CN114117225A

CN114117225A - Book recommendation method and book recommendation equipment

Info

Publication number: CN114117225A
Application number: CN202111435960.7A
Authority: CN
Inventors: 刘利明; 刘石勇
Original assignee: Hisense Group Holding Co Ltd
Current assignee: Hisense Group Holding Co Ltd
Priority date: 2021-11-29
Filing date: 2021-11-29
Publication date: 2022-03-01

Abstract

The application discloses a book recommendation method and book recommendation equipment, and relates to the technical field of book recommendation. The book recommendation device can determine the reference user image information with the highest similarity to the target user image information and can determine the reference image information group with the highest similarity to the target user image information. Thereafter, the book recommendation device may determine a recommended book based on the books that the user indicated by the reference user profile information has read and the books that the user indicated by each user profile information in the profile information group has read. Therefore, the method provided by the application can combine the reference user portrait information with the highest similarity with the target user portrait information and the reference portrait information group with the highest similarity with the target user portrait information to determine the recommended book, so that the determined recommended book can be ensured to be comprehensive and better accord with the reading interest of the target user.

Description

Book recommendation method and book recommendation equipment

Technical Field

The application relates to the technical field of book recommendation, in particular to a book recommendation method and book recommendation equipment.

Background

The user can read the book through the mobile terminal. The mobile terminal can recommend books to the user through the books which are read by the user, so that the user has better reading experience.

In the related art, the mobile terminal may determine the type of book in which the user is most interested from the books that the user has read. The mobile terminal may then recommend that type of book to the user.

However, the book recommendation method in the related art recommends a book that is not comprehensive enough.

Disclosure of Invention

The application provides a book recommendation method and book recommendation equipment, which can solve the problem that books recommended by the book recommendation method in the related art are not comprehensive enough. The technical scheme is as follows:

in one aspect, a book recommendation apparatus is provided, the book recommendation apparatus comprising: a processor; the processor is configured to:

acquiring target user portrait information of a target user, wherein the target user is a user of a book to be recommended, and the target user portrait information comprises reading interest information of the target user;

determining, from a plurality of user profile information, a first reference user profile information that is different from the target user profile information and has a highest similarity based on the target user profile information;

determining a first reference profile information group with highest similarity to the target user profile information from a plurality of profile information groups based on the target user profile information, the plurality of profile information groups being clustered with the plurality of user profile information;

determining a first alternative book based on the historical reading information of the user indicated by the first reference user portrait information, and determining a second alternative book based on the historical reading information of the user indicated by each user portrait information in the first reference portrait information group;

and determining a recommended book based on the first alternative book and the second alternative book.

On the other hand, a book recommendation method is provided, which is applied to book recommendation equipment; the method comprises the following steps:

Optionally, the determining a recommended book based on the first candidate book and the second candidate book includes:

determining a third alternative book associated with each first alternative book and determining a fourth alternative book associated with each second alternative book;

and determining a recommended book based on the first alternative book, the second alternative book, the third alternative book and the fourth alternative book.

Optionally, the determining a recommended book based on the first candidate book, the second candidate book, the third candidate book, and the fourth candidate book includes:

determining the read books which have been read by the target user based on the historical reading information of the target user;

determining books except the read book in the first, second, third and fourth alternative books as recommended books.

and determining the books except the read book in the first alternative book and the second alternative book as recommended books.

Optionally, after determining the recommended book based on the first candidate book and the second candidate book, the method further includes:

in response to a reading planning request for a target book of at least one of the recommended books, determining alternative user portrait information of at least one user who has read the target book from the plurality of user portrait information, and determining at least one alternative portrait information group from the plurality of portrait information groups, each alternative portrait information group including at least one alternative user portrait information;

determining the time length, indicated by second reference user portrait information, of the at least one piece of alternative user portrait information, for the user to finish reading the target book, as a first reference time length, where the second reference user portrait information is the alternative user portrait information with the highest similarity to the target user portrait information in the at least one piece of alternative user portrait information;

determining an average value of time lengths used by users indicated by the at least one alternative user portrait information in a second reference portrait information group to finish reading the target book, as a second reference time length, wherein the second reference portrait information group is a candidate portrait information group with the highest similarity to the target user portrait information in the at least one alternative portrait information group;

and determining the estimated reading time of the target book based on the first reference time and the second reference time, wherein the estimated reading time is positively correlated with the first reference time and the second reference time.

Optionally, the determining the estimated reading time of the target book based on the first reference time and the second reference time includes:

and carrying out weighted summation on the first reference time length and the second reference time length to obtain the estimated reading time length of the target book.

Optionally, before the weighted summation of the first reference time length and the second reference time length is performed to obtain the estimated reading time length of the target book, the method further includes:

determining a first weight for the first reference duration and a second weight for the second reference duration based on a first similarity of the target user portrait information to the second reference user portrait information and a second similarity of the target user portrait information to the group of second reference portrait information;

wherein the first weight is positively correlated with the first similarity and negatively correlated with the sum of the similarities, the second weight is positively correlated with the second similarity and negatively correlated with the sum of the similarities, and the sum of the similarities is the sum of the first similarity and the second similarity.

Optionally, the similarity between each portrait information group and the target user portrait information is as follows:

and the average value of the similarity between each user portrait information in the portrait information group and the target user portrait information.

In still another aspect, there is provided a book recommendation apparatus including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the book recommendation method as described in the above aspect when executing the computer program.

In still another aspect, there is provided a computer-readable storage medium having a computer program stored therein, the computer program being loaded and executed by a processor to implement the book recommendation method according to the above aspect.

In yet another aspect, a computer program product containing instructions is provided, which when run on the computer, causes the computer to perform the book recommendation method of the above aspect.

