CN106294502B - Electronic book information processing method and device - Google Patents
Electronic book information processing method and device Download PDFInfo
- Publication number
- CN106294502B CN106294502B CN201510313663.3A CN201510313663A CN106294502B CN 106294502 B CN106294502 B CN 106294502B CN 201510313663 A CN201510313663 A CN 201510313663A CN 106294502 B CN106294502 B CN 106294502B
- Authority
- CN
- China
- Prior art keywords
- information
- similarity
- electronic book
- obtaining
- subset
- 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.)
- Active
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for processing electronic book information, wherein the method comprises the following steps: acquiring a first characteristic information set of a first electronic book which is currently displayed and a second characteristic information set of a second electronic book in an electronic book database; obtaining at least one first similarity between at least one pair of information subsets of the same type in the first set of feature information and the second set of feature information; and obtaining a second similarity of the first electronic book and the second electronic book based on the at least one first similarity. By the technical scheme, the similarity between the information subsets of the same type in the characteristic information is obtained, and the similarity between the electronic books is calculated according to the similarity between the characteristic information, so that the technical problem that the similarity calculation of the electronic books is inaccurate in the prior art is solved, and the accuracy of the similarity calculation of the electronic books is improved.
Description
Technical Field
The present invention relates to the field of multimedia information processing technologies, and in particular, to a method and an apparatus for processing electronic book information.
Background
With the continuous development of internet technology, electronic books are developed rapidly, and users can read the electronic books anytime and anywhere, so that great convenience is provided for reading life of the users. Meanwhile, the electronic equipment can recommend similar or related books for the user according to the electronic books read by the user, so that the time for the user to search for the books is saved.
In the prior art, an electronic book recommendation method is mainly based on content recommendation. And (3) directly performing characterization according to the content of the electronic book in the aspect of calculating the similarity of the electronic book based on the recommendation of the content, and then performing weight calculation according to the same characteristics. For example, electronic book characterization includes: in the prior art, the characteristics of the tag, the author, the classification and the like are compared to determine whether the characteristics of the two electronic books are the same, and then the same characteristics are multiplied by the weight and added to obtain the similarity of the two electronic books.
However, in the prior art, due to differences in the characteristics, electronic books with different characteristics may be similar. For example, the novel "night tomb note" is characterized as: "magic", "mysterious", "thriller" (label); "southern part tritertion" (author); "inference novel", "detective novel" (classification). The novel "ghost lamp" is characterized as: "quest," "suspicion" (label); "Tianxia Ba sing" (author); fantasy fiction, horror fiction (classification). By adopting the recommendation method in the prior art, almost no same characteristics exist between the ghost-blown lamp and the night tomb note, the similarity is very small, but in fact, the ghost-blown lamp and the night tomb note have very strong similarity, but the similarity between the ghost-blown lamp and the night tomb note cannot be calculated accurately due to the fact that the characteristics are different.
Therefore, in the prior art, the similarity calculation between electronic books has the technical problem of poor accuracy.
Disclosure of Invention
The embodiment of the invention provides an electronic book information processing method and device, which are used for solving the technical problem of poor similarity calculation accuracy among electronic books in the prior art and improving the similarity calculation accuracy.
The application provides an electronic book information processing method, which comprises the following steps:
acquiring a first characteristic information set of a first electronic book which is currently displayed and a second characteristic information set of a second electronic book in an electronic book database;
obtaining at least one first similarity between at least one pair of information subsets of the same type in the first set of feature information and the second set of feature information;
calculating a second similarity of the first electronic book and the second electronic book based on the at least one first similarity.
Optionally, the first characteristic information set and the second characteristic information set respectively include at least one of the following information subsets: a tag information subset, a category information subset, and an author information subset of the electronic book.
Optionally, the obtaining at least one first similarity between at least one pair of information subsets of the same type in the first characteristic information set and the second characteristic information set includes:
obtaining at least one first similarity by the following formula:
wherein, Sim(b,b)(B1B2) represents the first similarity, i ∈ { tag information, classification information, author information }, Si(B1) Information subset, S, representing the first set of characteristic informationi(B2) Information subset, Sim, representing said second set of characteristic information(i,i)(I1,I2) Representing the similarity of two information elements in the information subsets of the first characteristic information set and the information subsets of the second characteristic information set; i is1Denotes Si(B1) Any of the information elements in (1); i is2Denotes Si(B2) Any of the information elements in (1);
when I is1And I2When the same, Sim(i,i)(I1,I2)＝1；
When I is1And I2When the difference is not the same, the first and second substrates,
or
Sb(I1) Is represented by comprising I1E-book collection, Sb(I2) Is represented by comprising I2E-book collection of Sr(I1) Indicating that reading has covered I1Reader set of electronic book, Sr(I2) Indicating that reading has covered I2A collection of readers of the electronic book.
Optionally, the obtaining a second similarity between the first electronic book and the second electronic book based on the at least one first similarity includes:
obtaining each of the first similarities;
obtaining the product of each first similarity and the corresponding weight parameter;
and obtaining the sum of all the products as the second similarity.
Optionally, the method further includes:
obtaining a recommended electronic book of the first electronic book according to the second similarity;
and displaying the recommended electronic book.
Optionally, the displaying the recommended electronic book includes:
displaying a recommendation page, wherein the recommendation page comprises a recommendation electronic book and at least one path node as follows: label, category, author;
and obtaining the second similarity between the recommended electronic book and the first electronic book according to the first similarity corresponding to the path formed by the path nodes selected by the user or the path formed by the user behavior history.
The embodiment of the application further provides an electronic book information processing method, which comprises the following steps:
acquiring a first characteristic information set of a first electronic book which is currently displayed and a second characteristic information set of a second electronic book in an electronic book database;
obtaining at least one first similarity between at least one pair of different types of information subsets in the first set of characteristic information and the second set of characteristic information;
calculating a second similarity of the first electronic book and the second electronic book based on the at least one first similarity.
