Information processing method and apparatus, device, medium, and program product

Abstract

The present application relates to the technical field of computers and discloses an information processing method, an information processing apparatus, and a computer device. The method comprises: displaying a reading interface of a text reading platform, the reading interface being used for a reader to read online or offline reading text; and in response to receiving a page turning event, displaying advertisement text of target advertisement content in the reading interface, the advertisement text having literature style features associated with the reading text. Such a method, apparatus, and device facilitate reduction of the visual obtrusiveness feeling of readers, improvement of receptivity of the readers to advertisement text, and increase of a rate of interaction between the readers and advertisement content corresponding to the advertisement text, thereby increasing the conversion rate of the advertisement content, and improving the information processing effect.

Description

Information processing methods, devices, equipment, media and program products

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on January 30, 2024, with application number 2024101328411 and application name “Information Processing Method, Information Processing Device and Computer Equipment”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of the present application relate to the field of computer technology, and in particular to information processing. Background Art

[0003] With the development of computer technology, the application of information processing is becoming more and more extensive. For example, through information processing, advertisements can be displayed in the reading interface of a reading platform.

[0004] In related technologies, when advertisements are needed, the advertising content provided by the advertiser is directly displayed within the reading interface of the reading platform. However, the advertising content provided by the advertiser has a low relevance to the text on the reading platform. Directly displaying the advertising content within the reading interface can easily increase the user's visual abruptness, reduce user interaction with the advertising content, and result in a low conversion rate for the advertising content and poor information processing effectiveness. Summary of the Invention

[0005] The embodiments of the present application provide an information processing method, an information processing device, and a computer device that can be used to improve the conversion rate of advertising content. The technical solution is as follows:

[0006] In one aspect, an embodiment of the present application provides an information processing method, the method comprising:

[0007] Displaying a reading interface of a text reading platform, wherein the reading interface is used for a reader to read online or offline reading texts;

[0008] In response to receiving a page turning event, an advertisement text of the target advertisement content is displayed in the reading interface, wherein the advertisement text has a literary style feature associated with the reading text.

[0009] In a possible implementation, the introduction text includes time-sensitive text, and the time-sensitive text is used to indicate the effective time of the target advertising content.

[0010] In a possible implementation, displaying the target advertising content in the reading interface includes: displaying the target advertising content and historical interaction information corresponding to the target advertising content in the reading interface.

[0011] In one possible implementation, the target text generation model is obtained by training an initial text generation model based on the difference between the predicted advertising text and the standard advertising text, and the predicted advertising text calls the initial text generation model to generate text based on sample input information, and the sample input information is determined based on sample materials of the sample advertising content and sample text feature information of the sample reading text; wherein, the standard advertising text has literary style features associated with the sample reading text.

[0012] In another aspect, an information processing device is provided, the device comprising:

[0013] A display module, configured to display a reading interface of a text reading platform, wherein the reading interface is used for a reader to read online or offline reading texts;

[0014] The display module is configured to display the advertisement text of the target advertisement content in the reading interface in response to receiving a page turning event, wherein the advertisement text has a literary style feature associated with the reading text.

[0015] On the other hand, a computer device is provided, comprising a processor and a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor so that the computer device implements any of the above-mentioned information processing methods.

[0016] On the other hand, a computer-readable storage medium is provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to enable a computer to implement any of the above-mentioned information processing methods.

[0017] On the other hand, a computer program or a computer program product is also provided, wherein the computer program or the computer program product comprises computer instructions, and the computer instructions are loaded and executed by a processor to enable a computer to implement any of the above-mentioned information processing methods.

[0018] The technical solutions provided by the embodiments of the present application bring at least the following beneficial effects:

[0019] The technical solution provided in the embodiment of the present application displays an advertising text corresponding to the advertising content in the reading interface when an advertisement needs to be displayed. The advertising text has a strong correlation with the reading text in literary style and can be better integrated into the reading scene, which is conducive to reducing the visual abruptness of the reading object, improving the reading object's acceptance of the advertising text, and improving the interaction rate between the reading object and the advertising content corresponding to the advertising text, thereby improving the conversion rate of the advertising content and improving the information processing effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] FIG1 is a schematic diagram of an implementation environment of an information processing method provided in an embodiment of the present application;

[0021] FIG2 is a flow chart of an information processing method provided in an embodiment of the present application;

[0022] FIG3 is a schematic diagram of a reading interface provided in an embodiment of the present application;

[0023] FIG4 is a schematic diagram of a reading interface provided in an embodiment of the present application;

[0024] FIG5 is a flowchart of an information processing method provided in an embodiment of the present application;

[0025] FIG6 is a schematic diagram of a reading interface provided in an embodiment of the present application;

[0026] 7 is a flowchart of a method for generating an advertisement text based on original material of target advertisement content and text feature information of a reading text by using a natural language model according to an embodiment of the present application;

[0027] FIG8 is a schematic diagram of an information processing device provided in an embodiment of the present application;

[0028] FIG9 is a schematic structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0030] Some terms involved in this application are explained.

[0031] Outer advertising form: the way and form of advertising presentation, which belongs to the style of advertising presented when it is "exposed" in the advertising chain. In similar businesses, the outer advertising form is constructed by the advertiser in a self-rendering manner, or the advertising intermediary platform uses a cooperative embedded SDK (Software Development Kit) to render according to the template style and then fill in the ad space. This application can be implemented based on SDK rendering (for example, designed by the advertising intermediary platform, SDK rendering, and adapted to the ad space), and is committed to making the outer form more visually attractive, interactive, and better integrated with the scene, so as to attract advertisers to migrate from self-rendering to SDK rendering in cooperation with the advertising platform in such a way as to achieve higher advertising effects and lower implementation / investment costs for developers.

[0032] Native advertising: Native advertising is a form of advertising that resembles other content on the platform it appears on, behaves like, and blends in with its surroundings. The goal of native advertising is to provide a user experience similar to that of other content on the platform, thereby increasing ad engagement and user engagement. Native advertising can appear on various media platforms, such as social media, news sites, and apps, and can include text, video, and audio.

[0033] Nativeness: Nativeness refers to the degree of visual and content similarity between an ad and other content on the platform it appears on, ensuring that users don't feel the ad is intrusive or out of place when browsing or using the platform. Achieving a sense of nativeness helps increase user acceptance and interactivity, thereby enhancing advertising effectiveness. In novel-related media, nativeness manifests itself in the integration of advertising and novel content, such as when the ad's content resonates with the novel's plot or when the ad's format aligns with the novel's literary style.

[0034] FIG1 is a schematic diagram showing an implementation environment of the information processing method provided by an embodiment of the present application, wherein the implementation environment may include: a terminal 11 and a server 12 .

[0035] Among them, the terminal 11 is installed with an application or web page corresponding to the text reading platform. The text reading platform can be any platform that supports reading text, and the application or web page corresponding to the text reading platform is a display form of the text reading platform. In the embodiment of the present application, the application or web page installed by the terminal 11 can display the reading interface of the text reading platform, so that the reading object can select the reading text in the reading interface for reading. The text reading platform can insert some advertising content into the reading text read by the reading object to promote certain activities or items. When it is necessary to insert advertising content, the terminal 11 can display the advertising text of the advertising content to be inserted in the reading interface. The advertising text and the reading text have a strong correlation in literary style, which is conducive to reducing the visual abruptness of the reading object and improving the conversion rate of the advertisement.

[0036] Server 12 provides backend services for the text reading platform. In one possible implementation, server 12 performs the primary computing tasks of the text reading platform, while terminal 11 performs secondary computing tasks. Alternatively, server 12 performs secondary computing tasks of the text reading platform, while terminal 11 performs the primary computing tasks. Alternatively, server 12 and terminal 11 utilize a distributed computing architecture to perform collaborative computing on the text reading platform.

[0037] In one possible implementation, the terminal 11 is any electronic product that can perform human-computer interaction with an interactive object through one or more methods such as a keyboard, touchpad, touch screen, remote control, voice interaction, or handwriting device, such as a PC (Personal Computer), a mobile phone, a smart phone, a PDA (Personal Digital Assistant), a wearable device, a handheld portable gaming device, a PPC (Pocket PC), a tablet computer, a smart car computer, a smart TV, a smart speaker, a car terminal, etc. The server 12 can be a single server, a server cluster consisting of multiple servers, or a cloud computing service center. The terminal 11 establishes a communication connection with the server 12 via a wired or wireless network.

[0038] Those skilled in the art should understand that the above-mentioned terminal 11 and server 12 are only examples. Other existing or future terminals or servers that are applicable to this application should also be included in the scope of protection of this application and are included here by reference.

[0039] An embodiment of the present application provides an information processing method, which can be applied to the implementation environment shown in Figure 1 above. The method is executed by a computer device, which can be a terminal for example. The embodiment of the present application takes the method being executed by a terminal as an example. For example, the method can be executed by the terminal or an application corresponding to a text reading platform installed on the terminal. As shown in Figure 2, the information processing method provided in the embodiment of the present application may include the following steps 201 and 202.

[0040] In step 201 , a reading interface of a text reading platform is displayed, where the reading interface is used for a reader to read online or offline text.

[0041] The reading interface refers to the front-end display interface of the text reading platform. The text reading platform can be any platform that supports reading text. In some embodiments, the text reading platform can be a platform maintained by the client, a platform maintained by the server, or a platform maintained by both the client and the server.

[0042] Exemplarily, the terminal displays the reading interface of the text reading platform based on the entry operation of the application or web page corresponding to the text reading platform. After the reading interface is displayed, the identification information (such as cover, name, etc.) of the candidate reading text can be displayed in the reading interface. Based on the selection operation of the reading object on the identification information of a certain reading text, the reading text is displayed in the reading interface for the reading object to read the reading text. The reading text can be an online reading text or an offline reading text, which is not limited in the embodiment of the present application. Among them, the offline reading text refers to a reading text that is stored locally in the terminal and can be read without connecting to the network. In some embodiments, the reading text can also be called a novel.

[0043] Exemplarily, the reading object reads the reading text in a manner that the reading object reads the reading text based on the reading text pages that are switched in sequence. Exemplarily, the reading text pages can be switched left and right, or up and down. In the case where the reading object reads the reading text based on the reading text pages that are switched in sequence, the reading text is displayed in a manner that: the first reading text page corresponding to the reading text is displayed in the reading interface, and starting from the next reading text page, in response to the switching operation of the previous reading text page, the next reading text page corresponding to the reading text is displayed in the reading interface until the entire reading text is displayed. Different reading text pages display different contents in the reading text, and the content displayed on the next reading text page is coherent with the content displayed on the previous reading text page.

[0044] The switching operation of the reading text page can refer to a sliding operation in the reading text page, or a triggering operation of a switching control in the reading text page, or a clicking operation in the reading text page, etc. The embodiment of the present application does not limit this.

[0045] In step 202 , in response to receiving a page turning event, an advertisement text of the target advertisement content is displayed in a reading interface, where the advertisement text has literary style features associated with the reading text.