The beneficial effect that technical scheme that this application provided brought includes at least:

the application provides a book recommendation method and book recommendation equipment, and the book recommendation equipment can determine reference user image information with the highest similarity to target user image information and can determine a reference image information group with the highest similarity to the target user image information. Thereafter, the book recommendation device may determine a recommended book based on the books that the user indicated by the reference user profile information has read and the books that the user indicated by each user profile information in the profile information group has read. Therefore, the method provided by the application can combine the reference user portrait information with the highest similarity with the target user portrait information and the reference portrait information group with the highest similarity with the target user portrait information to determine the recommended book, so that the determined recommended book can be ensured to be comprehensive and better accord with the reading interest of the target user.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a flow chart of a book recommendation method provided in an embodiment of the present application;

FIG. 2 is a schematic structural diagram of a system to which a book recommendation method provided in the embodiments of the present application is applicable;

FIG. 3 is a flow chart of another book recommendation method provided in the embodiments of the present application;

fig. 4 is a schematic view of an interface from sending a book recommendation request to displaying an estimated reading duration of a target book by a mobile terminal according to an embodiment of the present application;

FIG. 5 is a diagram illustrating a method for determining recommended books according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a book recommendation device according to an embodiment of the present application;

fig. 7 is a block diagram of a software structure of a book recommendation device according to an embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

The embodiment of the application provides a book recommendation method which can be applied to book recommendation equipment. Optionally, the book recommendation device may be a mobile terminal or a server. The mobile terminal can be provided with a reading application, and can be a mobile phone, a tablet computer or a notebook computer. The server may be a server, or may be a server cluster composed of several servers, or may be a cloud computing service center. Referring to fig. 1, the method includes:

step 101, obtaining the portrait information of the target user.

The target user is a user of a book to be recommended, and the user portrait information of the target user may include: reading interest information of the target user. The reading interest information may include: the level of interest of the target user for different types of books. The degree of interest may be characterized by a numerical value. Alternatively, the target user may be a student.

In this embodiment of the application, if the book recommendation device is a mobile terminal, the mobile terminal may obtain the target user portrait information of the target user after running the reading application, or after detecting that the target user reads a new book through the reading application, or after receiving a touch operation for a recommendation control displayed in an application interface of the reading application. The embodiment of the application does not limit the triggering mode of the mobile terminal for acquiring the portrait information of the target user.

If the book recommendation device is a server and the server can be connected to the mobile terminal as shown in fig. 2, the server can obtain the target portrait information of the target user after receiving the book recommendation request sent by the mobile terminal. The triggering mode of sending the book recommendation request by the mobile terminal may refer to the triggering mode of obtaining the portrait information of the target user by the mobile terminal, and the embodiment of the application is not described herein again.

Step 102, based on the target user portrait information, a first reference user portrait information which is different from the target user portrait information and has the highest similarity is determined from the plurality of user portrait information.

After the book recommendation device obtains the target user portrait information of the target user, the similarity between the target user portrait information and each user portrait information except the target user portrait information in the plurality of user portrait information can be determined. Then, the book recommendation device may determine, based on the plurality of similarities, the first reference user portrait information that is different from the target user portrait information and has the highest similarity.

Step 103, based on the image information of the target user, a first reference image information group with the highest similarity to the image information of the target user is determined from the plurality of image information groups.

After the book recommendation device obtains the target user portrait information of the target user, the book recommendation device can also determine the similarity between the target user portrait information and each portrait information group. Then, the book recommendation device may determine a first reference portrait information group with the highest similarity to the target user portrait information based on the plurality of similarities. The portrait information groups may be clustered by user portrait information, each portrait information group including at least two user portrait information.

And 104, determining a first alternative book based on the historical reading information of the user indicated by the first reference user portrait information, and determining a second alternative book based on the historical reading information of the user indicated by each user portrait information in the first reference portrait information group.

The historical reading information of the user may include: an identification of the book that the user has read. The identification of the book may include the name of the book. The number of the first alternative books may be one or more books (i.e., at least one book), and the number of the second alternative books may be one or more books.

And 105, determining a recommended book based on the first alternative book and the second alternative book.

In the embodiment of the application, the book recommendation device may determine the first alternative book and the second alternative book as recommended books. Namely, the book recommendation device can determine the union of the first alternative book and the second alternative book as the recommended book. Or, the book recommendation device may determine a book that is the same as the at least one first alternative book and the at least one second alternative book as the recommended book. That is, the book recommendation device may determine the intersection of the at least one first candidate book and the at least one second candidate book as the recommended book. Still alternatively, the book recommendation device may first determine a third alternative book based on the first alternative book and a fourth alternative book based on the second alternative book. Then, the book recommendation device may determine the recommended book based on the first candidate book, the second candidate book, the third candidate book, and the fourth candidate book. The number of recommended books may be one or more.

In summary, the embodiment of the present application provides a book recommendation method, where a book recommendation device can determine reference user image information with the highest similarity to target user image information, and can determine a reference image information group with the highest similarity to target user image information. Thereafter, the book recommendation device may determine a recommended book based on the books that the user indicated by the reference user profile information has read and the books that the user indicated by each user profile information in the profile information group has read. Therefore, the method provided by the embodiment of the application can combine the reference user portrait information with the highest similarity with the target user portrait information and the reference portrait information group with the highest similarity with the target user portrait information to determine the recommended book, so that the determined recommended book can be ensured to be comprehensive and better accord with the reading interest of the target user.

The book recommendation device is used as a server, the server is connected with the mobile terminal, the reading application is installed in the mobile terminal, the server is a background server of the reading application, the number of the first alternative books and the number of the second alternative books are one or more, and the book recommendation method provided by the embodiment of the application is exemplarily described. Referring to fig. 3, the method may include:

step 201, the mobile terminal sends a book recommendation request to the server.

In the embodiment of the application, the mobile terminal is provided with the reading application, and the mobile terminal can acquire the target user portrait information of the target user when the reading application starts to run, or after the target user reads a new book through the reading application is detected, or after the touch operation of the recommendation control displayed on the application interface of the reading application is received. The embodiment of the application does not limit the triggering mode of the mobile terminal for acquiring the portrait information of the target user.

Wherein, the book recommendation request may include a target user identification of the target user. The target user identification may be a user account (e.g., a cell phone number) currently logged in a reading application installed in the mobile terminal. Alternatively, the target user may be a student, and the mobile terminal may be a mobile terminal of the target user.

For example, referring to fig. 4, an application interface of an installed reading application in the mobile terminal may be displayed with a recommendation control 01. If the target user needs the mobile terminal to recommend books for the target user, the recommendation control 01 can be touched. Correspondingly, the mobile terminal can respond to the touch operation of the target user for the recommendation control 01 and send a book recommendation request to the server.

Step 202, the server responds to the book recommendation request to acquire the target user portrait information of the target user.

After receiving the book recommendation request sent by the mobile terminal, the server can respond to the book recommendation request to acquire the target user portrait information of the target user. Wherein the target user representation information may include: reading interest information of the target user. The reading interest information may include: the level of interest of the target user for different types of books. The level of interest may be characterized by a numerical value, and the numerical value may be positively correlated with the level of interest of the target user in the book. The type of book may be one of the following types: literature, science fiction, suspicion, finance, philosophy, economics, sports, and geography, among others. Accordingly, the reading interest information in the target user portrait information may be characterized by a feature vector, which may have a dimension (also referred to as a length) that is the same as the total number of types of books. And each feature value in the feature vector may represent a level of interest of the target user in a type of book.

In the embodiment of the application, the server stores the corresponding relation between the user identification and the user portrait information in advance. After receiving the recommendation request sent by the mobile terminal, the server can respond to the book recommendation request, determine user portrait information corresponding to the target user identification of the target user based on the corresponding relation, and determine the user portrait information as the target user portrait information.

Alternatively, the target user may be a student. The target user representation information of the target user may further include: reading ability information of the target user, and/or attribute information of the target user. For example, the target user representation information of the target user may further include: reading ability information of the target user, and/or attribute information of the target user. Wherein, the reading ability information may include: a value for characterizing the reading ability of the target user. The attribute information may include: attribute values of attributes of the target user. The attributes of the target user may include: the target user's age, location, school, class, and class. For example, the attributes of the target user may include: the age, the region, the school, the class and the class of the target user. The attribute values of the region may be: the region is ranked among a plurality of regions arranged in sequence, or may be a code (e.g., a zip code) for the region. The attribute values of the school may be: the school may be targeted for ranks among multiple schools in the area, or may be a code for the school.

Since the target user profile information may also include: the reading capability information of the target user and the attribute information of the target user can ensure that the recommended book determined based on the portrait information of the target user can be matched with the reading capability and the attribute of the user, so that the matching degree of the determined recommended book and the target user is high, and the user experience is good.

In the embodiment of the present application, the reading interest information and the reading capability information of the target user may be determined based on the book that the target user has read. The attribute information of the target user may be acquired by the mobile terminal in response to an input operation by the user and transmitted to the server. The server can acquire the reading interest information of the target user through the following optional implementation modes:

in a first optional implementation manner, the mobile terminal may determine, based on the books that the target user has read, reading interest information and reading capability information of the target user, and send the reading interest information and the reading capability information to the server. Correspondingly, the server can acquire the reading interest information and the reading capability information of the target user.

In the embodiment of the application, for each book that the target user has read, the mobile terminal may determine the type of the book and determine the interest level of the target user in the book. Then, for each type, the mobile terminal may count the total number of the at least one book that the target user has read and belongs to the type, and determine the average value of the interest level of the target user in the at least one book as the interest level of the user in the type of book.

In the embodiment of the present application, the interest level of a user in a book is generally related to the reading time and the reading times of the user reading the book. And the interest level is positively correlated with the reading time length and the reading times. That is, the longer the reading time, the higher the user's interest level in the book, and the more the reading times, the higher the user's interest level in the book.

Wherein, the reading duration may refer to: the time length used by the user for reading the book each time can be the time length obtained after the mobile terminal starts timing when the content of the book is displayed each time and the timing is finished. The number of reads may be: the sum of the historical reading times and the value 1, the historical reading times may be: before the contents of the book are displayed this time, the target user reads the history times of the book.

Based on the method, the mobile terminal can count the reading time and the reading times of the target user for reading a book. Then, the mobile terminal may determine the interest level of the user in the book based on the reading duration and the reading times. For example, the server may determine, as the degree of interest of the user for the book, the degree of interest corresponding to the reading duration and the reading number based on the correspondence between the duration and the number of times and the degree of interest. Or, the server may input the reading duration and the reading times into a pre-trained interest level detection model, so as to obtain the interest level of the user for the book output by the interest level detection model, and then obtain a feature vector for representing the reading interest information of the target user. It should be noted that, before determining the feature vector, the mobile terminal may set various types of ranking order of the books.

Optionally, in a scenario that the mobile terminal needs to respond to the page turning operation of the target user and display different contents, if the mobile terminal does not receive the page turning operation within the target duration after receiving the previous page turning operation of the target user, the timing may be ended. That is, the mobile terminal may end the timing without turning pages for a long time by the target user. In this way, the accuracy of the determined reading duration can be ensured. The target time duration may be determined by the mobile terminal based on the page turning interval duration of the target user, for example, may be an average value of a plurality of page turning interval durations. The page turning interval duration may be an interval duration between a previous page turning operation and a subsequent page turning operation.

Optionally, if the mobile terminal finishes timing because the page turning operation is not received within the target time length after receiving the previous page turning operation of the target user, the mobile terminal may determine the difference between the timing time length and the target time length as the reading time length for the target user to read the book this time. That is, in the case that the target user does not turn pages for a long time, the mobile terminal may determine a time period from the start of displaying the contents of the book to the completion of displaying the contents of the previous page as the reading time period. Therefore, the accuracy of the determined reading time length can be ensured, and the accuracy of the determined interest degree of the target user in the book can be further ensured to be higher.

Optionally, after determining that the timing duration is greater than the duration threshold, the mobile terminal may update the reading times of the book to the sum of the historical reading times and the value 1. Therefore, the problem that the counted reading times are wrong due to misoperation of the target user can be avoided, and the accuracy of the determined reading information can be ensured.

In the embodiment of the application, the reading speeds of different users are different, which results in that the time length for reading the book is different for a plurality of users with the same interest level in the same book. Therefore, if the reading time of the target user for reading the book is directly adopted, the interest degree of the target user for the book is determined, and the accuracy of the determined interest degree may be low. Therefore, in the embodiment of the present application, the mobile terminal may determine the interest level of the target user in the book based on the ratio of the reading time length to the average reading time length. Thus, the accuracy of the determined interest degree of the target user for the book can be ensured to be higher. Wherein, the average reading time length may refer to: the average of the multiple reading durations of the target user reading the book multiple times.

In a second optional implementation manner, the mobile terminal may count the reading times and the reading duration of the target user for a certain book, and send the reading times and the reading duration to the server. After receiving the reading times and the reading duration, the server may determine the interest level of the target user in the book based on the reading times and the reading duration.

The server determines the interest level of the target user in the book based on the reading times and the reading duration, and may refer to the mobile terminal to determine the interest level of the target user in the book.

