CN112966176B

CN112966176B - Object display method and device, electronic equipment and readable storage medium

Info

Publication number: CN112966176B
Application number: CN202110136289.XA
Authority: CN
Inventors: 毛展宏; 张岩; 王卫礼; 王焜
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2021-02-01
Filing date: 2021-02-01
Publication date: 2022-08-26
Anticipated expiration: 2041-02-01
Also published as: CN112966176A

Abstract

The embodiment of the application provides an object display method and device, electronic equipment and a readable storage medium. The method comprises the following steps: obtaining a plurality of candidate objects and labels of the candidate objects respectively; aggregating the multiple candidate objects according to whether the labels of the multiple candidate objects are the same or not to obtain multiple object sets and multiple object individuals, wherein one object set comprises at least two candidate objects in the multiple candidate objects, the at least two candidate objects have the same label, and one object individual is one candidate object; determining an object queue to be shown from a plurality of object sets and a plurality of object individuals, wherein the object queue to be shown comprises at least one object set and/or at least one object individual; and displaying the queue of the objects to be displayed. The method can realize the mixed recommendation of the search object set and the search object individuals, remarkably increase the richness of the content displayed on the display interface, and further enhance the browsing depth of the user.

Description

Object display method and device, electronic equipment and readable storage medium

Technical Field

The embodiment of the application relates to the technical field of data processing, in particular to an object display method and device, electronic equipment and a readable storage medium.

Background

Search and recommendation are two main ways to obtain information in the internet era, and in the current search and recommendation lists, search objects are usually presented in the form of a single composition list. For example, in current take-away search and recommendation scenarios, multiple stores resulting from a search are typically displayed in a user interface in the form of a single composition list that can be clicked directly to view detailed information when the user is interested in a particular store.

However, in the current search and recommendation list, the exposure of the top-ranked recommendation objects is large, that is, the probability that most users make a search is low, and thus the recommendation objects that the users can see in one search are few. Therefore, the related art has the problem that the browsing depth of the user is low.

Disclosure of Invention

The embodiment of the application provides an object display method and device, an electronic device and a readable storage medium, which can realize mixed recommendation of a search object set and a search object individual, can remarkably increase the richness of content displayed on a display interface, and further enhance the browsing depth of a user.

A first aspect of an embodiment of the present application provides an object display method, where the method includes:

obtaining a plurality of candidate objects and respective labels of the candidate objects;

aggregating the candidate objects according to whether the labels of the candidate objects are the same or not to obtain a plurality of object sets and a plurality of object individuals, wherein one object set comprises at least two candidate objects in the candidate objects, the at least two candidate objects have the same label, and one object individual is one candidate object;

determining an object queue to be shown from the plurality of object sets and the plurality of object individuals, wherein the object queue to be shown comprises at least one object set and/or at least one object individual;

and displaying the object queue to be displayed.

Optionally, obtaining a plurality of candidate objects and labels of the candidate objects includes:

obtaining a plurality of candidate objects according to user operation;

and for each candidate object in the candidate objects, marking a corresponding label for the candidate object according to the feature data of the candidate object and the feature data of each object within a preset range from the candidate object.

Optionally, after obtaining the plurality of object sets, the method further includes:

for each set of objects in the plurality of sets of objects, performing the steps of:

obtaining respective historical user behavior data of each candidate object included in the object set;

obtaining the label matching degree of each candidate object according to the feature data of each candidate object in the object set and the feature data of each object within a preset range from the candidate object;

filtering partial candidate objects according to the respective historical user behavior data and the label matching degree of each candidate object included in the object set to obtain a filtered object set;

determining a queue of objects to be presented from the plurality of sets of objects and the plurality of individuals of the objects, including:

and determining an object queue to be displayed from the filtered object sets and the object individuals.

Optionally, determining a queue of objects to be displayed from the plurality of object sets and the plurality of object individuals includes:

determining the respective pre-estimated user behavior data of the plurality of object sets and the plurality of object individuals;

according to the estimated behavior data of the object sets and the object individuals and the preference of the user to the labels of the object sets and the object individuals, sequencing the object sets and the object individuals;

and determining an object queue to be displayed according to the respective sequence numbers of the object sets and the object individuals.

Optionally, the method further comprises:

carrying out duplicate removal processing on the candidate objects which repeatedly appear in the object queue to be displayed according to a mode of removing the same candidate object with the later serial number;

displaying the object queue to be displayed, including:

and displaying the queue to be displayed after the duplication removal processing.

Optionally, the displaying the queue of the objects to be displayed includes:

and displaying the queue of the objects to be displayed on a user interface in rows, wherein one object individual in the queue to be displayed occupies one row of display positions of the user interface, and one object set in the queue to be displayed occupies one row of display positions of the user interface.

Optionally, for each object set in the sequence of objects to be presented:

the method further comprises the following steps:

sorting the candidate objects included in the object set according to the respective historical user behavior data of the candidate objects included in the object set;

when the object set is displayed at a row of display positions of the user interface, displaying part of candidate objects included in the object set at the row of display positions according to the sequence number of each candidate object included in the object set, and hiding the remaining candidate objects included in the object set;

when the operation of the user on the display position of the row occupied by the object set is detected, the remaining candidate objects included by the object are displayed.

A second aspect of the embodiments of the present application provides an object displaying apparatus, including:

a first obtaining module, configured to obtain a plurality of candidate objects and respective tags of the plurality of candidate objects;

the aggregation module is used for aggregating the candidate objects according to whether the labels of the candidate objects are the same or not to obtain a plurality of object sets and a plurality of object individuals, wherein one object set comprises at least two candidate objects in the candidate objects, the at least two candidate objects have the same label, and one object individual is one candidate object;

the determining module is used for determining an object queue to be shown from the object sets and the object individuals, wherein the object queue to be shown comprises at least one object set and/or at least one object individual;

and the display module is used for displaying the object queue to be displayed.

Optionally, the first obtaining module includes:

the obtaining submodule is used for obtaining a plurality of candidate objects according to user operation;

and the marking module is used for marking a corresponding label for each candidate object in the candidate objects according to the feature data of the candidate object and the feature data of each object within a preset range from the candidate object.

Optionally, the apparatus further comprises:

a second obtaining module, configured to obtain historical user behavior data of each candidate object included in the object set;

a third obtaining module, configured to obtain a tag matching degree of each candidate object according to feature data of each candidate object in the object set and feature data of each object within a preset range from the candidate object;

the filtering module is used for filtering partial candidate objects according to the respective historical user behavior data and the label matching degree of each candidate object included in the object set to obtain a filtered object set;

the determining module comprises:

and the first determining submodule is used for determining an object queue to be displayed from the filtered object sets and the object individuals.

Optionally, the determining module includes:

a second determining submodule, configured to determine estimated user behavior data of each of the plurality of object sets and the plurality of object individuals;

the sequencing submodule is used for sequencing the object sets and the object individuals according to the estimated behavior data of the object sets and the object individuals and the preference of the user on the labels of the object sets and the object individuals;

and the third determining submodule is used for determining the object queue to be displayed according to the sequence numbers of the object sets and the object individuals.

Optionally, the apparatus further comprises:

the duplication removing module is used for carrying out duplication removing processing on the candidate objects which repeatedly appear in the object queue to be displayed according to the mode of removing the same candidate object with the later serial number;

the display module comprises:

and the first display submodule is used for displaying the queue to be displayed after the duplicate removal processing.

Optionally, the display module comprises:

and the second display submodule is used for displaying the to-be-displayed object queue on a user interface in rows, wherein one object individual in the to-be-displayed queue occupies one row of display positions of the user interface, and one object set in the to-be-displayed queue occupies one row of display positions of the user interface.

Optionally, the apparatus further comprises:

the sorting module is used for sorting the candidate objects included in the object set according to the respective historical user behavior data of the candidate objects included in the object set;

the first display module is used for displaying part of candidate objects included in the object set on a row of display positions according to the sequence number of each candidate object included in the object set when the object set is displayed on the row of display positions of the user interface, and hiding the rest candidate objects included in the object set;

and the second display module is used for displaying the remaining candidate objects included by the object when the operation of the user on the display position of the line occupied by the object set is detected.

A third aspect of embodiments of the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, performs the steps in the method according to the first aspect of the present application.

A fourth aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect of the present application when executed.

By adopting the object display method provided by the embodiment of the application, a plurality of candidate objects and respective labels of the candidate objects are obtained at first. Then, according to whether the labels of the candidate objects are the same or not, the candidate objects are aggregated to obtain a plurality of object sets and a plurality of object individuals, wherein one object set comprises at least two candidate objects in the candidate objects, the at least two candidate objects have the same label, and one object individual is one candidate object. Then, an object queue to be shown is determined from the plurality of object sets and the plurality of object individuals, wherein the object queue to be shown comprises at least one object set and/or at least one object individual. And finally, displaying the object queue to be displayed. By the method, the search object set and the search object individual can be mixed and recommended, and compared with the situation that the original display interface only displays a limited number of single candidate objects, the richness of the content displayed on the display interface can be remarkably increased, the browsing depth of the user is further enhanced, the user can find the satisfied search object more easily, and the recommendation requirement of the user is further met better.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the description of the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings may be obtained according to these drawings without inventive labor.

