CN110784500A - Information pushing method and device - Google Patents

Abstract

The embodiment of the application provides an information pushing method and an information pushing device, wherein the information pushing method comprises the following steps: acquiring first characteristic information of each target in a first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set; generating first association relation information between the first user and the second user according to the first characteristic information and the second characteristic information; determining at least one target to be pushed from each target in a second target set based on the first association relation information and selection information of the second user for selecting each target in the second target set; and sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user. The embodiment of the application can improve the accuracy of information pushing.

Description

Information pushing method and device

Technical Field

The present application relates to the technical field of data processing, and in particular, to a method and an apparatus for pushing information.

Background

Currently, in many fields, information is pushed to users based on two dimensions of related information: historical selection of a target corresponding to the push information by the user, and a current distance between the target corresponding to the push information and the user.

For example, when pushing information related to a gas station to a driver of a vehicle, one gas station closest to the vehicle is determined from a plurality of gas stations based on the distance between the gas station and the vehicle, and the pushing information corresponding to the gas station is pushed to a user; or based on the relevant characteristics of the gas stations selected by the driver all the time, for example, the gas stations with few people and low fuel price among the gas stations selected by the driver all the time, the user can select the gas station with few people and low fuel price from a plurality of gas stations based on the selection of the driver, and push the push information corresponding to the gas station to the user.

The current information pushing method has the problem of poor accuracy.

Disclosure of Invention

In view of the above, an object of the present application is to provide an information pushing method and apparatus, which can improve accuracy in information pushing.

In a first aspect, an embodiment of the present application provides an information pushing method, including:

acquiring first characteristic information of each target in a first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

generating first association relation information between the first user and the second user according to the first characteristic information and the second characteristic information;

determining at least one target to be pushed from each target in a second target set based on the first association relation information and selection information of the second user for selecting each target in the second target set;

and sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

In an optional implementation manner, the generating, according to the first feature information and the second feature information, first association relationship information between the first user and the second user includes:

generating a first feature vector of the first user according to the first feature information corresponding to the first user; and

generating a second feature vector corresponding to each second user according to the second feature information corresponding to each second user;

determining a first similarity between the first user and each second user according to the first feature vector and the second feature vector;

and determining the first similarity as the first incidence relation information.

In an optional implementation, the first feature information includes: the number of times that the first user selects each target in the first target set; the second feature information includes: the number of times that the second user selects each target in the first target set;

each element in the first feature vector represents the number of times that the first user selects each target in the first target set;

each element in the second feature vector characterizes a number of times that the second user selects each target in the first set of targets.

In an optional embodiment, the first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises: characteristic values of the objects in the first set of objects selected by a second user under at least one attribute characteristic.

In an optional implementation manner, the determining, based on the first association relationship information and selection information of the second user for selecting each target in the second target set, at least one target to be pushed from each target in the second target set includes:

determining at least one selected user from the plurality of second users according to a first similarity between the first user and each second user;

and determining at least one target to be pushed from the second target set according to the selection information of each selected user for selecting each target in the second target set.

In an alternative embodiment, the selection information includes: the number of times of selection of each target in the second target set by a second user;

the determining, according to selection information of each selected user for selecting each target in the second target set, at least one target to be pushed from the second target set includes:

comparing the selection times of each selected user on each target in the second target set with a preset selection time threshold;

determining the targets with the selection times larger than the selection time threshold in the second target set as alternative targets;

determining the at least one target to be pushed from each alternative target;

or,

determining a preset number of alternative targets from the targets in the second target set according to the sequence that the selection times of each selected user to each target in the second target set are from large to small;

and determining the at least one target to be pushed from the alternative targets.

In an optional embodiment, the determining the at least one target to be pushed from the candidate targets includes:

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one preset attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

In an optional embodiment, the determining, based on the feature value of each of the selected objects under the at least one attribute feature and the feature value of each of the candidate objects under the at least one attribute feature, the at least one object to be pushed from the candidate objects includes:

determining a second similarity between each selected object and each candidate object based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each candidate object under the at least one attribute characteristic;

and determining the at least one target to be pushed from each candidate target according to the second similarity between each selected target and each candidate target.

In an optional implementation manner, the determining, according to the second similarity between each selected target and each candidate target, the at least one target to be pushed from each candidate target includes:

for each candidate object, performing:

determining the average similarity corresponding to the candidate target according to the second similarity between the candidate target and each selected target;

and determining at least one target to be pushed from the alternative targets according to the sequence of the average similarity corresponding to the alternative targets from large to small.

In an alternative embodiment, the attribute features include one or more of:

distance between user and target, brand, price, preference information, service score, product quality, product quantity.

In a second aspect, an embodiment of the present application provides an information pushing method, including:

acquiring first characteristic information of each target in a first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

generating second incidence relation information between every two targets in the first target set according to the first characteristic information and the second characteristic information;

determining at least one target to be pushed from each target in the second target set based on the second association relation information and association relations between each target in the second target set and each target in the first target set;

and sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

In an optional implementation manner, the generating, according to the first feature information and the second feature information, second association relationship information between each two targets in the first target set includes:

generating a target feature vector of each target in the first target set according to the first feature information of the target and the second feature information corresponding to each second user;

generating a third similarity of each two targets according to the target feature vectors of the two targets in the first target set;

and determining the third similarity between every two targets in the first target set as the second incidence relation information.

In an optional implementation, the first feature information includes: the first user evaluates each target selected from the first target set; the second feature information includes: and the evaluation information of each target selected in the first target set by each second user.

In an optional embodiment, the first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises the following information: the characteristic value of each object in the first object set selected by the second user under at least one attribute characteristic.

In an optional implementation manner, the determining, based on the second association relationship information and an association relationship between each object in the second object set and each object in the first object set, at least one object to be pushed from each object in the second object set includes:

dividing each target in the first target set into a plurality of groups by using a preset clustering algorithm according to a third similarity between every two targets in the first target set;

determining each target in a first target set selected by a first user as a selected target, and determining a group to which the selected target belongs as a selected group;

and determining at least one target to be pushed from each target in the second target set according to the incidence relation between each target in the second target set and the selected target in each selected group.

In an alternative embodiment, the association relationship between each object in the second object set and each object in the first object set includes: a fourth similarity between each target in the second set of targets and each target in the first set of targets;

determining at least one target to be pushed from each target in the second target set according to the association relationship between each target in the second target set and the selected target in each selected group, including:

determining a plurality of second targets from a second target set as candidate targets according to a fourth similarity between each target in the second target set and each selected target in the selected group;

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

In an optional embodiment, the determining, based on the feature value of each of the selected objects under the at least one attribute feature and the feature value of each of the candidate objects under the at least one attribute feature, the at least one object to be pushed from the candidate objects includes:

determining a fifth similarity between each selected object and each candidate object based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature;

and determining the at least one target to be pushed from each candidate target according to the fifth similarity between each selected target and each candidate target.

In a third aspect, an embodiment of the present application provides an information pushing apparatus, including:

the first acquisition module is used for acquiring first characteristic information of each target in the first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

a first generating module, configured to generate first association relationship information between the first user and the second user according to the first feature information and the second feature information;

a first determining module, configured to determine at least one target to be pushed from each target in a second target set based on the first association relationship information and selection information of the second user for selecting each target in the second target set;

and the first pushing module is used for sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

In an optional implementation manner, the first generating module is configured to generate first association relationship information between the first user and the second user according to the first feature information and the second feature information in the following manner:

generating a first feature vector of the first user according to the first feature information corresponding to the first user; and

generating a second feature vector corresponding to each second user according to the second feature information corresponding to each second user;

determining a first similarity between the first user and each second user according to the first feature vector and the second feature vector;

and determining the first similarity as the first incidence relation information.

In an optional implementation, the first feature information includes: the number of times that the first user selects each target in the first target set; the second feature information includes: the number of times that the second user selects each target in the first target set;

each element in the first feature vector represents the number of times that the first user selects each target in the first target set;

each element in the second feature vector characterizes a number of times that the second user selects each target in the first set of targets.

In an optional embodiment, the first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises: characteristic values of the objects in the first set of objects selected by a second user under at least one attribute characteristic.

In an optional implementation manner, the first determining module is configured to determine, based on the first association relationship information and the selection information of the second user for selecting each target in the second target set, at least one target to be pushed from each target in the second target set by using the following manner:

determining at least one selected user from the plurality of second users according to a first similarity between the first user and each second user;

and determining at least one target to be pushed from the second target set according to the selection information of each selected user for selecting each target in the second target set.

In an alternative embodiment, the selection information includes: the number of times of selection of each target in the second target set by a second user;

the first determining module is configured to determine at least one target to be pushed from the second target set according to selection information of each selected user for selecting each target in the second target set in the following manner:

comparing the selection times of each selected user on each target in the second target set with a preset selection time threshold;

determining the targets with the selection times larger than the selection time threshold in the second target set as alternative targets;

determining the at least one target to be pushed from each alternative target;

or,

determining a preset number of alternative targets from the targets in the second target set according to the sequence that the selection times of each selected user to each target in the second target set are from large to small;

and determining the at least one target to be pushed from the alternative targets.

In an optional embodiment, the first determining module is configured to determine the at least one target to be pushed from among the candidate targets in the following manner:

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one preset attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

In an optional embodiment, the first determining module is configured to determine the at least one object to be pushed from the candidate objects based on a feature value of each selected object under the at least one attribute feature and a feature value of each candidate object under the at least one attribute feature in the following manner:

determining a second similarity between each selected object and each candidate object based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each candidate object under the at least one attribute characteristic;

and determining the at least one target to be pushed from each candidate target according to the second similarity between each selected target and each candidate target.

In an optional implementation manner, the first determining module is configured to determine the at least one object to be pushed from the candidate objects according to the second similarity between each selected object and each candidate object by using the following manner:

for each candidate object, performing:

determining the average similarity corresponding to the candidate target according to the second similarity between the candidate target and each selected target;

and determining at least one target to be pushed from the alternative targets according to the sequence of the average similarity corresponding to the alternative targets from large to small.

In an alternative embodiment, the attribute features include one or more of:

distance between user and target, brand, price, preference information, service score, product quality, product quantity.

In a fourth aspect, an embodiment of the present application provides an information pushing apparatus, including:

the second acquisition module is used for acquiring first characteristic information of each target in the first target set selected by the first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

the second generation module is used for generating second incidence relation information between every two targets in the first target set according to the first characteristic information and the second characteristic information;

a second determining module, configured to determine at least one target to be pushed from each target in the second target set based on the second association relationship information and association relationships between each target in the second target set and each target in the first target set;

and the second pushing module is used for sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

In an optional implementation manner, the second generating module is configured to generate second association relationship information between each two targets in the first target set according to the first feature information and the second feature information in the following manner:

generating a target feature vector of each target in the first target set according to the first feature information of the target and the second feature information corresponding to each second user;

generating a third similarity of each two targets according to the target feature vectors of the two targets in the first target set;

and determining the third similarity between every two targets in the first target set as the second incidence relation information.

In an optional implementation, the first feature information includes: the first user evaluates each target selected from the first target set; the second feature information includes: and the evaluation information of each target selected in the first target set by each second user.

In an optional embodiment, the first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises the following information: the characteristic value of each object in the first object set selected by the second user under at least one attribute characteristic.

In an optional implementation manner, the second determining module is configured to determine, based on the second association relationship information and association relationships between the targets in the second target set and the targets in the first target set, at least one target to be pushed from the targets in the second target set by:

dividing each target in the first target set into a plurality of groups by using a preset clustering algorithm according to a third similarity between every two targets in the first target set;

determining each target in a first target set selected by a first user as a selected target, and determining a group to which the selected target belongs as a selected group;

and determining at least one target to be pushed from each target in the second target set according to the incidence relation between each target in the second target set and the selected target in each selected group.

In an alternative embodiment, the association relationship between each object in the second object set and each object in the first object set includes: a fourth similarity between each target in the second set of targets and each target in the first set of targets;

the second determining module is configured to determine at least one target to be pushed from each target in the second target set according to an association relationship between each target in the second target set and a selected target in each selected group in the following manner:

determining a plurality of second targets from a second target set as candidate targets according to a fourth similarity between each target in the second target set and each selected target in the selected group;

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

In an optional embodiment, the second determining module is configured to determine the at least one object to be pushed from the candidate objects based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature in the following manner:

determining a fifth similarity between each selected object and each candidate object based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature;

and determining the at least one target to be pushed from each candidate target according to the fifth similarity between each selected target and each candidate target.

In a fifth aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is operating, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any one of the possible implementations of the first aspect, or the second aspect, or any one of the possible implementations of the second aspect.

In a fourth aspect, this embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps in the first aspect, or any one of the possible embodiments of the first aspect, or to perform the steps in the second aspect, or any one of the possible embodiments of the second aspect.

According to the embodiment of the application, the first association relation information between the first user and the second user can be generated according to the first characteristic information of the first user for selecting each target in the first target set and the second characteristic information of the plurality of second users for selecting each target in the first target set, then at least one target to be pushed is determined from each target in the second target set according to the first association relation information, and the information to be pushed corresponding to the target to be pushed is pushed to the user terminal of the first user, so that the collaborative recommendation of the information is realized, and the higher accuracy is achieved.

In addition, according to first characteristic information of a first user for selecting each target in a first target set and second characteristic information of a plurality of second users for selecting each target in the first target set, second association relation information between every two targets in the first target set is generated; and then determining at least one target to be pushed from each target in the second target set according to the second association relationship information and the association relationship between each target in the second target set and each target in the first target set, and pushing the information to be pushed corresponding to the target to be pushed to the user terminal of the first user, so that the collaborative recommendation of the information is realized, and the higher accuracy is achieved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a schematic diagram illustrating an architecture of a service system provided in an embodiment of the present application;

fig. 2 is a flowchart illustrating a method for pushing information according to an embodiment of the present application;

fig. 3 is a flowchart illustrating a specific method for generating first association relationship information in a method for pushing information provided in an embodiment of the present application;

fig. 4 is a flowchart illustrating a specific example of generating first association relation information in a method for pushing information provided in an embodiment of the present application;

fig. 5 is a flowchart illustrating another specific example of generating first association relation information in a method for pushing information provided in an embodiment of the present application;

fig. 6 is a flowchart illustrating a specific method for determining at least one target to be pushed from each target in the second target set in the information pushing method according to an embodiment of the present application;

fig. 7 is a flowchart illustrating a specific method for determining at least one target to be pushed from among targets in a second target set in a method for pushing information provided in an embodiment of the present application;

fig. 8 is a flowchart illustrating a method for pushing information provided in the second embodiment of the present application;

fig. 9 is a flowchart illustrating a specific example of generating second association information in the information pushing method provided in the second embodiment of the present application;

fig. 10 is a flowchart illustrating a specific example of generating second association information in the information pushing method provided in the second embodiment of the present application;

fig. 11 is a flowchart illustrating another specific example of generating second association information in the information pushing method provided in the second embodiment of the present application;

fig. 12 is a flowchart illustrating a specific method for determining at least one target to be pushed from each target in the second target set in the method for pushing information provided in the second embodiment of the present application;

fig. 13 is a flowchart illustrating a specific method for determining at least one target to be pushed from each target in the second target set in the information pushing method provided in the second embodiment of the present application;

fig. 14 shows a schematic structural diagram of an information pushing apparatus provided in the third embodiment of the present application;

fig. 15 shows a schematic structural diagram of a computer device 1500 provided in the fourth embodiment of the present application;

fig. 16 shows a schematic structural diagram of an information pushing apparatus provided in the fifth embodiment of the present application;

fig. 17 shows a schematic structural diagram of a computer device 1700 according to a sixth embodiment of the present application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

In order to enable a person skilled in the art to use the present disclosure, the following embodiments are given in connection with a specific application scenario "gas station recommendation". It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is mainly described in the context of pushing push information corresponding to a gasoline station to a user terminal of a user to be pushed, it should be understood that this is only one exemplary embodiment.

It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.

In the related art, when generating push information, a target to be pushed is determined first, then push information corresponding to the target to be pushed is generated, and the push information is pushed to a user. There are generally two ways to determine the target to be pushed; firstly, a target to be pushed is determined for a user according to basic information of the user such as sex, age, home address and the like, for example, for a female of about 25 to 35 years old, the determined target to be pushed may be a mother-infant product, and for a user with a vehicle with the home address of a, the determined target to be pushed may be a gas station and the like within a preset distance from the place a. Secondly, determining user preference based on the historical behaviors of the user, and determining a target corresponding to the push information according to the user preference; for example, when a gas station is pushed to a user, the preference of the user for selecting the gas station in the history is the price and the brand of the gas station; then the gasoline stations to be pushed are determined for the user based on the price of the gasoline in the respective gasoline station and the brand of the gasoline station when the gasoline stations to be pushed are determined for the user. In the first mode, the pushed information may not be required by the user, and the problem of poor accuracy exists; in the second mode, targeted pushing can be performed only for one target, and the preference of the user to other targets except the same target cannot be excavated, so that the problem of poor pushing accuracy also exists.

Based on this, one aspect of the present application relates to an information push system. The information pushing system can generate first association relation information between a first user and a second user according to first characteristic information selected by the first user for each target in a first target set and second characteristic information selected by a plurality of second users for each target in the first target set, then determines at least one target to be pushed from each target in a second target set according to the first association relation information, and pushes the information to be pushed corresponding to the target to be pushed to a user terminal of the first user, so that collaborative recommendation of information is realized, and higher accuracy is achieved.

Another aspect of the present application also relates to another information pushing system. The information pushing system can generate second association relation information between every two targets in the first target set according to first characteristic information of each target in the first target set selected by a first user and second characteristic information of each target in the first target set selected by a plurality of second users; and then determining at least one target to be pushed from each target in the second target set according to the second association relationship information and the association relationship between each target in the second target set and each target in the first target set, and pushing the information to be pushed corresponding to the target to be pushed to the user terminal of the first user, so that the collaborative recommendation of the information is realized, and the higher accuracy is achieved.

Fig. 1 is a schematic architecture diagram of an information push system 100 according to an embodiment of the present disclosure. For example, the information push system 100 may be an information push service platform for pushing various items in a shopping website, pushing a physical store, pushing a tourist attraction, and the like. The information push system 100 may include one or more of aserver 110, anetwork 120, auser terminal 130, and adatabase 140.

In some embodiments, theserver 110 may include a processor. The processor may process information and/or data related to the user and the target to perform one or more of the functions described herein. For example, the processor may determine the target to be pushed for the user from a plurality of targets, or from other targets, based on the obtained information of the user's selection of the targets and the related information of the respective targets. In some embodiments, a processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set computer (Reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.

In some embodiments, the device type corresponding to theuser terminal 130 may be a mobile device, such as a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or may be a tablet computer, a laptop computer, or a built-in device in a motor vehicle, or the like.

In some embodiments, adatabase 140 may be connected to thenetwork 120 to communicate with one or more components (e.g., theserver 110, theuser terminal 130, etc.) in the information push system 100. One or more components in the information push system 100 may access data or instructions stored in thedatabase 140 via thenetwork 120. In some embodiments, thedatabase 140 may be directly connected to one or more components in the information push system 100, or thedatabase 140 may be part of theserver 110.

The information push method provided by the embodiment of the present application is described in detail below with reference to the content described in the information push system 100 shown in fig. 1.

Example one

Referring to fig. 2, a flowchart of an information push method provided in an embodiment of the present application is shown, where the method may be executed by a server in the information push system 100, and the method includes S201 to S204:

s201: acquiring first characteristic information of each target in a first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

s202: generating first association relation information between the first user and the second user according to the first characteristic information and the second characteristic information;

s203: determining at least one target to be pushed from each target in a second target set based on the first association relation information and selection information of the second user for selecting each target in the second target set;

s204: and sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

The following is a detailed description of S201 to S204 shown in fig. 2:

i: in S201, the plurality of targets included in the first target set may be the same kind of targets, such as a plurality of gas stations, a plurality of restaurants, a plurality of hotels, and the like. Different kinds of objects are possible, such as various kinds of clothes and shoes.

Illustratively, the first characteristic information of the first user selecting each object in the first object set includes the number of times the first user selects each object in the first object set. The second characteristic information of the second user for selecting each target in the first target set comprises the times of selecting each target in the first target set by the second user.

Illustratively, the first characteristic information includes: the first user selected characteristic value of each object in the first set of objects under at least one attribute characteristic.

The attribute features include, for example: one or more of the following:

distance between user and target, brand, price, preference information, service score, product quality, product quantity.

For example: when the target is a gas station, the attribute feature may include: distance from the gasoline station, price of the oil in the gasoline station, environment of the gasoline station, quality of the oil, type and quantity of the oil, brand of the oil, etc.; when the target is clothing, the attribute feature may include: the price of the clothes, the type of the clothes, the material of the clothes, the style of the clothes, the evaluation of the shop selling the clothes, the preference information, and the like.

The attribute features can reflect characteristics of the targets, and selection of the first user for each target in the first target set can actually represent selection tendency of the first user for the characteristics. Therefore, the association relationship between the first user and each second user can be established according to the attribute characteristics of each target in the first target set, and corresponding first association relationship information is generated.

The second characteristic information of the similar second user selecting each object in the first object set may also be a characteristic value of each object in the first object set selected by the second user under at least one attribute characteristic.

II: in the above S202, the first association relationship information between the first user and the second user is used to characterize whether the first user and the second user have the same or similar target selection trend.

Specifically, referring to fig. 3, an embodiment of the present application provides a specific method for generating first association relationship information, including:

s301: generating a first feature vector of the first user according to the first feature information corresponding to the first user; and

s302: generating a second feature vector corresponding to each second user according to the second feature information corresponding to each second user;

s303: determining a first similarity between the first user and each second user according to the first feature vector and the second feature vector;

s304: and determining the first similarity as the first incidence relation information.

Specifically, the method comprises the following steps:

(1) aiming at the first characteristic information, the times of selecting each target in the first target set by the first user are included, the second characteristic information comprises the times of selecting each target in the first target set by the second user, and each element in the first characteristic vector represents the times of selecting each target in the first target set by the first user.

Each element in the second feature vector characterizes the number of times that the second user selects each target in the first set of targets.

Specifically, referring to fig. 4, generating a specific example of the first association relationship information includes:

s401: and forming a first feature vector according to the times of selecting each target in the first target set by the first user.

S402: and forming second feature vectors respectively corresponding to the second users according to the times of selecting the targets in the first target set by the second users.

For example, if there are 10 first targets in the first target set, which are a 1-a 10, and the number of times the first user selects a 1-a 10 is: 0. 3, 12, 10, 5, 0, 1, 2, 1, the first feature vector is formed as follows: (0,3, 12, 10,5,0,0,1,2,1).

The times of selection of a second user for a 1-a 10 are respectively as follows: 1. 2, 9, 0, 3, 15, 1, the second feature vector constituting the second user is: (1,2,9,0,0,0,3, 15,1,1).

S403: and determining a first similarity between the first user and each second user according to the first feature vector and the second feature vector, and determining the first similarity as the first association relation information.

Here, the first similarity between the first user and each of the second users may be obtained by calculating a distance between the first selection behavior vector and the second selection behavior vector.

The distance between the first selection behavior vector and the second selection behavior vector may be: one or more of euclidean distance, manhattan distance, chebyshev distance, and the like.

(2) The first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises the following information: the characteristic value of each target in the first target set selected by the second user under at least one attribute characteristic:

referring to fig. 5, an embodiment of the present application further provides another specific example of generating first association relation information, where the example includes:

s501: and generating a first feature vector according to the feature value of each target in the first target set selected by the first user under at least one attribute feature.

S502: and generating a second feature vector of each second user according to the feature value of each target in the first target set selected by each second user under the at least one attribute feature.

For example, if the targets in the first set of targets are gas stations and there are 10 gas stations, which are a 1-a 10, and the attribute features of the gas stations include: the distance between the user and the gas station, the price of the oil product, the scale of the oil station, the service attitude of the oil station, the safety management level of the oil station, the quality of the oil product, the quantity of the oil product and the brand of the oil product.

The first user has selected a petrol station a1, a5, a7 among them;

the characteristic values of the gas station a1 under the characteristic features are respectively as follows: 1.3km, 9.93 yuan, big, good, normal, good, 15, "XX" brand;

the characteristic values of the gas station a5 under the characteristic features are respectively as follows: 1.7km, 10.2 yuan, medium, good, normal, good, 3 "XX" brand;

the characteristic values of the gas station a7 under the characteristic features are respectively as follows: 2.1km, 9.95 yuan, medium, good, normal, good, 3, "XX" brand.

For the numerical characteristics, corresponding numerical representations are directly used, for example, the distance between a user and a gas station, the price of oil products, and the quantity of oil products are all represented by corresponding numerical values, for the category characteristics, for example, the scale of the oil station, the service attitude of the oil station, the safety management level of the oil station, the quality of oil products, and the brand of oil products, a one-hot (one-hot) encoding mode can be used, that is, each attribute characteristic corresponds to a vector consisting of 0 and 1, when the attribute characteristic takes different values, the position corresponding to the vector takes 1, and all other parts take 0.

For example, if the attribute characteristic is "oil brand", and if the oil brand has 3 kinds, respectively, "XX", "YY", "ZZ", then "XX" can be expressed as: (1, 0, 0); "YY" represents (0, 1, 0) and "ZZ" represents (0, 0, 1).

Thus, the characteristic values of the targets in the first target set under at least one attribute feature can be converted into a representation vector of numerical representation.

A first feature vector of the first user is then constructed from the representation vectors of the individual targets in the first set of targets selected by the first user.

The first feature vector may be obtained by performing weighted summation on the representation vectors of the targets in the first target set selected by the first user, and the more times the targets in the first target set are selected by the first user, the greater the weight corresponding to the representation vector of the target is.

S503: and determining a first similarity between the first user and each second user according to the first feature vector and the second feature vector, and determining the first similarity as the first association relation information.

III: in S203, the objects in the second object set and the first object set may be the same, partially the same, or completely different.

For example, when the first user and the second user both belong to users in the same area, the first user and the second user have the same selection preference for gas stations in the same area; therefore, the second user can select more gas stations, and the gas stations which are not selected by the first user are pushed to the first user, so that accurate information pushing of the first user is achieved.

For another example, the first user and the second user belong to different areas, and the first user and the second user have the same selection preference for gas stations in different areas, so that when the first user is located within the area range to which the second user belongs, the second user can select more gas stations and push the gas stations to the first user, so as to realize accurate information push for the first user.

Referring to fig. 6, an embodiment of the present application further provides a specific method for determining at least one target to be pushed from among targets in the second target set, including:

s601: and determining at least one selected user from the plurality of second users according to a first similarity between the first user and each second user.

Here, the first similarity between the first user and each second user may be compared with a preset similarity threshold; and determining the second user with the first similarity larger than a preset similarity threshold as the selected user.

Or, a preset number of selected users can be selected from the second users according to the sequence of the first similarity between the first user and each second user from large to small.

S602: and determining at least one target to be pushed from the second target set according to the selection information of each selected user for selecting each target in the second target set.

Here, the selection information includes: the number of selections of each target in the second set of targets by the second user.

The selection information corresponding to the selected user is the number of times that each selected user selects each target in the second target set.

Here, there may be one or a plurality of selected users. And the selection times of each selected user for each target in the second target set represent the preference degree of each selected user for each target in the second target set, and the greater the selection times, the higher the corresponding preference degree. The selected users are users which are screened out from the second users and have the same or similar preference as the first users, so that the times of selecting the targets in the second target set by the selected users determine the second targets which are preferred by the selected users, and the second targets which are preferred by the selected users are used as targets to be pushed.

Specifically, at least one target to be pushed may be determined from the second target set in any one of the following two ways:

the first method comprises the following steps: comparing the selection times of each selected user on each target in the second target set with a preset selection time threshold; determining the targets with the selection times larger than the selection time threshold in the second target set as alternative targets; and determining the at least one target to be pushed from the alternative targets.

Here, in order to determine the targets preferred by the selected user from the second target set, for each selected user, the targets of which the number of times of selection of each target in the second target set by the selected user is greater than a preset number threshold may be used as candidate targets, and at least one target to be pushed is determined from the candidate targets.

And the second method comprises the following steps: determining a preset number of targets from the second target set according to the sequence that the selection times of all selected users on all targets in the second target set are from large to small, and determining the determined preset number of targets as alternative targets; and determining the at least one target to be pushed from the alternative targets.

After the alternative targets are determined, all the alternative targets can be used as targets to be pushed, the pushing information corresponding to each target to be pushed is pushed to the first user, the alternative targets can be screened again in a certain mode, and the screened alternative targets are used as the targets to be pushed.

Specifically, referring to fig. 7, an embodiment of the present application further provides a specific method for determining at least one target to be pushed from among various candidate targets, including:

s701: determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one preset attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic.

Here, the determination method of the feature value of each selected object under the preset at least one attribute feature is similar to the manner of obtaining the feature value of each object under the at least one attribute feature in the first object set selected by the first user in S502, and is not described herein again.

The characteristic value of each candidate object under the at least one attribute feature is also similar to the manner of obtaining the characteristic value of each object in the first object set selected by the first user under the at least one attribute feature in the above S502, and is not described herein again.

S702: and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

Here, the second similarity between each selected object and each candidate object may be determined based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature.

The determination method of the second similarity is similar to the specific obtaining method of the first similarity in the embodiment corresponding to fig. 5, and is not repeated here.

S703: and determining the at least one target to be pushed from each candidate target according to the second similarity between each selected target and each candidate target.

Here, the average similarity corresponding to the candidate object may be determined according to the second similarity between the candidate object and each selected object; and determining at least one target to be pushed from the alternative targets according to the sequence of the average similarity corresponding to the alternative targets from large to small.

According to the method and the device for recommending the information, the first association relation information between the first user and the second user is generated according to the first characteristic information of the first user for selecting each target in the first target set and the second characteristic information of the second user for selecting each target in the first target set, then at least one target to be pushed is determined from each target in the second target set according to the first association relation information and the second characteristic information of the second user for selecting each target in the second target set, the information to be pushed corresponding to the target to be pushed is pushed to the user terminal of the first user, and therefore collaborative recommendation of the information is achieved, and higher accuracy is achieved.

Example two

Based on the same inventive concept, another information pushing method is further provided in the embodiment of the present application, and as shown in fig. 8, the information pushing method provided in the second embodiment of the present application includes S801 to S804:

s801: acquiring first characteristic information of each target in a first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

s802: generating second incidence relation information between every two targets in the first target set according to the first characteristic information and the second characteristic information;

s803: determining at least one target to be pushed from each target in the second target set based on the second incidence relation information and incidence relations between each target in the second target set and each target in the first target set;

s804: and sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

The following is a detailed description of S801 to S804 shown in fig. 8:

i: in S801 described above, similarly, the plurality of targets included in the first target set may be a plurality of targets of the same kind, such as a plurality of gas stations, a plurality of restaurants, a plurality of hotels, and the like. Multiple targets of different kinds, such as various clothes and shoes, etc., are also possible.

Illustratively, the first feature information of the first user selecting each target in the first target set includes evaluation information of the first user on each target selected in the first target set; the second feature information includes evaluation information of each first target selected in the first target set by each second user.

Here, the evaluation information may be an evaluation of product quality, an evaluation of environment, an evaluation of service, an evaluation of after-sales, and the like.

Illustratively, the first characteristic information further includes: the first user selected characteristic value of each object in the first set of objects under at least one attribute characteristic.

The attribute features include, for example: one or more of the following:

brand, price, offer information, service score, product quality, product quantity.

For example: when the target is a gas station, the attribute feature may include: price of oil in the station, environment of the station, quality of oil, type and quantity of oil, brand of oil, etc.; when the target is clothing, the attribute feature may include: the price of the clothes, the type of the clothes, the material of the clothes, the style of the clothes, the evaluation of the shop selling the clothes, the preference information, and the like.

The attribute characteristics can reflect the characteristics of each object in the first object set, so that the association relationship between every two objects in the first object set can be established according to the attribute characteristics of each object in the first object set, and corresponding second association relationship information can be generated.

The similar second feature information of the second user for selecting each target in the first target set in the second target set includes: the characteristic value of each object in the first object set selected by the second user under at least one attribute characteristic.

II: in the above S802, the second association relationship information between every two first targets is generally the similarity between every two first targets. The user's selection of different targets will usually have some common characteristics, and through these characteristics, the association relationship between every two first targets, that is, the second association relationship information, can be characterized.

Specifically, referring to fig. 9, an embodiment of the present application provides a specific method for generating second association relationship information between each two targets in a first target set according to first feature information and second feature information, including:

s901: and aiming at each target in the first target set, generating a target feature vector of the target according to the first feature information of the target and the second feature information corresponding to each second user.

S902: and generating a third similarity of the two targets according to the target feature vectors of every two targets in the first target set.

S903: and determining the third similarity between every two targets in the first target set as the second incidence relation information.

Here:

(1) for a case where the first feature information includes evaluation information of each target selected in the first target set by the first user, and the second feature information includes evaluation information of each target selected in the first target set by each second user, referring to fig. 10, second association relationship information may be generated in a manner in the following example:

s1001: and aiming at each first target, generating a target feature vector of the target according to the evaluation information of the first user on each target in the first target set and the evaluation information of each target selected by each second user on the first target set. Each element in the target feature vector represents a specific evaluation result of one evaluation item.

For example, if the targets in the first set of targets are gas stations, and there are 10 gas stations, which are a 1-a 10, and there are 4 evaluation items for each gas station, which are: evaluation of product quality, evaluation of environment, evaluation of service, evaluation of after sales.

The first user a has selected a1 therein.

The scores of the A on the evaluation items of the a1 are respectively as follows: 5 min, 3 min and 2 min;

and the second user score B, the second user C and the third user D respectively evaluate the a1, and the obtained scores of the evaluation items of a1 are respectively as follows:

the scores of the evaluation items in the a1 by the B are respectively as follows: 3 min, 4 min and 1 min;

the scores of the evaluation items in the a1 by the C are respectively as follows: 4 min, 2 min and 4 min;

d, the scores of the evaluation items in the a1 are respectively as follows: 4 min, 2 min, 1 min and 1 min.

The target feature vector of a1 can be obtained by scoring the respective evaluation items of a1 by A, B, C and D.

For example, A, B, C and D are respectively used for averaging the scores of a1 for each evaluation item to obtain the feature value of a1 under the evaluation item, and the target feature vector of a1 is (4, 2.75, 2.5, 2) according to the feature value of a1 under each evaluation item.

It should be noted here that, if the first user can evaluate some first targets in the first target set, the first user can also evaluate all the first targets; similarly, the second user may rate some or all of the first objectives in the first set of objectives.

S1002: and generating a third similarity of the two targets according to the target feature vectors of every two targets in the first target set.

S1003: and determining the third similarity between every two targets in the first target set as the second incidence relation information.

(2) The first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises the following information: in the case of the feature values of the respective targets in the first target set selected by the second user under the at least one attribute feature, referring to fig. 11, the second association relationship information may be generated in the following manner in the following example:

s1101: and aiming at each target in the first target set, generating a target feature vector of the target according to the feature value under at least one attribute feature when the first user and/or the second user selects the target.

S1102: and generating a third similarity of the two targets according to the target feature vectors of every two targets in the first target set.

S1103: and determining the third similarity between every two targets in the first target set as the second incidence relation information.

For example: if the targets in the first target set are filling stations and the number of the filling stations is 10, the number of the filling stations is a 1-a 10, and the attribute characteristics of the filling stations comprise: the distance between a user and a gas station, the price of oil products, the scale of the oil station, the service attitude of the oil station, the safety management level of the oil station, the quality of the oil products, the quantity of the oil products, the brand of the oil products and whether preferential information exists.

The first user a selects the gas station a1, and the corresponding feature values under the attribute features are: 1.3km, 9.93 yuan, big, good, ordinary, good, 15, "XX" brand, good;

the second user B has selected a gasoline station a1 therein; and the corresponding characteristic values under each attribute characteristic are respectively: 1.5km, 9.93 yuan, medium, good, normal, good, 14, "XX" brand, good;

the third user C has selected gas station a1 therein; and the corresponding characteristic values under each attribute characteristic are respectively: 2.1km, 9.93 yuan, medium, good, general, good, 16, "XX" brand, good.

For the numerical features, corresponding numerical representations are directly used, for example, the distance between a user and a gas station, the price of oil, and the quantity of oil are all represented by corresponding numerical representations, and for the category features, for example, the above-mentioned oil station scale, oil station service attitude, oil station safety management level, oil quality, and oil brand, a one-hot (one-hot) encoding mode can be used, that is, each attribute feature corresponds to a vector composed of 0 and 1, when the attribute feature takes different values, the position corresponding to the vector takes 1, and all other parts take 0, so that the feature value of each object in the first object set under at least one attribute feature is converted into a representation vector represented by a numerical representation.

And then aiming at each target in the first target set, generating a target feature vector of the target according to the corresponding representation vector when the first user and/or the second user selects the target.

The target feature vector may be obtained by performing weighted summation on corresponding expression vectors when the first user and/or the second user selects the target.

III: in the above S803, referring to fig. 12, at least one target to be pushed may be determined from the targets in the second target set in the following manner:

s1201: and dividing each target in the first target set into a plurality of groups by using a preset clustering algorithm according to the third similarity between every two targets in the first target set.

Here, the clustering algorithm may employ at least one of a partition-based clustering method, a hierarchy-based clustering method, a density-based clustering method, a network-based clustering method, a model-based clustering method, and a model-based clustering method.

S1202: and determining each target in the first target set selected by the first user as a selected target, and determining a group to which the selected target belongs as a selected group.

Here, there may be one or more selected groups. The targets, belonging to the first target set, selected by the first user may be all selected packets.

S1203: and determining at least one target to be pushed from each target in the second target set according to the incidence relation between each target in the second target set and the selected target in each selected group.

Specifically, the association relationship between each target in the second target set and each target in the first target set includes: a fourth similarity between each object in the second set of objects and each object in the first set of objects.

Here, the fourth similarity between the second target and the first target is similar to the obtaining manner of the third similarity between every two targets in the first target set, and is not repeated herein.

Referring to fig. 13, when determining at least one target to be pushed from each target in the second target set according to the association relationship between each target in the second target set and the selected target in each selected group, the following method may be adopted in the embodiment of the present application:

s1301: and determining a plurality of targets from the second target set as candidate targets according to the fourth similarity between each target in the second target set and each selected target in the selected group.

Here, for each object in the second object set, the number of the selected objects whose fourth similarity is greater than a certain threshold may be determined according to the fourth similarity between the object and each selected object in the selected group, and if the number of the selected objects whose fourth similarity is greater than the certain threshold reaches a preset number threshold, the object is determined as the candidate object.

S1302: determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under a preset attribute characteristic; and acquiring the characteristic value of each candidate target under the attribute characteristic.

Here, the attribute features may be the same as those in the first embodiment, and the obtaining manner is also similar, which is not described herein again.

S1303: and determining the at least one target to be pushed from the alternative targets based on the characteristic value of each selected target under the attribute characteristic and the characteristic value of each alternative target under the attribute characteristic.

Determining a fifth similarity between each selected object and each candidate object based on the feature value of each selected object under the attribute feature and the feature value of each candidate object under the attribute feature; and determining the at least one target to be pushed from each candidate target according to the fifth similarity between each selected target and each candidate target.

Specifically, the fifth similarity is obtained in a manner similar to that of the second similarity in the first embodiment. A specific manner of determining the at least one object to be pushed from each candidate object according to the fifth similarity between each selected object and each candidate object is similar to the manner of determining the at least one object to be pushed from each candidate object according to the second similarity between each selected object and each candidate object in the first embodiment, and is not described herein again.

According to first characteristic information of a first user for selecting each target in a first target set and second characteristic information of a plurality of second users for selecting each target in the first target set, second association relation information between every two targets in the first target set is generated; and then determining at least one target to be pushed from each target in the second target set according to the second association relationship information and the association relationship between each target in the second target set and each target in the first target set, and pushing the information to be pushed corresponding to the target to be pushed to the user terminal of the first user, so that the collaborative recommendation of the information is realized, and the higher accuracy is achieved.

Based on the same inventive concept, an information pushing device corresponding to the information pushing method is further provided in the embodiment of the present application, and as the principle of solving the problem of the device in the embodiment of the present application is similar to the information pushing method in the embodiment of the present application, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.

EXAMPLE III

Referring to fig. 14, a schematic diagram of an information pushing apparatus provided in a third embodiment of the present application is shown, where the apparatus includes: a first obtaining module 141, a first generating module 142, a first determining module 143, and a first pushing module 144; wherein:

a first obtaining module 141, configured to obtain first feature information that a first user selects each target in a first target set; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

a first generating module 142, configured to generate first association relationship information between the first user and the second user according to the first feature information and the second feature information;

a first determining module 143, configured to determine at least one target to be pushed from each target in the second target set based on the first association relationship information and selection information of the second user for selecting each target in the second target set;

the first pushing module 144 is configured to send the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

In a possible implementation manner, the first generating module 142 is configured to generate the first association relationship information between the first user and the second user according to the first feature information and the second feature information in the following manner:

generating a first feature vector of the first user according to the first feature information corresponding to the first user; and

generating a second feature vector corresponding to each second user according to the second feature information corresponding to each second user;

determining a first similarity between the first user and each second user according to the first feature vector and the second feature vector;

and determining the first similarity as the first incidence relation information.

In a possible implementation, the first feature information includes: the number of times that the first user selects each target in the first target set; the second feature information includes: the number of times that the second user selects each target in the first target set;

each element in the first feature vector represents the number of times that the first user selects each target in the first target set;

each element in the second feature vector characterizes a number of times that the second user selects each target in the first set of targets.

In one possible implementation, the first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises: characteristic values of the objects in the first set of objects selected by a second user under at least one attribute characteristic.

In a possible implementation manner, the first determining module 143 is configured to determine, based on the first association relationship information and the selection information of the second user for selecting each target in the second target set, at least one target to be pushed from each target in the second target set by:

determining at least one selected user from the plurality of second users according to a first similarity between the first user and each second user;

and determining at least one target to be pushed from the second target set according to the selection information of each selected user for selecting each target in the second target set.

In a possible embodiment, the selection information includes: the number of times of selection of each target in the second target set by a second user;

the first determining module 143 is configured to determine, according to the selection information that each selected user selects each target in the second target set, at least one target to be pushed from the second target set in the following manner:

comparing the selection times of each selected user on each target in the second target set with a preset selection time threshold;

determining the targets with the selection times larger than the selection time threshold in the second target set as alternative targets;

determining the at least one target to be pushed from each alternative target;

or,

determining a preset number of alternative targets from the targets in the second target set according to the sequence that the selection times of each selected user to each target in the second target set are from large to small;

and determining the at least one target to be pushed from the alternative targets.

In a possible embodiment, the first determining module 143 is configured to determine the at least one target to be pushed from the candidate targets in the following manner:

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one preset attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

In a possible embodiment, the first determining module 143 is configured to determine the at least one object to be pushed from the candidate objects based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature in the following manner:

determining a second similarity between each selected object and each candidate object based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each candidate object under the at least one attribute characteristic;

and determining the at least one target to be pushed from each candidate target according to the second similarity between each selected target and each candidate target.

In a possible implementation manner, the first determining module 143 is configured to determine the at least one object to be pushed from the candidate objects according to the second similarity between the selected object and the candidate objects by:

for each candidate object, performing:

determining the average similarity corresponding to the candidate target according to the second similarity between the candidate target and each selected target;

and determining at least one target to be pushed from the alternative targets according to the sequence of the average similarity corresponding to the alternative targets from large to small.

In one possible embodiment, the attribute features include one or more of the following:

distance between user and target, brand, price, preference information, service score, product quality, product quantity.

The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.

Example four

An embodiment of the present application further provides a computer device 1500, as shown in fig. 15, which is a schematic structural diagram of the computer device 1500 provided in the embodiment of the present application, and includes: a processor 151, a memory 152, and a bus 153. The memory 152 stores machine-readable instructions executable by the processor 151 (for example, execution instructions corresponding to the first obtaining module 141, the first generating module 142, the first determining module 143, and the first pushing module 144 in the apparatus in fig. 14, and the like), when the computer device 1500 is executed, the processor 151 and the memory 152 communicate through the bus 153, and when the processor 151 executes the following processes:

acquiring first characteristic information of each target in a first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

generating first association relation information between the first user and the second user according to the first characteristic information and the second characteristic information;

determining at least one target to be pushed from each target in a second target set based on the first association relation information and selection information of the second user for selecting each target in the second target set;

and sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

In a possible implementation manner, the generating, by the processor 151, first association relationship information between the first user and the second user according to the first feature information and the second feature information includes:

generating a first feature vector of the first user according to the first feature information corresponding to the first user; and

generating a second feature vector corresponding to each second user according to the second feature information corresponding to each second user;

determining a first similarity between the first user and each second user according to the first feature vector and the second feature vector;

and determining the first similarity as the first incidence relation information.

In a possible implementation manner, the first feature information in the instructions executed by the processor 151 includes: the number of times that the first user selects each target in the first target set; the second feature information includes: the number of times that the second user selects each target in the first target set;

each element in the first feature vector represents the number of times that the first user selects each target in the first target set;

each element in the second feature vector characterizes a number of times that the second user selects each target in the first set of targets.

In a possible implementation manner, in the instructions executed by the processor 151, the first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises: characteristic values of the objects in the first set of objects selected by a second user under at least one attribute characteristic.

In a possible implementation manner, in the instructions executed by the processor 151, the determining, based on the first association relationship information and the selection information of the second user for selecting each object in the second object set, at least one object to be pushed from each object in the second object set includes:

determining at least one selected user from the plurality of second users according to a first similarity between the first user and each second user;

and determining at least one target to be pushed from the second target set according to the selection information of each selected user for selecting each target in the second target set.

In a possible implementation manner, in the instructions executed by the processor 151, the selection information includes: the number of times of selection of each target in the second target set by a second user;

the determining, according to selection information of each selected user for selecting each target in the second target set, at least one target to be pushed from the second target set includes:

comparing the selection times of each selected user on each target in the second target set with a preset selection time threshold;

determining the targets with the selection times larger than the selection time threshold in the second target set as alternative targets;

determining the at least one target to be pushed from each alternative target;

or,

determining a preset number of alternative targets from the targets in the second target set according to the sequence that the selection times of each selected user to each target in the second target set are from large to small;

and determining the at least one target to be pushed from the alternative targets.

In a possible implementation manner, in the instructions executed by the processor 151, the determining the at least one target to be pushed from among the candidate targets includes:

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one preset attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

In a possible embodiment, the determining, by the processor 151, the at least one object to be pushed from the candidate objects based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature includes:

determining a second similarity between each selected object and each candidate object based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each candidate object under the at least one attribute characteristic;

and determining the at least one target to be pushed from each candidate target according to the second similarity between each selected target and each candidate target.

In a possible implementation manner, in the instructions executed by the processor 151, the determining, according to the second similarity between each selected object and each candidate object, the at least one object to be pushed from each candidate object includes:

for each candidate object, performing:

determining the average similarity corresponding to the candidate target according to the second similarity between the candidate target and each selected target;

and determining at least one target to be pushed from the alternative targets according to the sequence of the average similarity corresponding to the alternative targets from large to small.

In one possible implementation, in the instructions executed by processor 151, the attribute features include one or more of the following:

distance between user and target, brand, price, preference information, service score, product quality, product quantity.

An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor 151, the steps of the information pushing method are performed.

Specifically, the storage medium can be a general storage medium, such as a removable disk, a hard disk, and the like, and when a computer program on the storage medium is executed, the information push method can be executed, so that the problem of poor push accuracy in the existing information push method is solved, and the effect of improving the information push accuracy is achieved.

EXAMPLE five

Referring to fig. 16, a schematic diagram of an information pushing apparatus provided in a fifth embodiment of the present application is shown, where the apparatus includes: a second obtaining module 161, a second generating module 162, a second determining module 163, and a second pushing module 164; wherein:

a second obtaining module 161, configured to obtain first feature information that the first user selects each target in the first target set; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

a second generating module 162, configured to generate second association relationship information between every two targets in the first target set according to the first feature information and the second feature information;

a second determining module 163, configured to determine at least one object to be pushed from each object in the second object set based on the second association relationship information and the association relationship between each object in the second object set and each object in the first object set;

a second pushing module 164, configured to send the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

In a possible implementation manner, the second generating module 162 is configured to generate, according to the first feature information and the second feature information, second association relationship information between each two objects in the first object set in the following manner:

generating a target feature vector of each target in the first target set according to the first feature information of the target and the second feature information corresponding to each second user;

generating a third similarity of each two targets according to the target feature vectors of the two targets in the first target set;

and determining the third similarity between every two targets in the first target set as the second incidence relation information.

In one possible implementation, the first feature information includes: the first user evaluates each target selected from the first target set; the second feature information includes: and the evaluation information of each target selected in the first target set by each second user.

In one possible implementation, the first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises the following information: the characteristic value of each object in the first object set selected by the second user under at least one attribute characteristic.

In a possible implementation manner, the second determining module 163 is configured to determine at least one object to be pushed from each object in the second object set based on the second association relationship information and the association relationship between each object in the second object set and each object in the first object set, in the following manner:

dividing each target in the first target set into a plurality of groups by using a preset clustering algorithm according to a third similarity between every two targets in the first target set;

determining each target in a first target set selected by a first user as a selected target, and determining a group to which the selected target belongs as a selected group;

and determining at least one target to be pushed from each target in the second target set according to the incidence relation between each target in the second target set and the selected target in each selected group.

In a possible embodiment, the association relationship between each object in the second object set and each object in the first object set includes: a fourth similarity between each target in the second set of targets and each target in the first set of targets;

the second determining module 163 is configured to determine at least one object to be pushed from each object in the second object set according to the association relationship between each object in the second object set and the selected object in each selected group, in the following manner:

determining a plurality of second targets from a second target set as candidate targets according to a fourth similarity between each target in the second target set and each selected target in the selected group;

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

In a possible embodiment, the second determining module 163 is configured to determine the at least one object to be pushed from the candidate objects based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature in the following manner:

determining a fifth similarity between each selected object and each candidate object based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature;

and determining the at least one target to be pushed from each candidate target according to the fifth similarity between each selected target and each candidate target.

EXAMPLE six

An embodiment of the present application further provides a computer device 1700, as shown in fig. 17, which is a schematic structural diagram of the computer device 170 provided in the embodiment of the present application, and includes: aprocessor 171, amemory 172, and a bus 173. Thememory 172 stores machine-readable instructions executable by the processor 171 (for example, execution instructions corresponding to the second obtaining module 161, the second generating module 162, the second determining module 163, and the second pushing module 164 in the apparatus in fig. 16, and the like), when the computer device 1700 runs, theprocessor 171 communicates with thememory 172 through the bus 173, and the machine-readable instructions, when executed by theprocessor 171, perform the following processes:

acquiring first characteristic information of each target in a first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

generating second incidence relation information between every two targets in the first target set according to the first characteristic information and the second characteristic information;

determining at least one target to be pushed from each target in the second target set based on the second association relation information and association relations between each target in the second target set and each target in the first target set;

and sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

In a possible implementation manner, the generating, by theprocessor 171, second association relationship information between each two targets in the first target set according to the first feature information and the second feature information includes:

generating a target feature vector of each target in the first target set according to the first feature information of the target and the second feature information corresponding to each second user;

generating a third similarity of each two targets according to the target feature vectors of the two targets in the first target set;

and determining the third similarity between every two targets in the first target set as the second incidence relation information.

In a possible implementation manner, the first feature information in the instructions executed by theprocessor 171 includes: the first user evaluates each target selected from the first target set; the second feature information includes: and the evaluation information of each target selected in the first target set by each second user.

In a possible implementation manner, in the instructions executed by theprocessor 171, the first feature information includes: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises the following information: the characteristic value of each object in the first object set selected by the second user under at least one attribute characteristic.

In a possible implementation manner, the determining, by theprocessor 171, at least one target to be pushed from each target in the second target set based on the second association relationship information and the association relationship between each target in the second target set and each target in the first target set includes:

dividing each target in the first target set into a plurality of groups by using a preset clustering algorithm according to a third similarity between every two targets in the first target set;

determining each target in a first target set selected by a first user as a selected target, and determining a group to which the selected target belongs as a selected group;

and determining at least one target to be pushed from each target in the second target set according to the incidence relation between each target in the second target set and the selected target in each selected group.

In a possible implementation, theprocessor 171 executes instructions that include the association relationship between each object in the second set of objects and each object in the first set of objects: a fourth similarity between each target in the second set of targets and each target in the first set of targets;

determining at least one target to be pushed from each target in the second target set according to the association relationship between each target in the second target set and the selected target in each selected group, including:

determining a plurality of second targets from a second target set as candidate targets according to a fourth similarity between each target in the second target set and each selected target in the selected group;

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

In a possible embodiment, theprocessor 171 executes instructions to determine the at least one object to be pushed from the candidate objects based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature, and the instructions include:

determining a fifth similarity between each selected object and each candidate object based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature;

and determining the at least one target to be pushed from each candidate target according to the fifth similarity between each selected target and each candidate target.

The present embodiment also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by theprocessor 171, the computer program performs the steps of the information pushing method.

Specifically, the storage medium can be a general storage medium, such as a removable disk, a hard disk, and the like, and when a computer program on the storage medium is executed, the information push method can be executed, so that the problem of poor push accuracy in the existing information push method is solved, and the effect of improving the information push accuracy is achieved.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (36)

1. A method of information push, comprising:

acquiring first characteristic information of each target in a first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

generating first association relation information between the first user and the second user according to the first characteristic information and the second characteristic information;

determining at least one target to be pushed from each target in a second target set based on the first association relation information and selection information of the second user for selecting each target in the second target set;

and sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

2. The method according to claim 1, wherein the generating first association relationship information between the first user and the second user according to the first feature information and the second feature information comprises:

generating a first feature vector of the first user according to the first feature information corresponding to the first user; and

generating a second feature vector corresponding to each second user according to the second feature information corresponding to each second user;

determining a first similarity between the first user and each second user according to the first feature vector and the second feature vector;

and determining the first similarity as the first incidence relation information.

3. The method of claim 2, wherein the first feature information comprises: the number of times that the first user selects each target in the first target set; the second feature information includes: the number of times that the second user selects each target in the first target set;

each element in the first feature vector represents the number of times that the first user selects each target in the first target set;

each element in the second feature vector characterizes a number of times that the second user selects each target in the first set of targets.

4. The method of claim 2, wherein the first feature information comprises: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises: characteristic values of the objects in the first set of objects selected by a second user under at least one attribute characteristic.

5. The method according to claim 2, wherein the determining at least one target to be pushed from each target in the second target set based on the first association relationship information and selection information of the second user for selecting each target in the second target set comprises:

determining at least one selected user from the plurality of second users according to a first similarity between the first user and each second user;

and determining at least one target to be pushed from the second target set according to the selection information of each selected user for selecting each target in the second target set.

6. The method of claim 5, wherein the selection information comprises: the number of times of selection of each target in the second target set by a second user;

the determining, according to selection information of each selected user for selecting each target in the second target set, at least one target to be pushed from the second target set includes:

comparing the selection times of each selected user on each target in the second target set with a preset selection time threshold;

determining the targets with the selection times larger than the selection time threshold in the second target set as alternative targets;

determining the at least one target to be pushed from each alternative target;

or,

determining a preset number of alternative targets from the targets in the second target set according to the sequence that the selection times of each selected user to each target in the second target set are from large to small;

and determining the at least one target to be pushed from the alternative targets.

7. The method according to claim 6, wherein the determining the at least one target to be pushed from among the candidate targets comprises:

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one preset attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

8. The method according to claim 7, wherein the determining the at least one object to be pushed from the candidate objects based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature comprises:

determining a second similarity between each selected object and each candidate object based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each candidate object under the at least one attribute characteristic;

and determining the at least one target to be pushed from each candidate target according to the second similarity between each selected target and each candidate target.

9. The method according to claim 8, wherein the determining the at least one object to be pushed from each candidate object according to the second similarity between each selected object and each candidate object comprises:

for each candidate object, performing:

determining the average similarity corresponding to the candidate target according to the second similarity between the candidate target and each selected target;

and determining at least one target to be pushed from the alternative targets according to the sequence of the average similarity corresponding to the alternative targets from large to small.

10. The method of claim 7, wherein the attribute features include one or more of:

distance between user and target, brand, price, preference information, service score, product quality, product quantity.

11. A method of information push, comprising:

acquiring first characteristic information of each target in a first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

generating second incidence relation information between every two targets in the first target set according to the first characteristic information and the second characteristic information;

determining at least one target to be pushed from each target in the second target set based on the second association relation information and association relations between each target in the second target set and each target in the first target set;

and sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

12. The method according to claim 11, wherein the generating second association relationship information between each two targets in the first target set according to the first feature information and the second feature information includes:

generating a target feature vector of each target in the first target set according to the first feature information of the target and the second feature information corresponding to each second user;

generating a third similarity of each two targets according to the target feature vectors of the two targets in the first target set;

and determining the third similarity between every two targets in the first target set as the second incidence relation information.

13. The method of claim 12, wherein the first feature information comprises: the first user evaluates each target selected from the first target set; the second feature information includes: and the evaluation information of each target selected in the first target set by each second user.

14. The method of claim 12, wherein the first feature information comprises: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises the following information: the characteristic value of each object in the first object set selected by the second user under at least one attribute characteristic.

15. The method according to claim 12, wherein the determining at least one target to be pushed from each target in the second target set based on the second association relationship information and the association relationship between each target in the second target set and each target in the first target set comprises:

dividing each target in the first target set into a plurality of groups by using a preset clustering algorithm according to a third similarity between every two targets in the first target set;

determining each target in a first target set selected by a first user as a selected target, and determining a group to which the selected target belongs as a selected group;

and determining at least one target to be pushed from each target in the second target set according to the incidence relation between each target in the second target set and the selected target in each selected group.

16. The method of claim 15, wherein the association between each object in the second set of objects and each object in the first set of objects comprises: a fourth similarity between each target in the second set of targets and each target in the first set of targets;

determining at least one target to be pushed from each target in the second target set according to the association relationship between each target in the second target set and the selected target in each selected group, including:

determining a plurality of second targets from a second target set as candidate targets according to a fourth similarity between each target in the second target set and each selected target in the selected group;

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

17. The method of claim 16, wherein the determining the at least one object to be pushed from the candidate objects based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature comprises:

determining a fifth similarity between each selected object and each candidate object based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature;

and determining the at least one target to be pushed from each candidate target according to the fifth similarity between each selected target and each candidate target.

18. An information pushing apparatus, comprising:

the first acquisition module is used for acquiring first characteristic information of each target in the first target set selected by a first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

a first generating module, configured to generate first association relationship information between the first user and the second user according to the first feature information and the second feature information;

a first determining module, configured to determine at least one target to be pushed from each target in a second target set based on the first association relationship information and selection information of the second user for selecting each target in the second target set;

and the first pushing module is used for sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

19. The apparatus of claim 18, wherein the first generating module is configured to generate the first association relationship information between the first user and the second user according to the first feature information and the second feature information by:

generating a first feature vector of the first user according to the first feature information corresponding to the first user; and

generating a second feature vector corresponding to each second user according to the second feature information corresponding to each second user;

determining a first similarity between the first user and each second user according to the first feature vector and the second feature vector;

and determining the first similarity as the first incidence relation information.

20. The apparatus of claim 19, wherein the first feature information comprises: the number of times that the first user selects each target in the first target set; the second feature information includes: the number of times that the second user selects each target in the first target set;

each element in the first feature vector represents the number of times that the first user selects each target in the first target set;

each element in the second feature vector characterizes a number of times that the second user selects each target in the first set of targets.

21. The apparatus of claim 19, wherein the first feature information comprises: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises: characteristic values of the objects in the first set of objects selected by a second user under at least one attribute characteristic.

22. The apparatus of claim 19, wherein the first determining module is configured to determine at least one target to be pushed from each target in the second target set based on the first association information and the selection information of the second user for selecting each target in the second target set in the following manner:

determining at least one selected user from the plurality of second users according to a first similarity between the first user and each second user;

and determining at least one target to be pushed from the second target set according to the selection information of each selected user for selecting each target in the second target set.

23. The apparatus of claim 22, wherein the selection information comprises: the number of times of selection of each target in the second target set by a second user;

the first determining module is configured to determine at least one target to be pushed from the second target set according to selection information of each selected user for selecting each target in the second target set in the following manner:

comparing the selection times of each selected user on each target in the second target set with a preset selection time threshold;

determining the targets with the selection times larger than the selection time threshold in the second target set as alternative targets;

determining the at least one target to be pushed from each alternative target;

or,

determining a preset number of alternative targets from the targets in the second target set according to the sequence that the selection times of each selected user to each target in the second target set are from large to small;

and determining the at least one target to be pushed from the alternative targets.

24. The apparatus of claim 23, wherein the first determining module is configured to determine the at least one target to be pushed from among the candidate targets in the following manner:

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one preset attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

25. The apparatus of claim 24, wherein the first determining module is configured to determine the at least one object to be pushed from the candidate objects based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature in the following manner:

determining a second similarity between each selected object and each candidate object based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each candidate object under the at least one attribute characteristic;

and determining the at least one target to be pushed from each candidate target according to the second similarity between each selected target and each candidate target.

26. The apparatus of claim 25, wherein the first determining module is configured to determine the at least one object to be pushed from each candidate object according to the second similarity between each selected object and each candidate object in the following manner:

for each candidate object, performing:

determining the average similarity corresponding to the candidate target according to the second similarity between the candidate target and each selected target;

and determining at least one target to be pushed from the alternative targets according to the sequence of the average similarity corresponding to the alternative targets from large to small.

27. The apparatus of claim 24, wherein the attribute features comprise one or more of:

distance between user and target, brand, price, preference information, service score, product quality, product quantity.

28. An information pushing apparatus, comprising:

the second acquisition module is used for acquiring first characteristic information of each target in the first target set selected by the first user; acquiring second characteristic information of a plurality of second users for selecting each target in the first target set;

the second generation module is used for generating second incidence relation information between every two targets in the first target set according to the first characteristic information and the second characteristic information;

a second determining module, configured to determine at least one target to be pushed from each target in the second target set based on the second association relationship information and association relationships between each target in the second target set and each target in the first target set;

and the second pushing module is used for sending the information to be pushed corresponding to the target to be pushed to the user terminal of the first user.

29. The apparatus of claim 28, wherein the second generating module is configured to generate the second association relationship information between each two targets in the first target set according to the first feature information and the second feature information in the following manner:

generating a target feature vector of each target in the first target set according to the first feature information of the target and the second feature information corresponding to each second user;

generating a third similarity of each two targets according to the target feature vectors of the two targets in the first target set;

and determining the third similarity between every two targets in the first target set as the second incidence relation information.

30. The apparatus of claim 29, wherein the first feature information comprises: the first user evaluates each target selected from the first target set; the second feature information includes: and the evaluation information of each target selected in the first target set by each second user.

31. The apparatus of claim 29, wherein the first feature information comprises: the characteristic value of each target in the first target set selected by the first user under at least one attribute characteristic comprises the following information: the characteristic value of each object in the first object set selected by the second user under at least one attribute characteristic.

32. The apparatus of claim 29, wherein the second determining module is configured to determine at least one target to be pushed from each target in the second target set based on the second association relationship information and the association relationship between each target in the second target set and each target in the first target set in the following manner:

dividing each target in the first target set into a plurality of groups by using a preset clustering algorithm according to a third similarity between every two targets in the first target set;

determining each target in a first target set selected by a first user as a selected target, and determining a group to which the selected target belongs as a selected group;

and determining at least one target to be pushed from each target in the second target set according to the incidence relation between each target in the second target set and the selected target in each selected group.

33. The apparatus of claim 32, wherein the association between each object in the second set of objects and each object in the first set of objects comprises: a fourth similarity between each target in the second set of targets and each target in the first set of targets;

the second determining module is configured to determine at least one target to be pushed from each target in the second target set according to an association relationship between each target in the second target set and a selected target in each selected group in the following manner:

determining a plurality of second targets from a second target set as candidate targets according to a fourth similarity between each target in the second target set and each selected target in the selected group;

determining each target in a first target set selected by a first user as a selected target, and acquiring a characteristic value of each selected target under at least one attribute characteristic; and acquiring a characteristic value of each candidate target under the at least one attribute characteristic;

and determining the at least one object to be pushed from the alternative objects based on the characteristic value of each selected object under the at least one attribute characteristic and the characteristic value of each alternative object under the at least one attribute characteristic.

34. The apparatus of claim 33, wherein the second determining module is configured to determine the at least one object to be pushed from the candidate objects based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature by:

determining a fifth similarity between each selected object and each candidate object based on the feature value of each selected object under the at least one attribute feature and the feature value of each candidate object under the at least one attribute feature;

and determining the at least one target to be pushed from each candidate target according to the fifth similarity between each selected target and each candidate target.

35. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the method of any one of claims 1 to 10 or to perform the steps of the method of any one of claims 11 to 17.

36. A computer-readable storage medium, having stored thereon a computer program for performing, when executed by a processor, the method according to any one of claims 1 to 10, or for performing the steps of the method according to any one of claims 11 to 17.

Images