092512A1 (en) * 2014-09-26 2016-03-31 Kobo Inc. System and method for using book recognition to recommend content items for a user
CN113034213A (zh) * 2019-12-09 2021-06-25 腾讯科技（深圳）有限公司 漫画内容的显示方法、装置、设备及可读存储介质
CN114764726A (zh) * 2021-01-14 2022-07-19 腾讯科技（深圳）有限公司 推广信息的处理方法、装置及存储介质
CN116681801A (zh) * 2023-06-16 2023-09-01 平安科技（深圳）有限公司 海报生成方法、装置、服务器以及存储介质
CN117314585A (zh) * 2023-10-27 2023-12-29 北京字跳网络技术有限公司 书籍信息处理方法、装置、设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160092512A1 (en) * 2014-09-26 2016-03-31 Kobo Inc. System and method for using book recognition to recommend content items for a user
CN113034213A (zh) * 2019-12-09 2021-06-25 腾讯科技（深圳）有限公司 漫画内容的显示方法、装置、设备及可读存储介质
CN114764726A (zh) * 2021-01-14 2022-07-19 腾讯科技（深圳）有限公司 推广信息的处理方法、装置及存储介质
CN116681801A (zh) * 2023-06-16 2023-09-01 平安科技（深圳）有限公司 海报生成方法、装置、服务器以及存储介质
CN117314585A (zh) * 2023-10-27 2023-12-29 北京字跳网络技术有限公司 书籍信息处理方法、装置、设备和存储介质

Also Published As

Publication number Publication date
CN120981800A (zh) 2025-11-18

Similar Documents

Publication Publication Date Title
US11776018B2 (en) Universal ad creative
WO2020215977A1 (zh) 用于展示信息的系统、方法及装置
CN112200614A (zh) 广告文本植入、展示方法及其相应的装置、设备、介质
CN114969556B (zh) 基于用户个性化的兴趣点呈现和交互方法、相关装置
US12401844B2 (en) Video processing method, video processing apparatus, and non-transitory computer-readable storage medium
CN120151561A (zh) 基于多智能体协作的视频生成方法、装置、智能体及设备
CN118898256A (zh) 内容生成方法、装置、电子设备、存储介质和程序产品
CN110909154A (zh) 摘要生成方法及装置
CN114840162B (zh) 首屏页面呈现方法、装置、电子设备和存储介质
US20250217419A1 (en) Information generation method and apparatus, and non-transitory computer-readable storage medium
WO2025189355A1 (zh) 推荐方法、装置、计算机可读存储介质和计算机程序产品
CN119849506A (zh) 基于大模型的评论展示方法、装置、设备、介质及智能体
CN113763009A (zh) 一种图片处理方法、图片跳转方法、装置、设备和介质
US20100192058A1 (en) Passive access by online ads to a landing zone
JP5597428B2 (ja) 情報を表示する端末、システム、方法及びプログラム
US20260051086A1 (en) Interaction method, non-transitory computer-readable storage medium and electronic device
TWI914926B (zh) 選擇與用戶提問有關的信息提供者的方法及系統
CN112288452A (zh) 广告预览方法、装置、电子设备及存储介质
US20250117602A1 (en) Large model-based recommendation method, electronic device and storage medium
US20260056982A1 (en) Method and system for dynamically generating artificial intelligence-based answer in which message of information provider is projected
US20220197946A1 (en) Method and system for implementing global index of arts practitioners
WO2025217911A1 (zh) 内容发布方法及装置、电子设备、存储介质、程序产品
WO2026000180A1 (zh) 信息处理方法、装置、电子设备、存储介质和程序产品
WO2026044780A1 (zh) 内容处理方法、装置、电子设备、介质、程序和程序产品
KR20250031122A (ko) 사용자 질의에 대한 정보 제공자를 선정하는 방법 및 시스템

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24928837

Country of ref document: EP

Kind code of ref document: A1