CN117668373B - Cascade label recommendation method and device, electronic equipment and storage medium - Google Patents
Cascade label recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117668373B CN117668373B CN202410145859.5A CN202410145859A CN117668373B CN 117668373 B CN117668373 B CN 117668373B CN 202410145859 A CN202410145859 A CN 202410145859A CN 117668373 B CN117668373 B CN 117668373B
- Authority
- CN
- China
- Prior art keywords
- label
- cascade
- labels
- tag
- application object
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000004044 response Effects 0.000 claims description 11
- 230000015654 memory Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 description 10
- 238000012423 maintenance Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000002131 composite material Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
- G06F16/9538—Presentation of query results
-
- 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
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a cascade label recommending method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps of pre-configuring cascade relations among a plurality of labels of a target application object and a plurality of labels through attribute features of the application object to obtain a cascade label library, after receiving the target application object uploaded by a user side, responding to the target application object to meet label recommendation conditions, determining a first label in the cascade label library, determining a classification position of the first label in the cascade label library, determining cascade groups corresponding to the first label according to the classification position, selecting candidate labels with the correlation degree meeting a preset threshold value from second labels included in all the cascade groups according to the correlation degree of each second label in the cascade groups for each cascade group, sending the candidate labels to the user side, determining the target label selected by the user based on user selection, adding the target label to the target application object, and displaying the target label of the target application object at the user side.
Description
Technical Field
The application relates to the technical field of computers, in particular to a cascade label recommending method, a cascade label recommending device, electronic equipment and a storage medium.
Background
With the continuous development of the internet, related contents conforming to the individuation of users are often required to be recommended to the users in the scenes of teaching, shopping and the like, so that the users can obtain the contents widely.
At present, related contents are recommended to a user mainly through a plurality of recommendation systems based on collaborative filtering, content filtering, knowledge graph, context awareness and the like.
However, the existing recommendation system has the disadvantages of complex algorithm, relatively high operation requirement on staff and high maintenance cost, and is difficult to apply to small and medium-scale enterprises.
Disclosure of Invention
In view of the above, the present application aims to provide a cascade tag recommendation method, apparatus, electronic device and storage medium, by pre-configuring a cascade tag library, determining a candidate tag according to a first tag in the cascade tag library to send to a user, and determining a target tag selected by a user to add the target tag to a target application object, only the cascade tag library needs to be pre-configured, the recommendation algorithm is simpler, the operation requirement on staff is reduced, and the maintenance cost is lower, so that the cascade tag recommendation method is easy to apply in small and medium-scale enterprises.
In a first aspect, an embodiment of the present application provides a cascading label recommendation method, which is applied to a server, and the method includes:
According to the attribute characteristics of the application object, preconfiguring a plurality of labels of a target application object and cascading relations among the labels to obtain a cascading label library applicable to the target application object;
after receiving a target application object uploaded by a user side, responding to the target application object meeting a label recommendation condition, determining a first label in the cascade label library, and determining a classification position of the first label in the cascade label library;
Determining a cascade group corresponding to the first tag according to the classification position of the first tag in the cascade tag library; wherein each cascade group comprises a first label and a second label which has a direct or indirect cascade relation with the first label;
selecting candidate labels with the correlation degree meeting a preset threshold value from second labels included in all cascade groups according to the correlation degree of each second label in the cascade groups and the first label aiming at each cascade group, and sending the candidate labels to a user side so as to push the candidate labels to the user side;
and responding to a selection instruction of a user on the candidate labels, determining the target label selected by the user, adding the target label for the target application object, and displaying the target label of the target application object at the user side.
In one possible embodiment, the determining the first tag in the cascade tag library includes at least one of:
Determining a first label based on the label input by the user aiming at the target application object;
Determining a first label based on a label selected by a user from a basic label group recommended by the server for the target application object; the base tag set includes one of the following categories of tags: a target history tag; a plurality of tags at any stage in the cascade tag library; and a plurality of labels in any cascade group in the cascade label library.
In one possible implementation, the server recommends the basic tag set by a method comprising:
acquiring identification information of the target application object, and determining a target category label of the basic label group through the identification information; the identification information comprises a name and/or description information of the target application object;
And determining one or more labels included in the target category label, and generating a basic label group matched with the target application object according to the one or more labels.
In one possible implementation, determining the target history tag in the base tag set includes:
counting history labels selected by a user in a preset history time period;
For each history tag, determining the comprehensive score of the history tag according to the selection times of the user on the history tag and the importance of the history tag in a preset history time period; the importance is determined according to the category to which the history tag belongs and the importance identification of the history tag in the category;
A first tag is determined from a plurality of the history tags based on the combined score for each history tag.
In one possible implementation manner, the pre-configuring the cascade relationship between the plurality of tags of the target application object and the plurality of tags according to the attribute characteristics of the application object includes:
Acquiring attribute characteristics of the application object, and determining a plurality of levels of the application object and a plurality of labels of each level according to the attribute characteristics;
And establishing connection between a plurality of labels of any two levels by analyzing the characteristic relation among the attribute characteristics to obtain a cascade relation among the plurality of labels of the multiple levels.
In a possible implementation manner, the selecting, from the second tags included in all the cascade groups, a candidate tag whose correlation degree meets a preset threshold value includes:
for each cascade group, acquiring effective information of second labels included in the cascade group, and calculating the relevance of each second label and the first label according to the effective information to obtain a relevance score of each second label in the cascade group; the valid information includes at least one of the following of the second tag: the weight, the overlapping times, the historical frequency of the second label selected by the current user, the times of the second label selected by all users and the priority among the second labels;
Sorting all the second labels in the cascade group according to the relevance score of each second label in the cascade group to obtain sorted second labels;
and selecting a second label with the relevance score meeting a preset threshold value from the second labels as a candidate label.
