CN112685627A - Object pushing method and device, electronic equipment and storage medium - Google Patents
Object pushing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112685627A CN112685627A CN201910989857.3A CN201910989857A CN112685627A CN 112685627 A CN112685627 A CN 112685627A CN 201910989857 A CN201910989857 A CN 201910989857A CN 112685627 A CN112685627 A CN 112685627A
- Authority
- CN
- China
- Prior art keywords
- target
- combination
- user
- resource
- resources
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012549 training Methods 0.000 claims description 16
- 238000012512 characterization method Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 16
- 235000021186 dishes Nutrition 0.000 description 14
- 241000209094 Oryza Species 0.000 description 10
- 235000007164 Oryza sativa Nutrition 0.000 description 10
- 235000009566 rice Nutrition 0.000 description 10
- 235000021152 breakfast Nutrition 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000012216 screening Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 6
- 235000012054 meals Nutrition 0.000 description 6
- 238000007619 statistical method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 239000000796 flavoring agent Substances 0.000 description 4
- 235000013372 meat Nutrition 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000006694 eating habits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 235000005955 light diet Nutrition 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- 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
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the disclosure discloses an object pushing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring characteristic data of a target user; determining at least one target object according to the characteristic data of the target user; determining at least one target combination corresponding to the target object; wherein the target combination comprises at least two resources provided by the same target object; and pushing at least one target object and at least one target combination to a terminal corresponding to the target user. The problem that a user needs to select resource combinations one by one to spend a large amount of time and energy in an application scene where the user is used to obtain the resource combinations can be solved through the method and the device, and the resources in the target combinations are provided by the same target object, so that the problems of simultaneous delivery timeliness and delivery cost are solved, and the use experience of the user is greatly improved.
Description
Technical Field
The disclosure relates to the technical field of computers, in particular to an object pushing method and device, electronic equipment and a storage medium.
Background
With the development of internet technology, more and more online platforms appear, and the types of resources provided by the online platforms are more and more. The user can input the key words through a search interface provided by the online platform and search the required resources, or search the required resources one by one through a home page, a channel page or an activity meeting place page and the like of the online platform. However, the method has the disadvantages of complex operation flow, long time consumption, low efficiency, easy omission of required resources and difficult guarantee of accuracy.
Disclosure of Invention
The embodiment of the disclosure provides an object pushing method and device, electronic equipment and a storage medium.
In a first aspect, an embodiment of the present disclosure provides an object pushing method.
Specifically, the object pushing method includes:
acquiring characteristic data of a target user;
determining at least one target object according to the characteristic data of the target user;
determining at least one target combination corresponding to the target object; wherein the target combination comprises at least two resources provided by the same target object;
and pushing at least one target object and at least one target combination to a terminal corresponding to the target user.
With reference to the first aspect, the present disclosure provides in a first implementation manner of the first aspect, the feature data of the target user includes portrait data and location information; determining at least one target object according to the feature data of the target user, including:
determining a plurality of candidate objects in the area range of the position information;
determining at least one of the target objects from a plurality of the candidate objects using a machine self-learning model based on the target user's portrait data and the portrait data of the candidate objects.
With reference to the first aspect and/or the first implementation manner of the first aspect, in a second implementation manner of the first aspect, the positive sample used for training the machine self-learning model is a positive sample object obtained by a user; a negative example is a negative example object that was exposed before the user and has not been acquired by the user of a resource.
With reference to the first aspect, the first implementation manner of the first aspect, and/or the second implementation manner of the first aspect, in a third implementation manner of the first aspect, the feature data of the positive sample includes portrait data of the positive sample object and portrait data of a user who acquired a resource of the positive sample object; the characterization data of the negative exemplar includes portrait data of the negative exemplar object and portrait data of a user whose resources of the negative exemplar object are exposed.
With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, and/or the third implementation manner of the first aspect, in a fourth implementation manner of the first aspect, the feature data of the target user includes time information; determining at least one target combination corresponding to the target object, including:
and determining at least one target combination corresponding to the target object in the target time period of the time information.
With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, and/or the fourth implementation manner of the first aspect, in a fifth implementation manner of the first aspect, the determining at least one target combination corresponding to the target object in a target time period in which the time information is located includes:
and determining at least one target combination from resource combinations corresponding to the target object in the target time period according to the demand information provided by the target user.
With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, and/or the fifth implementation manner of the first aspect, in a sixth implementation manner of the first aspect, the determining, according to the requirement information provided by the target user, at least one target combination from resource combinations corresponding to the target object in the target time period includes:
when at least one first resource combination corresponding to the target object in the target time period exists, determining the target combination from the at least one first resource combination according to the requirement information; wherein the first resource combination comprises at least two resources of the target object;
when at least one first target combination corresponding to the target object in the target time period does not exist, determining the target combination from at least one second resource combination according to the demand information; the first resource combination is a preset fixed combination, and the times of acquisition by a user exceed a first preset threshold; the second resource combination is different from the preset fixed combination, the second resource combination comprises at least two resources of the target object, and the co-occurrence probability of the at least two resources acquired by the user at the same time exceeds a second preset threshold.
With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, and/or the sixth implementation manner of the first aspect, in a seventh implementation manner of the first aspect, the method further includes:
aiming at least one object and at least one preset time period, acquiring a candidate combination corresponding to the object in the preset time period according to a preset resource combination keyword and/or a preset resource combination attribute; the candidate combination comprises at least two resources which are provided by the object and can be acquired by a user within the preset time period;
determining at least one first resource combination corresponding to the object in the preset time period from the candidate combinations according to first history acquisition data; wherein the first history acquisition data comprises the number of times the candidate combination has been acquired by the user.
With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, and/or the seventh implementation manner of the first aspect, in an eighth implementation manner of the first aspect, the determining, from the candidate combinations, at least one first resource combination corresponding to the object within the preset time period according to the first history acquisition data includes:
sorting the candidate combinations according to the first history acquisition times;
determining at least one of the first resource combinations according to the ranking.
With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, the seventh implementation manner of the first aspect, and/or the eighth implementation manner of the first aspect, in a ninth implementation manner of the first aspect, the disclosure further includes:
determining a co-occurrence probability that at least two resources of at least one object are commonly acquired for at least one object and at least one preset time period; wherein the at least two resources can be acquired by the user within the preset time period;
and when the co-occurrence probability exceeds a second preset threshold, determining a resource combination comprising the at least two resources as a second resource combination corresponding to the object in the preset time period.
With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, the seventh implementation manner of the first aspect, the eighth implementation manner of the first aspect, and/or the ninth implementation manner of the first aspect, in a tenth implementation manner of the first aspect, the determining a co-occurrence probability that at least two resources of the object are jointly acquired includes:
determining a second historical acquisition time of one of the at least two resources;
determining a third history acquisition frequency that the at least two resources are acquired together;
and determining the co-occurrence probability according to the second history acquisition times and the third history acquisition times.
In a second aspect, an object pushing apparatus is provided in the embodiments of the present disclosure.
Specifically, the object pushing apparatus includes:
the first acquisition module is configured to acquire characteristic data of a target user;
a first determination module configured to determine at least one target object according to the feature data of the target user;
a second determination module configured to determine at least one target combination corresponding to the target object; wherein the target combination comprises at least two resources provided by the same target object;
and the pushing module is configured to push the at least one target object and the at least one target combination to a terminal corresponding to the target user.
With reference to the second aspect, the present disclosure provides in a first implementation manner of the second aspect, the feature data of the target user includes portrait data and location information; the first determining module includes:
a first determination submodule configured to determine a plurality of candidate objects within a region range in which the position information is located;
a second determination sub-module configured to determine at least one of the target objects from a plurality of the candidate objects using a machine self-learning model based on the portrait data of the target user and the portrait data of the candidate objects.
With reference to the second aspect and/or the first implementation manner of the second aspect, in a second implementation manner of the second aspect, the positive sample obtained by training the machine self-learning model is a positive sample object obtained by a user; a negative example is a negative example object that was exposed before the user and has not been acquired by the user of a resource.
With reference to the second aspect, the first implementation manner of the second aspect, and/or the second implementation manner of the second aspect, in a third implementation manner of the second aspect, the feature data of the positive sample includes portrait data of the positive sample object and portrait data of a user who acquired a resource of the positive sample object; the characterization data of the negative exemplar includes portrait data of the negative exemplar object and portrait data of a user whose resources of the negative exemplar object are exposed.
With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, and/or the third implementation manner of the second aspect, in a fourth implementation manner of the second aspect, the feature data of the target user includes time information; the second determining module includes:
and the third determining submodule is configured to determine at least one target combination corresponding to the target object in a target time period where the time information is located.
With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, and/or the fourth implementation manner of the second aspect, in a fifth implementation manner of the second aspect, the third determining submodule includes:
a fourth determining sub-module, configured to determine at least one target combination from resource combinations corresponding to the target object in the target time period according to the demand information provided by the target user.
With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, and/or the fifth implementation manner of the second aspect, in a sixth implementation manner of the second aspect, the fourth determining submodule includes:
a fifth determining submodule configured to determine, when at least one first resource combination corresponding to the target object in the target time period exists, the target combination from the at least one first resource combination according to the requirement information; wherein the first resource combination comprises at least two resources of the target object;
a sixth determining submodule configured to determine, when at least one first target combination corresponding to the target object in the target time period does not exist, the target combination from at least one second resource combination according to the demand information; the first resource combination is a preset fixed combination, and the times of acquisition by a user exceed a first preset threshold; the second resource combination is different from the preset fixed combination, the second resource combination comprises at least two resources of the target object, and the co-occurrence probability of the at least two resources acquired by the user at the same time exceeds a second preset threshold.
With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, and/or the sixth implementation manner of the second aspect, in a seventh implementation manner of the second aspect, the apparatus further includes:
the second acquisition module is configured to acquire a candidate combination corresponding to at least one object in at least one preset time period according to a preset resource combination keyword and/or a preset resource combination attribute; the candidate combination comprises at least two resources which are provided by the object and can be acquired by a user within the preset time period;
a third determining module configured to determine, from the candidate combinations, at least one first resource combination corresponding to the object within the preset time period according to the first history acquisition data; wherein the first history acquisition data comprises the number of times the candidate combination has been acquired by the user.
With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, and/or the seventh implementation manner of the second aspect, in an eighth implementation manner of the second aspect, the third determining module includes:
a ranking submodule configured to rank the candidate combinations according to the first historical acquisition times;
a seventh determining submodule configured to determine at least one of the first resource combinations according to the ordering.
With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, the seventh implementation manner of the second aspect, and/or the eighth implementation manner of the second aspect, in a ninth implementation manner of the second aspect, the apparatus further includes:
a fourth determination module configured to determine, for at least one object and at least one preset time period, a co-occurrence probability that at least two resources of the object are commonly acquired; wherein the at least two resources can be acquired by the user within the preset time period;
a fifth determining module, configured to determine, when the co-occurrence probability exceeds a second preset threshold, a resource combination including the at least two resources as a second resource combination corresponding to the object within the preset time period.
With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, the seventh implementation manner of the second aspect, the eighth implementation manner of the second aspect, and/or the ninth implementation manner of the second aspect, in a tenth implementation manner of the second aspect, the fifth determining module includes:
an eighth determining submodule configured to determine a second historical acquisition number of one of the at least two resources;
a ninth determining sub-module configured to determine a third history acquisition number of times that the at least two resources are acquired in common;
a tenth determination submodule configured to determine the co-occurrence probability according to the second and third history acquisition times.
The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above-described functions.
In one possible design, the object pushing apparatus includes a memory and a processor, the memory is used for storing one or more computer instructions for supporting the object pushing apparatus to execute the object pushing method in the first aspect, and the processor is configured to execute the computer instructions stored in the memory. The object pushing device may further comprise a communication interface for the object pushing device to communicate with other devices or a communication network.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including a memory and a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the object pushing method in the first aspect.
In a fourth aspect, the present disclosure provides a computer-readable storage medium for storing computer instructions for an object pushing device, where the computer instructions include computer instructions for performing any one of the methods described above.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
the method comprises the steps of obtaining characteristic data of a target user, determining a target object according with the characteristics of the target user according to the characteristic data, then determining a target combination provided by the target object, and further pushing the target object and the target combination to the target user; wherein the target combination comprises at least two resources included by the target object. By the method, the target object can be determined according to the characteristic data of the target user, the target combination is further obtained from the resources provided by the determined target object, the problem that the user needs to select the resource combinations one by one in the application scene of obtaining the resource combination to spend a large amount of time and energy is solved, and the resources in the target combination provided by the embodiment of the disclosure are provided by the same target object, so that the problems of simultaneous delivery timeliness and delivery cost are solved, and the use experience of the user is greatly improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings:
fig. 1 illustrates a flowchart of an object pushing method according to an embodiment of the present disclosure;
FIG. 2 shows a flow chart of step S102 according to the embodiment shown in FIG. 1;
FIG. 3 illustrates a flow diagram of a target combining portion according to an embodiment of the present disclosure;
FIG. 4 illustrates a flow diagram for obtaining a first resource combination portion according to an embodiment of the present disclosure;
FIG. 5 shows a flowchart of step S402 according to the embodiment shown in FIG. 4;
FIG. 6 illustrates a flow diagram for obtaining a second resource combination portion according to an embodiment of the present disclosure;
fig. 7 shows a flowchart of step S601 according to the embodiment shown in fig. 6;
fig. 8 illustrates a block diagram of an object pushing device according to an embodiment of the present disclosure;
FIG. 9 illustrates a block diagram of the structure of a first determination module 802 according to the embodiment illustrated in FIG. 8;
FIG. 10 shows a block diagram of the structure of a target combining section according to an embodiment of the present disclosure;
FIG. 11 is a block diagram illustrating a structure of a portion for obtaining a first resource combination according to an embodiment of the present disclosure;
FIG. 12 is a block diagram illustrating a third determination module 1102 according to the embodiment shown in FIG. 11;
FIG. 13 is a block diagram illustrating a structure of a portion for obtaining a second resource combination according to an embodiment of the present disclosure;
FIG. 14 is a block diagram illustrating a fifth determination module 1302 according to the embodiment shown in FIG. 13;
fig. 15 is a schematic structural diagram of an electronic device suitable for implementing an object pushing method according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.
In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or resource combinations thereof, and are not intended to preclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or resource combinations thereof are present or added.
It should also be noted that the embodiments and features of the embodiments in the present disclosure may be resource-combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 shows a flowchart of an object pushing method according to an embodiment of the present disclosure. As shown in fig. 1, the object pushing method includes the following steps:
in step S101, feature data of a target user is acquired;
in step S102, at least one target object is determined according to the feature data of the target user;
in step S103, at least one target combination corresponding to the target object is determined; wherein the target combination comprises at least two resources provided by the same target object;
in step S104, at least one target object and at least one target combination are pushed to the terminal of the target user.
In this embodiment, the object may be a system object for providing resources for a user in an online platform, such as a content provider, a business, and the like. The target object may be any object in the online platform. The resources provided by the object may be resources of content, products, services, etc. Online platforms include, but are not limited to, content distribution platforms, e-commerce platforms, and the like. For a content distribution platform, an object may be a content publisher or content owner, and the resource provided by the object may be an article, a piece of shared text, a piece of video, etc., whereas for an e-commerce platform, an object may be a merchant, and the resource provided by the object may be a product, a service, etc. The object related to the embodiment is mainly related to a provider providing resources such as data, content, products, services, and the like, and the provided resources are shared on an online platform for browsing, using, purchasing, and the like of a user.
The target user's feature data may include, but is not limited to, portrait data, location information, and/or time information of the target user. The portrait data may be user characteristics obtained by the online platform through statistical analysis according to historical behavior data of the target user, such as user gender, user age, user study, user customer unit price, user order-taking frequency, user interests and hobbies. The location information may be a current location of the target user or a location where the target user desires to obtain the resource (the location may be different from the current location information of the target user, for example, in a takeaway ordering platform, the current location of the target user is a company address, and the food delivery address may be a home address, etc.). The time information may be a time when the target user wants to obtain the resource from the target object, may be a current time, or may be a preset time in the future, which is determined according to an actual situation, and is not limited herein.
Since an object may have a regional attribute, the resources it provides have a regional limitation. For example, in the takeaway ordering platform, the object may correspond to a shop, and dishes provided by the shop are only limited to be obtained by users in the area where the physical shop is located, so that the position information provided by the target user may be considered when obtaining the target object. Furthermore, the object may also have a time attribute that provides a resource with a time limit, such as in a take-away ordering platform, where the dishes provided by the object may be breakfast dishes, lunch dishes, or dinner dishes, and are served during breakfast, lunch, or dinner sessions, respectively. The time information provided by the target user may also be taken into account when acquiring the target object. In the embodiment of the disclosure, at least one target object conforming to the characteristics of the target user can be obtained by screening the target user according to the characteristic data of the target user. For example, for the takeaway ordering platform, a shop whose delivery range covers the position information provided by the target user, and which provides dishes for the target user in the ordering time period and conforms to the eating habits, preferences, and the like of the target user may be screened out for the target user.
After the target object is determined, at least one target combination may be determined according to the resources provided by the target object, and the target combination may include at least two resources provided by the target object. Two resources may refer to two different resources. The target combination may be a hotspot combination among the numerous resource combinations provided by the target object that meets the needs of the target user. The target combination corresponding to the target object may be predetermined, for example, preset fixed combinations provided by the target object itself may be sorted according to the confidence, and when the target combination is determined according to the feature data of the target user, a target combination which meets the feature of the target user and/or can meet the requirement of the target user may be selected from the preset fixed combinations with higher confidence provided by the target object; for another example, a new combination may be formed according to the co-occurrence probability that the multiple resources are commonly acquired by the user for the resources provided by the target object, and a combination with the co-occurrence probability greater than a certain value is determined as a candidate combination corresponding to the target object.
After the target object and the target combination provided by the target object are determined, the target object and the target combination can be pushed to a terminal of a target user. When needed, the target user can check the target object and the target combination pushed by the online platform through the terminal and acquire the needed target combination.
The method comprises the steps of obtaining characteristic data of a target user, determining a target object according with the characteristics of the target user according to the characteristic data, then determining a target combination provided by the target object, and further pushing the target object and the target combination to the target user; wherein the target combination comprises at least two resources included by the target object. By the method, the target object can be determined according to the characteristic data of the target user, the target combination is further obtained from the resources provided by the determined target object, the problem that the user needs to select the resource combinations one by one in the application scene of obtaining the resource combination to spend a large amount of time and energy is solved, and the resources in the target combination provided by the embodiment of the disclosure are provided by the same target object, so that the problems of simultaneous delivery timeliness and delivery cost are solved, and the use experience of the user is greatly improved.
In an alternative implementation of this embodiment, as shown in fig. 2, the feature data of the target user includes portrait data and location information; the step S102, namely the step of determining at least one target object according to the feature data of the target user, further includes the following steps:
in step S201, a plurality of candidate objects within the area range where the position information is located are determined;
in step S202, at least one target object is determined from a plurality of candidate objects using a machine self-learning model based on the target user' S portrait data and the portrait data of the candidate objects.
In this alternative implementation, the feature data of the target user includes portrait data and location information of the target user. The portrait data of the target user may be user characteristics obtained by the online platform according to statistical analysis of historical behavior data of the target user, such as user gender, user age, user study, user unit price, user order frequency, user hobbies and interests, and the like. Different users have different choices for objects, for example, some users in a take-away dining platform like a heavy-tasting dish, and some users like a light diet. Therefore, the target object can be identified by filtering based on the image data of the target user. In addition, for the object with the region attribute, the current position of the target user or the position such as the delivery address set by the target user can be acquired, the object capable of providing resources for the target user at the position can be selected, and other objects can be eliminated.
In addition, different objects have different image data, and the image data of the object may be object characteristics obtained by statistical analysis of the online platform according to resource attributes provided by the object and crowd characteristics of resources obtained from the object, such as unit price of a merchant, whether the merchant is a brand merchant, and home-run scope of the merchant in the e-commerce platform.
In the screening of the target object, a part of the candidate objects may be screened out by the position information, and then the target object may be determined based on the image data of the target user, the image data of the candidate object, or the like. In some embodiments, the machine self-learning model may be trained in advance, and the image data of the target user and the image data of the candidate object may be input into the trained machine self-learning model, the machine self-learning model scores each candidate object according to the image data of the target user and the image data of the candidate object, and the candidate object having a score higher than a certain value may be determined as the target object.
In some embodiments, the machine self-learning model may be a linear model. It is understood that the machine self-learning model may also be a neural network model, and is not limited herein.
In an optional implementation manner of this embodiment, the positive sample obtained by training the machine self-learning model is a positive sample object obtained by the user; a negative example is a negative example object that was exposed before the user and has not been acquired by the user of a resource.
In this alternative implementation, a large number of sample objects may be collected and divided into positive and negative samples during the training process of the machine self-learning model. In some embodiments, sample objects that have been acquired by the user for the resource may be determined to be positive sample objects, while sample objects that have been exposed to the user (e.g., displayed in a page viewed by the user), but have not been acquired by the user for the resource, may be determined to be negative sample objects.
In an optional implementation of this embodiment, the feature data of the positive exemplar includes portrait data of the positive exemplar object and portrait data of a user who acquired a resource of the positive exemplar object; the characterization data of the negative exemplar includes portrait data of the negative exemplar object and portrait data of a user whose resources of the negative exemplar object are exposed.
In this alternative implementation, after the sample objects are determined, feature data may be extracted for the positive sample objects and the negative sample objects, respectively. For a positive exemplar object, the portrait data for the positive exemplar object itself and for the user who acquired the resources provided by the positive exemplar object may be extracted. For a negative exemplar object, the image data of the negative exemplar object itself and the image data of a user who has been exposed but has not acquired the resources provided by the negative exemplar object (e.g., the negative exemplar object is displayed on the browser page of user A, but user A has not acquired the resources of the negative exemplar object) may be extracted.
In the training process, after the machine self-learning model is selected, for example, a linear model is selected, the feature data corresponding to the positive sample object and the negative sample object may be brought into the linear model for training, and finally, after a large number of positive and negative samples are trained, the trained machine self-learning model may be obtained, and the specific training process may use a known training technique, which is not limited herein.
In an optional implementation manner of this embodiment, the feature data of the target user includes time information; the step S103, namely, the step of determining at least one target combination corresponding to the target object, further includes the following steps:
and determining at least one target combination corresponding to the target object in the target time period of the time information.
In this optional implementation, for an object having a time attribute, that is, an object supplied by the provided resource in a time-division manner, for example, a shop in a takeaway ordering platform, a target combination corresponding to the target object may also be determined in a time-division manner. For example, the resource combination provided by the object may be configured with an acquisition time period in advance, and when the target time period in which the time information in the feature data is located does not coincide with the acquisition time period of the resource combination, the resource combination may be removed.
In an optional implementation manner of this embodiment, the feature data of the target user includes time information; the step of determining at least one target combination corresponding to the target object in the target time period where the time information is located further includes the following steps:
and determining at least one target combination from resource combinations corresponding to the target object in the target time period according to the demand information provided by the target user.
In this optional implementation, the target combination may be obtained by screening according to the requirement information provided by the target user. The demand information of the target user may include, for example, restrictions on resource acquisition costs, the number of resources, and the like. For the take-away ordering platform, the demand information of the target user can comprise the number of people having meals, the total price range and the like. In the resource combination obtained by screening the time information, the resource combination can be further screened according to the requirement information of the target user, and the resource combination meeting the requirement information of the user is determined as the target combination.
In an optional implementation manner of this embodiment, as shown in fig. 3, the step of determining at least one target combination from resource combinations corresponding to the target object in the target time period according to the requirement information provided by the target user further includes the following steps:
in step S301, when at least one first resource combination corresponding to the target object exists in the target time period, determining the target combination from the at least one first resource combination according to the requirement information; wherein the first resource combination comprises at least two resources of the target object;
in step S302, when there is no at least one first target combination corresponding to the target object in the target time period, determining the target combination from at least one second resource combination according to the requirement information; the first resource combination is a preset fixed combination, and the times of acquisition by a user exceed a first preset threshold; the second resource combination is different from the preset fixed combination, the second resource combination comprises at least two resources of the target object, and the co-occurrence probability of the at least two resources acquired by the user at the same time exceeds a second preset threshold.
In this optional implementation, for the target object, two resource combinations may be predetermined: a first combination of resources and a second combination of resources; the first resource combination may be a resource combination with a higher confidence obtained by sorting preset fixed combinations provided by the target object according to the confidence, for example, the confidence of the resource combination may be measured by a first historical acquisition frequency of the resource combination obtained by the user, so in this way, a resource combination with a first historical acquisition frequency that is sorted before exceeding a first preset threshold may be determined as the first resource combination; the first preset threshold may be predetermined empirically or the like, and is not limited herein.
The second resource combination may be a resource provided for the target object and determined according to the co-occurrence probability obtained by the user in common for the plurality of resources, for example, in the takeaway ordering platform, when the probability of the "fish-flavor shredded meat" and the "rice" appearing in the user's order is greater than 0.5, the "fish-flavor shredded meat" and the "rice" combination may be determined as the second resource combination. In some embodiments, the second combination of resources may be in addition to the first combination of resources, and thus the second combination of resources may be different from the first combination of resources, i.e., the combinations that occurred in the first combination of resources will no longer occur in the second combination of resources.
When the target combination is screened according to the feature data and the demand information of the target user, the target combination can be screened from the first resource combination, and the first resource combination is a preset fixed combination provided by the target object, and the preset fixed combination can be matched in advance for related personnel according to the characteristics and the like of the resources provided by the target object, so that the first resource combination can be considered as the resource combination which best meets the habits, demands and the like of the user; therefore, the resource combination which is consistent with the target time period can be preferentially screened from the first resource combination, that is, the first resource combination which can be acquired by the user in the target time period is preferentially screened, and the target combination is finally determined from the resource combinations according to the requirement information of the target user.
If the first resource combination does not have a target combination which is consistent with the target time period, the resource combination which can be acquired by the user in the target time period can be screened from the second resource combination, and then the target combination is determined according to the requirement information of the target user.
In addition, if there is no resource combination corresponding to the target time period in the first resource combination and the second resource combination, a resource combination corresponding to another time period may be further selected from the first resource combination and the second resource combination, where the another time period may be a preset time period close to the target time period, for example, in a takeaway ordering platform, when the target time period is a lunch time period, the another time period may be a dinner time period, and may be preset according to an actual situation, which is not limited herein.
In an optional implementation manner of this embodiment, as shown in fig. 4, the method further includes the following steps:
in step S401, for at least one object and at least one preset time period, acquiring a candidate combination corresponding to the object within the preset time period according to a preset resource combination keyword and/or a preset resource combination attribute; the candidate combination comprises at least two resources which are provided by the object and can be acquired by a user within the preset time period;
in step S402, determining at least one first resource combination corresponding to the object in the preset time period from the candidate combinations according to first history acquisition data; wherein the first history acquisition data comprises the number of times the candidate combination has been acquired by the user.
In this optional implementation manner, for each of all objects or some objects of the online platform, in each preset time period, a corresponding first resource combination of the object in the preset time period may be predetermined.
The preset time period may be determined according to the supply time of the resource provided by the object of the online platform, for example, for a take away dining platform, the preset time period may be divided into five periods in total, breakfast, lunch, dinner and night.
When the first resource combination is determined, the preset fixed combination provided by the current object can be acquired from the online platform according to the preset resource combination keyword and/or the preset resource combination attribute. For example, in the take-away ordering platform, a package which is already collocated and is served by a merchant can be searched from a shop through keywords such as "package", "1 person meal", "two persons meal", and the like, and when the merchant enters dishes on the online platform, whether the package is a package may be marked through a fixed attribute tag and the like, so that the package served by the shop can also be obtained through the attribute tag.
In order to help a user to accelerate the time for selecting resources, a candidate combination with higher confidence coefficient is screened out from candidate combinations obtained through preset resource combination keywords and/or preset resource combination attributes, and is determined as a first resource combination. In some embodiments, the confidence of a candidate combination may be measured by the first historical number of times the candidate combination was obtained by the user, and if the number of times the candidate combination was obtained by the user is greater, the confidence of the candidate combination may be considered to be higher, otherwise the confidence of the candidate combination is lower.
In an optional implementation manner of this embodiment, as shown in fig. 5, the step S402, namely, the step of determining, from the candidate combinations according to the first history acquisition data, at least one first resource combination corresponding to the object within the preset time period, further includes the following steps:
in step S501, the candidate combinations are ranked according to the first history acquisition times;
in step S502, at least one of the first resource combinations is determined according to the ranking.
In this alternative implementation, the candidate combinations are ranked according to how many times the user has acquired the first history over a period of time in the past. In some embodiments, the candidate combinations may be ranked from at least the first history acquisition number, and a certain number of top ranked candidate combinations may be determined as the first resource combination of the target object.
In an optional implementation manner of this embodiment, as shown in fig. 6, the method further includes the following steps:
in step S601, for at least one object and at least one preset time period, determining a co-occurrence probability that at least two resources of the object are commonly acquired; wherein the at least two resources can be acquired by the user within the preset time period;
in step S602, when the co-occurrence probability exceeds a second preset threshold, a resource combination including the at least two resources is determined as a second resource combination corresponding to the object in the preset time period.
In this optional implementation manner, for each of all objects or some objects of the online platform, in each preset time period, a second resource combination corresponding to the object in the preset time period may also be predetermined.
The preset time period may be determined according to the supply time of the resource provided by the object of the online platform, for example, for a take away dining platform, the preset time period may be divided into five periods in total, breakfast, lunch, dinner and night.
In determining the second resource combination, the second resource combination may be determined according to a co-occurrence probability that a plurality of resources provided by the same object are collectively acquired. The common acquisition here may be, for example, a common ordering of the plurality of resources in the same order. The co-occurrence probability may be determined according to the number of times the plurality of resources are acquired in the past period of time together with the number of times the plurality of resources are acquired.
The second preset threshold may be predetermined empirically or the like, and is not limited herein.
In an optional implementation manner of this embodiment, as shown in fig. 7, the step S601, that is, the step of determining a co-occurrence probability that at least two resources of the object are commonly acquired, further includes the following steps:
in step S701, determining a second history acquisition number of one of the at least two resources;
in step S702, a third history acquisition number of times that the at least two resources are commonly acquired is determined;
in step S703, the co-occurrence probability is determined according to the second history acquisition times and the third history acquisition times.
In this alternative implementation, the co-occurrence probability may be determined by the second history acquisition times of the plurality of resources in the resource combination and the third history acquisition times of the plurality of resources being acquired together.
For example, if the number of times that resource a is acquired is m and the number of times that resources a and B are acquired together is n, the co-occurrence probability may be determined by the ratio of n to m, and if the value of n/m is large, the co-occurrence probability of resources a and B may be considered to be large, and if the value of n/m is small, the co-occurrence probability of resources a and B may be considered to be small.
In some embodiments, the second historical acquisition times may be the historical acquisition times of any one of the resource combinations, or may be the acquisition times of the dominant resource, because one resource combination selected by the user may be formed by matching the primary resource and the secondary resource, and the secondary resource may often be a matching resource of a plurality of different resources, and if the historical acquisition times of the secondary resource are selected to obtain a co-occurrence probability, the result may not be very accurate. For example, in the takeaway ordering platform, in the matching combination of the pan and the rice, the pan is the dominant position, and the rice is the secondary position, so that the historical acquisition times of the pan can be taken as the second historical acquisition times, and the times of the pan and the rice being acquired together can be taken as the third historical acquisition times.
The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.
Fig. 8 illustrates a block diagram of an object pushing apparatus according to an embodiment of the present disclosure, which may be implemented as part or all of an electronic device through software, hardware, or a combination of the two. As shown in fig. 8, the object pushing apparatus includes:
a first obtaining module 801 configured to obtain feature data of a target user;
a first determination module 802 configured to determine at least one target object according to the feature data of the target user;
a second determining module 803 configured to determine at least one target combination corresponding to the target object; wherein the target combination comprises at least two resources provided by the same target object;
a pushing module 804 configured to push at least one target object and at least one target combination to a terminal corresponding to the target user.
In this embodiment, the object may be a system object for providing resources for a user in an online platform, such as a content provider, a business, and the like. The target object may be any object in the online platform. The resources provided by the object may be resources of content, products, services, etc. Online platforms include, but are not limited to, content distribution platforms, e-commerce platforms, and the like. For a content distribution platform, an object may be a content publisher or content owner, and the resource provided by the object may be an article, a piece of shared text, a piece of video, etc., whereas for an e-commerce platform, an object may be a merchant, and the resource provided by the object may be a product, a service, etc. The object related to the embodiment is mainly related to a provider providing resources such as data, content, products, services, and the like, and the provided resources are shared on an online platform for browsing, using, purchasing, and the like of a user.
The target user's feature data may include, but is not limited to, portrait data, location information, and/or time information of the target user. The portrait data may be user characteristics obtained by the online platform through statistical analysis according to historical behavior data of the target user, such as user gender, user age, user study, user customer unit price, user order-taking frequency, user interests and hobbies. The location information may be a current location of the target user or a location where the target user desires to obtain the resource (the location may be different from the current location information of the target user, for example, in a takeaway ordering platform, the current location of the target user is a company address, and the food delivery address may be a home address, etc.). The time information may be a time when the target user wants to obtain the resource from the target object, may be a current time, or may be a preset time in the future, which is determined according to an actual situation, and is not limited herein.
Since an object may have a regional attribute, the resources it provides have a regional limitation. For example, in the takeaway ordering platform, the object may correspond to a shop, and dishes provided by the shop are only limited to be obtained by users in the area where the physical shop is located, so that the position information provided by the target user may be considered when obtaining the target object. Furthermore, the object may also have a time attribute that provides a resource with a time limit, such as in a take-away ordering platform, where the dishes provided by the object may be breakfast dishes, lunch dishes, or dinner dishes, and are served during breakfast, lunch, or dinner sessions, respectively. The time information provided by the target user may also be taken into account when acquiring the target object. In the embodiment of the disclosure, at least one target object conforming to the characteristics of the target user can be obtained by screening the target user according to the characteristic data of the target user. For example, for the takeaway ordering platform, a shop whose delivery range covers the position information provided by the target user, and which provides dishes for the target user in the ordering time period and conforms to the eating habits, preferences, and the like of the target user may be screened out for the target user.
After the target object is determined, at least one target combination may be determined according to the resources provided by the target object, and the target combination may include at least two resources provided by the target object. Two resources may refer to two different resources. The target combination may be a hotspot combination among the numerous resource combinations provided by the target object that meets the needs of the target user. The target combination corresponding to the target object may be predetermined, for example, preset fixed combinations provided by the target object itself may be sorted according to the confidence, and when the target combination is determined according to the feature data of the target user, a target combination which meets the feature of the target user and/or can meet the requirement of the target user may be selected from the preset fixed combinations with higher confidence provided by the target object; for another example, a new combination may be formed according to the co-occurrence probability that the multiple resources are commonly acquired by the user for the resources provided by the target object, and a combination with the co-occurrence probability greater than a certain value is determined as a candidate combination corresponding to the target object.
After the target object and the target combination provided by the target object are determined, the target object and the target combination can be pushed to a terminal of a target user. When needed, the target user can check the target object and the target combination pushed by the online platform through the terminal and acquire the needed target combination.
The method comprises the steps of obtaining characteristic data of a target user, determining a target object according with the characteristics of the target user according to the characteristic data, then determining a target combination provided by the target object, and further pushing the target object and the target combination to the target user; wherein the target combination comprises at least two resources included by the target object. By the method, the target object can be determined according to the characteristic data of the target user, the target combination is further obtained from the resources provided by the determined target object, the problem that the user needs to select the resource combinations one by one in the application scene of obtaining the resource combination to spend a large amount of time and energy is solved, and the resources in the target combination provided by the embodiment of the disclosure are provided by the same target object, so that the problems of simultaneous delivery timeliness and delivery cost are solved, and the use experience of the user is greatly improved.
In an alternative implementation of this embodiment, as shown in fig. 9, the feature data of the target user includes portrait data and location information; the first determining module 802 includes:
a first determining submodule 901 configured to determine a plurality of candidate objects within a region range where the position information is located;
a second determining sub-module 902 configured to determine at least one of the target objects from a plurality of the candidate objects using a machine self-learning model based on the portrait data of the target user and the portrait data of the candidate objects.
In this alternative implementation, the feature data of the target user includes portrait data and location information of the target user. The portrait data of the target user may be user characteristics obtained by the online platform according to statistical analysis of historical behavior data of the target user, such as user gender, user age, user study, user unit price, user order frequency, user hobbies and interests, and the like. Different users have different choices for objects, for example, some users in a take-away dining platform like a heavy-tasting dish, and some users like a light diet. Therefore, the target object can be identified by filtering based on the image data of the target user. In addition, for the object with the region attribute, the current position of the target user or the position such as the delivery address set by the target user can be acquired, the object capable of providing resources for the target user at the position can be selected, and other objects can be eliminated.
In addition, different objects have different image data, and the image data of the object may be object characteristics obtained by statistical analysis of the online platform according to resource attributes provided by the object and crowd characteristics of resources obtained from the object, such as unit price of a merchant, whether the merchant is a brand merchant, and home-run scope of the merchant in the e-commerce platform.
In the screening of the target object, a part of the candidate objects may be screened out by the position information, and then the target object may be determined based on the image data of the target user, the image data of the candidate object, or the like. In some embodiments, the machine self-learning model may be trained in advance, and the image data of the target user and the image data of the candidate object may be input into the trained machine self-learning model, the machine self-learning model scores each candidate object according to the image data of the target user and the image data of the candidate object, and the candidate object having a score higher than a certain value may be determined as the target object.
In some embodiments, the machine self-learning model may be a linear model. It is understood that the machine self-learning model may also be a neural network model, and is not limited herein.
In an optional implementation manner of this embodiment, the positive sample obtained by training the machine self-learning model is a positive sample object obtained by the user; a negative example is a negative example object that was exposed before the user and has not been acquired by the user of a resource.
In this alternative implementation, a large number of sample objects may be collected and divided into positive and negative samples during the training process of the machine self-learning model. In some embodiments, sample objects that have been acquired by the user for the resource may be determined to be positive sample objects, while sample objects that have been exposed to the user (e.g., displayed in a page viewed by the user), but have not been acquired by the user for the resource, may be determined to be negative sample objects.
In an optional implementation of this embodiment, the feature data of the positive exemplar includes portrait data of the positive exemplar object and portrait data of a user who acquired a resource of the positive exemplar object; the characterization data of the negative exemplar includes portrait data of the negative exemplar object and portrait data of a user whose resources of the negative exemplar object are exposed.
In this alternative implementation, after the sample objects are determined, feature data may be extracted for the positive sample objects and the negative sample objects, respectively. For a positive exemplar object, the portrait data for the positive exemplar object itself and for the user who acquired the resources provided by the positive exemplar object may be extracted. For a negative exemplar object, the image data of the negative exemplar object itself and the image data of a user who has been exposed but has not acquired the resources provided by the negative exemplar object (e.g., the negative exemplar object is displayed on the browser page of user A, but user A has not acquired the resources of the negative exemplar object) may be extracted.
In the training process, after the machine self-learning model is selected, for example, a linear model is selected, the feature data corresponding to the positive sample object and the negative sample object may be brought into the linear model for training, and finally, after a large number of positive and negative samples are trained, the trained machine self-learning model may be obtained, and the specific training process may use a known training technique, which is not limited herein.
In an optional implementation manner of this embodiment, the feature data of the target user includes time information; the second determining module 803 includes:
and the third determining submodule is configured to determine at least one target combination corresponding to the target object in a target time period where the time information is located.
In this optional implementation, for an object having a time attribute, that is, an object supplied by the provided resource in a time-division manner, for example, a shop in a takeaway ordering platform, a target combination corresponding to the target object may also be determined in a time-division manner. For example, the resource combination provided by the object may be configured with an acquisition time period in advance, and when the target time period in which the time information in the feature data is located does not coincide with the acquisition time period of the resource combination, the resource combination may be removed.
In an optional implementation manner of this embodiment, the feature data of the target user includes time information; the third determination submodule includes:
a fourth determining sub-module, configured to determine at least one target combination from resource combinations corresponding to the target object in the target time period according to the demand information provided by the target user.
In this optional implementation, the target combination may be obtained by screening according to the requirement information provided by the target user. The demand information of the target user may include, for example, restrictions on resource acquisition costs, the number of resources, and the like. For the take-away ordering platform, the demand information of the target user can comprise the number of people having meals, the total price range and the like. In the resource combination obtained by screening the time information, the resource combination can be further screened according to the requirement information of the target user, and the resource combination meeting the requirement information of the user is determined as the target combination.
In an optional implementation manner of this embodiment, as shown in fig. 10, the fourth determining sub-module includes:
a fifth determining submodule 1001, configured to determine, when at least one first resource combination corresponding to the target object exists in the target time period, the target combination from the at least one first resource combination according to the requirement information; wherein the first resource combination comprises at least two resources of the target object;
a sixth determining sub-module 1002, configured to determine, when at least one first target combination corresponding to the target object in the target time period does not exist, the target combination from at least one second resource combination according to the requirement information; the first resource combination is a preset fixed combination, and the times of acquisition by a user exceed a first preset threshold; the second resource combination is different from the preset fixed combination, the second resource combination comprises at least two resources of the target object, and the co-occurrence probability of the at least two resources acquired by the user at the same time exceeds a second preset threshold.
In this optional implementation, for the target object, two resource combinations may be predetermined: a first combination of resources and a second combination of resources; the first resource combination may be a resource combination with a higher confidence obtained by sorting preset fixed combinations provided by the target object according to the confidence, for example, the confidence of the resource combination may be measured by a first historical acquisition frequency of the resource combination obtained by the user, so in this way, a resource combination with a first historical acquisition frequency that is sorted before exceeding a first preset threshold may be determined as the first resource combination; the first preset threshold may be predetermined empirically or the like, and is not limited herein.
The second resource combination may be a resource provided for the target object and determined according to the co-occurrence probability obtained by the user in common for the plurality of resources, for example, in the takeaway ordering platform, when the probability of the "fish-flavor shredded meat" and the "rice" appearing in the user's order is greater than 0.5, the "fish-flavor shredded meat" and the "rice" combination may be determined as the second resource combination. In some embodiments, the second combination of resources may be in addition to the first combination of resources, and thus the second combination of resources may be different from the first combination of resources, i.e., the combinations that occurred in the first combination of resources will no longer occur in the second combination of resources.
When the target combination is screened according to the feature data and the demand information of the target user, the target combination can be screened from the first resource combination, and the first resource combination is a preset fixed combination provided by the target object, and the preset fixed combination can be matched in advance for related personnel according to the characteristics and the like of the resources provided by the target object, so that the first resource combination can be considered as the resource combination which best meets the habits, demands and the like of the user; therefore, the resource combination which is consistent with the target time period can be preferentially screened from the first resource combination, that is, the first resource combination which can be acquired by the user in the target time period is preferentially screened, and the target combination is finally determined from the resource combinations according to the requirement information of the target user.
If the first resource combination does not have a target combination which is consistent with the target time period, the resource combination which can be acquired by the user in the target time period can be screened from the second resource combination, and then the target combination is determined according to the requirement information of the target user.
In addition, if there is no resource combination corresponding to the target time period in the first resource combination and the second resource combination, a resource combination corresponding to another time period may be further selected from the first resource combination and the second resource combination, where the another time period may be a preset time period close to the target time period, for example, in a takeaway ordering platform, when the target time period is a lunch time period, the another time period may be a dinner time period, and may be preset according to an actual situation, which is not limited herein.
In an optional implementation manner of this embodiment, as shown in fig. 11, the apparatus further includes:
a second obtaining module 1101, configured to, for at least one object and at least one preset time period, obtain, according to a preset resource combination keyword and/or a preset resource combination attribute, a candidate combination corresponding to the object within the preset time period; the candidate combination comprises at least two resources which are provided by the object and can be acquired by a user within the preset time period;
a third determining module 1102, configured to determine, from the candidate combinations, at least one first resource combination corresponding to the object within the preset time period according to the first history acquisition data; wherein the first history acquisition data comprises the number of times the candidate combination has been acquired by the user.
In this optional implementation manner, for each of all objects or some objects of the online platform, in each preset time period, a corresponding first resource combination of the object in the preset time period may be predetermined.
The preset time period may be determined according to the supply time of the resource provided by the object of the online platform, for example, for a take away dining platform, the preset time period may be divided into five periods in total, breakfast, lunch, dinner and night.
When the first resource combination is determined, the preset fixed combination provided by the current object can be acquired from the online platform according to the preset resource combination keyword and/or the preset resource combination attribute. For example, in the take-away ordering platform, a package which is already collocated and is served by a merchant can be searched from a shop through keywords such as "package", "1 person meal", "two persons meal", and the like, and when the merchant enters dishes on the online platform, whether the package is a package may be marked through a fixed attribute tag and the like, so that the package served by the shop can also be obtained through the attribute tag.
In order to help a user to accelerate the time for selecting resources, a candidate combination with higher confidence coefficient is screened out from candidate combinations obtained through preset resource combination keywords and/or preset resource combination attributes, and is determined as a first resource combination. In some embodiments, the confidence of a candidate combination may be measured by the first historical number of times the candidate combination was obtained by the user, and if the number of times the candidate combination was obtained by the user is greater, the confidence of the candidate combination may be considered to be higher, otherwise the confidence of the candidate combination is lower.
In an optional implementation manner of this embodiment, as shown in fig. 12, the third determining module 1102 includes:
a ranking submodule 1201 configured to rank the candidate combinations according to the first history acquisition times;
a seventh determining submodule 1202 configured to determine at least one of the first resource combinations according to the ranking.
In this alternative implementation, the candidate combinations are ranked according to how many times the user has acquired the first history over a period of time in the past. In some embodiments, the candidate combinations may be ranked from at least the first history acquisition number, and a certain number of top ranked candidate combinations may be determined as the first resource combination of the target object.
In an optional implementation manner of this embodiment, as shown in fig. 13, the apparatus further includes:
a fourth determining module 1301 configured to determine, for at least one object and at least one preset time period, a co-occurrence probability that at least two resources of the object are commonly acquired; wherein the at least two resources can be acquired by the user within the preset time period;
a fifth determining module 1302, configured to determine, when the co-occurrence probability exceeds a second preset threshold, a resource combination including the at least two resources as a second resource combination corresponding to the object within the preset time period.
In this optional implementation manner, for each of all objects or some objects of the online platform, in each preset time period, a second resource combination corresponding to the object in the preset time period may also be predetermined.
The preset time period may be determined according to the supply time of the resource provided by the object of the online platform, for example, for a take away dining platform, the preset time period may be divided into five periods in total, breakfast, lunch, dinner and night.
In determining the second resource combination, the second resource combination may be determined according to a co-occurrence probability that a plurality of resources provided by the same object are collectively acquired. The common acquisition here may be, for example, a common ordering of the plurality of resources in the same order. The co-occurrence probability may be determined according to the number of times the plurality of resources are acquired in the past period of time together with the number of times the plurality of resources are acquired.
The second preset threshold may be predetermined empirically or the like, and is not limited herein.
In an optional implementation manner of this embodiment, as shown in fig. 14, the fifth determining module 1302 includes:
an eighth determining submodule 1401 configured to determine a second historical acquisition number of one of the at least two resources;
a ninth determining sub-module 1402 configured to determine a third history acquisition number of times that the at least two resources are acquired in common;
a tenth determination submodule 1403 configured to determine the co-occurrence probability according to the second and third history acquisition times.
In this alternative implementation, the co-occurrence probability may be determined by the second history acquisition times of the plurality of resources in the resource combination and the third history acquisition times of the plurality of resources being acquired together.
For example, if the number of times that resource a is acquired is m and the number of times that resources a and B are acquired together is n, the co-occurrence probability may be determined by the ratio of n to m, and if the value of n/m is large, the co-occurrence probability of resources a and B may be considered to be large, and if the value of n/m is small, the co-occurrence probability of resources a and B may be considered to be small.
In some embodiments, the second historical acquisition times may be the historical acquisition times of any one of the resource combinations, or may be the acquisition times of the dominant resource, because one resource combination selected by the user may be formed by matching the primary resource and the secondary resource, and the secondary resource may often be a matching resource of a plurality of different resources, and if the historical acquisition times of the secondary resource are selected to obtain a co-occurrence probability, the result may not be very accurate. For example, in the takeaway ordering platform, in the matching combination of the pan and the rice, the pan is the dominant position, and the rice is the secondary position, so that the historical acquisition times of the pan can be taken as the second historical acquisition times, and the times of the pan and the rice being acquired together can be taken as the third historical acquisition times.
The disclosed embodiments also provide an electronic device, as shown in fig. 15, comprising at least one processor 1501; and a memory 1502 communicatively coupled to the at least one processor 1501; the memory 1502 stores instructions executable by the at least one processor 1501, the instructions being executable by the at least one processor 1501 to implement:
acquiring characteristic data of a target user;
determining at least one target object according to the characteristic data of the target user;
determining at least one target combination corresponding to the target object; wherein the target combination comprises at least two resources provided by the same target object;
and pushing at least one target object and at least one target combination to a terminal corresponding to the target user.
The feature data of the target user comprises portrait data and position information; determining at least one target object according to the feature data of the target user, including:
determining a plurality of candidate objects in the area range of the position information;
determining at least one of the target objects from a plurality of the candidate objects using a machine self-learning model based on the target user's portrait data and the portrait data of the candidate objects.
The positive sample for training the machine self-learning model is a positive sample object of a resource obtained by a user; a negative example is a negative example object that was exposed before the user and has not been acquired by the user of a resource.
Wherein the feature data of the positive exemplar includes portrait data of the positive exemplar object and portrait data of a user who acquired a resource of the positive exemplar object; the characterization data of the negative exemplar includes portrait data of the negative exemplar object and portrait data of a user whose resources of the negative exemplar object are exposed.
Wherein the characteristic data of the target user comprises time information; determining at least one target combination corresponding to the target object, including:
and determining at least one target combination corresponding to the target object in the target time period of the time information.
Determining at least one target combination corresponding to the target object in the target time period in which the time information is located includes:
and determining at least one target combination from resource combinations corresponding to the target object in the target time period according to the demand information provided by the target user.
Wherein, determining at least one target combination from the resource combinations corresponding to the target object in the target time period according to the demand information provided by the target user comprises:
when at least one first resource combination corresponding to the target object in the target time period exists, determining the target combination from the at least one first resource combination according to the requirement information; wherein the first resource combination comprises at least two resources of the target object;
when at least one first target combination corresponding to the target object in the target time period does not exist, determining the target combination from at least one second resource combination according to the demand information; the first resource combination is a preset fixed combination, and the times of acquisition by a user exceed a first preset threshold; the second resource combination is different from the preset fixed combination, the second resource combination comprises at least two resources of the target object, and the co-occurrence probability of the at least two resources acquired by the user at the same time exceeds a second preset threshold.
Wherein, still include:
aiming at least one object and at least one preset time period, acquiring a candidate combination corresponding to the object in the preset time period according to a preset resource combination keyword and/or a preset resource combination attribute; the candidate combination comprises at least two resources which are provided by the object and can be acquired by a user within the preset time period;
determining at least one first resource combination corresponding to the object in the preset time period from the candidate combinations according to first history acquisition data; wherein the first history acquisition data comprises the number of times the candidate combination has been acquired by the user.
Determining at least one first resource combination corresponding to the object in the preset time period from the candidate combinations according to first history acquisition data, wherein the determining comprises:
sorting the candidate combinations according to the first history acquisition times;
determining at least one of the first resource combinations according to the ranking.
Wherein, still include:
determining a co-occurrence probability that at least two resources of at least one object are commonly acquired for at least one object and at least one preset time period; wherein the at least two resources can be acquired by the user within the preset time period;
and when the co-occurrence probability exceeds a second preset threshold, determining a resource combination comprising the at least two resources as a second resource combination corresponding to the object in the preset time period.
Wherein determining a co-occurrence probability that at least two resources of the object are commonly acquired comprises:
determining a second historical acquisition time of one of the at least two resources;
determining a third history acquisition frequency that the at least two resources are acquired together;
and determining the co-occurrence probability according to the second history acquisition times and the third history acquisition times.
Specifically, the processor 1501 and the memory 1502 may be connected by a bus or in another manner, and fig. 15 illustrates an example of connection by a bus. The memory 1502, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 1501 executes various functional applications of the device and data processing, i.e., implements the above-described methods in the embodiments of the present disclosure, by executing nonvolatile software programs, instructions, and modules stored in the memory 1502.
The memory 1502 may include a program storage area that may store an operating system, an application program required for at least one function, and a data storage area; the storage data area may store historical data of shipping network traffic, and the like. Further, the memory 1502 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the electronic device optionally includes a communications component 1503 and the memory 1502 optionally includes memory remotely located from the processor 1501, which may be connected to an external device through the communications component 1503. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations of resources thereof.
One or more modules are stored in the memory 1502 and when executed by the one or more processors 1501 perform the above-described methods in embodiments of the present disclosure.
The product can execute the method provided by the embodiment of the disclosure, has corresponding functional modules and beneficial effects of the execution method, and reference can be made to the method provided by the embodiment of the disclosure for technical details which are not described in detail in the embodiment.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.
As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be understood by those skilled in the art that the scope of the present invention in the present disclosure is not limited to the technical solutions in which the specific resources of the above technical features are combined, and also covers other technical solutions in which any resource combination of the above technical features or their equivalents is performed without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Claims (10)
1. An object pushing method, comprising:
acquiring characteristic data of a target user;
determining at least one target object according to the characteristic data of the target user;
determining at least one target combination corresponding to the target object; wherein the target combination comprises at least two resources provided by the same target object;
and pushing at least one target object and at least one target combination to a terminal corresponding to the target user.
2. The method of claim 1, wherein the target user's feature data includes portrait data and location information; determining at least one target object according to the feature data of the target user, including:
determining a plurality of candidate objects in the area range of the position information;
determining at least one of the target objects from a plurality of the candidate objects using a machine self-learning model based on the target user's portrait data and the portrait data of the candidate objects.
3. The method of claim 2, wherein the positive sample for training the machine self-learning model is a positive sample object of a resource acquired by a user; a negative example is a negative example object that was exposed before the user and has not been acquired by the user of a resource.
4. The method of claim 3, wherein the feature data of the positive sample comprises representation data of the positive sample object and representation data of a user who acquired a resource of the positive sample object; the characterization data of the negative exemplar includes portrait data of the negative exemplar object and portrait data of a user whose resources of the negative exemplar object are exposed.
5. The method according to any of claims 1-4, wherein the characteristic data of the target user comprises time information; determining at least one target combination corresponding to the target object, including:
and determining at least one target combination corresponding to the target object in the target time period of the time information.
6. The method of claim 5, wherein determining at least one target combination corresponding to the target object within a target time period in which the time information is located comprises:
and determining at least one target combination from resource combinations corresponding to the target object in the target time period according to the demand information provided by the target user.
7. The method according to claim 6, wherein determining at least one target combination from resource combinations corresponding to the target object in the target time period according to the demand information provided by the target user comprises:
when at least one first resource combination corresponding to the target object in the target time period exists, determining the target combination from the at least one first resource combination according to the requirement information; wherein the first resource combination comprises at least two resources of the target object;
when at least one first target combination corresponding to the target object in the target time period does not exist, determining the target combination from at least one second resource combination according to the demand information; the first resource combination is a preset fixed combination, and the times of acquisition by a user exceed a first preset threshold; the second resource combination is different from the preset fixed combination, the second resource combination comprises at least two resources of the target object, and the co-occurrence probability of the at least two resources acquired by the user at the same time exceeds a second preset threshold.
8. An object pushing apparatus, comprising:
the first acquisition module is configured to acquire characteristic data of a target user;
a first determination module configured to determine at least one target object according to the feature data of the target user;
a second determination module configured to determine at least one target combination corresponding to the target object; wherein the target combination comprises at least two resources provided by the same target object;
and the pushing module is configured to push the at least one target object and the at least one target combination to a terminal corresponding to the target user.
9. An electronic device comprising a memory and at least one processor; wherein,
the memory is to store one or more computer instructions, wherein the one or more computer instructions are to be executed by the at least one processor to implement the method of any one of claims 1-7.
10. A computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, implement the method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910989857.3A CN112685627A (en) | 2019-10-17 | 2019-10-17 | Object pushing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910989857.3A CN112685627A (en) | 2019-10-17 | 2019-10-17 | Object pushing method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112685627A true CN112685627A (en) | 2021-04-20 |
Family
ID=75444573
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910989857.3A Withdrawn CN112685627A (en) | 2019-10-17 | 2019-10-17 | Object pushing method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112685627A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909399A (en) * | 2017-11-13 | 2018-04-13 | 维沃移动通信有限公司 | A kind of available resources recommend method and apparatus |
CN107911449A (en) * | 2017-11-15 | 2018-04-13 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
CN110264301A (en) * | 2019-05-10 | 2019-09-20 | 拉扎斯网络科技(上海)有限公司 | Recommendation method and device, electronic equipment and nonvolatile storage medium |
CN110322323A (en) * | 2019-07-02 | 2019-10-11 | 拉扎斯网络科技(上海)有限公司 | Entity display method, entity display device, storage medium and electronic equipment |
-
2019
- 2019-10-17 CN CN201910989857.3A patent/CN112685627A/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909399A (en) * | 2017-11-13 | 2018-04-13 | 维沃移动通信有限公司 | A kind of available resources recommend method and apparatus |
CN107911449A (en) * | 2017-11-15 | 2018-04-13 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
CN110264301A (en) * | 2019-05-10 | 2019-09-20 | 拉扎斯网络科技(上海)有限公司 | Recommendation method and device, electronic equipment and nonvolatile storage medium |
CN110322323A (en) * | 2019-07-02 | 2019-10-11 | 拉扎斯网络科技(上海)有限公司 | Entity display method, entity display device, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6301958B2 (en) | Method and apparatus for configuring search terms, delivering advertisements, and retrieving product information | |
WO2020200199A1 (en) | Personalized recommendation method, terminal apparatus and system | |
US9087108B2 (en) | Determination of category information using multiple stages | |
WO2019056661A1 (en) | Search term pushing method and device, and terminal | |
US20140172821A1 (en) | Generating filters for refining search results | |
JP5581408B2 (en) | Information processing system, information processing apparatus, information processing method, and program | |
CN109300059B (en) | Dish recommending method and device | |
WO2015135110A1 (en) | Systems and methods for keyword suggestion | |
CN104395901A (en) | Method and system for facilitating users to obtain content | |
US20200226168A1 (en) | Methods and systems for optimizing display of user content | |
Liyanage et al. | Foody-Smart restaurant management and ordering system | |
US11048771B1 (en) | Method and system for providing organized content | |
US20200356781A1 (en) | Method and apparatus for performing categorised matching of videos, and selection engine | |
US20200195594A1 (en) | Method and system for dynamically generating a card | |
US20160299951A1 (en) | Processing a search query and retrieving targeted records from a networked database system | |
CN110750697B (en) | Merchant classification method, device, equipment and storage medium | |
US20130006760A1 (en) | Systems and methods for presenting comparative advertising | |
CN113077317A (en) | Item recommendation method, device and equipment based on user data and storage medium | |
CN111597447A (en) | Object pushing method and device, electronic equipment and storage medium | |
CN110428277B (en) | Touch method of recommended product, storage medium and program product | |
US10929905B2 (en) | Method, system and machine-readable medium for online task exchange | |
CN111352624A (en) | Interface display method, information processing method and device | |
US20190266648A1 (en) | Systems and methods for analyzing consumer products | |
KR20140010679A (en) | System and method for recommendation | |
US20200111130A1 (en) | Systems and methods for automatic processing of marketing documents |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210420 |