CN113076428A - Method and device for generating book list - Google Patents
Method and device for generating book list Download PDFInfo
- Publication number
- CN113076428A CN113076428A CN202110294908.8A CN202110294908A CN113076428A CN 113076428 A CN113076428 A CN 113076428A CN 202110294908 A CN202110294908 A CN 202110294908A CN 113076428 A CN113076428 A CN 113076428A
- Authority
- CN
- China
- Prior art keywords
- event
- book
- information
- propagation medium
- current propagation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000000977 initiatory effect Effects 0.000 claims description 21
- 230000004044 response Effects 0.000 claims description 20
- 238000012216 screening Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 11
- 230000001960 triggered effect Effects 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 25
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 230000000644 propagated effect Effects 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 210000003128 head Anatomy 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 210000001747 pupil Anatomy 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- KULDXINYXFTXMO-UHFFFAOYSA-N bis(2-chloroethyl) (3-chloro-4-methyl-2-oxochromen-7-yl) phosphate Chemical compound C1=C(OP(=O)(OCCCl)OCCCl)C=CC2=C1OC(=O)C(Cl)=C2C KULDXINYXFTXMO-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention discloses a method and a device for generating a book form, and relates to the technical field of computers. One embodiment of the method comprises: acquiring information of an event from network data; determining whether the event needs to respond according to the information of the event, and if so, generating a graph retrieval statement according to the information of the event; retrieving a book knowledge graph constructed in advance according to the graph retrieval statement to obtain a retrieval result; and generating a book list according to the retrieval result. According to the method and the system for generating the book list, the book list can be generated according to the network hot spot event, and books in the book list are more diverse.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for generating a book list.
Background
The e-commerce platform typically recommends books to users in the form of a book slip. In the existing method, books are generally screened from a book library according to attribute tags of readers, and then a book list is generated. For example, the attribute label of the reader is a pupil, and the method screens books suitable for the pupil to read from the book library to generate a book list. However, the attribute labels of the readers are relatively fixed, so that the book generated by the method is relatively single in content.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for generating a book form, which can generate a book form according to a network hotspot event, so that books in the book form are more diverse.
In a first aspect, an embodiment of the present invention provides a method for generating a book entry, including:
acquiring information of an event from network data;
determining whether the event needs to respond according to the information of the event, and if so, generating a graph retrieval statement according to the information of the event;
retrieving a book knowledge graph constructed in advance according to the graph retrieval statement to obtain a retrieval result;
and generating a book list according to the retrieval result.
Alternatively,
the determining whether the event needs to be responded according to the information of the event includes:
determining whether the information of the event meets a preset screening rule, if so, calculating the heat value of the event according to the information of the event;
and determining whether the event needs to be responded according to the heat value of the event.
Alternatively,
the information of the event comprises: initiating a subject, a theme, and content;
the screening rule comprises the following steps: the initiating main body is a designated initiating main body, the theme is a designated theme, and the similarity between the keywords of the content and the designated keywords is greater than a similarity threshold value.
Alternatively,
the information of the event comprises: a plurality of current propagation media and user behavior data of the current propagation media;
the calculating the heat value of the event according to the information of the event comprises the following steps:
calculating the heat value of the current propagation medium according to the current propagation medium and the user behavior data thereof;
and calculating the heat value of the event according to the heat value of each current propagation medium.
Alternatively,
the calculating the heat value of the current propagation medium according to the current propagation medium and the user behavior data thereof comprises:
determining the medium score of the current propagation medium according to the corresponding relation between the pre-configured propagation medium and the medium score;
calculating a propagation value of the current propagation medium according to the medium score and the medium weight coefficient of the current propagation medium;
calculating the attention value of the current propagation medium according to the user behavior data and the behavior weight coefficient of the current propagation medium;
and calculating the heat value of the current propagation medium according to the propagation value and the attention value of the current propagation medium.
Alternatively,
the determining whether the event needs to be responded according to the heat value of the event comprises the following steps:
and determining whether the heat value of the event is greater than a pre-configured heat threshold value, and if so, determining whether the event meets a pre-configured response condition according to the information of the event.
Alternatively,
the response condition includes: the number of covered people of the event exceeds a preset number threshold, the search ranking of the event in the propagation medium exceeds a preset rank, the event is displayed on the head of the propagation medium, and the event is matched with a preset book marketing item.