Optionally, the first characteristic information set and the second characteristic information set respectively include at least one of the following information subsets: a tag information subset, a category information subset, an author information subset, and a reader information subset of the electronic book.
Optionally, the obtaining at least one first similarity between at least one pair of different types of information subsets in the first characteristic information set and the second characteristic information set includes:
obtaining a third similarity of each information element in the information subset of the first characteristic information set and the first electronic book;
obtaining a fourth similarity of each information element in the information subset of the second characteristic information set and the second electronic book;
obtaining a fifth similarity between at least one pair of different types of information elements in the first set of feature information and the second set of feature information;
obtaining the at least one first similarity based on the third similarity, a fourth similarity, and the fifth similarity.
Optionally, when information elements in the first feature information set and the second feature information set are author information, obtaining that the third similarity and the fourth similarity are 1;
when the information elements in the first and second feature information sets are not author information, obtaining the third and fourth similarities by the following formulas:
where x ∈ { tag information, classification information, reader information }, NbRepresenting the number of electronic books in the electronic database; sx(B) A subset of information representing the first set of characteristic information or a subset of information representing the second set of characteristic information; k represents the number of electronic books containing the information element X; when X is any information element in the information subset of the first characteristic information set and B is the first electronic book, Sim(b,x)(B, X) is the third similarity; when X is any information element in the information subset of the second characteristic information set and B is the first electronic book, Sim(b,x)(B, X) is the fourth similarity.
Optionally, the obtaining a fifth similarity between at least one pair of different types of information elements in the first characteristic information set and the second characteristic information set includes:
the fifth similarity is obtained by the following formula:
wherein, Sim(i,j)(I1,J2) The fifth similarity is represented by I, j ∈ { label information, author information, classification information, reader information }, I and j are different in type, I1Represents one information element of the subset i of the first set of characteristic information, J2Represents one information element in the subset j of the second set of characteristic information; sb(I1) Is represented by comprising I1A collection of electronic books of (1); sb(J2) Is represented by the formula containing J2A collection of electronic books.
Optionally, the obtaining the at least one first similarity based on the third similarity, the fourth similarity, and the fifth similarity includes:
obtaining the at least one first similarity by:
wherein, Sim(b,b)(B1B2) represents the first similarity; sim(b,i)(B1,I1) Representing the third similarity; sim(b,j)(B2,J2) Representing the fourth similarity.
Optionally, the obtaining a second similarity between the first electronic book and the second electronic book based on the at least one first similarity includes:
obtaining each of the first similarities;
obtaining the product of each first similarity and the corresponding weight parameter;
and obtaining the sum of all the products as the second similarity.
Optionally, the method further includes:
obtaining a recommended electronic book of the first electronic book according to the second similarity;
and displaying the recommended electronic book.
Optionally, the displaying the recommended electronic book includes:
displaying a recommendation page, wherein the recommendation page comprises a recommendation electronic book and at least one path node as follows: label, category, author;
and obtaining the second similarity between the recommended electronic book and the first electronic book according to the first similarity corresponding to the path formed by the path nodes selected by the user or the path formed by the user behavior history.
An embodiment of the present application further provides an electronic book information processing apparatus, where the apparatus includes:
the electronic book display device comprises a first obtaining unit, a second obtaining unit and a display unit, wherein the first obtaining unit is used for obtaining a first characteristic information set of a first electronic book which is displayed currently and a second characteristic information set of a second electronic book in an electronic book database;
a second obtaining unit, configured to obtain at least one first similarity between at least one pair of information subsets of the same type in the first feature information set and the second feature information set;
a calculating unit, configured to calculate a second similarity between the first electronic book and the second electronic book based on the at least one first similarity.
Optionally, the first characteristic information set and the second characteristic information set respectively include at least one of the following information subsets: a tag information subset, a category information subset, and an author information subset of the electronic book.
Optionally, the computing unit is specifically configured to: obtaining each of the first similarities; obtaining the product of each first similarity and the corresponding weight parameter; and obtaining the sum of all the products as the second similarity.
Optionally, the apparatus further comprises:
the recommending unit is used for obtaining a recommended electronic book of the first electronic book according to the second similarity;
and the display unit is used for displaying the recommended electronic book.
Optionally, the display unit is specifically configured to: displaying a recommendation page, wherein the recommendation page comprises a recommendation electronic book and at least one path node as follows: label, category, author; and obtaining the second similarity between the recommended electronic book and the first electronic book according to the first similarity corresponding to the path formed by the path nodes selected by the user or the path formed by the user behavior history.
An embodiment of the present application provides an electronic book information processing apparatus, where the apparatus includes:
the electronic book display device comprises a first obtaining unit, a second obtaining unit and a display unit, wherein the first obtaining unit is used for obtaining a first characteristic information set of a first electronic book which is displayed currently and a second characteristic information set of a second electronic book in an electronic book database;
a second obtaining unit, configured to obtain at least one first similarity between at least one pair of different types of information subsets in the first feature information set and the second feature information set;
a calculating unit, configured to calculate a second similarity between the first electronic book and the second electronic book based on the at least one first similarity.
Optionally, the first characteristic information set and the second characteristic information set respectively include at least one of the following information subsets: a tag information subset, a category information subset, an author information subset, and a reader information subset of the electronic book.
Optionally, the second obtaining unit is specifically configured to: obtaining a third similarity of each information element in the information subset of the first characteristic information set and the first electronic book; obtaining a fourth similarity of each information element in the information subset of the second characteristic information set and the second electronic book; obtaining a fifth similarity between at least one pair of different types of information elements in the first set of feature information and the second set of feature information; obtaining the at least one first similarity based on the third similarity, a fourth similarity, and the fifth similarity.
Optionally, the computing unit is specifically configured to: obtaining each of the first similarities; obtaining the product of each first similarity and the corresponding weight parameter; and obtaining the sum of all the products as the second similarity.
Optionally, the apparatus further comprises:
the recommending unit is used for obtaining a recommended electronic book of the first electronic book according to the second similarity;
and the display unit is used for displaying the recommended electronic book.
Optionally, the display unit is specifically configured to: displaying a recommendation page, wherein the recommendation page comprises a recommendation electronic book and at least one path node as follows: label, category, author; and obtaining the second similarity between the recommended electronic book and the first electronic book according to the first similarity corresponding to the path formed by the path nodes selected by the user or the path formed by the user behavior history.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
by obtaining the characteristic information of the electronic books, calculating the similarity between the characteristic information of the electronic books and obtaining the similarity between the electronic books according to the similarity between the characteristic information, the similarity between the electronic books can be avoided from being excluded due to different literal of the characteristic information and obtained according to the same and similar characteristic information, the technical problem of inaccurate calculation of the similarity of the electronic books in the prior art is solved, and the accuracy of calculation of the similarity is improved.
Drawings
Fig. 1 is a schematic flowchart of an electronic book information processing method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of an associated path of an electronic book provided in an embodiment of the present application;
fig. 3 is a schematic flowchart of an electronic book information processing method according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of an electronic book information processing apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of an electronic book information processing apparatus according to an embodiment of the present disclosure.
Detailed Description
In the technical scheme provided by the embodiment of the application, by obtaining the characteristic information of the electronic books, calculating the similarity between the characteristic information of the electronic books and obtaining the similarity between the electronic books according to the similarity between the characteristic information, the similarity between the electronic books can be avoided being excluded due to different literal aspects of the characteristic information and being obtained according to the same and similar characteristic information, the technical problem of inaccurate calculation of the similarity of the electronic books in the prior art is solved, and the accuracy of calculation of the similarity between the electronic books is improved.
The main implementation principle, the specific implementation mode and the corresponding beneficial effects of the technical scheme of the embodiment of the present application are explained in detail with reference to the accompanying drawings.
Example one
Referring to fig. 1, an embodiment of the present application provides an electronic book information processing method, including:
s101: acquiring a first characteristic information set of a first electronic book which is currently displayed and a second characteristic information set of a second electronic book in an electronic book database;
s102: obtaining at least one first similarity between at least one pair of information subsets of the same type in the first set of feature information and the second set of feature information;
s103: and obtaining a second similarity of the first electronic book and the second electronic book based on the at least one first similarity.
After the second similarity between the first electronic book and the second electronic book is obtained, the recommended electronic book of the currently displayed first electronic book is further obtained according to the obtained second similarity, and the obtained recommended electronic book is displayed. Specifically, N second similarities between N second electronic books in the electronic book database and the first electronic book may be obtained first; and taking the second electronic book with the second similarity at the front M positions as a recommended electronic book of the first electronic book, and displaying the recommended electronic book, wherein N, M is an integer greater than or equal to 1. Of course, the second electronic book with the second similarity greater than the set threshold with the first electronic book may also be obtained as the recommended electronic book of the first electronic book, and the recommended electronic book is displayed.
In the specific implementation process, the electronic book characterization information is divided into three categories: tag information, classification information, and author information, wherein each type of information may include multiple information elements. For example: the label information can contain information elements such as 'magic', 'mysterious', 'thriller' and the like; the classification information can comprise information elements such as 'reasoning novel', 'detective novel', 'martial arts novel', and the like; the author information may contain one or more author information elements. The characteristic information set of the electronic book can effectively help the electronic equipment to identify and distinguish different or similar electronic books. In addition, reader information of the electronic book can also effectively help the electronic equipment to identify and distinguish different or similar electronic books, because the same readers or reader groups often like the same kind of reading materials or similar reading materials, and the possibility that the read books are similar is very high, for example, readers A and B read the night book and the ghost lamp, and the night book and the ghost lamp are indeed similar books.
In order to obtain the similarity between the feature information, in the embodiment of the present application, when obtaining the similarity between the electronic books, S101 is executed to obtain a first feature information set including the feature information of the first electronic book and a second feature information set including the feature information of the second electronic book. The first characteristic information set and the second characteristic information set respectively comprise at least one type of information subsets as follows: a tag information subset, a category information subset, and an author information subset of the electronic book. Preferably, the characteristic information set does not include a subset of reader information.
Referring to fig. 2, the feature information of the electronic Book may include: tag information Tag, Category information Category and Author information Author. As shown by the solid line in fig. 2, each electronic book corresponds to tag information, category information, and author information, that is, there is an explicit association between the electronic book and the tag information, the category information, and the author information. Since the two electronic books may include the same tag information, category information, and/or author information, the two electronic books may be associated by the same feature information. As shown by the dashed line in fig. 2, two different information elements (e.g., tag 1 and tag 2, tag 1 and class 1) in the tag information subset, the classification information subset or the author information subset may be related to each other through an intermediate medium such as an electronic book, i.e., there is an implicit relationship between two different information elements in the tag information subset, the classification information subset or the author information subset. Since there is also an implicit association between two information elements belonging to different subsets of information in the tag information subset, the category information subset, and the author information subset, different subsets of information may also associate two electronic books. To this end, the embodiment of the present application performs S102 to obtain at least one first similarity between at least one pair of information subsets of the same type, so as to increase the accuracy of calculating the similarity of the electronic book. Of course, the present application may also obtain at least one first similarity between at least one pair of different types of information subsets to increase the accuracy of calculating the similarity of the electronic book, which will be described in detail in the following embodiments.
After obtaining at least one first similarity between at least one pair of different types of information subsets, S103 is continuously executed to obtain a second similarity between the first electronic book and the second electronic book based on the at least one first similarity. Specifically, a weight parameter corresponding to each first similarity may be obtained first, where the weight parameter is specifically a preset parameter and may be selected and set according to an empirical value; further, obtaining the product of each weight parameter and the corresponding first similarity; then, the sum of all the products is obtained as the second similarity.