In a possible implementation manner, the weight is preconfigured according to the influence of each second tag on the target application object;
The number of overlaps is determined by: analyzing cascade relations among a plurality of labels of a plurality of levels in the cascade label library, and counting to obtain overlapping times of each second label; the overlapping times are times when other tags point to the second tag;
The priority between the second tags is determined by: and determining the upper and lower level relation among a plurality of second labels included in the cascade group according to the level information of each second label, and calculating the priority among the second labels according to the upper and lower level relation and the preset priority among the upper and lower levels.
In a second aspect, an embodiment of the present application further provides a cascading label recommendation apparatus, which is applied to a server, where the apparatus includes:
The acquisition module is used for pre-configuring a plurality of labels of a target application object and cascading relations among the labels according to attribute characteristics of the application object to obtain a cascading label library applicable to the target application object;
The first determining module is used for determining a first label in the cascade label library and determining a classification position of the first label in the cascade label library in response to the target application object meeting a label recommendation condition after receiving the target application object sent by the user terminal;
The second determining module is used for determining a cascade group corresponding to the first tag according to the classification position of the first tag in the cascade tag library; wherein each cascade group comprises a first label and a second label which has a direct or indirect cascade relation with the first label;
The selecting module is used for selecting candidate labels with the correlation degree meeting a preset threshold value from the second labels included in all cascade groups according to the correlation degree of each second label in the cascade groups and the first label aiming at each cascade group, and sending the candidate labels to a user side so as to push the candidate labels to the user side;
And the display module is used for responding to a selection instruction of a user for the candidate labels, determining the target label selected by the user, adding the target label for the target application object, and displaying the target label of the target application object at the user side.
In a possible embodiment, the first determining module is specifically configured to at least one of the following:
Determining a first label based on the label input by the user aiming at the target application object;
Determining a first label based on a label selected by a user from a basic label group recommended by the server for the target application object; the base tag set includes one of the following categories of tags: a target history tag; a plurality of tags at any stage in the cascade tag library; and a plurality of labels in any cascade group in the cascade label library.
In a possible implementation manner, the first determining module is specifically configured to:
acquiring identification information of the target application object, and determining a target category label of the basic label group through the identification information; the identification information comprises a name and/or description information of the target application object;
And determining one or more labels included in the target category label, and generating a basic label group matched with the target application object according to the one or more labels.
In a possible implementation manner, the first determining module is specifically configured to:
counting history labels selected by a user in a preset history time period;
For each history tag, determining the comprehensive score of the history tag according to the selection times of the user on the history tag and the importance of the history tag in a preset history time period; the importance is determined according to the category to which the history tag belongs and the importance identification of the history tag in the category;
A first tag is determined from a plurality of the history tags based on the combined score for each history tag.
In a possible implementation manner, the acquiring module is specifically configured to:
Acquiring attribute characteristics of the application object, and determining a plurality of levels of the application object and a plurality of labels of each level according to the attribute characteristics;
And establishing connection between a plurality of labels of any two levels by analyzing the characteristic relation among the attribute characteristics to obtain a cascade relation among the plurality of labels of the multiple levels.
In a possible implementation manner, the selecting module is specifically configured to:
for each cascade group, acquiring effective information of second labels included in the cascade group, and calculating the relevance of each second label and the first label according to the effective information to obtain a relevance score of each second label in the cascade group; the valid information includes at least one of the following of the second tag: the weight, the overlapping times, the historical frequency of the second label selected by the current user, the times of the second label selected by all users and the priority among the second labels;
Sorting all the second labels in the cascade group according to the relevance score of each second label in the cascade group to obtain sorted second labels;
and selecting a second label with the relevance score meeting a preset threshold value from the second labels as a candidate label.
In a possible implementation manner, the selecting module is specifically configured to:
Wherein the weight is preconfigured according to the influence of each second tag on the target application object;
The number of overlaps is determined by: analyzing cascade relations among a plurality of labels of a plurality of levels in the cascade label library, and counting to obtain overlapping times of each second label; the overlapping times are times when other tags point to the second tag;
The priority between the second tags is determined by: and determining the upper and lower level relation among a plurality of second labels included in the cascade group according to the level information of each second label, and calculating the priority among the second labels according to the upper and lower level relation and the preset priority among the upper and lower levels.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor in communication with the storage medium via the bus when the electronic device is running, the processor executing the machine-readable instructions to perform the steps of the cascading label recommendation method according to any one of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the cascading label recommendation method of any one of the first aspects.
According to the cascading label recommendation method, the cascading label recommendation device, the electronic equipment and the storage medium, cascading relations among a plurality of labels of a target application object and the labels are preconfigured through attribute characteristics of the application object, and a cascading label library applicable to the target application object is obtained; then, after receiving a target application object uploaded by a user side, determining a first label in a cascade label library in response to the target application object meeting a label recommendation condition, and determining a classification position of the first label in the cascade label library; furthermore, determining a cascade group corresponding to the first tag according to the classification position of the first tag in the cascade tag library; then, selecting candidate labels with the correlation degree meeting a preset threshold value from the second labels included in all cascade groups according to the correlation degree of each second label and the first label in each cascade group, and sending the candidate labels to a user side so as to push the candidate labels to the user side; and finally, determining a target label selected by the user based on the user selection, adding the target label to the target application object, and displaying the target label of the target application object at the user side. According to the method and the device for adding the target label to the target application object, the cascade label library is preconfigured, the candidate label is determined according to the first label in the cascade label library and is sent to the user side, and the target label selected by the user is determined to add the target label to the target application object.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a cascading label recommendation method according to one embodiment of the present application;
FIG. 2 is a schematic diagram of a cascading label library;
FIG. 3 is a flow chart of a cascading label recommendation method according to another embodiment of the present application;
FIG. 4 is a flow diagram of a cascading label recommendation method;
FIG. 5 is a schematic diagram of a cascading label recommendation apparatus according to one embodiment of the present application;
fig. 6 is a schematic structural view of a computer device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for the purpose of illustration and description only and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that the term "comprising" will be used in embodiments of the application to indicate the presence of the features stated hereafter, but not to exclude the addition of other features.
Considering that with the continuous development of the internet, related contents conforming to the individuation of the user are often required to be recommended to the user in the scenes of teaching, shopping and the like, so that the user can obtain the contents widely. At present, related contents are recommended to a user mainly through a plurality of recommendation systems based on collaborative filtering, content filtering, knowledge graph, context awareness and the like.
However, the existing recommendation system has the disadvantages of complex algorithm, relatively high operation requirement on staff and high maintenance cost, and is difficult to apply to small and medium-scale enterprises.
In order to solve the problem, the application provides a cascade label recommending method, a device, electronic equipment and a storage medium, wherein a cascade label library is preconfigured, candidate labels are determined according to a first label in the cascade label library and are sent to a user side, a target label selected by a user is determined to add the target label to a target application object, and the cascade label library is only preconfigured, so that a recommending algorithm is simpler, the operation requirement on staff is reduced, and the maintenance cost is lower, thereby being easy to apply to small and medium-scale enterprises.
Fig. 1 is a flowchart of a cascading label recommendation method according to an embodiment of the present application, where the cascading label recommendation method is applied to a server, and as shown in fig. 1, the cascading label recommendation method according to an embodiment of the present application may specifically include:
S101, according to the attribute characteristics of the application object, preconfiguring cascade relations among a plurality of labels of the target application object and the labels to obtain a cascade label library applicable to the target application object.
S102, after receiving a target application object uploaded by a user side, determining a first label in a cascade label library in response to the target application object meeting a label recommendation condition, and determining a classification position of the first label in the cascade label library.
S103, determining a cascade group corresponding to the first label according to the classification position of the first label in the cascade label library.
S104, selecting candidate labels with the correlation degree meeting a preset threshold value from the second labels included in all cascade groups according to the correlation degree of each second label and the first label in each cascade group, and sending the candidate labels to the user side so as to push the candidate labels to the user side.
S105, responding to a selection instruction of a user for the candidate labels, determining the target label selected by the user, adding the target label for the target application object, and displaying the target label of the target application object at the user side.
According to the cascade label recommending method, the cascade label library is preconfigured, the candidate labels are determined according to the first labels in the cascade label library and are sent to the user side, the target labels selected by the user are determined to be added to the target application object, and the cascade label library is preconfigured only, so that the recommending algorithm is simple, the operation requirement on staff is reduced, the maintenance cost is low, and the cascade label recommending method is easy to apply to small and medium-scale enterprises.
The following fig. 1 and 4 illustrate the above exemplary steps of an embodiment of the present application with reference to specific examples:
s101, according to the attribute characteristics of the application object, preconfiguring cascade relations among a plurality of labels of the target application object and a plurality of labels to obtain a cascade label library applicable to the target application object.
The method for constructing the cascade tag library comprises the steps of obtaining attribute characteristics of an application object, and determining a plurality of layers of the application object and a plurality of tags of each layer according to the attribute characteristics; and establishing connection between a plurality of labels of any two levels by analyzing the characteristic relation among the attribute characteristics to obtain a cascade relation among the plurality of labels of the multiple levels. Wherein the attribute features are features that characterize the attributes of the application object. In the embodiment of the present application, the application object, that is, the object to which the user adds the cascading labels, for example, a course video in a teaching scene, where an attribute feature of the application object may be a course, which is displayed in a video manner, and the course specifically includes a plurality of different subjects, such as physics and architecture; the courses also include a plurality of different schools, and can also include a plurality of different grades of courses, such as primary schools, middle schools, high schools and universities; each level of lesson may also include a plurality of different professions, e.g., computer profession, construction profession, financial profession, literature, science, computer profession, each of which may also include a plurality of different lesson contents, e.g., C language programming.
Firstly, acquiring the attribute characteristics of an application object, and then determining a plurality of layers of the application object and a plurality of labels of each layer according to the attribute characteristics; for example, four levels and a tag included in each level; for example, the four levels are a first level tag, a second level tag, a third level tag, and a fourth level tag, where the first level tag may include: universities, junior middle schools, primary schools, and high schools; the secondary labels may include computer professions, construction professions, financial professions, literature, and science; the tertiary labels may include a primary, a quaternary, and a sixth grade; four-level tags may include C language programming, history, math, and pinde and society.
Then, by analyzing the characteristic relation among the attribute characteristics, for example, universities include construction professions, and the universities in the primary labels and the secondary label construction professions are connected; in this way, connection between a plurality of labels of any two levels is established, so that a cascade relation among the plurality of labels of the plurality of levels is obtained, and finally, a cascade label library shown in fig. 2 is obtained.
Specifically, for example, the attribute of the school course is characterized by a school, a specialty, a grade, and a subject, and it is determined that the school course has four levels, that is, four-level tags of the school, the specialty, the grade, the subject, and the like, and each level tag includes a plurality of tags, specifically, a first level tag (school): universities, high school, junior middle school, and primary school; secondary label (professional): computer profession, construction profession, finance profession, literature, science; three-level label (grade): primary, secondary, tertiary, quaternary, penta, and hexa; four-level label (subject): mathematics, chinese, history, moral and social, C language programming, thereby determining multiple levels of application objects, i.e., school courses, and multiple tags of each level. In a further aspect, the feature relationships among the four attribute features of the school, the specialty, the grade, and the subject are analyzed, and a connection between the labels of any two of the four levels of the school, the specialty, the grade, and the subject is established, for example, university-computer specialty, computer specialty-grade, and the like, so that the cascade relationship among the labels of the multiple levels is shown in fig. 2.
The cascade finger may form association data having a relationship of upper and lower levels, and the cascade relationship between a plurality of tags, that is, the association of the tags having a relationship of upper and lower levels. For example, there are four levels of tags, where one level of tags: universities, high school, junior middle school, primary school, secondary label: computer specialty, construction specialty, finance specialty, literature, science, three-level label: first grade, second grade, third grade, fourth grade, fifth grade, sixth grade, fourth grade label: mathematics, chinese, history, moral and social, and C language programming, the four-level tag can form four tag chains with cascade relations: university- - > computer specialty/construction specialty/finance specialty- - > first grade/second grade/third grade/fourth grade- > math/language/history/C language programming, senior- > literature/science- > first grade/second grade/third grade- > math/language/history, junior- > first grade/second grade/third grade- > math/language/history, primary school- > first grade/second grade/third grade- > math/fifth grade- > math/language/history/mor and society, based on which a cascade tag library as shown in fig. 2 (all tags in the fourth grade tags are not shown and the positions are adjusted) can be obtained.
It should be noted that, the present application is described by taking the cascade tag library shown in fig. 2 as an example, but the cascade tag library is not limited thereto, and may be specifically set according to practical situations.
S102, after receiving a target application object uploaded by a user terminal, determining a first label in a cascade label library in response to the target application object meeting a label recommendation condition, and determining a classification position of the first label in the cascade label library.
In the embodiment of the application, after the user (refer to the current user) makes the target application object, for example, after recording a course, the course is uploaded to the server through the user terminal, and the server processes based on the course so as to recommend course labels for the course of the user. Specifically, the processing method of the server is as follows: the server judges whether the course meets the label recommendation condition, for example, a user opens a recommendation mode, or the course is considered to meet the label recommendation condition without special non-recommended labels, when the course is determined to meet the label recommendation condition, a first label of the course is determined first, and the first label is used for recommending subsequent candidate labels by the server, so that labels can be added to the course more efficiently, accurately and comprehensively.
After determining the first tag, determining the hierarchical position of the first tag in the cascaded tag library, for example, if the first tag is "one grade", the cascaded tag library shown in fig. 2 may determine that the classification position of the "one grade" in the cascaded tag library is a three-level tag, and when the target application object meets the tag recommendation condition, starting to recommend the tag, determining the first tag in the cascaded tag library, and determining the classification position of the first tag in the cascaded tag library, so as to perform subsequent processing.
It should be noted that, in response to the user opening the tag recommendation function, it is determined that the target application object satisfies the tag recommendation condition. Optionally, in response to the user controlling the cursor to click on the tag recommendation input box of the target application object, it is determined that the user opens the tag recommendation function.
It should be further noted that, the specific mode of determining the first tag in the cascade tag library is not excessively limited, and the method and the device can be set according to actual situations.
As one possible implementation, determining the first tag in the cascade tag library includes at least one of:
The first tag is determined based on the tag entered by the user for the target application object. Wherein the first tag is determined directly from the tag of the user video input for the lesson as illustrated in the examples.
The first tag is determined based on a tag selected by a user from a set of base tags recommended by the server for the target application object. Wherein the base tag set includes one of the following categories of tags: a target history tag; cascading a plurality of tags at any stage in a tag library; a plurality of tags in any cascade group in the cascade tag library.
Optionally, the server recommends the basic tag group by:
Acquiring identification information of a target application object, and determining a target category label of a basic label group through the identification information; the identification information includes a name and/or descriptive information of the target application object. For example, for a school course, the name and/or description information of the course is information related to the school course, and the target category label of the corresponding basic label set of the school course is determined to be school, professional, grade and subject through the information related to the school course.
One or more labels included in the target class label are determined, and a basic label set matched with the target application object is generated according to the one or more labels. For example, for a school course, after determining that the target class labels of the corresponding basic label group are the labels of the school, the specialty, the grade and the subject, determining one or more labels included in the school, the specialty, the grade and the subject, as described above, specifically, the school in the target class labels includes a plurality of labels of universities, juniors, universities and high-middle levels, and other target class labels are the same, which are not described herein, then generating the basic label group of the school course according to one or more labels of the target class labels, specifically, as shown in fig. 2, constructing a connection relationship between labels of each stage, where the connection relationship is determined according to the identification information of the school course, for example, the university and the literature obviously cannot construct the connection relationship, because the university has no distinction between the literature and the science, and the university and the computer specialty can construct the connection relationship, so that the basic label group matching the school course can be obtained.
Optionally, the target history tag in the base tag group is determined by the following method:
Counting history labels selected by a user in a preset history time period; for each history tag, determining the comprehensive score of the history tag according to the selection times of the user on the history tag and the importance of the history tag in a preset history time period; a first tag is determined from the plurality of history tags based on the composite score for each history tag. The importance is determined according to the category to which the history tag belongs and the importance identification of the history tag in the category. For example, all history tags selected by the user in the past year are counted, 100 times are selected for a history tag "computer specialty" in the past year, and for importance, "computer specialty" belongs to the secondary tag and importance identification of the secondary tag can be set to be particularly important, comprehensive scores of the "computer specialty" are determined according to the number of selections and importance of the "computer specialty", for example, the "particularly important" of the importance identification is assigned to 100%, the number of selections of the "computer specialty" and the assignment of the importance can be multiplied, and thus the comprehensive score of the "computer specialty" can be obtained as 100 points, so that the comprehensive score of all history tags is obtained, and the first tag is selected according to the comprehensive score of each history tag, for example, the history tag with the highest comprehensive score is selected as the first tag.
Optionally, storing all tags input by the user in the past into a preset user behavior database; and acquiring a history label selected by the user in a first preset time period based on the user behavior database, and determining a first label based on the history label. For example, all tags input by the user in the past are stored in the user behavior database, the history tags input by the user in the last month are queried based on the user behavior database, and the history tag input the most times is taken as the first tag.
As a possible implementation, the first tag is determined based on a tag selected by the user among a set of base tags recommended by the server. The basic tag group, i.e. the tag group recommended first by the server before the user inputs the tags, includes a plurality of tags, and may include a plurality of levels of tags. Optionally, recommending a preset basic tag group to the user side, so that the user can select the tags in the basic tag group; and responding to a selection instruction of a user in the basic tag group, and determining the tag selected by the user as a first tag. For example, the server recommends a base set of tags to the user, which tag is determined to be the first tag when the user selects a tag within the base set of tags.
S103, determining a cascade group corresponding to the first label according to the classification position of the first label in the cascade label library; wherein each cascade group comprises a first label and a second label which has a direct or indirect cascade relation with the first label.
In the embodiment of the application, each cascade group comprises a first label and a second label which has a direct or indirect cascade relation with the first label, and the cascade group corresponding to the first label is determined according to the classification position of the first label in a cascade label library. For example, as shown in fig. 2, when the first tag is a grade one, the classification position of the first tag is determined to be a grade three tag, and based on this, it can be known that the corresponding upper level tag (grade two tag) of the grade one (grade three tag) is: the corresponding lower-level tags (four-level tags) of the "one-level" (three-level tags) of the computer profession, the building profession, the finance profession, the literature, the science are: mathematics, chinese, history, politics, wherein multiple cascading groups such as a grade-computer specialty, a grade-mathematics, etc. may be determined.
S104, selecting candidate labels with the correlation degree meeting a preset threshold value from the second labels included in all cascade groups according to the correlation degree of each second label and the first label in each cascade group, and sending the candidate labels to the user side so as to push the candidate labels to the user side.
In the embodiment of the present application, the correlation degree is the correlation between the second label and the first label, the preset threshold is a preset threshold, and for each cascade group obtained in the step S103, candidate labels with the correlation degree meeting the preset threshold are selected from the second labels included in all cascade groups according to the correlation degree between each second label and the first label in the cascade group, and the candidate labels are sent to the user side, so as to push the candidate labels to the user side.
S105, responding to a selection instruction of a user for the candidate labels, determining the target label selected by the user, adding the target label for the target application object, and displaying the target label of the target application object at the user side.
In the embodiment of the application, the target label is the label selected by the user aiming at the candidate label, the target label selected by the user is determined after the user selects the candidate label, the target label is added for the target application object, and the target label corresponding to the target application object is displayed at the user side.
After the cascade labels are added to the course video, the course video corresponding to the cascade labels can be queried through the cascade labels, so that the query efficiency is improved.
According to the cascade label recommending method provided by the embodiment of the application, the cascade relation between a plurality of labels of a target application object and a plurality of labels is preconfigured through the attribute characteristics of the application object, so that a cascade label library applicable to the target application object is obtained; then, after receiving a target application object uploaded by a user side, determining a first label in a cascade label library in response to the target application object meeting a label recommendation condition, and determining a classification position of the first label in the cascade label library; furthermore, determining a cascade group corresponding to the first tag according to the classification position of the first tag in the cascade tag library; then, selecting candidate labels with the correlation degree meeting a preset threshold value from the second labels included in all cascade groups according to the correlation degree of each second label and the first label in each cascade group, and sending the candidate labels to a user side so as to push the candidate labels to the user side; and finally, determining a target label selected by the user based on the user selection, adding the target label to the target application object, and displaying the target label of the target application object at the user side. According to the cascade label recommending method, the cascade label library is preconfigured, the candidate labels are determined according to the first labels in the cascade label library and are sent to the user side, and the target labels selected by the user are determined to be added to the target application object, so that the cascade label library is preconfigured, the recommending algorithm is simple, the operation requirement on staff is reduced, the maintenance cost is low, and the cascade label recommending method is easy to apply to small and medium-scale enterprises.
Further, as shown in fig. 3, in step S104 in the foregoing embodiment, "selecting a candidate tag whose correlation degree satisfies a preset threshold from the second tags included in all the cascade groups" may specifically include the following steps:
S301, for each cascade group, obtaining effective information of second labels included in the cascade group, and calculating the relevance of each second label and the first label according to the effective information to obtain a relevance score of each second label in the cascade group.
In the embodiment of the application, the effective information comprises at least one of the following second labels: the method comprises the steps of obtaining effective information of second labels included in a cascade group, calculating the relevance of each second label and a first label according to the effective information, and obtaining a relevance score of each second label in the cascade group for subsequent processing.
The weight is preconfigured according to the influence of each second tag on the target application object, and the weight can be freely set according to the requirement of a user. For example, for school courses, when the first label is a grade, the corresponding second label includes computer professions, building professions, finance professions, literature, science and the like, and the computer professions, the building professions and the finance professions are clear, so that the influence on the school courses is larger, at this time, three specific professions of the computer professions, the building professions and the finance professions can be set to have larger weights, and the two professions of the literature and the science are set to have smaller weights, so that redundant description is omitted.
The number of overlapping times was determined as follows: and analyzing cascade relations among a plurality of labels of a plurality of levels in a cascade label library, and counting to obtain the overlapping times of each second label. Wherein the overlapping times are times when the other tags point to the second tag. For example, for school courses, the first labels are "one-year" and "university", then the second labels that determine that "one-year" can be recommended are: computer profession, construction profession, financial profession, literature, science, mathematics, chinese, history, politics, second tags that "university" can recommend are: computer specialty, construction specialty, finance specialty, to determine the number of overlapping times of each of the second tags as: computer specialty 2, construction specialty 2, finance specialty 2, literature 1, science 1, mathematics 1, chinese 1, history 1, politics 1.
It should also be noted that the priority between the second tags is determined by: and determining the upper and lower level relation among the plurality of second labels included in the cascade group according to the level information of each second label, and calculating the priority among the second labels according to the upper and lower level relation and the preset priority among the upper and lower levels. For example, for school courses, the first label is "computer specialty", then the second label that determines "computer specialty" can recommend is: university, first grade, fourth grade, etc., wherein the first grade label "university" may be set to have a higher priority than the third grade labels "first grade", "fourth grade" under the first grade label, so that the resulting priority order is university > first grade = fourth grade.
S302, sorting all the second labels in the cascade group according to the relevance scores of each second label in the cascade group, and obtaining sorted second labels.
In the embodiment of the application, all the second labels in the cascade group are ordered according to the relevance score of each second label in the cascade group, so as to obtain the ordered second labels.
S303, selecting a second label with the relevance score meeting a preset threshold value from the second labels as a candidate label.
In the embodiment of the present application, according to the relevance score of each second label in step S301, the second label whose relevance score satisfies the preset threshold value is selected as the candidate label, so as to perform the subsequent processing.
To clearly describe the cascading label recommendation method of the present application, further description is provided below in conjunction with fig. 4.
As shown in fig. 4, a cascade tag library is configured, and the upper and lower relationships among tags are defined to form a multi-cascade tree structure; providing a management background, wherein the relation between labels can be flexibly added, deleted and modified by people; collecting labels input by a user in a system as a history record and storing the history record into a user behavior database; when a user needs label recommendation, inquiring a database to acquire a history label of the user as a first label; analyzing the classification position of the first tag in the tag tree structure of the cascade tag library; recursively searching the upper and lower-level labels, namely the second label, of the first label according to the classification position; sorting the second labels according to the correlation with the first labels to obtain candidate labels; returning top N candidate labels with the forefront ordering, and pushing the candidate labels to a user as target labels; after the user selects the interesting label, the label is added to the course, and the newly selected label is added to the history record again to be stored in the user behavior database for the reference of the follow-up recommendation; the background can observe the label recommending effect and carry out manual adjustment or optimization.
Fig. 5 is a flowchart of a cascading label recommendation apparatus according to an embodiment of the present application, as shown in fig. 5, a cascading label recommendation apparatus 500 according to an embodiment of the present application is applied to a server, and may specifically include:
The obtaining module 501 is configured to pre-configure, according to the attribute characteristics of the application object, a plurality of labels of the target application object and a cascade relationship between the plurality of labels, so as to obtain a cascade label library applicable to the target application object.
The first determining module 502 is configured to determine, after receiving a target application object sent by the user terminal, a first tag in the cascaded tag library in response to the target application object meeting a tag recommendation condition, and determine a classification position of the first tag in the cascaded tag library.
A second determining module 503, configured to determine, according to the classification position of the first tag in the cascade tag library, a cascade group corresponding to the first tag; wherein each cascade group comprises a first label and a second label which has a direct or indirect cascade relation with the first label.
The selecting module 504 is configured to select, for each cascade group, candidate tags with a correlation degree satisfying a preset threshold from the second tags included in all the cascade groups according to the correlation degree between each second tag and the first tag in the cascade group, and send the candidate tags to the user terminal, so as to push the candidate tags to the user terminal.
The display module 505 is configured to determine a target tag selected by a user in response to a selection instruction of the candidate tag by the user, add the target tag to the target application object, and display the target tag of the target application object at the user side.
In one possible embodiment, the first determining module is specifically configured to at least one of:
determining a first label based on a label input by a user aiming at a target application object;
Determining a first label based on a label selected by a user from a basic label group recommended by a server for a target application object; the base tag group includes one of the following categories of tags: a target history tag; cascading a plurality of tags at any stage in a tag library; in one possible implementation, the first determining module is specifically configured to:
Acquiring identification information of a target application object, and determining a target category label of a basic label group through the identification information; the identification information comprises the name and/or the description information of the target application object;
One or more labels included in the target class label are determined, and a basic label set matched with the target application object is generated according to the one or more labels.
In one possible implementation manner, the first determining module is specifically configured to:
counting history labels selected by a user in a preset history time period;
for each history tag, determining the comprehensive score of the history tag according to the selection times of the user on the history tag and the importance of the history tag in a preset history time period; the importance is determined according to the category to which the history label belongs and the importance identification of the history label in the category;
A first tag is determined from the plurality of history tags based on the composite score for each history tag.
In one possible implementation manner, the acquiring module is specifically configured to:
acquiring attribute characteristics of an application object, and determining a plurality of levels of the application object and a plurality of labels of each level according to the attribute characteristics;
By analyzing the characteristic relation between the attribute characteristics, connection between a plurality of labels of any two levels is established, and a cascade relation between the plurality of labels of the plurality of levels is obtained, in a possible implementation mode, a module is selected, which is specifically used for:
For each cascade group, acquiring effective information of second labels included in the cascade group, and calculating the correlation degree of each second label and the first label according to the effective information to obtain a correlation degree score of each second label in the cascade group; the valid information includes at least one of the following of the second tag: the weight, the overlapping times, the historical frequency of the second label selected by the current user, the times of the second label selected by all users and the priority among the second labels;
sorting all the second labels in the cascade group according to the relevance score of each second label in the cascade group to obtain sorted second labels;
And selecting a second label with the relevance score meeting a preset threshold value from the second labels as a candidate label.
In one possible implementation, the selecting module is specifically configured to:
The weight is preconfigured according to the influence of each second label on the target application object;
the number of overlaps is determined as follows: analyzing cascade relations among a plurality of labels of a plurality of levels in a cascade label library, and counting to obtain overlapping times of each second label; the overlapping times are the times that other tags point to the second tag;
The priority between the second tags is determined by: and determining the upper and lower level relation among the plurality of second labels included in the cascade group according to the level information of each second label, and calculating the priority among the second labels according to the upper and lower level relation and the preset priority among the upper and lower levels.
According to the cascading label recommendation device provided by the embodiment of the application, cascading relations among a plurality of labels of a target application object and a plurality of labels are preconfigured through the attribute characteristics of the application object, so that a cascading label library applicable to the target application object is obtained; then, after receiving a target application object uploaded by a user side, determining a first label in a cascade label library in response to the target application object meeting a label recommendation condition, and determining a classification position of the first label in the cascade label library; furthermore, determining a cascade group corresponding to the first tag according to the classification position of the first tag in the cascade tag library; then, selecting candidate labels with the correlation degree meeting a preset threshold value from the second labels included in all cascade groups according to the correlation degree of each second label and the first label in each cascade group, and sending the candidate labels to a user side so as to push the candidate labels to the user side; and finally, determining a target label selected by the user based on the user selection, adding the target label to the target application object, and displaying the target label of the target application object at the user side. According to the cascade label recommending device, the cascade label library is preconfigured, the candidate labels are determined according to the first labels in the cascade label library and are sent to the user side, and the target labels selected by the user are determined to be added to the target application object, so that the cascade label library is preconfigured, the recommending algorithm is simple, the operation requirement on staff is reduced, the maintenance cost is low, and the cascade label recommending device is easy to apply to small and medium-scale enterprises.
As shown in fig. 6, an electronic device 600 provided in an embodiment of the present application includes: the system comprises a processor 601, a memory 602 and a bus, wherein the memory 602 stores machine-readable instructions executable by the processor 601, and when the electronic device is running, the processor 601 communicates with the memory 602 through the bus, and the processor 601 executes the machine-readable instructions to perform the steps of the cascade tag recommendation method.
Specifically, the above memory 602 and the processor 601 can be general-purpose memories and processors, which are not particularly limited herein, and the above cascade tag recommendation method can be performed when the processor 601 runs a computer program stored in the memory 602.
Corresponding to the above cascade label recommendation method, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program executes the steps of the cascade label recommendation method when being executed by a processor.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the method embodiments, and are not repeated in the present disclosure. In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, and the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, and for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, indirect coupling or communication connection of devices or modules, electrical, mechanical, or other form.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the deployment method described in the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (8)
1. A cascading label recommendation method, characterized by being applied to a server, the method comprising:
According to the attribute characteristics of the application object, preconfiguring a plurality of labels of a target application object and cascading relations among the labels to obtain a cascading label library applicable to the target application object; the cascade relation between a plurality of labels of a target application object and the labels is preconfigured according to the attribute characteristics of the application object, and the cascade relation comprises the following steps: acquiring attribute characteristics of the application object, and determining a plurality of levels of the application object and a plurality of labels of each level according to the attribute characteristics; establishing connection between a plurality of labels of any two levels by analyzing the characteristic relation among the attribute characteristics to obtain a cascade relation among the plurality of labels of the multiple levels; the application object is a course video;
after receiving a target application object uploaded by a user side, responding to the target application object meeting a label recommendation condition, determining a first label in the cascade label library, and determining a classification position of the first label in the cascade label library;
Determining a cascade group corresponding to the first tag according to the classification position of the first tag in the cascade tag library; wherein each cascade group comprises a first label and a second label which has a direct or indirect cascade relation with the first label;
selecting candidate labels with the correlation degree meeting a preset threshold value from second labels included in all cascade groups according to the correlation degree of each second label in the cascade groups and the first label aiming at each cascade group, and sending the candidate labels to a user side so as to push the candidate labels to the user side;
Responding to a selection instruction of a user on the candidate labels, determining a target label selected by the user, adding the target label for the target application object, and displaying the target label of the target application object at the user side;
the selecting candidate labels with the correlation degree meeting a preset threshold from the second labels included in all the cascade groups comprises the following steps:
for each cascade group, acquiring effective information of second labels included in the cascade group, and calculating the relevance of each second label and the first label according to the effective information to obtain a relevance score of each second label in the cascade group; the valid information includes at least one of the following of the second tag: the weight, the overlapping times, the historical frequency of the second label selected by the current user, the times of the second label selected by all users and the priority among the second labels;
Sorting all the second labels in the cascade group according to the relevance score of each second label in the cascade group to obtain sorted second labels;
and selecting a second label with the relevance score meeting a preset threshold value from the second labels as a candidate label.
2. The method of claim 1, wherein the determining a first tag in the cascade of tags comprises at least one of:
Determining a first label based on the label input by the user aiming at the target application object;
Determining a first label based on a label selected by a user from a basic label group recommended by the server for the target application object; the base tag set includes one of the following categories of tags: a target history tag; a plurality of tags at any stage in the cascade tag library; and a plurality of labels in any cascade group in the cascade label library.
3. The method of claim 2, wherein the server recommends the base tag group by a method comprising:
acquiring identification information of the target application object, and determining a target category label of the basic label group through the identification information; the identification information comprises a name and/or description information of the target application object;
And determining one or more labels included in the target category label, and generating a basic label group matched with the target application object according to the one or more labels.
4. The method of claim 2, wherein determining the target history tag in the base tag set comprises:
counting history labels selected by a user in a preset history time period;
For each history tag, determining the comprehensive score of the history tag according to the selection times of the user on the history tag and the importance of the history tag in a preset history time period; the importance is determined according to the category to which the history tag belongs and the importance identification of the history tag in the category;
A first tag is determined from a plurality of the history tags based on the combined score for each history tag.
5. The method of claim 1, wherein the weights are pre-configured according to the impact of each second tag on the target application object;
The number of overlaps is determined by: analyzing cascade relations among a plurality of labels of a plurality of levels in the cascade label library, and counting to obtain overlapping times of each second label; the overlapping times are times when other tags point to the second tag;
The priority between the second tags is determined by: and determining the upper and lower level relation among a plurality of second labels included in the cascade group according to the level information of each second label, and calculating the priority among the second labels according to the upper and lower level relation and the preset priority among the upper and lower levels.
6. A cascading label recommendation apparatus applied to a server, the apparatus comprising:
The acquisition module is used for pre-configuring a plurality of labels of a target application object and cascading relations among the labels according to attribute characteristics of the application object to obtain a cascading label library applicable to the target application object; the cascade relation between a plurality of labels of a target application object and the labels is preconfigured according to the attribute characteristics of the application object, and the cascade relation comprises the following steps: acquiring attribute characteristics of the application object, and determining a plurality of levels of the application object and a plurality of labels of each level according to the attribute characteristics; establishing connection between a plurality of labels of any two levels by analyzing the characteristic relation among the attribute characteristics to obtain a cascade relation among the plurality of labels of the multiple levels; the application object is a course video;
The first determining module is used for determining a first label in the cascade label library and determining a classification position of the first label in the cascade label library in response to the target application object meeting a label recommendation condition after receiving the target application object sent by the user terminal;
The second determining module is used for determining a cascade group corresponding to the first tag according to the classification position of the first tag in the cascade tag library; wherein each cascade group comprises a first label and a second label which has a direct or indirect cascade relation with the first label;
The selecting module is used for selecting candidate labels with the correlation degree meeting a preset threshold value from the second labels included in all cascade groups according to the correlation degree of each second label in the cascade groups and the first label aiming at each cascade group, and sending the candidate labels to a user side so as to push the candidate labels to the user side;
The display module is used for responding to a selection instruction of a user for the candidate labels, determining the target label selected by the user, adding the target label for the target application object, and displaying the target label of the target application object at the user side;
the selecting candidate labels with the correlation degree meeting a preset threshold from the second labels included in all the cascade groups comprises the following steps:
for each cascade group, acquiring effective information of second labels included in the cascade group, and calculating the relevance of each second label and the first label according to the effective information to obtain a relevance score of each second label in the cascade group; the valid information includes at least one of the following of the second tag: the weight, the overlapping times, the historical frequency of the second label selected by the current user, the times of the second label selected by all users and the priority among the second labels;
Sorting all the second labels in the cascade group according to the relevance score of each second label in the cascade group to obtain sorted second labels;
and selecting a second label with the relevance score meeting a preset threshold value from the second labels as a candidate label.
7. An electronic device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor and said memory communicating over the bus when the electronic device is running, said machine readable instructions when executed by said processor performing the steps of the cascading label recommendation method according to any one of claims 1 to 5.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the cascading label recommendation method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410145859.5A CN117668373B (en) | 2024-02-02 | 2024-02-02 | Cascade label recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410145859.5A CN117668373B (en) | 2024-02-02 | 2024-02-02 | Cascade label recommendation method and device, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117668373A CN117668373A (en) | 2024-03-08 |
CN117668373B true CN117668373B (en) | 2024-05-17 |
Family
ID=90068397
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410145859.5A Active CN117668373B (en) | 2024-02-02 | 2024-02-02 | Cascade label recommendation method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117668373B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114358814B (en) * | 2021-11-29 | 2024-10-18 | 国网北京市电力公司 | Data processing method, device, electronic equipment and computer readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103412910A (en) * | 2013-08-02 | 2013-11-27 | 北京小米科技有限责任公司 | Methods and devices for building tag library and searching users |
CN105653691A (en) * | 2015-12-29 | 2016-06-08 | 珠海城建节能科技有限公司 | Information resource management method and management apparatus |
WO2017107457A1 (en) * | 2015-12-25 | 2017-06-29 | 乐视控股(北京)有限公司 | Query recommendation method and apparatus |
CN113537215A (en) * | 2021-07-19 | 2021-10-22 | 山东福来克思智能科技有限公司 | Method and device for labeling video label |
CN116775854A (en) * | 2023-06-30 | 2023-09-19 | 北京字跳网络技术有限公司 | Label display method, device, computer equipment and storage medium |
CN116910345A (en) * | 2023-01-30 | 2023-10-20 | 中移(杭州)信息技术有限公司 | Label recommending method, device, equipment and storage medium |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210027251A1 (en) * | 2014-07-01 | 2021-01-28 | Piazza Technologies, Inc. | Computer systems and methods for searching multi-dimensional content |
US20170185673A1 (en) * | 2015-12-25 | 2017-06-29 | Le Holdings (Beijing) Co., Ltd. | Method and Electronic Device for QUERY RECOMMENDATION |
-
2024
- 2024-02-02 CN CN202410145859.5A patent/CN117668373B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103412910A (en) * | 2013-08-02 | 2013-11-27 | 北京小米科技有限责任公司 | Methods and devices for building tag library and searching users |
WO2017107457A1 (en) * | 2015-12-25 | 2017-06-29 | 乐视控股(北京)有限公司 | Query recommendation method and apparatus |
CN105653691A (en) * | 2015-12-29 | 2016-06-08 | 珠海城建节能科技有限公司 | Information resource management method and management apparatus |
CN113537215A (en) * | 2021-07-19 | 2021-10-22 | 山东福来克思智能科技有限公司 | Method and device for labeling video label |
CN116910345A (en) * | 2023-01-30 | 2023-10-20 | 中移(杭州)信息技术有限公司 | Label recommending method, device, equipment and storage medium |
CN116775854A (en) * | 2023-06-30 | 2023-09-19 | 北京字跳网络技术有限公司 | Label display method, device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN117668373A (en) | 2024-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10929436B2 (en) | System and method for news events detection and visualization | |
KR102206256B1 (en) | How to Recommend Instructors in the Online Course System | |
US9904712B2 (en) | Systems, methods, and interfaces for aggregating and providing information regarding legal professionals | |
US8611675B2 (en) | Confusion matrix for classification systems | |
CN117668373B (en) | Cascade label recommendation method and device, electronic equipment and storage medium | |
CN108846097B (en) | User interest tag representation method, article recommendation device and equipment | |
CN110727852A (en) | Method, device and terminal for pushing recruitment recommendation service | |
Shu | Knowledge discovery in the social sciences: A data mining approach | |
US20110082803A1 (en) | Business flow retrieval system, business flow retrieval method and business flow retrieval program | |
CN111696656B (en) | Doctor evaluation method and device of Internet medical platform | |
CN105190619B (en) | The program of terminal installation and device | |
JP2020091539A (en) | Information processing device, information processing method, and information processing program | |
CN108132940B (en) | Application program data extraction method and device | |
CN112328752B (en) | Course recommendation method and device based on search content, computer equipment and medium | |
CN114417010A (en) | Knowledge graph construction method and device for real-time workflow and storage medium | |
CN111506826A (en) | User recommendation method, device, equipment and storage medium based on intimacy | |
CN118396803B (en) | Intelligent education system based on artificial intelligence | |
US11410098B1 (en) | Method for computational modelling and analysis of the skills and competencies of individuals | |
CN116187632B (en) | Behavior prediction model training method, house source matching method, device and storage medium | |
CN118708808A (en) | Recommendation method, device, equipment and storage medium based on large model | |
CN118628151A (en) | Policy information screening and customer matching equipment, system and method | |
JP2022083413A (en) | Store property recommendation system and program thereof | |
CN115907914A (en) | Financial product intelligent recommendation method and system based on customer requirements | |
CN117493683A (en) | Question recommending method and device, electronic equipment and storage medium | |
CN115186181A (en) | Virtual asset recommendation method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |