CN116301502A

CN116301502A - Directory processing method and device for electronic book and computer equipment

Info

Publication number: CN116301502A
Application number: CN202310280339.0A
Authority: CN
Inventors: 吴梦; 康伟
Original assignee: Lenovo Beijing Ltd
Current assignee: Lenovo Beijing Ltd
Priority date: 2023-03-21
Filing date: 2023-03-21
Publication date: 2023-06-23

Abstract

In order to quickly and accurately locate electronic book contents which a user wants to read in the process of reading the electronic book, determining a selected first content by acquiring a selection operation for the current display content of the electronic book, and acquiring historical reading information of a current reader of the electronic book, so that recommended contents for the current reader are acquired at least according to the first content, the historical reading information and corresponding content weights; and generating an auxiliary catalog aiming at the current reader according to the recommended content, and outputting the auxiliary catalog.

Description

Directory processing method and device for electronic book and computer equipment

Technical Field

The present invention relates generally to the field of internet applications, and more particularly, to a method and apparatus for processing a directory of an electronic book, and a computer device.

Background

With the development of internet technology, electronic books provide great convenience for life, work, entertainment and other aspects of people. In the reading process of the electronic book, the user often needs to look up the directory of the electronic book and jump to the selected chapter for display, and then further searches the interested content of the user, which is limited by the display mode of the electronic book, and the process is tedious, so that the user experience is greatly reduced.

Disclosure of Invention

In order to solve the above problems, the present application provides the following technical solutions:

a directory processing method for an electronic book, the method comprising:

obtaining a selection operation for the current display content of the electronic book, and determining the selected first content;

acquiring historical reading information of a current reader of the electronic book;

acquiring recommended content for the current reader at least according to the first content, the historical reading information and the corresponding content weight;

generating an auxiliary catalog aiming at the current reader according to the recommended content;

and outputting the auxiliary catalogue.

Optionally, the obtaining the historical reading information of the current reader of the electronic book includes:

determining historical reading information of a current reader of the electronic book;

acquiring first historical display content of the electronic book which is read for the first time, second historical display content of the electronic book which is read this time and reading duration of the second historical display content from the historical reading information;

the obtaining the recommended content for the current reader at least according to the first content, the historical reading information and the corresponding content weight includes:

And acquiring recommended content for the current reader at least according to the first content, the first historical display content, the second historical display content, the reading duration and the corresponding content weight.

Optionally, the obtaining the recommended content for the current reader at least according to the first content, the first historical display content, the second historical display content, the reading duration and the corresponding content weight includes:

carrying out semantic analysis on the first historical display content to obtain second content; the second content is capable of characterizing a gist of the first historically displayed content;

determining third content with the reading time length larger than a preset time length threshold value from the second historical display content;

and obtaining recommended content for the current reader at least according to the first content, the second content, the third content and the corresponding content weight.

Optionally, the method further comprises:

acquiring the correlation degree between the current display content and each content contained in the electronic book;

determining fourth content with highest relativity in the electronic book;

And acquiring recommended content for the current reader according to the first content, the historical reading information, the fourth content and the corresponding content weight.

Optionally, the method further comprises:

obtaining reading selection operation aiming at the auxiliary catalogue, and outputting the corresponding recommended content;

acquiring the display time length of the currently output recommended content;

and adjusting at least one content weight according to the display duration to obtain an adjusted content weight so as to update recommended content for the current reader and obtain a new auxiliary catalog.

Optionally, the obtaining the recommended content for the current reader according to the first content, the historical reading information, the fourth content and the corresponding content weight includes:

obtaining a plurality of candidate recommended contents for the current reader and recommendation scores of the plurality of candidate recommended contents according to the first content, the historical reading information, the fourth content and the corresponding content weights;

and sequencing the plurality of candidate recommended contents according to the sequence from the large recommendation score to the small recommendation score to obtain a preset number of recommended contents with the front sequencing.

Optionally, generating the auxiliary catalog for the current reader according to the recommended content includes:

obtaining a recommendation index of the recommended content according to the recommendation score of each recommended content;

obtaining a recommended position identifier corresponding to the recommended content according to the corresponding relation between each content contained in the electronic book and different position identifiers;

analyzing the recommended content to obtain keywords and/or subject content of the recommended content;

and generating an auxiliary catalog aiming at the current reader by utilizing the keywords and/or the subject content of different recommended contents, the recommended position identification and the recommended index.

Optionally, the outputting the auxiliary catalog includes:

outputting a catalog identification aiming at the auxiliary catalog on a display interface of the current display content;

and acquiring triggering operation aiming at the target identifier, outputting an auxiliary catalog window, and displaying the auxiliary catalog in the auxiliary catalog window.

The application also provides a catalog processing device of the electronic book, which comprises:

a first content determining module for obtaining a selection operation for a currently displayed content of an electronic book, and determining the selected first content;

The historical reading information acquisition module is used for acquiring the historical reading information of the current reader of the electronic book;

the recommended content obtaining module is used for obtaining recommended content for the current reader at least according to the first content, the historical reading information and the corresponding content weight;

the auxiliary catalog generation module is used for generating an auxiliary catalog aiming at the current reader according to the recommended content;

and the auxiliary catalog output module is used for outputting the auxiliary catalog.

The application also proposes a computer device comprising:

a communication module;

a memory for storing a program for implementing the directory processing method of the electronic book as described above;

and the processor is used for loading and executing the program stored in the memory to realize the directory processing method of the electronic book.

In this way, in order to quickly and accurately locate the content of an electronic book which a user wants to read in the process of reading the electronic book, the method and device for processing the catalogue of the electronic book determine the first content selected by acquiring the selection operation of the current display content of the electronic book, and acquire the historical reading information of the current reader of the electronic book, so that the recommended content of the current reader is acquired at least according to the first content, the historical reading information and the corresponding content weight; and generating an auxiliary catalog aiming at the current reader according to the recommended content, and outputting the auxiliary catalog.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings may be obtained according to the provided drawings without inventive effort to a person skilled in the art.

Fig. 1 is a flowchart of an alternative embodiment of a method for processing a directory of an electronic book according to the present application;

fig. 2 is a schematic diagram of an output scene of an auxiliary directory for a current reader in the directory processing method of the electronic book provided in the present application;

fig. 3 is a flowchart of a second alternative embodiment of a directory processing method for an electronic book according to the present application;

fig. 4 is a flowchart of a third alternative embodiment of a directory processing method for an electronic book according to the present application;

fig. 5 is a flowchart of an alternative embodiment of a directory processing method for an electronic book according to the present application;

fig. 6 is a schematic structural diagram of an alternative embodiment of a catalog processing device for an electronic book according to the present application;

fig. 7 is a schematic structural diagram of a second alternative embodiment of a directory processing device of an electronic book according to the present application;

Fig. 8 is a schematic structural diagram of an alternative embodiment of a directory processing device of an electronic book according to the present application;

FIG. 9 is a schematic diagram of a hardware architecture of an alternative embodiment of a computer device suitable for the method for processing a catalog of an electronic book as proposed in the present application;

fig. 10 is a schematic hardware structure of another alternative embodiment of a computer device suitable for the directory processing method of the electronic book proposed in the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments, and the embodiments and features in the embodiments of the present application may be combined with each other without conflict. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

Referring to fig. 1, a flowchart of an alternative embodiment of an electronic book directory processing method provided in the present application may be applicable to a computer device supporting electronic book reading, such as a terminal device of a smart phone, a notebook computer, a desktop computer, etc., or may be a server, etc., where the server may be implemented by interacting with a user terminal when the computer device is a server. Thus, in a scenario where a user reads an electronic book online using a computer device, or reads an electronic book downloaded offline, as shown in fig. 1, a target processing method performed by the computer device may include:

Step S11, obtaining a selection operation for the current display content of the electronic book, and determining the selected first content;

in the application, aiming at the problem that the position which the user wants to read can not be found freely in the reading of the electronic book, the method and the device can accurately obtain the position of the electronic book which the user wants to read based on comprehensive analysis of the habit of the user and the relevance of the content. Based on this, in a scenario where a certain position of the electronic book is read in the reading process using the electronic book, and the position associated with the currently displayed content is to be referred to, a first content associated with the content to be read (i.e., the content of interest) may be selected from the currently displayed content, so that the content of interest of the user may be predicted subsequently in combination with the first content.

In the process that a user views an electronic book through a display screen of a computer device, the user can update the display content output by the display area by performing page turning operation on the display content output by the display area of the display screen, such as sliding operation on a touch display screen or pressing operation on a key supporting the page turning function of the electronic book, and the implementation process is not described in detail in the application. Thus, when the user views a certain position of a certain page of the electronic book, that is, views the display content currently output by the display area, a selection operation can be performed on one or more sentences in the current display content, and the selected sentence is determined as the first content.

The selecting operation of the current display content may include, but is not limited to: and performing long-press operation on the content of interest of the user or the content related to the content of interest of the user in the current display content, so that the operated content enters a selection editing state, and when the content entering the selection boundary state is incomplete, updating the selected content to determine the complete first content, namely the content which is greatly related to the content which the current reader wants to read. The present application does not limit how one or more sentences can be selected from the text content.

Step S12, acquiring historical reading information of a current reader of the electronic book;

in order to know the behavior habit of a user on an electronic book, in a scene that a current reader reads the electronic book for many times, the application can also acquire the historical reading information of the current reader on the electronic book for reading, such as the historical reading content of the current reader for first reading the electronic book, namely the display content output by the display area of the display screen when the current reader reads the electronic book for the first time; in the process of reading the electronic book, the history display content output by the display area of the display screen stays for a long time for reading, namely, the history display content of which the display time length reaches a preset time length threshold value; the method can also comprise the steps of repeatedly reading the history display content in the reading process of the electronic book for many times in the past, and/or the history collection content, the content provided with the tag or the key mark and the like in the reading process of the electronic book by the current reader.

In practical application, since the same electronic book may be read by multiple users, in order to accurately obtain the historical reading information of the current reader on the electronic book, the current reader identifier of the electronic book, such as an application account number of application software used for reading the electronic book, or a device identifier of a computer device used, may be obtained first, so that the historical reading information of the current reader on the electronic book may be obtained according to the current reader identifier and the electronic book identifier (such as an electronic book name or an ID, etc.), but the method is not limited to this method.

Step S13, obtaining recommended content for the current reader at least according to the first content, the historical reading information and the corresponding content weight;

because the first content is the display content of interest of the current reader or the content related to the content which the current reader wants to review, the historical reading information can represent the reading content of interest of the current reader in the past, and therefore, the method and the device can predict the content of interest of the current reader in the electronic book at least through the first content and the historical reading information as the recommended content of the current reader.

In the method, in a reading scene of different contents of an electronic book, accuracy of predicting interesting contents of a current reader by the first content and the historical reading information are often different, content weights of the first content and the historical reading information are predetermined according to actual conditions, influence of the content corresponding to the content of the current reader on the interesting contents of the current reader is predicted by the content weight, and the influence of the content corresponding to the content is characterized to be larger under the normal condition, the influence of the content corresponding to the content is not limited, and the content weight value can be flexibly adjusted according to the actual conditions.

Based on this, the present application may analyze the first content, the historical reading information and the corresponding content weight based on the artificial intelligence algorithm such as machine learning/deep learning, predict the content of interest of the current reader to the electronic book content, determine the content as the recommended content of the current reader, which may be the content of the recommended interface (i.e. the display area of the electronic book text display area in the display screen of the computer device), and the present application does not limit the implementation method of step S13.

Step S14, generating an auxiliary catalog aiming at the current reader according to the recommended content;

in practical application of the application, in the case of multiple recommended contents of a current reader in the electronic book currently read according to the above method, in order to facilitate the current reader to review the multiple recommended contents, the main content (may be summarizing the recommended contents by using fewer sentences, such as 1-3 sentences) and/or the keyword extraction may be performed on each recommended content, at least the main content and/or the keyword of each of the multiple extracted recommended contents are utilized to generate an auxiliary catalog for the current reader, that is, a personalized catalog for the current reader, and the application does not limit the generation method and the representation mode of the auxiliary catalog.

In order to facilitate the current reader to accurately determine the position of each obtained recommended content in the electronic book, the page number of each obtained recommended content in the electronic book can also be determined; or, constructing a link relation between each recommended content or the main content and/or the key words thereof and the actual position of each recommended content or the main content and/or key words in the electronic book, so that the current reader can trigger any entry in the auxiliary directory, directly enter the corresponding position of the electronic book according to the link relation, and output the content at the position.

In some embodiments, in the implementation process of obtaining the recommended content in step S13, the prediction probability or the prediction score of different recommended content is generally obtained, where a larger value may indicate a higher prediction accuracy of the corresponding recommended content, that is, a higher interest level of the current reader in the recommended content. Based on the above, the recommendation indexes of the corresponding auxiliary directories can be determined by using the prediction probability or the prediction score of each recommended content, and then the generated plurality of auxiliary directories can be ordered according to the high-low order of the recommendation indexes, so that a user can quickly select to review the target content in the electronic book.

It should be noted that, for the contents of the auxiliary catalog generated above, including but not limited to the subject contents, keywords, recommendation indexes, and the like of the recommended contents listed above, new page numbers may be generated to represent the order of each auxiliary catalog, and the contents of the auxiliary catalog may be flexibly adjusted according to the actual situation, which is not described in detail in the application.

In addition, it should be understood that, for reading the same electronic book by different readers, the generated auxiliary catalog content is often different according to the method described in the context, and compared with the original catalog of the electronic book, the personalized catalog generation method provided by the application can assist the readers to more quickly and accurately locate the target content. In addition, for the same reader to read the same electronic book, as the number of times of reading increases, the auxiliary catalogue for the reader generated by reading the electronic book each time may be different, and the implementation process is not described in detail in the present application.

Step S15, outputting the auxiliary catalog.

In some embodiments, in order to facilitate that the current reader may view the auxiliary catalog without exiting the current display content, a target identifier for the auxiliary catalog may be output on the display interface of the current display content, such as an icon shown in the left side drawing of the first row in fig. 2 (a plus sign icon in the upper right corner of the display interface shown in fig. 2), where the generated auxiliary catalog is in a collapsed state, when the current reader wants to view the auxiliary catalog, the target identifier may be clicked, and the computer device obtains a triggering operation for the target identifier, and may output an auxiliary catalog window, such as shown in the right side drawing of the first row in fig. 2, in which the generated auxiliary catalog may be displayed, but is not limited to the auxiliary catalog output method described in this embodiment.

In the auxiliary catalog window shown in the right drawing of the first row of fig. 2, that is, in the expanded state of the auxiliary catalog, a plurality of auxiliary catalogs for different recommended contents may be displayed in the display area thereof, and the contents of each auxiliary catalog may include, but are not limited to, the contents listed above. When the current reader does not need to view the auxiliary catalog content, the collapsed logo (e.g., the minus sign logo in the upper right hand corner of the right hand drawing of fig. 2) in the auxiliary catalog window may be clicked, the auxiliary catalog window minimized,

optionally, for different auxiliary directories, the display state of the corresponding auxiliary directory content can be adjusted according to the high-low order of the recommendation index, for example, the higher the recommendation index is, the larger the content word size of the corresponding auxiliary directory is, the larger the word size interval is, and the like, and even the font color of the auxiliary directory with the highest recommendation index can be adjusted, and/or the font of the auxiliary directory is thickened and displayed, so that a current reader can conveniently and rapidly and accurately review the recommended content which is most likely to be interested in the electronic book.

For example, the word size of the content of the directory where the keyword 1 is located is 20, the word size of the content of the directory where the keyword 2 is located is 18, and then the word sizes of other directory contents can be determined according to the way that the word size interval is 2. Font thickening processing may be performed on the directory contents corresponding to the recommended contents of the recommendation score, but is not limited to the control method of the directory content display state described in the present embodiment.

It should be noted that, in the case that the computer device is a server, the server may send the generated auxiliary directory for the current reader to the terminal device according to the device identifier of the terminal device used by the current reader to view the electronic book, so that the terminal device may output the auxiliary directory according to the above-described method.

In summary, in the embodiment of the present application, in order to assist a current reader to quickly and accurately locate a target content in an electronic book in reading the electronic book, a selection operation may be performed on a current display content of the electronic book, and a selected first content, that is, an interested content of the current reader or a content associated with the interested content, may be determined.

Referring to fig. 3, a flowchart of a second alternative embodiment of the method for processing a directory of an electronic book according to the present application may describe an alternative refinement implementation of the method for processing a directory of an electronic book according to the present application, as shown in fig. 3, the method may include:

step S31, obtaining a selection operation for the current display content of the electronic book, and determining the selected first content;

step S32, determining historical reading information of a current reader of the electronic book;

regarding the implementation procedure of step S31 and step S32, reference may be made to the description of the corresponding parts of the above embodiments, which are not described herein.

It should be noted that, for the history reading information recorded by the computer device, the reading time of different history reading contents, that is, the display time of the history display contents that have been output by the display area of the display screen of the computer device, is generally recorded, so as to identify the reading sequence of the recorded plurality of history reading contents (that is, the history display contents output by the display area of the display screen).

For different reading times of the same electronic book, the reading time can be determined according to time intervals of different historical reading contents, for example, the reading time difference between two adjacent historical reading contents is greater than a time threshold (for example, 24 hours or 12 hours, etc., and can be flexibly configured according to actual conditions), and the two historical reading contents can be considered not to be generated when the electronic book is read at the same time. Of course, when the electronic book is accessed to read each time, a reading or access request for the electronic book can be output, so that different reading times can be distinguished according to the output time of the access request.

Step S33, obtaining a first history display content of the first read of the electronic book, a second history display content of the current read of the electronic book and a reading time of the second history display content from the history reading information;

in combination with the above related description of the technical solution of the present application, the present application may predict what the current reader wants to read, i.e. the above content of interest, by analyzing the usage habit of the current reader. In general, when a user reads a new electronic book, the user can look up the interested content in the original directory of the electronic book to read. In addition, when the electronic book is read for a plurality of times, the content of interest is often read for a long time when the electronic book is read this time.

Based on the above, the display content of the current reader when the current reader reads the electronic book for the first time can be determined according to the reading time of each recorded historical reading content and recorded as the first historical display content, so that the main content or key content and the like of the current reader read for the first time can be analyzed and determined later. In addition, a plurality of pieces of history display contents generated from the electronic book reading at this time can be recorded as second history display contents, so that the history display contents of the current reader for staying for reading for a long time can be determined later according to the reading time (namely the display time in the display area of the display screen at the same time).

The computer device may obtain the recommended content for the current reader according to at least the first content, the first historical display content, the second historical display content, the reading time length thereof, and the content weights of different contents, and specifically may analyze these contents by using one or more artificial intelligence algorithms such as a natural language processing (Natural Language Processing, NLP) algorithm, a neural network algorithm, etc., predict the content of interest of the current reader, and determine the personalized recommended content for the current reader.

Step S34, carrying out semantic analysis on the first historical display content to obtain second content; the second content is capable of characterizing a gist of the first historically displayed content;

and after the analysis, the application can perform semantic analysis on the acquired first historical display content based on an artificial intelligence algorithm to acquire the main content, and record the main content as the second content as a clue for analyzing the use habit of the current reader. The implementation method for extracting the text content is not limited, and can be determined according to the situation.

Step S35, determining third content with reading time longer than a preset time threshold from the second historical display content;

the preset duration threshold value can be determined according to the average duration or experience value of electronic book reading, and the numerical value of the preset duration threshold value is not limited. Based on the above, the reading time length of each second historical display content can be respectively compared with the preset time length threshold value, and the second historical display content with the reading time length larger than the preset time length threshold value is determined to be the third content, or the second historical display content with the reading time length larger than the preset time length threshold value is subjected to subject matter extraction, so that the corresponding third content is obtained.

In still other embodiments of the present application, the second historical display content obtained according to the method may be ranked according to the reading time length, for example, the second historical display content may be ranked according to the order of the reading time length from big to small, the first second historical display content with the top ranking may be selected, for example, the second historical display content with the top5 reading time length after the ranking is selected, and the second historical display content is used as a further clue for analyzing the usage habit of the current reader and is marked as the third content. Optionally, the selected second history display content may be subjected to subject extraction or keyword extraction as needed to obtain the corresponding third content.

In other embodiments, in the implementation process of screening out the content of interest of the current reader from the historical reading content generated from the current reading electronic book, if the current reader sequentially browses the content of interest of the current reader in the electronic book by referring to the original directory of the electronic book, after determining the second historical display content, the computer device may determine that a preset number of pieces of second historical display content with earlier reading time are third content, and the implementation process is not described in detail in the application.

It should be noted that, regarding how to screen out or predict the history display content that may be of interest to the current reader from the history reading information, including but not limited to the above-described method, flexible adjustment may be performed according to the actual situation, which is not described in detail in this application.

Step S36, at least a first content, a second content, a third content and corresponding content weights are obtained, and recommended content for the current reader is obtained;

according to the above related descriptions of the first content, the second content and the third content, the corresponding content weight can be determined according to the influence of each content on the content of interest of the current reader or the association degree of the content to be referred to by the current reader, then the content under the multi-dimension is subjected to weighted analysis to obtain the personalized recommended content for the current reader, and the implementation process can be implemented by adopting a suitable artificial intelligence algorithm.

It should be noted that, in the process of obtaining the recommended content for the current reader, in addition to the content in the plurality of dimensions given above, the content in the electronic book with higher correlation with the currently displayed content may be obtained, and the content in the electronic book with higher correlation with the selected first content may also be obtained. Therefore, the computer device may also perform weighted analysis of the multidimensional content in combination with the content with higher correlation, predict the recommended content for the current reader, and of course, is not limited to the multidimensional content described above, and may be determined as appropriate.

In the process of obtaining the recommended content, through weighted analysis of the multidimensional content, the prediction probability or the prediction score of the interested content of the current reader of different content of the electronic book can be obtained, and the larger the value of the prediction probability or the prediction score is, the higher the possibility that the corresponding content of the electronic book is the interested content of the current reader is, so that the obtained interested content prediction probability or the prediction score can be ranked according to, and a specified number of interested content with higher prediction probability or prediction score is selected as the recommended content of the current reader, but the method is not limited to the method for realizing the prediction of the personalized recommended content.

Step S37, generating an auxiliary catalog aiming at the current reader according to the recommended content;

step S38, outputting the auxiliary catalog.

Regarding the implementation procedure of step S37 and step S38, reference may be made to the descriptions of the corresponding portions of the context, and this embodiment will not be described in detail here.

In summary, in order to accurately and quickly locate the content that the current reader wants to read in the electronic book, according to the situation that the current reader reads the electronic book for the first time, the history display content that is read for a long time in the current reading process of the electronic book and the first content selected from the current display content that is read currently, that is, the multi-dimensional content such as the content that has great association with the content that the current reader wants to read, the recommended content that the current reader may be interested in (that is, want to read) is predicted, so as to generate a personalized auxiliary catalog, so that the current reader can quickly select the content that the current reader wants to read from the content, to quickly locate the corresponding position of the electronic book, assist the current reader to obtain satisfactory content, so as to relieve the emotion that the user cannot grasp the electronic book, and improve the user experience.

Referring to fig. 4, a flowchart of a third alternative embodiment of the method for processing a directory of an electronic book according to the present application may describe another alternative refinement implementation of the method for processing a directory of an electronic book according to the present application, as shown in fig. 4, the method may include:

Step S41, obtaining a selection operation for the current display content of the electronic book, and determining the selected first content;

step S42, determining historical reading information of a current reader of the electronic book;

step S43, obtaining a first history display content of the first read of the electronic book, a second history display content of the current read of the electronic book and a reading time of the second history display content from the history reading information;

step S44, carrying out semantic analysis on the first historical display content to obtain second content; the second content is capable of characterizing a gist of the first historically displayed content;

step S45, determining third content with reading time longer than a preset time threshold from the second historical display content;

regarding the implementation procedure of step S41 to step S45, reference may be made to the description of the corresponding parts of the above embodiments, which are not described in detail herein.

Step S46, obtaining the relativity between the current display content and each content contained in the electronic book;

step S47, determining fourth content with highest relativity in the electronic book;

in combination with the description of the corresponding parts of the above embodiments, the present application may use an NLP algorithm to obtain the correlation between each content included in the electronic book and the current display content, sort the obtained multiple correlations, and select the electronic book content with the highest correlation as the fourth content. Optionally, according to the sorting result, a set number of electronic book contents with higher relevance may be selected as the fourth content, the method for obtaining the fourth content is not limited, other similarity algorithms may be adopted, and a plurality of contents with highest similarity or higher similarity with the current display content may be selected as the fourth content, so that the implementation process is not described in detail in one example.

Step S48, inputting the first content, the second content, the third content and the fourth content into a content prediction model, and outputting recommended content for the current reader;

different from other embodiments above, this embodiment adds the dimension content of the fourth content, so as to more accurately analyze the usage habit of the current reader, and in combination with the core content (i.e., the first content) selected by the current reader in the current display content, predict, through weighted analysis, a plurality of contents interested by the current reader in the electronic book, and record the contents as recommended contents. The content weights corresponding to the four-dimensional content listed above may be 0.5, 0.1 and 0.3 in sequence, and then the content selection operation in the auxiliary directory output at this time may be dynamically updated according to the current reader.

Optionally, as shown in the implementation manner described in step S48, the present application may use an NLP algorithm to perform model training on sample contents under multiple dimensions of e-book reading (which may include the selected content, the primary content, the content read longer in a certain reading process, and the e-book content with higher correlation with the display content where the selected content is located described above, but is not limited to these four dimensions, two or three of these dimensions may be selected according to actual situations, and may be implemented in combination with other dimensions), so as to obtain a content prediction model for predicting the content of interest in the e-book by the user. The content weight of the content with different dimensions in the content prediction model can be different, and the content weight can be dynamically updated according to the selection operation of the current reader on the output auxiliary catalog, so that the prediction accuracy of the content prediction model is improved.

Based on this, in practical application, after obtaining the multi-dimensional content according to the method, a pre-trained content prediction model may be invoked, and the multi-dimensional content is input into the content prediction model to obtain a plurality of recommended contents for the current reader, and the implementation process is not described in detail in the present application. It should be noted that, regarding the method for obtaining the recommended content, including but not limited to a multidimensional content weighted analysis method implemented based on a content prediction model, a suitable artificial intelligence algorithm may also be adopted to directly perform weighted analysis on the multidimensional content to obtain the personalized recommended content of the current reader, and the implementation process is not described in detail in the present application.

Step S49, generating an auxiliary catalog aiming at the current reader according to the recommended content;

step S410, the auxiliary catalog is output.

Regarding the implementation procedure of step S49 and step S410, reference may be made to the description of the corresponding parts of the above embodiments, which will not be described in detail.

Referring to fig. 5, a flowchart of a fourth alternative embodiment of the method for processing a directory of an electronic book according to the present application may describe a further alternative refinement implementation of the method for processing a directory of an electronic book according to the present application, as shown in fig. 5, the method may include:

Step S51, obtaining a selection operation for the current display content of the electronic book, and determining the selected first content;

step S52, acquiring historical reading information of a current reader of the electronic book;

regarding the implementation method of step S52, reference may be made to, but not limited to, the content described in the above embodiments, and the obtained history reading information may include the first history display content (or the subject content obtained by analysis thereof, etc.) and/or the second history display content, etc. as a behavioral cue for analyzing the usage habit of the current reader, and the recommended content of interest of the current reader is predicted in combination with the fourth content obtained below, so as to implement the process embodiment herein.

Step S53, obtaining the correlation degree between the current display content and each content contained in the electronic book, and determining a fourth content with the highest correlation degree in the electronic book;

step S54, obtaining a plurality of candidate recommended contents for the current reader and recommendation scores of the plurality of candidate recommended contents according to the first content, the historical reading information, the fourth content and the corresponding content weights;

in practical application of the application, in combination with the above related description content of the historical reading information, the application may perform weighted analysis on the first content and the first historical display content (or extract the subject matter or the keyword from the first historical display content to obtain the second content) and/or the second historical display content (or determine that the reading duration reaches a preset duration threshold according to the reading duration of the second historical display content, or a preset number of third contents with larger reading duration, etc.), and the fourth content, predict a plurality of contents possibly interested by the current reader and their prediction probabilities or prediction scores, and record the predicted contents as candidate recommended contents.

Optionally, in the analysis, the obtained multi-dimensional content may be input into a trained content prediction model, and a plurality of candidate recommended contents and recommendation scores thereof for the current reader may be output.

Step S55, sorting the plurality of candidate recommended contents according to the sequence from the large to the small of the recommended scores, and obtaining the recommended contents with the preset quantity which are sorted in front;

it can be appreciated that the recommendation score of each candidate recommended content may also be compared with a preset score threshold, so as to determine the candidate recommended content with the recommendation score greater than the preset score threshold, which is used as the recommended content for the current reader, but is not limited to such a recommended content acquisition method. The preset number of recommended content obtained in step S55 may be determined according to the number of auxiliary directory display bars that are preset, which is not limited in this application.

Step S56, obtaining a recommendation index of the corresponding recommended content according to the recommendation score of each recommended content;

in the embodiment of the present application, the recommendation index may be represented by the number of five-pointed star icons, where a larger number of five-pointed star icons indicates that the content is more likely to be the content that the reader wants to read, but is not limited to this recommendation index representation mode. In combination with the above description about the recommendation score, the higher the recommendation score is, the higher the recommendation index corresponding to the recommended content is, and the conversion relationship between the recommendation score and the recommendation index, such as the recommendation score threshold value corresponding to each five-star icon in the recommendation index, may be preconfigured, so as to implement step S56, which is not limited to this recommendation index obtaining method.

Step S57, obtaining a recommended position identifier corresponding to the recommended content according to the corresponding relation between each content contained in the electronic book and different position identifiers;

in combination with the above description of the scenario shown in fig. 2, in order to facilitate the current reader to know where each obtained recommended content is located in the electronic book, the recommended location identifier of each recommended content, such as the actual page number of the recommended content in the electronic book, may be obtained according to, but not limited to, the method shown in step S57.

Alternatively, the scene interface shown in fig. 2 may also directly perform serial numbering according to the obtained number of recommended contents and the order of the recommendation indexes of the recommended contents from high to low, so as to generate the recommendation position identifier of each recommended content, such as n serial page numbers including page number 1 and page number 2 shown in fig. 2. In this alternative embodiment, the step S57 may be updated to generate the recommended position identifier of the corresponding recommended content according to the ranking of the recommendation indexes of the plurality of recommended contents, such as the page number, but is not limited to the method for generating the recommended position identifier of each recommended content in the two auxiliary directories described in the present application.

Step S58, analyzing the recommended content to obtain the key words and/or the subject content of the recommended content;

Step S59, generating an auxiliary catalog aiming at the current reader by utilizing the keywords and/or the subject content of different recommended contents, the recommended position identification and the recommended index;

in order to simplify the content of each entry in the auxiliary catalog, after the recommended content for the current reader is obtained according to the above-described method, the recommended content may be extracted according to an auxiliary catalog template (which can represent the content format contained in each entry, etc.), so as to generate the personalized auxiliary catalog of the current reader by combining the obtained recommendation position identifier and recommendation index of the corresponding recommended content, but not limited to the auxiliary catalog generation method described in this embodiment.

Step S510, outputting a catalog identification aiming at the auxiliary catalog on a display interface of the current display content;

step S511, a triggering operation aiming at the target mark is obtained, an auxiliary catalog window is output, and each auxiliary catalog is displayed in the auxiliary catalog window;

in combination with the above related description of the method for outputting the auxiliary catalog, under the condition that the reading of the current display content by the current reader is not interfered, the target identifier of the auxiliary catalog can be directly output on the display interface of the current reader, as shown in fig. 2, the default state can be a stowage state, and when the current reader wants to view the auxiliary catalog content and search other interested contents, the target identifier can be directly triggered to expand the auxiliary catalog and display the contents such as the subject matter, the keyword, the recommended position identifier, the recommended index and the like of each catalog.

It should be noted that, the method for implementing the switch between different display states of the auxiliary directory includes, but is not limited to, the method for implementing the switch based on the trigger of the target identifier described above, which can be flexibly configured according to the actual situation.

Step S512, obtaining reading selection operation for the displayed auxiliary catalogue, and outputting corresponding recommended content;

step S513, obtaining the display time length of the currently output recommended content;

step S514, at least one content weight is adjusted according to the display time length, and the adjusted content weight is obtained so as to update the recommended content for the current reader and obtain a new auxiliary catalog.

In combination with the method for processing the electronic book in the foregoing embodiments, after the personalized auxiliary catalog for the current reader is output, the current reader may select a certain catalog content of interest from the auxiliary catalog, and trigger the same, for example, click on any position of the corresponding catalog display area, the electronic book text display area of the computer device may output the electronic book content corresponding to the triggered catalog content, that is, the detailed recommended content, and then, the duration that the current reader stays on the newly output electronic book content, that is, the reading duration of the newly output electronic book content, that is, the display duration of the electronic book content, update the recommended content accordingly, adjust the generated auxiliary catalog, so that the content of the output auxiliary catalog can meet the electronic input query requirement of the current reader, and assist the current reader to quickly and accurately locate the content that is wanted to be read in the electronic book.

It should be noted that, regarding the dynamic adjustment of the recommended content and the auxiliary catalog, the content weight of each dimensional content in the content prediction model may be dynamically adjusted according to the comparison result of the catalog content selected by the current reader from the currently outputted auxiliary catalog and each dimensional content, and the catalog sequence of the selected catalog in the auxiliary catalog, for the reading duration of the electronic book content outputted in response to the target content, etc., and then the interested content of the current reader may be predicted according to the new content prediction model, so the implementation process will not be described in detail in the present application.

In combination with the above description about content weights, for example, if the current reader actually selects the keyword 3 of the third directory in the auxiliary directory and reads the corresponding electronic book content for a longer time, it is explained that the current reader is actually interested in the electronic book content associated with the keyword 3, but not in other directory contents in the auxiliary directory, so that the application can adaptively increase the content weight of the content corresponding to the keyword 3, reduce the content weight of the content having a dimension unrelated to the keyword 3, so as to improve the accuracy of predicting the recommended content of the current reader. Optionally, the present application may further adjust other model parameters of the content prediction model according to needs, and the dynamic update method of the content prediction model is not described in detail in the present application.

It should be understood that if the current reader triggers the keyword 3 in the outputted auxiliary catalog, after outputting the electronic book content associated with the current reader, the current reader simply reads and finds that the current reader is not the required content (the reading duration of the electronic book content is shorter), and one catalog can be reselected from the auxiliary catalog to be referred to, for example, the keyword 2 is selected to trigger, and the associated electronic book content can be read for a longer time. Based on this, in the content weight dynamic adjustment process, the content weight of the dimension content associated with the keyword 3 may be reduced, the content weight of the dimension content associated with the keyword 2 may be increased, and for other dimension content, the corresponding content weight may be adjusted according to the degree of correlation with each of the keyword 2 and the keyword 3, but the content weight adjustment method is not limited thereto.

In practical applications, each step included in each method embodiment described above may be implemented by an integrated logic circuit of hardware in a processor or an instruction in a software form. The method for processing the catalogue of the electronic book disclosed in the above embodiment may be performed by a hardware processor or by a combination of hardware and software modules in the processor. The software modules may be located in random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, and other storage media. The processor may read the information in the storage medium or the memory where the storage medium is located, and implement the steps of the breeding data processing method in combination with corresponding hardware, and the implementation process may refer to the description of the method embodiment, which is not described herein.

Referring to fig. 6, a schematic structural diagram of an alternative embodiment of a catalog processing device for an electronic book according to the present application, as shown in fig. 6, the device may include:

a first content determining module 61 for obtaining a selection operation for a currently displayed content of an electronic book, determining a selected first content;

a historical reading information obtaining module 62, configured to obtain historical reading information for a current reader of the electronic book;

a recommended content obtaining module 63, configured to obtain recommended content for the current reader at least according to the first content, the historical reading information, and the corresponding content weight;

an auxiliary catalog generation module 64, configured to generate an auxiliary catalog for the current reader according to the recommended content;

and an auxiliary catalog output module 65, configured to output the auxiliary catalog.

In one possible implementation manner, referring to the schematic structural diagram of the second alternative embodiment of the directory processing device of the electronic book shown in fig. 7, the history read information obtaining module 62 may include:

a history reading information determining unit 621 for determining history reading information for a current reader of the electronic book;

A first obtaining unit 622, configured to obtain, from the history read information, a first history display content of the electronic book that is read for the first time, a second history display content of the electronic book that is read this time, and a reading duration of the second history display content;

based on this, the recommended content obtaining module 63 may include:

the second obtaining unit 631 is configured to obtain recommended content for the current reader at least according to the first content, the first historical display content, the second historical display content, the reading duration, and the corresponding content weight.

Alternatively, as shown in fig. 7, the second obtaining unit 631 may include:

a second content obtaining unit 6311 configured to perform semantic analysis on the first history display content to obtain second content; the second content is capable of characterizing a gist of the first historically displayed content;

a third content determining unit 6312 configured to determine, from the second history display content, a third content whose reading time period is longer than a preset time period threshold;

and a third obtaining unit 6313, configured to obtain recommended content for the current reader according to at least the first content, the second content, the third content, and the corresponding content weights.

In still other embodiments, referring to the schematic structural diagram of the second alternative embodiment of the directory processing device of the electronic book shown in fig. 8, the foregoing device may further include:

a relevance obtaining module 66, configured to obtain relevance between the currently displayed content and each content included in the electronic book;

a fourth content determining module 67, configured to determine a fourth content with the highest relevance in the electronic book;

based on this, the recommended content obtaining module 63 may include:

a fourth obtaining unit 632, configured to obtain recommended content for the current reader according to the first content, the historical reading information, the fourth content, and the corresponding content weight.

Alternatively, as shown in fig. 8, the fourth obtaining unit 632 may include:

a candidate recommended content obtaining unit 6321 configured to obtain a plurality of candidate recommended contents for the current reader and recommendation scores of the plurality of candidate recommended contents according to the first content, the history reading information, the fourth content, and the corresponding content weights;

and a fifth obtaining unit 6322, configured to sort the plurality of candidate recommended contents in order of the recommendation scores from large to small, to obtain a preset number of recommended contents with the top sorting.

In still other embodiments, as shown in fig. 8, the auxiliary catalog generation module 64 described above may include:

a recommendation index obtaining unit 641 configured to obtain a recommendation index of the recommended content according to a recommendation score of each of the recommended content;

a recommended position identifier obtaining unit 642, configured to obtain a recommended position identifier corresponding to the recommended content according to a correspondence between each content included in the electronic book and different position identifiers;

an analysis unit 643, configured to analyze the recommended content to obtain keywords and/or subject content of the recommended content;

and an auxiliary catalog generating unit 644 configured to generate an auxiliary catalog for the current reader using the keywords and/or the subject contents of the recommended contents, the recommended position identifier, and the recommendation index.

Optionally, based on the description of the above embodiment, as shown in fig. 8, the above apparatus may further include:

a recommended content output module 68, configured to obtain a reading selection operation for the auxiliary catalog, and output the corresponding recommended content;

a display duration obtaining module 69, configured to obtain a display duration of the currently output recommended content;

And an updating module 610, configured to adjust at least one content weight according to the display duration, to obtain an adjusted content weight, so as to update the recommended content for the current reader, and to obtain a new auxiliary catalog.

Based on the description of the apparatus embodiments above, as shown in fig. 8, the auxiliary catalog output module 65 may include:

a target identifier output unit 651, configured to output, on a display interface of the current display content, a directory identifier for the auxiliary directory;

and an auxiliary catalog display unit 652 configured to obtain a trigger operation for the target identifier, output an auxiliary catalog window in which the auxiliary catalog is displayed.

It should be noted that, regarding the various modules, units, and the like in the foregoing embodiments of the apparatus, the various modules and units may be stored as program modules in memories of corresponding nodes, and the processor of the node executes the program modules stored in the memories to implement corresponding functions, and regarding the functions implemented by each program module and the combination thereof, and the achieved technical effects, reference may be made to descriptions of corresponding parts of the foregoing method embodiments, which are not repeated herein.

The present application also provides a computer readable storage medium on which a computer program may be stored, which computer program may be called and loaded by a processor of a computer device, to implement the steps of the directory processing method of an electronic book described in the above method embodiments executed by the computer device.

Referring to fig. 9, a schematic structural diagram of a computer device suitable for the method for processing a catalog of an electronic book proposed in the present application may include: a communication module 91, a memory 92 and a processor 93, wherein,

the number of each of the communication module 91, the memory 92 and the processor 93 may be at least one, and may be connected to each other by a bus, but is not limited to the connection manner shown in fig. 9, and the connection manner between each of them and other components of the computer device is not described in detail herein. The bus may include an address bus, a data bus, a control bus, etc., which are not shown in fig. 9, and may be determined according to actual needs, which is not described in detail in this application.

The communication module 91 may include a communication module capable of implementing data interaction using a wireless communication network, such as a WIFI module, a 5G/6G (fifth generation mobile communication network/sixth generation mobile communication network) module, a GPRS module, etc., to implement communication between a terminal device and a server, or communication between different terminal devices, and communication between a server and other types of devices, as the case may be. It should be understood that the communication module 91 may further include a communication interface, such as a USB interface, a serial/parallel port, etc., for implementing data interaction between internal components of the computer device, and the specific content included in the communication module 91 is not limited in this application.

The memory 92 may be used to store a program that implements the directory processing method of the electronic book proposed in the present application; the processor 93 may be configured to load and execute a program stored in the memory 92, to implement the directory processing method of the electronic book set forth in the present application, and the implementation process will not be described in detail herein.

In practical applications of the present application, the memory 92 may be a nonvolatile memory, such as a hard disk (HDD) or a Solid State Drive (SSD), or may be a volatile memory (volatile memory), such as a random-access memory (RAM). As analyzed above, the memory 92 can be any available storage medium that can be accessed by the processor 93 and/or computer device. It should be appreciated that the memory 92 of the present application may also be circuitry or any other device capable of performing a memory function for storing program instructions and/or data, and the type of memory 92 and its physical connection to other devices described above is not limited, as the case may be.

Optionally, the processor 93 may include one or more processors, where the processor may include, but is not limited to, performing the directory processing method of the electronic book set forth in the present application: microprocessors, microcontrollers, digital signal processors (digitalsignal processor, DSP), digital signal processing devices (digital signal processing device, DSPD), application specific integrated circuits (application specific integrated circuit, ASIC), field programmable gate arrays (field programmable gate array, FPGA), programmable logic devices (programmable logicdevice, PLD), central Processing Units (CPU), processing circuits or other suitable hardware, firmware and/or combinations of hardware and software, etc., the present application does not limit the composition of the processor 93 of the computer device.

It should be understood that the structure of the computer device shown in fig. 9 does not limit the computer device in the embodiment of the present application, in practical application, the computer device may include more components than those shown in fig. 9, or some components may be combined, and in the case where the computer device is a terminal device, as shown in fig. 10, the computer device may further include a display screen, a pickup, a speaker, a camera, an antenna, a power management module, various sensors, and the like, which are not specifically mentioned herein.

Finally, it is pointed out that in the various embodiments described above, relational terms such as first, second, and the like, are used solely to distinguish one from another operation, unit or module without necessarily requiring or implying any actual such relationship or order between such units, operations or modules. And is not to be taken as indicating or implying a relative importance or implying that the number of technical features indicated is such that the features defining "first", "second" or "a" may explicitly or implicitly include one or more such features.

Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method or system comprising such elements.

In this specification, each embodiment is described in a progressive or parallel manner, and each embodiment is mainly described by a difference from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the apparatus and the computer device disclosed in the embodiments, the description is relatively simple, and the relevant places refer to the description of the method section because the apparatus and the computer device correspond to the methods disclosed in the embodiments.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A directory processing method for an electronic book, the method comprising:

and outputting the auxiliary catalogue.

2. The method of claim 1, the obtaining historical reading information for a current reader of the electronic book, comprising:

3. The method of claim 2, wherein the obtaining recommended content for the current reader based at least on the first content, the first historical display content, the second historical display content, the reading duration, and the corresponding content weights comprises:

4. A method according to any one of claims 1-3, the method further comprising:

determining fourth content with highest relativity in the electronic book;

5. The method of claim 4, the method further comprising:

Acquiring the display time length of the currently output recommended content;

6. The method of claim 4, wherein obtaining recommended content for the current reader according to the first content, the historical reading information, the fourth content, and the corresponding content weights comprises:

7. The method of claim 6, wherein generating the auxiliary catalog for the current reader based on the recommended content comprises:

8. A method according to any of claims 1-3, said outputting said auxiliary directory, comprising:

9. A catalog processing apparatus for an electronic book, the apparatus comprising:

10. A computer device, the computer device comprising:

a communication module;

a memory for storing a program for implementing the directory processing method of the electronic book as recited in any one of claims 1 to 8;

a processor, configured to load and execute the program stored in the memory, to implement the directory processing method of the electronic book as claimed in any one of claims 1 to 8.