After the second similarity is obtained by executing the step S103, further obtaining N second similarities between N second electronic books and the first electronic book in the electronic book database; and taking the second electronic book with the second similarity in the front M positions as the recommended electronic book of the first electronic book, wherein N, M is an integer greater than or equal to 1. Specifically, M may be an integer of 1, 2, 3, 5, 10, or the like; n can be a parameter preset by a designer according to actual needs; n may also be the number of all electronic books included in the electronic book database except the first electronic book, and N may also be the total number of books in a certain category of books to which the first electronic book belongs minus 1. For example: assuming that the category to which the first electronic book belongs is science fiction, and the total number of books in the science fiction category in the electronic book data is 10000, N may be 9999, and after obtaining the second similarity between the 9999 second electronic book and the first electronic book, the electronic device obtains an M book that is most similar to the first electronic book, that is, the second electronic book whose second similarity is M front, as a recommended electronic book of the first electronic book.
The specific process of obtaining the first similarity and the second similarity is further described below by specific parameters and formulas. First, the following parameters will be explained: s represents a set; b represents a book, T represents a label, a represents an author, C represents a classification, corresponding B refers to a certain book, T refers to a certain label, A refers to a certain author, C refers to a certain classification, and R refers to a certain reader; stRepresenting a set of labels, and similarly Sa、Sc、SrEtc.; sim represents the similarity.
Calculation method of first and second similarity
The i-i path calculates a first similarity, i.e. at least one first similarity is obtained according to at least one pair of information subsets of the same type in the obtained first characteristic information set and the second characteristic information set. Specifically, the first similarity of the i-i path may be calculated by the following formula (1):
wherein, Sim(b,b)(B1B2) represents the first similarity, i ∈ { tag information, classification information, author information }, Si(B1) Representing a subset of the first set of characteristic information, Si(B2) Represents a subset, Sim, of said second set of characteristic information(i,i)(I1,I2) Representing the similarity of two elements in the subset of the first set of feature information and the subset of the second set of feature information; i is1Denotes Si(B1) Any of the information elements in (1); i is2Denotes Si(B2) Any of the information elements in (1);
when I is1And I2When the same, Sim(i,i)(I1,I2)＝1；
When I is1And I2When not identical, calculating Sim by formula (2) or (3)(i,i)(I1,I2)：
Wherein S isb(I1) Is represented by comprising I1E-book collection, Sb(I2) Is represented by comprising I2E-book collection of Sr(I1) Indicating that reading has covered I1Reader set of electronic book, Sr(I2) Indicating that reading has covered I2A collection of readers of the electronic book.
In a specific implementation process, when an i-i path is t-t, that is, when a first similarity between tag information in a first characteristic information set and tag information in a second characteristic information set is calculated, substituting i-t into formula (2) to obtain a similarity Sim between two tag information elements in the first characteristic set and the second characteristic set(t,t)(T1,T2)：
Similarly, when the path i-i is c-c, substituting i-c into the formula (2) can calculate the similarity Sim between two classified information elements in the first feature set and the second feature set(c,c)(C1,C2) (ii) a When the path i-i is r-r, substituting i-r into formula (2) can calculate two reader information elements in the first feature set and the second feature setSimilarity between them Sim(r,r)(R1,R2)。
When the path i-i is a-a, since books of different authors may not intersect but reader-readers of the books may intersect, substituting i ═ a into formula (3) can calculate the similarity Sim between two author information elements in the first feature set and the second feature set(a,a)(A1,A2):
Calculation of second and third similarity
After obtaining at least one first similarity, a second similarity between the first electronic book and the second electronic book may be obtained through formula (4):
wherein, Sim(b,b)(B1,B2) Denotes a second similarity, k denotes the number of paths from the first electronic book to the second electronic book, i.e., the number of first similarities, αfα representing the weight parameter corresponding to the first similarityfThe specific setting can be preset by the designer according to different paths.
For example: assuming that paths for calculating the first similarity in the e-book database are as shown in table one, and a total of 3 paths are included, k is 3.
| f | i-i path | Means of |
| 1 | B-T-T-B | Book being equal to>Label ═ tag->Label ═ tag->Book with |
| 2 | B-A-A-B | Book being equal to>The authors become>The authors become>Book with |
| 3 | B-C-C-B | Book being equal to>Classify as>Classify as>Book with detachable cover |
Watch 1
Further, when the second similarity is calculated based on at least one of the first similarities, the second similarity may also be calculated based on a specific first similarity. The specific first similarity is a first similarity calculated by a path selected by the user or a path formed by a user behavior history. Specifically, when the first electronic book is displayed, a recommended page is displayed, and the recommended page includes at least one of the following path nodes: labels, classifications, and authors; then, obtaining a path formed by path nodes selected by a user or obtaining a path formed by behavior history of the user; and then, obtaining a second similarity based on the first similarity corresponding to the path.
For example: and displaying to the user: path nodes and paths such as authors, labels, categories, and e-books recommend pages such as paths, as shown in fig. 2. The user may select nodes by directly clicking on path nodes, such as authors or tags, or may select path nodes at both ends of the path by clicking on the path. Correspondingly, the path for obtaining the same type of feature information set by the electronic device according to the path node selected by the user, such as an author or a label, is as follows: author-author or tag-tag (i.e., path 1 or 2 in fig. 2), then a second similarity is obtained based on the first similarity corresponding to the path. Assume again that the user's behavioral history is: the selected path nodes are: label, classification, then the path formed by the behavior history can be obtained: label-label, sort-sort (i.e. paths 2, 3 in fig. 2), and obtain a second similarity based on the obtained first similarity corresponding to the paths.
Through the embodiment, the first similarity between at least one pair of different types of information subsets is calculated and obtained according to the characteristic information sets of the first electronic book and the second electronic book, the implicit association between the characteristic information is included, the second similarity between the first electronic book and the second electronic book is further obtained according to the obtained first similarity, the similar characteristic information is prevented from being excluded due to different character faces of the characteristic information, the similarity between the electronic books is obtained according to the similarity between the characteristic information, the technical problem of inaccurate calculation of the similarity of the electronic books in the prior art is solved, and the accuracy of calculation of the similarity of the electronic books is improved.
Example two
Referring to fig. 3, an embodiment of the present application provides an electronic book information processing method, including:
s301: acquiring a first characteristic information set of a first electronic book which is currently displayed and a second characteristic information set of a second electronic book in an electronic book database;
s302: obtaining at least one first similarity between at least one pair of different types of information subsets in the first set of characteristic information and the second set of characteristic information;
s303: calculating a second similarity of the first electronic book and the second electronic book based on the at least one first similarity.
In a specific implementation process, the first characteristic information set and the second characteristic information set obtained by executing S301 respectively include at least one of the following information subsets: a tag information subset, a category information subset, an author information subset, and a reader information subset of the electronic book. Since there is also an implicit association between information elements in different types of information subsets, the embodiment of the present application further performs S302: at least one first similarity between at least one pair of different types of information subsets in the first set of feature information and the second set of feature information is obtained.
The specific process of obtaining the first similarity and the second similarity is further described below by specific parameters and formulas. First, the following parameters will be explained: s represents a set; b represents a book, T represents a label, a represents an author, C represents a classification, R represents a reader, corresponding B particularly refers to a certain book, T particularly refers to a certain label, A particularly refers to a certain author, C particularly refers to a certain classification, and R particularly refers to a certain reader; stRepresenting a set of labels, and similarly Sa、Sc、SrEtc.; sim represents the similarity.
Calculation of first and second similarity
And calculating the first similarity by the i-j path, namely obtaining at least one first similarity according to the obtained information subsets with different types in the first characteristic information set and the second characteristic information set. Specifically, the third similarity Sim of each information element in the first characteristic information set and the first electronic book can be obtained(b,i)(B1,I1) (ii) a And obtaining a fourth similarity Sim between each information element in the second characteristic information set and the second electronic book(b,j)(B2,J2) (ii) a And obtaining a fifth similarity Sim between at least one pair of different types of information subsets in the first and second sets of feature information(i,j)(I1,J2) (ii) a Then, the at least one first similarity is obtained based on the third similarity, the fourth similarity, and the fifth similarity. Wherein the first similarity of i-j paths can be obtained by formula (5):
wherein, Sim(b,b)(B1B2) indicates a first similarity, i, j ∈ { tag information, classification information, author information, reader information }, i being different from j in type.
Specifically, the third similarity Sim is obtained(b,i)(B1,I1) And a fourth degree of similarity Sim(b,j)(B2,J2) When directed at I1、J2The actual values of (a) are different, and the third similarity and the fourth similarity are different. And when the information elements in the first characteristic information set and the second characteristic information set are author information, obtaining that the third similarity and the fourth similarity are 1.
When the information elements in the first feature information set and the second feature information set are not author information, the third similarity and the fourth similarity are obtained by the following equations (6) and (7):
where x ∈ { tag information, category information, reader information }, i.e., x ═ i or x ═ j, NbRepresenting the number of electronic books in the electronic database, and K is the number of electronic books containing the information element X; when X is any information element I in the first characteristic information set1B is a first electronic book B1When, Sim(b,x)(B, X) is a third similarity; when X is any information element J in the second characteristic information set2B is a first electronic book B2When, Sim(b,x)(B, X) is a fourth similarity.
In a specific implementation process, the fifth similarity Sim between at least one pair of different types of information subsets in the first characteristic information set and the second characteristic information set can be obtained through the following formula (8)(i,j)(I1,J2)：
Wherein, Sim(i,j)(I1,J2) Represents the fifth degree of similarity, I1Represents an information element in i, J2Represents one information element in j; sb(I1) Is represented by comprising I1A collection of electronic books of (1); sb(J2) Is represented by the formula containing J2A collection of electronic books. Please refer to table two, the fifth similarity Sim when i and j are label information t, author information a, and reader information r, respectively(i,j)(I1,J2) Wherein in Table II, Sim is(i,j)(I1,J2) Simplified to Sim(i,j)：
Calculation of second and third similarity
After the first similarity of each path is obtained, a second similarity between the first electronic book and the second electronic book can be obtained through formula (9):
wherein, Sim(b,b)(B1,B2) Denotes a second similarity, k denotes the number of paths from the first electronic book to the second electronic book, i.e., the number of first similarities, αfα representing the weight parameter corresponding to the first similarityfThe specific setting can be preset by the designer according to different paths.
For example: assuming that paths for calculating the first similarity between the first electronic book and the second electronic book in the electronic book database are as shown in table three, and a total of 6 paths are included, k is 6.
| f | i-j path | Means of |
| 1 | B-C-R-B | Book being equal to>Classify as>Reader as a whole>Book with |
| 2 | B-C-T-B | Book being equal to>Classify as>Label ═ tag->Book with |
| 3 | B-C-A-B | Book being equal to>Classify as>The authors become>Book with detachable cover |
| 4 | B-T-A-B | Book being equal to>Label ═ tag->The authors become>Book with detachable cover |
| 5 | B-T-R-B | Book being equal to>Label ═ tag->Reader as a whole>Book with detachable cover |
| 6 | B-A-R-B | Book being equal to>The authors become>Reader as a whole>Book with detachable cover |
Watch III
Further, when the second similarity is calculated based on at least one of the first similarities, the second similarity may also be calculated based on a specific first similarity. The specific first similarity is a first similarity calculated by a path selected by the user or a path formed by a user behavior history. Specifically, when the first electronic book is displayed, a recommended page is displayed, and the recommended page includes at least one of the following path nodes: tags, classifications, authors and readers; then, obtaining a path formed by path nodes selected by a user or obtaining a path formed by behavior history of the user; and then, obtaining a second similarity based on the first similarity corresponding to the path.
For example: and displaying to the user: path nodes and paths such as authors, tags, categories, readers, and ebooks are shown in fig. 2. The user can select nodes by directly clicking path nodes such as authors and labels, and can also select path nodes at both ends of the path by clicking the path. Correspondingly, the electronic device obtains the paths of different types of feature information sets according to the path nodes selected by the user, such as the author, the label and the reader, as follows: author-tag, author-reader, tag-reader (i.e., paths 7, 6, 5 in fig. 2), then a second similarity is obtained based on the first similarity corresponding to the above paths. Assume again that the user's behavioral history is: the selected path nodes are: label, classification, then the path formed by the behavior history can be obtained: label-classification (i.e., path 9 in fig. 2), and obtaining a second similarity based on the obtained first similarity corresponding to the path.
Through the embodiment, the first similarity between at least one pair of different types of information subsets in the feature information sets of the first electronic book and the second electronic book is obtained, the implicit association between the different types of feature information is included, the second similarity between the first electronic book and the second electronic book is further obtained according to the obtained first similarity, the similar feature information is prevented from being excluded due to different word planes of the feature information, the similarity between the electronic books is obtained according to the similarity between the different types of feature information, the technical problem of inaccurate calculation of the similarity of the electronic books in the prior art is solved, and the accuracy of calculation of the similarity of the electronic books is improved.
It should be noted that, when calculating the second similarity between the first electronic book and the second electronic book, the present invention may also use at least one first similarity obtained in the first embodiment together with at least one first similarity obtained in the second embodiment in the calculation of the second similarity, that is, the path for calculating the second similarity includes i-i and i-j.
EXAMPLE III
Referring to fig. 4, an embodiment of the present application provides an electronic book information processing apparatus, including:
a first obtaining unit 401, configured to obtain a first feature information set of a currently displayed first electronic book and a second feature information set of a second electronic book in an electronic book database;
a second obtaining unit 402, configured to obtain at least one first similarity between at least one pair of information subsets of the same type in the first feature information set and the second feature information set;
a calculating unit 403, configured to calculate a second similarity between the first electronic book and the second electronic book based on the at least one first similarity.
In a specific implementation process, the first feature information set and the second feature information set respectively include at least one of the following information subsets: a tag information subset, a category information subset, and an author information subset of the electronic book.
When the calculating unit calculates and obtains the second similarity, it is specifically configured to: obtaining each of the first similarities; obtaining the product of each first similarity and the corresponding weight parameter; and obtaining the sum of all the products as the second similarity.
Further, the apparatus further comprises: a recommending unit 404, configured to obtain a recommended electronic book of the first electronic book according to the second similarity; a display unit 405, configured to display the recommended electronic book. Wherein the display unit 405 is specifically configured to: displaying a recommendation page, wherein the recommendation page comprises a recommendation electronic book and at least one path node as follows: label, category, author; and obtaining the second similarity between the recommended electronic book and the first electronic book according to the first similarity corresponding to the path formed by the path nodes selected by the user or the path formed by the user behavior history.
Example four
Referring to fig. 5, an embodiment of the present application provides an electronic book information processing apparatus, including:
a first obtaining unit 501, configured to obtain a first feature information set of a currently displayed first electronic book and a second feature information set of a second electronic book in an electronic book database;
a second obtaining unit 502, configured to obtain at least one first similarity between at least one pair of different types of information subsets in the first characteristic information set and the second characteristic information set;
a calculating unit 503, configured to calculate a second similarity between the first electronic book and the second electronic book based on the at least one first similarity.
In a specific implementation process, the first feature information set and the second feature information set respectively include at least one of the following information subsets: a tag information subset, a category information subset, an author information subset, and a reader information subset of the electronic book.
When acquiring at least one first similarity, the second acquiring unit 502 is specifically configured to: obtaining a third similarity of each information element in the information subset of the first characteristic information set and the first electronic book; obtaining a fourth similarity of each information element in the information subset of the second characteristic information set and the second electronic book; obtaining a fifth similarity between at least one pair of different types of information elements in the first set of feature information and the second set of feature information; obtaining the at least one first similarity based on the third similarity, a fourth similarity, and the fifth similarity.
When the second similarity is obtained through calculation, the calculating unit 503 is specifically configured to: obtaining each of the first similarities; obtaining the product of each first similarity and the corresponding weight parameter; and obtaining the sum of all the products as the second similarity.
In a specific implementation process, the device further comprises: a recommending unit 504, configured to obtain a recommended electronic book of the first electronic book according to the second similarity; a display unit 505, configured to display the recommended electronic book. The display unit 505 is specifically configured to: displaying a recommendation page, wherein the recommendation page comprises a recommendation electronic book and at least one path node as follows: label, category, author; and obtaining the second similarity between the recommended electronic book and the first electronic book according to the first similarity corresponding to the path formed by the path nodes selected by the user or the path formed by the user behavior history.
Through one or more technical solutions in the embodiments of the present application, one or more of the following technical effects can be achieved:
by obtaining the characteristic information of the electronic books, calculating the similarity between the characteristic information of the electronic books and obtaining the similarity between the electronic books according to the similarity between the characteristic information, the similarity between the electronic books can be avoided from being excluded due to different characters of the characteristic information and obtained according to the same and similar characteristic information, the technical problem of inaccurate calculation of the similarity of the electronic books in the prior art is solved, and the accuracy of calculation of the similarity of the electronic books is improved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (17)
1. An electronic book information processing method, characterized by comprising:
acquiring a first characteristic information set of a first electronic book which is currently displayed and a second characteristic information set of a second electronic book in an electronic book database;
obtaining at least one first similarity between at least one pair of information subsets of the same type in the first feature information set and the second feature information set, the first similarity being obtained based on a similarity between any information element in the information subsets of the first feature information set and any information element in the information subsets of the second feature information set;
calculating a second similarity of the first electronic book and the second electronic book based on the at least one first similarity.
2. The method of claim 1, wherein the first set of feature information and the second set of feature information each comprise at least one of the following types of subsets of information: a tag information subset, a category information subset, and an author information subset of the electronic book.
3. The method of claim 2, wherein said obtaining at least one first similarity between at least one pair of same type information subsets of said first and second sets of feature information comprises:
obtaining at least one first similarity by the following formula:
wherein, Sim(b,b)(B1,B2) Indicating a first similarity, i ∈ { tag information, classification information, author information }, Si(B1) Information subset, S, representing the first set of characteristic informationi(B2) Information subset, Sim, representing said second set of characteristic information(i,i)(I1,I2) Representing the similarity of two information elements in the information subsets of the first characteristic information set and the information subsets of the second characteristic information set; i is1Denotes Si(B1) Any of the information elements in (1); i is2Denotes Si(B2) Any of the information elements in (1);
when I is1And I2When the same, Sim(i,i)(I1,I2)＝1；
When I is1And I2When the difference is not the same, the first and second substrates,
or
Sb(I1) Is represented by comprising I1E-book collection, Sb(I2) Is represented by comprising I2E-book collection of Sr(I1) Indicating that reading has covered I1Reader set of electronic book, Sr(I2) Indicating that reading has covered I2A collection of readers of the electronic book.
4. The method of any one of claims 1 to 3, wherein the obtaining a second similarity between the first electronic book and the second electronic book based on the at least one first similarity comprises:
obtaining each of the first similarities;
obtaining the product of each first similarity and the corresponding weight parameter;
and obtaining the sum of all the products as the second similarity.
5. The method of any of claims 1 to 3, further comprising:
obtaining a recommended electronic book of the first electronic book according to the second similarity;
and displaying the recommended electronic book.
6. The method of claim 5, wherein the displaying the recommended electronic book comprises:
displaying a recommendation page, wherein the recommendation page comprises a recommendation electronic book and at least one path node as follows: label, category, author;
the second similarity between the recommended electronic book and the first electronic book is obtained according to a first similarity corresponding to a path formed by path nodes selected by a user or a path formed by user behavior history, and the path formed by the path nodes selected by the user is a feature information set corresponding to the path nodes of the first electronic book and a path formed between the recommended electronic book and the feature information set corresponding to the path nodes.
7. An electronic book information processing method, characterized by comprising:
acquiring a first characteristic information set of a first electronic book which is currently displayed and a second characteristic information set of a second electronic book in an electronic book database;
obtaining at least one first similarity between at least one pair of different types of information subsets in the first set of feature information and the second set of feature information, the first similarity being obtained based on a similarity between any information element in the information subset of the first set of feature information and any information element in the information subset of the second set of feature information;
calculating a second similarity of the first electronic book and the second electronic book based on the at least one first similarity.
8. The method of claim 7, wherein the first set of feature information and the second set of feature information each comprise at least one of the following types of subsets of information: a tag information subset, a category information subset, an author information subset, and a reader information subset of the electronic book.
9. The method of claim 8, wherein said obtaining at least one first similarity between at least one pair of different types of information subsets in the first set of feature information and the second set of feature information comprises:
obtaining a third similarity of each information element in the information subset of the first characteristic information set and the first electronic book;
obtaining a fourth similarity of each information element in the information subset of the second characteristic information set and the second electronic book;
obtaining a fifth similarity between at least one pair of different types of information elements in the first set of feature information and the second set of feature information;
obtaining the at least one first similarity based on the third similarity, a fourth similarity, and the fifth similarity.
10. The method according to claim 9, wherein when information elements in the first feature information set and the second feature information set are author information, the third similarity and the fourth similarity are obtained as 1;
when the information elements in the first and second feature information sets are not author information, obtaining the third and fourth similarities by the following formulas:
where x ∈ { tag information, classification information, reader information }, NbRepresenting the number of electronic books in the electronic database; sx(B) A subset of information representing the first set of characteristic information or a subset of information representing the second set of characteristic information; k represents the number of electronic books containing the information element X; when X is any information element in the information subset of the first characteristic information set and B is the first electronic book, Sim(b,x)(B, X) is the third similarity; when X is any information element in the information subset of the second characteristic information set and B is the first electronic book, Sim(b,x)(B, X) is the fourth similarity.
11. The method of claim 10, wherein said obtaining a fifth degree of similarity between at least one pair of different types of information elements in the first set of feature information and the second set of feature information comprises:
the fifth similarity is obtained by the following formula:
wherein, Sim(i,j)(I1,J2) The fifth similarity is represented by I, j ∈ { label information, author information, classification information, reader information }, I and j are different in type, I1Represents one information element of the subset i of the first set of characteristic information, J2Represents one information element in the subset j of the second set of characteristic information; sb(I1) Is represented by comprising I1A collection of electronic books of (1); sb(J2) Is represented by the formula containing J2A collection of electronic books.
12. The method of claim 11, wherein the obtaining the at least one first similarity based on the third similarity, a fourth similarity, and the fifth similarity comprises:
obtaining the at least one first similarity by:
wherein, Sim(b,b)(B1,B2) Representing a first similarity; sim(b,i)(B1,I1) Representing the third similarity; sim(b,j)(B2,J2) Representing the fourth similarity.
13. The method of any one of claims 7 to 12, wherein the obtaining a second similarity between the first electronic book and the second electronic book based on the at least one first similarity comprises:
obtaining each of the first similarities;
obtaining the product of each first similarity and the corresponding weight parameter;
and obtaining the sum of all the products as the second similarity.
14. The method of any of claims 7 to 12, further comprising:
obtaining a recommended electronic book of the first electronic book according to the second similarity;
and displaying the recommended electronic book.
15. The method of claim 14, wherein the displaying the recommended electronic book comprises:
displaying a recommendation page, wherein the recommendation page comprises a recommendation electronic book and at least two path nodes as follows: label, category, author;
and obtaining the second similarity between the recommended electronic book and the first electronic book according to the first similarity corresponding to the path formed by the path nodes selected by the user or the path formed by the user behavior history.
16. An electronic book information processing apparatus, characterized in that the apparatus comprises:
the electronic book display device comprises a first obtaining unit, a second obtaining unit and a display unit, wherein the first obtaining unit is used for obtaining a first characteristic information set of a first electronic book which is displayed currently and a second characteristic information set of a second electronic book in an electronic book database;
a second obtaining unit, configured to obtain at least one first similarity between at least one pair of information subsets of the same type in the first feature information set and the second feature information set, where the first similarity is obtained based on a similarity between any information element in the information subset of the first feature information set and any information element in the information subset of the second feature information set;
a calculating unit, configured to calculate a second similarity between the first electronic book and the second electronic book based on the at least one first similarity.
17. An electronic book information processing apparatus, characterized in that the apparatus comprises:
the electronic book display device comprises a first obtaining unit, a second obtaining unit and a display unit, wherein the first obtaining unit is used for obtaining a first characteristic information set of a first electronic book which is displayed currently and a second characteristic information set of a second electronic book in an electronic book database;
a second obtaining unit, configured to obtain at least one first similarity between at least one pair of different types of information subsets in the first feature information set and the second feature information set, where the first similarity is obtained based on a similarity between any information element in the information subset of the first feature information set and any information element in the information subset of the second feature information set;
a calculating unit, configured to calculate a second similarity between the first electronic book and the second electronic book based on the at least one first similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510313663.3A CN106294502B (en) | 2015-06-09 | 2015-06-09 | Electronic book information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510313663.3A CN106294502B (en) | 2015-06-09 | 2015-06-09 | Electronic book information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106294502A CN106294502A (en) | 2017-01-04 |
| CN106294502B true CN106294502B (en) | 2020-06-23 |
Family
ID=57659985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510313663.3A Active CN106294502B (en) | 2015-06-09 | 2015-06-09 | Electronic book information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106294502B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109729126A (en) * | 2017-10-31 | 2019-05-07 | 北京国双科技有限公司 | Method for pushing, device, storage medium and the processor of textual resources |
| CN110555135B (en) * | 2018-03-27 | 2023-04-07 | 阿里巴巴（中国）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555131B (en) * | 2018-03-27 | 2023-04-07 | 阿里巴巴（中国）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555157B (en) * | 2018-03-27 | 2023-04-07 | 阿里巴巴（中国）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN109522488A (en) * | 2018-12-27 | 2019-03-26 | 上海连尚网络科技有限公司 | A kind of information recommendation method and equipment |
| CN111124988A (en) * | 2019-12-19 | 2020-05-08 | 掌阅科技股份有限公司 | Book display method based on book map, computing equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542046A (en) * | 2011-12-27 | 2012-07-04 | 纽海信息技术（上海）有限公司 | Book recommendation method based on book contents |
| CN102902744A (en) * | 2012-09-17 | 2013-01-30 | 杭州东信北邮信息技术有限公司 | Book recommendation method |
| CN103412880A (en) * | 2013-07-17 | 2013-11-27 | 百度在线网络技术（北京）有限公司 | Method and device for determining implicit associated information between multimedia resources |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140095148A1 (en) * | 2012-10-03 | 2014-04-03 | Kanjoya, Inc. | Emotion identification system and method |
| US10489842B2 (en) * | 2013-09-30 | 2019-11-26 | Ebay Inc. | Large-scale recommendations for a dynamic inventory |
-
2015
- 2015-06-09 CN CN201510313663.3A patent/CN106294502B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542046A (en) * | 2011-12-27 | 2012-07-04 | 纽海信息技术（上海）有限公司 | Book recommendation method based on book contents |
| CN102902744A (en) * | 2012-09-17 | 2013-01-30 | 杭州东信北邮信息技术有限公司 | Book recommendation method |
| CN103412880A (en) * | 2013-07-17 | 2013-11-27 | 百度在线网络技术（北京）有限公司 | Method and device for determining implicit associated information between multimedia resources |
Non-Patent Citations (1)
| Title |
|---|
| Feature Weighting in Content Based Recommendation System Using Social Network Analysis;Souvik Debnath 等;《Proceedings of the 17th international conference on World Wide Web》;20080421;第1041-1042页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106294502A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106294502B (en) | Electronic book information processing method and device | |
| Bannach-Brown et al. | Machine learning algorithms for systematic review: reducing workload in a preclinical review of animal studies and reducing human screening error | |
| Quercia et al. | Tweetlda: supervised topic classification and link prediction in twitter | |
| CN103164463B (en) | Method and device for recommending labels | |
| JP5717858B2 (en) | Text set matching | |
| US9600561B2 (en) | Computer-implemented system and method for generating an interest profile for a user from existing online profiles | |
| US9619481B2 (en) | Method and apparatus for generating ordered user expert lists for a shared digital document | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| US20170366632A1 (en) | Apparatus and method for processing information and program for the same | |
| AU2017250467B2 (en) | Query optimizer for combined structured and unstructured data records | |
| AU2013246140B2 (en) | Discovering spam merchants using product feed similarity | |
| CN108132963A (en) | Resource recommendation method and device, computing device and storage medium | |
| Bahamonde et al. | Power structure in Chilean news media | |
| US9390166B2 (en) | Specific online resource identification and extraction | |
| Mena et al. | On the Bayesian mixture model and identifiability | |
| Li et al. | A text-mining framework for supporting systematic reviews | |
| CN102289514A (en) | Social label automatic labelling method and social label automatic labeller | |
| CN111522886A (en) | Information recommendation method, terminal and storage medium | |
| CN115525838A (en) | Health knowledge recommendation method and system based on big data user portrait | |
| Faisal et al. | A novel framework for social web forums’ thread ranking based on semantics and post quality features | |
| Imhof et al. | Multimodal social book search | |
| CN103679502A (en) | Application recommendation method and system thereof | |
| TW201503041A (en) | Personalized textbook recommendation system | |
| CN107679121B (en) | Mapping method and device of classification system, storage medium and computing equipment | |
| CN104750692B (en) | A kind of information processing method, information retrieval method and its corresponding device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |