Intelligent reading method and system based on digital magazine electronic book and medium

Abstract

The invention provides an intelligent reading method and system based on a digital magazine electronic book and a medium. The method comprises the steps of generating a reading record data queue list by obtaining personalized reading record information, obtaining keyword information and real-time environment data, inquiring to obtain recommended article information, extracting article reading guide feature data, and obtaining a reading live environment recommendation index in combination with the real-time environment data. Querying according to the article classification data to obtain a corresponding article content difficulty coefficient and reading average speed data, and processing according to the article reading guide feature data, the article content difficulty coefficient and the reading average speed data in combination with a reading live environment recommendation index to obtain a reading adaptation coefficient corresponding to the recommended article; according to the method, the recommended article information is preliminarily obtained, specific content is further analyzed, the reading adaptation coefficient is obtained in combination with live environment processing, whether the recommended article passes recommendation or not is finally determined through threshold value comparison, and the pertinence and effectiveness of user reading are improved.

Description

Technical Field

[0001] The present application relates to the field of digital reading technology, and in particular to an intelligent reading method, system and medium based on digital magazine e-books. Background Art

[0002] With the continuous development of digitization and networking, digital magazines and e-books have gradually become one of the important ways for people to obtain information and read. The existing digital magazine and e-book reading recommendation methods are relatively simple. Generally, recommendations are only made based on the user's historical reading information. It is impossible to make adaptive recommendations based on the user's actual environment and specific reading needs. The reading experience is poor, which affects the user's reading experience and reading effectiveness.

[0003] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention

[0004] The purpose of this application is to provide an intelligent reading method, system and medium based on digital magazine e-books, which can initially obtain recommended article information, further analyze the specific content and obtain the reading adaptation coefficient in combination with the actual environment processing, and finally determine whether the recommended article is recommended by threshold comparison, thereby improving the pertinence and effectiveness of user reading.

[0005] The present application also provides an intelligent reading method based on digital magazine e-books, comprising the following steps:

[0006] Obtain the user's personalized reading record information and generate a user reading record data queue table;

[0007] Obtaining keyword information of the user's reading search and real-time environment data of the user's real-time reading, wherein the real-time environment data includes brightness data and time point data;

[0008] According to the personalized reading record information, keyword information and time point data, a preset e-book reading database is queried to obtain recommended article information;

[0009] Extracting article reading guide feature data according to the recommended article information, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data;

[0010] Processing the real-time environment data and the estimated reading time data to obtain a reading environment recommendation index;

[0011] According to the article classification data, query the user reading record data queue table to obtain corresponding user reading record data, including article content difficulty coefficient and average reading speed data corresponding to the article classification data;

[0012] Comparing the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data with the reading actual environment recommendation index, to obtain a reading adaptation coefficient corresponding to the recommended article;

[0013] A threshold comparison is performed based on the reading adaptation coefficient and a preset reading adaptation threshold. If the threshold comparison result meets the preset threshold requirement, the recommended article is recommended.

[0014] Optionally, in the digital magazine e-book based intelligent reading method described in the present application, the step of querying a preset e-book reading database according to the personalized reading record information, keyword information and time point data to obtain recommended article information includes:

[0015] The personalized reading record information includes reading category information, article content information and reading speed record information;

[0016] The keyword information includes word category information and word meaning analysis information;

[0017] According to the reading category information, article content information, reading speed record information, word category information, word meaning analysis information and time point data, a preset e-book reading database is queried to obtain recommended article information.

[0018] Optionally, in the intelligent reading method based on digital magazines and electronic books described in the present application, the processing according to the real-time environment data and the reading time estimation data to obtain the reading real-time environment recommendation index includes:

[0019] Input the brightness data, time point data and reading time estimation data into a preset reading environment recommendation index evaluation model for analysis and processing to obtain a reading environment recommendation index;

[0020] The calculation formula of the reading real-time environment recommendation index in the reading real-time environment recommendation index evaluation model is:

[0021]

[0022] Among them, e r Recommended index for reading live environment, b h ,t n ,t r They are brightness data, time point data and reading time estimation data, and κ1, κ2, κ3 and λ are preset characteristic coefficients.

[0023] Optionally, in the intelligent reading method based on digital magazine e-books described in the present application, the comparison processing based on the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data combined with the reading real-life environment recommendation index to obtain the reading adaptation coefficient corresponding to the recommended article includes:

[0024] Input the article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data, and reading real-life environment recommendation index into a preset reading adaptation coefficient evaluation model for processing to obtain a reading adaptation coefficient corresponding to the recommended article;

[0025] The calculation formula of the reading adaptation coefficient in the reading adaptation coefficient evaluation model is:

[0026]

[0027] Among them, R e is the reading adaptation coefficient, d in 、s p1 d ac 、s p2 、e r They are article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data and reading environment recommendation index, θ, ψ1 and ψ2 are preset characteristic coefficients.

[0028] Optionally, in the intelligent reading method based on digital magazine e-book described in the present application, the method further includes:

[0029] Get the historical average page-turning time data of users of the same article category data;

[0030] Obtain the average reading time data, help-seeking data and reference data of different users of the same article classification data, and analyze and process to obtain the difficulty coefficient of the article;

[0031] According to the historical average page turning time data combined with the article difficulty coefficient analysis and processing, automatic page turning time data is obtained;

[0032] Automatically turning pages according to the automatic page turning time data;

[0033] If the user returns manually, the repeated reading time data is obtained and the automatic page turning time data is corrected.

[0034] Optionally, the intelligent reading method based on digital magazine e-book described in the present application further includes:

[0035] Obtain the user's vision data and gaze duration data;

[0036] Inputting the visual acuity data, fixation duration data, brightness data, and time point data into a preset visual fatigue assessment model for analysis and processing to obtain a user's visual fatigue index;

[0037] The visual fatigue index is compared with a preset visual fatigue threshold. If the visual fatigue index is greater than the preset visual fatigue threshold, the user-side reading interface is adaptively adjusted and an early warning is issued.

[0038] Optionally, in the intelligent reading method based on digital magazine e-book described in the present application, the method further includes:

[0039] Get user registration information;

[0040] Acquire the user's multi-reading platform setting information, historical reading information and historical annotation information according to the registration information;

[0041] Comparing the setting information, historical reading information and historical annotation information respectively for similarity, to obtain setting information similarity, reading information similarity and annotation information similarity;

[0042] According to the analysis and processing of the setting information similarity, the reading information similarity and the annotation information similarity, a cross-platform similarity is obtained;

[0043] Performing a threshold comparison between the cross-platform similarity and a preset cross-platform similarity threshold;

[0044] If it is greater than the preset cross-platform similarity threshold, the setting information, reading information and annotation information are removed;

[0045] If it is less than or equal to the preset cross-platform similarity deviation threshold, a user comprehensive reading record data queue table is constructed according to the setting information, historical reading information and historical annotation information of the user's multiple reading platforms.

[0046] In a second aspect, the present application provides an intelligent reading system based on digital magazine e-books, the system comprising: a memory and a processor, the memory comprising a program of an intelligent reading method based on digital magazine e-books, the program of the intelligent reading method based on digital magazine e-books being executed by the processor to implement the following steps:

[0047] Obtain the user's personalized reading record information and generate a user reading record data queue table;

[0048] Obtaining keyword information of the user's reading search and real-time environment data of the user's real-time reading, wherein the real-time environment data includes brightness data and time point data;

[0049] According to the personalized reading record information, keyword information and time point data, a preset e-book reading database is queried to obtain recommended article information;

[0050] Extracting article reading guide feature data according to the recommended article information, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data;

[0051] Processing the real-time environment data and the estimated reading time data to obtain a reading environment recommendation index;

[0052] According to the article classification data, query the user reading record data queue table to obtain corresponding user reading record data, including article content difficulty coefficient and average reading speed data corresponding to the article classification data;

[0053] Comparing the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data with the reading actual environment recommendation index, to obtain a reading adaptation coefficient corresponding to the recommended article;

[0054] A threshold comparison is performed based on the reading adaptation coefficient and a preset reading adaptation threshold. If the threshold comparison result meets the preset threshold requirement, the recommended article is recommended.

[0055] Optionally, in the digital magazine e-book based intelligent reading system described in the present application, the querying through a preset e-book reading database according to the personalized reading record information, keyword information and time point data to obtain recommended article information includes:

[0056] The personalized reading record information includes reading category information, article content information and reading speed record information;

[0057] The keyword information includes word category information and word meaning analysis information;

[0058] According to the reading category information, article content information, reading speed record information, word category information, word meaning analysis information and time point data, a preset e-book reading database is queried to obtain recommended article information.

[0059] In a third aspect, the present application also provides a computer-readable storage medium, in which a program for an intelligent reading method based on digital magazine e-books is stored. When the program for an intelligent reading method based on digital magazine e-books is executed by a processor, the steps of the intelligent reading method based on digital magazine e-books as described in any one of the above items are implemented.

[0060] From the above, it can be seen that the intelligent reading method, system and medium based on digital magazine e-books provided by the present application preliminarily obtain the recommended article information, further analyze the specific content and obtain the reading adaptation coefficient in combination with the actual environment processing, and finally determine whether the recommended article is recommended by threshold comparison, thereby improving the pertinence and effectiveness of user reading.

[0061] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 A flowchart of an intelligent reading method based on digital magazines and e-books provided in an embodiment of the present application;

[0064] Figure 2 A flowchart of obtaining recommended article information based on the intelligent reading method of digital magazine e-books provided in an embodiment of the present application;

[0065] Figure 3 A flow chart of obtaining a user's visual fatigue index in an intelligent reading method based on digital magazine e-books provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0067] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0068] Please refer to Figure 1 , Figure 1 This is a flow chart of a smart reading method based on digital magazine e-books in some embodiments of the present application. The smart reading method based on digital magazine e-books is used in a terminal device, such as a computer, a mobile phone terminal, etc. The smart reading method based on digital magazine e-books includes the following steps:

[0069] S11, obtaining the user's personalized reading record information and generating a user reading record data queue table;

[0070] S12, obtaining keyword information of a user's reading search and real-time environment data of the user's real-time reading, wherein the real-time environment data includes brightness data and time point data;

[0071] S13, querying a preset e-book reading database according to the personalized reading record information, keyword information and time point data to obtain recommended article information;

[0072] S14, extracting article reading guide feature data according to the recommended article information, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data;

[0073] S15, performing processing according to the real-time environment data and the reading time estimation data to obtain a reading real-time environment recommendation index;

[0074] S16, querying the user reading record data queue table according to the article classification data to obtain corresponding user reading record data, including article content difficulty coefficient and average reading speed data corresponding to the article classification data;

[0075] S17, performing comparison processing based on the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data in combination with the reading real-life environment recommendation index to obtain a reading adaptation coefficient corresponding to the recommended article;

[0076] S18, performing a threshold comparison between the reading adaptation coefficient and a preset reading adaptation threshold, and if the threshold comparison result meets the preset threshold requirement, the recommended article is recommended.

[0077] It should be noted that in order to obtain recommended articles that meet the user's actual environment and needs, personalized reading record information including reading category information, article content information and reading speed record information is first obtained, and a user reading record data queue table is generated to obtain keyword information including word category information and word meaning analysis information, including brightness data and time point data. The preset e-book reading database is queried based on the obtained personalized reading record information, keyword information and real-time environment data to obtain recommended article information, and article reading guidance feature data is extracted, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data. The brightness data, time point data and reading time estimation data are combined for processing to obtain the reading speed data. The real-time environment recommendation index is used to determine whether it meets the real-time environment requirements of the user. Then, according to the article classification data, the user reading record data queue table is queried to obtain the user reading record data including the corresponding article content difficulty coefficient and the average reading speed data. According to the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data, the reading adaptation coefficient corresponding to the recommended article is obtained in combination with the reading real-time environment recommendation index. Finally, according to the threshold comparison, it is determined whether the recommended article is recommended. In this embodiment, the preset reading adaptation threshold is (0, 0.7), and [0.7, 1] corresponds to not recommending and recommending. For example, if the obtained reading adaptation coefficient is 0.8, the recommended article is recommended and sent to the user reading terminal for display.

[0078] Please refer to Figure 2 , Figure 2 The flowchart of the method for obtaining recommended article information based on the intelligent reading of digital magazine e-books in some embodiments of the present application is as follows. According to the embodiment of the present invention, the method of obtaining recommended article information by querying a preset e-book reading database according to the personalized reading record information, keyword information and time point data includes:

[0079] S21, the personalized reading record information includes reading category information, article content information and reading speed record information;

[0080] S22, the keyword information includes word category information and word meaning analysis information;

[0081] S23, querying a preset electronic book reading database according to the reading category information, article content information, reading speed record information, word category information, word meaning analysis information and time point data to obtain recommended article information.

[0082] It should be noted that in order to obtain recommended article information, the user's personalized reading record information is first obtained to understand the user's historical reading records, including reading category information, article content information and reading speed record information, and then the search keyword information input by the user in real time is obtained. Finally, the time of the user's real-time environment is obtained, such as 8:00 a.m. on the subway commute. Finally, according to the reading category information, article content information, reading speed record information, word category information, word meaning analysis information and time point data, the preset e-book reading database is queried to obtain recommended article information, and based on the recommended article information, article reading guidance feature data is extracted, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data, for adaptation detection.

[0083] According to an embodiment of the present invention, the processing according to the real-time environment data and the reading time estimation data to obtain a reading real-time environment recommendation index includes:

[0084] Input the brightness data, time point data and reading time estimation data into a preset reading real-life environment recommendation index evaluation model for analysis and processing to obtain a reading real-life environment recommendation index;

[0085] The calculation formula of the reading real-time environment recommendation index in the reading real-time environment recommendation index evaluation model is:

[0086]

[0087] Among them, e r Recommended index for reading live environment, b h ,t n ,t r They are brightness data, time point data and reading time estimation data respectively, and κ1, κ2, κ3, λ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform).

[0088] It should be noted that by inputting brightness data, time point data and reading time estimation data into a preset reading environment recommendation index evaluation model for analysis and processing, the reading environment recommendation index is obtained, which is used to determine whether the recommendation requirements are met in combination with the article content.

[0089] According to an embodiment of the present invention, the comparison processing of the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data in combination with the reading real-life environment recommendation index to obtain the reading adaptation coefficient corresponding to the recommended article includes:

[0090] Input the article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data, and reading real-life environment recommendation index into a preset reading adaptation coefficient evaluation model for processing to obtain a reading adaptation coefficient corresponding to the recommended article;

[0091] The calculation formula of the reading adaptation coefficient in the reading adaptation coefficient evaluation model is:

[0092]

[0093] Among them, R e is the reading adaptation coefficient, d in 、s p1 d ac 、s p2 、e r They are respectively the article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data and reading environment recommendation index; θ, ψ1 and ψ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform).

[0094] It should be noted that the reading adaptability of an article needs to refer to the difficulty of the article, the time required for reading, and be finally determined in combination with the carnival. Therefore, the article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data, and reading environment recommendation index are input into the preset reading adaptability coefficient evaluation model for processing, and finally the reading adaptability coefficient corresponding to the recommended article is obtained.

[0095] According to an embodiment of the present invention, it also includes:

[0096] Get the historical average page-turning time data of users of the same article category data;

[0097] Obtain the average reading time data, help-seeking data and reference data of different users of the same article classification data, and analyze and process to obtain the difficulty coefficient of the article;

[0098] According to the historical average page turning time data combined with the article difficulty coefficient analysis and processing, automatic page turning time data is obtained;

[0099] Automatically turning pages according to the automatic page turning time data;

[0100] If the user returns manually, the repeated reading time data is obtained and the automatic page turning time data is corrected.

[0101] It should be noted that, in order to facilitate user reading, we first understand the historical average page turning time data of users for this type of article, and then obtain the difficulty coefficient of the corresponding article. According to the historical average page turning time data combined with the article difficulty coefficient analysis and processing, we obtain the automatic page turning time data, realize automatic page turning reading, and improve the reading experience. At the same time, if the user manually turns back to the previous page, the repeated reading time is counted, and then the automatic page turning time data is corrected to ensure that it is more suitable for the user's reading and page turning needs;

[0102] The calculation formula for the article difficulty coefficient is:

[0103]

[0104] Among them, d in is the difficulty coefficient of the article, d u 、a t d m They are the average reading time data, help-seeking data, and search data. γ1 and γ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform);

[0105] The automatic page turning time data calculation formula is:

[0106] T au =αT h d in ;

[0107] Among them, T au is the automatic page turning time data, T h d in are the historical average page turning time data and article difficulty coefficient, and α is the preset feature coefficient (the feature coefficient is obtained by querying the preset intelligent reading platform).

[0108] Please refer to Figure 3 , Figure 3 This is a flow chart of obtaining a user's visual fatigue index in a smart reading method based on digital magazines and e-books in some embodiments of the present application. According to an embodiment of the present invention, it also includes:

[0109] S31, obtaining the user's vision data and gaze duration data;

[0110] S32, inputting the visual acuity data, fixation duration data, brightness data, and time point data into a preset visual fatigue assessment model for analysis and processing to obtain a user's visual fatigue index;

[0111] S33, comparing the visual fatigue index with a preset visual fatigue threshold, if it is greater than the preset visual fatigue threshold, activating adaptive adjustment of the user-side reading interface and issuing an early warning.

[0112] It should be noted that users will experience visual fatigue after reading for a long time. To improve visual fatigue, the user's vision data and annotation duration data are first obtained, and then combined with the brightness data of the user's environment and the time point data, they are input into the preset visual fatigue assessment model for analysis and processing to obtain the user's visual fatigue index.

[0113] The calculation formula of the visual fatigue index in the visual fatigue evaluation model is:

[0114]

[0115] Among them, a st is the visual fatigue index, v i ,t l 、b h ,t n They are vision data, gaze duration data, brightness data, and time point data, respectively; ζ1 and ζ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform); and then a threshold comparison is performed with the preset visual fatigue threshold; in this embodiment, the preset visual fatigue threshold is set to (0, 0.4), [0.4, 1]. For example, when the visual fatigue index is calculated to be 0.6, the user-side reading interface is activated for adaptive adjustment, and an early warning is issued to remind the user to pay attention to eye health.

[0116] According to an embodiment of the present invention, it also includes:

[0117] Get user registration information;

[0118] Acquire the user's multi-reading platform setting information, historical reading information and historical annotation information according to the registration information;

[0119] Comparing the setting information, historical reading information and historical annotation information respectively for similarity, to obtain setting information similarity, reading information similarity and annotation information similarity;

[0120] According to the analysis and processing of the setting information similarity, the reading information similarity and the annotation information similarity, a cross-platform similarity is obtained;

[0121] Performing a threshold comparison between the cross-platform similarity and a preset cross-platform similarity threshold;

[0122] If it is greater than the preset cross-platform similarity threshold, the setting information, reading information and annotation information are removed;

[0123] If it is less than or equal to the preset cross-platform similarity deviation threshold, a user comprehensive reading record data queue table is constructed according to the setting information, historical reading information and historical annotation information of the user's multiple reading platforms.

[0124] It should be noted that in order to comprehensively evaluate the user's historical reading records, the setting information, historical reading information and historical annotation information of the same user on different reading platforms are obtained, and the similarity between multiple platforms is compared to obtain the setting information similarity, reading information similarity and annotation information similarity, and the cross-platform similarity is obtained by analysis and processing;

[0125] The cross-platform similarity calculation formula is:

[0126]

[0127] Among them, p c is the cross-platform similarity, s e 、r e 、n t The information similarity, reading information similarity and annotation information similarity are set respectively, and υ, ω1, ω2, and ω3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform); finally, a threshold comparison is performed with the preset cross-platform similarity threshold. In this embodiment, the preset cross-platform similarity threshold is set to (0, 0.3], (0.3, 1] corresponding to dissimilarity and similarity. For example, if the cross-platform similarity obtained is 0.4, it means that the two platforms are similar and there is information overlap, which is then removed; if the cross-platform similarity obtained is 0.2, it means that the two platforms are not similar and there is information difference, which is used to construct a user comprehensive reading record data queue table.

[0128] It is worth mentioning that according to an embodiment of the present invention, it also includes:

[0129] Get the user's reading page stay time data;

[0130] Comparing the page reading dwell time data with a preset page reading dwell time threshold;

[0131] If it is less than the first preset page reading dwell time threshold, it will be displayed normally;

[0132] If it is greater than or equal to the first preset page reading dwell time threshold and less than the second preset page reading dwell time threshold, then activate the content annotation response;

[0133] If it is greater than or equal to a second preset page reading dwell time threshold, the content annotation is stored and the screen-off response is activated.

[0134] It should be noted that when users are reading e-books, they may stay in one interface for a long time. At this time, there may be two situations: one is that they encounter reading difficulties, and the other is that they leave reading. To address this problem, when the time is greater than or equal to the first preset page reading stay time threshold and less than the second preset page reading stay time threshold, it is judged that there are reading difficulties, and content annotations are displayed in combination with the article content to assist users in reading. If the time is greater than or equal to the second preset page reading stay time threshold and the user is judged to have left reading, the content annotations are stored and the screen-off response is activated to protect reading privacy while saving battery power on the reading terminal.

[0135] It is worth mentioning that according to an embodiment of the present invention, it also includes:

[0136] Extracting multiple article keyword information including article word category information and article word meaning analysis information according to the recommended article information;

[0137] Comparing the word category information with the article word category information;

[0138] If the categories are the same, query the preset category weight score table to obtain the category weight value;

[0139] If the categories are different, then the word meaning analysis information is compared with the article word meaning analysis information to obtain semantic similarity;

[0140] The semantic weight value is calculated based on the semantic similarity and the preset category weight score table of the word category information;

[0141] Accumulate the category weight value and the semantic weight value to obtain a keyword score;

[0142] A list of recommended articles is generated from high to low according to the keyword scores.

[0143] It should be noted that after obtaining the recommended articles, in order to better facilitate users to choose to read, the recommended articles are sorted and displayed. First, the keyword information of the recommended articles including the article word category information and the article word meaning analysis information is extracted, and the word category information is compared with the article word category information. If they belong to the same category, the preset category weight score table is queried to obtain the category weight value. For example, the weight value is 10. If the categories are different, the semantic analysis information is compared with the article word meaning analysis information to obtain the semantic similarity. For example, the similarity is 0.6, and the queried category weight score is 8, then the semantic weight value is 0.6X8=4.8. The category weight value and the semantic weight value are added, 10+4.8=14.8, which is the keyword score; finally, a list of recommended articles is generated from high to low according to the obtained keyword scores for users to choose to read.

[0144] The present invention also discloses an intelligent reading system based on digital magazine electronic books, comprising a memory and a processor, wherein the memory comprises an intelligent reading method program based on digital magazine electronic books, and when the intelligent reading method program based on digital magazine electronic books is executed by the processor, the following steps are implemented:

[0145] Obtain the user's personalized reading record information and generate a user reading record data queue table;

[0146] Obtaining keyword information of the user's reading search and real-time environment data of the user's real-time reading, wherein the real-time environment data includes brightness data and time point data;

[0147] According to the personalized reading record information, keyword information and time point data, a preset e-book reading database is queried to obtain recommended article information;

[0148] Extracting article reading guide feature data according to the recommended article information, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data;

[0149] Processing the real-time environment data and the estimated reading time data to obtain a reading environment recommendation index;

[0150] According to the article classification data, query the user reading record data queue table to obtain corresponding user reading record data, including article content difficulty coefficient and average reading speed data corresponding to the article classification data;

[0151] Comparing the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data with the reading actual environment recommendation index, to obtain a reading adaptation coefficient corresponding to the recommended article;

[0152] A threshold comparison is performed based on the reading adaptation coefficient and a preset reading adaptation threshold. If the threshold comparison result meets the preset threshold requirement, the recommended article is recommended.

[0153] It should be noted that in order to obtain recommended articles that meet the user's actual environment and needs, personalized reading record information including reading category information, article content information and reading speed record information is first obtained, and a user reading record data queue table is generated to obtain keyword information including word category information and word meaning analysis information, including brightness data and time point data. The preset e-book reading database is queried based on the obtained personalized reading record information, keyword information and real-time environment data to obtain recommended article information, and article reading guidance feature data is extracted, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data. The brightness data, time point data and reading time estimation data are combined for processing to obtain the reading speed data. The real-time environment recommendation index is used to determine whether it meets the real-time environment requirements of the user. Then, according to the article classification data, the user reading record data queue table is queried to obtain the user reading record data including the corresponding article content difficulty coefficient and the average reading speed data. According to the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data, the reading adaptation coefficient corresponding to the recommended article is obtained in combination with the reading real-time environment recommendation index. Finally, according to the threshold comparison, it is determined whether the recommended article is recommended. In this embodiment, the preset reading adaptation threshold is (0, 0.7), and [0.7, 1] corresponds to not recommending and recommending. For example, if the obtained reading adaptation coefficient is 0.8, the recommended article is recommended and sent to the user reading terminal for display.

[0154] According to an embodiment of the present invention, querying a preset e-book reading database according to the personalized reading record information, keyword information and time point data to obtain recommended article information includes:

[0155] The personalized reading record information includes reading category information, article content information and reading speed record information;

[0156] The keyword information includes word category information and word meaning analysis information;

[0157] According to the reading category information, article content information, reading speed record information, word category information, word meaning analysis information and time point data, a preset e-book reading database is queried to obtain recommended article information.

[0158] It should be noted that in order to obtain recommended article information, the user's personalized reading record information is first obtained to understand the user's historical reading records, including reading category information, article content information and reading speed record information, and then the search keyword information input by the user in real time is obtained. Finally, the time of the user's real-time environment is obtained, such as 8:00 a.m. on the subway commute. Finally, according to the reading category information, article content information, reading speed record information, word category information, word meaning analysis information and time point data, the preset e-book reading database is queried to obtain recommended article information, and based on the recommended article information, article reading guidance feature data is extracted, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data, for adaptation detection.

[0159] According to an embodiment of the present invention, the processing according to the real-time environment data and the reading time estimation data to obtain a reading real-time environment recommendation index includes:

[0160] Input the brightness data, time point data and reading time estimation data into a preset reading real-life environment recommendation index evaluation model for analysis and processing to obtain a reading real-life environment recommendation index;

[0161] The calculation formula of the reading real-time environment recommendation index in the reading real-time environment recommendation index evaluation model is:

[0162]

[0163] Among them, e r Recommended index for reading live environment, b h ,t n ,t r They are brightness data, time point data and reading time estimation data respectively, and κ1, κ2, κ3, λ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform).

[0164] It should be noted that by inputting brightness data, time point data and reading time estimation data into a preset reading environment recommendation index evaluation model for analysis and processing, the reading environment recommendation index is obtained, which is used to determine whether the recommendation requirements are met in combination with the article content.

[0165] According to an embodiment of the present invention, the comparison processing of the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data in combination with the reading real-life environment recommendation index to obtain the reading adaptation coefficient corresponding to the recommended article includes:

[0166] Input the article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data, and reading real-life environment recommendation index into a preset reading adaptation coefficient evaluation model for processing to obtain a reading adaptation coefficient corresponding to the recommended article;

[0167] The calculation formula of the reading adaptation coefficient in the reading adaptation coefficient evaluation model is:

[0168]

[0169] Among them, R e is the reading adaptation coefficient, d in 、s p1 d ac 、s p2 、e r They are respectively the article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data and reading environment recommendation index; θ, ψ1 and ψ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform).

[0170] It should be noted that the reading adaptability of an article needs to refer to the difficulty of the article, the time required for reading, and be finally determined in combination with the carnival. Therefore, the article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data, and reading environment recommendation index are input into the preset reading adaptability coefficient evaluation model for processing, and finally the reading adaptability coefficient corresponding to the recommended article is obtained.

[0171] According to an embodiment of the present invention, it also includes:

[0172] Get the historical average page-turning time data of users of the same article category data;

[0173] Obtain the average reading time data, help-seeking data and reference data of different users of the same article classification data, and analyze and process to obtain the difficulty coefficient of the article;

[0174] According to the historical average page turning time data combined with the article difficulty coefficient analysis and processing, automatic page turning time data is obtained;

[0175] Automatically turning pages according to the automatic page turning time data;

[0176] If the user returns manually, the repeated reading time data is obtained and the automatic page turning time data is corrected.

[0177] It should be noted that, in order to facilitate user reading, we first understand the historical average page turning time data of users for this type of article, and then obtain the difficulty coefficient of the corresponding article. According to the historical average page turning time data combined with the article difficulty coefficient analysis and processing, we obtain the automatic page turning time data, realize automatic page turning reading, and improve the reading experience. At the same time, if the user manually turns back to the previous page, the repeated reading time is counted, and then the automatic page turning time data is corrected to ensure that it is more suitable for the user's reading and page turning needs;

[0178] The calculation formula for the article difficulty coefficient is:

[0179]

[0180] Among them, d in is the difficulty coefficient of the article, d u 、a t d m They are the average reading time data, help-seeking data, and search data. γ1 and γ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform);

[0181] The automatic page turning time data calculation formula is:

[0182] T au =αT h d in ;

[0183] Among them, T au is the automatic page turning time data, T h d in are the historical average page turning time data and article difficulty coefficient, and α is the preset feature coefficient (the feature coefficient is obtained by querying the preset intelligent reading platform).

[0184] According to an embodiment of the present invention, it also includes:

[0185] Obtain the user's vision data and gaze duration data;

[0186] Inputting the visual acuity data, fixation duration data, brightness data, and time point data into a preset visual fatigue assessment model for analysis and processing to obtain a user's visual fatigue index;

[0187] The visual fatigue index is compared with a preset visual fatigue threshold. If the visual fatigue index is greater than the preset visual fatigue threshold, the user-side reading interface is adaptively adjusted and an early warning is issued.

[0188] It should be noted that users will experience visual fatigue after reading for a long time. To improve visual fatigue, the user's vision data and annotation duration data are first obtained, and then combined with the brightness data of the user's environment and the time point data, they are input into the preset visual fatigue assessment model for analysis and processing to obtain the user's visual fatigue index.

[0189] The calculation formula of the visual fatigue index in the visual fatigue evaluation model is:

[0190]

[0191] Among them, a st is the visual fatigue index, v i ,t l 、b h ,t n They are vision data, gaze duration data, brightness data, and time point data, respectively; ζ1 and ζ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform); and then a threshold comparison is performed with the preset visual fatigue threshold; in this embodiment, the preset visual fatigue threshold is set to (0, 0.4), [0.4, 1]. For example, when the visual fatigue index is calculated to be 0.6, the user-side reading interface is activated for adaptive adjustment, and an early warning is issued to remind the user to pay attention to eye health.

[0192] According to an embodiment of the present invention, it also includes:

[0193] Get user registration information;

[0194] Acquire the user's multi-reading platform setting information, historical reading information and historical annotation information according to the registration information;

[0195] Comparing the setting information, historical reading information and historical annotation information respectively for similarity, to obtain setting information similarity, reading information similarity and annotation information similarity;

[0196] According to the analysis and processing of the setting information similarity, the reading information similarity and the annotation information similarity, a cross-platform similarity is obtained;

[0197] Performing a threshold comparison between the cross-platform similarity and a preset cross-platform similarity threshold;

[0198] If it is greater than the preset cross-platform similarity threshold, the setting information, reading information and annotation information are removed;

[0199] If it is less than or equal to the preset cross-platform similarity deviation threshold, a user comprehensive reading record data queue table is constructed according to the setting information, historical reading information and historical annotation information of the user's multiple reading platforms.

[0200] It should be noted that in order to comprehensively evaluate the user's historical reading records, the setting information, historical reading information and historical annotation information of the same user on different reading platforms are obtained, and the similarity between multiple platforms is compared to obtain the setting information similarity, reading information similarity and annotation information similarity, and the cross-platform similarity is obtained by analysis and processing;

[0201] The cross-platform similarity calculation formula is:

[0202]

[0203] Among them, p c is the cross-platform similarity, s e 、r e 、n t The information similarity, reading information similarity and annotation information similarity are set respectively, and υ, ω1, ω2, and ω3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset intelligent reading platform); finally, a threshold comparison is performed with the preset cross-platform similarity threshold. In this embodiment, the preset cross-platform similarity threshold is set to (0, 0.3], (0.3, 1] corresponding to dissimilarity and similarity. For example, if the cross-platform similarity obtained is 0.4, it means that the two platforms are similar and there is information overlap, which is then removed; if the cross-platform similarity obtained is 0.2, it means that the two platforms are not similar and there is information difference, which is used to construct a user comprehensive reading record data queue table.

[0204] It is worth mentioning that according to an embodiment of the present invention, it also includes:

[0205] Get the user's reading page stay time data;

[0206] Comparing the page reading dwell time data with a preset page reading dwell time threshold;

[0207] If it is less than the first preset page reading dwell time threshold, it will be displayed normally;

[0208] If it is greater than or equal to the first preset page reading dwell time threshold and less than the second preset page reading dwell time threshold, then activate the content annotation response;

[0209] If it is greater than or equal to a second preset page reading dwell time threshold, the content annotation is stored and the screen-off response is activated.

[0210] It should be noted that when users are reading e-books, they may stay in one interface for a long time. At this time, there may be two situations: one is that they encounter reading difficulties, and the other is that they leave reading. To address this problem, when the time is greater than or equal to the first preset page reading stay time threshold and less than the second preset page reading stay time threshold, it is judged that there are reading difficulties, and content annotations are displayed in combination with the article content to assist users in reading. If the time is greater than or equal to the second preset page reading stay time threshold and the user is judged to have left reading, the content annotations are stored and the screen-off response is activated to protect reading privacy while saving battery power on the reading terminal.

[0211] It is worth mentioning that according to an embodiment of the present invention, it also includes:

[0212] Extracting multiple article keyword information including article word category information and article word meaning analysis information according to the recommended article information;

[0213] Comparing the word category information with the article word category information;

[0214] If the categories are the same, query the preset category weight score table to obtain the category weight value;

[0215] If the categories are different, then the word meaning analysis information is compared with the article word meaning analysis information to obtain semantic similarity;

[0216] The semantic weight value is calculated based on the semantic similarity and the preset category weight score table of the word category information;

[0217] Accumulate the category weight value and the semantic weight value to obtain a keyword score;

[0218] A list of recommended articles is generated from high to low according to the keyword scores.

[0219] It should be noted that after obtaining the recommended articles, in order to better facilitate users to choose to read, the recommended articles are sorted and displayed. First, the keyword information of the recommended articles including the article word category information and the article word meaning analysis information is extracted, and the word category information is compared with the article word category information. If they belong to the same category, the preset category weight score table is queried to obtain the category weight value. For example, the weight value is 10. If the categories are different, the semantic analysis information is compared with the article word meaning analysis information to obtain the semantic similarity. For example, the similarity is 0.6, and the queried category weight score is 8, then the semantic weight value is 0.6X8=4.8. The category weight value and the semantic weight value are added, 10+4.8=14.8, which is the keyword score; finally, a list of recommended articles is generated from high to low according to the obtained keyword scores for users to choose to read.

[0220] A third aspect of the present invention provides a readable storage medium, which stores a program for an intelligent reading method based on digital magazine e-books. When the program for an intelligent reading method based on digital magazine e-books is executed by a processor, the steps of the intelligent reading method based on digital magazine e-books as described in any one of the above items are implemented.

[0221] The present invention discloses an intelligent reading method, system and medium based on digital magazine e-books, which preliminarily obtains recommended article information, further analyzes the specific content and obtains a reading adaptation coefficient in combination with real-life environment processing, and finally determines whether the recommended article is recommended by threshold comparison, thereby improving the pertinence and effectiveness of user reading.

[0222] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0223] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0224] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0225] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0226] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. An intelligent reading method based on digital magazine e-books, characterized in that: The following steps are involved: Obtain the user's personalized reading record information and generate a user reading record data queue table; Obtaining keyword information of the user's reading search and real-time environment data of the user's real-time reading, wherein the real-time environment data includes brightness data and time point data; According to the personalized reading record information, keyword information and time point data, a preset e-book reading database is queried to obtain recommended article information; Extracting article reading guide feature data according to the recommended article information, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data; Processing the real-time environment data and the reading time estimation data to obtain a reading environment recommendation index; According to the article classification data, query the user reading record data queue table to obtain corresponding user reading record data, including article content difficulty coefficient and average reading speed data corresponding to the article classification data; Comparing the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data with the reading actual environment recommendation index, to obtain a reading adaptation coefficient corresponding to the recommended article; A threshold comparison is performed based on the reading adaptation coefficient and a preset reading adaptation threshold. If the threshold comparison result meets the preset threshold requirement, the recommended article is recommended.

2. The intelligent reading method based on digital magazine e-book according to claim 1, characterized in that: The step of querying a preset e-book reading database according to the personalized reading record information, keyword information, and time point data to obtain recommended article information includes: The personalized reading record information includes reading category information, article content information and reading speed record information; The keyword information includes word category information and word meaning analysis information; According to the reading category information, article content information, reading speed record information, word category information, word meaning analysis information and time point data, a preset e-book reading database is queried to obtain recommended article information.

3. The intelligent reading method based on digital magazine e-book according to claim 2 is characterized in that: The step of processing the real-time environment data and the reading time estimation data to obtain a reading environment recommendation index includes: Input the brightness data, time point data and reading time estimation data into a preset reading environment recommendation index evaluation model for analysis and processing to obtain a reading environment recommendation index; The calculation formula of the reading real-time environment recommendation index in the reading real-time environment recommendation index evaluation model is: Among them, e r Recommended index for reading live environment, b h ,t n ,t r They are brightness data, time point data and reading time estimation data, and κ1, κ2, κ3 and λ are preset characteristic coefficients.

4. The intelligent reading method based on digital magazine e-book according to claim 3 is characterized in that: The step of performing comparison processing based on the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data in combination with the reading real-life environment recommendation index to obtain a reading adaptation coefficient corresponding to the recommended article includes: Input the article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data, and reading real-life environment recommendation index into a preset reading adaptation coefficient evaluation model for processing to obtain a reading adaptation coefficient corresponding to the recommended article; The calculation formula of the reading adaptation coefficient in the reading adaptation coefficient evaluation model is: Among them, R e is the reading adaptation coefficient, d in 、s p1 ,d ac 、s p2 、e r They are article difficulty coefficient, recommended reading speed data, article content difficulty coefficient, average reading speed data and reading environment recommendation index, θ, ψ1 and ψ2 are preset characteristic coefficients.

5. The intelligent reading method based on digital magazine electronic book according to claim 4 is characterized in that: Also includes: Get the historical average page-turning time data of users of the same article category data; Obtain the average reading time data, help-seeking data and reference data of different users of the same article classification data, and analyze and process to obtain the difficulty coefficient of the article; According to the historical average page turning time data combined with the article difficulty coefficient analysis and processing, automatic page turning time data is obtained; Automatically turning pages according to the automatic page turning time data; If the user returns manually, the repeated reading time data is obtained and the automatic page turning time data is corrected.

6. The intelligent reading method based on digital magazine electronic book according to claim 5, characterized in that: Also includes: Obtain the user's vision data and gaze duration data; Inputting the visual acuity data, fixation duration data, brightness data, and time point data into a preset visual fatigue assessment model for analysis and processing to obtain a user's visual fatigue index; The visual fatigue index is compared with a preset visual fatigue threshold. If the index is greater than the preset visual fatigue threshold, the user-side reading interface is adaptively adjusted and an early warning is issued.

7. The intelligent reading method based on digital magazine electronic book according to claim 6, characterized in that: Also includes: Get user registration information; Acquire the user's multi-reading platform setting information, historical reading information and historical annotation information according to the registration information; Comparing the setting information, historical reading information and historical annotation information respectively for similarity, to obtain setting information similarity, reading information similarity and annotation information similarity; According to the analysis and processing of the setting information similarity, the reading information similarity and the annotation information similarity, a cross-platform similarity is obtained; Performing a threshold comparison between the cross-platform similarity and a preset cross-platform similarity threshold; If it is greater than the preset cross-platform similarity threshold, the setting information, reading information and annotation information are removed; If it is less than or equal to the preset cross-platform similarity deviation threshold, a user comprehensive reading record data queue table is constructed according to the setting information, historical reading information and historical annotation information of the user's multiple reading platforms.

8. An intelligent reading system based on digital magazines and electronic books, characterized in that: The invention comprises a memory and a processor, wherein the memory comprises a program of an intelligent reading method based on digital magazines and electronic books, and the program of the intelligent reading method based on digital magazines and electronic books is executed by the processor to implement the following steps: Obtain the user's personalized reading record information and generate a user reading record data queue table; Obtaining keyword information of the user's reading search and real-time environment data of the user's real-time reading, wherein the real-time environment data includes brightness data and time point data; According to the personalized reading record information, keyword information and time point data, a preset e-book reading database is queried to obtain recommended article information; Extracting article reading guide feature data according to the recommended article information, including article classification data, article difficulty coefficient, recommended reading speed data and reading time estimation data; Processing the real-time environment data and the reading time estimation data to obtain a reading environment recommendation index; According to the article classification data, query the user reading record data queue table to obtain corresponding user reading record data, including article content difficulty coefficient and average reading speed data corresponding to the article classification data; Comparing the article difficulty coefficient, the recommended reading speed data, the article content difficulty coefficient and the average reading speed data with the reading actual environment recommendation index, to obtain a reading adaptation coefficient corresponding to the recommended article; A threshold comparison is performed based on the reading adaptation coefficient and a preset reading adaptation threshold. If the threshold comparison result meets the preset threshold requirement, the recommended article is recommended.

9. The intelligent reading system based on digital magazine and electronic book according to claim 8, characterized in that: The step of querying a preset e-book reading database according to the personalized reading record information, keyword information, and time point data to obtain recommended article information includes: The personalized reading record information includes reading category information, article content information and reading speed record information; The keyword information includes word category information and word meaning analysis information; According to the reading category information, article content information, reading speed record information, word category information, word meaning analysis information and time point data, a preset e-book reading database is queried to obtain recommended article information.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an intelligent reading program based on digital magazine e-books. When the intelligent reading program based on digital magazine e-books is executed by the processor, the steps of the intelligent reading method based on digital magazine e-books as described in any one of claims 1 to 7 are implemented.

Images