[0046] If a page turning event is triggered by the reading object during the process of reading the text, the terminal obtains the page turning event and displays the advertisement text of the target advertisement content in the reading interface in response to the page turning event.

[0047] For example, a page-turning event is used to switch the target reading text page displayed in the reading interface. The target reading text page refers to the page of advertising text after which the advertising content is to be displayed. Which reading text pages in the reading text are the target reading text pages can be set based on experience or flexibly adjusted according to the application scenario, and this embodiment of the application is not limited to this.

[0048] In an exemplary embodiment, the target reading text page may refer to a reading text page that has not been updated within a reference time period, where the reference time period is set based on experience, for example, the reference time period is 1 minute.

[0049] In an exemplary embodiment, the target reading text page may refer to a reading text page whose corresponding reading progress meets the progress condition. The reading progress corresponding to the reading text page is used to measure the reading status of the reading object after reading the reading text page. The representation method of the reading progress corresponding to the reading text page can be set according to experience, or it can be flexibly adjusted according to the application scenario, and the embodiment of the present application does not limit this. Exemplarily, the reading progress corresponding to the reading text page can be represented by the number of reading text pages that have been switched after switching the reading text page. Exemplarily, the reading progress corresponding to the reading text page can also be represented by the ratio of the number of words in the content that has been read in the reading text to the total number of words in the reading text after reading the content in the reading text page.

[0050] The reading progress corresponding to the reading text page can meet the progress condition based on experience, or can be flexibly adjusted according to the application scenario, and the embodiments of the present application are not limited to this. For example, the specific situation in which the reading progress meets the progress condition is related to the representation method of the reading progress. Next, the specific situation in which the reading progress corresponding to the reading text page meets the progress condition is exemplified in combination with the representation method of the reading progress corresponding to the reading text page.

[0051] Exemplarily, for the case where the reading progress corresponding to the reading text page is represented by the number of reading text pages that have been switched after switching the reading text page, the reading progress corresponding to the reading text page meets the progress condition and can refer to the number of reading text pages that have been switched after switching the reading text page being an integer multiple of a reference number. The reference number can be set based on experience, or it can be flexibly adjusted according to the type of reading text, etc., and the embodiment of the present application is not limited to this. For example, the reference number can be 10, or it can be 15, etc. In this case, it is possible to quickly and conveniently determine whether the reading progress corresponding to the reading text page meets the progress condition by determining whether the number of reading text pages that have been switched after switching the reading text page is an integer multiple of the reference number, thereby improving the efficiency of determination. In addition, this case can ensure that the advertising text is displayed once every reference number of reading text pages, so that the advertising text is displayed at a fixed frequency (adload), thereby improving the acceptance of the advertising text by the reading object, thereby improving the interaction rate between the reading object and the advertising content corresponding to the advertising text, and improving the conversion rate of the advertising content.

[0052] For example, when the reading progress corresponding to a reading text page is represented by the number of reading text pages switched after the reading text page is switched, the reading progress corresponding to the reading text page meeting the progress condition may also mean that the number of reading text pages switched after the reading text page is switched is any number among candidate numbers. The candidate number refers to a preset number of advertisement texts to be displayed. The candidate number can be set based on experience or flexibly adjusted based on the chapter settings of the reading text.

[0053] For example, if the reading progress corresponding to a reading text page is represented by the ratio of the number of words in the content read in the reading text to the total number of words in the reading text after the content in the reading text page is read, the reading progress corresponding to the reading text page meeting the progress condition may mean that after the content in the reading text page is read, the ratio of the number of words in the content read in the reading text to the total number of words in the reading text is any ratio among candidate ratios. The candidate ratio refers to a preset ratio for displaying advertising text, and the candidate ratio can be set based on experience or flexibly adjusted based on the chapter settings of the reading text.

[0054] It is understandable that by reasonably setting the progress conditions, the advertising text can be displayed at the end of a complete content paragraph or a complete chapter in the reading text, so as to reduce the abruptness caused by the display of the advertising text.

[0055] Regardless of which of the above situations the target reading text page is, after receiving a page-turning event for switching the target reading text page, the advertisement text of the target advertisement content is displayed in the reading interface. The target advertisement content refers to the advertisement content inserted by the text reading platform into the reading text. The target advertisement content is the advertisement content provided by the advertiser to be displayed in the reading text of the text reading platform. The target advertisement content can be flexibly set by the text reading platform based on the type of reading text and the reading progress, and can also be flexibly adjusted according to the advertisement display requirements. This embodiment of the present application does not limit this.

[0056] It should be noted that the reading text is the text written by the author, and the target advertising content is the content provided by the advertiser. The reading text and the target advertising content are independent of each other. That is, the target advertising content is not the advertising content embedded in the reading text by the author, but the advertising content inserted and displayed by the text reading platform during the reading process of the reading text according to the needs of the advertiser. This type of advertising content is highly flexible and can be flexibly changed according to needs.

[0057] When it is necessary to insert target advertising content, the embodiment of the present application displays the advertising text of the target advertising content in the reading interface. The advertising text is used to introduce the target advertising content, that is, the reader can understand the target advertising content by reading the advertising text. The advertising text has literary style characteristics associated with the reading text. Compared with directly displaying the advertising content, displaying the advertising text that is associated with the reading text in literary style is conducive to reducing the visual abruptness of the reading object, improving the reader's acceptance of the advertising text, and increasing the interaction rate between the reader and the advertising content corresponding to the advertising text, thereby improving the conversion rate of the advertising content and improving the information processing effect.

[0058] The literary style features of an advertising text are features that reflect the text's literary style. Literary style refers to a style unique to literature. For example, literary style can include dialogue style, scene description style, language style, and sentence structure style. The literary style features of an advertising text can include the characteristics of the characters in the advertising text, the tone of the dialogue in the advertising text, the sentence patterns in the dialogue in the advertising text, the characteristics of the scenes described in the advertising text, the language style types of the advertising text, and the sentence structure types of the advertising text. The literary style features of an advertising text that are associated with a reading text refer to the literary style features of the advertising text being determined by considering the reading text, thereby matching the literary style of the advertising text with the reading text, making the advertising text appear to be part of the reading text in terms of literary style, and enhancing the relevance of the advertising text to the reading text.

[0059] In an exemplary embodiment, the advertisement text having the literary style features associated with the reading text may mean that the advertisement text has the literary style features associated with the entire reading text, so that the advertisement text matches the entire reading text in terms of literary style.

[0060] In an exemplary embodiment, the advertisement text having literary style features associated with the reading text may also mean that the advertisement text has literary style features associated with the currently displayed content of the reading text, so that the advertisement text matches the currently displayed content of the reading text in literary style.

[0061] Of course, in some embodiments, the advertising text having literary style features associated with the reading text may also mean that the advertising text has literary style features associated with the reading text as a whole, and the advertising text has literary style features associated with the content currently displayed in the reading text, so that the advertising text not only matches the overall aspect of the reading text in literary style, but also matches the literary style of the content currently displayed in the reading text, thereby fully improving the relevance of the advertising text to the reading text from both the overall aspect and the currently displayed content.

[0062] Exemplarily, the currently displayed content of the reading text involved above is determined based on the target reading text corresponding to the page turning event, and the relationship between the currently displayed content and the content of the target reading text can be flexibly set according to demand. Exemplarily, the currently displayed content includes the content of the last sentence in the target reading text page, the last paragraph in the target reading text page, the entire content in the target reading text page, the content of the chapter corresponding to the target reading text page, or the entire content from the first sentence in the reading text to the last sentence in the target reading text page. The currently displayed content of the reading text can reflect the real-time reading progress of the reading object. In the case where the advertising text has literary style features associated with the currently displayed content of the reading text, it can improve the correlation between the advertising text and the real-time reading progress of the reading object, further improve the reading object's acceptance of the advertising text, and improve the interaction rate between the reading object and the advertising content corresponding to the advertising text, thereby improving the conversion rate of the advertising content and improving the information processing effect.

[0063] For example, different reading texts have different literary styles. Because the target advertising content's advertising text has literary style characteristics associated with the reading text being read by the target audience, and different reading texts have different literary styles, the target advertising content has different advertising texts corresponding to different reading texts, each with different literary style characteristics. In other words, for the same advertising content, the advertising text displayed in different reading texts has different literary style characteristics, providing greater flexibility in the display of the advertising text, thereby facilitating improved display effects of the advertising text.

[0064] The specific situation in which the advertising text has literary style characteristics associated with the reading text can be set based on experience or flexibly adjusted according to needs, and the present embodiment does not limit this. Next, the situation in which the advertising text has literary style characteristics associated with the reading text is exemplified.

[0065] In an exemplary embodiment, the advertisement text having the literary style characteristics associated with the reading text may include at least one of the following cases 1 to 5:

[0066] Case 1: The advertisement text includes a first text in a dialogue form, and characters in the dialogue in the first text are associated with characters involved in the content currently displayed by the reading text.

[0067] The embodiment of the present application is described by taking the case where at least one person is involved in the content currently displayed in the reading text as an example. The person involved in the content currently displayed in the reading text refers to the person whose name or nickname appears in the content currently displayed in the reading text.

[0068] The association between the character in the first text and the character involved in the content currently displayed by the reading text may mean that the character in the first text is any character involved in the content currently displayed by the reading text, or it may mean that the character in the first text is a character having an association relationship with any character involved in the content currently displayed by the reading text. For example, the association relationship may refer to a kinship relationship, a hostile relationship, a friendship relationship, etc.

[0069] In this case 1, by constructing the advertising text using the dialogues of the characters involved in the content currently displayed by the reading text, it is beneficial to improve the relevance of the advertising text to the content currently displayed by the reading text in terms of the dialogue characters, reduce the visual abruptness brought to the reading object by the display of the advertising text, improve the reading object's acceptance of the advertising text, and increase the interaction rate between the reading object and the advertising content corresponding to the advertising text, thereby improving the conversion rate of the advertising content and improving the information processing effect.

[0070] For example, in this case 1, the advertisement text having literary style features associated with the reading text may also include: the dialogue tone of the characters in the first text matches the personality of the characters described in the reading text.

[0071] The tone of dialogue refers to the tone used by characters when they are talking to each other, and the tone of dialogue can be reflected by some modal particles. For example, if the character in the dialogue in the first text is any character involved in the reading text, the reading text will describe the character's personality, for example, the character's personality is gentle, harsh, etc. The tone of dialogue between the characters in the dialogue in the first text and the character's personality described in the reading text match means that the tone of dialogue between the characters in the dialogue in the first text is the tone commonly used by characters with the personality described in the reading text. For example, if the character of the character in the dialogue in the first text is gentle, then the tone of dialogue between the characters in the dialogue in the first text is gentle; if the character of the character in the dialogue in the first text is harsh, then the tone of dialogue between the characters in the dialogue in the first text is harsh.

[0072] By constructing advertising texts using dialogues between characters in the reading text that have a conversational tone that matches their personalities, it is beneficial to improve the relevance of the advertising text to the content currently displayed in the reading text in terms of the conversational tone, reduce the visual abruptness brought to the readers by the displayed advertising text, improve the readers' acceptance of the advertising text, and increase the interaction rate between the readers and the advertising content corresponding to the advertising text, thereby improving the conversion rate of the advertising content.

[0073] Case 2: The advertisement text includes a first text in a dialogue form, and the dialogue sentence pattern of the first text matches the dialogue sentence pattern in the content currently displayed by the reading text.

[0074] The dialogue sentence structure indicates the order of character descriptions and dialogue content. The character description describes the character's name, as well as their expressions, actions, and other aspects of the dialogue. For example, a dialogue sentence structure can have the character description first, followed by the dialogue content (see Dialogue 1 below); it can also have the dialogue content first, followed by the character description (see Dialogue 2 below); or it can have the character description in the middle, with the dialogue content placed both before and after the character description (see Dialogue 3 below).

[0075] Dialogue 1: Character A said happily: "I won the prize!"

[0076] Dialogue 2: "I won the prize!" Character A said happily.

[0077] Dialogue 3: "Hahaha." Character A said happily, "I won the prize!"

[0078] The matching of the dialogue sentence patterns of the first text with the dialogue sentence patterns in the content currently displayed by the reading text may mean that the dialogue sentence patterns of the first text are consistent with the dialogue sentence patterns of any dialogue in the content currently displayed by the reading text, or it may mean that the dialogue sentence patterns of the first text are the most frequently used dialogue sentence patterns in all the dialogues in the content currently displayed by the reading text, etc.

[0079] In this case 2, by constructing the advertising text using dialogue sentences that match the dialogue sentences in the content currently displayed in the reading text, it is beneficial to improve the relevance of the advertising text to the content currently displayed in the reading text in terms of dialogue sentences, reduce the visual abruptness brought to the reading object by the display of the advertising text, improve the reading object's acceptance of the advertising text, and increase the interaction rate between the reading object and the advertising content corresponding to the advertising text, thereby improving the conversion rate of the advertising content and improving the information processing effect.

[0080] Case 3: The advertisement text includes a second text in the form of a scene description, and the scene described in the second text is associated with a scene involved in the content currently displayed in the reading text.

[0081] The scene description form is a narrative form, that is, a non-dialogue form.

[0082] In an exemplary embodiment, the association of the scene described in the second text with the scene involved in the content currently displayed in the reading text may mean that the scene described in the second text is a further detailed description of the scene involved in the content currently displayed in the reading text; or it may mean that the type of the scene described in the second text is the same as the type of the scene involved in the content currently displayed in the reading text, for example, the type of scene may be a war scene, an everyday life scene, etc. In some embodiments, a scene may also be referred to as a plot, a storyline, etc.

[0083] In this case 3, constructing the advertising text by describing the scenes related to the scenes involved in the content currently displayed in the reading text is conducive to improving the relevance of the advertising text to the content currently displayed in the reading text from the scene aspect, reducing the visual abruptness brought to the reading object by the display of the advertising text, improving the reading object's acceptance of the advertising text, and increasing the interaction rate between the reading object and the advertising content corresponding to the advertising text, thereby improving the conversion rate of the advertising content and improving the information processing effect.

[0084] Case 4: The language style type of the advertising text is consistent with the language style type of the reading text.

[0085] The language style refers to the writing style of the text content. For example, the language style types may include humorous language style, domineering language style, aloof language style, fresh and natural language style, etc.

[0086] In this case 4, constructing the advertising text using a language style type that is consistent with the language style type of the reading text is beneficial to improving the relevance of the advertising text to the content currently displayed in the reading text in terms of language style, reducing the visual abruptness brought to the reading object by the display of the advertising text, improving the reading object's acceptance of the advertising text, and increasing the interaction rate between the reading object and the advertising content corresponding to the advertising text, thereby improving the conversion rate of the advertising content and improving the information processing effect.

[0087] Case 5: The sentence structure of the advertising text is the same as that of the reading text.

[0088] Sentence pattern refers to the form of sentences in a text. For example, sentence pattern can refer to the pattern of a complete sentence, such as a parallel sentence or a rhyming sentence. Another example is the pattern of a scattered sentence, which is a sentence of varying lengths. Another example is the pattern of a sentence that combines a complete sentence with scattered sentences.

[0089] In this case 5, by constructing the advertising text using sentence patterns consistent with those of the reading text, it is beneficial to improve the relevance of the advertising text to the content currently displayed in the reading text in terms of sentence patterns, reduce the visual abruptness brought to the reading object by the display of the advertising text, improve the reading object's acceptance of the advertising text, and increase the interaction rate between the reading object and the advertising content corresponding to the advertising text, thereby improving the conversion rate of the advertising content and improving the information processing effect.

[0090] The above cases 1 to 3 are possible implementations when the advertising text has literary style features associated with the content currently displayed in the reading text. The above cases 4 and 5 are possible implementations when the advertising text has literary style features associated with the reading text as a whole. The above cases 1 to 5 can be combined arbitrarily, and the embodiments of the present application are not limited to this. It should be noted that the above cases 1 to 5 are only exemplary descriptions, and the embodiments of the present application are not limited to this. In some embodiments, the advertising text having literary style features associated with the reading text can also be other cases, for example, the characters in the dialogue in the advertising text are any characters involved in the reading text, the dialogue sentence pattern in the advertising text is the most frequently used dialogue sentence pattern in all the dialogues in the reading text, etc.

[0091] Cases 1 through 5 above describe the advertising text from the perspective of having literary stylistic features associated with the reading text. In an exemplary embodiment, in addition to having literary stylistic features associated with the reading text, the advertising text also needs to be able to introduce the target advertising content, so that the reader can understand the target advertising content to be displayed based on the advertising text.

[0092] In an exemplary embodiment, the advertising text includes an introductory text corresponding to the target advertising content, and the introductory text is used to introduce the target advertising content. Exemplarily, the introductory text may refer to the promotional copy in the target advertising content, or may refer to a text obtained by adjusting the promotional copy in the target advertising content. For example, assuming that the target advertising content is used to promote an event on platform A, and the promotional copy in the target advertising content is "Discounts for purchases over 100 yuan will be reduced to 20 yuan, and there will be a shopping spree at 8 pm every night during Double Eleven", the promotional copy may be used directly as the introductory text. Exemplarily, the introductory text may be part of the first or second text of the above introduction, or it may be independent of the first and second texts, and this embodiment of the present application does not limit this.

[0093] In an exemplary embodiment, the introductory text is displayed with a highlight mark on the page displaying the advertisement text. The highlight mark can be set based on experience, as long as the display effect of the introductory text is different from that of other text in the advertisement text. For example, the highlight mark can be a cursor selection mark, or a rectangular selection mark, etc.

[0094] Highlighting the mark can attract more attention from readers, thereby attracting readers to understand the inserted target advertising content by paying attention to the introductory text in the advertising text, improving readers' acceptance of the target advertising content, and further improving readers' interaction rate with the target advertising content and improving the conversion rate of the target advertising content.

[0095] In an exemplary embodiment, the introductory text includes a time-sensitive text, which is used to indicate the effective time of the target advertising content. The embodiment of the present application does not limit the type of time-sensitive text, and can be flexibly set according to the type of target advertising content. For example, the time-sensitive text can be a countdown text indicating the remaining effective time of the target advertising content, or a time-limited text that directly indicates the effective time of the target advertising content, etc. By setting the time-sensitive text in the introductory text, the timeliness of the target advertising content can be emphasized in the introductory text, thereby stimulating the reader's sense of urgency, prompting the reader to participate in the activities promoted by the target advertising content more quickly by interacting with the target advertising content, and improving the conversion rate of the target advertising content.

[0096] In one possible implementation, in addition to displaying the ad text, a prompt element is also displayed in the reading interface. This prompt element indicates that the text displayed on the current page is an ad text. By displaying this prompt element, readers can intuitively distinguish between the ad text and the reading text, given the literary style of the ad text and the reading text, ensuring that readers can accurately identify the ad text and improving their interactive experience.

[0097] The type and form of the prompt element can be set based on experience or flexibly adjusted according to needs, and the embodiments of the present application do not limit this. In an exemplary embodiment, the prompt element includes at least one prompt sub-element, and different prompt sub-elements are used to indicate that the text displayed on the current page is an advertisement text in different ways (e.g., different text content, different forms, etc.).

[0098] Exemplarily, the prompt element includes at least one of prompt text, a prompt icon, or a prompt page corner. The prompt text uses text to indicate that the text displayed on the current page is an advertisement. The text of the prompt text can be flexibly set based on experience. For example, the text of the prompt text can be "Relaxing Moment." The prompt icon uses an icon to indicate that the text displayed on the current page is an advertisement. For example, the prompt icon is an icon labeled with the word "Advertisement."

[0099] The page corner indication is located within the area of ​​any corner of the current page, and the page corner indication is in a folded state. In other words, the folded state of the page corner indication indicates that the text displayed on the current page is advertising text. The area within which the page corner indication is located can be flexibly set according to needs. For example, the page corner indication can be located within the area within the lower right corner of the current page; or the page corner indication can be located within the area within the upper right corner of the current page.

[0100] In an exemplary embodiment, the display style of the advertisement text in the reading interface matches the display style of the reading text in the reading interface. Display style refers to the style used to display text. Exemplarily, the display style includes but is not limited to the text display background, text display font type, text display font size, text display font color, text display line spacing, etc. Matching the display style of the advertisement text with the display style of the reading text can mean that the display style of the advertisement text is consistent with the display style of the reading text, or it can mean that the difference between the display style of the advertisement text and the display style of the reading text is less than a difference threshold, and the difference threshold is set based on experience.

[0101] By matching the display style of the advertising text with the display style of the reading text, the advertising text can simulate the UI (User Interface) style of the reading text, so that the visual effect of the advertising text converges with the visual effect of the reading text, making the advertising text visually consistent with the reading text. By improving the integration of the advertising text and the reading environment in the visual experience, the visual abruptness brought by the advertising text is reduced, the interaction rate between the reading object and the target advertising content is increased, and the conversion rate of the target advertising content is thereby increased.

[0102] For example, if the display style of the advertisement text matches the display style of the reading text, it can be considered that the advertisement text is displayed using a customized media style. The customized media style is a fixed UI style preset according to the display style of the reading text.

[0103] If the display style of the advertising text matches the display style of the reading text, then before displaying the advertising text, it is necessary to first determine the display style of the advertising text, for example, use the display style of the reading text as the display style of the advertising text, or for another example, fine-tune the display style of the reading text, and use the fine-tuned display style as the display style of the advertising text. The method of fine-tuning the display style of the reading text can be set according to experience, or flexibly adjusted according to demand, and the embodiments of the present application are not limited to this. For example, fine-tuning the display style of the reading text can refer to fine-tuning the brightness of the text display background of the reading text, or it can refer to fine-tuning the text display font line spacing of the reading text, etc.

[0104] In some embodiments, in addition to displaying the ad text in the reading interface, an ad image or ad video may also be displayed on the same page. The ad image may be an image obtained by editing the original image in the target ad content based on the literary style of the reading text, and the ad video may be a video obtained by editing the original video in the target ad content based on the literary style of the reading text. By displaying ad images or ad videos, the reader can be more clearly prompted from multiple dimensions that the target ad content is about to be displayed, thereby reducing the reader's resistance, increasing the reader's interaction rate with the target ad content, and improving the conversion rate of the target ad content.

[0105] For example, the reading interface may be as shown in FIG3. As shown in FIG3 (1), before the advertisement text is displayed, the reading interface displays the reading text. The reading object can switch the reading text page by sliding from right to left, as shown in FIG3 (2). If a page turning event for switching the target reading text page displayed in the reading text is received, the target reading text page is switched to the page displaying the advertisement text. After the page is completely switched to the page displaying the advertisement text, the reading interface is shown in FIG3 (3).

[0106] In (3) of FIG3 , an advertisement text is displayed in the reading interface. The display style of the advertisement text is consistent with the display style of the reading text, and the literary style of the advertisement text is associated with the literary style of the reading text. The advertisement text includes an introduction text 311 corresponding to the target advertisement content. The content of the introduction text 311 is "Discounts are available for purchases over 100 yuan, and there will be a shopping spree at 8 o'clock every night during the Double Eleven period." The introduction text 311 has a cursor selection mark (i.e., a highlight display mark). Continuing to refer to (3) of FIG3 , on the page displaying the advertisement text, three prompt sub-elements are also displayed, namely, a prompt icon 312 with the text "Advertisement", a prompt text 313 with the text "Relaxing Moment", and a prompt page corner 314 located in the area of ​​the lower right corner of the page displaying the advertisement text and in a folded state.

[0107] Continuing to refer to (3) in FIG3 , the advertisement text includes not only the introduction text 311 corresponding to the target advertisement content, but also the name of the advertiser (Platform A) and other information (saying that the bystanders were shocked when they heard it and whispered to each other, “Is it true?”, and that a fortune teller counted with his fingers and said, “Today is a good day for trading, and the calculation is quite powerful”, and everyone who heard it was moved).

[0108] It should be understood that (3) in FIG3 is only an exemplary example of a page displaying advertisement text, and the embodiments of the present application are not limited thereto. For example, a page displaying advertisement text may also be shown in FIG4 . Referring to (1) in FIG4 , on the page displaying advertisement text, a rectangular box check mark may be used to mark the introduction text; referring to (2) in FIG4 , on the page displaying advertisement text, only a prompt sub-element, a prompt icon with the word “advertisement”, is displayed.

[0109] Before displaying the advertising text, it is necessary to obtain the advertising text first. The method for obtaining the advertising text can be flexibly set according to needs. In one possible implementation method, the advertising text is generated by a natural language model based on the original material of the target advertising content and the text feature information of the reading text. The natural language model is a model with a text generation function. The text feature information of the reading text is used to characterize the reading text and can reflect the literary style of the reading text. The process of generating the advertising text based on the original material of the target advertising content and the text feature information of the reading text through the natural language model can be implemented by the terminal or by the server, and this embodiment of the present application does not limit this. The process of generating the advertising text based on the original material of the target advertising content and the text feature information of the reading text through the natural language model is detailed in the embodiment shown in Figure 7 and will not be repeated here.

[0110] In another implementation, the advertising text is obtained from the target platform by calling the interface of the target platform, wherein the target platform is used to generate the advertising text based on the original material of the target advertising content and the text feature information of the reading text. The target platform is an intermediary platform between the advertiser and the text reading platform, that is, the target platform can obtain the original material of the target advertising content from the advertiser, and can also obtain the text feature information of the reading text from the text reading platform. The target platform can generate the advertising text based on the obtained original material of the target advertising content and the text feature information of the reading text. After obtaining the advertising text, the target platform encapsulates the advertising text in the SDK and provides the terminal with the SDK interface (such as API (Application Programming Interface)). The terminal calls the interface of the target platform to obtain the advertising text from the target platform.

[0111] Exemplarily, the target platform may provide the advertisement text in the form of providing the content of the advertisement text and the display style of the advertisement text. In this case, before displaying the advertisement text, the terminal needs to render the page according to the obtained content and display style of the advertisement text, and then display the rendered page to display the advertisement text. Exemplarily, the target platform may provide the advertisement text in the form of providing data corresponding to a page rendered according to the display style of the advertisement text and the content of the advertisement text. In this case, the terminal does not need to render again and can directly load the data corresponding to the page provided by the target platform to display the advertisement text.

[0112] In another implementation, the advertisement text is obtained based on a text generation template. Exemplarily, the process of obtaining the advertisement text based on the text generation template includes: obtaining the text generation template, the text generation template including a text area to be filled and fixed text, the fixed text having literary style characteristics associated with the reading text; determining filler text based on the target advertisement content; filling the text area to be filled in the text generation template with the filler text, and using the filled text generation template as the advertisement text.

[0113] The text generation template includes an area to be filled and fixed text with literary style characteristics associated with the reading text. The area to be filled is used to fill in information related to the target advertising content to ensure that the generated advertising text can serve as an introduction to the target advertising content.

[0114] For example, the process of determining filler text based on the target advertisement content may include using the name of the advertiser corresponding to the target advertisement content and the introduction text corresponding to the target advertisement content as filler text. After the filler text is used to fill the text area to be filled in the text generation template, the advertisement text is obtained.

[0115] The text generation template can be pre-set according to the needs of the advertising text. In an exemplary embodiment, a plurality of text generation templates corresponding to literary styles can be set, and the text generation template corresponding to the literary style of the reading text is selected from the plurality of text generation templates corresponding to literary styles to generate the advertising text.

[0116] In an exemplary embodiment, the content of the advertising text matches the object data of the reading object. The object data of the reading object refers to data related to the reading object, and the type of object data can be set based on experience, and can also be flexibly adjusted according to demand. Exemplarily, the object data may include but is not limited to the reading object's age, gender, interests and hobbies, consumption habits, reading preferences, historical interactions with advertising content, etc. It should be noted that the object data can be obtained from the reading object's registration information, browsing history, purchase history, etc. with the reading object's authorization. Exemplarily, a portrait of the reading object can be constructed based on the reading object's object data. The portrait of the reading object is a way to express the image of the reading object in a concrete way through a label.

[0117] If the content of the advertising text matches the object data of the reader, it is possible to generate advertising texts that are tailored to each reader, ensuring that the content of the advertising text is what the reader is interested in, thereby further increasing the reader's attention to the advertising text, increasing the reader's interaction rate with the target advertising content corresponding to the advertising text, and increasing the conversion rate of the target advertising content.

[0118] In an exemplary embodiment, as shown in FIG5 , after displaying the advertisement text, the method further includes:

[0119] In step 203, in response to the display of the advertisement text meeting the display requirement, the target advertisement content is displayed in the reading interface.

[0120] After displaying the ad text, a determination is made as to whether the display of the ad text meets the display requirements. If the display of the ad text meets the display requirements, the target ad content is displayed in the reading interface. Whether the display of the ad text meets the display requirements indicates that the target ad content needs to be displayed in the reading interface. Whether the display of the ad text meets the display requirements can be set based on experience or flexibly adjusted based on the type of text being read, and is not limited in this embodiment of the present application.

[0121] In one possible implementation, the display of the advertising text meets the display requirements, including: the display time of the advertising text reaches a time threshold, or a switching operation for the advertising text is obtained. The time threshold is set based on experience, or is flexibly adjusted according to the type of reading text, etc., and the embodiments of the present application do not limit this. For example, the time threshold can be 2 seconds, or 3 seconds, etc. The switching operation for the advertising text can refer to a sliding operation generated by the reading object on the page displaying the advertising text, or it can refer to the triggering operation of the switching control on the page displaying the advertising text by the reading object, etc. It supports both automatic control of whether to display the target advertising content according to the display time, and control of whether to display the target advertising content according to the operation of the reading object. The method of controlling whether to display the target advertising content is relatively comprehensive, which can not only meet the needs of the reading object, but also avoid the display time of the advertising text being too long, thereby ensuring the display effect of the target advertising content, improving the interaction rate of the reading object with the target advertising content, and thus improving the conversion rate of the target advertising content.

[0122] When the display of the advertising text meets the display requirements, the target advertising content is displayed in the reading interface. Exemplarily, displaying the target advertising content in the reading interface refers to displaying the original material of the target advertising content in the reading interface. That is to say, when displaying the target advertising content, the original material provided by the advertiser will not be changed to ensure the complete exposure of the original material of the target advertising content provided by the advertiser, and meet the advertiser's display requirements for the target advertising content. The original material of the target advertising content may include at least one of text, pictures, and videos. Exemplarily, before displaying the target advertising content, it is necessary to first obtain the original material of the target advertising content. The terminal can extract the original material of the target advertising content from the local storage, or obtain the original material of the target advertising content from the server or the target platform or the advertiser, and the embodiments of the present application are not limited to this.

[0123] In one possible implementation, the process of displaying target advertising content in a reading interface includes: popping up an advertising content display area on a page displaying advertising text; and displaying the target advertising content in the advertising content display area. When the target advertising content is needed, the target advertising content is displayed in the advertising content display area on the page displaying the advertising text. This allows the target advertising content to overlay the page displaying the advertising text, thereby visually demonstrating the relevance between the advertising text and the target advertising content, improving the reader's acceptance of the target advertising content, and thereby increasing the reader's interaction rate with the target advertising content, thereby improving the target advertising content's conversion rate.

[0124] In an exemplary embodiment, a pop-up ad content display location on a page displaying ad text is implemented by causing the ad content display location to pop up on the page displaying ad text through an animation effect. The animation effect matches the text being read. In other words, by causing the ad content display location to pop up on the page displaying ad text through an animation effect that matches the text being read, the pop-up effect of the ad content display location can be more integrated with the reading context of the text, reducing the visual abruptness of the pop-up ad content display location for the reader, increasing the reader's acceptance of the target ad content, and thereby increasing the reader's interaction rate with the target ad content and the conversion rate of the target ad content.

[0125] For example, matching the animation effect with the reading text may refer to matching the animation effect with the text type of the reading text. The terminal may pre-store or obtain from a server a correspondence between text types and animation effects, and may search for the animation effect corresponding to the text type of the reading text from the correspondence, and use the found animation effect as the animation effect used in the pop-up advertisement content display position.

[0126] Exemplarily, the matching of animation effects with reading text may also refer to the matching of animation effects with the currently displayed content of the reading text. The terminal may input the currently displayed content of the reading text into the animation effect determination model, and use the animation effect output by the animation effect determination model as the animation effect utilized by the pop-up advertising content display position. The animation effect determination model has the function of determining the probabilities corresponding to a plurality of candidate animation effects according to the input content, and outputting the animation effect with the highest probability. The animation effect determination model can be obtained through supervised training using sample content and the standard animation effect corresponding to the sample content.

[0127] In another possible implementation, the process of displaying the target advertising content in the reading interface includes: hiding the advertising text and displaying the target advertising content at a designated location on the reading interface. The designated location can be set based on experience or flexibly adjusted according to actual needs, and is not limited in this embodiment of the present application. For example, the designated location can be the center of the reading interface, the bottom of the reading interface, or the top of the reading interface.

[0128] For example, in addition to displaying the original material of the target advertising content, the reading interface also displays interactive controls for readers to interact with the target advertising content. The interactive controls can be in the form of icons, buttons, etc. In some embodiments, the interactive controls can also be called call-to-action buttons. After displaying the interactive controls, it also includes: responding to the triggering operation of the interactive controls, jumping to the application or web page associated with the target advertising content. When providing the target advertising content, the advertiser can also provide the application or web page associated with the target advertising content, so that the terminal can directly jump to the application or web page associated with the target advertising content after obtaining the triggering operation of the interactive controls.

[0129] In one possible implementation, similar to the page displaying the ad text, the page displaying the target ad content also has a folded-over corner for a visual reminder. For example, the folded corners of the page displaying the ad text and the page displaying the target ad content are located in the same position to enhance the visual effect.

[0130] For example, referring to FIG6 , when the display of the ad text meets the display requirements, the target ad content and interactive controls are displayed in ad content display position 600 on the page displaying the ad text. The target ad content displayed in ad content display position 600 includes original materials such as images, text, and the advertiser's name. The interactive controls are labeled "Click to learn more."

[0131] In one possible implementation, in addition to displaying the target ad content, the reading interface also displays historical interaction information corresponding to the target ad content. This historical interaction information indicates the historical interactions between the interacting audience and the target ad content. Therefore, incorporating this social element into the display of the target ad content can enhance the credibility of the target ad content, increase the likelihood of readers interacting with the target ad content, and improve the conversion rate of the target ad content.

[0132] For example, the historical interaction information corresponding to the target advertising content may include the avatars and nicknames of the interacting parties who have interacted with the target advertising content, their evaluations of the target advertising content, and their recommendations for the target advertising content. For example, when displaying historical interaction information, relatively brief information such as the interacting parties' avatars and nicknames may be displayed first. After this brief information is triggered, information such as the interacting parties' evaluations and recommendations may be displayed, thereby avoiding excessive information from interfering with the target advertising content and improving the display effect.

[0133] In an exemplary embodiment, after displaying the ad text, data on the reader's interaction with the personalized ad text, such as click-through rate and dwell time, can also be collected. By analyzing this data, the text generation model and display strategy can be continuously optimized to increase the ad's appeal and conversion rate. Furthermore, this data can be fed back to advertisers and text reading platforms to help them understand the effectiveness of their ads and optimize their advertising strategies.

[0134] The information processing method provided in the embodiment of the present application is an advertising display method for optimizing the outer layer advertising form. By first displaying the advertising text with literary style characteristics associated with the reading text and then displaying the target advertising content, the native sense of the target advertising content can be increased, making the target advertising content a native advertising content, thereby creating an advertisement with a strong sense of plot and scene. Reading objects in the reading scene are more sensitive to text and plot, so creating advertisements with a strong sense of plot and scene can make the advertisements more native. Advertisements with a strong sense of nativeness can reduce the resistance of the reading objects, stimulate the reading interest of the reading objects, increase the reading objects' acceptance of the advertisements, better attract the reading objects, and guide the reading objects to actively interact with the advertising content, thereby increasing the click-through rate and conversion rate of the advertisements. In addition, the display method of displaying the advertising text first and then the advertising content is better integrated with the scene and has a stronger sense of fun, which can help advertisers better convey information, attract the attention of the reading objects, and increase the conversion rate of advertisements.

[0135] The method provided in the embodiment of the present application can generate a certain template or a thousand-face advertisement by understanding the literary style of the reading text, creating a more immersive and distinctive advertising form in the reading scene, which can improve the overall interaction, feedback and display effect of the advertisement, so that the reader can encounter more interesting and more scene-appropriate advertisements in the process of immersing in the reading scene, and promote the active interaction between the reader and the advertisement. Based on the portrait of the reading object and the key information of the advertisement content, personalized advertising text is generated for the characteristics of different reading objects. This kind of advertising text with a thousand faces can better meet the needs and interests of the reading object, thereby improving the attractiveness and interactivity of the advertisement.

[0136] The target advertising content displayed in this application can be called a soft copy advertisement. After sliding open the ad page, readers who are accustomed to reading text from left to right and top to bottom will first see the ad text (also known as ad copy), and then see the target ad content (such as ad images, ad videos, etc.) and buttons (such as CTA (Call to Action) buttons). Borrowing the form of reading text, providing a virtual plot, guiding readers to interact with the target ad content, can play the role of using content to attract readers who are currently skimming ten lines, using native eye-catching methods to attract readers' attention, and improve the conversion rate of the target ad content.

[0137] In an embodiment of the present application, when it is necessary to display an advertisement, an advertisement text corresponding to the advertisement content is displayed in the reading interface. The advertisement text has a strong correlation with the reading text in literary style and can be better integrated into the reading scene, which is conducive to reducing the visual abruptness of the reading object, improving the reading object's acceptance of the advertisement text, and improving the interaction rate between the reading object and the advertisement content corresponding to the advertisement text, thereby improving the conversion rate of the advertisement content and improving the information processing effect.

[0138] In addition, by constructing advertising text using dialogues of characters associated with characters involved in the content currently displayed in the reading text, using dialogue sentence patterns that match the dialogue sentence patterns in the content currently displayed in the reading text, using dialogues of characters in the reading text with dialogue tones that match their personalities, describing scenes associated with scenes involved in the content currently displayed in the reading text, using language style types that are consistent with the language style types of the reading text, using sentence patterns that are consistent with the sentence patterns of the reading text, etc., it is beneficial to improve the relevance of the advertising text to the content currently displayed in the reading text in terms of dialogue characters, dialogue sentence patterns, dialogue tone, scenes, language style, sentence patterns, etc., reduce the visual abruptness brought to the readers by the display of advertising text, improve the readers' acceptance of advertising text, and improve the interaction rate between the readers and the advertising content corresponding to the advertising text, thereby improving the conversion rate of advertising content and the information processing effect.

[0139] The same targeted ad content can be displayed differently for different reading texts, providing greater flexibility in displaying the ad text and improving its effectiveness. Furthermore, ad text can be automatically generated using a natural language model to ensure quality.

[0140] By displaying prompt elements, when the advertising text has literary style characteristics associated with the reading text, the reading object can intuitively distinguish between the advertising text and the reading text, ensuring that the reading object can accurately identify the advertising text and improving the reading object's interactive experience.

[0141] Setting a prominent display mark for the introductory text can attract the reader's attention, thereby encouraging the reader to anticipate the target ad content that will be displayed later by focusing on the introductory text in the ad text. This reduces the visual abruptness of the target ad content and improves the reader's acceptance of the target ad content. This in turn increases the reader's interaction rate with the target ad content and improves the target ad content's conversion rate. By setting time-sensitive text in the introductory text, the timeliness of the target ad content can be emphasized in the introductory text, thereby stimulating the reader's sense of urgency and prompting the reader to more quickly participate in the activities promoted by the target ad content through interaction with the target ad content, thereby improving the target ad content's conversion rate.

[0142] By matching the display style of the advertising text with that of the reading text, the advertising text can simulate the UI style of the reading text, achieving the effect that the visual effect of the advertising text converges with the visual effect of the reading text, making the advertising text visually consistent with the reading text. By improving the integration of the advertising text and the reading environment in the visual experience, the visual abruptness brought by the advertising text is reduced, the interaction rate between the reading object and the target advertising content is increased, and thus the conversion rate of the target advertising content is improved.

[0143] When the display of the ad text meets the display requirements, the target ad content is displayed in the reading interface. This ensures that the original material of the target ad content provided by the advertiser is fully exposed, meeting the advertiser's display requirements for the target ad content. When the target ad content needs to be displayed, the target ad content is displayed in the ad content display position on the page displaying the ad text. This allows the target ad content to be overlaid on the page displaying the ad text, thereby visually demonstrating the relevance between the ad text and the target ad content, improving the reader's acceptance of the target ad content, and thereby increasing the reader's interaction rate with the target ad content, thereby improving the conversion rate of the target ad content.

[0144] By popping up the advertising content display position with animation effects that match the reading text on the page displaying the advertising text, the pop-up effect of the advertising content display position can be more integrated with the reading scene of the reading text, reducing the visual abruptness brought by the pop-up advertising content display position to the reading object, and improving the reading object's acceptance of the target advertising content, thereby increasing the interaction rate between the reading object and the target advertising content and improving the conversion rate of the target advertising content.

[0145] Adding the social element of historical interaction information to the display of target advertising content can increase the credibility of the target advertising content, increase the possibility of readers interacting with the target advertising content, and improve the conversion rate of the target advertising content.

[0146] This embodiment of the present application provides a method for generating advertising text based on the original source material of target advertising content and text feature information of a reading text using a natural language model. The method is performed by a computer device, which can be, for example, a terminal or a server. This embodiment of the present application uses the method performed by a terminal as an example. As shown in Figure 7, the method for generating advertising text based on the original source material of target advertising content and text feature information of a reading text using a natural language model can include the following steps 701 to 703.

[0147] In step 701, the original material of the target advertisement content, the text feature information of the reading text, and the target text generation model are obtained.

[0148] The original source material for the target advertising content can be provided by the advertiser to the text reading platform, allowing the terminal to obtain the original source material for the target advertising content from the text reading platform. The original source material for the target advertising content is the material provided by the advertiser to introduce the target advertising content. The original source material for the target advertising content may include, but is not limited to, at least one of text, images, and videos.

[0149] The text feature information of the reading text is information used to characterize the features of the reading text. Based on this text feature information, the target text generation model can learn the literary style of the reading text and then generate an advertising text with literary style features that match the reading text.

[0150] In an exemplary embodiment, if the advertising text has literary style features associated with the reading text, including the advertising text having literary style features associated with the reading text as a whole, then the text feature information includes information used to characterize the features of the reading text as a whole; if the advertising text has literary style features associated with the reading text, including the advertising text having literary style features associated with the content currently displayed by the reading text, then the text feature information includes information used to characterize the features of the content currently displayed by the reading text.

[0151] The specific circumstances of the text feature information may be related to the specific circumstances in which the advertising text has literary style characteristics associated with the reading text. This embodiment of the application does not limit the type of text feature information of the reading text. Next, referring to Cases 1 to 5 of the embodiment shown in FIG2 , in which the advertising text has literary style characteristics associated with the reading text, the specific circumstances of the text feature information are exemplified.

[0152] If the advertising text has literary style features associated with the reading text, which is Case 1 in the embodiment shown in FIG2 , that is, the advertising text includes a first text in the form of a dialogue, and the aforementioned associated literary style features include the association between the characters in the dialogue in the first text and the characters involved in the content currently displayed by the reading text, then the text feature information includes the identification information of the characters involved in the content currently displayed by the reading text and the character relationship information of the reading text.

[0153] The identification information of the person involved in the currently displayed content is used to identify the person involved in the currently displayed content. For example, the identification information of the person involved in the currently displayed content may refer to the name, nickname, etc. of the person involved in the currently displayed content. The identification information of the person involved in the currently displayed content may be extracted from the currently displayed content.

[0154] The character relationship information of a reading text indicates the relationships between characters involved in the reading text. This character relationship information can be obtained from a text reading platform. The character relationship information stored in the text reading platform can be information submitted by the author of the reading text to the text reading platform, or it can be information obtained by the developer of the text reading platform through analysis of the reading text.

[0155] In an exemplary embodiment, the advertising text has literary style features associated with the reading text. In case 1 of the embodiment shown in Figure 2, the conversational tone of the characters in the first text may also match the personality of the characters described in the reading text. In this case, the text feature information also includes the character representation content of the characters in the reading text.

[0156] The character representation content is used to represent the character of the characters in the reading text. The character representation content of any character includes at least one of the dialogue content of the any character in the reading text, the introduction of the any character provided by the author of the reading text, or the description of the any character in the reading text. For example, the dialogue content of any character in the reading text may refer to the entire dialogue content of any character in the reading text, or may refer to the dialogue content of any character in the reading text with a word count exceeding a word count threshold, etc. For example, the description content of any character in the reading text may refer to the content in the reading text that describes at least one of the clothing, appearance, height, actions, or demeanor of the any character. The character representation content may be provided by the author of the reading text or extracted from the reading text.

[0157] If the advertising text has literary style features associated with the reading text, which is Case 2 in the embodiment shown in Figure 2, that is, the advertising text includes a first text in the form of a dialogue, and the aforementioned associated literary style features include the dialogue sentence patterns of the first text matching the dialogue sentence patterns in the content currently displayed by the reading text, then the text feature information includes the dialogue text in the content currently displayed by the reading text.

[0158] The dialogue text is used to represent the dialogue sentence structure in the currently displayed content. The dialogue sentence structure is used to indicate the order of character descriptions and dialogue content. For example, the dialogue text in the currently displayed content of the reading text can refer to the text consisting of part or all of the dialogue content in the currently displayed content. The dialogue text in the currently displayed content can be extracted from the currently displayed content.

[0159] If the advertising text has literary style features associated with the reading text, which is Case 3 in the embodiment shown in FIG2 , that is, the advertising text includes a second text in the form of a scene description, and the aforementioned associated literary style features include an association between the scene described in the second text and a scene involved in the content currently displayed in the reading text, then the text feature information includes the scene description text in the content currently displayed in the reading text.

[0160] The scene description text is used to characterize the scene involved in the currently displayed content. For example, the scene description text in the currently displayed content may refer to the text composed of all or part of the content in the currently displayed content used to describe the scene.

[0161] If the advertising text has literary style features associated with the reading text, which is case 4 in the embodiment shown in Figure 2, that is, the aforementioned associated literary style features include that the language style type of the advertising text is consistent with the language style type of the reading text, then the text feature information includes identification information of the language style type of the reading text.

[0162] The identification information of the language style type of the reading text is used to identify the language style type of the reading text. The language style type of the reading text is used to indicate the writing style of the reading text. The identification information of the language style type of the reading text can be obtained from the reading text's tags. The reading text tags are tags that are used by the reading text's author or text reading platform to identify the reading text's characteristics.

[0163] If the advertising text has literary style features associated with the reading text, which is case 5 in the embodiment shown in Figure 2, that is, the aforementioned associated literary style features include sentence patterns of the advertising text that are the same as the sentence patterns of the reading text, then the text feature information includes identification information of the sentence patterns of the reading text.

[0164] The identification information of the sentence pattern of the reading text is used to identify the sentence pattern of the reading text. For example, the identification information of the sentence pattern can refer to information directly used to identify the sentence pattern, such as the sentence pattern of a complete sentence or a scattered sentence. For example, the identification information of the sentence pattern can also refer to one or more paragraphs in the reading text. The identification information of the sentence pattern can be extracted from the reading text or obtained by analyzing the content of the reading text.

[0165] It should be noted that, in the embodiment shown in FIG. 2 , cases 1 to 5 in which the advertisement text has literary style features associated with the reading text can be combined arbitrarily, and the information included in the above-mentioned text feature information can also be combined arbitrarily.

[0166] For example, if the advertising text has literary style features associated with the reading text including Case 1 and Case 2, that is, the aforementioned associated literary style features also include the association between the characters in the dialogue in the first text in the advertising text and the characters involved in the content currently displayed by the reading text, the dialogue tone of the characters in the dialogue in the first text matches the character of the character described in the reading text, and the dialogue sentence structure of the first text matches the dialogue sentence structure in the currently displayed content, then the text feature information includes the identification information of the characters involved in the currently displayed content, the character relationship information of the reading text, and the character personality representation content in the reading text.

[0167] For another example, if the advertising text has literary style features associated with the reading text including cases 3 to 5, that is, the scene described by the second text in the advertising text is associated with the scene involved in the content currently displayed in the reading text, the language style type of the advertising text is consistent with the language style type of the reading text, and the sentence pattern of the advertising text is the same as the sentence pattern of the reading text, then the text feature information includes the scene description text in the currently displayed content, the identification information of the language style type of the reading text, and the identification information of the sentence pattern of the reading text.

[0168] It should be further explained that the text feature information described above is only an exemplary description of the five exemplary cases in which the advertising text has literary style features associated with the reading text. The embodiments of the present application are not limited thereto. When the advertising text has literary style features associated with the reading text in other cases, the text feature information can also be flexibly changed. In some embodiments, in addition to the information mentioned above, the text feature information can also include basic information of the reading text, such as the name of the reading text, the author of the reading text, the text type of the reading text, the chapter list of the reading text, etc., which will not be given one by one here.

[0169] The target text generation model is a natural language model that generates an advertising text with literary style features associated with the reading text based on the original material of the target advertising content and the text feature information of the reading text. This application does not limit the model architecture of the target text generation model, as long as it can handle the task of generating text. Exemplarily, the model architecture of the target text generation model can be RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), GRU (Gated Recurrent Unit), Transformer (converter), etc. These model architectures have advantages in processing sequence data and can capture long-distance dependencies in text. For example, the model architecture of Transformer can specifically refer to BERT (Bidirectional Encoder Representations from Transformers, bidirectional encoder representations from converters), GPT (Generative Pre-Trained Transformer, generative pre-trained converter model), etc.

[0170] The terminal can obtain the target text generation model from the server or extract it from local storage. The target text generation model can be obtained through supervised training by the terminal or server. The process of training the target text generation model will be described below and will not be detailed here.

[0171] In an exemplary embodiment, if the content of the advertisement text matches the object data of the reading object, the object data of the reading object needs to be obtained before executing step 702. The object data of the reading object refers to data related to the reading object. The type of object data can be set based on experience or flexibly adjusted according to needs. For example, the object data can include but is not limited to the reading object's age, gender, interests and hobbies, consumption habits, reading preferences, historical interactions with the advertisement content, etc. It should be noted that the object data can be obtained from the reading object's registration information, browsing history, purchase history, etc. with the reading object's authorization.

[0172] In step 702, input information is obtained based on the original material and text feature information.

[0173] Input information refers to information that needs to be input into the target text generation model. In an exemplary embodiment, based on the original material and text feature information, obtaining input information may refer to obtaining input information directly based on the original material and text feature information. Exemplarily, the implementation process of obtaining input information directly based on the original material and text feature information may be: obtaining the first feature corresponding to the original material of the target advertising content and the second feature corresponding to the text feature information; based on the first feature and the second feature, obtaining input information. For example, the first feature and the second feature are used as input information; for another example, the concatenation feature of the first feature and the second feature is used as input information; for another example, the corresponding elements of the first feature and the second feature are added, and the added feature is used as input information. It should be understood that the splicing order between multiple features can be set according to experience or flexibly adjusted according to needs, and the embodiments of the present application do not limit this. In addition, before adding multiple features, it is necessary to expand the multiple features to the same dimension.

[0174] For example, the target advertising content's original materials, such as text, images, and videos, are converted into a form that can be directly processed by the model to obtain a first feature; and the text feature information is converted into a form that can be directly processed by the model to obtain a second feature. For example, a feature extraction model can be used to extract the first feature of the target advertising content's original materials and the second feature of the text feature information.

[0175] For example, in the case where the original material and text feature information of the target advertising content are both in the form of text, the original material of the target advertising content can be segmented to obtain multiple first words, and the features corresponding to the multiple first words can be spliced ​​together to obtain the first feature; the text feature information can be segmented to obtain multiple second words, and the features corresponding to the multiple second words can be spliced ​​together to obtain the second feature. Optionally, a word feature table can be pre-constructed, and the word feature table records the features corresponding to candidate words. The candidate words can be extracted from a word library or from the Internet. The features corresponding to the words are used to characterize the words. For example, the features corresponding to the words can be a one-hot (unique hot encoding) feature.

[0176] In an exemplary embodiment, obtaining input information based on the original source material and text feature information may also refer to obtaining input information based on the original source material, text feature information, and the target audience's object data. The input information obtained in this manner includes the target audience's object data, enabling the model to generate advertising text that matches the target audience's object data, thereby improving the match between the advertising text and the target audience's interests, increasing the target audience's receptiveness to the advertising text, and thereby increasing the conversion rate of the advertising content.

[0177] Exemplarily, the process of acquiring input information based on the original material, text feature information, and object data of the reading object may include: acquiring a first feature corresponding to the original material of the target advertising content, a second feature corresponding to the text feature information, and a third feature corresponding to the object data; and acquiring the input information based on the first, second, and third features. Exemplarily, a feature extraction model may be used to extract the third feature corresponding to the object data of the reading object.

[0178] In step 703, the target text generation model is called to generate text based on the input information to obtain the advertisement text.

[0179] After obtaining input information, the input information is input into a target text generation model to obtain advertising text with the assistance of the target text generation model. In an exemplary embodiment, the process of invoking the target text generation model to generate text based on the input information to obtain the advertising text includes: invoking the target text generation model to obtain target features based on the input information, generating text based on the target features to obtain a first text; and obtaining the advertising text based on the first text output by the target text generation model.

[0180] Exemplarily, calling the target text generation model to obtain target features based on input information may refer to calling the target text generation model to perform feature extraction on the input information to obtain the target features. Exemplarily, a fully connected layer (or densely connected layer) may be provided at the input layer of the target text generation model. This fully connected layer is capable of performing feature extraction on the input information to form the target features.

[0181] The target ad's raw material, text feature information, and target audience data are preprocessed to meet the model's input requirements. This preprocessed input is then fed into the trained target text generation model. The model generates words one by one based on the input information. This process continues until a complete copy is formed, which serves as the first text. It should be understood that when generating a word for a specific position, the output is typically a probability distribution, representing the probability of each candidate word appearing at that position given the context. The candidate word with the highest probability in this probability distribution is then used as the word for that position.

[0182] Exemplarily, acquiring the advertisement text based on the first text may refer to using the first text as the advertisement text. This approach can improve the efficiency of acquiring the advertisement text based on the first text.

[0183] Exemplarily, obtaining advertisement text based on the first text may also involve repairing the first text to obtain the advertisement text. Optionally, repairing the first text may include, but is not limited to, removing duplicate words, completing incomplete sentences, and supplementing missing text. Optionally, the missing text may include the advertiser's name, introductory text corresponding to the target advertisement content, etc. This approach can ensure the quality of the advertisement text.

[0184] The target text generation model is obtained by training the initial text generation model based on the difference between the predicted advertisement text and the standard advertisement text. The predicted advertisement text invokes the initial text generation model to generate text based on sample input information. The sample input information is determined based on sample material of the sample advertisement content and sample text feature information of the sample reading text. The standard advertisement text has literary style features associated with the sample reading text. Taking the process of training the target text generation model as performed by a terminal as an example, the process of training the target text generation model includes steps A to D.

[0185] Step A: Obtain sample materials of sample advertising content, sample text feature information of sample reading text, and standard advertising text.

[0186] Sample materials for sample advertising content can be extracted from an advertising content library. The advertising material library includes various advertising content materials, such as advertising content materials provided by various types of advertisers, advertising content materials corresponding to various products, advertising content materials corresponding to various services, etc. The advertising content materials in the advertising material library can be obtained from media platforms, advertising case libraries, or the Internet. In some embodiments, the sample materials for sample advertising content can be obtained by pre-processing the advertising content materials in the advertising material library (e.g., removing special symbols, word segmentation, and part-of-speech tagging).

[0187] Sample text feature information of sample reading texts can be extracted from a reading text library. The reading texts in the reading text library can include reading texts of different types, plot settings, and literary styles, as well as text feature information of each reading text. The reading texts in the reading text library can help the model learn the literary styles of various reading texts. The reading texts in the reading text library can be obtained from public reading text databases, websites, e-book resources, etc. Sample text feature information of the reading texts in the reading text library can be extracted from the tags or content of the reading texts in the reading text library.

[0188] Standard ad text is used to introduce the sample target ad content. Standard ad text has literary style characteristics that match the sample reading text. Standard ad text is a target for the text generation model to learn. By setting standard ad text, the text generation model can learn to combine the material of the ad content with the literary style of the reading text. Standard ad text is text that incorporates the literary style of the sample reading text into the material of the ad content. Standard ad text can be manually written or generated using rules or algorithms, and this application does not limit this.

[0189] For example, if the type of the sample reading text is fantasy, the sample text feature information is "He drew his sword and prepared to fight the dragon", the advertiser corresponding to the sample advertising content is platform A, and the text in the sample advertising content is "20 off for purchases over 100", then the standard advertising text can be "In the midst of this fierce battle, why don't warriors come to platform A and use the power of 20 off for purchases over 100 to buy more powerful props to help you?"

[0190] For example, a sample material of a sample advertisement, sample text feature information of a sample reading text, and a corresponding standard advertisement text can be used as sample data. A dataset including the plurality of sample data can be pre-constructed. The dataset can be divided into a training set, a validation set, and a test set. For example, the dataset can be divided into a ratio of 80% training set, 10% validation set, and 10% test set. During the training of the text generation model, sample data can be extracted from the training set for training.

[0191] In an exemplary embodiment, when the content of an advertisement text matches the object data of a reader, sample object data is also required during the text generation model training process. This sample object data can be extracted from the data generated by the reader while reading the text. For example, the sample object data can be represented as a profile of the sample object. This profile can be constructed by analyzing the reader's behavioral data while reading the sample text. The sample object profile can include information such as the reader's interests, reading preferences, and historical interactions with the target advertisement content.

[0192] Step B: Determine sample input information based on sample material and sample text feature information of the sample advertisement content.

[0193] Step C: Call the initial text generation model to generate text based on the sample input information to obtain the predicted advertising text.

[0194] The implementation principles of the above steps B and C are the same as those of steps 702 and 703, and will not be repeated here.

[0195] Step D: The initial text generation model is trained based on the difference between the predicted advertisement text and the standard advertisement text to obtain a target text generation model.

[0196] Exemplarily, the process of training an initial text generation model based on the difference between the predicted advertising text and the standard advertising text to obtain a target text generation model includes: determining a first loss based on the difference between the predicted advertising text and the standard advertising text, calculating the gradient of the first loss relative to the parameters of the initial text generation model, and using the gradient to reversely update the parameters of the initial text generation model to obtain an updated text generation model; if the updated text generation model meets the training termination condition, then the updated text generation model is used as the target text generation model. If the updated text generation model does not meet the training termination condition, a new first loss is obtained based on the updated text generation model, and the parameters of the updated text generation model are reversely updated based on the new first loss, and so on, until the obtained text generation model meets the training termination condition, and the obtained text generation model is used as the target text generation model.

[0197] Exemplarily, the method for determining the first loss based on the difference between the predicted advertising text and the standard advertising text may be: based on the difference between the predicted advertising text and the standard advertising text, the first loss is determined using a loss function. The loss function may be a cross-entropy loss function or a mean square error loss function, etc. The first loss is used to measure the difference between the predicted advertising text obtained based on the model and the standard advertising text. Updating the parameters of the text generation model may refer to updating the parameters of the text generation model using an optimizer, for example, the optimizer may be an Adam (Adaptive Moment Estimation) optimizer or an RMSProp (Root Mean Square Propagation) optimizer, etc.

[0198] The updated text generation model meeting the training termination condition can be set based on experience or flexibly adjusted according to demand, and the embodiments of the present application do not limit this. For example, the updated text generation model meeting the training termination condition may include any of the following: the first loss based on which the updated text generation model is obtained is not greater than the loss threshold, the first loss based on which the updated text generation model is obtained converges, and the number of model parameter updates executed when obtaining the updated text generation model reaches the number threshold. The loss threshold and the number threshold can be set based on experience or flexibly adjusted according to demand.

[0199] For example, the hyperparameters of the initial text generation model can be set based on task requirements and computational complexity. For example, the hyperparameters may include the number of model layers, the number of hidden units, the learning rate, the batch size, etc. In practical applications, multiple attempts and adjustments can be made to find more appropriate hyperparameter settings.

[0200] During the training of the text generation model, the performance of the text generation model can be regularly evaluated on the validation set. According to the validation results, the hyperparameters of the text generation model, such as the learning rate, the number of model layers, and the number of hidden units, are adjusted. If it is found that the text generation model performs well on the training set but performs poorly on the validation set, overfitting may have occurred. You can try to increase the training data or use regularization methods to alleviate overfitting. When the text generation model achieves satisfactory performance on the validation set, the trained model parameters are saved to obtain the target text generation model. In some embodiments, after the training is completed, the text generation model can be evaluated to ensure that the text generated by the text generation model has a high sense of nativeness and appeal.

[0201] In an embodiment of the present application, an advertising text is generated by understanding the original material of the target advertising content and the text feature information of the reading text through a target text generation model. The target text generation model is trained under the supervision of a standard advertising text, which is conducive to ensuring the generation quality of the advertising text, improving the attractiveness of the advertising text to the reading object, and thereby improving the conversion rate of the target advertising content corresponding to the advertising text.

[0202] Referring to FIG8 , an embodiment of the present application provides an information processing device, the device including:

[0203] Display module 801, used to display the reading interface of the text reading platform, which is used for readers to read online or offline reading texts;

[0204] The display module 802 is configured to display the advertisement text of the target advertisement content in the reading interface in response to receiving a page turning event, wherein the advertisement text has literary style features associated with the reading text.

[0205] In one possible implementation, the display module 802 is used to display advertising text and prompt elements in the reading interface, and the prompt element is used to indicate that the text displayed in the current page is advertising text; wherein the prompt element includes at least one of prompt text, prompt icon, or prompt page corner; the prompt page corner is located in the area where any page corner of the current page is located, and the prompt page corner is in a folded state.

[0206] In a possible implementation, the advertisement text includes an introduction text corresponding to the target advertisement content, and the introduction text has a prominent display mark on the page displaying the advertisement text.

[0207] In a possible implementation, the introduction text includes time-sensitive text, which is used to indicate the effective time of the target advertising content.

[0208] In one possible implementation, the display style of the advertisement text in the reading interface matches the display style of the reading text in the reading interface.

[0209] In a possible implementation, the display module 802 is further configured to display target advertisement content in the reading interface in response to the display of the advertisement text meeting the display requirements.

[0210] In a possible implementation, the display module 802 is configured to pop up an advertisement content display position on a page displaying advertisement text; and display target advertisement content in the advertisement content display position.

[0211] In a possible implementation, the display module 802 is configured to pop up an advertisement content display location on a page displaying advertisement text through an animation effect, where the animation effect matches the reading text.

[0212] In a possible implementation, the display module 802 is configured to display the target advertising content and historical interaction information corresponding to the target advertising content in a reading interface.

[0213] In a possible implementation, the target advertisement content has different advertisement texts corresponding to different reading texts, and different advertisement texts have different literary style characteristics.

[0214] In one possible implementation, the advertisement text is generated by a natural language model based on the original material of the target advertisement content and text feature information of the reading text.

[0215] In one possible implementation, the device further includes:

[0216] The acquisition module is used to obtain the original material of the target advertising content, the text feature information of the reading text and the target text generation model; based on the original material and the text feature information, the input information of the target text generation model is obtained; and the target text generation model is called to generate text based on the input information to obtain the advertising text.

[0217] In one possible implementation, the advertisement text includes a first text in the form of a dialogue, and the associated literary style features include an association between characters in the dialogue in the first text and characters involved in the content currently displayed by the reading text;

[0218] The text feature information includes identification information of the characters involved in the currently displayed content and character relationship information of the reading text. The character relationship information is used to indicate the association relationship between the characters involved in the reading text. The currently displayed content is determined based on the target reading text page corresponding to the page turning event.

[0219] In a possible implementation, the associated literary style features further include the matching of the dialogue tone of the characters in the first text and the personality of the characters described in the reading text;

[0220] The text feature information also includes the character characterization content in the reading text; wherein, the character characterization content is used to characterize the character of the characters in the reading text, and the character representation content of any character includes at least one of the dialogue content of any character in the reading text, the introduction of any character provided by the author of the reading text, or the description of any character in the reading text.

[0221] In one possible implementation, the advertisement text includes a first text in a dialogue format, and the associated literary style features include a dialogue sentence pattern of the first text matching a dialogue sentence pattern in the currently displayed content of the reading text, wherein the dialogue sentence pattern is used to indicate the order of character descriptions and dialogue content;

[0222] The text feature information includes the dialogue text in the currently displayed content, where the dialogue text is used to represent the dialogue sentence patterns in the currently displayed content. The currently displayed content is determined based on the target reading text page corresponding to the page turning event.

[0223] In one possible implementation, the advertisement text includes a second text in the form of a scene description, and the associated literary style features include that the scene described in the second text is associated with a scene involved in the content currently displayed in the reading text;

[0224] The text feature information includes scene description text in the currently displayed content. The scene description text is used to characterize the scene involved in the currently displayed content. The currently displayed content is determined based on the target reading text page corresponding to the page turning event.

[0225] In one possible implementation, the currently displayed content includes the last sentence in the target reading text page, the last paragraph in the target reading text page, the entire content in the target reading text page, the content of the chapter corresponding to the target reading text page, or the entire content from the first sentence in the reading text to the last sentence in the target reading text page.

[0226] In a possible implementation, the associated literary style features include that the language style type of the advertisement text is consistent with the language style type of the reading text; and the text feature information includes identification information of the language style type of the reading text.

[0227] In a possible implementation, the associated literary style features include that the sentence patterns of the advertisement text are the same as the sentence patterns of the reading text; and the text feature information includes identification information of the sentence patterns of the reading text.

[0228] In a possible implementation, the acquisition module is further configured to acquire object data of the reading object; and acquire input information based on the original material, text feature information, and object data.

[0229] In one possible implementation, the target text generation model is obtained by training the initial text generation model based on the difference between the predicted advertising text and the standard advertising text. The predicted advertising text calls the initial text generation model to generate text based on sample input information. The sample input information is determined based on sample materials of the sample advertising content and sample text feature information of the sample reading text; wherein the standard advertising text has literary style features associated with the sample reading text.

[0230] It should be noted that the device provided in the above embodiment only uses the division of the above functional modules as an example to illustrate when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here. The effects that can be achieved by the above embodiment are also detailed in the method embodiment and will not be repeated here.

[0231] Figure 9 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a terminal, such as a PC, mobile phone, smartphone, PDA, wearable device, handheld portable gaming device, PPC, tablet computer, smart car computer, smart TV, smart speaker, or vehicle-mounted terminal. A terminal may also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or other similar terminology.

[0232] Typically, the terminal includes: a processor 1001 and a memory 1002 .

[0233] Processor 1001 may include one or more processing cores, such as a quad-core processor or an octa-core processor. In some embodiments, processor 1001 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, processor 1001 may also include an AI (Artificial Intelligence) processor, which is used to handle computing operations related to machine learning.

[0234] The memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1002 is used to store at least one instruction, which is executed by the processor 1001 to enable the terminal to implement the information processing method provided in the method embodiment of the present application.

[0235] In some embodiments, the terminal may optionally further include: a peripheral device interface 1003 and at least one peripheral device.

[0236] The peripheral device interface 1003 may be used to connect at least one I / O (Input / Output)-related peripheral device to the processor 1001 and the memory 1002 .

[0237] The RF circuit 1004 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1004 communicates with a communication network and other communication devices via electromagnetic signals.

[0238] Display screen 1005 is used to display a UI. The UI may include graphics, text, icons, videos, and any combination thereof.

[0239] The camera assembly 1006 is used to collect images or videos. Optionally, the camera assembly 1006 includes a front camera and a rear camera.

[0240] Audio circuit 1007 may include a microphone and a speaker.

[0241] The power supply 1008 is used to supply power to various components in the terminal.

[0242] In some embodiments, the terminal further includes one or more sensors 1009 , including but not limited to: an acceleration sensor 1010 , a gyroscope sensor 1011 , a pressure sensor 1012 , an optical sensor 1013 , and a proximity sensor 1014 .

[0243] Those skilled in the art will appreciate that the structure shown in FIG9 does not limit the terminal and may include more or fewer components than shown, or combine certain components, or adopt a different component arrangement.

[0244] In an exemplary embodiment, a computer device is further provided, comprising a processor and a memory, wherein the memory stores at least one computer program. The at least one computer program is loaded and executed by one or more processors to enable the computer device to implement any of the above-mentioned information processing methods.

[0245] In an exemplary embodiment, a computer-readable storage medium is further provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor of a computer device to enable the computer to implement any of the above-mentioned information processing methods.

[0246] Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments can be accomplished by hardware or by a program instructing the relevant hardware. Optionally, the program is stored in the above-mentioned computer-readable storage medium. The above-mentioned computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, or the like.

[0247] In an exemplary embodiment, a computer program or a computer program product is further provided. The computer program or the computer program product includes computer instructions. The computer instructions are loaded and executed by a processor to enable a computer to implement any one of the above information processing methods.

[0248] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, storage, and display, etc.), and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the object data of the reading objects involved in this application are all obtained with full authorization.

[0249] The terms "first," "second," and the like in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential sequence. It should be understood that the data used in this manner are interchangeable where appropriate so that the embodiments of the application described herein can be implemented in a sequence other than those illustrated or described herein. The embodiments described in the exemplary embodiments above do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application.

[0250] It should be understood that the term "plurality" used herein refers to two or more. "And / or" describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates an "or" relationship between the associated objects.

[0251] The above description is merely an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. An information processing method, the method being executed by a computer device, the method comprising: Displaying a reading interface of a text reading platform, wherein the reading interface is used for a reader to read online or offline reading texts; In response to receiving a page turning event, an advertisement text of the target advertisement content is displayed in the reading interface, wherein the advertisement text has a literary style feature associated with the reading text.

2. The method according to claim 1, wherein displaying the advertisement text of the target advertisement content in the reading interface comprises: Displaying the advertisement text and a prompt element in the reading interface, wherein the prompt element is used to indicate that the text displayed on the current page is an advertisement text; The prompt element includes at least one of a prompt text, a prompt icon or a prompt page corner; the prompt page corner is located in the area where any page corner of the current page is located, and the prompt page corner is in a folded state.

3. The method according to claim 1, wherein the advertisement text comprises an introduction text corresponding to the target advertisement content, and the introduction text has a prominent display mark on a page displaying the advertisement text.

4. The method according to claim 1, wherein the display style of the advertisement text in the reading interface matches the display style of the reading text in the reading interface.

5. The method according to any one of claims 1 to 4, wherein after displaying the advertisement text of the target advertisement content in the reading interface, the method further comprises: In response to the display of the advertisement text meeting the display requirement, the target advertisement content is displayed in the reading interface.

6. The method according to claim 5, wherein displaying the target advertisement content in the reading interface comprises: Pop up an advertisement content display area on the page displaying the advertisement text; The target advertising content is displayed in the advertising content display position.

7. The method according to claim 6, wherein the step of popping up an advertisement content display area on a page displaying the advertisement text comprises: The advertisement content display position is popped up on the page displaying the advertisement text through an animation effect, and the animation effect matches the reading text.

8. The method according to any one of claims 1 to 7, wherein the target advertisement content has different advertisement texts corresponding to different reading texts, and the different advertisement texts have different literary style characteristics.

9. The method according to any one of claims 1 to 7, wherein the advertisement text is generated by a natural language model based on the original material of the target advertisement content and text feature information of the reading text.

10. The method according to claim 9, further comprising: Obtaining the original material of the target advertising content, the text feature information of the reading text, and a target text generation model; Based on the original material and the text feature information, obtaining input information of a target text generation model; The target text generation model is called to generate text based on the input information to obtain the advertisement text.

11. The method according to claim 10, wherein the advertisement text comprises a first text in a dialogue format, and the associated literary style features comprise an association between characters in the dialogue in the first text and characters involved in the content currently displayed in the reading text; The text feature information includes identification information of the characters involved in the currently displayed content and character relationship information of the reading text. The character relationship information is used to indicate the association relationship between the characters involved in the reading text. The currently displayed content is determined based on the target reading text page corresponding to the page turning event.

12. The method according to claim 11, wherein the associated literary style features further include a tone of dialogue between characters in the first text matching the personality of the characters described in the reading text; The text feature information also includes the character representation content of the characters in the reading text; in, The character representation content is used to represent the character of the characters in the reading text. The character representation content of any character includes at least one of the dialogue content of any character in the reading text, the introduction of any character provided by the author of the reading text, or the description of any character in the reading text.

13. The method according to claim 10, wherein the advertisement text comprises a first text in a dialogue format, the associated literary style features comprising a dialogue sentence pattern of the first text matching a dialogue sentence pattern in the currently displayed content of the reading text, the dialogue sentence pattern being used to indicate a sequence of character descriptions and dialogue content; The text feature information includes a dialogue text in the currently displayed content, where the dialogue text is used to represent a dialogue sentence pattern in the currently displayed content. The currently displayed content is determined based on a target reading text page corresponding to the page turning event.

14. The method according to claim 10, wherein the advertisement text includes a second text in the form of a scene description, and the associated literary style feature includes an association between the scene described in the second text and a scene involved in the content currently displayed in the reading text; The text feature information includes scene description text in the currently displayed content, where the scene description text is used to characterize scenes involved in the currently displayed content. The currently displayed content is determined based on a target reading text page corresponding to the page turning event.

15. According to any one of the methods described in claims 11-14, the currently displayed content includes the last sentence in the target reading text page, the last paragraph in the target reading text page, all the content in the target reading text page, the content of the chapter corresponding to the target reading text page, or all the content from the first sentence in the reading text to the last sentence in the target reading text page.

16. The method according to claim 10, wherein the associated literary style features include a language style type of the advertising text being consistent with a language style type of the reading text; The text feature information includes identification information of the language style type of the reading text.

17. The method according to claim 10, wherein the associated literary style features include a sentence pattern of the advertisement text being the same as a sentence pattern of the reading text; The text feature information includes identification information of the sentence pattern of the reading text.

18. The method according to any one of claims 10 to 17, further comprising: Acquire object data of the reading object; The acquiring of input information based on the original material and the text feature information includes: The input information is acquired based on the original material, the text feature information and the object data.

19. An information processing device, comprising: A display module, configured to display a reading interface of a text reading platform, wherein the reading interface is used for a reader to read online or offline reading texts; The display module is configured to display the advertisement text of the target advertisement content in the reading interface in response to receiving a page turning event, wherein the advertisement text has a literary style feature associated with the reading text.

20. A computer device, comprising a processor and a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor, so that the computer device implements the information processing method according to any one of claims 1 to 18.

21. A storage medium for storing a computer program for executing the information processing method according to any one of claims 1 to 18.

22. A computer program product comprising a computer program, which, when run on a computer, enables the computer to execute the information processing method according to any one of claims 1 to 18.

Images