Information Push Method, Electronic Device and Storage Medium

Abstract

The present disclosure relates to an information push method, an electronic device, and a storage medium. Among them, the information push method includes: obtaining reading-related data of at least one data dimension of a target user and a copywriting preference classification of the target user; screening out books to be pushed from multiple preset books based on the reading-related data of at least one data dimension; screening out copywriting to be pushed from multiple preset copywritings corresponding to the books to be pushed based on the copywriting preference classification; generating a target push message corresponding to the target user according to the copywriting to be pushed. According to the embodiments of the present disclosure, it is possible to make the generated push message conform to the book reading preferences of the target user, meet the needs of personalized information push, and at the same time, the target push message can attract the book reading interest of the target user, so that the target user reads the books to be pushed on the e-book platform, further improving the popularity and page views of the e-book platform.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and particularly to an information push method, an electronic device, and a storage medium. Background Art

[0002] With the continuous development of Internet technology, users can utilize network resources to browse e-books of their interest on different platforms.

[0003] In order to increase the popularity of the e-book platform and the user access volume, push messages can be generated for the books provided by the e-book platform. However, the current information push method is single, and for different users, only a unified method can be used to generate push messages. Therefore, the diverse information push requirements of different users cannot be met. Summary of the Invention

[0004] To solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an information push method, an electronic device, and a storage medium.

[0005] In a first aspect, the present disclosure provides an information push method, including:

[0006] Obtaining reading-related data of at least one data dimension of a target user and the copywriting preference classification of the target user;

[0007] Based on the reading-related data of at least one data dimension, screening out books to be pushed from multiple preset books;

[0008] Based on the copywriting preference classification, screening out copywriting to be pushed from multiple preset copywritings corresponding to the books to be pushed;

[0009] Generating a target push message corresponding to the target user according to the copywriting to be pushed.

[0010] In a second aspect, the present disclosure provides an electronic device, including a processor and a memory, where the memory is used to store executable instructions, and the executable instructions cause the processor to perform the following operations:

[0011] Obtaining reading-related data of at least one data dimension of a target user and the copywriting preference classification of the target user;

[0012] Based on the reading-related data of at least one data dimension, screening out books to be pushed from multiple preset books;

[0013] Based on the copywriting preference classification, screening out copywriting to be pushed from multiple preset copywritings corresponding to the books to be pushed;

[0014] Generating a target push message corresponding to the target user according to the copywriting to be pushed.

[0015] In a third aspect, the present disclosure provides a computer-readable storage medium storing a computer program, which when executed by a processor, causes the processor to implement the information pushing method of the first aspect.

[0016] The technical solutions provided by the embodiments of the present disclosure have the following advantages compared with the prior art:

[0017] The information pushing method, electronic device and storage medium of the embodiments of the present disclosure can obtain the reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user. Then, based on the reading-related data of at least one data dimension, the books to be pushed are screened out from multiple preset books. Further, based on the copywriting preference classification, the copywriting to be pushed is screened out from multiple preset copywritings corresponding to the books to be pushed, and the target push message corresponding to the target user is generated according to the copywriting to be pushed. Thus, when pushing information, books matching the target user can be screened out, and the copywriting to be pushed and the target push message that meet the user's preferences can be generated, so that the generated push message can conform to the target user's book reading preferences, meeting the need for personalized information pushing. At the same time, the target user's interest in book reading can be attracted through the target push message, enabling the target user to read the books to be pushed on the e-book platform, further improving the popularity and viewing volume of the e-book platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages and aspects of the embodiments of the present disclosure will become more obvious. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic, and the original and elements are not necessarily drawn to scale.

[0019] Figure 1 FIG. shows a flowchart of an information pushing method provided by an embodiment of the present disclosure;

[0020] Figure 2 FIG. shows a flowchart of another information pushing method provided by an embodiment of the present disclosure;

[0021] Figure 3 FIG. shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0023] It should be understood that the various steps recited in the method embodiments of the present disclosure can be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0024] As used herein, the term "including" and its variations are open-ended, that is, "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0025] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0026] It should be noted that the modifications of "one" and "plural" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0027] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0028] The embodiments of the present disclosure provide an information push method, an electronic device and a storage medium that can generate a target push message of a book to be pushed.

[0029] First, the following is combined with Figure 1 - Figure 2 to illustrate the information push method provided by the embodiments of the present disclosure.

[0030] The information push method provided by the embodiments of the present disclosure can be implemented by an electronic device capable of providing the function of generating target push messages. Among them, the electronic device may include, but is not limited to, mobile terminals such as smart phones, laptop computers, personal digital assistants (PDAs), tablet computers (PADs), portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), wearable devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, servers, etc., which are not limited herein.

[0031] Figure 1 The flowchart of an information push method provided by the embodiments of the present disclosure is shown.

[0032] As Figure 1 shown, the information push method may include the following steps.

[0033] S110. Obtain the reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user.

[0034] In the embodiments of the present disclosure, when it is necessary to generate a push message corresponding to the book pushed to the target user, the electronic device may obtain the reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user, so as to determine the book recommended to the user according to the reading-related data, and determine the copywriting pushed to the user according to the copywriting preference classification.

[0035] In the embodiments of the present disclosure, the target user may be any user who needs to receive information push.

[0036] In the embodiments of the present disclosure, the data dimension may be an angle of consideration for determining the screening of books.

[0037] Optionally, the data dimension may include the dimension of unread books of the target user, the dimension of interacted books of the target user, the dimension of best-selling books, etc.

[0038] In some embodiments, the data dimension is the dimension of unread books of the target user, and the reading-related data may be the reading data of the books of the target user on the e-book platform.

[0039] In other embodiments, the data dimension is the dimension of interacted books of the target user, and the reading-related data may be the book interaction data of the target user on the e-book platform.

[0040] In still other embodiments, the data dimension is the dimension of best-selling books, and the reading-related data may be the book information of best-selling books.

[0041] In the embodiments of the present disclosure, the copywriting preference classification may be the classification of copywriting templates liked by the target user.

[0042] Optionally, the copywriting preference classification may include at least one of classifications such as the protagonist copywriting template classification of the book, the author copywriting template classification, the book title copywriting template classification, and the popular comment template classification of the book.

[0043] S120. Based on the reading-related data of at least one data dimension, screen out the books to be pushed from multiple preset books.

[0044] In the embodiment of the present disclosure, after the electronic device obtains the reading-related data of at least one data dimension, it may screen out the books for generating the copywriting to be pushed from multiple preset books according to the reading-related data of at least one data dimension, that is, determine the books to be pushed.

[0045] In the embodiment of the present disclosure, the preset books may be multiple books provided by an e-book platform.

[0046] In the embodiment of the present disclosure, the books to be pushed may be the books for pushing to the target user and for generating the copywriting to be pushed. Specifically, the books to be pushed may be the books matching the target user.

[0047] In some embodiments, for each data dimension, at least one book may be screened out from multiple preset books according to the reading-related data as the book to be pushed.

[0048] In other embodiments, for each data dimension, according to the reading-related data, the candidate books corresponding to the data dimension may be first screened out from multiple preset books, and then the books to be pushed may be selected from the candidate books corresponding to each data dimension according to the push priority of each data dimension.

[0049] In still other embodiments, according to the reading-related data corresponding to any one data dimension, at least one book corresponding to the data dimension is screened out from multiple preset books as the book to be pushed.

[0050] Thus, in the embodiment of the present disclosure, based on the reading-related data of at least one data dimension of the target user, the books matching the target user may be screened out from the preset books as the books to be pushed.

[0051] S130. Based on the copywriting preference classification, screen out the copywriting to be pushed from multiple preset copywritings corresponding to the book to be pushed.

[0052] In the embodiment of the present disclosure, after the electronic device obtains the copywriting preference classification of the target user, it may select the preset copywriting corresponding to the copywriting preference classification from multiple preset copywritings corresponding to the book to be pushed as the copywriting to be pushed.

[0053] In the embodiment of the present disclosure, the preset copywriting may be any type of copywriting generated based on the core elements of the book to be pushed.

[0054] In some embodiments, if the core element is the protagonist, the corresponding copywriting category of the preset copy is the protagonist category.

[0055] In some other embodiments, if the core element is the author, the corresponding copywriting category of the preset copy is the author category.

[0056] In still some other embodiments, if the core element is the book title, the corresponding copywriting category of the preset copy is the book title category.

[0057] In yet some other embodiments, if the core element is the popular book review, the corresponding copywriting category of the preset copy is the popular book review category.

[0058] In the embodiments of the present disclosure, the copy to be pushed can be a book push copy for generating a push message.

[0059] Optionally, the copy to be pushed can be in the form of pure pictures, pure text, a combination of text and pictures, etc., which is not limited herein.

[0060] Thus, in the embodiments of the present disclosure, the copy to be pushed corresponding to the copy preference category can be screened out from multiple preset copies, so that the generated copy to be pushed better meets the user's preference, achieving the purpose of personalized copy generation.

[0061] S140. Generate a target push message corresponding to the target user according to the copy to be pushed.

[0062] In the embodiments of the present disclosure, after the electronic device generates the copy to be pushed, a target push message corresponding to the target user can be generated based on the copy content of the copy to be pushed.

[0063] In the embodiments of the present disclosure, the target push message can be a push message for pushing to the terminal used by the target user.

[0064] In some embodiments, if the copy to be pushed is in the form of pure pictures, some picture content in the copy to be pushed can be converted into text and non-text, and a target push message for the target user can be generated according to the editing rules of the push message.

[0065] In some other embodiments, if the copy to be pushed is in the form of pure text, some text for generating the push message can be extracted from the copy to be pushed, and a target push message for the target user can be generated according to the editing rules of the push message.

[0066] In still other embodiments, if the copywriting to be pushed is a copywriting in the form of a combination of text and pictures, some of the picture content can be converted into text and non-text, and some text for generating the message to be pushed can be extracted from the text of the copywriting to be pushed, and according to the editing rules of the push message, a target push message for the target user can be generated.

[0067] Optionally, the editing rules of the push message can include rules such as the text limit rule and the text layout rule of the push message.

[0068] Thus, in the embodiments of the present disclosure, a message to be pushed can be generated according to the copywriting to be pushed that conforms to the user's preference, so that the reading interest of the target user in books can be attracted through the message to be pushed. If a trigger operation for the target push message is received from the target user, it can be redirected to the e-book platform, enabling the user to read the books they are interested in on the e-book platform.

[0069] In the embodiments of the present disclosure, at least one data dimension of reading-related data of the target user and the copywriting preference classification of the target user can be obtained. Then, based on the reading-related data of at least one data dimension, the books to be pushed are screened out from multiple preset books. Further, based on the copywriting preference classification, the copywriting to be pushed is screened out from multiple preset copywritings corresponding to the books to be pushed, and a target push message corresponding to the target user is generated according to the copywriting to be pushed. Thus, when pushing information, books matching the target user can be screened out, and a copywriting to be pushed and a target push message that conform to the user's preference can be generated, so that the generated push message can conform to the book reading preferences of the target user, meeting the need for personalized information push. At the same time, the reading interest of the target user in books can be attracted through the target push message, enabling the target user to read the books to be pushed on the e-book platform, further improving the popularity and page views of the e-book platform.

[0070] In another implementation manner of the present disclosure, a pre-trained copywriting preference detection model can be used to calculate the predicted values corresponding to each preset copywriting classification, and based on the predicted values, the copywriting preference classification is determined.

[0071] In some embodiments of the present disclosure, for obtaining the copywriting preference classification of the target user in S110, it can specifically include the following steps.

[0072] S1101. Obtain the message interaction data of the target user for the historical push message.

[0073] In the embodiments of the present disclosure, when it is necessary to determine the copywriting preference classification of the target user, the electronic device can obtain the historical push message, and for the historical push message, obtain the message interaction data of the target user for the historical push message.

[0074] In the embodiments of the present disclosure, the historical push message may be the push message corresponding to the pushed book. Specifically, the historical push message may be a push message generated based on the pushed copywriting corresponding to the pushed book.

[0075] In the embodiments of the present disclosure, the message interaction data may be the operation record of the target user for the historical push message and / or the operation record for the pushed book corresponding to the historical push message.

[0076] Optionally, the operation record of the target user for the historical push message may include at least one of the target user's click-open record and ignore record.

[0077] Optionally, the operation record of the target user for the pushed book corresponding to the historical push message may include at least one of records such as purchase record, like record, comment record, favorite record, add-to-bookshelf record, and reading record.

[0078] S1102. Input the message interaction data into a pre-trained copywriting preference detection model to obtain the predicted values corresponding to each preset copywriting classification output by the copywriting preference detection model.

[0079] In the embodiments of the present disclosure, after the electronic device obtains the message interaction data, the message interaction data may be input into a pre-trained copywriting preference detection model, so that the copywriting preference detection model is used to calculate the predicted values corresponding to each preset copywriting classification.

[0080] In the embodiments of the present disclosure, the copywriting preference detection model may be trained using the sample interaction data of multiple sample users for the sample push messages. Specifically, the sample push messages may be input into an initial model, and the initial model is used to vectorize each push copywriting corresponding to the sample push messages. Based on the vectorized push copywriting corresponding to the sample push messages and the sample interaction data, the initial model is iteratively trained to obtain a trained copywriting preference detection model.

[0081] S1103. Select the copywriting preference classification from multiple preset copywriting classifications according to the predicted values.

[0082] In the embodiments of the present disclosure, after the electronic device calculates the predicted values corresponding to each preset copywriting classification, the copywriting preference classification may be selected according to the magnitudes of the predicted values corresponding to each preset copywriting classification.

[0083] In some embodiments, the preset copywriting classification with the largest predicted value calculated by the copywriting preference classification model may be used as the copywriting preference classification.

[0084] In other embodiments, S1103 may specifically include the following steps.

[0085] S11031. Classify the preset copywriting categories that have not been pushed within the first preset time period as candidate copywriting categories.

[0086] Specifically, for the first preset time period, the electronic device can select the copywriting categories that have not been pushed from the preset copywriting categories as candidate copywriting categories, so as to further determine the copywriting preference categories of the target user based on the candidate copywriting categories.

[0087] Among them, the first preset time period can be the time period corresponding to each push cycle for determining the preset copywriting categories that have not been pushed.

[0088] Optionally, the push cycle can be time periods such as 1 day, 3 days, 1 week, etc., which are not limited here.

[0089] Among them, the candidate copywriting categories can be the preset copywriting categories used to determine the copywriting preference categories.

[0090] Exemplarily, if the push cycle is 1 day and the first preset time period is 12 hours, within each day, the electronic device can determine the copywriting that has been pushed and the copywriting that has not been pushed within the 12 hours before the current time, and then select the candidate copywriting categories from the copywriting that has not been pushed within the 12 hours before the current time.

[0091] S11032. Use the candidate copywriting category with the largest predicted value as the copywriting preference category.

[0092] Specifically, after the electronic device determines the candidate copywriting categories, it can select the copywriting category with the largest predicted value from the candidate copywriting categories as the copywriting preference category.

[0093] Thus, in the embodiments of the present disclosure, by classifying the preset copywriting categories that have not been pushed within the first preset time period as candidate copywriting categories, and using the candidate copywriting category with the largest predicted value as the copywriting preference category, the determined copywriting preference categories are not repeated within the first preset time period, avoiding always using the same copywriting category as the copywriting preference category of the target user, and thus avoiding always generating the same target push message.

[0094] In still other embodiments, S1103 may specifically include the following steps.

[0095] S11033. Select candidate copywriting categories from the preset copywriting categories whose predicted values are greater than or equal to the predicted value threshold.

[0096] Specifically, the electronic device can compare the predicted values corresponding to each preset copywriting category with the predicted value threshold, and use the preset copywriting categories whose predicted values are greater than or equal to the predicted value threshold as candidate copywriting categories.

[0097] Among them, the predicted value threshold can be a predicted value preset according to needs for selecting candidate copywriting classifications.

[0098] S11034. Classify the candidate copywriting with the largest predicted value that has not been pushed within the first preset time period as the copywriting preference classification.

[0099] Specifically, for the first preset time period, the electronic device can select, from the preset copywriting classifications, the candidate copywriting classification with the largest predicted value that has not been pushed as the copywriting preference classification of the target user.

[0100] Thus, in the embodiments of the present disclosure, the candidate copywriting classifications with predicted values greater than or equal to the predicted value threshold can be first selected from the preset copywriting classifications, and then the candidate copywriting classification with the largest predicted value that has not been pushed within the first preset time period is used as the copywriting preference classification, so that the determined copywriting preference classification is not repeated within the first preset time period, avoiding always using the same copywriting classification as the copywriting preference classification of the target user, and further avoiding always generating the same target push message.

[0101] In summary, in the embodiments of the present disclosure, the copywriting preference classification of the target user can be determined based on the predicted values corresponding to each preset copywriting classification, and different methods can be adopted based on the predicted values, improving the flexibility of determining the copywriting preference classification.

[0102] In another implementation manner of the present disclosure, the number of message pushes of the target user within the second preset time period can be compared with a preset number threshold, and according to different comparison results, different methods can be adopted to select the copywriting to be pushed corresponding to the copywriting preference classification from the preset copywriting.

[0103] In some embodiments of the present disclosure, S130 may specifically include the following steps.

[0104] S1301. Obtain the number of message pushes for the target user within the second preset time period.

[0105] In the embodiments of the present disclosure, after the electronic device determines the copywriting preference classification of the target user, for the second preset time period, the number of message pushes of the target user can be obtained, so as to determine the copywriting to be pushed based on the magnitude of the number of message pushes.

[0106] In the embodiments of the present disclosure, the second preset time period can be the time period corresponding to each push cycle for determining the number of message pushes.

[0107] Optionally, the push cycle can be a time period such as 1 day, 3 days, 1 week, etc., which is not limited here.

[0108] In the embodiments of the present disclosure, the number of message pushes can be the number of pushes of the copywriting corresponding to the copywriting preference classification that has been pushed.

[0109] Exemplarily, if the push period is 1 day and the second preset time period is 6 hours, and the pushed copy corresponding to the copy preference classification is the protagonist copy, within each day, the electronic device can determine the number of message pushes of the protagonist copy within 6 hours before the current time, so as to determine the copy to be pushed based on the magnitude of the number of message pushes of the protagonist copy within 6 hours before the current time.

[0110] S1302. When the number of message pushes is less than the preset number threshold, use the preset copy corresponding to the copy preference classification as the copy to be pushed.

[0111] In the embodiment of the present disclosure, after the electronic device determines the number of message pushes, it can compare the number of message pushes with the preset number threshold. If the number of message pushes is less than the preset number threshold, use the preset copy corresponding to the copy preference classification as the copy to be pushed; otherwise, use other methods to determine the copy to be pushed.

[0112] In the embodiment of the present disclosure, the preset push number threshold may be the maximum number of pushes for generating push copies of the same classification within the second preset time period.

[0113] Optionally, the preset number threshold may be 3 times, 4 times, etc., which is not limited herein.

[0114] Exemplarily, if the push period is 1 day and the second preset time period is 6 hours, and the pushed copy corresponding to the copy preference classification is the protagonist copy, within each day, the electronic device can determine that the number of message pushes of the protagonist copy within 6 hours before the current time is 2 times. If the preset push number threshold is 3 times, then the number of message pushes is less than the preset number threshold, and the preset copy corresponding to the copy preference classification can be used as the copy to be pushed, that is, use the copy preference classification corresponding to the protagonist copy as the copy to be pushed.

[0115] Thus, in the embodiment of the present disclosure, if the number of message pushes of the target user within the second time period is small, the preset copy corresponding to the copy preference classification can be directly used as the copy to be pushed.

[0116] In another implementation manner of the present disclosure, S130 may specifically include the following steps.

[0117] S1303. Obtain the number of message pushes for the target user within the second preset time period.

[0118] Among them, the specific implementation manner of S1303 is similar to that of S1301, and will not be elaborated herein.

[0119] S1304. When the number of message pushes is greater than or equal to the preset number threshold, use any preset copy other than the copy preference classification as the copy to be pushed.

[0120] In an embodiment of the present disclosure, after the electronic device determines the number of message pushes, the number of message pushes can be compared with a preset number threshold. If the number of message pushes is greater than or equal to the preset number threshold, any preset copywriting other than the copywriting preference classification can be used as the copywriting to be pushed.

[0121] Exemplarily, if the push period is 1 day, the second preset time period is 6 hours, the pushed copywriting corresponding to the copywriting preference classification is the protagonist copywriting, and the classifications other than the copywriting preference classification include the author classification, the book title classification, and the book hot comment classification. Within each day, the electronic device can determine that the number of message pushes of the protagonist copywriting within 6 hours before the current time is 3 times. If the preset push number threshold is 3 times, then the number of message pushes is equal to the preset number threshold, and any preset copywriting corresponding to one of the author classification, the book title classification, and the book hot comment classification can be used as the copywriting to be pushed.

[0122] Thus, in an embodiment of the present disclosure, if the number of message pushes of the target user within the second time period is large, any preset copywriting other than the copywriting preference classification can be used as the copywriting to be pushed, so that any preset copywriting other than the copywriting preference classification is used as the detection copywriting and pushed to the target user, avoiding repeated pushing of the same copywriting, and attracting the target user to read the book to be pushed through different copywriting categories.

[0123] In summary, in an embodiment of the present disclosure, the number of message pushes of the target user within the second time period can be compared with a preset number threshold, and according to different comparison results, different methods can be used to determine the copywriting to be pushed, which can adapt to different scenarios of generating the copywriting to be pushed.

[0124] In another implementation manner of the present disclosure, for each data dimension, candidate data corresponding to the data dimension can be screened out, and the book to be pushed can be selected from the candidate books according to the push priority corresponding to each data dimension.

[0125] In an embodiment of the present disclosure, optionally, S120 may specifically include the following steps.

[0126] S1201. For each data dimension, according to the reading-related data of the data dimension, candidate books corresponding to the data dimension are screened out from multiple preset books.

[0127] In an embodiment of the present disclosure, for each data dimension, the electronic device can screen out candidate books corresponding to the data dimension from multiple preset books according to the reading-related data corresponding to the data dimension and using the book screening strategy corresponding to the data dimension.

[0128] In some embodiments of the present disclosure, the data dimension is the dimension that the target user has not completed reading, and the reading-related data includes the reading intensity data corresponding to at least one first book, where the first book is a book that the target user has not completed reading.

[0129] Correspondingly, S1201 may specifically include the following steps.

[0130] S12011. Calculate the reading intensity score for each first book based on the reading intensity data.

[0131] Among them, the reading intensity data may be the read-related data of the target user for the first book.

[0132] Optionally, the reading intensity data may include the interaction freshness, interaction depth, and reading progress of the target user for the first book. Optionally, the interaction depth may include data such as reading duration, number of likes, and number of comments, which are not limited herein.

[0133] In some embodiments, the electronic device may calculate the reading intensity score for each first book based on the interaction freshness in the reading intensity data.

[0134] In some other embodiments, the electronic device may calculate the reading intensity score for each first book based on the interaction depth in the reading intensity data.

[0135] In still some other embodiments, the electronic device may calculate the reading intensity score for each first book based on the reading progress in the reading intensity data.

[0136] In still some other embodiments, the electronic device may perform a weighted sum of the interaction freshness, interaction depth, and reading progress in the reading intensity data to obtain the reading intensity score for each first book.

[0137] Thus, in the embodiments of the present disclosure, the reading intensity score for each first book may be calculated according to different data in the reading intensity data.

[0138] S12012. Use the first books with a reading intensity score greater than or equal to the score threshold as candidate books.

[0139] In the embodiments of the present disclosure, after the electronic device calculates the reading intensity score, the reading intensity score may be compared with the score threshold, and the first books with a reading intensity score greater than or equal to the score threshold are used as candidate books.

[0140] In the embodiments of the present disclosure, the score threshold may be a score determined in advance as needed for determining candidate books.

[0141] Thus, in the embodiments of the present disclosure, a reading intensity score can be calculated based on the reading intensity data, and candidate books can be determined according to the reading intensity score and the score threshold.

[0142] In some other embodiments of the present disclosure, the data dimension is the dimension with which the target user has interacted, and the reading-related data includes book interaction data corresponding to at least one second book, and the second book is a book with which the target user has interacted. Optionally, the interacted books may include books that have been read, books that have not been read, books that have been commented on, books that have been liked, books that have been added to the bookshelf, books that have been purchased, etc.

[0143] Correspondingly, S1201 may specifically include the following steps.

[0144] S12013. Calculate the reading preference scores of the target user for each preset book type based on the book interaction data.

[0145] In the embodiments of the present disclosure, the book interaction data may be the interaction record of the target user for the second book.

[0146] Optionally, the book interaction data may include at least one of data such as the reading progress of the target user for the second book, the number of comments, the number of likes, the purchase status data, the add-to-cart status data, the collection status data, etc.

[0147] In the embodiments of the present disclosure, the preset book type may be a pre-set book classification.

[0148] Optionally, the preset book types may include urban type, fantasy type, romance type, reasoning type, etc., and are not limited herein.

[0149] In the embodiments of the present disclosure, the reading preference score can be used to represent the preference degree of the target user for each preset book type. Specifically, the higher the reading preference score of the preset book type, the higher the preference degree of the target user for the preset book type, otherwise, the lower the preference degree of the user for the preset book type.

[0150] In some embodiments, the reading preference scores of the target user for each preset book type can be calculated according to any one of the data interaction data.

[0151] In some other embodiments, at least two data interaction data can be weighted and summed to obtain the reading preference scores of the target user for each preset book type.

[0152] S12014. Use the book corresponding to the preset book type with the highest reading preference score as the candidate book.

[0153] In an embodiment of the present disclosure, after the electronic device calculates the reading preference scores for each preset book type, it may select the book type with the highest reading preference score from the preset data types, and use the book corresponding to the preset book type with the highest reading preference score as the candidate book.

[0154] Thus, in an embodiment of the present disclosure, based on the book interaction data, the reading preference scores of the target user for each preset book type can be calculated, and the book corresponding to the preset book type with the highest reading preference score can be used as the candidate book.

[0155] In some other embodiments of the present disclosure, the data dimension is the dimension of popular books, and the reading-related data includes the book information of at least one popular book; specifically, the book information of the popular book may include the book name of the popular book, the channel to which the book belongs, and the type to which the book belongs. Specifically, the book with the largest cumulative reading volume and / or the book with the largest cumulative consumption volume can be used as the popular book.

[0156] In some embodiments, all popular books can be used as candidate books based on the book names of the popular books.

[0157] In some other embodiments, S1201 may specifically include the following steps.

[0158] S12015. According to the book information, select the books that meet the popular book screening conditions from the popular books as candidate books.

[0159] In an embodiment of the present disclosure, the popular book screening conditions may be pre-determined screening conditions for screening candidate books from popular books.

[0160] Optionally, the popular book screening conditions may include at least one of the channel of the popular book being a preset channel and the type of the popular book being a preset type. Optionally, the preset channels may include a male channel and a female channel. Optionally, the types of popular books may include at least one of types such as urban type, fantasy type, romance type, and reasoning type, which are not limited herein.

[0161] In some embodiments, the popular book screening condition is that the channel of the popular book is a preset channel. The electronic device can obtain the channel to which the popular book belongs and determine the channel preferred by the target user. If the channel of the popular book is the same as the channel preferred by the target user, the popular book is used as the book to be pushed.

[0162] In some other embodiments, the popular book screening condition is that the type of the popular book is a preset type. The electronic device can obtain the type of the popular book and determine the book type preferred by the target user. If the type of the popular book is the same as the book type preferred by the target user, the popular book is used as the book to be pushed.

[0163] Thus, in the embodiments of the present disclosure, candidate books can be selected from best-selling books in different ways based on the book information of best-selling books.

[0164] S1202. Select the books to be pushed from the candidate books corresponding to multiple data dimensions according to the push priorities of each data dimension.

[0165] In the embodiments of the present disclosure, the push priority can be the book push level corresponding to each data dimension.

[0166] Optionally, the push priority can be: the dimension that the target user has not finished reading > the dimension that the target user has interacted with > the dimension of best-selling books.

[0167] In some embodiments of the present disclosure, S1202 may specifically include the following steps.

[0168] S12021. Within each time period, calculate the first quantity of the books to be pushed according to the predetermined information push frequency;

[0169] S12022. Select the first quantity of the books to be pushed from the candidate books in the order of decreasing push priority.

[0170] In the embodiments of the present disclosure, within each time period, the electronic device can determine the number of book recommendations according to the information push frequency, that is, calculate the first quantity of the books to be pushed, obtain the quantity of the candidate books corresponding to the data dimension with the highest recommendation priority. If the quantity of the candidate books with the highest recommendation priority is equal to the first quantity, then use the candidate books corresponding to the data dimension with the highest recommendation priority as the books to be pushed. Otherwise, continue to obtain the quantity of the candidate books corresponding to the data dimension with the second highest recommendation priority. If the sum of the quantity of the candidate books with the highest recommendation priority and the quantity of the candidate books with the second highest recommendation priority is equal to the first quantity, then use the candidate books with the highest recommendation priority and the candidate books with the second highest recommendation priority as the books to be pushed. Otherwise, continue to obtain the quantity of the candidate books corresponding to the data dimension with the lowest recommendation priority until the first quantity of the books to be pushed is selected from the candidate books.

[0171] In the embodiments of the present disclosure, the information push frequency can be determined according to the activity of the target user's book reading.

[0172] Thus, in the embodiments of the present disclosure, the books to be pushed can be pushed in sequence within each time period.

[0173] In other embodiments of the present disclosure, S1202 may specifically include the following steps.

[0174] S12023. For each data dimension, determine the push order of the candidate books corresponding to each data dimension;

[0175] S12024. Starting from the data dimension with the highest push priority, select the books to be pushed from the candidate books according to the push order of the candidate books corresponding to each data dimension.

[0176] In the embodiments of the present disclosure, for each data dimension, the electronic device can determine the push order of the candidate books corresponding to each data dimension, and starting from the data dimension with the highest push priority, select the books to be pushed from the candidate books according to the push order of the candidate books corresponding to each data dimension. That is to say, according to the push priority, first select the books to be pushed from the candidate books corresponding to the data dimension with the highest push priority, then select the books to be pushed from the candidate books corresponding to the data dimension with the second highest priority, and finally select the books to be pushed from the candidate books corresponding to the data dimension with the lowest priority.

[0177] In some other embodiments of the present disclosure, S1202 may specifically include the following steps.

[0178] S12025. For each data dimension corresponding to the push priority, select the first book to be pushed from the candidate books corresponding to each data dimension;

[0179] S12024. For each data dimension corresponding to the push priority, select the second book to be pushed from the candidate books corresponding to each data dimension until all the books to be recommended are obtained.

[0180] In the embodiments of the present disclosure, for each data dimension, the electronic device can select the first book to be pushed from the candidate books corresponding to each data dimension corresponding to the push priority, and select the second book to be pushed from the candidate books corresponding to each data dimension corresponding to the push priority until all the books to be recommended are obtained. That is to say, the first book to be pushed for each data dimension can be obtained first, then the second book to be pushed for each data dimension can be obtained, and then the third book to be pushed for each data dimension can be obtained until all the books to be recommended are obtained.

[0181] Thus, in the embodiments of the present disclosure, different methods can be used to select the books to be pushed from the candidate books, which can adapt to different scenarios for determining the books to be pushed.

[0182] In summary, different methods can be used to screen out the candidate books corresponding to the data dimension from multiple preset books, and different methods can be used to select the books to be pushed from the candidate books, which improves the flexibility of determining the books to be pushed.

[0183] In another implementation manner of the present disclosure, after generating the target push message corresponding to the target user, the target push message may be pushed to the target device corresponding to the target user.

[0184] Figure 2 The flowchart shows another information push method provided by the embodiments of the present disclosure.

[0185] As Figure 2 shown, the information push method may include the following steps.

[0186] S210. Obtain the reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user.

[0187] In the embodiments of the present disclosure, optionally, S210 may specifically include the following steps.

[0188] S2101. Obtain the reading-related data and the copywriting preference classification at the active time of the target user determined in advance.

[0189] Among them, the active time of the target user may be the book browsing time of the target user.

[0190] In some embodiments, S2101 may specifically include the following steps.

[0191] S21011. Obtain the activity of the target user.

[0192] Among them, the activity may be the active degree of the user reading e-books on the e-book platform.

[0193] In some embodiments, the activity of the target user may be determined according to the number of times the target user logs in to the e-book platform.

[0194] In other embodiments, the activity of the target user may be determined according to the reading duration of the target user on the e-book platform.

[0195] In still other embodiments, the number of times the target user logs in to the e-book platform and the reading duration on the e-book platform may be weighted and summed to obtain the activity of the target user.

[0196] S21012. Based on the activity, determine the message push frequency for the target user.

[0197] Specifically, the message push frequency for the target user may be determined according to the corresponding relationship between the activity and the message push frequency.

[0198] Optionally, the higher the activity, the higher the message push frequency for the target user can be determined; otherwise, the lower the message push frequency for the target user can be determined.

[0199] S21013. Determine at least one active time of the target user within a third preset time period based on the message push frequency.

[0200] Specifically, the electronic device can determine at least one active time of the target user within the third preset time period according to the message push frequency and the third preset time period.

[0201] In the embodiments of the present disclosure, the third preset time period may be a time period determined in advance for the user to obtain reading-related data and copywriting preference classification.

[0202] Optionally, the third preset time period may be a time period such as 1 day, 3 days, 1 week, etc., which is not limited herein.

[0203] In some other embodiments, S2101 may specifically include the following steps.

[0204] S21014. Obtain the reading time data of the target user.

[0205] Specifically, the electronic device can detect the reading status of the target user on the electronic platform in real time and determine the reading time data of the target user.

[0206] Among them, the reading time data may be the time for the target user to browse e-books.

[0207] S21015. Determine the preferred reading time of the target user according to the reading time data.

[0208] Specifically, the electronic device can count the reading time data and determine the preferred reading time of the target user according to the statistical results.

[0209] Among them, the preferred reading time may be the habitual browsing time of the target user.

[0210] S21016. Determine the active time according to the preferred reading time.

[0211] Specifically, the electronic device can use the preset time before the preferred reading time as the active time.

[0212] Optionally, the preset time before the preferred reading time may be 5 minutes, 10 minutes, etc. before the preferred reading time, which is not limited herein.

[0213] In still some other embodiments, S2101 may specifically include the following steps.

[0214] S21017. When the target user has granted the permission to obtain the geographical location, obtain the reading geographical location data of the target user.

[0215] Specifically, when the target user has granted the permission to obtain the geographical location, the electronic device can detect the geographical location data of the target user reading the e-book in real time.

[0216] Among them, the geographical location data can be the location information of the target user.

[0217] S21018. Determine the preferred reading geographical location of the target user according to the reading geographical location data.

[0218] Specifically, the electronic device can statistically analyze the reading geographical location data, and determine the preferred reading geographical location of the target user according to the statistical results.

[0219] Among them, the preferred reading geographical location can be the geographical location where the target user is used to browsing e-books.

[0220] S21019. Detect the real-time geographical location of the target user.

[0221] Specifically, the electronic device can detect the geographical location where the target user is located in real time as the real-time geographical location.

[0222] S21020. Use the time when the detected real-time geographical location is the preferred reading geographical location as the active time.

[0223] Specifically, the electronic device can determine in real time whether the real-time geographical location is consistent with the preferred reading geographical location. If they are consistent, the time when the real-time geographical location is consistent with the preferred reading geographical location is used as the active time.

[0224] Thus, in the embodiments of the present disclosure, different methods can be used to determine the active time, improving the flexibility of the active time.

[0225] S220. Based on the reading-related data of at least one data dimension, screen out the books to be pushed from multiple preset books.

[0226] S230. Based on the copywriting preference classification, screen out the copywriting to be pushed from multiple preset copywritings corresponding to the books to be pushed.

[0227] S240. Generate a target push message corresponding to the target user according to the copywriting to be pushed.

[0228] Among them, S220~S240 are similar to S120~S140 and will not be elaborated here.

[0229] S250. At the active time of the target user determined in advance, push the target push message to the target device corresponding to the target user.

[0230] In an embodiment of the present disclosure, the electronic device can detect the active time of the target user in real time. If the active time of the target user is detected, the target push message is pushed to the target device corresponding to the target user.

[0231] Among them, the active time can be determined according to any one of the methods in S210.

[0232] Thus, in an embodiment of the present disclosure, the target push message can be pushed to the target device corresponding to the target user at the active time of the target user, which can well adapt to the reading habits of the target user, so that the target user can view the target push message during the active time. If the target user clicks on the target push message, the e-book platform can be launched to open the e-book, which is beneficial to increasing the access volume and popularity of the e-book platform.

[0233] Figure 3 FIG. shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

[0234] The electronic device provided by an embodiment of the present disclosure may include an electronic device supporting the e-book reading function. The electronic device may include, but is not limited to, mobile terminals such as smart phones, laptop computers, personal digital assistants (PDAs), tablet computers (PADs), portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), wearable devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, servers, etc.

[0235] It should be noted that Figure 3 The illustrated electronic device 300 is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0236] The electronic device 300 traditionally includes a processor 310 and a computer program product or computer-readable medium in the form of a memory 320. The memory 320 may be an electronic memory such as a flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk, or ROM. The memory 320 has a storage space 321 for executable instructions (or program codes) 3211 for performing any method steps in the above information push method. For example, the storage space 321 for executable instructions may include respective executable instructions 3211 for implementing various steps in the above information push method. These executable instructions can be read out from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, compact discs (CDs), memory cards, or floppy disks. Such computer program products are generally portable or fixed storage units. The storage unit may have Figure 3A storage segment, storage space, etc. with a similar layout in the memory 320 of the electronic device 300. The executable instructions can be compressed in an appropriate form, for example. Generally, the storage unit includes executable instructions for performing the steps of the information push method according to the present disclosure, that is, code that can be read by a processor such as the processor 310. When these codes are run by the electronic device 300, the electronic device 300 is caused to execute each step in the information push method described above.

[0237] Of course, for simplicity, Figure 3 only some of the components related to the present disclosure in the electronic device 300 are shown, and components such as buses, input / output interfaces, input devices, and output devices are omitted. In addition, according to specific application scenarios, the electronic device 300 may further include any other appropriate components.

[0238] Embodiments of the present disclosure also provide a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are run by a processor, the processor is caused to execute the information push methods provided by the various embodiments of the present disclosure.

[0239] The computer-readable storage medium may be any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0240] The above computer-readable medium may be included in the above electronic device; or it may exist separately and not be assembled into the electronic device.

[0241] In the embodiments of the present disclosure, program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by connecting through an Internet service provider via the Internet).

[0242] This application discloses:

[0243] A1. An information push method, which includes:

[0244] Obtain the reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user;

[0245] Based on the reading-related data of at least one data dimension, screen out the books to be pushed from multiple preset books;

[0246] Based on the copywriting preference classification, screen out the copywriting to be pushed from multiple preset copywritings corresponding to the books to be pushed;

[0247] Generate a target push message corresponding to the target user according to the copywriting to be pushed.

[0248] A2. The method according to claim A1, wherein when the processor executes to obtain the copywriting preference classification of the target user, the executable instructions specifically cause the processor to execute:

[0249] Obtain the message interaction data of the target user for the historical push messages;

[0250] Input the message interaction data into a pre-trained copywriting preference detection model to obtain the predicted values corresponding to each preset copywriting classification output by the copywriting preference detection model;

[0251] According to the predicted values, select the copywriting preference classification from multiple preset copywriting classifications.

[0252] A3. The method according to claim A2, wherein when the processor executes to select the copywriting preference classification from multiple preset copywriting classifications according to the predicted values, the executable instructions specifically cause the processor to execute:

[0253] Classify the preset copywriting that has not been pushed within the first preset time period as the candidate copywriting classification;

[0254] Classify the candidate copywriting classification with the largest predicted value as the copywriting preference classification.

[0255] A4. The method according to claim A1, wherein when the processor executes screening the copywriting to be pushed from multiple preset copywritings corresponding to the book to be pushed based on the copywriting preference classification, the executable instruction specifically causes the processor to execute:

[0256] Obtain the number of message pushes for the target user within the second preset time period;

[0257] When the number of message pushes is less than the preset number threshold, use the preset copywriting corresponding to the copywriting preference classification as the copywriting to be pushed.

[0258] A5. The method according to claim A4, wherein after the processor executes obtaining the number of message pushes for the target user within the second preset time period, the executable instruction specifically causes the processor to execute:

[0259] When the number of message pushes is greater than or equal to the preset number threshold, use any preset copywriting other than the copywriting preference classification as the copywriting to be pushed.

[0260] A6. The method according to claim A1, wherein when the processor executes screening the book to be pushed from multiple preset books based on the reading-related data of at least one data dimension, the executable instruction specifically causes the processor to execute:

[0261] For each data dimension, screen out the candidate books corresponding to the data dimension from multiple preset books according to the reading-related data of the data dimension;

[0262] Select the book to be pushed from the candidate books corresponding to multiple data dimensions according to the push priorities of each data dimension.

[0263] A7. The method according to claim A6, wherein the reading-related data includes the reading intensity data of at least one first book, and the first book is a book that the target user has not finished reading;

[0264] Wherein, when the processor executes screening out the candidate books corresponding to the data dimension from multiple preset books according to the reading-related data of the data dimension, the executable instruction specifically causes the processor to execute:

[0265] Based on the reading intensity data, calculate the reading intensity score of each first book;

[0266] Use the first books with a reading intensity score greater than or equal to the score threshold as candidate books.

[0267] A8. The method according to claim A6, wherein reading the relevant data includes book interaction data corresponding to at least one second book, and the second book is a book that the target user has interacted with;

[0268] Wherein, when the processor executes reading the relevant data according to the data dimension and screening out candidate books corresponding to the data dimension among multiple preset books, the executable instruction specifically causes the processor to execute:

[0269] Based on the book interaction data, calculate the reading preference scores of the target user for each preset book type;

[0270] Take the book corresponding to the preset book type with the highest reading preference score as the candidate book.

[0271] A9. The method according to claim A6, wherein reading the relevant data includes book information of at least one best-selling book;

[0272] Wherein, when the processor executes reading the relevant data according to the data dimension and screening out candidate books corresponding to the data dimension among multiple preset books, the executable instruction specifically causes the processor to execute:

[0273] According to the book information, select books that meet the best-selling book screening conditions among the best-selling books as candidate books.

[0274] A10. The method according to claim A1, wherein, after the processor executes generating a target push message corresponding to the target user according to the to-be-pushed copywriting, the executable instruction specifically causes the processor to execute:

[0275] Push the target push message to the target device corresponding to the target user at the pre-determined active time of the target user.

[0276] A11. The method according to claim A1, wherein, when the processor executes obtaining reading relevant data of at least one data dimension of the target user and the copywriting preference classification of the target user, the executable instruction specifically causes the processor to execute:

[0277] Obtain the reading relevant data and the copywriting preference classification at the pre-determined active time of the target user.

[0278] A12. The method according to claim A10 or A11, wherein the executable instruction specifically causes the processor to execute:

[0279] Obtain the activity level of the target user;

[0280] Based on the activity level, determine the message push frequency for the target user;

[0281] Based on the message push frequency, determine at least one active time of the target user within a third preset time period.

[0282] A13. The method according to claim A10 or A11, wherein the executable instructions specifically cause the processor to perform:

[0283] Obtain the reading time data of the target user;

[0284] Determine the preferred reading time of the target user according to the reading time data;

[0285] Determine the active time according to the preferred reading time.

[0286] A14. The method according to claim A10 or A11, wherein the executable instructions specifically cause the processor to perform:

[0287] When the target user has granted the permission to obtain the geographical location, obtain the reading geographical location data of the target user;

[0288] Determine the preferred reading geographical location of the target user according to the reading geographical location data;

[0289] Detect the real-time geographical location of the target user;

[0290] Take the time when the detected real-time geographical location is the preferred reading geographical location as the active time.

[0291] B15. An electronic device, comprising a processor and a memory, wherein the memory is used to store executable instructions, and the executable instructions cause the processor to perform the following operations:

[0292] Obtain the reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user;

[0293] Based on the reading-related data of at least one data dimension, screen out the books to be pushed from multiple preset books;

[0294] Based on the copywriting preference classification, screen out the copywriting to be pushed from multiple preset copywritings corresponding to the books to be pushed;

[0295] Generate a target push message corresponding to the target user according to the copywriting to be pushed.

[0296] B16. The electronic device according to claim B15, wherein when obtaining the copywriting preference classification of the target user, the executable instructions further cause the processor to perform:

[0297] Obtain the message interaction data of the target user for the historical push messages;

[0298] Input the message interaction data into a pre-trained copywriting preference detection model to obtain the predicted values corresponding to each preset copywriting classification output by the copywriting preference detection model;

[0299] Select a copywriting preference classification from multiple preset copywriting classifications according to the predicted value.

[0300] B17. The electronic device according to claim B16, wherein when selecting a copywriting preference classification from multiple preset copywriting classifications according to the predicted value, the executable instruction further causes the processor to execute:

[0301] Use the preset copywriting classifications that have not been pushed within the first preset time period as candidate copywriting classifications;

[0302] Use the candidate copywriting classification with the largest predicted value as the copywriting preference classification.

[0303] B18. The electronic device according to claim B15, wherein when screening out the copywriting to be pushed from multiple preset copywritings corresponding to the book to be pushed based on the copywriting preference classification, the executable instruction further causes the processor to execute:

[0304] Obtain the number of message pushes for the target user within the second preset time period;

[0305] In the case where the number of message pushes is less than the preset number threshold, use the preset copywriting corresponding to the copywriting preference classification as the copywriting to be pushed.

[0306] B19. The electronic device according to claim B18, wherein after obtaining the number of message pushes for the target user within the second preset time period, the executable instruction further causes the processor to execute:

[0307] In the case where the number of message pushes is greater than or equal to the preset number threshold, use any preset copywriting other than the copywriting preference classification as the copywriting to be pushed.

[0308] B20. The electronic device according to claim B15, wherein when screening out the book to be pushed from multiple preset books based on the reading-related data of at least one data dimension, the executable instruction further causes the processor to execute:

[0309] For each data dimension, screen out the candidate books corresponding to the data dimension from multiple preset books according to the reading-related data of the data dimension;

[0310] Select the book to be pushed from the candidate books corresponding to multiple data dimensions according to the push priorities of each data dimension.

[0311] B21. The electronic device according to claim B20, wherein the reading-related data includes the reading intensity data of at least one first book, and the first book is a book that the target user has not finished reading;

[0312] Among them, when screening candidate books corresponding to the data dimension from multiple preset books according to the reading-related data of the data dimension, the executable instruction further causes the processor to execute:

[0313] Based on the reading intensity data, calculate the reading intensity score for each first book;

[0314] Use the first books with a reading intensity score greater than or equal to the score threshold as candidate books.

[0315] B22. The electronic device according to claim B20, wherein the reading-related data includes book interaction data corresponding to at least one second book, and the second book is an interacted book of the target user;

[0316] Among them, when screening candidate books corresponding to the data dimension from multiple preset books according to the reading-related data of the data dimension, the executable instruction further causes the processor to execute:

[0317] Based on the book interaction data, calculate the reading preference score of the target user for each preset book type;

[0318] Use the books corresponding to the preset book type with the highest reading preference score as candidate books.

[0319] B23. The electronic device according to claim B20, wherein the reading-related data includes book information of at least one best-selling book;

[0320] Among them, when screening candidate books corresponding to the data dimension from multiple preset books according to the reading-related data of the data dimension, the executable instruction further causes the processor to execute:

[0321] According to the book information, select books that meet the best-selling book screening conditions from the best-selling books as candidate books.

[0322] B24. The electronic device according to claim B15, wherein after the processor executes to generate a target push message corresponding to the target user according to the pending push copywriting, the executable instruction further causes the processor to execute:

[0323] At the active time of the target user determined in advance, push the target push message to the target device corresponding to the target user.

[0324] B25. The electronic device according to claim B15, wherein when the processor executes to obtain the reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user, the executable instruction further causes the processor to execute:

[0325] At the active time of the target user determined in advance, obtain the reading-related data and the copywriting preference classification.

[0326] The electronic device according to claim B24 or B25, wherein the executable instructions further cause the processor to execute:

[0327] Obtain the activity level of the target user;

[0328] Based on the activity level, determine the message push frequency for the target user;

[0329] Based on the message push frequency, determine at least one active time of the target user within a third preset time period.

[0330] The electronic device according to claim B24 or B25, wherein the executable instructions further cause the processor to execute:

[0331] Obtain the reading time data of the target user;

[0332] Based on the reading time data, determine the preferred reading time of the target user;

[0333] Based on the preferred reading time, determine the active time.

[0334] The electronic device according to claim B24 or B25, wherein the executable instructions further cause the processor to execute:

[0335] When the target user has granted the permission to obtain the geographical location, obtain the reading geographical location data of the target user;

[0336] Based on the reading geographical location data, determine the preferred reading geographical location of the target user;

[0337] Detect the real-time geographical location of the target user;

[0338] Take the time when the detected real-time geographical location is the preferred reading geographical location as the active time.

[0339] A computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the information push method according to any one of the above claims A1 - A14.

[0340] Each component embodiment of the present disclosure may be implemented in whole or in part by hardware, or by software modules running on one or more processors, or by a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the electronic device according to the embodiments of the present disclosure. The present disclosure can also be implemented as a device or apparatus program (such as a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present disclosure can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0341] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0342] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although a number of specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments can also be implemented combinatorially in a single embodiment. Conversely, the various features described in the context of a single embodiment can also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0343] Although the subject matter has been described in language specific to structural features and / or methodological act logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms for implementing the claims.

Claims

1. An information push method, characterized in that, The method includes: Obtaining reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user, where the data dimension includes at least one of the dimension of uncompleted reading by the target user, the dimension of interacted by the target user, and the dimension of best-selling books; Based on the reading-related data of the at least one data dimension, screening out books to be pushed among multiple preset books; Based on the copywriting preference classification, screening out copywriting to be pushed among multiple preset copywritings corresponding to the books to be pushed; Generating a target push message corresponding to the target user according to the copywriting to be pushed, where the target push message is generated based on the editing rules of the push message, and the editing rules of the push message include the text limit rule and the text layout rule of the push information.

2. The method according to claim 1, wherein Obtaining the copywriting preference classification of the target user includes: Obtaining the message interaction data of the target user for the historical push messages; Inputting the message interaction data into a pre-trained copywriting preference detection model to obtain the predicted values corresponding to each preset copywriting classification output by the copywriting preference detection model; According to the predicted values, selecting the copywriting preference classification from the multiple preset copywriting classifications.

3. The method according to claim 2, wherein The selecting the copywriting preference classification from the multiple preset copywriting classifications according to the predicted values includes: Regarding the preset copywriting classifications not pushed within the first preset time period as candidate copywriting classifications; Regarding the candidate copywriting classification with the largest predicted value as the copywriting preference classification.

4. The method according to claim 1, wherein The screening out copywriting to be pushed among multiple preset copywritings corresponding to the books to be pushed based on the copywriting preference classification includes: Obtaining the number of message pushes to the target user within the second preset time period; In the case where the number of message pushes is less than the preset number threshold, regarding the preset copywriting corresponding to the copywriting preference classification as the copywriting to be pushed.

5. The method according to claim 4, characterized in that, After obtaining the number of message pushes to the target user within the second preset time period, the method further includes: In the case where the number of message pushes is greater than or equal to the preset number threshold, regarding any preset copywriting other than the copywriting preference classification as the copywriting to be pushed.

6. The method according to claim 1, characterized in that The screening out books to be pushed among multiple preset books based on the reading-related data of the at least one data dimension includes: For each of the data dimensions, according to the reading-related data of the data dimension, screening out candidate books corresponding to the data dimension among the multiple preset books; Selecting the books to be pushed from the candidate books corresponding to the multiple data dimensions according to the push priorities of the respective data dimensions.

7. The method according to claim 6, characterized in that, The reading-related data includes reading intensity data corresponding to at least one first book, and the first book is a book not completed by the target user; Among them, the screening out candidate books corresponding to the data dimension among the multiple preset books according to the reading-related data of the data dimension includes: Based on the reading intensity data, calculating the reading intensity score of each first book; Regarding the first books with the reading intensity score greater than or equal to the score threshold as the candidate books.

8. The method according to claim 6, wherein The reading-related data includes book interaction data corresponding to at least one second book, where the second book is a book that the target user has interacted with; Among them, screening out candidate books corresponding to the data dimension from multiple preset books according to the reading-related data of the data dimension includes: Based on the book interaction data, calculating the reading preference scores of the target user for each preset book type; Taking the book corresponding to the preset book type with the highest reading preference score as the candidate book.

9. The method according to claim 6, characterized in that The reading-related data includes book information of at least one best-selling book; Among them, screening out candidate books corresponding to the data dimension from the multiple preset books according to the reading-related data of the data dimension includes: According to the book information, selecting books that meet the best-selling book screening conditions from the best-selling books as the candidate books.

10. The method according to claim 1, wherein After generating the target push message corresponding to the target user according to the to-be-pushed copywriting, the method further includes: Pushing the target push message to the target device corresponding to the target user at the active time of the target user determined in advance.

11. The method according to claim 1, characterized in that, Obtaining the reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user includes: Obtaining the reading-related data and the copywriting preference classification at the active time of the target user determined in advance.

12. The method according to claim 10 or 11, characterized in that, The method further includes: Obtaining the activity level of the target user; Based on the activity level, determining the message push frequency for the target user; Based on the message push frequency, determining at least one active time of the target user within a third preset time period.

13. The method according to claim 10 or 11, characterized in that, The method further includes: Obtaining the reading time data of the target user; According to the reading time data, determining the preferred reading time of the target user; According to the preferred reading time, determining the active time.

14. The method according to claim 10 or 11, characterized in that The method further includes: When the target user has granted the permission to obtain the geographical location, obtaining the reading geographical location data of the target user; According to the reading geographical location data, determining the preferred reading geographical location of the target user; Detecting the real-time geographical location of the target user; Taking the time when the detected real-time geographical location is the preferred reading geographical location as the active time.

15. An electronic device, characterized in that, Including a processor and a memory, the memory is used to store executable instructions, and the executable instructions cause the processor to perform the following operations: Obtaining the reading-related data of at least one data dimension of the target user and the copywriting preference classification of the target user, where the data dimension includes at least one of the dimension of uncompleted reading of the target user, the dimension of interacted books of the target user, and the dimension of best-selling books; Based on the reading-related data of the at least one data dimension, screening out books to be pushed from multiple preset books; Based on the copywriting preference classification, screening out to-be-pushed copywriting from multiple preset copywritings corresponding to the books to be pushed; Generate a target push message corresponding to the target user according to the text to be pushed. The target push message is generated based on the editing rules of the push message, and the editing rules of the push message include the text limit rule and the text layout rule of the push information.

16. The electronic device according to claim 15, characterized in that, When the processor executes to obtain the text preference classification of the target user, the executable instruction specifically causes the processor to execute: Obtain the message interaction data of the target user for the historical push messages; Input the message interaction data into a pre-trained text preference detection model to obtain the predicted values corresponding to each preset text classification output by the text preference detection model; According to the predicted values, select the text preference classification from the multiple preset text classifications.

17. The electronic device according to claim 16, wherein When the processor executes to select the text preference classification from the multiple preset text classifications according to the predicted values, the executable instruction specifically causes the processor to execute: Regard the preset text classifications that have not been pushed within the first preset time period as candidate text classifications; Regard the candidate text classification with the largest predicted value as the text preference classification.

18. The electronic device according to claim 15, wherein When the processor executes to screen out the text to be pushed from the multiple preset texts corresponding to the book to be pushed based on the text preference classification, the executable instruction specifically causes the processor to execute: Obtain the number of message pushes for the target user within the second preset time period; In the case where the number of message pushes is less than the preset number threshold, regard the preset text corresponding to the text preference classification as the text to be pushed.

19. The electronic device according to claim 18, characterized in that, After the processor executes to obtain the number of message pushes for the target user within the second preset time period, the executable instruction further causes the processor to execute: In the case where the number of message pushes is greater than or equal to the preset number threshold, regard any preset text other than the text preference classification as the text to be pushed.

20. The electronic device according to claim 15, wherein When the processor executes to screen out the book to be pushed from the multiple preset books based on the reading-related data of at least one data dimension, the executable instruction further causes the processor to execute: For each data dimension, screen out the candidate books corresponding to the data dimension from the multiple preset books according to the reading-related data of the data dimension; Select the book to be pushed from the candidate books corresponding to the multiple data dimensions according to the push priorities of the respective data dimensions.

21. The electronic device according to claim 20, wherein, The reading-related data includes the reading intensity data of at least one first book, and the first book is a book that the target user has not finished reading; Among them, when the processor executes to screen out the candidate books corresponding to the data dimension from the multiple preset books according to the reading-related data of the data dimension, the executable instruction further causes the processor to execute: Based on the reading intensity data, calculate the reading intensity score of each first book; Regard the first books with the reading intensity score greater than or equal to the score threshold as the candidate books.

22. The electronic device according to claim 20, wherein The reading-related data includes the book interaction data corresponding to at least one second book, and the second book is a book that the target user has interacted with; Wherein, when the processor executes reading relevant data according to the data dimension and filters candidate books corresponding to the data dimension from multiple preset books, the executable instruction further causes the processor to execute: Based on the book interaction data, calculate the reading preference scores of the target user for each preset book type; Use the book corresponding to the preset book type with the highest reading preference score as the candidate book.

23. The electronic device according to claim 20, wherein The reading relevant data includes book information of at least one best-selling book; Wherein, when the processor executes reading relevant data according to the data dimension and filters candidate books corresponding to the data dimension from the multiple preset books, the executable instruction further causes the processor to execute: According to the book information, select books that meet the best-selling book screening conditions from the best-selling books as the candidate books.

24. The electronic device according to claim 15, wherein After the processor executes generating the target push message corresponding to the target user according to the to-be-pushed copywriting, the executable instruction further causes the processor to execute: At the pre-determined active time of the target user, push the target push message to the target device corresponding to the target user.

25. The electronic device according to claim 15, characterized in that, When the processor executes obtaining reading relevant data of at least one data dimension of the target user and the copywriting preference classification of the target user, the executable instruction further causes the processor to execute: At the pre-determined active time of the target user, obtain the reading relevant data and the copywriting preference classification.

26. The electronic device according to claim 24 or 25, characterized in that, The executable instruction further causes the processor to execute: Obtain the activity of the target user; Based on the activity, determine the message push frequency for the target user; Based on the message push frequency, determine at least one active time of the target user within a third preset time period.

27. The electronic device according to claim 24 or 25, characterized in that, The executable instruction further causes the processor to execute: Obtain the reading time data of the target user; According to the reading time data, determine the preferred reading time of the target user; According to the preferred reading time, determine the active time.

28. The electronic device according to claim 24 or 25, characterized in that, The executable instruction further causes the processor to execute: When the target user has granted the permission to obtain the geographical location, obtain the reading geographical location data of the target user; According to the reading geographical location data, determine the preferred reading geographical location of the target user; Detect the real-time geographical location of the target user; Use the time when the detected real-time geographical location is the preferred reading geographical location as the active time.

29. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which when executed by a processor, causes the processor to implement the information push method described in any one of the above claims 1-14.

Images