In this embodiment of the present application, the process that the server may obtain the reading capability information of the target user may include: the mobile terminal sends a test question acquisition request to the server after determining that the target user finishes reading a certain chapter of the book or determining that the target user finishes reading the book. The server can respond to the test question acquisition request sent by the mobile terminal and send the test questions aiming at the book to the mobile terminal. After the mobile terminal receives the test questions, the test questions can be displayed. Then, the mobile terminal can respond to the answering operation of the user, obtain the answering result and send the answering result to the server. After receiving the answer result, the server can compare the answer result with the answer of the test question to obtain the answer score of the target user, and determine the numerical value for representing the reading capability of the target user based on the answer score. The value is positively correlated with the answer score.

Optionally, the test questions may be set from multiple dimensions. The plurality of dimensions may be at least two of the following dimensions: information extraction, contact inference, analysis summarization, application comprehension and appreciation evaluation. For example, referring to fig. 5, the plurality of dimensions may include: information extraction, contact inference, analysis summarization, application of comprehension, appreciation evaluation and the like.

Because the test questions are set from multiple dimensions, the test comprehensiveness can be ensured to be higher, and the accuracy of the reading capability of the determined target user can be ensured to be higher.

In step 203, the server identifies, from the plurality of user profile information, a first reference user profile information having a highest similarity and different from the target user profile information, based on the target user profile information.

After the server obtains the target user representation information of the target user, the server may determine a similarity between the target user representation information and each of the plurality of user representation information (hereinafter referred to as other user representation information for convenience of description) other than the target user representation information. The server may then determine, based on the plurality of similarities, a first reference user representation that is different from the target user representation and has a highest similarity.

In this embodiment, for each piece of other user portrait information, the server may process the target user portrait information and the other user portrait information using a similarity calculation formula, so as to obtain a similarity between the target user portrait information and the other user portrait information.

In addition, if the target user image information includes: reading interest information, reading ability information and attribute information of the target user, and then the portrait information of each other user also comprises: reading interest information, reading ability information and attribute information of other users. The sequence of arrangement of the three pieces of information in the target user image information is the same as the sequence of arrangement of the three pieces of information in the other user image information.

Alternatively, the similarity calculation formula may be a pearson calculation formula. The similarity r between the target user profile information and any other user profile information determined using the pilson equation satisfies the following equation:

in formula (1), n is the total number of information included in each user portrait information, and n is an integer of 1 or more. For example, if each user profile information includes: and if the reading interest information, the reading capability information and the attribute information exist, n is 3. X_iThe ith information in the target user portrait information.

The average value of n pieces of information included in the target user profile information is obtained. Y is_iFor the ith message in the any other user representation message,

the average of the n pieces of information included in the any other user profile information is used.

Optionally, the server may perform normalization processing on the target user portrait information and any other user portrait information before determining the similarity between the target user portrait information and any other user portrait information by using a similarity calculation formula. The server may then process the normalized target user portrait information and any user portrait information based on a similarity calculation formula, thereby obtaining a similarity between the target user portrait information and any user portrait information. In this way, the accuracy of the determined similarity can be ensured. The ith information after normalization processing meets the following formula:

in the formula (2), maxX_iThe maximum value is the ith information among the plurality of user portrait information.

In step 204, the server determines a first reference image information group having the highest similarity to the target user image information from the plurality of image information groups based on the target user image information.

After the server acquires the target user portrait information of the target user, the similarity between the target user portrait information and each portrait information group can be determined. The server may then determine a first group of reference image information with the highest similarity to the target user image information based on the plurality of similarities. The portrait information groups may be clustered with respect to user portrait information, and each portrait information group may include at least two user portrait information.

In this embodiment, the similarity between each portrait information group and the target user portrait information may refer to: the average value of the similarity between each user image information in the image information group and the target user image information. That is, for each image information group, the server may determine the similarity between each user image information in the image information group and the target user image information, and obtain a plurality of similarities. Then, the server determines the average value of the similarity as the similarity between the portrait information group and the portrait information of the target user.

Alternatively, the similarity between each portrait information group and the target user portrait information may be: the similarity between the central user portrait information and the target user portrait information in the portrait information group.

In this embodiment, before determining the first reference portrait information group with the highest similarity to the target user portrait information from the plurality of portrait information groups, the server may perform clustering processing on the plurality of user portrait information by using a clustering algorithm to obtain the plurality of portrait information groups. Optionally, the clustering algorithm may be a K-center clustering algorithm. The server adopts a K-center clustering algorithm to cluster a plurality of user portrait information to obtain a plurality of portrait information groups, and the process is as follows:

the server may randomly determine K initial central user profile information. And for each remaining user profile information of the plurality of user profile information other than the K initial central user profile information, the server may determine a similarity of the remaining user profile information to each initial central user profile information of the K initial central user profile information. The server may then, for each remaining user profile information, partition the remaining user profile information into an initial profile information group corresponding to the initial central user profile information having the highest similarity to the remaining user profile information. Wherein, the central user portrait information of the initial portrait information group corresponding to any initial central user portrait information is any initial central user portrait information. K is pre-stored in the server.

For each initial portrait information group, the server may repeat the initial central user portrait information update procedure until the initial portrait information group converges, thereby obtaining multiple portrait information groups. Wherein convergence means that the similarity between the user image information in the initial image group is small. The initial central user profile information update process may include: the server repeatedly performs the operations of updating the initial central user portrait information of the initial portrait information group to one remaining user portrait information of the plurality of remaining user portrait information and determining an update cost until an end condition is satisfied. The server may then update the remaining user representation information with the least update cost to the initial central user representation information. Wherein the update cost can be represented by a cost function. The termination condition may be: each remaining user representation information of the plurality of remaining user representation information was updated to the initial central user representation information.

In the embodiment of the present application, the target user is a student, and the portrait information of the target user includes: attribute information of the target user, and the attribute information includes: the server clusters a plurality of user portrait information by adopting a K-center clustering algorithm to obtain each user portrait information group, wherein each user portrait information group is composed of user portrait information of students of one class. That is, the user portrait information of students of the same class can be clustered to one user portrait information group through the K-center clustering algorithm. As the reading abilities of students in the same class are equivalent and the reading interests are similar, the determined recommended books can be ensured to be high in reasonability and accuracy.

Step 205, the server determines at least one first candidate book based on the historical reading information of the user indicated by the first reference portrait information, and determines at least one second candidate book based on the historical reading information of the user indicated by each user portrait information in the first reference portrait information group.

The historical reading information of the user may include: an identification of the book that the user has read. The identification of the book may include the name of the book.

In the embodiment of the application, the server also stores the corresponding relation between the user portrait information and the historical reading information. After determining the first reference user profile information and the first reference profile information group, the server may obtain historical reading information corresponding to the first reference user profile information and historical reading information corresponding to each user profile information in the first reference profile information group based on the correspondence. Then, the server may determine at least one book indicated by the identifier of at least one book in the historical reading information corresponding to the first reference user portrait information as at least one first candidate book, and determine at least one book indicated by the identifier of at least one book in each historical reading information corresponding to each user portrait information in the first reference portrait information group as at least one second candidate book.

And step 206, the server determines at least one recommended book based on the at least one first alternative book and the at least one second alternative book.

In a first optional implementation manner, the server may determine at least one of the first candidate book and the second candidate book as at least one of the recommended books. Namely, the server can determine the union of at least one first alternative book and at least one second alternative book as at least one recommended book.

In a second alternative implementation manner, the server may determine that the same book in the at least one first alternative book and the at least one second alternative book is the at least one recommended book. That is, the server may determine the intersection of at least one first candidate book and at least one second candidate book as at least one recommended book.

In a third optional implementation manner, the server may determine at least one third alternative book based on each first alternative book, and determine at least one fourth alternative book based on each second alternative book. Then, the server can determine at least one recommended book based on at least one first alternative book, at least one second alternative book, at least one third alternative book and at least one fourth alternative book.

Optionally, the server may determine at least one first alternative book, at least one second alternative book, at least one third alternative book, and at least one fourth alternative book as the at least one recommended book. Or, the server may determine the same book among at least one first alternative book, at least one second alternative book, at least one third alternative book, and at least one fourth alternative book as the at least one recommended book.

In this embodiment of the application, for any one of the three implementation manners, the server may determine the read book that the target user has read based on the historical reading information of the target user. Then, the server can determine at least one initial recommended book except the read book in the at least one initial recommended book as the at least one recommended book. That is, the server can filter out the books that the target user has read from at least one initially recommended book, so as to obtain at least one recommended book. Therefore, books read by the target user can be prevented from being recommended to the target user, and the user experience of the target user is effectively improved.

In a first optional implementation manner, at least one initially recommended book includes: at least one first alternative book and at least one second alternative book. In a second alternative implementation manner, at least one of the initially recommended books includes: the book in the at least one first alternative book and the book in the at least one second alternative book are the same. In a third optional implementation manner, at least one of the initially recommended books includes: at least one first alternative book, at least one second alternative book, at least one third alternative book and at least one fourth alternative book. Or, at least one of the initially recommended books includes: the book is the same among at least one first alternative book, at least one second alternative book, at least one third alternative book and at least one fourth alternative book.

Optionally, the server may further obtain the book being read by the target user, the book scheduled to be read and not started to be read, and filter the book being read by the target user and the book scheduled to be read and not started to be read from the at least one initially recommended book, so as to obtain the at least one recommended book. Wherein, books which are planned to be read and do not start to be read can refer to: the server has generated a book reading plan for books that the target user has not yet read. Thus, the user experience of the target user can be further improved.

In this embodiment of the application, the server may determine, from the plurality of books, at least one third alternative book associated with each first alternative book and determine, from the plurality of books, at least one fourth alternative book associated with each second alternative book by using a type-based recommendation method. Thus, the determined type of each third alternative book is the same as that of the first alternative book, and the determined type of each fourth alternative book is the same as that of the second alternative book. The plurality of books may be books recommended by the education department.

Or, the server may determine at least one third alternative book associated with each first alternative book from the plurality of books and determine at least one fourth alternative book associated with each second alternative book from the plurality of books by using a content-based recommendation method. Thus, each determined third alternative book has the same content keywords as the first alternative book, and each determined fourth alternative book has the same content keywords as the second alternative book. Because the books determined by the content-based recommendation method are comprehensive, the recommended books determined by the server provided by the embodiment of the application are comprehensive, multi-dimensional reading of the target user can be ensured, and user experience is improved.

For example, assume that the plurality of user pictorial information includes: user portrait information of student A, user portrait information of student B, and user portrait information of student C. Student A has read book a and book C, student B has read book d, and student C has read book d. The plurality of portrait information groups include: group A, group B, and group C. The books read by group a include: books c, which are read by group B, include: book d, the books read by group C include: book a and book b. The target user has read book d.

Suppose that the user image information having the highest similarity to the target user image information is the user image information of student B, and the image information group having the highest similarity to the target user image information is the image information group of group A. The server determines at least one first book candidate comprising: book d, at least one second alternative book includes: and c, books.

Assume that the at least one third alternative book associated with book d determined by the server comprises: and the book e and the book f, and at least one fourth alternative book related to the book c comprises: book e and book g. Referring to fig. 5, the server determines at least one recommended book including: book c, book e, book f, and book g.

And step 207, the server sends the identification of at least one recommended book to the mobile terminal.

And after obtaining the at least one recommended book, the server can send the identification of the at least one recommended book to the mobile terminal. Wherein, the identifier of each recommended book may include: the name of the book is recommended.

Optionally, the identification of each recommended book may further include: the name of the author of the book is recommended.

And step 208, displaying the identification of at least one recommended book by the mobile terminal.

After the mobile terminal receives the identification of the recommended book sent by the server, the identification of the recommended book can be displayed, so that the effect of recommending the book to the user is achieved.

Optionally, the mobile terminal may display the identifier of at least one recommended book in a list form.

For example, assume that at least one recommended book includes: the mobile terminal displays the at least one recommended book in a list form, and the mobile terminal can display the interface shown in fig. 4 after receiving the touch operation of the target user on the recommendation control 01.

As can be seen from fig. 4, the mobile terminal may further display the name of the author of each recommended book, so that the target user can know more information of the recommended books, and the user experience is improved.

And step 209, the mobile terminal sends a reading planning request aiming at the target book in at least one recommended book to the server.

If the mobile terminal receives the selection operation of the target user for the identifier of the target book in the displayed at least one recommended book, the mobile terminal can send a reading planning request for the target book to the server. The reading planning request may carry an identifier of the target book.

For example, continuing to refer to fig. 4, assuming that the target user needs the mobile terminal to display the estimated reading duration of the book g, the target user may select the book g. Accordingly, the mobile terminal can respond to the selection operation of the target user for the book g and send a reading planning request for the book g to the server.

Step 210, the server determines, in response to the reading planning request, candidate user portrait information for at least one user who has read the target book from the plurality of user portrait information, and determines at least one candidate portrait information group from the plurality of portrait information groups.

Wherein each group of alternate representation information includes at least one alternate user representation information.

In the embodiment of the application, the server stores the corresponding relation between the user portrait information and the historical reading information of the user. And the historical reading information of the user who read the target book may include: identification of the target book. After receiving the reading planning request for the target book, the server may filter out at least one target historical reading information including the identifier of the target book from the stored plurality of historical reading information. The server may then determine user representation information corresponding to each target historical reading information as candidate user representation information, thereby obtaining at least one candidate user representation information. The server may then screen out a portrait information group from the plurality of portrait information groups that includes at least one candidate user portrait information to obtain at least one candidate portrait information group.

Step 211, the server determines the time length used by the user to read the target book indicated by the second reference user image information in the at least one alternative user image information as the first reference time length.

After the server screens out at least one candidate user portrait information from the plurality of user portrait information, the candidate user portrait information with the highest similarity with the target user portrait information in the at least one candidate user portrait information may be determined as second reference user portrait information. Then, the server may determine the time length, indicated by the second reference user image information, for the user to read the target book, as the first reference time length.

Optionally, the historical reading information of the user may further include: the time taken to read each book that has been read is completed. After the server determines the second reference user portrait information, historical reading information corresponding to the second reference user portrait information can be determined from the corresponding relationship between the user portrait information and the historical reading information, and then the time length used for reading the target book by the user indicated by the second reference user portrait information is obtained from the historical reading information.

In step 212, the server determines an average value of the time length for each user indicated by the at least one candidate user portrait information included in the second reference portrait information group to read the target book as a second reference time length.

After the server screens out at least one candidate portrait information group from the plurality of portrait information groups, the server may determine, as a second reference portrait information group, a candidate portrait information group with the highest similarity to the target user portrait information from the at least one candidate portrait information group. The server may then determine a length of time for which the user indicated by each of the alternative user profile information has finished reading the target book, of the at least one alternative user profile information included in the second group of reference profile information, to obtain at least one length of time. Thereafter, the server may determine an average value of the at least one time period as the second reference time period.

The process of determining the time length for the user indicated by each of the candidate user portrait information to finish reading the target book by the server may refer to the related implementation process in step 211, which is not described herein again in this embodiment of the present application.

In step 213, the server determines the estimated reading time of the target book based on the first reference time and the second reference time.

The estimated reading time length is positively correlated with the first reference time length and the second reference time length. That is, the longer the first reference time duration is, the longer the estimated reading time duration is, and the longer the second reference time duration is, the longer the estimated reading time duration is.

In an alternative implementation manner, the server may determine an average value of the first reference time length and the second reference time length as the estimated reading time length of the target book.

In another optional implementation manner, the server may perform weighted summation on the first reference time length and the second reference time length to obtain the estimated reading time length of the target book. In this way, the accuracy of the determined reading plan duration can be ensured.

In this embodiment, before the server performs weighted summation on the first reference duration and the second reference duration to obtain the estimated reading duration of the target book, the server may determine a first weight of the first reference duration and a second weight of the second reference duration based on a first similarity between the target user portrait information and the second reference user portrait information and a second similarity between the target user portrait information and the second reference portrait information group. The first weight is positively correlated with the first similarity and negatively correlated with the sum of the similarities, the second weight is positively correlated with the second similarity and negatively correlated with the sum of the similarities, and the sum of the similarities is the sum of the first similarity and the second similarity.

Alternatively, the first weight of the first reference time period may be a ratio of the first similarity to a sum of the similarities, and the second weight of the second reference time period may be a ratio of the second similarity to the sum of the similarities. That is, the first weight may satisfy the following formula (3), and the second weight may satisfy the following formula (4).

In the formulae (3) and (4), r₁For the similarity of the target user profile information and the second reference user profile information, r₂The similarity between the target user image information and the second reference image information group is determined.

Further, the server may further consider a first ratio of the reading ability of the user indicated by the second reference user profile information to the reading ability of the target user in determining the first weight, and may also consider a second ratio of an average of the reading abilities of the users indicated by the at least one alternative user profile information to the reading ability of the target user in the second reference profile information group in determining the second weight. The first weight and the first ratio can be positively correlated, and the second weight and the second ratio can be positively correlated. Based on this, it may be determined that the first weight may satisfy the following equation (5) and the second weight may satisfy the following equation (6).

In the formulae (5) and (6), h₂Reading ability of the user indicated by the portrait information for the second reference user, h₁In order to be the reading ability of the target user,

the average value of the reading ability of each user indicated by the at least one candidate user profile information in the second group of reference profile information.

According to the above description, in the process of determining the estimated reading duration of the target book, the server may further consider the reading capability of the target user, the reading capability of the user indicated by the second reference user portrait information, and an average value of the reading capabilities of the users indicated by at least one alternative user portrait information in the second reference portrait information group. Therefore, the estimated reading time of the determined target book can be ensured to be matched with the reading capability of the target user, and the user experience is effectively improved.

And step 214, the server sends the estimated reading time of the target book to the mobile terminal.

After determining the estimated reading time of the target book, the server can send the estimated reading time to the mobile terminal.

Step 215, the mobile terminal displays the estimated reading time of the target book.

And after receiving the estimated reading time of the target book, the mobile terminal can display the estimated reading time so that the user can know the estimated reading time of the target book.

For example, assuming that the target book is book g, and the estimated reading time of book g determined by the server is 40 hours, referring to fig. 4, the mobile terminal may display the identifier of book g, and display the reading suggestion information 02 below the identifier. The reading advice information 02 includes an estimated reading time. As shown in fig. 4, the reading suggestion information may be a text: it is recommended that reading be complete within 40 hours.

It should be noted that the order of the steps of the book recommendation method provided in the embodiment of the present application may be appropriately adjusted, and the steps may also be correspondingly increased or decreased according to the situation. For example, step 201, step 207, and step 208 may be deleted as appropriate; or steps 209 to 215 may be deleted as appropriate. Any method that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application is covered by the protection scope of the present application, and thus the detailed description thereof is omitted.

Fig. 6 is a schematic structural diagram of a book recommendation device provided in an embodiment of the present application, where the book recommendation device may be configured to execute the book recommendation method provided in the foregoing method embodiment, and referring to fig. 6, the book recommendation device 110 may include: a processor 1101, the processor 1101 configured to:

determining first reference user profile information which is different from the target user profile information and has the highest similarity from the plurality of user profile information based on the target user profile information;

determining a first reference portrait information group with the highest similarity with the target user portrait information from a plurality of portrait information groups based on the target user portrait information, wherein the portrait information groups are obtained by clustering the user portrait information;

Optionally, the processor 1101 may be configured to:

and determining the recommended book based on the first alternative book, the second alternative book, the third alternative book and the fourth alternative book.

Optionally, the processor 1101 may be configured to:

and determining books except the read book in the first, second, third and fourth alternative books as recommended books.

Optionally, the processor 1101 may be configured to:

and determining the books except the read book in the first alternative book and the second alternative book as the recommended book.

Optionally, the processor 1101 may further be configured to:

in response to a reading planning request for a target book in at least one recommended book, determining alternative user portrait information of at least one user who has read the target book from the plurality of user portrait information, and determining at least one alternative portrait information group from the plurality of portrait information groups, wherein each alternative portrait information group comprises at least one alternative user portrait information;

determining the time length used by the user for reading the target book indicated by the second reference user image information in the at least one alternative user image information as the first reference time length, wherein the second reference user image information is the alternative user image information with the highest similarity to the target user image information in the at least one alternative user image information;

determining the average value of the time length used by each user indicated by the at least one alternative user portrait information included in the second reference portrait information group for reading the target book to be a second reference time length in the at least one alternative portrait information group, wherein the second reference portrait information group is the standby portrait information group with the highest similarity to the target user portrait information in the at least one alternative portrait information group;

Optionally, the processor 1101 may be configured to:

Optionally, the processor 1101 may further be configured to:

determining a first weight for the first reference duration and a second weight for the second reference duration based on a first similarity of the target user profile information to the second reference user profile information and a second similarity of the target user profile information to the second group of reference profile information;

the first weight is positively correlated with the first similarity and negatively correlated with the sum of the similarities, the second weight is positively correlated with the second similarity and negatively correlated with the sum of the similarities, and the sum of the similarities is the sum of the first similarity and the second similarity.

Optionally, the similarity between each portrait information group and the target user portrait information is as follows: the average value of the similarity between each user image information in the image information group and the target user image information.

In summary, the present application provides a book recommendation device, which is capable of determining reference user image information with the highest similarity to target user image information and determining a reference image information group with the highest similarity to target user image information. Thereafter, the book recommendation device may determine a recommended book based on the books that the user indicated by the reference user profile information has read and the books that the user indicated by each user profile information in the profile information group has read. Therefore, the method provided by the embodiment of the application can combine the reference user portrait information with the highest similarity with the target user portrait information and the reference portrait information group with the highest similarity with the target user portrait information to determine the recommended book, so that the determined recommended book can be ensured to be comprehensive and better accord with the reading interest of the target user.

As shown in fig. 6, the book recommendation device 110 provided in the embodiment of the present application may further include: a display unit 130, a Radio Frequency (RF) circuit 150, an audio circuit 160, a wireless fidelity (Wi-Fi) module 170, a bluetooth module 180, a power supply 190, and a camera 121.

The camera 121 may be used to capture still pictures or video, among other things. The object generates an optical picture through the lens and projects the optical picture to the photosensitive element. The photosensitive element may be a Charge Coupled Device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The light sensitive elements convert the light signals into electrical signals which are then passed to the processor 1101 for conversion into digital picture signals.

The processor 1101 is a control center of the book recommending apparatus 110, connects various parts of the entire terminal using various interfaces and lines, and performs various functions of the book recommending apparatus 110 and processes data by running or executing software programs stored in the memory 140 and calling up data stored in the memory 140. In some embodiments, processor 1101 may include one or more processing units; the processor 1101 may also integrate an application processor, which mainly handles operating systems, user interfaces, applications, etc., and a baseband processor, which mainly handles wireless communications. It will be appreciated that the baseband processor described above may not be integrated into the processor 1101. In the present application, the processor 1101 may run an operating system and an application program, may control a user interface to display, and may implement the book recommendation method provided in the embodiment of the present application. Additionally, processor 1101 is coupled to input unit and display unit 130.

The display unit 130 may be used to receive input numeric or character information and generate signal inputs related to user settings and function controls of the book recommendation device 110, and optionally, the display unit 130 may also be used to display Graphical User Interface (GUI) information input by or provided to the user and various menus of the book recommendation device 110. The display unit 130 may include a display screen 131 provided on the front of the book recommendation device 110. The display screen 131 may be configured in the form of a liquid crystal display, a light emitting diode, or the like. The display unit 130 may be used to display various graphical user interfaces described herein.

The display unit 130 includes: a display screen 131 and a touch screen 132 disposed on the front of the book recommendation device 110. The display screen 131 may be used to display preview pictures. Touch screen 132 may collect touch operations on or near by the user, such as clicking a button, dragging a scroll box, and the like. The touch screen 132 may be covered on the display screen 131, or the touch screen 132 and the display screen 131 may be integrated to implement the input and output functions of the book recommendation device 110, and after the integration, the touch screen may be referred to as a touch display screen for short.

Memory 140 may be used to store software programs and data. The processor 1101 performs various functions of the book recommendation device 110 and data processing by executing software programs or data stored in the memory 140. The memory 140 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. The memory 140 stores an operating system that enables the book recommendation device 110 to function. The memory 140 in the present application may store an operating system and various application programs, and may also store codes for executing the book recommendation method provided in the embodiments of the present application.

The RF circuit 150 may be used for receiving and transmitting signals during information transmission and reception or during a call, and may receive downlink data of a base station and then deliver the received downlink data to the processor 1101 for processing; the uplink data may be transmitted to the base station. Typically, the RF circuitry includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.

The audio circuitry 160, speaker 161, microphone 162 can provide an audio interface between the user and the book recommendation device 110. The audio circuit 160 may transmit the electrical signal converted from the received audio data to the speaker 161, and convert the electrical signal into a sound signal for output by the speaker 161. The book recommendation device 110 may also be configured with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 162 converts the collected sound signal into an electrical signal, converts the electrical signal into audio data after being received by the audio circuit 160, and then outputs the audio data to the RF circuit 150 to be transmitted to, for example, another terminal or outputs the audio data to the memory 140 for further processing. In this application, the microphone 162 may capture the voice of the user.

Wi-Fi belongs to a short-distance wireless transmission technology, and the book recommendation device 110 can help a user to send and receive e-mails, browse webpages, access streaming media and the like through the Wi-Fi module 170, and provides wireless broadband Internet access for the user.

And the Bluetooth module 180 is used for performing information interaction with other Bluetooth devices with Bluetooth modules through a Bluetooth protocol. For example, the book recommendation device 110 can establish a bluetooth connection with a wearable electronic device (e.g., a smart watch) also equipped with a bluetooth module through the bluetooth module 180 for data interaction.

The book recommendation device 110 also includes a power source 190 (such as a battery) to power the various components. The power supply may be logically coupled to the processor 1101 through a power management system to manage charging, discharging, and power consumption functions through the power management system. The book recommendation device 110 may also be configured with power buttons for powering on and off the terminal, and locking the screen.

The book recommendation device 110 may include at least one sensor 1110, such as a motion sensor 11101, a distance sensor 11102, a fingerprint sensor 11103, and a temperature sensor 11104. The book recommendation device 110 may also be configured with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the book recommendation device and each device described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

Fig. 7 is a block diagram of a software structure of the book recommendation device according to the embodiment of the present application. The layered architecture divides the software into several layers, each layer having a clear role and division of labor. The layers communicate with each other through a software interface. In some embodiments, the android system is divided into four layers, an application layer, an application framework layer, an Android Runtime (ART) and system library, and a kernel layer from top to bottom.

The application layer may include a series of application packages. As shown in fig. 7, the application package may include applications such as camera, gallery, calendar, phone call, map, navigation, WLAN, bluetooth, music, video, short message, etc. The application framework layer provides an Application Programming Interface (API) and a programming framework for the application programs of the application layer. The application framework layer includes a number of predefined functions.

As shown in FIG. 7, the application framework layers may include a window manager, content provider, view system, phone manager, resource manager, notification manager, and the like.

The window manager is used for managing window programs. The window manager can obtain the size of the display screen, judge whether a status bar exists, lock the screen, intercept the screen and the like.

The content provider is used to store and retrieve data and make it accessible to applications. The data may include video, pictures, audio, calls made and received, browsing history and bookmarks, phone books, etc.

The view system includes visual controls such as controls to display text, controls to display pictures, and the like. The view system may be used to build applications. The display interface may be composed of one or more views. For example, the display interface including the short message notification icon may include a view for displaying text and a view for displaying pictures.

The phone manager is used to provide the communication function of the book recommendation device 110. Such as management of call status (including on, off, etc.).

The resource manager provides various resources for the application, such as localized strings, icons, pictures, layout files, video files, and the like.

The notification manager enables the application to display notification information in the status bar, can be used to convey notification-type messages, can disappear automatically after a short dwell, and does not require user interaction. Such as a notification manager used to inform download completion, message alerts, etc. The notification manager may also be a notification that appears in the form of a chart or scroll bar text at the top status bar of the system, such as a notification of a background running application, or a notification that appears on the screen in the form of a dialog window. For example, text information is prompted in the status bar, a prompt tone is given, the communication terminal vibrates, and an indicator light flashes.

The android run is composed of a core library and a virtual machine. android runtime is responsible for the scheduling and management of the android system.

The core library comprises two parts: one part is a function which needs to be called by java language, and the other part is a core library of android.

The application layer and the application framework layer run in a virtual machine. And executing java files of the application program layer and the application program framework layer into a binary file by the virtual machine. The virtual machine is used for performing the functions of object life cycle management, stack management, thread management, safety and exception management, garbage collection and the like.

The system library may include a plurality of functional modules. For example: surface managers (surface managers), media libraries (media libraries), three-dimensional graphics processing libraries (e.g., openGL ES), 2D graphics engines (e.g., SGL), and the like.

The surface manager is used to manage the display subsystem and provide fusion of 2D and 3D layers for multiple applications.

The media library supports a variety of commonly used audio, video format playback and recording, and still picture files, etc. The media library may support a variety of audio-video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

The three-dimensional graphic processing library is used for realizing three-dimensional graphic drawing, picture rendering, synthesis, layer processing and the like.

The 2D graphics engine is a drawing engine for 2D drawing.

The kernel layer is a layer between hardware and software. The inner core layer at least comprises a display driver, a camera driver, an audio driver and a sensor driver.

An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored, and the computer program is loaded by a processor and executes a book recommendation method provided in the above-mentioned embodiment, for example, the method shown in fig. 1 or fig. 3.

Embodiments of the present application further provide a computer program product containing instructions, which, when running on a computer, causes the computer to execute the book recommendation method provided by the above method embodiments, for example, the method shown in fig. 1 or fig. 3.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

It should be understood that reference herein to "and/or" means that there may be three relationships, for example, a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Also, the term "at least one" in the present application means one or more, and the term "a plurality" in the present application means two or more.

The terms "first," "second," and the like in this application are used for distinguishing between similar items and items that have substantially the same function or similar functionality, and it should be understood that "first," "second," and "nth" do not have any logical or temporal dependency or limitation on the number or order of execution. For example, a first reference user representation information may be referred to as a second reference user representation information, and similarly, a second reference user representation information may be referred to as a first reference user representation information, without departing from the scope of various described examples.

It can be understood that the user portrait information of the user, which is acquired by the book recommendation device provided in the embodiment of the present application, is acquired after the user authorization. In addition, the book recommendation device provided by the embodiment of the application strictly complies with relevant laws and regulations in the processes of collecting, using and processing the user portrait information.

The above description is only exemplary of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements and the like that are made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A book recommendation device, characterized in that the book recommendation device comprises: a processor; the processor is configured to:

2. The book recommendation device of claim 1, wherein said processor is further configured to:

3. The book recommendation device of claim 2, wherein the processor is configured to:

4. The book recommendation device of claim 3, wherein said processor is further configured to:

5. The book recommendation device of any of claims 1-4, wherein said processor is configured to:

6. The book recommendation device of claim 5, wherein the processor is configured to:

7. The book recommendation device of any of claims 1-4, wherein said processor is configured to:

8. The book recommendation device of any one of claims 1 to 4, wherein the similarity between each portrait information group and the target user portrait information is:

9. A book recommendation method is characterized by being applied to book recommendation equipment; the method comprises the following steps:

10. The method of claim 9, wherein after the determining a recommended book based on the first alternative book and the second alternative book, the method further comprises: