CN107656787B

CN107656787B - Method for generating topics based on electronic book, computing device and computer storage medium

Info

Publication number: CN107656787B
Application number: CN201710883774.7A
Authority: CN
Inventors: 王海璐; 李国鹏; 陈新港; 柳燕煌; 朱军; 孙上斌; 秦银波; 冯东旭
Original assignee: Ireader Technology Co Ltd
Current assignee: Ireader Technology Co Ltd
Priority date: 2017-09-26
Filing date: 2017-09-26
Publication date: 2021-04-30
Anticipated expiration: 2037-09-26
Also published as: CN107656787A; WO2019062045A1

Abstract

The invention discloses a method, a computing device and a computer storage medium for generating topics based on an electronic book, wherein the method comprises the following steps: acquiring related information of at least one text object containing comment information in at least one electronic book, and generating at least one corresponding electronic book topic; the electronic book topics comprise text object contents and comment information of at least one text object; summarizing at least one electronic book topic in at least one electronic book to obtain a topic square page; and displaying the text content and/or comment information of each electronic book topic on the topic square page. By acquiring the relevant information of the text object containing the comment information in the electronic book and generating the corresponding electronic book topic for the text object, the comment information of the text object is effectively utilized, and more users can know the electronic book through the electronic book topic.

Description

Method for generating topics based on electronic book, computing device and computer storage medium

Technical Field

The invention relates to the technical field of information processing, in particular to a method, a computing device and a computer storage medium for generating topics based on an electronic book.

Background

In order to improve interactivity among users and facilitate users expressing emotion, many applications support comment functions. For example, the video playback application supports the user to fill in video comments such as a sense of after-view and the like for the viewed video content, and the e-book reading application supports the user to fill in comment information for the read e-book. For example, comment information of an electronic book mainly refers to: the user can evaluate the contents in the book and express the personal emotional viewpoint after reading a certain book. Through the comment information of the electronic book, a channel for information exchange can be constructed between the author and the reader and between the reader and the reader. The quality of the comment information of the electronic book can often influence the reading selection of other users.

However, in the existing situation, the comment information in the electronic book is often only visible to the user who reads the electronic book during reading, so that the comment information of the electronic book cannot be effectively utilized to recommend the electronic book to other users who do not read the electronic book.

Disclosure of Invention

In view of the above, the present invention has been made to provide a method, a computing device, a computer storage medium based on electronic book generated topics that overcomes or at least partially solves the above mentioned problems.

According to an aspect of the present invention, there is provided a method of generating topics based on e-books, including:

acquiring related information of at least one text object containing comment information in at least one electronic book, and generating at least one corresponding electronic book topic; the electronic book topics comprise text object contents and comment information of at least one text object;

summarizing at least one electronic book topic in at least one electronic book to obtain a topic square page;

and displaying the text content and/or comment information of each electronic book topic on the topic square page.

According to another aspect of the present invention, there is provided a computing device comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is configured to store at least one executable instruction that causes the processor to:

According to yet another aspect of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing the processor to:

According to the method, the computing equipment and the computer storage medium for generating topics based on the electronic book, provided by the invention, the related information of at least one text object containing comment information in at least one electronic book is obtained, and at least one corresponding electronic book topic is generated; the electronic book topics comprise text object contents and comment information of at least one text object; summarizing at least one electronic book topic in at least one electronic book to obtain a topic square page; and displaying the text content and/or comment information of each electronic book topic on the topic square page. By acquiring the relevant information of the text object containing the comment information in the electronic book and generating the corresponding electronic book topic for the text object, the comment information of the text object is effectively utilized, and more users can know the electronic book through the electronic book topic.

The above description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a flow chart illustrating a method for generating topics based on e-books according to an embodiment of the present invention;

FIG. 2 shows a schematic diagram of the topic square page of the present invention;

FIG. 3 is a flowchart illustrating a method for generating topics based on e-books according to a second embodiment of the present invention;

FIG. 4 is a flow chart illustrating text object filtering according to a second embodiment of the present invention;

FIG. 5 shows a flowchart of a method for interacting an electronic book with an electronic book topic according to a third embodiment of the present invention;

FIG. 6 is a schematic diagram of the topic presentation page of the present invention;

fig. 7 is a schematic structural diagram of a computing device according to a fourth embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The text object in the electronic book may be one or more paragraphs, a segment of characters, or one or more sentences of characters in the electronic book. The text object in the embodiments of the present invention is described by taking a paragraph as an example, but is not limited thereto.

Example one

Fig. 1 shows a flowchart of a method for generating a topic based on an electronic book according to an embodiment of the present invention, and as shown in fig. 1, the method for generating a topic based on an electronic book specifically includes the following steps:

step S101, obtaining related information of at least one text object containing comment information in at least one electronic book, and generating at least one corresponding electronic book topic.

Each text object in the electronic book allows a user to comment on the text object, and specifically, the user can add the content of reading feeling, thinking and the like to each text object in the electronic book as comment information for the text object. The comment information is automatically added by the user to the text object that the user wants to comment on during the process of reading the electronic book. After the comment information is added, the text object can correspondingly record the comment information added by the text object, and meanwhile, when a user reads the electronic book, the text object can be correspondingly marked in a special marking mode and then displayed on the client, so that all users can clearly know that the text object has the comment of the user when reading the text object. However, because the comment information can only be seen when the text object is read, the invention generates the topic of the electronic book so as to provide convenience for users to see the text object and the corresponding comment information.

The electronic book topics include text object content and comment information of at least one text object. The text object content is the text content of the text object in the electronic book. When generating an electronic book topic, a text object containing comment information in an electronic book needs to be acquired first. And acquiring related information of the text object containing the comment information, wherein the related information comprises book ID, chapter ID, text object position information, text object content, comment information and the like of the electronic book. When the content of the electronic book is long and includes a plurality of chapters, and the plurality of chapters further include a plurality of paragraphs, the text object position information is information such as a specific paragraph position in a specific chapter or a specific line number position of a specific paragraph position in a more detailed specific chapter. The electronic book chapter ID is acquired, so that the text object can be found quickly when the text object content is acquired subsequently, and meanwhile, the position of the text object in the electronic book can be known according to the chapter ID, so that the plot development position where the text object is located and the like can be known conveniently.

And correspondingly generating an electronic book topic for each text object according to the acquired related information of at least one text object containing the comment information in at least one electronic book.

Step S102, summarizing at least one electronic book topic in at least one electronic book to obtain a topic square page.

And summarizing the generated electronic book topics to obtain a topic square page containing at least one electronic book topic in at least one electronic book. The topic square page may be composed of one or more electronic book topics, wherein each electronic book topic includes a text object content and a plurality of pieces of comment information.

Step S103, displaying the text content and/or comment information of each electronic book topic on the topic square page.

As shown in fig. 2, the topic square page displays text contents of respective electronic book topics, comment information corresponding to the respective text contents, and the like.

According to the method for generating topics based on the electronic book, provided by the invention, the related information of at least one text object containing comment information in at least one electronic book is obtained, and at least one corresponding electronic book topic is generated; the electronic book topics comprise text object contents and comment information of at least one text object; summarizing at least one electronic book topic in at least one electronic book to obtain a topic square page; and displaying the text content and/or comment information of each electronic book topic on the topic square page. By acquiring the related information of the text object containing the comment information in the electronic book and generating the corresponding electronic book topic for the text object, the comment information of the text object is effectively utilized, and more users can decode the electronic book through the electronic book topic.

Example two

Fig. 3 is a flowchart illustrating a method for generating a topic based on an electronic book according to a second embodiment of the present invention, and as shown in fig. 3, the method for generating a topic based on an electronic book includes the following steps:

step S301, obtaining related information of at least one text object containing comment information in at least one electronic book.

Generating a corresponding e-book topic based on the e-book is mainly generated for a text object containing comment information. Therefore, a text object containing comment information in the electronic book is acquired first. When obtaining, it is necessary to obtain relevant information of the text object including the comment information, where the relevant information includes a book ID, a chapter ID, text object position information, text object content, comment information, and the like of the electronic book.

Step S302, at least one text object is screened according to the related information of the at least one text object.

And screening the text objects according to the acquired related information of the text objects so as to ensure that the quality of the electronic book topics generated by the text objects is high. The specific screening process is as follows:

step S3021, a plurality of text objects adjacent to each other are integrated and merged into one text object.

When a plurality of text objects are obtained, according to the book ID, the chapter ID, and the text object position information of the electronic book included in the related information of each text object, a plurality of text objects adjacent to each other at the same chapter position of the same electronic book may be integrated, the text object contents thereof are merged and merged into one text object, and the comment information of the original plurality of text objects is recorded as the comment information of the text object merged after the integration processing. On one hand, the generated e-book topics contain more text object contents, so that the scenarios of the e-book can be known more easily, and the contents related to the trend of the scenarios in the comment information can be better understood. On the other hand, text objects are integrated, and each adjacent text object in a book does not need to be independently generated into an electronic book topic, so that the number of the electronic book topics is reduced, the content richness contained in the electronic book topics is improved, a user can conveniently read the electronic book topics, and the reading experience of the user is improved.

Step S3022, analyzing the text object contents of the plurality of text objects, integrating the text objects with the similarity greater than the preset threshold, and merging the text objects into one text object.

The method comprises the steps of analyzing the text object contents of a plurality of text objects in the same electronic book, analyzing from multiple aspects such as words and semantics of the words, integrating the text objects with the similarity of the text object contents larger than a preset threshold value, and combining the text objects into one text object. If the contents of the plurality of text objects describe substantially the same meaning, the plurality of text objects may be integrated. The analysis of the similarity of the contents of the text objects and the comparison of the similarity of the contents of the text objects with a preset threshold value can perform word segmentation on the contents of the text objects, and the content similarity calculation methods such as a full matching algorithm, a similarity matching algorithm, an edit distance algorithm, a maximum common sequence algorithm and the like are used for confirming whether the content similarity of the text objects is larger than the preset threshold value or not. The preset threshold is specifically set according to implementation, and the preset threshold and the used content similarity algorithm are not limited here.

The text object contents of the text objects are analyzed, and the text objects with the text object content similarity larger than a preset threshold are integrated, so that the problem that electronic book topics generated according to the text objects are repeated can be avoided.

The execution sequence of the above two steps is not limited, and any step may be executed first. After the two steps, a plurality of text objects are obtained, and then the text objects are sequenced, and the text objects with high heat degree are arranged at the front position. The popularity here can be understood as that many users comment on it, the content of the text object is very wonderful, and the user is attracted to read. In the process of sorting, a text object sorting model is obtained through step S3023 and step S3024.

Step S3023, determining semantic features corresponding to the preset text object samples and semantic features corresponding to the at least one text object, and determining feature vectors of the text object samples according to the semantic features corresponding to each text object sample in the at least one text object.

The semantic features comprise latent semantic features and explicit semantic features. Latent semantic features are obtained from a feature extraction algorithm. Feature extraction algorithms are algorithms that facilitate mining deep connections between semantics, e.g., word2vec algorithms, LDA algorithms. The role of the latent semantic features is to express the popularity of the text object from the perspective of its content. Semantic features are extracted according to specified dimensions. The specified dimension may include, for example, the number of words of the text object content, the number of pieces of comment information, and the like. The semantic feature has the function of reflecting the heat of the text object from the aspect of the attribute of the text object. The determination of the semantic features is determined in different ways.

The method comprises the steps of adding pre-selected text object samples and text objects to be sequenced into the same training set together, enabling the text object samples and the text objects to be trained in the same space, so that potential semantic relations between the text object samples and the text objects can be mined conveniently, and determining latent semantic features corresponding to each text object sample and each text object according to the potential semantic relations. Preferably, the latent semantic features include multiple dimensions in order to more accurately reflect the features of the text object. And the semantic features are directly obtained from the text object content and the comment information according to the specified dimension.

After determining each text object sample and the semantic features corresponding to the text object, further determining the feature vector of the text object sample according to the semantic features corresponding to each text object sample. The determination method of the feature vector may be multiple: for example, the feature value of each dimension corresponding to the semantic feature may be directly used as a feature vector; for another example, the feature vector of the text object sample may also be further determined by combining preset features of the text object sample, which is not limited in the present invention.

And step S3024, training the feature vectors of the text object samples by a machine learning algorithm and combining the sample labeling results of the text object samples to obtain a text object sequencing model.

Machine learning algorithms facilitate determining the Rank, such as the Pairwise Rank algorithm, the SVM Rank algorithm, and the like. When the feature vectors of the text object samples are trained through a machine learning algorithm, the feature vectors are realized by combining with the sample labeling results of the text object samples, so that a model for realizing the text object sequencing is trained. The sample labeling time and the labeling mode of each text object sample can be flexibly selected by the person skilled in the art. For example, the labeling may be performed before the execution of step S3023, or the labeling may be performed in step S3024. In addition, the labeling mode can be a manual labeling mode, a machine labeling mode or even a man-machine combined labeling mode. The sample labeling result may be embodied by positive and negative samples, or by sample score or sample sorting, or by Pairwise points obtained after sorting, which is not limited in the present invention.

Step S3025, determining a feature vector of at least one text object according to the semantic features corresponding to the at least one text object, and determining an evaluation score of each text object in the at least one text object by combining the text object ranking model and the feature vector of the at least one text object.

Determining a feature vector of at least one text object according to the semantic features corresponding to the at least one text object obtained in step S3023, and determining an evaluation score of each text object in the at least one text object by combining the text object ranking model obtained through training in step S3024. The specific comment score is 3 points, and the text object is commented by a very wonderful user; 2, the text object is attractive and good, and the user can possibly comment; 1, the text object is good for attracting the pen, but the user may not comment; score 0, text object has no value and no meaning, etc.

Step S3026, ranking the at least one text object according to the evaluation score.

And sequencing at least one text object according to the obtained comment score. Text objects with high scores are ranked first when ordered.

The at least one text object is sequenced according to the related information of the at least one text object, namely, the text object content, the comment information and the like in the steps.

Step S3027, according to the sorting result, screening the text objects sorted in the top specified number as at least one text object obtained by screening.

According to the ordering result of the text objects, preferably, a specified number of the text objects ordered at the top can be screened out as the text objects generating the topics of the electronic book. These text objects belong to the text objects with better quality and popularity. For text objects that are ranked behind and do not attract a user to comment on value, an e-book topic may not be generated for them. The specified number of specific screens is not limiting.

Through the steps, at least one text object is screened according to the related information of the text object, namely the text object content, comment information and the like.

And step S303, filtering the comment information of each text object according to a preset filtering rule.

The comment information may include many pieces of repeated comment information, or some pieces of comment information may be spam comment information such as advertisement information, which does not provide a recommendation effect for the user on the text object. The comment information in these text objects is required for filtering.

In filtering, filtering may be performed using a preset filtering rule. For example, a sensitive word lexicon can be preset according to the rule of filtering the sensitive words, and sensitive words such as reaction, dirt, common words of advertisements and the like are stored in the lexicon to remove the spam comment information. A rule for filtering out repeated comments can be set, and only one or all of the repeated comment information can be reserved or filtered out by comparing the comment information; a rule for filtering the comment information with the word number lower than a preset word number threshold value can be set, for example, comment information with the word number less than 10 words is filtered, and comment information with less word number such as 'good look' and 'haha' is filtered; and a rule that the comment information praise number filtered out is lower than a preset praise number threshold value can be set, and only high-quality comment information with more praise numbers is retained. The preset filtering rule is set according to implementation conditions, and is not limited herein.

Step S304, the comment information of each text object is respectively sorted.

The order of the comment information is also important when the user reads the comment information. If the comment information read first cannot provide valuable comment information for the user, the user may not continue reading. Therefore, the comment information needs to be sorted to attract the user to continue reading.

And during sorting, respectively sorting the comment information of each text object according to the comment information sorting rule. If the user interest is ranked according to a ranking rule, for example, daily reading habits of the user are collected, the content which the user is interested in is obtained, and comment information containing the content which the user is interested in is ranked in front of the comment information; different orders can be carried out on the comment information according to different users; the rule of sequencing can be further carried out according to the number of praise, the more the praise number is, the better the comment information is, and sequencing is carried out in sequence according to the number of praise number; the latest comment information of the comment time can be arranged in front according to the rule of sequencing the comment information time, and the timeliness of the comment information is kept. The setting of the comment information sorting rule is set according to the implementation situation, and is not limited herein.

Further, step S303 and step S304 may also be executed before step S302, and the comment information of the obtained text object only retains the high-quality comment information, and then the text objects retaining only the high-quality comment information are sorted, so that a more accurate sorting result can be obtained.

Step S305, generating the e-book topics according to the text object contents of the text objects and the sequenced comment information.

After the steps are executed, the electronic book topics can be correspondingly generated according to the text object contents of the text objects obtained through screening and the filtered and sequenced comment information.

Step S306, summarizing at least one electronic book topic in at least one electronic book to obtain a topic square page.

When at least one electronic book topic in at least one electronic book is summarized, the summary can be carried out in multiple modes, and different reading requirements of users are met. If so, summarizing at least one electronic book topic in at least one electronic book according to the book ID to obtain a topic square page of the specific book. The topic square pages of the electronic books are obtained by summarizing one or more electronic book topics in each electronic book according to the book ID of each electronic book, and a user can select to view the topic square pages of each electronic book. Furthermore, the electronic book topics in the electronic book square page can be sequenced, for example, sequencing is performed according to the electronic book scenarios, or sequencing is performed according to the number of comment information in the electronic book topics, or sequencing is performed according to the generation time of the electronic book topics, so that the electronic book topics in the topic square page are sequenced, and the electronic book square page is convenient for a user to view.

When at least one e-book topic in at least one e-book is summarized, at least one e-book topic in at least one e-book can be summarized according to the reading interest of the current user, and a topic square page conforming to the reading interest of the current user is obtained. If the user is interested in the swordsmen electronic book, the swordsmen electronic book topics can be collected to obtain the topic court page of the swordsmen electronic book topics. Furthermore, the electronic book topics can be sequenced, for example, the electronic book topics in the topic square page are sequenced in a mode of sequencing according to the number of the comment information in the electronic book topics, or sequencing according to the generation time of the electronic book topics, so that a user can conveniently check the electronic book topics.

When at least one electronic book topic in at least one electronic book is summarized, the at least one electronic book topic in the at least one electronic book can be summarized according to the current heat of each electronic book topic to obtain a topic square page with higher current heat. For example, summarizing according to different click rates of the topics of the electronic book, and obtaining topic square pages after summarizing of the topics of the electronic book of different classifications such as daily click rate, weekly click rate, monthly click rate, total click rate and the like.

When at least one electronic book topic in at least one electronic book is summarized, at least one electronic book topic in at least one electronic book can be sequenced, and a user can conveniently check the topics according to different sequencing sequences. The ranking may be performed in conjunction with the above-described aggregation, or after aggregation, the electronic book topics may be ranked. And obtaining a topic square page according to the sequencing result of the electronic book. When at least one e-book topic in at least one e-book is sequenced, the corresponding e-book topic can be sequenced according to the sequencing result of at least one text object. Or the corresponding electronic book topics can be sorted according to the topic sorting rule. Specifically, as the rule of sequencing according to the user interests, the user is interested in the swordsmen electronic books, and the swordsmen electronic book topics can be sequenced in front; or according to the rule of topic popularity ordering, if the current users read the electronic book of Beijing, the electronic book topics generated by the text objects in the electronic book are ordered in the front; or ordering according to the reading sequence of the user, and ordering the electronic book topics generated by the text objects in the electronic book being read by the current user in the front; or sequencing the corresponding electronic book topics according to the sequencing rule of the electronic book scenarios and the sequence of the position information of the text objects in the electronic book and the trend sequence of the scenarios; or sequencing according to the number of the comment information, and sequencing the e-book topics containing more comment information in the front; or a rule for sorting according to time, sorting according to the latest time of the comment information, and the like. After the plurality of electronic book topics are gathered, sequencing the corresponding electronic book topics according to a topic sequencing rule to obtain a topic square page.

The electronic book topics can be summarized and sequenced in any mode to obtain topic square pages, and the electronic book topics can also be sequenced and summarized in various modes to obtain topic square pages. The invention is not limited thereto.

Step S307, receiving an access request of the topic square page sent by the client.

Step S308, judging whether the client has the right to access the specific comment information in the topic square page.

And receiving an access request of the topic square page sent by the client, and sending the topic square page to the client for the client to display. However, some specific comment information in the comment information is paid comment information, and the user can read the comment information after paying. Such as comment information written by experts, stars and the like. Therefore, before sending the topic square page to the client, it is necessary to determine whether the client has the right to access the specific comment information in the topic square page, that is, determine whether the client has paid and purchased the reading right of the specific comment information, if yes, execute step S309, otherwise, execute step S310.

Step S309, the topic square page containing the specific comment information is sent to the client for showing.

And sending the topic square page containing the specific content of the specific comment information to a client for displaying, so that the user can see the specific content of the specific comment information.

And step S310, sending the topic square page hiding the specific comment information to the client for showing.

The specific content of the specific comment information is hidden and can be displayed in a payment button mode, the topic square page where the specific comment information is hidden is sent to the client to be displayed, and after a user sees the payment button, the user can independently select whether to pay to read the specific content of the specific comment information.

After the topic square page is sent to the client, the topic square page can be displayed on the client in a waterfall flow mode. When the topic square page is displayed, partial or all text object contents of each text object and partial or all comment information are displayed in blocks according to factors such as the size of a display interface, the length of text object contents in the text objects, the amount of comment information, the length of comment information and the like.

According to the method for generating topics based on the electronic book, provided by the invention, potential semantic relations among a large number of text objects are mined through a machine learning algorithm, and the latent semantic features of the text objects and the semantic features according to the designated dimensions are determined according to the latent semantic features. The text object ordering model trained according to the semantic features can better determine the quality of each text object, and orders the text objects to obtain the text objects with high quality and high hot spots, so that the quality of the corresponding generated electronic book topics is high. Meanwhile, the comment information is filtered and sequenced, so that the user experience during reading is better. And classifying and sequencing the generated e-book topics so as to promote the reading interest of the user on the e-book topics. Furthermore, the reading authority of the specific comment information is judged, and the correct display of the topic square page is guaranteed.

EXAMPLE III

After the topic square page is obtained, the contents of each text object and comment information of the text object can be seen on the topic square page, when a user reads the electronic book topics, the user has reading interest in the corresponding electronic book, and when the user wants to read the electronic book, or when the user wants to read the electronic book in detail and the comment information of a certain text object, the following steps can be further carried out, so that the two-way interaction between the electronic book and the electronic book topics is realized, and the reading of the user is facilitated.

Fig. 5 shows a flowchart of a method for interacting an electronic book with an electronic book topic according to a third embodiment of the present invention, and as shown in fig. 5, the method includes the following steps:

step S501, an association relation between an electronic book text object and an electronic book topic in a topic square page is established.

Because the electronic book topics are generated according to the related information of the text objects of the electronic book, the association relationship between each text object of the electronic book and each corresponding electronic book topic in the topic square page can be established according to the related information of each text object in the electronic book. The related information of the text object includes at least one of: book ID of the electronic book, chapter ID, position information of the text object in the electronic book, content of the text object, comment information on the text object. When the content of the electronic book is long and includes a plurality of chapters, and the plurality of chapters further include a plurality of paragraphs, the text object position information is information such as a specific paragraph position in a specific chapter or a specific line number position of a specific paragraph position in a more detailed specific chapter. The electronic book chapter ID can conveniently and quickly locate the electronic book text object, and meanwhile, the position of the electronic book text object in the electronic book can be known according to the chapter ID, so that the plot development position where the text object is located can be conveniently known.

Step S502, according to a first trigger request for a first specified text object in an electronic book page sent by a client, a first specified topic associated with the first specified text object is inquired, and a first specified topic display page is returned to the client.

When a user reads an electronic book, if the user wants to read an electronic book topic corresponding to a certain specified text object in detail, according to a first trigger request for a first specified text object sent by a client on a page of the electronic book, the first trigger request carries relevant information of the text object. Due to the fact that the text object and the e-book topics have the association relationship, according to the relevant information of the text object carried by the first trigger request, the first specified topic associated with the first specified text object can be inquired. And then returning the first specified topic display page to the client.

Before the first specified topic display page is returned to the client, some specific comment information in the first specified topic display page is paid comment information, and the user can read the comment information after paying. Such as comment information written by experts, stars and the like. Therefore, before the first specified topic display page is returned to the client, whether the client has the right to access the specific comment information of the first specified topic needs to be judged, namely whether the client pays for purchasing the reading right of the specific comment information is judged, if yes, the first specified topic display page containing the specific comment information is returned to the client, namely the user can see the specific content of the specific comment information; and if not, returning the first specified topic display page hiding the specific comment information to the client. Namely, the specific content of the specific comment information is hidden, the specific content can be displayed as a payment button, and the first specified topic display page for hiding the specific comment information is returned to the client. After the user sees the payment button, the user can autonomously select whether to pay to read the specific content of the specific comment information.

In the page of the electronic book, text objects in the electronic book can be traversed, text objects which have an association relationship with topics in a topic square are detected, and the text objects are determined to be topic text objects. In the electronic book page, the topic text object can be displayed in a specific mark mode. Such as displaying the topic text object in red font.

In the topic presentation page, as in the first specified topic presentation page, the text object content of the first specified topic is displayed, as in the page shown in fig. 6. Wherein the first specified topic includes textual object content and contextual content. And displaying the text object content in a specific marking mode, and normally displaying the context content without marking. If the text object is displayed in a red font, the context content black font is normally displayed.

Step S503, according to a second trigger request for a second specified topic in the topic square page sent by the client, querying a second specified text object associated with the second specified topic, and returning a related page of a second electronic book to which the second specified text object belongs to the client.

When a user reads an electronic book topic on a topic square page, if the user wants to read an electronic book corresponding to a certain electronic book topic, the topic square page may include a button for trying to read the book, as shown in fig. 6. The user can click a button for trying to read the book, and according to a second trigger request for a second specified topic in the topic square page sent by the client, the second trigger request carries relevant information of an electronic book text object corresponding to the electronic book topic. Due to the fact that the text object and the electronic book topic have the association relation, according to the related information of the electronic book text object corresponding to the electronic book topic carried by the second trigger request, a second specified text object associated with the second specified topic can be inquired. And then the related page of the second electronic book to which the second specified text object belongs is returned to the client.

The relevant page of the second electronic book to which the second specified text object belongs may be a book detail page of the second electronic book. At this time, the second trigger request carries the book ID of the electronic book to which the second specified text object belongs. According to the book ID carried in the second trigger request, the electronic book to which the second specified text object belongs may be determined. And then sending the book detail page of the electronic book to which the second specified text object belongs to the client for displaying.

The related page of the second electronic book to which the second specified text object belongs may also be the page of the electronic book to which the second specified text object belongs. At this time, the second trigger request carries the book ID and the chapter ID of the electronic book to which the second specified text object belongs, and the position information of the second specified text object in the second electronic book. According to the book ID, the chapter ID and the position information of the second specified text object in the second electronic book carried in the second trigger request, the electronic book page where the second specified text object is located can be determined in the second electronic book, and therefore the electronic book page where the second specified text object is located is sent to the client. Because some electronic book text objects need to be read only by paying, before sending the electronic book page where the second specified text object is located to the client, whether the client has the reading right of the electronic book page where the second specified text object is located needs to be judged, that is, whether a user has purchased the reading right of the electronic book page where the second specified text object is located is judged, and if so, the electronic book page where the second specified text object is located is returned to the client; if not, displaying the permission request page, namely the payment page. And after the client side obtains the reading permission, namely after the user pays for purchasing the reading permission of the e-book page where the second specified text object is located, returning the e-book page where the second specified text object is located to the client side.

In the ebook page returned to the client, the second specified text object needs to be marked in a specific marking manner. For example, the second specified text object is marked in a red font, so that when a user reads the second specified text object, the user can clearly know that the second specified text object has comment information, is associated with the second specified topic, and can interact with the corresponding second specified topic.

Step S504, adding comment information at the first specified text object in the page of the electronic book according to a request for adding comment information to the first specified text object in the page of the electronic book, which is sent by a client; and querying a first specified topic associated with the first specified text object, and synchronizing the comment information to the first specified topic in the topic square.

The user can also add comment information to the text object of the electronic book in the process of reading the electronic book, and add the comment information to the first specified text object in the page of the electronic book according to a request sent by the client for adding the comment information to the first specified text object in the page of the electronic book. Meanwhile, a first specified topic associated with the first specified text object is inquired according to the related information of the first specified text object, and the comment information is synchronized to the first specified topic in the topic square, so that the first specified topic can be synchronously displayed or synchronously added comment information can be conveniently obtained.

Step S505, adding comment information to a second specified topic display page according to a request for adding comment information to the second specified topic in the second specified topic display page, which is sent by a client; and querying a second specified text object associated with the second specified topic, and synchronizing the comment information to the second specified text object.

The user may also add comment information to the second specified topic on the second specified topic presentation page as shown in fig. 6, and add comment information to the second specified topic presentation page according to a request sent by the client to add comment information to the second specified topic on the second specified topic presentation page. Meanwhile, a second specified text object associated with a second specified topic is inquired, and the comment information is synchronized to the second specified text object, so that the user can conveniently check the added comment information at the second specified text object when reading the second specified text object of the electronic book.

Step S506, receiving a sharing request sent by the client and initiated on a second specified topic display page; and sharing the second specified topic to the friend user.

When the user reads the second specified topic display page, the user can share the second specified topic. Specifically, a sharing request sent by the client and initiated on a second specified topic display page is received, and the second specified topic is shared to the friend users, so that the friend users can share the topic conveniently.

Step S507, according to a book ID carrying an electronic book and sent by the client on the first specified topic display page, an upper-level skip request is made, an electronic book topic associated with the book ID of the electronic book is queried, and a topic square page containing the electronic book topic is returned to the client.

When a user reads an electronic book, a first trigger request for a first specified text object can be triggered from a page of the electronic book to obtain a first specified topic display page, and the first specified topic associated with the first specified text object is viewed. Further, when the user views the first specified topic presentation page, the user can jump upwards from the first topic presentation page to view the topic square page of the topic related to the electronic book. Specifically, according to a request for jumping to the upper level by a book ID carrying an electronic book, which is sent by a client on a first specified topic display page, an electronic book topic associated with the book ID of the electronic book is inquired, and a topic square page containing the electronic book topic is returned to the client. The topic contained in the topic square page is a topic related to the electronic book, namely an electronic book topic of a text object in the electronic book, so that a user can conveniently find all related topics of the electronic book at one time, and the electronic book can be more thoroughly understood.

There is no context relationship between the above steps S502-S507, and the corresponding steps are executed according to the request sent by the client.

According to the method for generating the topic based on the electronic book, provided by the invention, the incidence relation between the text object of the electronic book and the topic of the electronic book in the topic square page is established. According to a first trigger request for a first specified text object in an electronic book page sent by a client, a first specified topic associated with the first specified text object is inquired, and a first specified topic display page is returned to the client. The user can directly jump to the topic display page on the electronic page surface to check related topics. Furthermore, the topic display page can jump upwards to a topic square page containing other related topics of the electronic book, so that a user can conveniently check other related topics of the electronic book, and the electronic book can be known more. And according to a second trigger request for a second specified topic in the topic square page sent by the client, querying a second specified text object associated with the second specified topic, and returning a related page of a second electronic book to which the second specified text object belongs to the client. The method and the device facilitate the user to directly jump to the page of the electronic book on the topic display page to read the electronic book, and reduce the complicated process of searching the electronic book. Furthermore, when the electronic book pages are jumped to, the book detail pages of the electronic book can be jumped to, so that the user can conveniently know the overall plot information of the electronic book; or jumping to the page of the electronic book where the text object is located, and directly reading the corresponding text object content; and the reading authority of the content of the specific text object in the electronic book can be detected, and whether the user pays or not is detected when the user needs to pay to read. The method avoids directly displaying the text object content of the electronic book needing to be read for payment, and hardly causes loss to an electronic book provider. Interfaces for adding comment information are provided on the pages of the electronic book and the topic display pages, when comment information is added on any page of the pages of the electronic book and the topic display pages, the two pages are kept in bidirectional synchronization, and the comment information added on one page can be synchronized to the other page. The invention also judges the reading authority of the specific comment information, and ensures the correct display of the topic display page. The invention can also share the topics to the friend users, so that the friend users can share the topics.

Example four

An embodiment of the present application provides a non-volatile computer storage medium, where the computer storage medium stores at least one executable instruction, and the computer executable instruction may execute the method for generating topics based on electronic books in any of the method embodiments.

The executable instructions may be specifically configured to cause the processor to:

acquiring related information of at least one text object containing comment information in at least one electronic book, and generating at least one corresponding electronic book topic; the electronic book topics comprise text object contents and comment information of at least one text object; summarizing at least one electronic book topic in at least one electronic book to obtain a topic square page; and displaying the text content and/or comment information of each electronic book topic on the topic square page.

In an alternative embodiment, the executable instructions further cause the processor to: screening the at least one text object according to the related information of the at least one text object; the related information of the text object comprises a book ID, a chapter ID, text object position information, text object content and/or comment information of the electronic book; and generating at least one corresponding electronic book topic according to the relevant information of the at least one text object obtained by screening.

In an alternative embodiment, the executable instructions further cause the processor to: sorting the at least one text object according to the related information of the at least one text object; and screening the text objects with the specified number ranked in the top as at least one text object obtained by screening according to the sorting result.

In an alternative embodiment, the executable instructions further cause the processor to: determining semantic features corresponding to preset text object samples and semantic features corresponding to at least one text object, and determining feature vectors of the text object samples according to the semantic features corresponding to the text object samples; training the feature vectors of the text object samples by a machine learning algorithm and combining the sample labeling results of the text object samples to obtain a text object sequencing model; determining a feature vector of at least one text object according to semantic features corresponding to the at least one text object, and determining an evaluation score of each text object in the at least one text object by combining a text object sequencing model and the feature vector of the at least one text object; the at least one text object is sorted according to the evaluation score.

In an alternative embodiment, the semantic features include: latent semantic features and explicit semantic features; the latent semantic features are obtained according to a feature extraction algorithm, and the explicit semantic features are extracted according to specified dimensions.

In an alternative embodiment, the executable instructions further cause the processor to: and integrating a plurality of text objects adjacent to each other in position to form one text object.

In an alternative embodiment, the executable instructions further cause the processor to: and analyzing the text object contents of the text objects, integrating the text objects with the similarity of the text object contents larger than a preset threshold value, and combining the text objects into one text object.

In an alternative embodiment, the executable instructions further cause the processor to: ranking the comment information of each text object respectively; and generating the e-book topics according to the text object contents of the text objects and the sequenced comment information.

In an alternative embodiment, the executable instructions further cause the processor to: ranking the comment information of each text object according to a comment information ranking rule; wherein the comment information ordering rule comprises: the rules of ordering according to user interests, ordering according to the number of praise, and/or ordering according to comment information time.

In an alternative embodiment, the executable instructions further cause the processor to: filtering the comment information of each text object according to a preset filtering rule; wherein, the preset filtering rule comprises: the method comprises the steps of filtering according to sensitive words, filtering repeated comments, filtering comments information with the number of words lower than a preset word number threshold value and/or filtering comments information with the number of praise lower than a preset praise number threshold value.

In an alternative embodiment, the executable instructions further cause the processor to: summarizing at least one electronic book topic in at least one electronic book according to the book ID to obtain a topic square page of a specific book; or summarizing at least one electronic book topic in at least one electronic book according to the reading interest of the current user to obtain a topic square page which accords with the reading interest of the current user; or summarizing at least one electronic book topic in at least one electronic book according to the current heat of each electronic book topic to obtain a topic square page with higher current heat.

In an alternative embodiment, the executable instructions further cause the processor to: sequencing at least one e-book topic in at least one e-book; and obtaining a topic square page according to the sequencing result of the topics of the electronic book.

In an alternative embodiment, the executable instructions further cause the processor to: sequencing at least one electronic book topic according to a topic sequencing rule; wherein the topic ordering rule comprises: the electronic book system comprises a rule for sequencing according to the interest of a user, a rule for sequencing according to the popularity of a topic, a rule for sequencing according to the reading sequence of the user, a rule for sequencing according to the scenario of an electronic book, a rule for sequencing according to the number of comment information and/or a rule for sequencing according to time.

In an alternative embodiment, the executable instructions further cause the processor to: the method comprises the steps of receiving an access request of a topic square page sent by a client, sending the topic square page to the client, and displaying the topic square page at the client in a waterfall flow mode.

In an alternative embodiment, the topic square page blocks show part or all of the text object content of each text object and part or all of the comment information.

In an alternative embodiment, the executable instructions further cause the processor to: judging whether the client has the authority to access the specific comment information in the topic square page or not; if yes, sending the topic square page containing the specific comment information to a client for displaying; and if not, sending the topic square page hiding the specific comment information to the client for displaying.

In an alternative embodiment, the executable instructions further cause the processor to: and receiving an access request of a specified topic sent by the client, and sending a specified topic display page to the client, wherein the specified topic display page comprises all text object contents, the context of the text object contents and all comment information.

In an alternative embodiment, the executable instructions further cause the processor to: establishing an incidence relation between an electronic book text object and an electronic book topic in a topic square page; according to a first trigger request for a first specified text object in an electronic book page sent by a client, inquiring a first specified topic associated with the first specified text object, and returning a first specified topic display page to the client; according to a second trigger request for a second specified topic in the topic square page sent by the client, a second specified text object associated with the second specified topic is inquired, and a related page of a second electronic book to which the second specified text object belongs is returned to the client.

In an alternative embodiment, the executable instructions further cause the processor to: establishing an incidence relation between each text object of the electronic book and each corresponding electronic book topic in the topic square page according to the relevant information of each text object in the electronic book; wherein the related information of the text object comprises at least one of the following: book ID of the electronic book, chapter ID, position information of the text object in the electronic book, content of the text object, comment information on the text object.

In an alternative embodiment, the relevant pages of the second electronic book to which the second specified text object belongs are: a book detail page for a second electronic book; the second trigger request carries a book ID of a second electronic book to which the second specified text object belongs; the executable instructions further cause the processor to: determining a second electronic book to which the second specified text object belongs according to the book ID carried in the second trigger request; and sending the book detail page of the second electronic book to which the second specified text object belongs to the client for displaying.

In an alternative embodiment, the relevant pages of the second electronic book to which the second specified text object belongs are: a second designated text object is located on the page of the electronic book; the second trigger request carries a book ID and a chapter ID of a second electronic book to which the second specified text object belongs, and position information of the second specified text object in the second electronic book; the executable instructions further cause the processor to: determining an electronic book page where a second specified text object is located in a second electronic book according to the book ID, the chapter ID and the position information of the second specified text object in the second electronic book, wherein the book ID and the chapter ID are carried in the second trigger request; and sending the e-book page where the second specified text object is located to the client.

In an alternative embodiment, the executable instructions further cause the processor to: judging whether the client has the reading permission of the e-book page where the second specified text object is located; if so, sending the e-book page where the second specified text object is located to the client; and if not, displaying the permission request page, and after the client acquires the reading permission, sending the e-book page where the second specified text object is located to the client.

In an alternative embodiment, the executable instructions further cause the processor to: traversing each text object in the electronic book, detecting a text object having an association relation with a topic in a topic square, and determining the text object as a topic text object; in an electronic book page, topic text objects are displayed in a specific mark mode.

In an alternative embodiment, the executable instructions further cause the processor to: and marking the second specified text object in a specific marking mode in the page of the electronic book and returning the second specified text object to the client.

In an alternative embodiment, the executable instructions further cause the processor to: and displaying the text object content of the topic in a specific mark mode in the topic display page.

In an alternative embodiment, the executable instructions further cause the processor to: adding comment information at a first specified text object in an electronic book page according to a request for adding comment information to the first specified text object in the electronic book page, which is sent by a client; and querying a first specified topic associated with the first specified text object, and synchronizing the comment information to the first specified topic in the topic square page.

In an alternative embodiment, the executable instructions further cause the processor to: adding comment information to a second specified topic display page according to a request for adding comment information to the second specified topic in the second specified topic display page, which is sent by a client; and querying a second specified text object associated with the second specified topic, and synchronizing the comment information to the second specified text object.

In an alternative embodiment, the executable instructions further cause the processor to: receiving a sharing request sent by a client and initiated on a second specified topic display page; and sharing the second specified topic to the friend user.

In an alternative embodiment, the executable instructions further cause the processor to: judging whether the client has the authority of accessing the specific comment information of the first specified topic; if yes, returning a first specified topic display page containing specific comment information to the client; and if not, returning the first specified topic display page hiding the specific comment information to the client.

In an alternative embodiment, the executable instructions further cause the processor to: according to a request for jumping to a superior level by a book ID carrying an electronic book, which is sent by a client on a first specified topic display page, an electronic book topic associated with the book ID of the electronic book is inquired, and a topic square page containing the electronic book topic associated with the book ID of the electronic book is returned to the client.

EXAMPLE five

Fig. 7 is a schematic structural diagram of a computing device according to a fifth embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.

As shown in fig. 7, the computing device may include: a processor (processor)702, a Communications Interface 704, a memory 706, and a communication bus 708.

Wherein:

the processor 702, communication interface 704, and memory 706 communicate with each other via a communication bus 708.

A communication interface 704 for communicating with network elements of other devices, such as clients or other servers.

The processor 702 is configured to execute the program 710, and may specifically execute relevant steps in the above method for generating topics based on electronic books.

In particular, the program 710 may include program code that includes computer operating instructions.

The processor 702 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the present invention. The server comprises one or more processors, which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.

The memory 706 stores a program 710. The memory 706 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 710 may specifically be used to cause the processor 702 to perform the following operations:

in an alternative embodiment, the program 710 is configured to enable the processor 702 to obtain related information of at least one text object containing comment information in at least one electronic book, and generate at least one corresponding electronic book topic; the electronic book topics comprise text object contents and comment information of at least one text object; summarizing at least one electronic book topic in at least one electronic book to obtain a topic square page; and displaying the text content and/or comment information of each electronic book topic on the topic square page.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to filter the at least one text object according to information about the at least one text object; the related information of the text object comprises book ID, chapter ID, text object position information, text object content and/or comment information of the electronic book; and generating at least one corresponding electronic book topic according to the relevant information of the at least one text object obtained by screening.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to rank the at least one text object according to information about the at least one text object; and screening the text objects with the specified number in the front order as at least one screened text object according to the sorting result.

In an optional implementation, the program 710 is configured to enable the processor 702 to determine preset semantic features corresponding to each text object sample and semantic features corresponding to at least one text object, and determine a feature vector of each text object sample according to the semantic features corresponding to each text object sample; training the feature vectors of the text object samples by a machine learning algorithm and combining the sample labeling results of the text object samples to obtain a text object ordering model; determining a feature vector of at least one text object according to semantic features corresponding to the at least one text object, and determining an evaluation score of each text object in the at least one text object by combining a text object sequencing model and the feature vector of the at least one text object; the at least one textual object is ranked according to the evaluation score.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to integrate and process a plurality of adjacently located text objects into one text object.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to analyze the text object contents of a plurality of text objects, integrate and process the text objects with the similarity greater than a preset threshold, and combine the text objects into one text object.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to sort the comment information of each text object separately; and generating the e-book topics according to the text object contents of the text objects and the sequenced comment information.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to sort the comment information of each text object according to a comment information sorting rule; the comment information ordering rule comprises the following steps: the rules of ranking according to user interest, ranking according to praise number, and/or ranking according to comment information time.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to filter comment information of each text object according to a preset filtering rule; wherein, preset filtering rules include: the comment processing method comprises the steps of filtering according to sensitive words, filtering repeated comments, filtering comments information with the number of words lower than a preset word number threshold value and/or filtering comments information with the number of praise lower than a preset praise number threshold value.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to summarize at least one e-book topic in at least one e-book according to a book ID to obtain a topic square page of a specific book; or summarizing at least one electronic book topic in at least one electronic book according to the reading interest of the current user to obtain a topic square page which accords with the reading interest of the current user; or summarizing at least one electronic book topic in at least one electronic book according to the current heat of each electronic book topic to obtain a topic square page with higher current heat.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to order at least one ebook topic in at least one ebook; and obtaining a topic square page according to the sequencing result of the electronic book topics.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to order at least one ebook topic according to a topic ordering rule; wherein the topic ordering rule comprises: the rule of ordering according to user interests, the rule of ordering according to topic popularity, the rule of ordering according to user reading sequence, the rule of ordering according to e-book scenarios, the rule of ordering according to comment information quantity and/or the rule of ordering according to time.

In an optional implementation, the program 710 is configured to enable the processor 702 to receive an access request of a topic square page sent by a client, send the topic square page to the client, and display the topic square page on the client in a waterfall flow manner.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to determine whether the client has permission to access particular comment information in the topic plaza page; if yes, sending the topic square page containing the specific comment information to a client for displaying; and if not, sending the topic square page hiding the specific comment information to the client for displaying.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to receive an access request of a specified topic sent by a client, and send a specified topic presentation page to the client, where the specified topic presentation page contains all text object contents, contexts of the text object contents, and all comment information.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to establish an association between an e-book text object and an e-book topic in a topic square page; according to a first trigger request for a first specified text object in an electronic book page sent by a client, inquiring a first specified topic associated with the first specified text object, and returning a first specified topic display page to the client; and according to a second trigger request for a second specified topic in the topic square page sent by the client, querying a second specified text object associated with the second specified topic, and returning a related page of a second electronic book to which the second specified text object belongs to the client.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to establish an association relationship between each text object of the electronic book and each corresponding electronic book topic in the topic square page according to the related information of each text object in the electronic book; wherein the related information of the text object comprises at least one of the following: book ID of the electronic book, chapter ID, position information of the text object in the electronic book, content of the text object, comment information on the text object.

In an alternative embodiment, the relevant pages of the second electronic book to which the second specified text object belongs are: a book detail page for a second electronic book; the second trigger request carries a book ID of a second electronic book to which the second specified text object belongs; the program 710 is configured to enable the processor 702 to determine, according to the book ID carried in the second trigger request, a second electronic book to which the second specified text object belongs; and sending the book detail page of the second electronic book to which the second specified text object belongs to the client for displaying.

In an alternative embodiment, the relevant pages of the second electronic book to which the second specified text object belongs are: a second designated text object is located on the page of the electronic book; the second trigger request carries a book ID and a chapter ID of a second electronic book to which the second specified text object belongs, and position information of the second specified text object in the second electronic book; the program 710 is configured to enable the processor 702 to determine, according to the book ID, the chapter ID, and the location information of the second specified text object in the second electronic book, an electronic book page where the second specified text object is located in the second electronic book; and sending the e-book page where the second specified text object is located to the client.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to determine whether the client has the reading right of the ebook page where the second specified text object is located; if so, sending the e-book page where the second specified text object is to the client; and if not, displaying the permission request page, and after the client acquires the reading permission, sending the e-book page where the second specified text object is located to the client.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to traverse text objects in the electronic book, detect a text object having an association relationship with a topic in a topic square, and determine the text object as a topic text object; in an electronic book page, topic text objects are displayed in a specific mark mode.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to mark a second specified text object in a particular mark back to the client on the page of the ebook.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to display the text object content of the topic in a particular markup manner in the topic presentation page.

In an alternative embodiment, program 710 is configured to cause processor 702 to add comment information at a first specified text object in a page of an electronic book according to a client-sent request to add comment information to the first specified text object in the page of the electronic book; and querying a first specified topic associated with the first specified text object, and synchronizing the comment information to the first specified topic in the topic square page.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to add comment information on a second specified topic presentation page according to a request sent by a client to add comment information on the second specified topic presentation page; and querying a second specified text object associated with the second specified topic, and synchronizing the comment information to the second specified text object.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to receive a sharing request sent by a client and initiated on a second specified topic presentation page; and sharing the second specified topic to the friend user.

In an alternative embodiment, the program 710 is configured to cause the processor 702 to determine whether the client has permission to access particular comment information on a first specified topic; if yes, returning a first specified topic display page containing specific comment information to the client; and if not, returning the first specified topic display page hiding the specific comment information to the client.

In an alternative embodiment, the program 710 is configured to enable the processor 702 to query an electronic book topic associated with the book ID of the electronic book according to a request for jumping to the upper level by the client based on the book ID carrying the electronic book sent from the first specified topic presentation page, and return a topic square page containing the electronic book topic associated with the book ID of the electronic book to the client.

For specific implementation of each step in the program 710, reference may be made to the corresponding description in the corresponding step in the above embodiment based on the topic generated by the electronic book, which is not described herein again. It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, and are not described herein again.

According to the scheme provided by the embodiment, the related information of at least one text object containing comment information in at least one electronic book is acquired, and at least one corresponding electronic book topic is generated; the electronic book topics comprise text object contents and comment information of at least one text object; summarizing at least one electronic book topic in at least one electronic book to obtain a topic square page; and displaying the text content and/or comment information of each electronic book topic on the topic square page. By acquiring the relevant information of the text object containing the comment information in the electronic book and generating the corresponding electronic book topic for the text object, the comment information of the text object is effectively utilized, and more users can know the electronic book through the electronic book topic.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and placed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Moreover, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than others, the combination of features of different embodiments is intended to be within the scope of the invention and form part of different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims

1. A method of generating topics based on e-books, comprising:

acquiring related information of at least one text object containing comment information in at least one electronic book, and generating at least one corresponding electronic book topic; wherein the e-book topic comprises textual object content and comment information for the at least one textual object; the text object content is the character content of the text object in the electronic book;

summarizing at least one electronic book topic in the at least one electronic book to obtain a topic square page; the topic square page is composed of one or more electronic book topics;

displaying the text content and comment information of each electronic book topic on the topic square page; the topic square page also comprises a book trial reading button, wherein when a user clicks the book trial reading button, the electronic book page to which the text object content in the electronic book topic belongs is returned;

wherein the e-book topic further comprises contextual content; displaying the text object content in a specific marking mode, and normally displaying the context content without marking;

the obtaining of the relevant information of at least one text object containing comment information in at least one electronic book and generating of the corresponding at least one electronic book topic further includes:

determining a feature vector of the at least one text object according to semantic features corresponding to the at least one text object, and determining an evaluation score of each text object in the at least one text object by combining a text object ordering model and the feature vector of the at least one text object;

ranking the at least one textual object according to the evaluation score;

according to the sorting result, screening the text objects with the designated number sorted in the front as at least one text object obtained by screening;

and generating at least one corresponding electronic book topic according to the relevant information of the at least one text object obtained by screening.

2. The method of claim 1, wherein the information related to the text object includes a book ID, a chapter ID, text object location information, text object content, and/or comment information of the electronic book.

3. The method of claim 1, wherein the method further comprises:

determining semantic features corresponding to preset text object samples and semantic features corresponding to the at least one text object, and determining feature vectors of the text object samples according to the semantic features corresponding to the text object samples;

and training the characteristic vectors of the text object samples by a machine learning algorithm and combining the sample labeling results of the text object samples to obtain a text object sequencing model.

4. The method of claim 3, wherein the semantic features comprise: latent semantic features and explicit semantic features; the latent semantic features are obtained according to a feature extraction algorithm, and the explicit semantic features are extracted according to a specified dimension.

5. The method of claim 1, wherein before determining the feature vector of the at least one text object according to the semantic features corresponding to the at least one text object, and determining the evaluation score of each text object in the at least one text object by combining a text object ordering model and the feature vector of the at least one text object, the method further comprises:

and integrating a plurality of text objects adjacent to each other in position to form one text object.

6. The method of claim 1, wherein before determining the feature vector of the at least one text object according to the semantic features corresponding to the at least one text object, and determining the evaluation score of each text object in the at least one text object by combining a text object ordering model and the feature vector of the at least one text object, the method further comprises:

and analyzing the text object contents of the text objects, integrating the text objects with the similarity of the text object contents larger than a preset threshold value, and combining the text objects into one text object.

7. The method of any one of claims 1-6, wherein the obtaining information about at least one text object containing comment information in at least one electronic book, and the generating of the corresponding at least one electronic book topic further comprises:

ranking the comment information of each text object respectively;

and generating the e-book topics according to the text object contents of the text objects and the sequenced comment information.

8. The method of claim 7, wherein said individually ranking the comment information of the respective text object further comprises:

ranking the comment information of each text object according to a comment information ranking rule; wherein the comment information sorting rule comprises: the rules of ranking according to user interest, ranking according to praise number, and/or ranking according to comment information time.

9. The method of any of claims 1-6, wherein, prior to the generating the corresponding at least one ebook topic, the method further comprises:

filtering the comment information of each text object according to a preset filtering rule; wherein the preset filtering rule comprises: the comment processing method comprises the steps of filtering according to sensitive words, filtering repeated comments, filtering comments information with the number of words lower than a preset word number threshold value and/or filtering comments information with the number of praise lower than a preset praise number threshold value.

10. The method of any one of claims 1-6, wherein the aggregating at least one electronic book topic in the at least one electronic book to obtain a topic square page further comprises:

summarizing at least one electronic book topic in the at least one electronic book according to the book ID to obtain a topic square page of a specific book; or,

summarizing at least one electronic book topic in the at least one electronic book according to the reading interest of the current user to obtain a topic square page which accords with the reading interest of the current user; or,

summarizing at least one electronic book topic in the at least one electronic book according to the current heat of each electronic book topic to obtain a topic square page with higher current heat.

11. The method of any one of claims 1-6, wherein the aggregating at least one electronic book topic in the at least one electronic book to obtain a topic square page further comprises:

sequencing at least one e-book topic in the at least one e-book;

and obtaining a topic square page according to the sequencing result of the electronic book topics.

12. The method of claim 10, wherein the ordering at least one ebook topic of the at least one ebook further comprises:

sequencing the at least one e-book topic according to a topic sequencing rule; wherein the topic ordering rule comprises: the electronic book system comprises a rule for sequencing according to the interest of a user, a rule for sequencing according to topic popularity, a rule for sequencing according to the reading sequence of the user, a rule for sequencing according to the scenario of an electronic book, a rule for sequencing according to the number of comment information and/or a rule for sequencing according to time.

13. The method of any of claims 1-6, wherein the displaying text content and comment information for each electronic book topic on the topic square page further comprises:

the method comprises the steps of receiving an access request of a topic square page sent by a client, sending the topic square page to the client, and displaying the topic square page on the client in a waterfall flow mode.

14. The method of claim 13, wherein the topsides page tiles expose partial or all textual object content and partial or all comment information for each textual object.

15. The method of any of claims 1-6, wherein prior to the displaying of the textual content and comment information for each electronic book topic at the topic square page, the method further comprises:

judging whether the client has the authority to access the specific comment information in the topic square page or not;

if yes, sending the topic square page containing the specific comment information to a client for displaying;

and if not, sending the topic square page hiding the specific comment information to a client for displaying.

16. The method according to any one of claims 1-6, wherein the method further comprises:

receiving an access request of a specified topic sent by a client, and sending a specified topic display page to the client, wherein the specified topic display page comprises all text object contents, the context of the text object contents and all comment information.

17. The method of claim 16, wherein the method further comprises:

establishing an incidence relation between an electronic book text object and an electronic book topic in a topic square page;

according to a first trigger request for a first specified text object in an electronic book page sent by a client, inquiring a first specified topic associated with the first specified text object, and returning a first specified topic display page to the client;

according to a second trigger request for a second specified topic in the topic square page sent by the client, a second specified text object associated with the second specified topic is inquired, and a related page of a second electronic book to which the second specified text object belongs is returned to the client.

18. The method of claim 17, wherein the establishing an association of an e-book text object with an e-book topic in a topic square page further comprises:

establishing an incidence relation between each text object of the electronic book and each corresponding electronic book topic in the topic square page according to the relevant information of each text object in the electronic book;

wherein the related information of the text object comprises at least one of the following: book ID of the electronic book, chapter ID, position information of the text object in the electronic book, content of the text object, comment information on the text object.

19. The method of claim 18, wherein the relevant pages of the second electronic book to which the second designated text object belongs are: a book detail page of the second electronic book;

the second trigger request carries a book ID of a second electronic book to which the second specified text object belongs;

the returning the relevant page of the second electronic book to which the second specified text object belongs to the client comprises: determining a second electronic book to which the second specified text object belongs according to the book ID carried in the second trigger request; and sending the book detail page of the second electronic book to which the second specified text object belongs to the client for displaying.

20. The method of claim 18, wherein the relevant pages of the second electronic book to which the second designated text object belongs are: the electronic book page where the second specified text object is located;

the second trigger request carries a book ID and a chapter ID of a second electronic book to which the second specified text object belongs, and position information of the second specified text object in the second electronic book;

the returning the relevant page of the second electronic book to which the second specified text object belongs to the client comprises: determining an electronic book page where a second specified text object is located in the second electronic book according to the book ID, the chapter ID and the position information of the second specified text object in the second electronic book, wherein the book ID and the chapter ID are carried in the second trigger request; and sending the e-book page where the second specified text object is located to a client.

21. The method of claim 20, wherein prior to the sending the ebook page on which the second designated text object is located to the client, the method further comprises:

judging whether the client has the reading permission of the e-book page where the second specified text object is located;

if so, sending the e-book page where the second specified text object is located to a client; and if not, displaying an authority request page, and after the client acquires the reading authority, sending the e-book page where the second specified text object is located to the client.

22. The method of claim 17, wherein the method further comprises:

traversing each text object in the electronic book, detecting a text object having an association relation with a topic in a topic square, and determining the text object as a topic text object;

and displaying the topic text object in a specific mark mode in the page of the electronic book.

23. The method of claim 20, wherein the sending the ebook page on which the second specified text object is located to the client further comprises:

marking the second specified text object in a specific marking mode in the page of the electronic book.

24. The method of claim 17, wherein the method further comprises:

and displaying the text object content of the topic in a specific mark mode in the topic display page.

25. The method of claim 17, wherein the method further comprises:

adding comment information at a first specified text object in an electronic book page according to a request for adding comment information to the first specified text object in the electronic book page, which is sent by a client;

and querying a first specified topic associated with the first specified text object, and synchronizing the comment information to the first specified topic in the topic square page.

26. The method of claim 17, wherein the method further comprises:

adding comment information to a second specified topic display page according to a request for adding comment information to the second specified topic in the second specified topic display page, which is sent by a client;

and querying a second specified text object associated with a second specified topic, and synchronizing the comment information to the second specified text object.

27. The method of claim 17, wherein the method further comprises:

receiving a sharing request sent by a client and initiated on a second specified topic display page;

and sharing the second specified topic to the friend user.

28. The method of claim 17, wherein prior to said returning the first specified topic presentation page to the client, the method further comprises:

judging whether the client has the authority of accessing the specific comment information of the first specified topic;

if yes, returning a first specified topic display page containing the specific comment information to the client;

and if not, returning the first specified topic display page hiding the specific comment information to the client.

29. The method of claim 17, wherein the method further comprises:

and inquiring the e-book topics associated with the book IDs of the e-books according to a request for jumping to the upper level by the client side for the book IDs carrying the e-books, which is sent on the first specified topic display page, and returning a topic square page containing the e-book topics associated with the book IDs of the e-books to the client side.

30. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

ranking the at least one textual object according to the evaluation score;

31. The computing device of claim 30, the information related to the text object comprising a book ID, a chapter ID, text object location information, text object content, and/or comment information of the electronic book.

32. The computing device of claim 30, the executable instructions further cause the processor to:

33. The computing device of claim 32, the semantic features comprising: latent semantic features and explicit semantic features; the latent semantic features are obtained according to a feature extraction algorithm, and the explicit semantic features are extracted according to a specified dimension.

34. The computing device of claim 30, the executable instructions further cause the processor to:

35. The computing device of claim 30, the executable instructions further cause the processor to:

36. The computing device of any of claims 30-35, the executable instructions further cause the processor to:

ranking the comment information of each text object respectively;

37. The computing device of claim 36, the executable instructions further cause the processor to:

38. The computing device of any of claims 30-35, the executable instructions further cause the processor to:

39. The computing device of any of claims 30-35, the executable instructions further cause the processor to:

40. The computing device of any of claims 30-35, the executable instructions further cause the processor to:

sequencing at least one e-book topic in the at least one e-book;

41. The computing device of claim 39, the executable instructions further cause the processor to:

42. The computing device of any of claims 30-35, the executable instructions further cause the processor to:

43. The computing device of claim 42, the topic plaza page tile exposing some or all of the textual object content of each textual object, and some or all of the comment information.

44. The computing device of any of claims 30-35, the executable instructions further cause the processor to:

45. The computing device of any of claims 30-35, the executable instructions further cause the processor to:

46. The computing device of claim 45, the executable instructions further cause the processor to:

47. The computing device of claim 46, the executable instructions further cause the processor to:

48. The computing device of claim 47, the relevant pages of the second electronic book to which the second designated text object belongs being: a book detail page of the second electronic book;

the executable instructions further cause the processor to: determining a second electronic book to which the second specified text object belongs according to the book ID carried in the second trigger request; and sending the book detail page of the second electronic book to which the second specified text object belongs to the client for displaying.

49. The computing device of claim 47, the relevant pages of the second electronic book to which the second designated text object belongs being: the electronic book page where the second specified text object is located;

the executable instructions further cause the processor to: determining an electronic book page where a second specified text object is located in the second electronic book according to the book ID, the chapter ID and the position information of the second specified text object in the second electronic book, wherein the book ID and the chapter ID are carried in the second trigger request; and sending the e-book page where the second specified text object is located to a client.

50. The computing device of claim 49, the executable instructions further cause the processor to:

51. The computing device of claim 46, the executable instructions further cause the processor to:

52. The computing device of claim 49, the executable instructions further cause the processor to:

53. The computing device of claim 46, the executable instructions further cause the processor to:

54. The computing device of claim 46, the executable instructions further cause the processor to:

adding comment information at a first specified text object in an electronic book page according to a request sent by a client for adding the comment information to the first specified text object in the electronic book page;

55. The computing device of claim 46, the executable instructions further cause the processor to:

56. The computing device of claim 46, the executable instructions further cause the processor to:

and sharing the second specified topic to the friend user.

57. The computing device of claim 46, the executable instructions further cause the processor to:

58. The computing device of claim 46, the executable instructions further cause the processor to:

59. A computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to:

ranking the at least one textual object according to the evaluation score;

60. The computer storage medium of claim 59, the information related to the text object comprising a book ID, a chapter ID, text object location information, text object content, and/or comment information of the electronic book.

61. The computer storage medium of claim 59, the executable instructions further causing the processor to:

62. The computer storage medium of claim 61, the semantic features comprising: latent semantic features and explicit semantic features; the latent semantic features are obtained according to a feature extraction algorithm, and the explicit semantic features are extracted according to a specified dimension.

63. The computer storage medium of claim 59, the executable instructions further causing the processor to:

64. The computer storage medium of claim 59, the executable instructions further causing the processor to:

65. The computer storage medium of any one of claims 59-64, the executable instructions further cause the processor to:

ranking the comment information of each text object respectively;

66. The computer storage medium of claim 65, the executable instructions further causing the processor to:

67. The computer storage medium of any one of claims 59-64, the executable instructions further cause the processor to:

68. The computer storage medium of any one of claims 59-64, the executable instructions further cause the processor to:

69. The computer storage medium of any one of claims 59-64, the executable instructions further cause the processor to:

sequencing at least one e-book topic in the at least one e-book;

70. The computer storage medium of claim 68, the executable instructions further causing the processor to:

71. The computer storage medium of any one of claims 59-64, the executable instructions further cause the processor to:

72. The computer storage medium of claim 71, the topsides page tiles exposing partial or full textual object content of respective textual objects and partial or full comment information.

73. The computer storage medium of any one of claims 59-64, the executable instructions further cause the processor to:

74. The computer storage medium of any one of claims 59-64, the executable instructions further cause the processor to:

75. The computer storage medium of claim 74, the executable instructions further causing the processor to:

76. The computer storage medium of claim 75, the executable instructions further causing the processor to:

77. The computer storage medium of claim 76, the relevant pages of the second e-book to which the second designated text object belongs being: a book detail page of the second electronic book;

78. The computer storage medium of claim 76, the relevant pages of the second e-book to which the second designated text object belongs being: the electronic book page where the second specified text object is located;

79. The computer storage medium of claim 78, the executable instructions further causing the processor to:

80. The computer storage medium of claim 75, the executable instructions further causing the processor to:

81. The computer storage medium of claim 78, the executable instructions further causing the processor to:

82. The computer storage medium of claim 75, the executable instructions further causing the processor to:

and displaying the text object content of the topic in a specific marking mode in the topic display page.

83. The computer storage medium of claim 75, the executable instructions further causing the processor to:

84. The computer storage medium of claim 75, the executable instructions further causing the processor to:

adding comment information to a second specified topic display page according to a request sent by a client for adding the comment information to the second specified topic in the second specified topic display page;

85. The computer storage medium of claim 75, the executable instructions further causing the processor to:

and sharing the second specified topic to the friend user.

86. The computer storage medium of claim 75, the executable instructions further causing the processor to:

87. The computer storage medium of claim 75, the executable instructions further causing the processor to: