CN110909247A - Text information pushing method, electronic equipment and computer storage medium - Google Patents
Text information pushing method, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN110909247A CN110909247A CN201911222007.7A CN201911222007A CN110909247A CN 110909247 A CN110909247 A CN 110909247A CN 201911222007 A CN201911222007 A CN 201911222007A CN 110909247 A CN110909247 A CN 110909247A
- Authority
- CN
- China
- Prior art keywords
- text
- target electronic
- book
- electronic book
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a text information pushing method, electronic equipment and a computer storage medium, wherein the method comprises the following steps: determining a target electronic book corresponding to a reading user; acquiring a book tag vector of the target electronic book and a text tag vector of each text message; determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book; and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users. The method can push the text information according to the reading preference of the user when reading the electronic book, so that the pushed text information is matched with the reading preference of the user, and the pushing accuracy is improved.
Description
Technical Field
The invention relates to the field of computers, in particular to a text information pushing method, electronic equipment and a computer storage medium.
Background
At present, with the enhancement of reading consciousness of users, the types and contents of text information which are interested by the users are increasingly rich. For example, short novels, short contents, highlight sentences, highlight paragraphs, and the like all belong to the text information of interest to the user.
Because the number of text messages available for users to browse in the network is large, how to screen valuable information of users from massive text messages and accurately push the valuable information becomes a technical problem to be solved urgently. In the prior art, the method is generally implemented as follows: and counting the historical browsing number of each text message, so as to screen out popular text messages with higher browsing number, and further push the popular text messages to the user.
However, in the process of implementing the present invention, the inventor finds that the above solution in the prior art has at least the following defects: because the interest preference and the service field of each user are different, the popular text information screened by the method cannot meet the individual requirements of the users, and the pushing accuracy is low.
Disclosure of Invention
In view of the above, the present invention is proposed to provide a pushing method of text information, an electronic device and a computer storage medium that overcome or at least partially solve the above problems.
According to an aspect of the present invention, a method for pushing text information is provided, including:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
According to another aspect of the present invention, there is provided an electronic apparatus including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
According to yet another aspect of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing the processor to:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
In the text information pushing method, the electronic device and the computer storage medium provided by the invention, the target electronic book corresponding to the reading user can be determined, the book tag vector of the target electronic book and the text tag vector of each text information are obtained, and the text preference index of the reading user corresponding to each text information is determined according to the similarity between the text tag vector of each text information and the book tag vector of the target electronic book, so that a preset number of text information is screened according to the text preference index and pushed to the reading user. Therefore, the method can determine the text preference index of the reading user corresponding to each text message according to the book tag vector of the target electronic book and the similarity between the text tag vectors of each text message, and convert the similarity comparison problem between the electronic book and the text message into the comparison problem between the tag vectors, so that the text message to be pushed can be screened according to the similarity between the text message and the target electronic book. The method can push the text information according to the reading preference of the user when reading the electronic book, so that the pushed text information is matched with the reading preference of the user, and the pushing accuracy is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 shows a flowchart of a method for pushing text information according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for pushing text information according to another embodiment of the present invention;
fig. 3 shows a schematic structural diagram of an electronic device according to another embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
Fig. 1 shows a flowchart of a method for pushing text information according to an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
step S110: and determining a target electronic book corresponding to the reading user.
Wherein, the target electronic book corresponding to the reading user is usually the book of interest to the user. The determination manner of the target electronic book may be various. For example, the books that the user has read, the books that have been collected, the books that have been downloaded, etc. may be determined according to the historical reading data of the user, so as to determine the target electronic books corresponding to the reading user in combination with the types of the books that have been read, the books that have been collected, and the books that have been downloaded. In summary, this approach aims to mine books that may be of interest to the user, thereby treating the books that are of interest to the user as target e-books.
In addition, the electronic book which is currently read by the reading user can be determined as the target electronic book, so that the text information associated with the electronic book is pushed to the user in the process of reading the current electronic book by the user, and the purpose of extended reading is further achieved.
In short, the present invention does not limit the specific determination manner of the target electronic book, as long as the target electronic book can be matched with the reading behavior of the user. In addition, the number of the target electronic books may be one or more, and the number of the target electronic books is not limited in the present invention.
Step S120: and acquiring a book tag vector of the target electronic book and a text tag vector of each text message.
The target electronic book corresponds to one book tag vector, the book tag vector is used for reflecting content characteristics of the target electronic book, and the book tag vector corresponding to the target electronic book can be determined in various ways such as a document theme generation model, a word embedding algorithm, or a word correlation algorithm.
In specific implementation, for a target electronic book, book content of the target electronic book is acquired, and the book content is subjected to vectorization expression, so that a corresponding book tag vector is generated. In addition, optionally, in consideration of a longer book content of the target electronic book, in order to improve processing efficiency, a preset chapter may be extracted from the book content of the target electronic book in advance, and a book tag vector may be generated according to the extracted preset chapter. The preset chapter can be determined in various ways. For example, in an alternative manner, considering that the amount of information of the initial part of the general electronic book is large, important contents such as a story background and the like are generally described collectively, and therefore, the preset chapters are the first N chapters of the electronic book; alternatively, considering that the end portion of the electronic book is generally more attractive to the user, the preset chapters may also be the last M chapters of the electronic book, where N, M is a natural number. In addition, in order to enable the preset chapters to reflect more important contents and highlights of the electronic book, in another alternative manner, word frequency information of each entity noun included in the electronic book may be counted through a word frequency statistical manner, and then chapters with more entity nouns including people, places, events and the like are selected as the preset chapters. Or, a chapter with a higher user interaction frequency may be extracted as a preset chapter according to user interaction data corresponding to the target electronic book, where the user interaction data includes: note-like interactive data, comment-like interactive data, idea-like interactive data, and the like.
In addition, one text message corresponds to one text tag vector, the text tag vector is used for reflecting content characteristics of the text message, and the text tag vector can be generated in various ways such as a document theme generation model, a word embedding algorithm, or a word correlation algorithm, similar to the generation way of the book tag vector.
The text information may be various text paragraphs or sentences. For example, the text information may be short text contents included in the target electronic book, or may be various types of short text contents other than the target electronic book, such as a highlight paragraph in a celebrity language book or a partial paragraph in a periodical magazine, and the specific content of the text information is not limited by the present invention.
Step S130: and determining text preference indexes corresponding to the text information by the reading user according to the similarity between the text label vector of the text information and the book label vector of the target electronic book.
Because the text tag vectors and the book tag vectors are generated in a similar manner, the similarity between the text tag vectors of the text information and the book tag vectors of the target electronic book can be determined in a vector calculation manner, and the similarity can reflect the similarity between the text information and the target electronic book. Accordingly, according to the similarity between each text message and the target electronic book, the text preference index corresponding to each text message of the reading user is determined.
When there is one target electronic book, the text preference index is proportional to the similarity between the text information and the target electronic book, that is: the greater the similarity between the text information and the target electronic book, the higher the text preference index of the text information. When a plurality of target electronic books are available, the text preference index is further determined in a weighting manner by combining the weight of each target electronic book, wherein the weight of each target electronic book can be determined according to the preference degree of the user for the target electronic book.
Step S140: and screening a preset number of text messages according to the text preference indexes corresponding to the text messages of the reading user, and pushing the text messages to the reading user.
Specifically, the text messages are sorted from high to low according to the text preference index, so that a plurality of text messages with the top sorting are screened and pushed to the reading user to be displayed by the terminal device corresponding to the reading user.
Therefore, the method can determine the text preference index of the reading user corresponding to each text message according to the book tag vector of the target electronic book and the similarity between the text tag vectors of each text message, and convert the similarity comparison problem between the electronic book and the text message into the comparison problem between the tag vectors, so that the text message to be pushed can be screened according to the similarity between the text message and the target electronic book. The method can push the text information according to the reading preference of the user when reading the electronic book, so that the pushed text information is matched with the reading preference of the user, and the pushing accuracy is improved.
Example two
Fig. 2 shows a flowchart of a method for pushing text information according to another embodiment of the present invention. As shown in fig. 2, the method comprises the steps of:
step S210: and determining a target electronic book corresponding to the reading user according to the historical reading data of the reading user.
Specifically, according to the historical reading data of the reading user, the reading preference of the reading user is mined, so that the electronic book matched with the reading preference is determined as the target electronic book.
Firstly, an interactive book list corresponding to a reading user is determined according to historical reading data corresponding to the reading user. The interactive book list is used for storing books with interactive behaviors with the reading user. Wherein the interaction behavior comprises at least one of: browse, download, read, and collect.
Then, for each electronic book in the interactive book list, screening a plurality of electronic books from the interactive book list as target electronic books according to the interactive duration, interactive sections and/or interactive types of the reading user for the electronic book. The electronic books with longer time length can be selected according to the interaction duration, the electronic books with more reading chapters can be selected according to the interaction chapters, and the electronic books with preset interaction types (such as reading or collecting) can be selected according to the interaction types. In addition, the interaction duration, the interaction sections and the interaction types respectively belong to different interaction dimensions, and accordingly, corresponding interaction weights can be set in advance for the interaction dimensions, and the target electronic book is screened according to the weighting results of the interaction dimensions.
It can be seen that the role of filtering the target e-books is to determine the books that are of interest to the user. In specific implementation, the interactive book list corresponding to each user can be established in advance according to historical reading books of each reading user. Then, for each electronic book in the interactive book list, determining a book preference index of each electronic book according to a weighting result of each interactive dimension, and screening a preset number of target electronic books according to the order from high to low of the book preference index.
Step S220: and acquiring a book tag vector of the target electronic book and a text tag vector of each text message.
The book label vector and the text label vector can be realized in various ways, and the purpose is to vectorize and express books or texts so as to facilitate comparison. The book tag vector and the text tag vector may also be referred to as a non-dominant tag vector or a recessive tag vector, where the contents belong to non-dominant contents.
In an implementation manner of this embodiment, a theme vector corresponding to a target electronic book is generated through a document theme generation model, and the theme vector of the target electronic book is used as a book tag vector of the target electronic book; and generating a theme vector corresponding to each text message through the document theme generation model, and taking the theme vector of each text message as a text label vector of the text message. The document theme generation model is an lda (latent dirichletalllocation) model, and includes three-layer structures of words, themes and documents. Specifically, the LDA model may generate the topic vector by the following process: firstly, extracting a theme from theme distribution for each electronic book; then, extracting a word from the word distribution corresponding to the extracted subject; and finally, repeating the process until each word in the electronic book is traversed. Each document in the corpus corresponds to one multinomial distribution of multiple topics. Each topic, in turn, corresponds to a multinomial distribution of a plurality of words in the vocabulary. By the method, the theme vectors of the electronic books and the text information can be generated.
In another implementation manner of this embodiment, a word embedding vector corresponding to a target electronic book is generated by a word embedding algorithm, and the word embedding vector of the target electronic book is used as a book tag vector of the target electronic book; and generating word embedding vectors corresponding to the text messages by a word embedding algorithm, and taking the word embedding vector of each text message as a text label vector of the text message. In summary, the person skilled in the art can determine the book tag vector and the text tag vector in various ways as long as the vectorized representation of the text content can be realized.
Step S230: and determining the similarity between the text label vector of each text message and the book label vector of the target electronic book.
In this embodiment, the target electronic books are plural, and therefore, the similarity between the text tag vector of each text information and the book tag vector of each target electronic book is determined respectively. Specifically, for each piece of text information, the similarity between the text label vector of the text information and the book label vector of each target electronic book is calculated one by one, so as to obtain a similarity score between the text information and each target electronic book. Or respectively calculating the similarity between the book tag vector of the target electronic book and the text tag vector of each text message one by one aiming at each target electronic book, so as to obtain the similarity score between the target electronic book and each text message.
Step S240: and determining text preference indexes corresponding to the text information by the reading user according to the similarity between the text label vector of the text information and the book label vector of the target electronic book.
Since there are a plurality of target electronic books in this embodiment, it is necessary to further determine in combination with the book preference index of each target electronic book. Specifically, book preference indexes of the reading user corresponding to the target electronic books are respectively determined, and text preference indexes of the reading user corresponding to the text information are determined by combining the book preference indexes of the reading user corresponding to the target electronic books. Wherein, the book preference index of the reading user corresponding to each target electronic book can be determined by the following modes: and respectively determining the interaction duration, the interaction section and/or the interaction type of the reading user for each target electronic book, and determining the book preference index of the target electronic book according to the interaction duration, the interaction section and/or the interaction type. Specifically, the interaction duration, the interaction sections and the interaction types respectively correspond to different interaction dimensions, corresponding interaction weights can be set for the interaction dimensions respectively, and accordingly, book preference indexes of the target electronic book are determined according to weighting results of the interaction dimensions.
In specific implementation, the text preference index corresponding to each text message of the reading user is determined by the following method:
firstly, determining similar text information sets corresponding to target electronic books; each similar text information set is used for storing a plurality of text information with the similarity between the text information set and the corresponding target electronic book larger than a preset threshold value. For example, in the embodiment, a similar text information set corresponding to each electronic book in the electronic book database and a similarity score between each piece of text information in the similar text information set and the electronic book may be determined in advance for each electronic book in the electronic book database, and the similar text information set corresponding to each electronic book and the similarity score between each piece of text information in the similar text information set and the electronic book are stored in the preset database. In specific implementation, the number of the text information included in each similar text information set may be preset, for example, 10, and accordingly, for each electronic book, the similarity score between each text information in the text database and the electronic book is respectively calculated, 10 text information are filtered according to the similarity score from high to low and added to the similar text information set corresponding to the electronic book, and the similarity score between each text information and the electronic book is correspondingly stored.
Then, aiming at each piece of text information contained in the similar text information set corresponding to each target electronic book, determining each target electronic book corresponding to each similar text information set containing the text information as the similar target electronic book corresponding to the text information; and determining the text preference index corresponding to the text information by the reading user according to the similarity between the text information and each similar target electronic book and the book preference index of each similar target electronic book.
For example, assuming that there are 5 target electronic books and each target electronic book contains 10 text messages in the similar text message set, there are 50 text messages available for pushing. In practical situations, since the same text message may appear in similar text message sets of different electronic books, the 50 text messages available for push may include multiple repeated text messages, and the number of text messages available for push obtained after deduplication is necessarily less than 50. Correspondingly, for each text information available for pushing obtained after the deduplication, each similar text information set containing the text information is determined first, and each target electronic book corresponding to each similar text information set containing the text information is determined as a similar target electronic book corresponding to the text information. Assuming that the text information available for pushing appears in the set of similar text information corresponding to the 3 target electronic books in total, the number of the similar target electronic books of the text information available for pushing is 3. And determining a text preference index corresponding to the text information by the reading user according to the similarity between the text information available for pushing and the 3 similar target electronic books and the book preference index of each similar target electronic book. For example, the similarity between the text information available for pushing and 3 similar target electronic books is s1, s2, s3, respectively, and the book preference index of each similar target electronic book is i1, i2, i3, respectively, then the text preference index corresponding to the text information by the reading user is calculated by the following formula: s1 × i1+ s2 × i2+ s3 × i 3. Therefore, the text preference index corresponding to the text information of the reading user is determined according to the accumulation result between the similarity score between the text information and each similar target electronic book and the book preference index of each similar target electronic book. The principle of the above mode is as follows: if a user is interested in an electronic book, the user is typically also interested in textual information similar to the electronic book.
Step S250: and screening a preset number of text messages according to the text preference indexes corresponding to the text messages of the reading user, and pushing the text messages to the reading user.
Specifically, a preset number of text messages are screened from the text preference indexes from high to low and pushed to the reading user so as to be displayed by the corresponding terminal equipment. In specific implementation, the screened text messages can be further sorted according to the text preference index, and the sorting serial numbers of the text messages are provided for the reading user together so as to determine the display sequence.
Therefore, by the method in the embodiment, the preference index of unknown text information can be determined according to the electronic book with the known preference index, so that the pushing of the text information is more in line with the actual service requirement of a user. In addition, the present embodiment generates, for each electronic book, a tag vector uniquely corresponding to the electronic book, where the tag vector is a recessive tag vector used for calculating similarity, and the recessive tag vector has the following advantages compared with a conventional dominant tag vector:
the inventor finds that, in the process of implementing the invention, because the number of electronic books in the electronic book database is large, if a conventional dominant tag mining mode is adopted, a large number of dominant tags are mined, and each dominant tag and each electronic book are often crossed: for example, for a given overt tag, the given display tag is typically present in a plurality of different electronic books; moreover, for a given electronic book, there are often a plurality of corresponding dominant tags. Therefore, the dominant tags obtained by the conventional dominant tag mining method do not have a one-to-one correspondence with the electronic books, and therefore, the method cannot be obviously used for accurately determining the similarity between the electronic books and the text information. In order to solve the problems, a tag vector which is uniquely corresponding to each electronic book is generated for each electronic book by using a hidden tag generation mode, so that the similarity problem between the electronic book and the text information is converted into the similarity problem between two tag vectors, the text information which is interested by a user is conveniently pushed according to the preference index of the electronic book, and the personalized requirement of the user is met. In addition, because the reading time of the electronic book is long and the number of reading users is large, the preference index of the electronic book is convenient to determine, and the text information is generally short and scattered, so that the preference index is inconvenient to directly determine, and accordingly, the preference index of the text information which is inconvenient to determine can be indirectly obtained through the preference index of the electronic book which is convenient to determine.
In addition, the text information specifically includes: articles, short content, and/or text segments contained in an electronic book. Therefore, the text information to be pushed can be a part of paragraphs in the electronic book, or paragraphs in the contents of web articles or other sources, and the specific form of the text information is not limited by the invention.
In addition, the embodiment is mainly used for pushing a plurality of text messages for the electronic book application when the user opens the electronic book application, so that the extended reading of the user is realized. Accordingly, the present embodiment may be triggered when a user login instruction or an electronic book application start instruction is detected. Alternatively, the method may also be triggered when a text push request triggered by a user for a text push portal included in the e-book interface is detected.
In other embodiments of the present invention, a pushing operation of the text information may also be triggered during the process of the user reading the current electronic book, so that the user can browse the extended information associated with the current electronic book. Correspondingly, when the target electronic book corresponding to the reading user is determined in the above steps, the electronic book currently read by the user is directly determined as the target electronic book, that is, the electronic book currently read by the user can be pushed in an associated manner.
In addition, in other embodiments of the present invention, the user characteristics of the reading user may also be determined according to the user portrait data, and accordingly, historical reading data of a same-type user group having similar characteristics to the reading user is obtained, so as to determine the target electronic book by combining the historical reading data of the same-type user group, which is not limited in this invention.
In summary, the present invention is not limited to specific application scenarios, and those skilled in the art can make various modifications and variations to the above-described embodiments.
In summary, by the method in this embodiment, the text preference index corresponding to each text message of the reading user can be determined according to the book tag vector of the target electronic book and the similarity between the text tag vectors of each text message, and the similarity comparison problem between the electronic book and the text message is converted into the comparison problem between the tag vectors, so that the text message to be pushed can be screened according to the similarity between the text message and the target electronic book. The method can push the text information according to the reading preference of the user when reading the electronic book, so that the pushed text information is matched with the reading preference of the user, and the pushing accuracy is improved.
EXAMPLE III
The embodiment of the application provides a non-volatile computer storage medium, wherein at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the text information pushing method in any method embodiment.
The executable instructions may be specifically configured to cause the processor to:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
In an alternative implementation, the executable instructions cause a processor to:
generating a theme vector corresponding to the target electronic book through a document theme generating model, and taking the theme vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating a theme vector corresponding to each text message through a document theme generating model, and taking the theme vector of each text message as a text label vector of the text message.
In an alternative implementation, the executable instructions cause a processor to:
generating a word embedding vector corresponding to the target electronic book through a word embedding algorithm, and taking the word embedding vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating word embedding vectors corresponding to the text messages by a word embedding algorithm, and taking the word embedding vector of each text message as a text label vector of the text message.
In an alternative implementation, the executable instructions cause a processor to:
determining an interactive book list corresponding to the reading user according to historical reading data corresponding to the reading user;
and screening a plurality of electronic books from the interactive book list as target electronic books according to the interactive duration, interactive sections and/or interactive types of the reading user for the electronic books.
In an alternative implementation, the executable instructions cause a processor to:
and determining the electronic book currently read by the user as the target electronic book.
In an alternative implementation, if the target electronic book corresponding to the reading user is plural, the executable instructions cause the processor to:
and respectively determining book preference indexes of the reading user corresponding to the target electronic books, and determining text preference indexes of the reading user corresponding to the text information by combining the book preference indexes of the reading user corresponding to the target electronic books.
In an alternative implementation, the executable instructions cause a processor to:
and respectively determining the interaction duration, the interaction section and/or the interaction type of the reading user for each target electronic book, and determining the book preference index of the target electronic book according to the interaction duration, the interaction section and/or the interaction type.
In an alternative implementation manner, the text preference index of the reading user corresponding to each text message is determined by the following method:
determining similar text information sets corresponding to the target electronic books; each similar text information set is used for storing a plurality of text information of which the similarity with the corresponding target electronic book is greater than a preset threshold value;
for each piece of text information contained in the similar text information set corresponding to each target electronic book, determining each target electronic book corresponding to each similar text information set containing the text information as the similar target electronic book corresponding to the text information; and determining the text preference index corresponding to the text information by the reading user according to the similarity between the text information and each similar target electronic book and the book preference index of each similar target electronic book.
In an optional implementation, the text information includes: articles, short content, and/or text segments contained in an electronic book.
Example four
Fig. 3 is a schematic structural diagram of an electronic device according to another embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the electronic device.
As shown in fig. 3, the electronic device may include: a processor (processor)302, a communication Interface 304, a memory 306, and a communication bus 308.
Wherein: the processor 302, communication interface 304, and memory 306 communicate with each other via a communication bus 308. A communication interface 304 for communicating with network elements of other devices, such as clients or other servers. The processor 302 is configured to execute the program 310, and may specifically perform relevant steps in the foregoing pushing method embodiment of the text message.
In particular, program 310 may include program code comprising computer operating instructions.
The processor 302 may be a central processing unit CPU, or an application specific Integrated circuit (asic), or one or more Integrated circuits configured to implement an embodiment of the present invention. The electronic device comprises one or more processors, which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 306 for storing a program 310. Memory 306 may comprise high-speed RAM memory and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 310 may specifically be configured to cause the processor 302 to perform the following operations:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
In an alternative implementation, the executable instructions cause a processor to:
generating a theme vector corresponding to the target electronic book through a document theme generating model, and taking the theme vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating a theme vector corresponding to each text message through a document theme generating model, and taking the theme vector of each text message as a text label vector of the text message.
In an alternative implementation, the executable instructions cause a processor to:
generating a word embedding vector corresponding to the target electronic book through a word embedding algorithm, and taking the word embedding vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating word embedding vectors corresponding to the text messages by a word embedding algorithm, and taking the word embedding vector of each text message as a text label vector of the text message.
In an alternative implementation, the executable instructions cause a processor to:
determining an interactive book list corresponding to the reading user according to historical reading data corresponding to the reading user;
and screening a plurality of electronic books from the interactive book list as target electronic books according to the interactive duration, interactive sections and/or interactive types of the reading user for the electronic books.
In an alternative implementation, the executable instructions cause a processor to:
and determining the electronic book currently read by the user as the target electronic book.
In an alternative implementation, if the target electronic book corresponding to the reading user is plural, the executable instructions cause the processor to:
and respectively determining book preference indexes of the reading user corresponding to the target electronic books, and determining text preference indexes of the reading user corresponding to the text information by combining the book preference indexes of the reading user corresponding to the target electronic books.
In an alternative implementation, the executable instructions cause a processor to:
and respectively determining the interaction duration, the interaction section and/or the interaction type of the reading user for each target electronic book, and determining the book preference index of the target electronic book according to the interaction duration, the interaction section and/or the interaction type.
In an alternative implementation manner, the text preference index of the reading user corresponding to each text message is determined by the following method:
determining similar text information sets corresponding to the target electronic books; each similar text information set is used for storing a plurality of text information of which the similarity with the corresponding target electronic book is greater than a preset threshold value;
for each piece of text information contained in the similar text information set corresponding to each target electronic book, determining each target electronic book corresponding to each similar text information set containing the text information as the similar target electronic book corresponding to the text information; and determining the text preference index corresponding to the text information by the reading user according to the similarity between the text information and each similar target electronic book and the book preference index of each similar target electronic book.
In an optional implementation, the text information includes: articles, short content, and/or text segments contained in an electronic book.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
The invention discloses A1. a text information pushing method, which comprises the following steps:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
A2. The method of a1, wherein the obtaining the book tag vectors of the target electronic book and the text tag vectors of the respective text information includes:
generating a theme vector corresponding to the target electronic book through a document theme generating model, and taking the theme vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating a theme vector corresponding to each text message through a document theme generating model, and taking the theme vector of each text message as a text label vector of the text message.
A3. The method of a1, wherein the obtaining the book tag vectors of the target electronic book and the text tag vectors of the respective text information includes:
generating a word embedding vector corresponding to the target electronic book through a word embedding algorithm, and taking the word embedding vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating word embedding vectors corresponding to the text messages by a word embedding algorithm, and taking the word embedding vector of each text message as a text label vector of the text message.
A4. The method according to any one of A1-3, wherein the determining the target electronic book corresponding to the reading user includes:
determining an interactive book list corresponding to the reading user according to historical reading data corresponding to the reading user;
and screening a plurality of electronic books from the interactive book list as target electronic books according to the interactive duration, interactive sections and/or interactive types of the reading user for the electronic books.
A5. The method according to any one of A1-3, wherein the determining the target electronic book corresponding to the reading user includes:
and determining the electronic book currently read by the user as the target electronic book.
A6. The method according to any one of a1-5, wherein, if there are a plurality of target electronic books corresponding to the reading user, the determining the text preference index of the reading user corresponding to each text information according to the similarity between the text label vector of each text information and the book label vector of the target electronic book includes:
and respectively determining book preference indexes of the reading user corresponding to the target electronic books, and determining text preference indexes of the reading user corresponding to the text information by combining the book preference indexes of the reading user corresponding to the target electronic books.
A7. The method of a6, wherein the respectively determining book preference indices of the reading user corresponding to respective target electronic books comprises: and respectively determining the interaction duration, the interaction section and/or the interaction type of the reading user for each target electronic book, and determining the book preference index of the target electronic book according to the interaction duration, the interaction section and/or the interaction type.
A8. The method according to a7, wherein the text preference index of the reading user corresponding to each text message is determined by:
determining similar text information sets corresponding to the target electronic books; each similar text information set is used for storing a plurality of text information of which the similarity with the corresponding target electronic book is greater than a preset threshold value;
for each piece of text information contained in the similar text information set corresponding to each target electronic book, determining each target electronic book corresponding to each similar text information set containing the text information as the similar target electronic book corresponding to the text information; and determining the text preference index corresponding to the text information by the reading user according to the similarity between the text information and each similar target electronic book and the book preference index of each similar target electronic book.
A9. The method according to any of a1-8, wherein the text information comprises: articles, short content, and/or text segments contained in an electronic book.
B10. An electronic device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
B11. The electronic device of B10, wherein the executable instructions cause the processor to:
generating a theme vector corresponding to the target electronic book through a document theme generating model, and taking the theme vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating a theme vector corresponding to each text message through a document theme generating model, and taking the theme vector of each text message as a text label vector of the text message.
B12. The electronic device of B10, wherein the executable instructions cause the processor to:
generating a word embedding vector corresponding to the target electronic book through a word embedding algorithm, and taking the word embedding vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating word embedding vectors corresponding to the text messages by a word embedding algorithm, and taking the word embedding vector of each text message as a text label vector of the text message.
B13. The electronic device of any of B10-12, wherein the executable instructions cause the processor to:
determining an interactive book list corresponding to the reading user according to historical reading data corresponding to the reading user;
and screening a plurality of electronic books from the interactive book list as target electronic books according to the interactive duration, interactive sections and/or interactive types of the reading user for the electronic books.
B14. The electronic device of any of B10-12, wherein the executable instructions cause the processor to:
and determining the electronic book currently read by the user as the target electronic book.
B15. The electronic device of any of B10-14, wherein the plurality of target electronic books corresponding to the reading user, the executable instructions cause the processor to:
and respectively determining book preference indexes of the reading user corresponding to the target electronic books, and determining text preference indexes of the reading user corresponding to the text information by combining the book preference indexes of the reading user corresponding to the target electronic books.
B16. The electronic device of B15, wherein the executable instructions cause the processor to:
and respectively determining the interaction duration, the interaction section and/or the interaction type of the reading user for each target electronic book, and determining the book preference index of the target electronic book according to the interaction duration, the interaction section and/or the interaction type.
B17. The electronic device of B16, wherein the text preference index of the reading user corresponding to each text message is determined by:
determining similar text information sets corresponding to the target electronic books; each similar text information set is used for storing a plurality of text information of which the similarity with the corresponding target electronic book is greater than a preset threshold value;
for each piece of text information contained in the similar text information set corresponding to each target electronic book, determining each target electronic book corresponding to each similar text information set containing the text information as the similar target electronic book corresponding to the text information; and determining the text preference index corresponding to the text information by the reading user according to the similarity between the text information and each similar target electronic book and the book preference index of each similar target electronic book.
B18. The electronic device of any of B10-17, wherein the textual information includes: articles, short content, and/or text segments contained in an electronic book.
C19. A computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
C20. The computer storage medium of C19, wherein the executable instructions cause a processor to:
generating a theme vector corresponding to the target electronic book through a document theme generating model, and taking the theme vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating a theme vector corresponding to each text message through a document theme generating model, and taking the theme vector of each text message as a text label vector of the text message.
C21. The computer storage medium of C19, wherein the executable instructions cause a processor to:
generating a word embedding vector corresponding to the target electronic book through a word embedding algorithm, and taking the word embedding vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating word embedding vectors corresponding to the text messages by a word embedding algorithm, and taking the word embedding vector of each text message as a text label vector of the text message.
C22. The computer storage medium of any of C19-21, wherein the executable instructions cause a processor to:
determining an interactive book list corresponding to the reading user according to historical reading data corresponding to the reading user;
and screening a plurality of electronic books from the interactive book list as target electronic books according to the interactive duration, interactive sections and/or interactive types of the reading user for the electronic books.
C23. The computer storage medium of any of C19-21, wherein the executable instructions cause a processor to:
and determining the electronic book currently read by the user as the target electronic book.
C24. The computer storage medium of any of C19-23, wherein the plurality of target electronic books corresponding to the reading user, the executable instructions cause the processor to:
and respectively determining book preference indexes of the reading user corresponding to the target electronic books, and determining text preference indexes of the reading user corresponding to the text information by combining the book preference indexes of the reading user corresponding to the target electronic books.
C25. The computer storage medium of C24, wherein the executable instructions cause a processor to:
and respectively determining the interaction duration, the interaction section and/or the interaction type of the reading user for each target electronic book, and determining the book preference index of the target electronic book according to the interaction duration, the interaction section and/or the interaction type.
C26. The computer storage medium of C25, wherein the text preference index of the reading user for each text message is determined by:
determining similar text information sets corresponding to the target electronic books; each similar text information set is used for storing a plurality of text information of which the similarity with the corresponding target electronic book is greater than a preset threshold value;
for each piece of text information contained in the similar text information set corresponding to each target electronic book, determining each target electronic book corresponding to each similar text information set containing the text information as the similar target electronic book corresponding to the text information; and determining the text preference index corresponding to the text information by the reading user according to the similarity between the text information and each similar target electronic book and the book preference index of each similar target electronic book.
C27. The computer storage medium of any of C19-26, wherein the textual information comprises: articles, short content, and/or text segments contained in an electronic book.
Claims (10)
1. A method for pushing text information comprises the following steps:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
2. The method of claim 1, wherein the obtaining of the book tag vector of the target electronic book and the text tag vector of each text message comprises:
generating a theme vector corresponding to the target electronic book through a document theme generating model, and taking the theme vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating a theme vector corresponding to each text message through a document theme generating model, and taking the theme vector of each text message as a text label vector of the text message.
3. The method of claim 1, wherein the obtaining of the book tag vector of the target electronic book and the text tag vector of each text message comprises:
generating a word embedding vector corresponding to the target electronic book through a word embedding algorithm, and taking the word embedding vector of the target electronic book as a book tag vector of the target electronic book; and the number of the first and second groups,
and generating word embedding vectors corresponding to the text messages by a word embedding algorithm, and taking the word embedding vector of each text message as a text label vector of the text message.
4. The method of any of claims 1-3, wherein the determining a target electronic book corresponding to the reading user comprises:
determining an interactive book list corresponding to the reading user according to historical reading data corresponding to the reading user;
and screening a plurality of electronic books from the interactive book list as target electronic books according to the interactive duration, interactive sections and/or interactive types of the reading user for the electronic books.
5. The method of any of claims 1-3, wherein the determining a target electronic book corresponding to the reading user comprises:
and determining the electronic book currently read by the user as the target electronic book.
6. The method of any one of claims 1 to 5, wherein the target electronic book corresponding to the reading user is plural, and the determining the text preference index of the reading user corresponding to each text message according to the similarity between the text tag vector of each text message and the book tag vector of the target electronic book comprises:
and respectively determining book preference indexes of the reading user corresponding to the target electronic books, and determining text preference indexes of the reading user corresponding to the text information by combining the book preference indexes of the reading user corresponding to the target electronic books.
7. The method of claim 6, wherein the separately determining the book preference indices of the reading user corresponding to the respective target electronic books comprises: and respectively determining the interaction duration, the interaction section and/or the interaction type of the reading user for each target electronic book, and determining the book preference index of the target electronic book according to the interaction duration, the interaction section and/or the interaction type.
8. The method of claim 7, wherein the text preference index of the reading user corresponding to each text message is determined by:
determining similar text information sets corresponding to the target electronic books; each similar text information set is used for storing a plurality of text information of which the similarity with the corresponding target electronic book is greater than a preset threshold value;
for each piece of text information contained in the similar text information set corresponding to each target electronic book, determining each target electronic book corresponding to each similar text information set containing the text information as the similar target electronic book corresponding to the text information; and determining the text preference index corresponding to the text information by the reading user according to the similarity between the text information and each similar target electronic book and the book preference index of each similar target electronic book.
9. An electronic device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
10. A computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to:
determining a target electronic book corresponding to a reading user;
acquiring a book tag vector of the target electronic book and a text tag vector of each text message;
determining text preference indexes of the reading user corresponding to the text information according to the similarity between the text label vector of the text information and the book label vector of the target electronic book;
and screening a preset number of text messages according to the text preference indexes of the reading users corresponding to the text messages, and pushing the text messages to the reading users.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911222007.7A CN110909247B (en) | 2019-12-03 | 2019-12-03 | Text information pushing method, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911222007.7A CN110909247B (en) | 2019-12-03 | 2019-12-03 | Text information pushing method, electronic equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110909247A true CN110909247A (en) | 2020-03-24 |
| CN110909247B CN110909247B (en) | 2022-07-12 |
Family
ID=69822116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911222007.7A Active CN110909247B (en) | 2019-12-03 | 2019-12-03 | Text information pushing method, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110909247B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488529A (en) * | 2020-06-28 | 2020-08-04 | 腾讯科技（深圳）有限公司 | Information processing method, information processing apparatus, server, and storage medium |
| JP7438808B2 (en) | 2020-03-26 | 2024-02-27 | 株式会社野村総合研究所 | Needs matching equipment and programs |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090132459A1 (en) * | 2007-11-16 | 2009-05-21 | Cory Hicks | Processes for improving the utility of personalized recommendations generated by a recommendation engine |
| CN103176982A (en) * | 2011-12-20 | 2013-06-26 | ***通信集团浙江有限公司 | Recommending method and recommending system of electronic book |
| CN104731866A (en) * | 2015-02-27 | 2015-06-24 | 湖南大学 | Individual gourmet recommending method based on position |
| CN104732422A (en) * | 2015-02-27 | 2015-06-24 | 湖南大学 | Mobile user tag based personalized food recommendation method |
| CN107483595A (en) * | 2017-08-23 | 2017-12-15 | 北京百度网讯科技有限公司 | Information-pushing method and device |
| CN108536804A (en) * | 2018-03-30 | 2018-09-14 | 掌阅科技股份有限公司 | Information-pushing method, electronic equipment based on e-book and computer storage media |
| CN108897750A (en) * | 2018-04-28 | 2018-11-27 | 中国地质大学（武汉） | Merge the personalized location recommendation method and equipment of polynary contextual information |
| CN109284500A (en) * | 2018-08-20 | 2019-01-29 | 张连祥 | Information transmission system and method based on merchants inviting work process and reading preference |
| CN109325173A (en) * | 2018-08-15 | 2019-02-12 | 山东师范大学 | Reading content personalized recommendation method and system based on AI open platform |
-
2019
- 2019-12-03 CN CN201911222007.7A patent/CN110909247B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090132459A1 (en) * | 2007-11-16 | 2009-05-21 | Cory Hicks | Processes for improving the utility of personalized recommendations generated by a recommendation engine |
| CN103176982A (en) * | 2011-12-20 | 2013-06-26 | ***通信集团浙江有限公司 | Recommending method and recommending system of electronic book |
| CN104731866A (en) * | 2015-02-27 | 2015-06-24 | 湖南大学 | Individual gourmet recommending method based on position |
| CN104732422A (en) * | 2015-02-27 | 2015-06-24 | 湖南大学 | Mobile user tag based personalized food recommendation method |
| CN107483595A (en) * | 2017-08-23 | 2017-12-15 | 北京百度网讯科技有限公司 | Information-pushing method and device |
| CN108536804A (en) * | 2018-03-30 | 2018-09-14 | 掌阅科技股份有限公司 | Information-pushing method, electronic equipment based on e-book and computer storage media |
| CN108897750A (en) * | 2018-04-28 | 2018-11-27 | 中国地质大学（武汉） | Merge the personalized location recommendation method and equipment of polynary contextual information |
| CN109325173A (en) * | 2018-08-15 | 2019-02-12 | 山东师范大学 | Reading content personalized recommendation method and system based on AI open platform |
| CN109284500A (en) * | 2018-08-20 | 2019-01-29 | 张连祥 | Information transmission system and method based on merchants inviting work process and reading preference |
Non-Patent Citations (6)
| Title |
|---|
| YE TIAN: "An enhanced personal photo recommendation system by fusing contextual and textual features on mobile device", 《IEEE TRANSACTIONS ON CONSUMER ELECTRONICS》 * |
| 严凡等: "基于图书语义信息的推荐方法研究", 《图书馆学研究》 * |
| 刘荣辉等: "移动阅读***中的多源动态混合推荐", 《情报科学》 * |
| 张淑华: "《云生活与后媒体时代的舆论场重构》", 31 August 2016 * |
| 逄淑超: "深度学习在计算机视觉领域的若干关键技术研究", 《中国优秀博硕士学位论文全文数据库(博士)》 * |
| 陈翔等: "用户电子书阅读行为研究进展述评", 《数字图书馆论坛》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7438808B2 (en) | 2020-03-26 | 2024-02-27 | 株式会社野村総合研究所 | Needs matching equipment and programs |
| CN111488529A (en) * | 2020-06-28 | 2020-08-04 | 腾讯科技（深圳）有限公司 | Information processing method, information processing apparatus, server, and storage medium |
| CN111488529B (en) * | 2020-06-28 | 2020-09-29 | 腾讯科技（深圳）有限公司 | Information processing method, information processing apparatus, server, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110909247B (en) | 2022-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102092691B1 (en) | Web page training methods and devices, and search intention identification methods and devices | |
| CN107992596B (en) | Text clustering method, text clustering device, server and storage medium | |
| RU2678716C1 (en) | Use of autoencoders for learning text classifiers in natural language | |
| CN109299994B (en) | Recommendation method, device, equipment and readable storage medium | |
| CN104778158B (en) | A kind of document representation method and device | |
| CN105069102A (en) | Information push method and apparatus | |
| CN111539197B (en) | Text matching method and device, computer system and readable storage medium | |
| CN111241389A (en) | Sensitive word filtering method and device based on matrix, electronic equipment and storage medium | |
| US9483740B1 (en) | Automated data classification | |
| CN108536868B (en) | Data processing method and device for short text data on social network | |
| CN110968789B (en) | Electronic book pushing method, electronic equipment and computer storage medium | |
| CN113449187A (en) | Product recommendation method, device and equipment based on double portraits and storage medium | |
| WO2019028990A1 (en) | Code element naming method, device, electronic equipment and medium | |
| US10956470B2 (en) | Facet-based query refinement based on multiple query interpretations | |
| CN111126060A (en) | Method, device and equipment for extracting subject term and storage medium | |
| CN110909247B (en) | Text information pushing method, electronic equipment and computer storage medium | |
| CN110377750B (en) | Comment generation method, comment generation device, comment generation model training device and storage medium | |
| US9516089B1 (en) | Identifying and processing a number of features identified in a document to determine a type of the document | |
| CN107908649B (en) | Text classification control method | |
| CN110019821A (en) | Text category training method and recognition methods, relevant apparatus and storage medium | |
| CN113343109A (en) | List recommendation method, computing device and computer storage medium | |
| KR102299525B1 (en) | Product Evolution Mining Method And Apparatus Thereof | |
| US20210089539A1 (en) | Associating user-provided content items to interest nodes | |
| CN112270177A (en) | News cover mapping method and device based on content similarity and computing equipment | |
| CN110019702B (en) | Data mining method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220829 Address after: 518054-13098, 13th floor, main tower of marine center, No. 59, Linhai Avenue, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong Patentee after: Shenzhen ZhangYue Animation Technology Co.,Ltd. Address before: 100124 2029e, Sihui building, Chaoyang District, Beijing Patentee before: ZHANGYUE TECHNOLOGY Co.,Ltd. |