Fig. 1 is a flowchart illustrating an object presentation method according to an embodiment of the present application;

fig. 2 is a schematic diagram illustrating a display result of a queue of objects to be displayed according to an embodiment of the present application;

FIG. 3 is a flow chart illustrating a method for obtaining candidates and tags according to an embodiment of the present application;

FIG. 4 is a flowchart illustrating a method for determining a queue of objects to be presented according to an embodiment of the present application;

FIG. 5 is a schematic diagram illustrating a display effect of a queue to be presented according to an embodiment of the application;

FIG. 6 is a schematic diagram illustrating a display effect of another queue to be presented according to an embodiment of the present application;

FIG. 7 is a process diagram of an object display method according to an embodiment of the present application;

FIG. 8 is a block diagram of an object display apparatus according to an embodiment of the present disclosure;

fig. 9 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.

Fig. 1 is a flowchart illustrating an object displaying method according to an embodiment of the present application. Referring to fig. 1, an object display method of the present application may include:

step S11: a plurality of candidate objects and respective labels of the plurality of candidate objects are obtained.

The execution subject of the method of the application can be an information recommendation system, and the information recommendation system is used for recommending information meeting the requirements of the user according to the operation of the user, wherein the candidate object is a unit for forming the information.

In this embodiment, the information recommendation system may be any information search system, for example, when the information recommendation system is a book search system of a library, the candidate object may be each book; for another example, when the information recommendation system is an enterprise employee information search system, the candidate objects may be employees of the enterprise; for another example, if the information recommendation system is a peripheral information search system of map software, and the user requests hotels around the current location, the candidate object may be each hotel within a preset range of the current location of the user.

In this embodiment, each candidate object may have at least one tag. Taking the book as an example, the label of the book can be religion, art, economy, military, law, management, archaeology and the like; when the candidate object is an employee of the enterprise, the label may be a high-level manager, a middle-level manager, a general employee, a trial-period employee, a trainee, or the like. The present embodiment does not specifically limit the labels of the respective candidates.

In specific implementation, when a user initiates an information recommendation request to an information recommendation system, the information recommendation system first obtains a plurality of candidate objects and respective tags of each candidate object. The information recommendation system may obtain the candidate object and the tag from its own database, or may obtain the candidate object and the tag from a third-party platform, and the obtaining manner is not particularly limited in this embodiment.

Step S12: and according to whether the labels of the candidate objects are the same or not, aggregating the candidate objects to obtain a plurality of object sets and a plurality of object individuals, wherein one object set comprises at least two candidate objects in the candidate objects, the at least two candidate objects have the same label, and one object individual is one candidate object.

In this embodiment, for each tag, if the number of candidate objects carrying the tag is at least two, the candidate objects may be aggregated into an object set corresponding to the tag. For each tag, if the number of candidate objects carrying the tag is only one, the only candidate object can be taken as an object individual.

For example, when a plurality of candidate objects and corresponding tags are shown in table 1, the aggregate set of objects and individual objects may be shown in table 2.

Candidate object	Label (R)
		Candidate 1	Label X, Label Y
Candidate 2	Label Y
		Candidate 3	Label Z
Candidate 4	Label X, Label Y
		Candidate 5	Label X

TABLE 1

Object collection	Candidate objects within a set
		Set of objects X	Candidate 1, candidate 4, candidate 5
Set of objects Y	Candidate 1, candidate 2, candidate 4
		Subject individual Z	Candidate 3

TABLE 2

Step S13: determining an object queue to be shown from the plurality of object sets and the plurality of object individuals, wherein the object queue to be shown comprises at least one object set and/or at least one object individual.

In this embodiment, after obtaining the plurality of object sets and the plurality of object individuals, at least one object set and/or at least one object individual may be screened from the plurality of object sets and the plurality of object individuals according to a preset condition, so as to form an object queue to be displayed. The preset condition may be set arbitrarily, and this embodiment is not limited to this specifically.

For example, the queue of objects to be displayed obtained by filtering from the object set and the object individuals in table 2 may be as shown in table 3.

Step S14: and displaying the object queue to be displayed.

In this embodiment, the queue of the objects to be displayed may be output to a display interface for a user to view.

Queue of objects to be displayed

Object set X, object set Y, and object individual Z

TABLE 3

The above steps S11 to S14 will be described in detail as an embodiment.

Taking a book whose candidate object is a library as an example, when a user inputs a book recommendation request with a search condition of "2010-2020" in a display interface of the book search system, the book search system first obtains all candidate objects and tags of the respective candidate objects that meet the condition of "2010-2020". Assuming that the tags include economy, military, law and management, the book searching system aggregates all books carrying the economy tags to obtain an object set-economy corresponding to the economy tags, and similarly, the book searching system aggregates books of all the tags to respectively obtain an object set-military corresponding to the military tags, an object set-law corresponding to the law tags and an object individual-management corresponding to the management tags. Then, the book searching system screens and obtains at least one object set and/or at least one object individual from object set-economy, object set-military, object set-law and object individual-management to form an object queue to be displayed. Assuming that the queue to be presented includes object set-economy, object set-military and object individual-management, the presentation result may be as shown in fig. 2, and fig. 2 is a schematic illustration of the presentation result of the queue to be presented according to an embodiment of the present application.

In the embodiment, the book searching system can perform mixed recommendation on the object set and the object individual according with a certain characteristic, so that the problem that a user can only check a limited number of single books on a display interface at one time is avoided, the browsing depth of the user is enhanced, the user can find a desired book more easily, and the user experience is optimized. For example, when a user clicks a displayed object set, namely economy, the interface can pop up a plurality of books related to economy, and when the user clicks the displayed object set, namely military, the interface can pop up a plurality of books related to military.

With the object display method provided by the embodiment, a plurality of candidate objects and respective labels of the plurality of candidate objects are obtained first. Then, according to whether the labels of the candidate objects are the same or not, the candidate objects are aggregated to obtain a plurality of object sets and a plurality of object individuals, wherein one object set comprises at least two candidate objects in the candidate objects, the at least two candidate objects have the same label, and one object individual is one candidate object. Then, an object queue to be shown is determined from the plurality of object sets and the plurality of object individuals, wherein the object queue to be shown comprises at least one object set and/or at least one object individual. And finally, displaying the object queue to be displayed. By the method, the search object set and the search object individual can be mixed and recommended, and compared with the situation that the original display interface only displays a limited number of single candidate objects, the richness of the content displayed on the display interface can be remarkably increased, the browsing depth of the user is further enhanced, the user can find the satisfied search object more easily, and the recommendation requirement of the user is further met better.

In combination with the above embodiments, in one implementation, the candidate object may also be an offline store. On the basis, the application also provides a method for obtaining the labels of the candidate objects and the candidate objects when the candidate objects are off-line shops. Fig. 3 is a flowchart illustrating a method for obtaining candidate objects and tags according to an embodiment of the present application. Referring to fig. 3, the process of obtaining a plurality of off-line stores and labels for the respective off-line stores may include the steps of:

step S111: according to the user operation, a plurality of candidate objects are obtained.

In some search scenarios, a user needs to search for off-line stores, which may be, for example, a search around map software, a takeaway search, or the like. Taking a takeaway search scene as an example, the information recommendation system may be a takeaway platform.

In specific implementation, a user may perform an operation on a terminal application interface of the takeout platform, for example, a search request of "merchants within 1km near" is triggered in the interface, and the takeout platform may obtain, in response to the search request, all merchants supporting takeout within 1km near the user according to the current location of the user, and then use the merchants as a plurality of candidate objects.

Step S112: and for each candidate object in the candidate objects, marking a corresponding label for the candidate object according to the feature data of the candidate object and the feature data of each object within a preset range from the candidate object.

In this embodiment, after obtaining each candidate object, the takeaway platform may add a corresponding tag to each candidate object according to the feature data of each candidate object. The feature data may include, but is not limited to: brand features, repurchase features, offer features, and the like. Each feature data has a corresponding label, for example, a brand feature corresponds to a brand label, a buyback feature corresponds to a buyback label, and a benefit feature corresponds to a benefit label.

When a corresponding tag is added to a candidate object, the feature data of the candidate object needs to be compared with the feature data of each object (hereinafter referred to as a peripheral object) within a preset range from the candidate object, and when the feature data of the candidate object and the feature data of the peripheral object satisfy a preset relationship, the tag corresponding to the feature data is determined to be added to the candidate object. The preset relationship is different according to different types of the feature data.

For example, taking the feature data as the repurchase rate in the repurchase feature as an example, when the repurchase rate of one merchant is greater than the average of the repurchase rates of surrounding merchants, it is determined that the merchant should add a tag indicating that the repurchase rate is higher. Taking the example that the feature data is the brand influence in the brand feature, when the brand influence of one merchant is larger than the average value of the brand influences of surrounding merchants, it is determined that the merchant should add a label indicating higher brand influence, wherein the brand influence can be measured by parameters including but not limited to user awareness ratio, promotional cost, merchant size, and the like. Taking the feature data as an example of the preferential strength in the preferential feature, when the preferential strength of one merchant is greater than the average value of the preferential strengths of surrounding merchants, determining that the merchant should add a label indicating that the merchant has a greater preferential strength, wherein the preferential strength can be measured by parameters, and the parameters include but are not limited to preferential duration, preferential amount, audience range and the like.

The determination condition for determining whether the merchant should add the label corresponding to the corresponding feature may also be set according to actual requirements, which is not specifically limited in this embodiment.

In this embodiment, the takeaway platform may obtain the tag of each candidate object in other manners besides adding the corresponding tag to each candidate object. For example, the takeaway platform may obtain the tag of each candidate object through a preset tag database, where the historical tag of each candidate object is stored in the tag database. Alternatively, the takeaway platform may obtain the tags of the candidate objects through a third-party platform, and the third-party platform may obtain the historical tags of the candidate objects.

By the embodiment, the labels of the off-line shops can be acquired, and further the mixed recommendation of the search object set and the search object individuals of the off-line shops can be realized, so that a user can find a satisfactory shop more easily.

With reference to the foregoing embodiment, in an implementation manner, after obtaining a plurality of object sets, the information recommendation system further performs a screening process on each object set to ensure quality of candidate objects in the object sets. Specifically, after obtaining the plurality of object sets, the following steps may be further performed on each object set in the plurality of object sets:

step 1: and obtaining the respective historical user behavior data of each candidate object included in the object set.

In this embodiment, the historical user behavior data of the candidate object may be a historical click rate, a historical order placement rate, a collection rate, and the like of the user, which is not specifically limited in this embodiment.

Step 2: and obtaining the label matching degree of the candidate object according to the feature data of each candidate object in the object set and the feature data of each object within a preset range from the candidate object.

In this embodiment, after obtaining a plurality of object sets for the offline store, the matching degree between each candidate object in the object set and the tag corresponding to the object set may be further determined. For example, candidate 1-candidate 3 are included in the object set M, and the corresponding label of the object set M is XX, the matching degree between candidate 1 and label XX, the matching degree between candidate 2 and label XX, and the matching degree between candidate 3 and label XX need to be calculated.

When the matching degree between each candidate object and the corresponding tag is calculated, the matching degree of the corresponding tag can be obtained according to a preset algorithm according to the feature data of the candidate object and the feature data of each object within a preset range from the candidate object. The principle can be as follows: ri ═ f (Ci, C). Wherein Ri represents a tag matching degree, f represents a preset algorithm for calculating the matching degree, Ci is feature data of the target candidate object, and C is feature data of each object within a preset range from the target candidate object, which is not specifically limited in this embodiment.

For example, when the matching degree of the target merchant and the label with the "higher repurchase rate" is calculated, the feature data adopted by the target merchant may be the repurchase rate in the repurchase feature, where Ci may represent the repurchase rate of the target merchant, and C may represent the average of the repurchase rates of merchants in the peripheral area of the target merchant. If the calculated match score is greater than the given threshold, it indicates that the tag match is high, i.e., the target merchant does have a high repurchase rate.

For another example, when calculating the matching degree between the target merchant and the tag with "higher brand influence", the feature data adopted by the target merchant may be the brand influence in the brand feature, where Ci may represent the brand influence of the target merchant, and C may represent the brand influence mean of the merchants in the peripheral area of the target merchant. If the calculated match score is greater than a given threshold, it indicates that the tag match is high, i.e., the target merchant does have a high brand impact.

And step 3: and filtering partial candidate objects according to the respective historical user behavior data and the label matching degree of each candidate object included in the object set to obtain a filtered object set.

In particular, the score of a candidate object may be obtained first according to the following formula:

Score＝ctri*k+p*Ri。

where ctri is a historical click rate, k is a first coefficient, Ri is a matching score of the candidate object and the corresponding tag, and p is a second coefficient.

Of course, ctri may also be other historical user behavior data, such as historical ordering rate, collection rate, etc., and at this time, k may be adaptively adjusted according to the type of the historical user behavior data.

In this embodiment, a score threshold (the score threshold is an empirical value) may be set in advance for each object set. For a set of objects, after calculating the score of each candidate object inside the set, the candidate objects with score scores smaller than a score threshold may be deleted from the set.

For example, when the object sets are shown in table 4 below, the process of filtering the object set a and the object set B may include:

TABLE 4

Step 1: the scores score of each candidate object in the object set a and the object set B are calculated.

For the set of objects a:

first a score of the candidate 1 is calculated _A1 ＝ctr _A1 *k+p*R _A1 Wherein ctr _A1 As the historical click rate of candidate 1, R _A1 Is the matching score of candidate 1 and tag X.

The score of the candidate 2 is then calculated _A2 ＝ctr _A2 *k+p*R ₂ Wherein ctr _A2 Is the historical click rate, R, of candidate 2 _A2 Is the matching score of candidate 2 with tag X.

Finally, the score of the candidate 3 is calculated _A3 ＝ctr _A3 *k+p*R _A3 Wherein ctr _A3 Is the historical click rate, R, of candidate 3 _A3 Is the matching score of candidate 3 with tag X.

For object set B:

first a score of the candidate 1 is calculated _B1 ＝ctr _B1 *k+p*R _B1 Wherein ctr is _B1 As the historical click rate of candidate 1, R _B1 Is the matching score of candidate 1 and label Y.

The score of the candidate 2 is then calculated _B2 ＝ctr _B2 *k+p*R _B2 Wherein ctr _B2 Is the historical click rate, R, of candidate 2 _B2 Is the matching score of candidate 2 with tag Y.

Finally, the score of the candidate 3 is calculated _B3 ＝ctr _B3 *k+p*R _B3 Wherein ctr _B3 Is the historical click rate, R, of candidate 3 _B3 Is the matching score of candidate 3 with label Y.

Step 2: and screening the candidate objects in the object set A according to the score threshold value 1 of the object set A, and screening the candidate objects in the object set B according to the score threshold value 2 of the object set B.

TABLE 5

For example, assuming the score condition of each candidate in table 4 is as shown in table 5, for the set a of objects, if it is specified that a score smaller than the score threshold 1 should be deleted and the score threshold 1 is 60, then the candidate object 2 should be deleted. For object set B, if it is specified that a score less than the score threshold 2 should be removed and the score threshold 2 is 60, then candidate object 1 should be removed.

After filtering each object set, the obtained filtered object set may be as shown in table 6:

TABLE 6

After the filtering operation is performed, the step S13 may include: and determining an object queue to be displayed from the plurality of filtered object sets and the plurality of object individuals.

In this embodiment, the filtered object set may include candidate objects with higher quality, so that the queue of the objects to be displayed is determined from the filtered object set and the plurality of object individuals, and it may be ensured that information recommended to the user can meet actual requirements of the user.

In this embodiment, the candidate objects in each object set are further screened through the historical behavior data obtained by the user feedback, so that the candidate objects in each object set are not only attached to the corresponding tags, but also better meet the actual requirements of the user.

In an implementation manner, in combination with the above embodiment, the present application further provides a method for determining a queue of objects to be presented from a plurality of object sets and a plurality of object individuals. Fig. 4 is a flowchart illustrating a method for determining a queue of objects to be presented according to an embodiment of the present application. Referring to fig. 4, the step S13 may include:

step S131: and determining the estimated user behavior data of the object sets and the object individuals.

In this embodiment, the estimated user behavior data may include an estimated click rate, an estimated order placing rate, an estimated collection rate, and the like, which is not specifically limited in this embodiment.

Step S132: and sequencing the object sets and the object individuals according to the estimated behavior data of the object sets and the object individuals and the preference of the user on the labels of the object sets and the object individuals.

In this embodiment, all the object sets and the object individuals may be mixed and sorted according to the sorting score of each object set or each object individual.

In specific implementation, for one object set, the process of obtaining the ranking score is as follows:

calculating the product of the quality of each candidate object inside and the weight parameter;

obtaining the sum of the products of the quality of all candidate objects and the weight parameter;

and summing the product of the weight parameter of the preference degree and the estimated click rate of the label corresponding to the object set with the sum of the products to obtain a value serving as a sorting score.

For one subject individual, the process of obtaining the ranking score is as follows:

calculating the product of the mass of the object individual and the weight parameter;

and summing the product of the weight parameter of the preference degree and the estimated click rate of the label corresponding to the object individual with the product of the mass of the object individual and the weight parameter to obtain a value as a sequencing score.

Specifically, the ranking score of each object set or each object individual can be calculated according to the following formula:

wherein l is a weight parameter of the preference degree, pctr is an estimated click rate of the user to the commercial tenants corresponding to different labels, ki is the weight parameter, qi is the quality score of each candidate object in an object set, and n is the number of the candidate objects in the object set.

After the ranking scores of all the object sets and the object individuals are obtained, the all the object sets and the object individuals can be ranked in a mixed mode from high to low according to the ranking scores. Illustratively, the ranking score of the set of objects 1 is 45, the ranking score of the set of objects 2 is 78, the ranking score of the set of objects 3 is 91, the ranking score of the set of objects 4 is 67, the ranking score of the individual of objects 1 is 42, and the ranking score of the individual of objects 2 is 59. Then the ranking results in order of ranking score from high to low are: object set 3, object set 2, object set 4, object individuals 2, object set 1, object individuals 1.

Step S133: and determining an object queue to be displayed according to the respective sequence numbers of the object sets and the object individuals.

After the sorting is completed, a part of object sets and object individuals can be selected from the sorted object sets and object individuals to form an object queue to be displayed. For example, the object queue to be presented may be composed of a preset number of object sets ranked at the top and object individuals.

In this embodiment, the plurality of object sets and the plurality of object individuals can be sequenced according to the pre-estimated user behavior data and the preference of the user to the respective tags of the plurality of object sets and the plurality of object individuals, so that the recommended object can better meet the actual requirements of the user, and the user experience is optimized.

In an implementation manner, the present application further provides a duplicate removal method in combination with the above embodiments. Specifically, the method further comprises:

displaying the object queue to be displayed, including:

In this embodiment, since the same candidate object may be in an object set corresponding to multiple tags, in order to avoid repeatedly recommending the same candidate object to the user for multiple times, the candidate object in the object queue to be displayed after the ranking may be removed, and only the candidate object appearing for the first time is retained, so that more recommendation information can be displayed in a limited display area, and the browsing depth of the user is improved.

With reference to the foregoing embodiments, the present application further provides a method for displaying a queue of objects to be displayed, which may specifically include:

In this embodiment, the user interface displays the object sets or the object individuals in units of lines, that is, a single object set is displayed in a line, a single object individual is displayed in a line, and the display effect is as shown in fig. 5. Fig. 5 is a schematic diagram illustrating a display effect of a queue to be presented according to an embodiment of the application. In fig. 5, the display area of the user interface may display 6 lines if the mixed ordering of the object set or the object individuals results in: the object set 1, the object set 2, the object individuals 3, the object set 4, the object set 5 and the object individuals 6, when displayed on the user interface, the first row displays the object set 1, the second row displays the object set 2, the third row displays the object individuals 3, the fourth row displays the object set 4, the fifth row displays the object set 5 and the sixth row displays the object individuals 6.

Of course, this embodiment only lists one display mode, and in specific implementation, the object set or the object individuals may also be displayed according to the setting of the user.

In this embodiment, the object set or the object individuals are displayed in a mixed manner, and compared with the case that the original display interface only displays a limited number of single candidate objects, the richness of the content displayed on the display interface can be significantly increased, so that the browsing depth of the user is enhanced, and the user can find a satisfactory search object more easily.

With reference to the above embodiment, in an implementation manner, when displaying the object set or the object individuals in rows, the following processing may be further performed:

for each object set in the object sequence to be displayed:

the method of the present application may further comprise:

when the object set is displayed at a row of display positions of the user interface, displaying part of candidate objects included in the object set at the row of display positions according to the sequence number of each candidate object included in the object set, and hiding the rest candidate objects included in the object set;

and when the operation of the user on the row of display positions occupied by the object set is detected, displaying the remaining candidate objects included by the object.

In this embodiment, for each object set, a plurality of candidate objects inside thereof may be sorted. The ranking criterion may be historical user behavior data of the candidate object, such as historical click rate, historical conversion rate, and the like, which is not limited in this embodiment.

For example, when sorting according to the historical click rate, the plurality of candidate objects may be sorted in the order of the historical click rate from high to low. For another example, when the objects are sorted according to the historical conversion rate, the objects can be sorted according to the historical conversion rate from high to low.

When an object set is displayed at a row of display positions of a user interface, part of candidate objects included in the object set may be displayed at the row of display positions according to the ranking number of each candidate object included in the object set, and a specified identifier is displayed at the end, and when a user clicks the identifier, the user interface automatically displays the remaining candidate objects included in the object set.

Fig. 6 is a schematic diagram illustrating a display effect of another queue to be presented according to an embodiment of the present application. In fig. 6, only 6 candidates (shaded portions) are displayed in the object set 1 displayed in the first row, more is displayed at the end, and when the user clicks the more flag, the remaining undisplayed candidates in the object set 1 are automatically loaded by the display interface. The displayed number 6 may be set to other values according to actual requirements, and the "more" identifier may also be set to other identifiers indicating that the remaining candidate objects may be requested, for example, "a", or the like.

In one embodiment, when the plurality of candidate objects in the object set are sorted according to the historical user behavior data, the plurality of candidate objects may be further sorted according to the following formula:

Q＝matchscore*f(ctr、cvr)

wherein, the matchscore of the candidate object and the label is set as matchedness score, ctr is historical click rate, cvr is historical conversion rate, and f (ctr, cvr) is quality score of the candidate object.

In the embodiment, the object set or the object individuals are displayed in a row mixing manner, and part of the candidate objects in the object set are displayed, so that compared with the situation that only a limited number of single candidate objects are displayed on the original display interface, the richness of the displayed content of the display interface can be remarkably increased, and the browsing depth of a user is further enhanced.

Fig. 7 is a process diagram of an object displaying method according to an embodiment of the present application. The object display method of the present application will be described in the following with reference to fig. 7.

In fig. 7, the information recommendation system first recalls a plurality of candidates according to the operation of the user. Then, obtaining respective labels of the multiple candidate objects, and then aggregating the multiple candidate objects according to whether the respective labels of the multiple candidate objects are the same, so as to obtain multiple object sets and multiple object individuals. Then, filtering processing is carried out on the candidate objects in each object set, and after filtering is finished, sorting processing is further carried out on the candidate objects in each object set. Then, a plurality of object individuals and each object set are mixed and ordered. And finally, obtaining and displaying the object queue to be displayed according to the mixed sorting result. When the plurality of object individuals and each object set are mixed and ranked, the preference degree of a user to each label can be considered, and when candidate objects in each object set are filtered, the respective historical user behavior data of each candidate object can be considered. The tags of the candidate objects may include basic tags obtained by the corresponding store in advance, such as a high-return passenger tag, a discount-amount tag, a good-boutique tag, and the like. The implementation of each step can be specifically referred to the above.

By the method, the search object set and the search object individual can be mixed and recommended, and compared with the situation that the original display interface only displays a limited number of single candidate objects, the richness of the content displayed on the display interface can be remarkably increased, the browsing depth of the user is further enhanced, the user can find the satisfied search object more easily, and the recommendation requirement of the user is further met better.

It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.

Based on the same inventive concept, an embodiment of the present application provides an object display apparatus 800. Referring to fig. 8, fig. 8 is a block diagram of an object display apparatus according to an embodiment of the present disclosure. As shown in fig. 8, the apparatus 800 includes:

a first obtaining module 801, configured to obtain a plurality of candidate objects and respective tags of the candidate objects;

an aggregation module 802, configured to aggregate the multiple candidate objects according to whether tags of the multiple candidate objects are the same or not, to obtain multiple object sets and multiple object individuals, where an object set includes at least two candidate objects of the multiple candidate objects, and the at least two candidate objects have the same tag, and an object individual is a candidate object;

a determining module 803, configured to determine a queue of objects to be displayed from the plurality of object sets and the plurality of object individuals, where the queue of objects to be displayed includes at least one object set and/or at least one object individual;

a displaying module 804, configured to display the queue of the objects to be displayed.

Optionally, the first obtaining module 801 includes:

Optionally, the apparatus 800 further comprises:

the determining module 803 includes:

Optionally, the determining module 803 includes:

the sequencing sub-module is used for sequencing the object sets and the object individuals according to the estimated behavior data of the object sets and the object individuals and the preference of the user on the labels of the object sets and the object individuals;

Optionally, the apparatus 800 further comprises:

the display module comprises:

and the first display submodule is used for displaying the queue to be displayed after the duplication elimination processing.

Optionally, the display module 804 includes:

Optionally, the apparatus 800 further comprises:

the first display module is used for displaying part of candidate objects included in the object set on a row display position according to the sequence number of each candidate object included in the object set when the object set is displayed on the row display position of the user interface, and hiding the rest candidate objects included in the object set;

Based on the same inventive concept, another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program, when executed by a processor, implements the steps in the method according to any of the above embodiments of the present application.

Based on the same inventive concept, another embodiment of the present application provides an electronic device 900, as shown in fig. 9. Fig. 9 is a schematic diagram of an electronic device according to an embodiment of the present application. The electronic device comprises a memory 902, a processor 901 and a computer program stored on the memory and executable on the processor, which when executed performs the steps of the method according to any of the embodiments of the present application.

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

The embodiments in the present specification are all described in a progressive manner, and each embodiment focuses on differences from other embodiments, and portions that are the same and similar between the embodiments may be referred to each other.

As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.

The object display method, the object display device, the electronic device and the readable storage medium provided by the present application are introduced in detail, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. An object display method, characterized in that the method comprises:

filtering part of candidate objects according to the respective historical user behavior data and the label matching degree of each candidate object in each object set to obtain a filtered object set, wherein the respective label matching degree of each candidate object in each object set is determined according to the feature data of the candidate object and the feature data of each object within a preset range from the candidate object;

determining an object queue to be displayed from a plurality of filtered object sets and the plurality of object individuals, wherein the object queue to be displayed comprises at least one object set and at least one object individual, or the object queue to be displayed comprises at least one object set;

and displaying the object queue to be displayed.

2. The method of claim 1, wherein obtaining a plurality of candidate objects and their respective labels comprises:

obtaining a plurality of candidate objects according to user operation;

3. The method of claim 1, wherein filtering out some candidate objects according to the respective historical user behavior data and the label matching degree of each candidate object included in each object set to obtain a filtered out object set, comprises:

and filtering partial candidate objects according to the respective historical user behavior data and the label matching degree of each candidate object included in the object set to obtain a filtered object set.

4. The method of claim 1, wherein determining a queue of objects to be presented from the plurality of sets of objects and the plurality of individuals of objects comprises:

5. The method of claim 4, further comprising:

displaying the object queue to be displayed, including:

6. The method according to any one of claims 1 to 5, wherein the displaying the queue of objects to be displayed comprises:

and displaying the object queue to be displayed on a user interface in rows, wherein one object individual in the object queue to be displayed occupies one row of display positions of the user interface, and one object set in the object queue to be displayed occupies one row of display positions of the user interface.

7. The method of claim 6, wherein for each set of objects in the queue of objects to be exposed:

the method further comprises the following steps:

8. An object display apparatus, the apparatus comprising:

the filtering module is used for filtering partial candidate objects according to the respective historical user behavior data and the label matching degree of each candidate object in each object set to obtain a filtered object set, wherein the respective label matching degree of each candidate object in each object set is determined according to the feature data of the candidate object and the feature data of each object within a preset range away from the candidate object;

a determining module, configured to determine an object queue to be displayed from the filtered object sets and the object individuals, where the object queue to be displayed includes at least one object set and at least one object individual, or the object queue to be displayed includes at least one object set;

and the display module is used for displaying the object queue to be displayed.

9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the object representing method according to any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing performs the steps of the object representation method according to any one of claims 1 to 7.