Reading interaction method and device, network equipment, medium and computer program product

By converting the comment information in the e-reading APP into audio and automatically playing, the problem of insufficient interactivity in the existing technology is solved, and a rich and diverse reading experience is achieved.

CN119071584APending Publication Date: 2024-12-03MIGU DIGITAL MEDIA CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411095418.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The note-taking function of the existing e-reading app cannot meet the interactive requirements. Users can only view the comment content by clicking on the comment tag, which lacks a rich interactive experience.

Method used

By obtaining comment information in the reading text, converting it into an audio file, and automatically playing when the user reads a specific location, forming a voice barrage, increasing interactivity and richness.

Benefits of technology

It realizes the automatic playback of comment information during reading, enhances the interactiveness and diversity of the reading experience, and provides a richer way of reading interaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119071584A_ABST
    Figure CN119071584A_ABST
Patent Text Reader

Abstract

The invention provides a reading interaction method and device, network equipment, a medium and a computer program product, and is applied to the technical field of multimedia interaction. The method comprises the steps of obtaining comment information at a target content in a read text, wherein the comment information comprises at least one comment; converting the comment information into an audio file; and playing the audio file corresponding to the comment information when monitoring that the reading position of the user for reading the reading text is located at the target content. By adopting the method, the comment information of the read text can be converted into the audio file, the reading position of the user is monitored in the reading process, the audio file corresponding to the comment information is automatically played, and a voice bullet screen form is formed, so that the interactivity of the read text is improved, and richer and diversified reading experience is provided for the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of multimedia interaction technology, and in particular to a reading interaction method, device, network equipment, medium and computer program product. Background Art

[0002] In order to increase the fun of electronic reading, existing reading apps have added a note function, where readers can add comments to the chapters they read. Based on the existing comments on the chapters they read, other readers can also like or add replies to the comments. Currently, the only way to view the comments added to the chapters they read is to click on the mark corresponding to the comment to open it and see all the content information, which brings inconvenience to the reading process and fails to meet the requirements of interactivity. Summary of the invention

[0003] The purpose of the technical solution of this application is to provide a reading interaction method, device, network equipment, medium and computer program product, which are used to solve the problem that the note-taking function on the existing reading APP cannot meet the interactivity requirements.

[0004] One embodiment of the present application provides a reading interaction method, which includes:

[0005] Acquire comment information at a target content in a reading text, wherein the comment information includes at least one comment;

[0006] Converting the comment information into an audio file;

[0007] When it is detected that the reading position of the user reading the reading text is located at the target content, the audio file corresponding to the comment information is played.

[0008] Optionally, the reading interaction method, wherein converting the comment information into an audio file, comprises:

[0009] Obtaining the sentiment attribute of each comment in the comment information;

[0010] Convert each of the comments into audio expressing emotions that conform to the emotion attributes;

[0011] The audio corresponding to the comment in the comment information is synthesized to obtain the audio file.

[0012] Optionally, in the reading interaction method, the step of obtaining the emotional attribute of each comment in the comment information includes:

[0013] Performing word segmentation processing on the comment to obtain multiple word segmentation phrases of the comment;

[0014] Determine the emotional attribute and corresponding emotional intensity of each of the segmented phrases according to the emotional dictionary;

[0015] Determining the emotion weight corresponding to each of the segmentation phrases in the comment according to the associated words of the segmentation phrases in the comment and the emotion intensity;

[0016] Determine the emotional attribute corresponding to the segmented phrase with the highest emotional weight in the comment as the emotional attribute of the comment.

[0017] Optionally, the reading interaction method, wherein, according to the associated words of the participle phrases in the comments and the emotional intensity, determining the emotional weight corresponding to each participle phrase in the comments, comprises:

[0018] According to the associated words of the segmentation phrase, the emotion intensity is adjusted in sequence according to one or more of the following methods to obtain the emotion weight corresponding to the segmentation phrase:

[0019] In the case where the associated words include a first associated word belonging to a degree adverb of the participle phrase, the emotional intensity is adjusted up according to a first rule;

[0020] In the case where the associated words include a second associated word that is a positive word, the emotion intensity is adjusted up according to a second rule;

[0021] In the case where the associated words include a third associated word that is a negative word, the emotion intensity is lowered according to a third rule.

[0022] Optionally, in the reading interactive method, the step of obtaining comment information at the target content in the reading text includes:

[0023] Obtain the comment information in the reading text that meets a first preset condition; wherein the first preset condition includes one or more of the following:

[0024] First-level comments and reply information corresponding to the first-level comments;

[0025] The attention parameter is greater than the first value;

[0026] The attention parameter is greater than the first value, and when a plurality of the comment information located within a portion of the reading text is arranged from high to low according to the attention parameter, the comment information is arranged in the front preset position.

[0027] Optionally, the reading interaction method further comprises:

[0028] Determining, according to the user's reading speed, whether the user's reading position of the reading text reaches the target content;

[0029] The reading speed is calculated based on the page turning time of the user, or the reading speed is the average reading speed of multiple different users calculated in advance, or the reading speed is a preset value.

[0030] Optionally, the reading interaction method, wherein converting the comment information into an audio file, comprises:

[0031] Acquire audio recording information of the user;

[0032] According to the audio recording information, the comment information is converted into an audio file using a corresponding timbre in the audio recording information.

[0033] Optionally, the reading interaction method, wherein synthesizing the audio corresponding to the comment in the comment information to obtain the audio file, comprises:

[0034] The audio files corresponding to the multiple comments in the comment information are synthesized, and the synthesized audio files are converted into two-channel audio files to obtain the audio files.

[0035] Optionally, in the reading interaction method, the attention parameter includes the number of likes, and the first value is equal to the average number of likes of multiple comment information within a reading range of a part of the reading text, or is a set value.

[0036] One embodiment of the present application further provides a reading interactive device, which includes:

[0037] An information acquisition module, used to acquire comment information at a target content in a reading text, wherein the comment information includes at least one comment;

[0038] An audio conversion module, used to convert the comment information into an audio file;

[0039] The playing module is used to play the audio file corresponding to the comment information when it is detected that the reading position of the user reading the reading text is located at the target content.

[0040] One embodiment of the present application further provides a network device, which includes a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the reading interaction method as described in any one of the above items.

[0041] One embodiment of the present application further provides a readable storage medium, wherein the readable storage medium stores a program, and when the program is executed by a processor, the steps in the reading interaction method as described in any of the above items are implemented.

[0042] One embodiment of the present application further provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, the steps in the reading interaction method described in any of the above items are implemented.

[0043] At least one of the above technical solutions of the present application has the following beneficial effects:

[0044] By adopting the reading interaction method described in the embodiment of the present application, the comment information of the reading text can be converted into an audio file, the user's reading position can be monitored during the reading process, and the audio file corresponding to the comment information can be automatically played to form a voice barrage format, so as to increase the interactivity of the reading text and provide users with a richer and more diverse reading experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of a reading interaction method according to one embodiment of the present application;

[0046] Figure 2 A schematic diagram of a process for determining the sentiment weight of a segmented phrase in an embodiment of the present application;

[0047] Figure 3 This is a schematic diagram of a process for determining the emotional attributes of a comment according to the emotional weights of multiple segmented word groups in an embodiment of the present application;

[0048] Figure 4 It is a structural schematic diagram of a reading interaction device described in one embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the technical problems, technical solutions and advantages to be solved by the present application clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0050] In order to solve the problem that the note-taking function on the reading APP used in the prior art cannot meet the requirements of interactivity, the embodiment of the present application provides a reading interaction method, which can convert the comment information of the reading text into an audio file, monitor the user's reading position during the reading process, and automatically play the audio file corresponding to the comment information in the form of voice barrage, so as to increase the interactivity of the reading text and provide users with a richer and more diverse reading experience.

[0051] One embodiment of the present application provides a reading interaction method, such as Figure 1 As shown, the method includes:

[0052] S110, obtaining comment information at the target content in the reading text, wherein the comment information includes at least one comment;

[0053] S120, converting the comment information into an audio file;

[0054] S130, when it is detected that the reading position of the user reading the reading text is located at the target content, playing the audio file corresponding to the comment information.

[0055] By adopting the reading interaction method described in the embodiment of the present application, on the basis of the note function of the reading App, a function of playing the audio file corresponding to the comment information is added; during the reading process, the audio file corresponding to the comment information is automatically played according to the user's reading position, forming a reading barrage interaction form that integrates audio content. The barrage is the reader's reading comments or experience on the target content. Optionally, the audio file played is synthesized into comments from multiple readers to provide users with a richer and more diverse reading experience.

[0056] In the embodiment of the present application, optionally, the reading method is executed by a network device or a platform device.

[0057] In one implementation of the present application, optionally, in step S110, obtaining comment information at the target content in the reading text includes:

[0058] Obtain the comment information in the reading text that meets a first preset condition; wherein the first preset condition includes one or more of the following:

[0059] First-level comments and reply information corresponding to the first-level comments;

[0060] The attention parameter is greater than the first value;

[0061] The attention parameter is greater than the first value, and when the plurality of comment information are arranged from high to low according to the attention parameter, the comment information is the one arranged at the front with a preset number of digits.

[0062] In the embodiment of the present application, the comment information converted into the audio file is the comment information of the part selected from the reading text. In the reading process, the user can add a first-level comment to the target content of the reading text, and can also add reply comments in sequence on the basis of the first-level comment to form comments of different levels. In addition, the user can also give likes and replies to the comments of different levels.

[0063] In an embodiment of the present application, optionally, the comment information mentioned includes the first-level comments added by the user to the reading text during the reading process and the reply comments corresponding to the first-level comments, that is, including the first-level comments and the second-level comments, so as to avoid excessive iterations.

[0064] In another embodiment, optionally, the attention parameter of the comment information used for audio file conversion is greater than the first value; in one embodiment, optionally, the attention parameter includes the number of likes, which is obtained by counting the number of likes of each level of comments and replies of the comment information. Optionally, the first value is equal to the average number of likes of a plurality of the comment information within a reading range of a portion of the reading text, or is a set value.

[0065] In one implementation mode, optionally, the comment information with the number of likes greater than 0 within the part of the reading range can be counted. For example, the number of comment information with the number of likes greater than 0 is M, where M is an integer greater than or equal to 1, and the number of likes for the i-th comment information is recorded as L(i). Then, the calculation method of the average number of likes P of the multiple comment information within the part of the reading range is:

[0066]

[0067] In one implementation mode, by calculating the average number of likes P within the part of the reading range, corresponding comment information with the number of likes within the part of the reading range being greater than the average number of likes P is screened out, and the comment information is converted into an audio file.

[0068] In another embodiment, after calculating the average number of likes P within the part of the reading range, for the corresponding comment information with a number of likes greater than the average number of likes P, the multiple comment information within the part of the reading range is sorted according to the order of the number of likes corresponding to the multiple comment information within the part of the reading range from high to low, and the comment information arranged at the front with a preset number of digits is selected, and the comment information corresponding to the selected preset number of digits is converted into an audio file. Optionally, the preset number of digits can be but is not limited to only 2 digits. With this embodiment, by selecting the comment information with the preset number of digits with the highest attention parameter for audio file conversion and playback, the problem of the user feeling tired due to the length of the audio playback can be avoided.

[0069] In another implementation manner, the first value may also be a set value, and the set value may be set according to the audio playback volume requirement.

[0070] It should be noted that in the embodiments of the present application, the part of the reading range mentioned includes but is not limited to only one or more paragraphs, one or more chapters, one or more pages or the entire reading text.

[0071] In the method described in the embodiment of the present application, in step S120, converting the comment information into an audio file includes:

[0072] Obtaining the sentiment attribute of each comment in the comment information;

[0073] Convert each of the comments into audio expressing emotions that conform to the emotion attributes;

[0074] The audio corresponding to the comment in the comment information is synthesized to obtain the audio file.

[0075] The reading interaction method described in the embodiment of the present application, after obtaining the comment information to be converted into an audio file, further determines the emotional attributes of the comments in the comment information, and converts each comment into an audio that expresses the emotion in accordance with the emotional attribute, and synthesizes the audio corresponding to multiple comments to obtain the audio file to be played. With this implementation, the played audio file can express the emotions and tone of comments made by different readers to achieve a rich and diverse form of expression. Compared with simply sending text bullet comments, audio bullet comments are more expressive and appealing.

[0076] In one embodiment of the present application, obtaining the emotional attribute of each comment in the comment information includes:

[0077] Performing word segmentation processing on the comment to obtain multiple word segmentation phrases of the comment;

[0078] Determine the emotional attribute and corresponding emotional intensity of each of the segmented phrases according to the emotional dictionary;

[0079] Determining the emotion weight corresponding to each of the segmentation phrases in the comment according to the associated words of the segmentation phrases in the comment and the emotion intensity;

[0080] Determine the emotional attribute corresponding to the segmented phrase with the highest emotional weight in the comment as the emotional attribute of the comment.

[0081] Optionally, in an embodiment of the present application, a text-to-speech (TTS) technology may be used to implement a text-to-speech function.

[0082] Optionally, the emotional attributes of each comment in the comment information are analyzed by natural speech analysis technology. First, each comment is segmented to obtain multiple segmentation phrases of the comment. In one implementation method, optionally, each comment can be segmented by the Jieba segmentation tool. Optionally, after the segmentation process, in addition to obtaining multiple segmentation phrases, the part of speech corresponding to each segmentation phrase is also obtained.

[0083] In this embodiment, the emotion attribute and the corresponding emotion intensity of each segmented word group are determined by constructing an emotion dictionary. The emotion dictionary records the correspondence between segmented word groups, emotion attributes and emotion intensity. Table 1 below shows part of the data content of the emotion dictionary.

[0084] Table 1

[0085] Participle phrase Part of Speech Emotional attributes Emotional intensity Overwhelmed adjective nervous 7 Incoherent adjective nervous 5 Cry verb sorrow 6 laughter noun excited 3

[0086] By using the emotion dictionary, after segmenting each comment to obtain the segmentation phrases and the part of speech of the segmentation phrases in the comment, the corresponding emotion attribute and emotion intensity are determined by searching the corresponding segmentation dictionary in the emotion dictionary.

[0087] Optionally, the emotion attribute includes but is not limited to only one or more of excitement, calmness, excitement, sadness, tension, etc.

[0088] In an embodiment of the present application, optionally, when a comment includes multiple segmentation phrases, the emotion weight corresponding to each segmentation phrase in the comment is determined based on the associated words of the segmentation phrases in the comment and the emotion intensity, and the emotion attribute corresponding to the segmentation phrase with the highest emotion weight in the comment is determined as the emotion attribute corresponding to the comment. With this implementation, each comment is annotated with an emotion attribute, that is, an emotion attribute is determined. When a comment includes multiple segmentation phrases, the emotion weight corresponding to the segmentation phrase is determined by analyzing the associated words and emotion intensity of the segmentation phrase, and the emotion weight corresponding to the segmentation phrase is determined by comparing the emotion weights corresponding to multiple segmentation phrases, and the emotion attribute with the highest emotion weight is determined as the emotion attribute corresponding to the comment.

[0089] In one implementation manner, optionally, determining the emotion weight corresponding to each of the segmentation phrases in the comment according to the associated words of the segmentation phrases in the comment and the emotion intensity includes:

[0090] According to the associated words of the segmentation phrase, the emotion intensity is adjusted in sequence according to one or more of the following methods to obtain the emotion weight corresponding to the segmentation phrase:

[0091] In the case where the associated words include a first associated word belonging to a degree adverb of the participle phrase, the emotional intensity is adjusted up according to a first rule;

[0092] In the case where the associated words include a second associated word that is a positive word, the emotion intensity is adjusted up according to a second rule;

[0093] In the case where the associated words include a third associated word that is a negative word, the emotion intensity is lowered according to a third rule.

[0094] See also Figure 2 As shown, the process of determining the sentiment weight of a word segmentation phrase may include the following steps:

[0095] S201, after performing word segmentation processing on a comment and obtaining multiple word segmentation phrases, the first word segmentation phrase is selected;

[0096] S202, determining the emotion attribute and the corresponding emotion intensity to which the first participle phrase belongs according to the emotion dictionary;

[0097] S203, if it is determined that the multiple participle phrases obtained from the comment include the first associated word of the degree adverb belonging to the first participle phrase, the emotion intensity corresponding to the first participle phrase is increased according to the first rule; otherwise, the corresponding emotion intensity remains unchanged; for example, the first rule may be to multiply the emotion intensity corresponding to the first participle phrase by a value greater than 1, so that the value of the emotion intensity is increased;

[0098] S204, obtaining the adjusted emotion intensity;

[0099] S205, if it is determined that the multiple segmented word groups obtained from the comment include a second associated word that is a positive word, the emotion intensity corresponding to the first segmented word group is increased according to the second rule; otherwise, the corresponding emotion intensity remains unchanged; for example, the second rule may be to increase the emotion intensity corresponding to the first segmented word group by 1, so that the value of the emotion intensity is increased;

[0100] S206, obtaining the adjusted emotion intensity;

[0101] S07, if it is determined that the multiple segmented word groups obtained from the comment include a third associated word that is a negative word, the emotion intensity corresponding to the first segmented word group is lowered according to the third rule; otherwise, the corresponding emotion intensity remains unchanged; for example, the third rule may be to reduce the emotion intensity corresponding to the first segmented word group by 1, so that the value of the emotion intensity is lowered;

[0102] S208: Determine the finally obtained value of the emotion intensity as the emotion weight corresponding to the first participle phrase.

[0103] Combination Figure 3 As shown, after a comment is segmented to obtain multiple segmentation phrases, and the above steps S01 to S208 are used to obtain the emotion weight of each segmentation phrase of the comment, the emotion weights corresponding to the multiple segmentation phrases are compared, and the emotion attribute corresponding to the segmentation phrase with the highest emotion weight is determined as the emotion attribute of the comment.

[0104] It should be noted that, in the embodiment of the present application, the above-mentioned specific implementation method of obtaining the emotional attribute of each comment in the comment information is only for illustration and is not limited thereto.

[0105] In one implementation of the present application, optionally, in step S120, converting the comment information into an audio file includes:

[0106] Acquire audio recording information of the user;

[0107] According to the audio recording information, the comment information is converted into an audio file using a corresponding timbre in the audio recording information.

[0108] By adopting this implementation mode, when the user's audio recording information is pre-stored, the comment information that needs to be converted into an audio file can be converted into an audio file with the timbre corresponding to the audio recording information based on the audio recording information, so that the audio file can be played directly with the timbre of the reading user; or, when the user's audio recording information is not pre-stored, the timbre of the reading user can be trained using an AI training method to generate a voice package belonging to the reading user, so that the audio file can be played directly with the timbre of the reading user, thereby enhancing the user's desire to participate.

[0109] In another implementation manner, optionally, converting the comment information into an audio file comprises:

[0110] Different comments in the comment information are converted into audios with different timbres, so that audios of different comments can be generated with different timbres, forming a display of comments or inner monologue OS corresponding to the reading target content of different reading users.

[0111] In the embodiment of the present application, optionally, synthesizing the audio corresponding to the comment in the comment information to obtain the audio file includes:

[0112] The audio files corresponding to the multiple comments in the comment information are synthesized, and the synthesized audio files are converted into two-channel audio files to obtain the audio files.

[0113] In a two-channel playback system, the mono audio is converted into two channels when synthesizing the audio, and with headphones or two-channel stereo speakers, the user can have a sense of direction of the audio, thus achieving an immersive "stereo" feeling. In this way, the whispers of multiple commentators can seem to surround the user.

[0114] According to the principle of dual-channel playback, if the same sound is emitted from two different sound sources and the time difference between the two sound waves reaching the listener is between 5 and 35 milliseconds, the human ear cannot distinguish the directions of the two sounds. The sound that a person hears first will be considered as the direction from which all the sounds come. This preconceived auditory characteristic is the Haas effect.

[0115] If the sound source direction is "right", the left channel is delayed by M milliseconds compared to the right channel; if the sound source direction is "left", the right channel is delayed by M milliseconds compared to the left channel; if the sound source direction is center, the left and right channels are synchronized without delay.

[0116] In the JAVA implementation, the left and right channels can be implemented using the audio processing library (Java Sound API). After the audio is made into the left channel, the same audio is copied to the right channel and delayed by 35 milliseconds to synthesize the two-channel audio to achieve the Haas effect.

[0117] Based on the above principle, the reading method described in the embodiment of the present application is adopted. When synthesizing the audio corresponding to the multiple comments in the comment information, the audio corresponding to the multiple comments is converted into two-channel audio to obtain an audio file. For example, it is assumed that the comment information includes comments from four users. In the process of synthesizing the four audio segments corresponding to the comments of the four users, when user B is a reply to user A's reply-type hot comment, it can be inserted 0.5S before the end of user A's audio. User C belongs to the second hot comment, so it is inserted after user A and user B finish playing. User D's audio is similar to that of user B, and is inserted 0.5S before the end of user C's audio playback.

[0118] By adopting the above method, during the reading process, not only can the audio comment information be heard, but also the dual-channel playback effect of multi-person audio can be obtained, thereby enhancing the expressiveness and appeal of the comment content.

[0119] In the embodiment of the present application, optionally, before playing the audio file corresponding to the comment information in step S130, the method further includes:

[0120] Determining, according to the user's reading speed, whether the user's reading position of the reading text reaches the target content;

[0121] The reading speed is calculated based on the page turning time of the user, or the reading speed is the average reading speed of multiple different users calculated in advance, or the reading speed is a preset value.

[0122] By adopting the reading interaction method described in the embodiment of the present application, after the comment information at the target content is converted into an audio file, when it is detected that the user's reading position reaches the target content, the audio file is automatically played.

[0123] For example, when a user is reading a book of the current type (such as literature, business management, etc.), the reading speed is 5 words per second, and the reading position of the audio file with comment information is 365 words from the beginning of this page, then the audio file will automatically play after 365 / 5=73 seconds.

[0124] Optionally, the user's reading speed may be calculated based on the user's page turning time, or the user's reading speed may be determined based on a pre-calculated average reading speed of multiple different users, or the user's reading speed may be determined as a preset value.

[0125] In one embodiment, the user's reading speed is optionally calculated during the user's reading process, as follows: when the user turns the reading page, the time T1 is recorded, and when the user finishes the corresponding reading page (such as turning the page, exiting, etc.), the time T2 is recorded, and the total time consumed T = T2-T1, in seconds. The number of words in the current reading page is C, and the number of words read by the user per second S = C / T. In this way, when the user starts to read the current page content, based on the reading speed calculated by the historical reading and the total number of words from the beginning of the current page to the target content, the time when the user reads the reading text to reach the target content can be determined, thereby determining whether the reading position of the user reading the reading text has reached the target content.

[0126] In addition, since the reading speeds for books with different contents are different, for example, the reading speed of leisure books is faster, while the reading speed of literary classics may be slower because one wants to savor them carefully, the reading speed S needs to be calculated separately when reading different types of reading texts.

[0127] In another embodiment, when the user's reading speed is not obtained in advance, it is possible to determine whether the user's reading position of the reading text has reached the target content based on the average reading speeds of multiple different users that are pre-counted; or, the user's reading speed is determined to be a preset value, and based on the preset value, it is determined whether the user's reading position of the reading text has reached the target content.

[0128] The reading interaction method described in the embodiment of the present application obtains comment information in the reading text, filters out comment information that can be converted into audio according to conditions such as attention parameters, and determines the emotional attributes of the comments in the comment information. Comments with different emotional attributes are matched with different timbres for audio generation; after each audio is generated, multiple audios are merged into an audio file with a dual-channel playback effect; during the user's reading process, the user's reading speed and the time to start reading the current page are obtained, and the time it takes for the user to read to the target content marked with comment information is calculated. When the user stays on the current page for the calculated time, it is monitored that the user's reading position of the reading text is at the target content, and the above-mentioned audio file is played to achieve the effect of audio barrage and provide a more diversified interactive method.

[0129] One embodiment of the present application also provides a reading interactive device, such as Figure 4 As shown, including:

[0130] An information acquisition module 410 is used to acquire comment information at a target content in a reading text, wherein the comment information includes at least one comment;

[0131] An audio conversion module 420, used to convert the comment information into an audio file;

[0132] The playing module 430 is used to play the audio file corresponding to the comment information when it is detected that the reading position of the user reading the reading text is located at the target content.

[0133] The reading interactive device described in the embodiment of the present application can convert the comment information of the reading text into an audio file, monitor the user's reading position during the reading process, and automatically play the audio file corresponding to the comment information in the form of voice barrage, so as to increase the interactivity of the reading text and provide users with a richer and more diverse reading experience.

[0134] Optionally, in the reading interaction device, the audio conversion module 420 converts the comment information into an audio file, including:

[0135] Obtaining the sentiment attribute of each comment in the comment information;

[0136] Convert each of the comments into audio expressing emotions that conform to the emotion attributes;

[0137] The audio corresponding to the comment in the comment information is synthesized to obtain the audio file.

[0138] Optionally, in the reading interaction device, the audio conversion module 420 obtains the emotional attribute of each comment in the comment information, including:

[0139] Performing word segmentation processing on the comment to obtain multiple word segmentation phrases of the comment;

[0140] Determine the emotional attribute and corresponding emotional intensity of each of the segmented phrases according to the emotional dictionary;

[0141] Determining the emotion weight corresponding to each of the segmentation phrases in the comment according to the associated words of the segmentation phrases in the comment and the emotion intensity;

[0142] Determine the emotional attribute corresponding to the segmented phrase with the highest emotional weight in the comment as the emotional attribute of the comment.

[0143] Optionally, in the reading interaction device, the audio conversion module 420 determines the emotion weight corresponding to each of the segmented phrases in the comment according to the associated words of the segmented phrases in the comment and the emotion intensity, including:

[0144] According to the associated words of the segmentation phrase, the emotion intensity is adjusted in sequence according to one or more of the following methods to obtain the emotion weight corresponding to the segmentation phrase:

[0145] In the case where the associated words include a first associated word belonging to a degree adverb of the participle phrase, the emotional intensity is adjusted up according to a first rule;

[0146] In the case where the associated words include a second associated word that is a positive word, the emotion intensity is adjusted up according to a second rule;

[0147] In the case where the associated words include a third associated word that is a negative word, the emotion intensity is lowered according to a third rule.

[0148] Optionally, in the reading interaction device, the information acquisition module 410 acquires comment information at the target content in the reading text, including:

[0149] Obtain the comment information in the reading text that meets a first preset condition; wherein the first preset condition includes one or more of the following:

[0150] First-level comments and reply information corresponding to the first-level comments;

[0151] The attention parameter is greater than the first value;

[0152] The attention parameter is greater than the first value, and when a plurality of the comment information located within a portion of the reading text is arranged from high to low according to the attention parameter, the comment information is arranged in the front preset position.

[0153] Optionally, in the reading interactive device, the playback module 430 is further used for:

[0154] Determining, according to the user's reading speed, whether the user's reading position of the reading text reaches the target content;

[0155] The reading speed is calculated based on the page turning time of the user, or the reading speed is the average reading speed of multiple different users calculated in advance, or the reading speed is a preset value.

[0156] Optionally, in the reading interaction device, the audio conversion module 420 converts the comment information into an audio file, including:

[0157] Acquire audio recording information of the user;

[0158] According to the audio recording information, the comment information is converted into an audio file using a corresponding timbre in the audio recording information.

[0159] Optionally, in the reading interactive device, the audio conversion module 420 performs synthesis processing on the audio corresponding to the comment in the comment information to obtain the audio file, including:

[0160] The audio files corresponding to the multiple comments in the comment information are synthesized, and the synthesized audio files are converted into two-channel audio files to obtain the audio files.

[0161] Optionally, in the reading interaction device, the attention parameter includes the number of likes, and the first value is equal to the average number of likes of multiple comment information within a reading range of a part of the reading text, or is a set value.

[0162] One embodiment of the present application further provides a network device, which includes a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the reading interaction method as described in any one of the above items.

[0163] Among them, the specific implementation method of executing the reading interaction method by the program running on the processor of the network device can refer to the detailed description when the reading interaction method is applied to the network device, and will not be repeated here.

[0164] In addition, a specific embodiment of the present application further provides a readable storage medium on which a computer program is stored, wherein when the program is executed by a processor, the steps in the reading interaction method described in any one of the above items are implemented.

[0165] Specifically, the readable storage medium is applied to the above-mentioned network device. When applied to the network device, the execution steps in the corresponding reading interaction method are described in detail above and will not be repeated here.

[0166] Another embodiment of the present invention further provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, the steps in any of the reading interaction methods described above are implemented.

[0167] Optionally, the embodiments of the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0168] The computer program product described in the embodiment of the present invention includes computer instructions that implement the various processes of the method embodiment shown above when executed by a processor, and can achieve the same technical effect. To avoid repetition, they are not described here.

[0169] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0170] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0171] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the sending and receiving methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0172] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary personnel in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A reading interaction method, characterized in that: include: Acquire comment information at a target content in a reading text, wherein the comment information includes at least one comment; Converting the comment information into an audio file; When it is detected that the reading position of the user reading the reading text is located at the target content, the audio file corresponding to the comment information is played.

2. The reading interactive method according to claim 1, characterized in that: Converting the comment information into an audio file includes: Obtaining the sentiment attribute of each comment in the comment information; Convert each of the comments into audio expressing emotions that conform to the emotion attributes; The audio corresponding to the comment in the comment information is synthesized to obtain the audio file.

3. The reading interactive method according to claim 2, characterized in that: The obtaining of the emotional attribute of each comment in the comment information includes: Performing word segmentation processing on the comment to obtain multiple word segmentation phrases of the comment; Determine the emotional attribute and corresponding emotional intensity of each of the segmented phrases according to the emotional dictionary; Determining the emotion weight corresponding to each of the segmentation phrases in the comment according to the associated words of the segmentation phrases in the comment and the emotion intensity; Determine the emotional attribute corresponding to the segmented phrase with the highest emotional weight in the comment as the emotional attribute of the comment.

4. The reading interactive method according to claim 3, characterized in that: Determining the emotion weight corresponding to each of the segmentation phrases in the comment according to the associated words of the segmentation phrases in the comment and the emotion intensity includes: According to the associated words of the segmentation phrase, the emotion intensity is adjusted in sequence according to one or more of the following methods to obtain the emotion weight corresponding to the segmentation phrase: In the case where the associated words include a first associated word belonging to a degree adverb of the participle phrase, the emotional intensity is adjusted up according to a first rule; In the case where the associated words include a second associated word that is a positive word, the emotion intensity is adjusted up according to a second rule; In the case where the associated words include a third associated word that is a negative word, the emotion intensity is lowered according to a third rule.

5. The reading interactive method according to claim 1, characterized in that: The step of obtaining comment information at the target content in the reading text includes: Obtain the comment information in the reading text that meets a first preset condition; wherein the first preset condition includes one or more of the following: First-level comments and reply information corresponding to the first-level comments; The attention parameter is greater than the first value; The attention parameter is greater than the first value, and when a plurality of the comment information located within a portion of the reading text is arranged from high to low according to the attention parameter, the comment information is arranged in the front preset position.

6. The reading interactive method according to claim 1, characterized in that: The method further comprises: Determining, according to the user's reading speed, whether the user's reading position of the reading text reaches the target content; The reading speed is calculated based on the page turning time of the user, or the reading speed is the average reading speed of multiple different users calculated in advance, or the reading speed is a preset value.

7. The reading interactive method according to claim 2, characterized in that: The audio corresponding to the comment in the comment information is synthesized to obtain the audio file, including: The audio files corresponding to the multiple comments in the comment information are synthesized, and the synthesized audio files are converted into two-channel audio files to obtain the audio files.

8. A reading interactive device, characterized in that: include: An information acquisition module, used to acquire comment information at a target content in a reading text, wherein the comment information includes at least one comment; An audio conversion module, used to convert the comment information into an audio file; The playing module is used to play the audio file corresponding to the comment information when it is detected that the reading position of the user reading the reading text is located at the target content.

9. A network device, characterized in that: It comprises a processor, a memory and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the reading interaction method according to any one of claims 1 to 7 is implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program, and when the program is executed by the processor, the steps in the reading interaction method according to any one of claims 1 to 7 are implemented.