Alternatively,
when the heat value of the event is greater than the heat threshold, before determining whether the event satisfies a preconfigured response condition according to the information of the event, the method further includes:
determining an initial publisher of the event according to the information of the event;
and verifying whether the event is real or not according to the initial publisher of the event, and if so, executing the information according to the event to determine whether the event meets a preset response condition or not.
Alternatively,
further comprising:
extracting book features from the book information;
extracting entities, attributes of the entities and relations among the entities from the book features;
performing entity alignment and entity disambiguation on the entities;
and constructing the book knowledge graph according to the processed entities, the attributes of the entities and the relationship among the entities.
Alternatively,
further comprising:
adding the book slip to the book knowledge graph; wherein the book order is associated with an entity in the book knowledge-graph.
In a second aspect, an embodiment of the present invention provides a book list generating apparatus, including:
the acquisition module is configured to acquire the information of the event from the network data;
the determining module is configured to determine whether the event needs to be responded according to the information of the event, and if so, the retrieving module is triggered;
the retrieval module is configured to generate a graph retrieval statement according to the information of the event; retrieving a book knowledge graph constructed in advance according to the graph retrieval statement to obtain a retrieval result;
and the generating module is configured to generate a book list according to the retrieval result.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method as in any one of the embodiments described above.
In a fourth aspect, the present invention provides a computer readable medium, on which a computer program is stored, and when the program is executed by a processor, the computer program implements the method according to any one of the above embodiments.
One embodiment of the above invention has the following advantages or benefits: the method generates the book list based on the information of the events and the established book knowledge graph, not only considers the attention degree of readers to the events occurring in the network, but also considers the correlation among books, so that the content of the book list can be richer, and the diversity and the accuracy of book recommendation are further improved.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a flow chart of a method for generating a book form according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for book recommendation provided by an embodiment of the present invention;
FIG. 3 is a flow chart of a method for generating a book form according to another embodiment of the present invention;
FIG. 4 is a schematic diagram of a book form generation apparatus provided by an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 6 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
As shown in fig. 1, an embodiment of the present invention provides a book sheet generation method, including:
step 101: and acquiring the information of the event from the network data.
The embodiment of the invention can acquire the network data through the crawler, and the network data can be from a book forum, a social platform, a publisher website and the like. One or more events may be included in the network data.
The information of the event may include: topics, content, propagation media, sponsoring bodies, and the like. For example, blogger Q posted a message "subway line 1 failed," which was then forwarded and reviewed extensively in the social platform. For the event of 'subway No. 1 line failure', the initiating main body is the blogger Q, the content of the event is 'subway No. 1 line failure', the theme of the event is 'subway failure', and besides, the information of the event can also comprise: the level, the number of fans, the topic popularity and the like of the blogger Q on the social platform.
Step 102: and determining whether the event needs to respond according to the information of the event, if so, executing step 103, otherwise, executing step 106.
And if the response is needed, generating a book list according to the information of the event, otherwise, terminating the current flow. Specifically, whether to trigger generation of the book list can be determined according to the heat degree of the event, and whether to trigger generation of the book list can also be determined according to the content of the event, the theme of the event and the like.
Step 103: and generating a graph search statement according to the information of the event.
Specifically, the graph search statement may be generated according to the subject of the event (e.g., a person, a historical knowledge point, a technology point, etc.), the audience of the event, and other information.
Step 104: and retrieving the book knowledge graph constructed in advance according to the graph retrieval statement to obtain a retrieval result.
The book knowledge graph is obtained by constructing the information of the book before retrieval.
Step 105: and generating a book list according to the retrieval result.
And splicing the searched information such as the name, introduction, recommendation reason and the like of the book into a book list. The book list may be presented to the user in the form of a web page or a picture.
Step 106: the current flow is terminated.
The method generates the book list based on the information of the events and the established book knowledge graph, not only considers the attention degree of readers to the events occurring in the network, but also considers the correlation among books, so that the content of the book list can be richer, and the diversity and the accuracy of book recommendation are further improved.
In one embodiment of the present invention, determining whether an event needs to be responded according to information of the event includes:
calculating a heat value of the event according to the information of the event;
and determining whether the event needs to respond according to the heat value of the event.
In the embodiment of the invention, the heat value of the event is used for representing the heat of the event, and whether the event is responded is determined according to the heat of the event. In an actual application scenario, whether to respond to an event can be determined according to information such as a topic and an initiating subject of the event.
Because a plurality of events may be included in the network data, and the correlation between some events and books is low, in an embodiment of the present invention, the events with higher correlation are screened out by the screening rule to be used for generating the book list, so that the subsequent calculation amount can be reduced. At this time, determining whether the event needs to be responded according to the information of the event includes:
determining whether the information of the event meets a preset screening rule, if so, calculating the heat value of the event according to the information of the event;
and determining whether the event needs to respond according to the heat value of the event.
In one embodiment of the invention, the information of the event comprises: initiating a subject, a theme, and content;
a screening rule comprising: the initiating main body is a designated initiating main body, the theme is a designated theme, and the similarity between the keywords of the content and the designated keywords is greater than a similarity threshold.
Specifically, the initiating agent of the event is screened through a screening rule, for example, the initiating agent is screened out as an event of a trusted public number (i.e., a designated initiating agent); performing NLP (Natural Language Processing) analysis on the event obtained by screening to extract the theme and content of the event; screening the subject of the event based on the screening rule, for example, screening the event with the subject of "big data" (i.e. the specified subject); and screening the contents meeting the screening rule according to the similarity between the keywords of the contents and the specified keywords configured in the screening rule, and further obtaining the events meeting the screening rule. The embodiment of the invention screens the event from the three layers of the initiation main body, the theme and the content of the event based on the screening rule. In an actual application scenario, the event may be filtered only according to the initiating subject, topic or content, or may be filtered according to information such as a propagation medium.
In one embodiment of the present invention, the information of the event includes: a plurality of current propagation media and user behavior data of the current propagation media;
calculating a heat value of the event according to the information of the event, comprising:
calculating the heat value of the current propagation medium according to the current propagation medium and the user behavior data;
and calculating the heat value of the event according to the heat value of each current propagation medium.
Events can be propagated through different propagation media, such as microblogs, circle of friends, and the like. The user behavior may include: like, comment, forward, browse, etc. The heat value of the event can be the sum of the heat values of the current propagation mediums, or can be determined by the heat value of the current propagation mediums and the weighting coefficients thereof. The embodiment of the invention considers the difference of different transmission media, so that the heat value of the current transmission medium is more accurate, and the heat of the event is more accurately measured. In an actual application scenario, the propagation medium may not be distinguished, and the heat value of the event is calculated based on the user behavior data, which is not described herein again.
In one embodiment of the present invention, calculating the heat value of the current propagation medium according to the current propagation medium and the user behavior data thereof includes:
determining the medium score of the current propagation medium according to the corresponding relation between the pre-configured propagation medium and the medium score;
calculating the propagation value of the current propagation medium according to the medium score and the medium weight coefficient of the current propagation medium;
calculating the attention value of the current propagation medium according to the user behavior data and the behavior weight coefficient of the current propagation medium;
and calculating the heat value of the current propagation medium according to the propagation value and the attention value of the current propagation medium.
The medium weight coefficient and the behavior weight coefficient are used for measuring the importance of the propagation medium and the user behavior data to the heat value of the current propagation medium. The medium score is used to distinguish the propagation values of different propagation media. The current heat value of the propagation medium is the sum of its propagation value and the value of interest. And the attention value of the current propagation medium is used for representing the attention degree of the user to the event propagated through the current propagation medium. The propagation value of the current propagation medium is used to characterize the ability of the current propagation medium to propagate the event. Therefore, the heat value of the current propagation medium not only considers the propagation range of the event, but also considers the attention of the user to the propagation event, and a more accurate heat value of the current propagation medium can be obtained.
The user behavior data may include different user behaviors, and at this time, weights of the different user behaviors may be distinguished or may not be distinguished. For example, the user behavior data includes a forwarding number and a comment number, if distinguished, the behavior weight coefficient includes a forwarding weight coefficient and a comment weight coefficient, and the attention value of the current propagation medium is the forwarding number × the forwarding weight coefficient + the comment number × the comment weight coefficient; if not, the attention value of the current propagation medium is (forwarding number + comment number) multiplied by a behavior weight coefficient.
In one embodiment of the invention, determining whether the event needs to respond according to the heat value of the event comprises the following steps:
and determining whether the heat value of the event is greater than a pre-configured heat threshold value, and if so, determining whether the event meets pre-configured response conditions according to the information of the event.
And when the heat value of the event exceeds a heat threshold, determining that the event is a hot event, in order to improve the quality of the generated book list and further improve the accuracy of book recommendation, further screening the event through configured response conditions after determining that the event is the hot event. In an actual application scenario, the system can also directly respond to the hot event, that is, when the heat value of the event is greater than the heat threshold, a graph retrieval statement is generated according to the information of the event.
In one embodiment of the invention, the response conditions include: the number of covered people of the event exceeds a preset number threshold, the search ranking of the event in the propagation medium exceeds a preset rank, the head edition of the event displayed in the propagation medium, and the matching of the event and the preset book marketing item.
In the embodiment of the invention, the response condition can be configured according to the service requirement. For example, the configured response condition is that "the number of persons covered by the event exceeds a pre-configured number threshold", at which time, based on the information of the event, the number of persons covered by the event is determined, and it is determined whether the number of persons covered is greater than the number threshold. And if the configured response condition is that the search ranking of the event in the propagation medium exceeds the pre-configured rank, determining the search ranking of the event in the propagation medium according to the information of the event, and determining whether the search ranking exceeds the configured rank. In a practical application scenario, whether the event is matched with the book marketing item can be determined through the correlation between the topic of the event and the book marketing item. For example, the subject of the event is "the dynasty of the large number of dynasties", the content of the book marketing item includes discount sales promotion for the history books of the spring and autumn warring countries, and the event is determined to match the book marketing item configured in advance because the correlation between the "dynasty of the large number of dynasties" and the "history books of the spring and autumn warring countries" exceeds a set value. The e-commerce platform can respond to events with larger business relevance by configuring book marketing items so as to meet the promotion and popularization requirements.
In an embodiment of the present invention, when the heat value of the event is greater than the heat threshold, before determining whether the event satisfies the preconfigured response condition according to the information of the event, the method further includes:
determining an initial publisher of the event according to the information of the event;
and verifying whether the event is real or not according to the initial publisher of the event, and if so, determining whether the event meets a preset response condition or not according to the information of the event.
The embodiment of the invention verifies the authenticity of the event through the initial publisher of the event so as to reduce the influence of the false event on the quality of the book sheet. Specifically, the authenticity of the event may be verified based on information such as the original publisher's identification number, registration ID, etc.
In one embodiment of the invention, the method further comprises: extracting book features from the book information;
extracting entities, attributes of the entities and relations among the entities from book features;
performing entity alignment and entity disambiguation on entities;
and constructing a book knowledge graph according to the processed entities, the attributes of the entities and the relationship among the entities.
Wherein the book features include: title, author, domain, catalog, abstract outline, etc. And performing NLP analysis on the book information to extract book features from the book information. The book features include: title, author, translator, publisher, publication date, page number, introduction, domain direction, category, outline of subject matter, category, rating, whether it is a book cluster, etc.
And extracting the entities, the attributes of the entities and the relationships among the entities from the book characteristics. For example, the title is Usner, the author is le Pont, the translator is von Kley, the publisher is the Central compilation publisher, the field is psychology, the publication date is 2011.5.1, and the number of pages is 183. The entities extracted from the book features may be the members of the unaided family, psychology. Attributes of the masses of Uygur include: author, translator, publisher, date and number of publication, attribute values of luxon, von krey, central compilation publisher, 2011.5.1 and 183, respectively. The relationship between the masses of the unaided human beings and psychology is: the public at large belongs to the field of psychology. The embodiment of the invention takes the book name and the field as the entity to construct the knowledge graph, and in other application scenes, the book name, the publishing company and the author can also be taken as the entity to construct the knowledge graph so as to meet the requirements of different scenes.
The embodiment of the invention improves the quality of the book knowledge graph through entity alignment and entity disambiguation. According to the embodiment of the invention, the book knowledge graph is established through the association between the book information, so that the quality of the book list is improved.
In one embodiment of the invention, the method further comprises: adding the book list into the book knowledge graph; wherein the book order is associated with an entity in the book knowledge-graph.
The generated book order can be added to the book knowledge graph for subsequent recommendation of the associated book order.
As shown in fig. 2, an embodiment of the present invention provides a method for recommending a book list, including:
step 201: and acquiring the information of the event from the network data.
Step 202: and determining whether the event needs to respond according to the information of the event, if so, executing step 203, otherwise, executing step 207.
Step 203: and generating a graph search statement according to the information of the event.
Step 204: and retrieving the book knowledge graph constructed in advance according to the graph retrieval statement to obtain a retrieval result.
Step 205: and generating a book list according to the retrieval result.
Step 206: and recommending the book list to the user.
In an actual application scenario, if the entity associates with other book sheets, both the book sheet generated in step 205 and the book sheet associated with the entity may be recommended to the user, so as to improve recommendation diversity. The method can recommend the book list to the user through the recommendation system, and can also directly recommend the book list to the user.
Step 207: the current flow is terminated.
The embodiment of the invention can recommend the book list to the user based on the events occurring in the network, thereby improving the diversity of book list recommendation.
As shown in fig. 3, an embodiment of the present invention provides a book sheet generation method, including:
step 301: and acquiring the information of the event from the network data.
And crawling the book forum and the publisher website to obtain the information of the event 1 and the information of the event 2. The following description will be made by taking event 1 as an example. The information of event 1 includes: the content is 'Daqin king dynasty TV drama hot broadcast', the subject is 'Daqin dynasty', the initiating subject is a blogger M, the current propagation media are book forums and publisher websites, the sum of the number of the book forums and the number of the comments is 100, and the number of the publisher websites and the number of the comments are 200.
Step 302: it is determined whether the subject of the event is the specified subject, if so, step 303 is performed, otherwise, step 313 is performed.
The pre-configured specified topics include: "big data", "haze", "the dynasty of the large Qin", the subject of the event belongs to the specified subject.
Step 303: and calculating the heat value of the event according to the information of the event.
The media scores of the pre-configured book forum and publisher sites are 20 and 10, respectively. The pre-configured medium weight coefficient is 0.4 and the behavior weight coefficient is 0.6. The dissemination value of the book forum is 20 × 0.4 ═ 8, and the dissemination value of the publisher website is 10 × 0.4 ═ 4.
The interest value of the book forum is 100 × 0.6 ═ 60, and the interest value of the publisher website is 200 × 0.6 ═ 120.
The popularity of the book forum is 8+ 60-68, and the popularity of the publisher site is 4+ 120-124.
The heat value of the event is 68+124 192.
Step 304: it is determined whether the heat value of the event is greater than a preconfigured heat threshold, if so, step 305 is performed, otherwise, step 313 is performed.
Step 305: and determining an initial publisher of the event according to the information of the event.
The initial publisher of the event can be traced according to the initiating subject of the event, for example, the blogger N publishes a dynamic state, after the blogger M forwards the state, the content of the dynamic state becomes a hot event, and the initial publisher of the event can be traced to be the blogger N according to the information of the event.
Step 306: verifying whether the event is real according to the initial publisher of the event, if so, executing step 307, otherwise, executing step 313.
The embodiment of the invention verifies the registered account number of the blogger N to determine whether the event 1 is real or not.
Step 307: and determining the number of covered persons of the event according to the information of the event.
And determining the number of coverage persons of the event according to the propagation medium and the content of the event. For example, the propagation medium is a book forum, the content is college entrance reform, and since the audience of the content is generally a teacher, a senior high school student and a senior high school student parent, the sum of the number of registered users who are the teacher, the senior high school student and the senior high school student parent is taken as the number of event coverage.
Step 308: it is determined whether the number of people covered by the event is greater than a number threshold, if so, step 309 is performed, otherwise, step 313 is performed.
Step 309: and generating a graph search statement according to the information of the event and the preset constraint condition.
The constraints may include: the minimum number of books in the book list, the maximum number of books in the book list, the language of the books in the book list, the attention degree of the books in the book list, the number of good comments in the books in the book list and the like.
According to the embodiment of the invention, a graph retrieval statement is generated according to the subject, the audience and the constraint condition of an event, and MATCH (a: Book (subject: history ', dynasty: Qin dynasty', level: Volkswagen)) unit MATCH (b: Book (subject: history ', dynasty: Chun autumn warrious', counter: Qin dynasty ', level: Volkswagen') RERN DISTINCT Book LIMIT 10 is generated.
Step 310: and retrieving the book knowledge graph constructed in advance according to the graph retrieval statement to obtain a retrieval result.
The construction of the book knowledge graph is performed prior to step 301 and will not be described in detail herein.
Step 311: and generating a book list according to the retrieval result.
And splicing the searched node information into a book list, such as book names, brief introduction and the like.
Step 312: adding the book list into the book knowledge graph; wherein the book order is associated with an entity in the book knowledge-graph.
Step 313: the current flow is terminated.
The embodiment of the invention can generate the book list according to the events with higher heat in the network, meet the interest of the user along with the hot events and improve the diversity of the contents of the book list.
As shown in fig. 4, an embodiment of the present invention provides a book sheet generation apparatus, including:
an obtaining module 401 configured to obtain information of an event from network data;
a determining module 402 configured to determine whether the event needs to be responded according to the information of the event, and if so, trigger the retrieving module 403;
a retrieval module 403 configured to generate a graph retrieval statement according to the information of the event; retrieving a book knowledge graph constructed in advance according to the graph retrieval sentences to obtain retrieval results;
and a generating module 404 configured to generate a book list according to the retrieval result.
In an actual application scenario, when determining that the event needs to respond, the determining module 402 may generate notification information, and trigger the retrieving module 403 by sending the notification information. The notification information may include information such as the subject, audience, etc. of the event.
In an embodiment of the present invention, the determining module 402 is configured to determine whether the information of the event satisfies a pre-configured filtering rule, and if so, calculate a heat value of the event according to the information of the event; and determining whether the event needs to respond according to the heat value of the event.
In one embodiment of the invention, the information of the event comprises: initiating a subject, a theme, and content; a screening rule comprising: the initiating main body is a designated initiating main body, the theme is a designated theme, and the similarity between the keywords of the content and the designated keywords is greater than a similarity threshold.
In one embodiment of the present invention, the information of the event includes: a plurality of current propagation media and user behavior data of the current propagation media; a determining module 402 configured to calculate a heat value of the current propagation medium according to the current propagation medium and user behavior data thereof; and calculating the heat value of the event according to the heat value of each current propagation medium.
In an embodiment of the present invention, the determining module 402 is configured to determine the medium score of the current propagation medium according to a pre-configured correspondence relationship between the propagation medium and the medium score; calculating the propagation value of the current propagation medium according to the medium score and the medium weight coefficient of the current propagation medium; calculating the attention value of the current propagation medium according to the user behavior data and the behavior weight coefficient of the current propagation medium; and calculating the heat value of the current propagation medium according to the propagation value and the attention value of the current propagation medium.
In one embodiment of the invention, the determining module 402 is configured to determine whether the heat value of the event is greater than a preconfigured heat threshold, and if so, determine whether the event satisfies a preconfigured response condition according to the information of the event.
In one embodiment of the invention, the response conditions include: the number of covered people of the event exceeds a preset number threshold, the search ranking of the event in the propagation medium exceeds a preset rank, the head edition of the event displayed in the propagation medium, and the matching of the event and the preset book marketing item.
In an embodiment of the present invention, the determining module 402 is configured to determine an initial publisher of the event according to the information of the event when the heat value of the event is greater than the heat threshold; and verifying whether the event is real or not according to the initial publisher of the event, and if so, determining whether the event meets a preset response condition or not according to the information of the event.
In an embodiment of the present invention, the obtaining module 401 is configured to extract book features from book information; extracting entities, attributes of the entities and relations among the entities from book features; performing entity alignment and entity disambiguation on entities; and constructing a book knowledge graph according to the processed entities, the attributes of the entities and the relationship among the entities.
In one embodiment of the invention, the generation module 404 is configured to add the book order to the book knowledge-graph; wherein the book order is associated with an entity in the book knowledge-graph.
An embodiment of the present invention provides an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method of any of the embodiments as described above.
Embodiments of the present invention provide a computer-readable medium, on which a computer program is stored, which when executed by a processor implements the method according to any of the above embodiments.
Fig. 5 shows an exemplary system architecture 500 of a book list generation method or apparatus to which an embodiment of the present invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server providing various services, such as a background management server (for example only) providing support for shopping websites browsed by users using the terminal devices 501, 502, 503. The backend management server may analyze and perform other processing on the received data such as the product information query request, and feed back a processing result (for example, target push information, product information — just an example) to the terminal device.
It should be noted that the book list generation method provided in the embodiment of the present invention is generally executed by the server 505, and accordingly, the book list generation apparatus is generally disposed in the server 505.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use with a terminal device implementing an embodiment of the invention is shown. The terminal device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a sending module, an obtaining module, a determining module, and a first processing module. The names of these modules do not form a limitation on the modules themselves in some cases, and for example, the sending module may also be described as a "module sending a picture acquisition request to a connected server".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise:
acquiring information of an event from network data;
determining whether the event needs to respond according to the information of the event, and if so, generating a graph retrieval statement according to the information of the event;
retrieving a book knowledge graph constructed in advance according to the graph retrieval statement to obtain a retrieval result;
and generating a book list according to the retrieval result.
According to the technical scheme of the embodiment of the invention, the attention degree of readers to events occurring in the network is considered, the correlation among books is also considered, the contents of the book list can be richer, and the diversity and the accuracy of book recommendation are further improved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (13)
1. A method for generating a book slip, comprising:
acquiring information of an event from network data;
determining whether the event needs to respond according to the information of the event, and if so, generating a graph retrieval statement according to the information of the event;
retrieving a book knowledge graph constructed in advance according to the graph retrieval statement to obtain a retrieval result;
and generating a book list according to the retrieval result.
2. The method of claim 1,
the determining whether the event needs to be responded according to the information of the event includes:
determining whether the information of the event meets a preset screening rule, if so, calculating the heat value of the event according to the information of the event;
and determining whether the event needs to be responded according to the heat value of the event.
3. The method of claim 2,
the information of the event comprises: initiating a subject, a theme, and content;
the screening rule comprises the following steps: the initiating main body is a designated initiating main body, the theme is a designated theme, and the similarity between the keywords of the content and the designated keywords is greater than a similarity threshold value.
4. The method of claim 2,
the information of the event comprises: a plurality of current propagation media and user behavior data of the current propagation media;
the calculating the heat value of the event according to the information of the event comprises the following steps:
calculating the heat value of the current propagation medium according to the current propagation medium and the user behavior data thereof;
and calculating the heat value of the event according to the heat value of each current propagation medium.
5. The method of claim 4,
the calculating the heat value of the current propagation medium according to the current propagation medium and the user behavior data thereof comprises:
determining the medium score of the current propagation medium according to the corresponding relation between the pre-configured propagation medium and the medium score;
calculating a propagation value of the current propagation medium according to the medium score and the medium weight coefficient of the current propagation medium;
calculating the attention value of the current propagation medium according to the user behavior data and the behavior weight coefficient of the current propagation medium;
and calculating the heat value of the current propagation medium according to the propagation value and the attention value of the current propagation medium.
6. The method of claim 2,
the determining whether the event needs to be responded according to the heat value of the event comprises the following steps:
and determining whether the heat value of the event is greater than a pre-configured heat threshold value, and if so, determining whether the event meets a pre-configured response condition according to the information of the event.
7. The method of claim 6,
the response condition includes: the number of covered people of the event exceeds a preset number threshold, the search ranking of the event in the propagation medium exceeds a preset rank, the event is displayed on the head of the propagation medium, and the event is matched with a preset book marketing item.
8. The method of claim 6,
when the heat value of the event is greater than the heat threshold, before determining whether the event satisfies a preconfigured response condition according to the information of the event, the method further includes:
determining an initial publisher of the event according to the information of the event;
and verifying whether the event is real or not according to the initial publisher of the event, and if so, executing the information according to the event to determine whether the event meets a preset response condition or not.
9. The method of claim 1, further comprising:
extracting book features from the book information;
extracting entities, attributes of the entities and relations among the entities from the book features;
performing entity alignment and entity disambiguation on the entities;
and constructing the book knowledge graph according to the processed entities, the attributes of the entities and the relationship among the entities.
10. The method of any one of claims 1-9, further comprising:
adding the book slip to the book knowledge graph; wherein the book order is associated with an entity in the book knowledge-graph.
11. A sheet generation apparatus, comprising:
the acquisition module is configured to acquire the information of the event from the network data;
the determining module is configured to determine whether the event needs to be responded according to the information of the event, and if so, the retrieving module is triggered;
the retrieval module is configured to generate a graph retrieval statement according to the information of the event; retrieving a book knowledge graph constructed in advance according to the graph retrieval statement to obtain a retrieval result;
and the generating module is configured to generate a book list according to the retrieval result.
12. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-10.
13. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110294908.8A CN113076428A (en) | 2021-03-19 | 2021-03-19 | Method and device for generating book list |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110294908.8A CN113076428A (en) | 2021-03-19 | 2021-03-19 | Method and device for generating book list |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113076428A true CN113076428A (en) | 2021-07-06 |
Family
ID=76612997
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110294908.8A Pending CN113076428A (en) | 2021-03-19 | 2021-03-19 | Method and device for generating book list |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113076428A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108268619A (en) * | 2018-01-08 | 2018-07-10 | 阿里巴巴集团控股有限公司 | Content recommendation method and device |
| CN108520076A (en) * | 2018-04-19 | 2018-09-11 | 掌阅科技股份有限公司 | E-book recommends method, electronic equipment and computer storage media |
| CN108763519A (en) * | 2018-05-30 | 2018-11-06 | 深圳市零度智控科技有限公司 | The recommendation method, apparatus and readable storage medium storing program for executing of reading |
| CN109885772A (en) * | 2019-02-27 | 2019-06-14 | 上海优谦智能科技有限公司 | The education content personalized recommendation system of knowledge based map |
| US20190332946A1 (en) * | 2018-04-30 | 2019-10-31 | Facebook, Inc. | Combining machine-learning and social data to generate personalized recommendations |
| CN110737774A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Book knowledge graph construction method, book recommendation method, device, equipment and medium |
| CN111159546A (en) * | 2019-12-24 | 2020-05-15 | 腾讯科技（深圳）有限公司 | Event pushing method and device, computer readable storage medium and computer equipment |
-
2021
- 2021-03-19 CN CN202110294908.8A patent/CN113076428A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108268619A (en) * | 2018-01-08 | 2018-07-10 | 阿里巴巴集团控股有限公司 | Content recommendation method and device |
| CN108520076A (en) * | 2018-04-19 | 2018-09-11 | 掌阅科技股份有限公司 | E-book recommends method, electronic equipment and computer storage media |
| US20190332946A1 (en) * | 2018-04-30 | 2019-10-31 | Facebook, Inc. | Combining machine-learning and social data to generate personalized recommendations |
| CN108763519A (en) * | 2018-05-30 | 2018-11-06 | 深圳市零度智控科技有限公司 | The recommendation method, apparatus and readable storage medium storing program for executing of reading |
| CN110737774A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Book knowledge graph construction method, book recommendation method, device, equipment and medium |
| CN109885772A (en) * | 2019-02-27 | 2019-06-14 | 上海优谦智能科技有限公司 | The education content personalized recommendation system of knowledge based map |
| CN111159546A (en) * | 2019-12-24 | 2020-05-15 | 腾讯科技（深圳）有限公司 | Event pushing method and device, computer readable storage medium and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 李飞;张健;王宗水;: "社会化推荐研究进展与发展趋势演化――基于文献计量和社会网络分析的视角", 数据分析与知识发现, no. 06 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10567329B2 (en) | Methods and apparatus for inserting content into conversations in on-line and digital environments | |
| CN109145280B (en) | Information pushing method and device | |
| US9374396B2 (en) | Recommended content for an endorsement user interface | |
| US10530899B2 (en) | Method and system for establishing a trust association | |
| US8447643B2 (en) | System and method for collecting and distributing reviews and ratings | |
| US20130198204A1 (en) | System and method determining online significance of content items and topics using social media | |
| US20150261760A1 (en) | Providing recommendations on a social networking system page | |
| US10230672B2 (en) | Inserting a search box into a mobile terminal dialog messaging protocol | |
| US10282752B2 (en) | Computerized system and method for displaying a map system user interface and digital content | |
| US20120041826A1 (en) | Method for Transformation of a Website | |
| US20150106156A1 (en) | Input/output interface for contextual analysis engine | |
| US20170109838A1 (en) | Cognitive Marketing Based on Social Networking of Positive Reviewers | |
| CN107526718B (en) | Method and device for generating text | |
| WO2015002830A1 (en) | Social network for employment search | |
| CN112771564A (en) | Artificial intelligence engine that generates semantic directions for web sites to map identities for automated entity seeking | |
| EP3905177A1 (en) | Recommending that an entity in an online system create content describing an item associated with a topic having at least a threshold value of a performance metric and to add a tag describing the item to the content | |
| JP2019212345A (en) | Internet content providing server and computer-readable recording medium including implemented method therefor | |
| CN107885872B (en) | Method and device for generating information | |
| CN113076428A (en) | Method and device for generating book list | |
| CN109408725B (en) | Method and apparatus for determining user interest | |
| TWI627545B (en) | Online community media instant news screening and notification method | |
| US10991037B1 (en) | Analyzing tracking requests generated by client devices based on metadata describing web page of a third party website | |
| CN114238229B (en) | Print file searching method and device, electronic equipment and storage medium | |
| CN113781150A (en) | Article recommendation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |