CN111782946A - Book friend recommendation method, calculation device and computer storage medium - Google Patents
Book friend recommendation method, calculation device and computer storage medium Download PDFInfo
- Publication number
- CN111782946A CN111782946A CN202010608747.0A CN202010608747A CN111782946A CN 111782946 A CN111782946 A CN 111782946A CN 202010608747 A CN202010608747 A CN 202010608747A CN 111782946 A CN111782946 A CN 111782946A
- Authority
- CN
- China
- Prior art keywords
- user
- recommended
- reading
- target user
- data
- 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.)
- Pending
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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention discloses a book friend recommendation method, a calculation device and a computer storage medium. The method comprises the following steps: determining a target user, and acquiring reading data of at least one dimension of the target user; acquiring reading data of at least one dimension of a user set to be recommended and each user to be recommended in the user set to be recommended; calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended; and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to the target user. According to the scheme provided by the invention, book friends with similar interests are recommended to the target user by using the reading data generated in the reading process, so that the recommendation accuracy is improved, the common topics between the target user and the recommended book friends are ensured, the activity rate of the user can be further improved, and the time for the user to use the reading application is prolonged.
Description
Technical Field
The invention relates to the technical field of computer application, in particular to a book friend recommendation method, a computing device and a computer storage medium.
Background
With the rapid development of internet technology, various applications based on the internet are produced, and in the aspect of reading, corresponding reading applications are generated, so that a reading fan can read an electronic book through the reading applications, and the transition from the traditional paper book reading to the electronic book reading is realized.
However, the current reading application has a single function, and the user usually only uses the reading application to read the electronic book, which results in low usage rate of the reading application by the user and low user activity rate of the reading application.
Disclosure of Invention
In view of the above, the present invention has been made to provide a book friend recommendation method, a computing device, and a computer storage medium that overcome or at least partially solve the above-mentioned problems.
According to an aspect of the present invention, there is provided a book friend recommendation method including:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring reading data of at least one dimension of a user set to be recommended and each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to the target user.
According to another aspect of the present invention, there is provided a computing device comprising: the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the following operations:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring reading data of at least one dimension of a user set to be recommended and each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to the target user.
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 a processor to:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring reading data of at least one dimension of a user set to be recommended and each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to the target user.
According to the scheme provided by the invention, a target user is determined, and reading data of at least one dimension of the target user is acquired; acquiring reading data of at least one dimension of a user set to be recommended and each user to be recommended in the user set to be recommended; calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended; and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to the target user. According to the scheme provided by the invention, book friends with similar interests are recommended to the target user by using the reading data generated in the reading process, so that the recommendation accuracy is improved, the common topics between the target user and the recommended book friends are ensured, the activity rate of the user can be further improved, and the time for the user to use the reading application is prolonged.
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 flow diagram of a book friend recommendation method according to one embodiment of the invention;
FIG. 2 shows a flow diagram of a book friend recommendation method according to another embodiment of the invention;
FIG. 3 shows a schematic structural diagram of a computing device according to one embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can 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 invention to those skilled in the art.
Fig. 1 shows a flow diagram of a book friend recommendation method according to an embodiment of the invention. As shown in fig. 1, the method comprises the steps of:
step S101, determining a target user, and acquiring reading data of at least one dimension of the target user.
The objective of the book friend recommendation method provided in this embodiment is to perform book friend recommendation, and therefore, it is necessary to determine a target user first, where the target user refers to a user who receives book friend recommendation, and for example, a user who actively triggers a book friend recommendation operation through a client may be determined as the target user, or a server may actively determine the target user who receives book friend recommendation.
After the target user is determined, reading data of at least one dimension of the target user is acquired, wherein the reading data of at least one dimension is data generated by the target user in the process of reading the electronic book.
Step S102, reading data of at least one dimension of the user set to be recommended and each user to be recommended in the user set to be recommended are obtained.
In this embodiment, in order to recommend a book friend to a target user, step S101 is only to determine the target user who receives the recommendation of the book friend, and therefore, a user set to be recommended needs to be obtained, where the user set to be recommended includes a plurality of users to be recommended, and the book friend who is finally recommended to the target user is screened from the user set to be recommended. In addition to obtaining the set of users to be recommended, reading data of at least one dimension of each user to be recommended in the set of users to be recommended needs to be obtained, where the reading data is data generated by each user to be recommended in the process of reading an electronic book.
Step S103, calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended.
In order to avoid that the target user and the recommended book friends do not have a common topic when the book friends are recommended to the target user randomly, after the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended are obtained according to the two steps, the similarity between the target user and each user to be recommended is calculated according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended. The similarity represents the similarity between the target user and the user to be recommended.
And step S104, screening book friends from the user set to be recommended according to the similarity and recommending the book friends to a target user.
After the similarity between the target user and each user to be recommended is calculated according to step S103, the book friends to be recommended to the target user may be screened from the set of users to be recommended according to the calculated similarity, and then, the screened book friends are recommended to the target user. The book friends recommended to the target user have certain similarity with the target user, so that similar interests between the target user and the book friends are guaranteed.
According to the method provided by the embodiment of the invention, the target user is determined, and the reading data of at least one dimension of the target user is acquired; acquiring reading data of at least one dimension of a user set to be recommended and each user to be recommended in the user set to be recommended; calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended; and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to the target user. According to the scheme provided by the invention, book friends with similar interests are recommended to the target user by using the reading data generated in the reading process, so that the recommendation accuracy is improved, the common topics between the target user and the recommended book friends are ensured, the activity rate of the user can be further improved, and the time for the user to use the reading application is prolonged.
Fig. 2 shows a flow diagram of a book friend recommendation method according to another embodiment of the invention. As shown in fig. 2, the method comprises the steps of:
step S201, determining a target user, and acquiring reading mark data of the target user.
The book friend recommendation method provided in this embodiment aims to perform book friend recommendation, and therefore, a target user needs to be determined first, where the target user refers to a user who receives book friend recommendation, for example, a reading application provides a book friend recommendation function, a "book friend recommendation button" is provided in an application display interface, and a certain user triggers the "book friend recommendation button" in a reading application process, that is, the user is considered to have sent a book friend recommendation request to a server, and the server determines the user as the target user after receiving the book friend recommendation request, where the book friend recommendation request carries user information of the user, and therefore, book friend recommendation can be performed according to the user information after determining a book friend to be recommended; or the server can actively determine the target user for receiving the book friend recommendation according to the service requirement, the server stores user information of a plurality of reading users, and one reading user can be selected as the target user.
After the target user is determined, reading mark data of the target user is obtained, wherein the reading mark data is marks made on the electronic book by the user in the process of reading the electronic book, for example, comment information, comments and/or ideas published by the target user on the contents of a specified paragraph of the electronic book, or comment information and/or ideas published for the specified electronic book, or the like can be obtained.
Specifically, the target user may mark the electronic book at any time in the process of reading the electronic book, after monitoring the reading mark data, the reading application reports the generated reading mark data to the server, and simultaneously reports user information of the target user, and the server stores the user information of the target user and the reading mark data in a database in an associated manner, so that after the target user is determined, the database can be queried based on the user information of the target user, and the reading mark data of the target user can be acquired from the database.
Step S202, reading mark data of the preset reference user set and each preset reference user in the preset reference user set are obtained.
Generally, there is a sense of distance between people, and if a common reader is directly recommended to a target user as a book friend, a situation that the target user does not accept the recommendation may occur, so a KOL (key Opinion leader) in the field of e-book reading may be recommended to the target user, in this embodiment, the KOL is also referred to as a preset reference user, and is a person having a calling force in the field of e-book reading, and the preset reference users are easily accepted or trusted by the relevant readers and have a great influence on the reading behavior of the relevant readers.
In general, there may be a plurality of preset reference users, and the step of obtaining the preset reference user set may use, for example, a specified paragraph content or a specified electronic book to which reading tag data of a target user is directed as a basis for obtaining, for example, obtain the preset reference user set corresponding to the specified paragraph content or obtain the preset reference user set corresponding to the specified electronic book, so as to be able to recommend, to the target user, a preset reference user that is resonant with the preset reference user at a certain electronic book or a certain paragraph of the electronic book more accurately, and in addition, need to obtain reading tag data of each preset reference user in the preset reference user set, where the reading tag data is data generated by each preset reference user in a process of reading the electronic book.
The reading mark data of the preset reference user obtained in this step corresponds to the reading mark data of the target user obtained in step S201, for example, if the comment and/or idea of the target user about the content of the specified paragraph is obtained in step S201, the comment and/or idea of the preset reference user about the content of the specified paragraph is obtained in this step; if the comment information of the target user about the specified electronic book is acquired in step S201, the comment information of the preset reference user about the specified electronic book is acquired in this step.
Step S203, semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each preset reference user, and the intention identification result of the target user and the intention identification result of each preset reference user are determined.
After the reading mark data of the target user and the reading mark data of each preset reference user are respectively obtained according to the two steps, semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each preset reference user, wherein one method of the semantic analysis is to firstly carry out word segmentation processing on the reading mark data, namely segmenting the reading mark data into meaningful words, then carry out intention recognition according to the result of the word segmentation processing, and finally determine the intention recognition result of the target user and the intention recognition result of each preset reference user.
For example, the reading mark data of a certain paragraph of the target user is "very wounded" in the process of reading the electronic book, the reading mark data of the same paragraph of a preset reference user is "not fast in mind" in the process of reading the electronic book, the intention recognition result of the target user is determined to be "sad emotion" by performing semantic analysis on the reading mark data, and the intention recognition result of the preset reference user is "sad emotion".
Through semantic analysis, reading mark data which are represented in different words in form but convey the same or similar intentions can be converted into the same or similar intention recognition results, so that a basis is provided for subsequent similarity calculation, and a plurality of different reading mark data can correspond to the same intention recognition results.
And step S204, calculating the similarity between the target user and each preset reference user according to the target user intention recognition result and each preset reference user intention recognition result.
After determining the target user intention recognition result and each preset reference user intention recognition result according to step S203, the similarity between the target user and each preset reference user may be calculated according to the target user intention recognition result and each preset reference user intention recognition result.
Specifically, the similarity between the target user intention recognition result and each preset reference user intention recognition result may be calculated by using a similarity calculation algorithm, and the calculated result may be used as the similarity between the target user and each preset reference user, for example, any one of the following similarity calculation algorithms may be used: firstly, editing a distance calculation algorithm; calculating algorithm of Jacobsard coefficient; ③ TF calculation algorithm; fourthly, calculating the TFIDF algorithm; word2Vec calculation algorithm, and the specific calculation process using various calculation algorithms is not described herein.
And S205, screening out preset reference users from the preset reference user set according to the similarity, and recommending the preset reference users to the target user.
After the similarity between the target user and each preset reference user is calculated according to step S204, the preset reference users to be recommended to the target user may be screened from the preset reference user set according to the calculated similarity, and then the screened preset reference users are recommended to the target user. The preset reference user recommended to the target user resonates with the target user in the same electronic book or the same paragraph of the electronic book, so that the target user and the preset reference user are guaranteed to have similar interests.
And step S206, recommending the book friends having relevance with the screened preset reference users to the target users.
After the preset reference users are screened from the preset reference user set, the book friends associated with the screened preset reference users may be recommended to the target users, for example, the users who pay attention to the preset reference users may be recommended to the target users as book friends.
Specifically, when there is an association between a preset reference user and another user, the association relationship between the preset reference user and the another user may be recorded in a user relationship list, for example, one user relationship list is recorded for each preset reference user, and then after the preset reference user is screened out, the user relationship list corresponding to the preset reference user may be found, and the user recorded in the user relationship list is recommended to a target user as a book friend; certainly, a user relationship list may be shared by a plurality of preset reference users, users having an association relationship with each preset reference user are recorded in the user relationship list, after the preset reference users are screened out, the users having an association relationship with the screened out preset reference users are found out from the user relationship list, and the found users are recommended to the target user as book friends.
Step S207, determining the electronic book to be recommended according to the reading history data of the recommending book friends, and recommending the electronic book to be recommended to the target user.
In this embodiment, the electronic books may also be recommended to the target user, and specifically, which electronic books are recommended to the target user may be determined by the following method: the method includes the steps that a bookfriend recommended to a target user is a user with similar reading interest to the user, and therefore the target user may be interested in an electronic book which is read by the bookfriend in a usual mode, reading history data of the recommended bookfriend can be obtained, wherein the reading history data include the electronic book which is read by the bookfriend in a history mode, the target user and the recommended bookfriend may have the condition that the same electronic book is read, in order to avoid recommending the electronic book which is already read to the target user, the reading history data of the target user can be obtained, then, deduplication processing is conducted on the reading history data of the target user and the reading history data of the recommended bookfriend, the electronic book after deduplication is determined to be the electronic book to be recommended, and the electronic book to be recommended is recommended to the target user.
In an alternative embodiment of the present invention, the reading data of at least one dimension may include, in addition to the reading mark data: reading behavior data, wherein the reading behavior data comprises one or more of the following data: reading book type, reading time length, reading time point (indicating at which time point of the day the user reads the electronic book), reading frequency of the specified chapter content and/or paragraph content (indicating the number of times the user repeatedly reads the specified chapter content and/or paragraph content), and therefore, similarity between the target user and each preset reference user can be calculated based on the reading behavior data of the target user and the reading behavior data of each preset reference user. For example, feature vectors may be generated based on the reading behavior data, and the similarity between the target user and each preset reference user may be calculated by using a cosine similarity algorithm; the similarity between the target user and each preset reference user can be calculated by using a pearson correlation coefficient algorithm, which is not described in detail herein. Of course other similarity calculation algorithms may be used.
In an optional implementation manner of the present invention, the set of users to be recommended may be a preset reference user set, or a set formed by a common reader, and the content of a specified paragraph or the specified electronic book to which the reading mark data of the target user is directed is used as an obtaining basis, for example, the reading mark data of the user set to be recommended corresponding to the content of the specified paragraph and the reading mark data of each user to be recommended in the user set to be recommended are obtained; or, the implementation process of obtaining the set of users to be recommended corresponding to the specified electronic book and the reading mark data of each user to be recommended in the set of users to be recommended, specifically, screening book friends from the set of users to be recommended and recommending the book friends to the target user is similar to the implementation process of the above embodiment, and is not repeated here.
In an alternative embodiment of the invention, a "book friend recommendation button" is provided in the application presentation interface, therefore, the user can actively search for book friends by triggering the book friend recommendation button, in addition, the application display interface also provides the user with the selection of the book friend screening range, for example, the user may select at least one electronic book among the plurality of electronic books presented by the application presentation interface, and/or at least one paragraph is selected from a certain electronic book, or the application display interface is provided with an input box, the user can input an electronic book mark or an electronic book paragraph mark in the input box as a book friend screening basis, then, reporting the book friend screening basis to a server, and acquiring a set of users to be recommended corresponding to the specified paragraph contents and reading mark data of each user to be recommended in the set of users to be recommended by the server; or, reading mark data of a user set to be recommended corresponding to the specified electronic book and reading mark data of each user to be recommended in the user set to be recommended are obtained, so that the user can actively search other reading users who are in resonance with the user in a certain electronic book or a certain paragraph of the electronic book, and therefore, the book friends can be accurately recommended.
In an optional implementation manner of the present invention, after the similarity between the target user and the preset reference user is obtained through calculation, for each preset reference user, a reading map including at least one reading attribute may be constructed based on the similarity obtained through calculation, the reading map is composed of the preset reference user and the target user having a higher similarity with the preset reference user, the reading attribute of the reading map is determined by the type of the electronic book, and the type of the electronic book read by the target user and the preset reference user together may be determined as the reading attribute; in order to recommend more book friends to the user, whether any two reading maps have the same reading attribute can be judged, and if yes, the book friends with the same reading attribute are recommended to the target user.
According to the scheme provided by the invention, the real intentions of the target user and the preset reference user can be obtained by performing semantic analysis on the reading mark data generated by the target user in the reading process and the reading mark data generated by the preset reference user in the reading process, and the similarity between the target user and each preset reference user is calculated based on the intention recognition result of the target user and the intention recognition result of each preset reference user, so that a basis is provided for accurately recommending the preset reference user to the target user, and the preset reference user is a person which is more easily accepted or trusted by the target user, so that the user which has relevance with the preset reference user is recommended to the user as a book friend and is more easily accepted by the target user. The recommended book friends have higher similarity with the target user, so that the recommendation accuracy is improved, the target user and the recommended book friends are guaranteed to have common topics, the activity rate of the user can be further improved, and the time of the user for reading application is prolonged.
The embodiment of the invention also provides a nonvolatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the book friend recommendation method in any method embodiment.
The executable instructions may be specifically configured to cause the processor to:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring reading data of at least one dimension of a user set to be recommended and each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to the target user.
In an alternative embodiment, the reading data of at least one dimension comprises: reading the marking data; the reading mark data includes: comment information, comments, and/or ideas specifying the content of the passage;
the executable instructions further cause the processor to: acquiring a user set to be recommended corresponding to the specified paragraph content and reading mark data of each user to be recommended in the user set to be recommended;
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user to be recommended intention identification result.
In an alternative embodiment, the reading data of at least one dimension comprises: reading the marking data; the reading mark data includes: specifying comment information and/or ideas for the electronic book;
the executable instructions further cause the processor to:
acquiring a set of users to be recommended corresponding to the specified electronic book and reading mark data of each user to be recommended in the set of users to be recommended;
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user to be recommended intention identification result.
In an alternative embodiment, the reading data of at least one dimension further comprises: reading behavior data; the reading behavior data includes one or more of the following: book type, reading duration, reading time point, designated chapter content and/or reading frequency of paragraph content.
In an alternative embodiment, the executable instructions further cause the processor to:
and determining the electronic book to be recommended according to the reading history data of the recommending book friends, and recommending the electronic book to be recommended to the target user.
In an optional embodiment, the set of users to be recommended includes: presetting a reference user set;
the executable instructions further cause the processor to:
calculating the similarity between the target user and each preset reference user according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each preset reference user in the preset reference user set;
screening preset reference users from a preset reference user set according to the similarity and recommending the preset reference users to a target user;
recommending the book friends having relevance with the screened preset reference users to the target users.
In an alternative embodiment, the executable instructions further cause the processor to:
constructing a reading map containing at least one reading attribute based on the calculated similarity for each preset reference user;
and judging whether any two reading maps have the same reading attribute, and if so, recommending the book friends with the same reading attribute to the target user.
Fig. 3 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
As shown in fig. 3, the computing 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 execute the relevant steps in the aforementioned embodiment of the book friend recommendation method.
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 computing device includes one or more processors, which may 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 user, and acquiring reading data of at least one dimension of the target user;
acquiring reading data of at least one dimension of a user set to be recommended and each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to the target user.
In an alternative embodiment, the reading data of at least one dimension comprises: reading the marking data; the reading mark data includes: comment information, comments, and/or ideas specifying the content of the passage;
acquiring a user set to be recommended corresponding to the specified paragraph content and reading mark data of each user to be recommended in the user set to be recommended;
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user to be recommended intention identification result.
In an alternative embodiment, the reading data of at least one dimension comprises: reading the marking data; the reading mark data includes: specifying comment information and/or ideas for the electronic book;
acquiring a set of users to be recommended corresponding to the specified electronic book and reading mark data of each user to be recommended in the set of users to be recommended;
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user to be recommended intention identification result.
In an alternative embodiment, the reading data of at least one dimension further comprises: reading behavior data; the reading behavior data includes one or more of the following: book type, reading duration, reading time point, designated chapter content and/or reading frequency of paragraph content.
In an alternative embodiment, program 310 also causes processor 302 to:
and determining the electronic book to be recommended according to the reading history data of the recommending book friends, and recommending the electronic book to be recommended to the target user.
In an optional embodiment, the set of users to be recommended includes: presetting a reference user set;
calculating the similarity between the target user and each preset reference user according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each preset reference user in the preset reference user set;
screening preset reference users from a preset reference user set according to the similarity and recommending the preset reference users to a target user;
recommending the book friends having relevance with the screened preset reference users to the target users.
In an alternative embodiment, program 310 also causes processor 302 to:
constructing a reading map containing at least one reading attribute based on the calculated similarity for each preset reference user;
and judging whether any two reading maps have the same reading attribute, and if so, recommending the book friends with the same reading attribute to the target user.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, 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. In addition, embodiments of the present invention are 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 embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention 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.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
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 steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
The invention discloses: A1. a book friend recommendation method comprising:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring a user set to be recommended and reading data of at least one dimension of each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to a target user.
A2. The method of a1, wherein the reading data for the at least one dimension includes: reading the marking data; the reading mark data includes: comment information, comments, and/or ideas specifying the content of the passage;
the obtaining of the set of users to be recommended and the reading data of at least one dimension of each user to be recommended in the set of users to be recommended further includes:
acquiring a user set to be recommended corresponding to the specified paragraph content and reading mark data of each user to be recommended in the user set to be recommended;
the calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended further comprises:
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user intention identification result to be recommended.
A3. The method of a1, wherein the reading data for the at least one dimension includes: reading the marking data; the reading mark data includes: specifying comment information and/or ideas for the electronic book;
the obtaining of the set of users to be recommended and the reading data of at least one dimension of each user to be recommended in the set of users to be recommended further includes:
acquiring a set of users to be recommended corresponding to a specified electronic book and reading mark data of each user to be recommended in the set of users to be recommended;
the calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended further comprises:
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user intention identification result to be recommended.
A4. The method of any one of a1-A3, wherein the reading data for at least one dimension further comprises: reading behavior data; the reading behavior data comprises one or more of the following data: book type, reading duration, reading time point, designated chapter content and/or reading frequency of paragraph content.
A5. The method according to any one of A1-A4, wherein after filtering out book-friend recommendations from the set of users to be recommended to target users according to similarity, the method further comprises: and determining an electronic book to be recommended according to the reading history data of the recommending book friends, and recommending the electronic book to be recommended to a target user.
A6. The method of any of A1-A5, wherein the set of users to be recommended includes: presetting a reference user set;
the calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended further comprises:
calculating the similarity between the target user and each preset reference user according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each preset reference user in a preset reference user set;
the step of screening book friends from the user set to be recommended according to the similarity and recommending the book friends to a target user further comprises the following steps:
screening preset reference users from the preset reference user set according to the similarity and recommending the preset reference users to target users;
the method further comprises the following steps: recommending the book friends having relevance with the screened preset reference users to the target users.
A7. The method of a6, wherein the method further comprises: constructing a reading map containing at least one reading attribute based on the calculated similarity for each preset reference user;
and judging whether any two reading maps have the same reading attribute, and if so, recommending the book friends with the same reading attribute to the target user.
B8. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring a user set to be recommended and reading data of at least one dimension of each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to a target user.
B9. The computing device of B8, wherein the reading data for the at least one dimension includes: reading the marking data; the reading mark data includes: comment information, comments, and/or ideas specifying the content of the passage;
the executable instructions further cause the processor to:
acquiring a user set to be recommended corresponding to the specified paragraph content and reading mark data of each user to be recommended in the user set to be recommended;
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user intention identification result to be recommended.
B10. The computing device of B8, wherein the reading data for the at least one dimension includes: reading the marking data; the reading mark data includes: specifying comment information and/or ideas for the electronic book;
the executable instructions further cause the processor to:
acquiring a set of users to be recommended corresponding to a specified electronic book and reading mark data of each user to be recommended in the set of users to be recommended;
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user intention identification result to be recommended.
B11. The computing device of any one of B8-B10, wherein the reading data for at least one dimension further comprises: reading behavior data; the reading behavior data comprises one or more of the following data: book type, reading duration, reading time point, designated chapter content and/or reading frequency of paragraph content.
B12. The computing device of any one of B8-B11, wherein the executable instructions further cause the processor to:
and determining an electronic book to be recommended according to the reading history data of the recommending book friends, and recommending the electronic book to be recommended to a target user.
B13. The computing device of any one of B8-B12, wherein the set of users to be recommended includes: presetting a reference user set;
the executable instructions further cause the processor to:
calculating the similarity between the target user and each preset reference user according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each preset reference user in a preset reference user set;
screening preset reference users from the preset reference user set according to the similarity and recommending the preset reference users to target users;
recommending the book friends having relevance with the screened preset reference users to the target users.
B14. The computing device of B13, wherein the executable instructions further cause the processor to:
constructing a reading map containing at least one reading attribute based on the calculated similarity for each preset reference user;
and judging whether any two reading maps have the same reading attribute, and if so, recommending the book friends with the same reading attribute to the target user.
C15. A computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring a user set to be recommended and reading data of at least one dimension of each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to a target user.
C16. The computer storage medium of C15, wherein the reading data for the at least one dimension comprises: reading the marking data; the reading mark data includes: comment information, comments, and/or ideas specifying the content of the passage;
the executable instructions further cause the processor to:
acquiring a user set to be recommended corresponding to the specified paragraph content and reading mark data of each user to be recommended in the user set to be recommended;
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user intention identification result to be recommended.
C17. The computer storage medium of C15, wherein the reading data for the at least one dimension comprises: reading the marking data; the reading mark data includes: specifying comment information and/or ideas for the electronic book;
the executable instructions further cause the processor to:
acquiring a set of users to be recommended corresponding to a specified electronic book and reading mark data of each user to be recommended in the set of users to be recommended;
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user intention identification result to be recommended.
C18. The computer storage medium of any one of C15-C17, wherein the reading data for at least one dimension further comprises: reading behavior data; the reading behavior data comprises one or more of the following data: book type, reading duration, reading time point, designated chapter content and/or reading frequency of paragraph content.
C19. The computer storage medium of any one of C15-C18, wherein the executable instructions further cause the processor to:
and determining an electronic book to be recommended according to the reading history data of the recommending book friends, and recommending the electronic book to be recommended to a target user.
C20. The computer storage medium of any one of C15-C19, wherein the set of users to be recommended includes: presetting a reference user set;
the executable instructions further cause the processor to:
calculating the similarity between the target user and each preset reference user according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each preset reference user in a preset reference user set;
screening preset reference users from the preset reference user set according to the similarity and recommending the preset reference users to target users;
recommending the book friends having relevance with the screened preset reference users to the target users.
C21. The computer storage medium of C20, wherein the executable instructions further cause the processor to:
constructing a reading map containing at least one reading attribute based on the calculated similarity for each preset reference user;
and judging whether any two reading maps have the same reading attribute, and if so, recommending the book friends with the same reading attribute to the target user.
Claims (10)
1. A book friend recommendation method comprising:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring a user set to be recommended and reading data of at least one dimension of each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to a target user.
2. The method of claim 1, wherein the reading data for the at least one dimension comprises: reading the marking data; the reading mark data includes: comment information, comments, and/or ideas specifying the content of the passage;
the obtaining of the set of users to be recommended and the reading data of at least one dimension of each user to be recommended in the set of users to be recommended further includes:
acquiring a user set to be recommended corresponding to the specified paragraph content and reading mark data of each user to be recommended in the user set to be recommended;
the calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended further comprises:
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user intention identification result to be recommended.
3. The method of claim 1, wherein the reading data for the at least one dimension comprises: reading the marking data; the reading mark data includes: specifying comment information and/or ideas for the electronic book;
the obtaining of the set of users to be recommended and the reading data of at least one dimension of each user to be recommended in the set of users to be recommended further includes:
acquiring a set of users to be recommended corresponding to a specified electronic book and reading mark data of each user to be recommended in the set of users to be recommended;
the calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended further comprises:
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user intention identification result to be recommended.
4. The method of any one of claims 1-3, wherein the reading data for at least one dimension further comprises: reading behavior data; the reading behavior data comprises one or more of the following data: book type, reading duration, reading time point, designated chapter content and/or reading frequency of paragraph content.
5. The method according to any one of claims 1-4, wherein after filtering out book-friend recommendations from the set of users to be recommended to target users according to similarity, the method further comprises: and determining an electronic book to be recommended according to the reading history data of the recommending book friends, and recommending the electronic book to be recommended to a target user.
6. The method according to any one of claims 1-5, wherein the set of users to be recommended includes: presetting a reference user set;
the calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended further comprises:
calculating the similarity between the target user and each preset reference user according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each preset reference user in a preset reference user set;
the step of screening book friends from the user set to be recommended according to the similarity and recommending the book friends to a target user further comprises the following steps:
screening preset reference users from the preset reference user set according to the similarity and recommending the preset reference users to target users;
the method further comprises the following steps: recommending the book friends having relevance with the screened preset reference users to the target users.
7. The method of claim 6, wherein the method further comprises: constructing a reading map containing at least one reading attribute based on the calculated similarity for each preset reference user;
and judging whether any two reading maps have the same reading attribute, and if so, recommending the book friends with the same reading attribute to the target user.
8. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring a user set to be recommended and reading data of at least one dimension of each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to a target user.
9. The computing device of claim 8, wherein the reading data for the at least one dimension comprises: reading the marking data; the reading mark data includes: comment information, comments, and/or ideas specifying the content of the passage;
the executable instructions further cause the processor to:
acquiring a user set to be recommended corresponding to the specified paragraph content and reading mark data of each user to be recommended in the user set to be recommended;
semantic analysis is respectively carried out on the reading mark data of the target user and the reading mark data of each user to be recommended, and an intention identification result of the target user and an intention identification result of each user to be recommended are determined;
and calculating the similarity between the target user and each user to be recommended according to the target user intention identification result and each user intention identification result to be recommended.
10. A computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to:
determining a target user, and acquiring reading data of at least one dimension of the target user;
acquiring a user set to be recommended and reading data of at least one dimension of each user to be recommended in the user set to be recommended;
calculating the similarity between the target user and each user to be recommended according to the reading data of at least one dimension of the target user and the reading data of at least one dimension of each user to be recommended;
and screening book friends from the user set to be recommended according to the similarity and recommending the book friends to a target user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010608747.0A CN111782946A (en) | 2020-06-30 | 2020-06-30 | Book friend recommendation method, calculation device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010608747.0A CN111782946A (en) | 2020-06-30 | 2020-06-30 | Book friend recommendation method, calculation device and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111782946A true CN111782946A (en) | 2020-10-16 |
Family
ID=72761243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010608747.0A Pending CN111782946A (en) | 2020-06-30 | 2020-06-30 | Book friend recommendation method, calculation device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111782946A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114021013A (en) * | 2021-11-04 | 2022-02-08 | 海信集团控股股份有限公司 | Book friend recommendation method, server and system |
| CN114218490A (en) * | 2021-12-17 | 2022-03-22 | 海信集团控股股份有限公司 | Book recommendation method and electronic equipment |
-
2020
- 2020-06-30 CN CN202010608747.0A patent/CN111782946A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114021013A (en) * | 2021-11-04 | 2022-02-08 | 海信集团控股股份有限公司 | Book friend recommendation method, server and system |
| CN114218490A (en) * | 2021-12-17 | 2022-03-22 | 海信集团控股股份有限公司 | Book recommendation method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108153901B (en) | Knowledge graph-based information pushing method and device | |
| CN108121795B (en) | User behavior prediction method and device | |
| JP6759844B2 (en) | Systems, methods, programs and equipment that associate images with facilities | |
| JP5350472B2 (en) | Product ranking method and product ranking system for ranking a plurality of products related to a topic | |
| JP6177871B2 (en) | Disclosure of product information | |
| TWI743773B (en) | Method and device for identifying abnormal collection behavior based on privacy data protection | |
| CN110543592B (en) | Information searching method and device and computer equipment | |
| US20240029086A1 (en) | Discovery of new business openings using web content analysis | |
| WO2019169978A1 (en) | Resource recommendation method and device | |
| EP3739470A1 (en) | Method and apparatus for performing categorised matching of videos, and selection engine | |
| CN111125566B (en) | Information acquisition method and device, electronic equipment and storage medium | |
| US20200401639A1 (en) | Personalizing a search query using social media | |
| CN111125376B (en) | Knowledge graph generation method and device, data processing equipment and storage medium | |
| CN112182391A (en) | User portrait drawing method and device | |
| CN108959550B (en) | User focus mining method, device, equipment and computer readable medium | |
| CN111782946A (en) | Book friend recommendation method, calculation device and computer storage medium | |
| CN105989066A (en) | Information processing method and device | |
| CN111131419A (en) | Information pushing method and server based on book pages | |
| US9442918B2 (en) | Perspective data management for common features of multiple items | |
| CN109688178B (en) | Recommendation method, device and equipment | |
| CN110889073B (en) | Page request response method, server and computer storage medium | |
| CN110515929B (en) | Book display method, computing device and storage medium | |
| CN111639269A (en) | Site recommendation method and device | |
| CN112685618A (en) | User feature identification method and device, computing equipment and computer storage medium | |
| CN110895587A (en) | Method and device for determining target user |
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 |