CN113112305A

CN113112305A - Information delivery method, device and equipment

Info

Publication number: CN113112305A
Application number: CN202110468295.5A
Authority: CN
Inventors: 张思远
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-04-28
Filing date: 2021-04-28
Publication date: 2021-07-13

Abstract

The application discloses an information delivery method, an information delivery device and information delivery equipment, wherein the method comprises the following steps: receiving an information delivery request corresponding to a target user sent by a client; determining target user characteristic information of a target user based on a target user identifier in the information delivery request; acquiring object characteristic information of an object to which at least one piece of information to be released belongs; determining price adjusting parameters corresponding to the object to which the at least one piece of information to be released belongs based on the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be released belongs; determining target release information from at least one piece of information to be released based on a price adjusting parameter corresponding to an object to which the at least one piece of information to be released belongs and a preset reference release price; and sending the target delivery information to the client so that the client delivers the target delivery information. By utilizing the technical scheme provided by the embodiment of the application, the information delivery efficiency and the income-output ratio can be at least improved.

Description

Information delivery method, device and equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to an information delivery method, apparatus, and device.

Background

In order to maximize the benefits of advertisement delivery, the current media platform adopts a bidding mode of a plurality of advertisers for advertisement delivery. Specifically, the media platform may analyze user data of the target population according to the target population specified by the advertiser, determine the degree of association of the target population with the advertiser, determine the bid of the advertiser according to the degree of association, and place the advertisement of the advertiser with a high bid.

However, in the advertisement delivery scheme, under the condition of analyzing the user data, the bid price of the advertiser is determined only according to the analysis result of the user data of the target population designated by the advertiser, the coverage population is limited, the accuracy of the bid price of the advertiser is influenced, the income-output ratio of advertisement delivery is reduced, and the advertisement delivery efficiency is greatly reduced. In addition, in the case where the advertiser is a new advertiser, the advertiser cannot specify an effective target group due to lack of delivery experience of the new advertiser, so that the media platform cannot effectively determine the bid of the new advertiser, and the accuracy of advertisement delivery, delivery efficiency, and revenue-output ratio of advertisement delivery may be reduced.

Disclosure of Invention

The application provides an information delivery method, an information delivery device, information delivery equipment and a computer readable storage medium, which can at least improve the accuracy, the delivery efficiency and the income-output ratio of information delivery.

In one aspect, the present application provides an information delivery method, including:

receiving an information delivery request corresponding to a target user sent by a client, wherein the information delivery request comprises a target user identifier of the target user;

determining target user characteristic information of the target user based on the target user identification;

acquiring object characteristic information of an object to which at least one piece of information to be released belongs;

determining price adjusting parameters corresponding to the object to which the at least one piece of information to be released belongs on the basis of the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be released belongs; the price-adjusting parameter represents the preference degree of the target user for the at least one piece of information to be released;

determining a target release price corresponding to the at least one piece of information to be released based on a price adjusting parameter corresponding to the object to which the at least one piece of information to be released belongs and a preset reference release price;

determining target release information from the at least one piece of information to be released according to the target release price;

and sending the target delivery information to the client so that the client delivers the target delivery information.

Another aspect provides an information delivery apparatus, including:

the system comprises a receiving module, a sending module and a receiving module, wherein the receiving module is used for receiving an information releasing request corresponding to a target user sent by a client, and the information releasing request comprises a target user identifier of the target user;

the first determination module is used for determining target user characteristic information of the target user based on the target user identification;

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring object characteristic information of an object to which at least one piece of information to be released belongs;

the second determining module is used for determining price adjusting parameters corresponding to the object to which the at least one piece of information to be released belongs on the basis of the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be released belongs; the price-adjusting parameter represents the preference degree of the target user for the at least one piece of information to be released;

a third determining module, configured to determine a target release price corresponding to the at least one piece of information to be released based on a price adjustment parameter and a preset reference release price corresponding to an object to which the at least one piece of information to be released belongs;

a fourth determining module, configured to determine target placement information from the at least one to-be-placed information according to the target placement price;

and the sending module is used for sending the target release information to the client so as to enable the client to release the target release information.

Another aspect provides an information delivery apparatus, which includes a processor and a memory, where at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded by the processor and executed to implement the information delivery method as described above.

Another aspect provides a computer-readable storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement the information delivery method as described above.

The information delivery method, the information delivery device, the information delivery equipment and the computer readable storage medium have the following technical effects:

according to the method and the device, the information delivery request corresponding to the target user sent by the client is received, the user characteristic information of the target user can be quickly determined according to the target user identification carried by the information delivery request, and the information delivery efficiency is improved. And then accurately determining a price adjusting parameter of the object to which the at least one piece of information to be released belongs according to the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be released belongs, accurately determining an adjusting parameter according to the price adjusting parameter and a preset reference price, and accurately obtaining a target releasing price of the object to which the at least one piece of information to be released belongs according to the adjusting parameter and the preset reference releasing price, thereby being beneficial to improving the accuracy and income-output ratio of advertisement releasing. And according to the target release price of the object to which the at least one piece of information to be released belongs, the target release information can be accurately determined from the at least one piece of information to be released, and the target release information is sent to the client, so that the release of the target release information is realized. The target delivery information is delivered, so that the income-output ratio of advertisement delivery can be improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic diagram of an information delivery system according to an embodiment of the present application;

FIG. 2 is a schematic diagram of another information delivery system provided by an embodiment of the present application;

fig. 3 is a schematic flowchart of an information delivery method according to an embodiment of the present application;

fig. 4 is a schematic flowchart of an object feature mapping information creating process according to an embodiment of the present disclosure;

fig. 5 is a schematic flow chart of a price adjustment parameter determination process provided in an embodiment of the present application;

fig. 6 is a schematic flow chart of another pricing parameter determining process provided in the embodiment of the present application.

Fig. 7 is a schematic view of an application scenario of an information delivery method according to an embodiment of the present application;

fig. 8 is a schematic flowchart of another information delivery method according to an embodiment of the present application;

fig. 9 is a schematic flowchart of another information delivery method according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of an information delivery apparatus according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of another information delivery apparatus provided in the embodiment of the present application;

fig. 12 is a schematic structural diagram of another information delivery apparatus provided in the embodiment of the present application;

fig. 13 is a schematic diagram of an information delivery server according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The information delivery system related to the embodiment of the application can be a distributed system formed by connecting a client, a plurality of nodes (any form of computing devices in an access network, such as servers and user terminals) through a network communication mode.

Taking a distributed system as an example of a blockchain system, referring to fig. 1, fig. 1 is an optional structural schematic diagram of a blockchain system to which a distributed system 100 provided in this embodiment of the present application is applied, where the system is formed by a plurality of nodes (computing devices in any form in an access network, such as servers and user terminals) and clients, and a Peer-to-Peer (P2P, Peerto Peer) network is formed between the nodes, and a P2P Protocol is an application layer Protocol operating on top of a Transmission Control Protocol (TCP). In a distributed system, any machine, such as a server or a terminal, can join to become a node, and the node comprises a hardware layer, a middle layer, an operating system layer and an application layer.

Referring to the functions of each node in the blockchain system shown in fig. 1, the functions involved include:

1) routing, a basic function that a node has, is used to support communication between nodes.

Besides the routing function, the node may also have the following functions:

2) the application is used for being deployed in a block chain, realizing specific services according to actual service requirements, recording data related to the realization functions to form recording data, carrying a digital signature in the recording data to represent a source of task data, and sending the recording data to other nodes in the block chain system, so that the other nodes add the recording data to a temporary block when the source and integrity of the recording data are verified successfully.

For example, the services implemented by the application include:

2.1) wallet, for providing the function of transaction of electronic money, including initiating transaction (i.e. sending the transaction record of current transaction to other nodes in the blockchain system, after the other nodes are successfully verified, storing the record data of transaction in the temporary blocks of the blockchain as the response of confirming the transaction is valid; of course, the wallet also supports the querying of the remaining electronic money in the electronic money address;

and 2.2) sharing the account book, wherein the shared account book is used for providing functions of operations such as storage, query and modification of account data, record data of the operations on the account data are sent to other nodes in the block chain system, and after the other nodes verify the validity, the record data are stored in a temporary block as a response for acknowledging that the account data are valid, and confirmation can be sent to the node initiating the operations.

2.3) Intelligent contracts, computerized agreements, which can enforce the terms of a contract, implemented by codes deployed on a shared ledger for execution when certain conditions are met, for completing automated transactions according to actual business requirement codes, such as querying the logistics status of goods purchased by a buyer, transferring the buyer's electronic money to the merchant's address after the buyer signs for the goods; of course, smart contracts are not limited to executing contracts for trading, but may also execute contracts that process received information.

3) The block chain comprises a series of blocks (B l ock) which are mutually connected according to the generated chronological order, new blocks cannot be removed once being added into the block chain, and recorded data submitted by nodes in the block chain system are recorded in the blocks.

Referring to fig. 2, fig. 2 is a schematic diagram of another information delivery system according to an embodiment of the present application, and as shown in fig. 2, the system may include a client 01 and a server 02. In this embodiment, the client 01 may be configured to receive target delivery information returned by the server 02 after sending an information delivery request corresponding to a target user to the server 02, and deliver the target delivery information. Optionally, the client 01 may include a smart phone, a desktop computer, a tablet computer, a notebook computer, a smart speaker, a digital assistant, an Augmented Reality (AR)/Virtual Reality (VR) device, a smart wearable device, and other types of entity devices. Software running on the physical device may also be included, such as applications, websites, etc.

In this embodiment of the application, the server 02 may be configured to receive an information delivery request corresponding to a target user sent by the client 01, determine target delivery information corresponding to the target user based on a target user identifier in the information delivery request, and send the target delivery information to the client 01, so that the client 01 delivers the target delivery information. Optionally, the service end 02 may be an independent physical server, or a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like.

The client 01 and the server 02 may be directly or indirectly connected through a wired or wireless communication manner, and the present application is not limited herein. In addition, it should be noted that the system architecture corresponding to fig. 2 is only an architecture of an information delivery system provided in the embodiment of the present specification, and in practical applications, other system architectures may also be included. For example, the program processing may be implemented on the server side.

The information delivery methods of the present application are described below, and the present specification provides method steps as described in the examples or flowcharts, but may include more or less steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel processor or multi-threaded environment) according to the embodiments or methods shown in the figures.

In a specific embodiment, as shown in fig. 3, the present application provides an information delivery method applied to an information delivery system, where the method includes:

s301: the client sends an information delivery request corresponding to a target user to the server, wherein the information delivery request comprises a target user identifier of the target user.

In the embodiment of the application, the client can be any client of an information delivery system facing a target user, and can be used for pushing corresponding information to the target user.

In the embodiment of the application, the server can be a server which provides background services for the client by any information delivery system.

In an alternative embodiment, the information delivery system may include an information delivery platform, such as a media delivery platform. The media delivery platform may deliver at least one media message, which may include at least one of video data, image data, and audio data.

In practical applications, the media delivery platform may be an advertisement delivery platform, and the advertisement delivered by the advertisement delivery platform may be a sound or soundless video type advertisement, or may also be a sound or soundless image type advertisement.

In this embodiment of the application, the target user may be any user who performs a preset operation on the client. Specifically, the preset operation may include, but is not limited to, an open operation and a login operation.

In this embodiment of the application, the information delivery request may be a request sent by the client to the server when the client needs to deliver information to the target user.

In an optional embodiment, the client may generate an information delivery request corresponding to the target user in response to a preset operation triggered by the target user, and send the information delivery request to the server.

Taking the information delivery platform as an advertisement delivery platform as an example, the client sends an information delivery request corresponding to the target user to the server of the advertisement delivery platform in response to an opening operation or a login operation triggered by the target user, so that the server provides the advertisement which can be delivered to the target user.

In the embodiment of the application, the information delivery corresponding to the target user can be realized through the interaction between the client and the server.

S303: and the server determines the target user characteristic information of the target user based on the target user identification.

In this embodiment of the present application, the target user identifier may include, but is not limited to, a user ID (Identity) of the target user, a user name, and a user number. Specifically, the target user identifier may be a unique identifier for distinguishing the target user from other users.

In the embodiment of the application, the target user characteristic information may represent the user characteristics of the target user.

In an optional embodiment, in order to quickly determine the user characteristic information of the target user, the server may pre-establish user characteristic mapping information. The user characteristic mapping information represents a mapping relation between at least one user identifier and corresponding user characteristic information. Correspondingly, before the service end determines the target user characteristic information of the target user based on the target user identifier, the method further includes:

the server side obtains a user identification and user characteristic information of a preset user;

and the server establishes the user characteristic mapping information according to the user identification and the user characteristic information of the preset user.

In this embodiment of the application, the preset user may be a user in the information delivery system. Specifically, the preset user may be a user who has logged in the information delivery system within a preset time period, and the preset time period may be a time period before the current target user login time, and may be set according to actual application requirements, for example, within a half year before the current target user login time.

In the embodiment of the application, the user identifier of the preset user is used for distinguishing different preset users and is a unique identifier.

In an optional embodiment, to obtain the user characteristic information of the preset user, the method further includes:

the server side obtains user attribute information of a preset user;

and the server inputs the user attribute information of the preset user into a user characteristic extraction network of the prediction model for characteristic extraction to obtain the user characteristic information of the preset user.

In this embodiment, the user attribute information of the preset user may include user portrait information and user behavior information. Specifically, the user profile information may include, but is not limited to, the age, sex, hobby, and occupation of the predetermined user. The user behavior information may include, but is not limited to, a preset user click behavior for favorite advertisements and a preset user mask behavior for objectionable advertisements.

In the embodiment of the present application, the user feature extraction network may be a deep learning-based neural network, and the types of the deep learning-based neural network include, but are not limited to, a deep convolutional network and a fully-connected network.

In the embodiment of the present application, the user feature extraction network includes an input layer, an intermediate layer, and an output layer. The user attribute information is mapped into a low-dimensional vector, and the low-dimensional vector is subjected to vector splicing, so that a user attribute splicing vector corresponding to the user attribute information can be obtained. And inputting the user attribute splicing vector into an input layer, and obtaining user characteristic information output by an output layer through characteristic extraction of an intermediate layer. For example, the user genusSexual information includes age 5, which can be mapped to a low dimensional vector

The user attribute information comprises gender male, and the gender male can be mapped into a low-dimensional vector

To pair

And

splicing is carried out to obtain a user attribute splicing vector

Optionally, in order to distinguish low-dimensional vectors obtained by mapping different user attribute information, the low-dimensional vectors may also be identified.

Specifically, the number of each layer of network nodes of the intermediate layer may be 128, 64 or 16. In addition, a drop parameter of the middle layer can be set so as to randomly disconnect part of network nodes between adjacent layers in the middle layer. With the droupout parameter set to 20%, the connections of 20% of the network nodes between adjacent layers in the middle layer can be randomly disconnected to prevent the problem of overfitting.

Specifically, the activation function of the intermediate layer may include, but is not limited to relu and sigmoid.

It is to be understood that the mathematical expression form of the user feature information may be a user feature vector, and the mathematical expression form of the object feature information may be an object feature vector. Accordingly, the mathematical expression form of the target feature user feature information may be a target user feature vector. And the user feature vector and the object feature vector are located in the same dimensional space.

Taking the information delivery system as an advertisement delivery platform as an example, the server may query the target user feature vector corresponding to the target ID from the user feature mapping information according to the target ID of the target user.

In the embodiment of the application, the server determines the target user characteristic information of the target user based on the target user identifier, so that the preference of the target user can be effectively determined.

S305: and the server side acquires object characteristic information of an object to which at least one piece of information to be put belongs.

In this embodiment of the application, the object to which the at least one piece of information to be delivered belongs may be an information provider of the at least one piece of information to be delivered.

In an alternative embodiment, the at least one to-be-delivered information may be at least one to-be-delivered media information. Correspondingly, the object to which the at least one piece of information to be delivered belongs may be a media information provider of the at least one piece of media information to be delivered.

In the embodiment of the application, the object feature information may represent an object feature of an object to which the information to be delivered belongs.

Taking the information delivery system as an advertisement delivery platform as an example, the at least one piece of information to be delivered may be at least one advertisement to be delivered, and the object to which the at least one piece of information to be delivered belongs may be at least one advertiser.

In an optional embodiment, in order to quickly obtain object feature information of an object to which at least one piece of information to be delivered belongs, the server may establish object feature mapping information in advance. Correspondingly, the step of obtaining the object feature information of the object to which the at least one piece of information to be delivered belongs by the server side comprises the following steps:

the server side obtains an object identifier of an object to which the at least one piece of information to be released belongs;

the server side determines object characteristic information corresponding to the object identification as the object characteristic information based on object characteristic mapping information; the object feature mapping information represents a mapping relation between at least one object identifier and corresponding object feature information.

In this embodiment of the application, the object identifier of the object to which the at least one piece of information to be delivered belongs may be an object ID, an object name, and an object number of the object to which the at least one piece of information to be delivered belongs. Specifically, the object identifier of the at least one object to which the information to be delivered belongs is used for distinguishing different objects to which the information to be delivered belongs, and is a unique identifier.

In an optional embodiment, as shown in fig. 4, in order to establish object feature mapping information, before the server obtains object feature information of an object to which at least one piece of information to be delivered belongs, the method further includes:

s401: and the server determines the object type of the object to which the at least one piece of information to be put belongs.

In the embodiment of the application, the object type of the object to which the at least one piece of information to be delivered belongs may include a historical training object, a historical non-training object, and a newly added object.

Specifically, the historical training objects and the historical sub-training objects are objects to which information to be released already exists on the information releasing platform. The difference between the historical training subjects and the historical non-training subjects is that the historical training subjects have historical conversion information and the historical non-training subjects do not have historical conversion information.

It can be understood that the historical conversion information may include a historical record of the conversion behavior existing when the preset user clicks on the historical training object, and may also include a historical record of the conversion behavior not existing when the preset user clicks on the historical training object. The above conversion behaviors include, but are not limited to, clicking, browsing, placing orders, and registering.

It can be understood that the preset user is a user of the information delivery system.

The server needs to train the prediction model by using the historical conversion information in the preset period, and then predicts the user characteristic information of the preset user, the user characteristic information of the target user and the object characteristic information of the object to which the information to be released belongs by using the trained prediction model in the next period. In addition, the server does not have any historical conversion information related to the newly added object. Therefore, the server can obtain the object feature information of the historical training object by using the prediction model, and needs to obtain the object feature information of the historical non-training object and the newly added object by adopting other modes.

In an optional embodiment, the server trains the prediction model according to the historical conversion information in the preset period to obtain the prediction model available in the next period. The specific training process is as follows:

and the server side obtains the history record in a preset period and determines a training sample set according to the history record. The training sample set comprises sample user attribute information of a sample user, sample object attribute information of an object to which released information belongs and a sample label. For each training sample, under the condition that a sample user clicks the released information and a conversion behavior exists, the training sample is a positive sample, and the sample label is 1; under the condition that the sample user clicks the released information and no conversion behavior exists, the training sample is a negative sample, and the sample label is 0. Specifically, the conversion behavior includes, but is not limited to, clicking, browsing, registering, and placing orders.

It is to be understood that the sample user may be a user existing in the history within a preset period.

In an optional embodiment, the length of the preset period may be one day, or may be three days, and may be set according to the actual application requirement.

Specifically, the sample object attribute information may include, but is not limited to, an ID, an industry, and a type of an object to which the delivered information belongs. The ID of the object to which the released information belongs is used for distinguishing different objects to which the released information belongs, and is a unique identifier, the industry can comprise education industry and e-commerce industry, and the type can comprise clothing, daily necessities and snacks.

The server inputs the sample user attribute information into a user characteristic extraction network of the prediction model to obtain sample user characteristic information; and inputting the sample object attribute information into an object feature extraction network of the prediction model to obtain sample object feature information. Calculating the similarity (representing correlation degree) of the sample user characteristic information and the sample object characteristic information by a similarity algorithm of a prediction network to obtain a prediction conversion probability; and calculating the target loss of the prediction model according to the prediction conversion probability and the sample label, adjusting the model parameters of the prediction model under the condition that the target loss does not meet the preset condition, updating the target loss based on the adjusted prediction model until the target loss meets the preset condition, and taking the current prediction model as the usable prediction model in the next period.

In an alternative embodiment, the preset condition may include: the target loss is greater than a first preset threshold. The first preset threshold may be set based on actual application requirements. Specifically, the loss function for calculating the target loss may be a cross-entropy loss function.

In an alternative embodiment, the preset condition may include: in the training samples with the predicted conversion rate larger than the second preset threshold, the proportion of the training samples with the sample label of 1 is larger than that of the training samples with the sample label of 0. Specifically, the loss function for calculating the target loss may be an AUC (Area under ROC curve), where the ROC curve is called Receiver operator performance curve in english and called Receiver operating characteristic curve in chinese.

The two preset conditions can ensure the successful training of the prediction model, wherein the AUC function can also ensure the classification capability of the classifier for positive examples and negative examples, and the successful training of the prediction model can also be ensured under the condition of unbalanced samples.

Taking the information delivery system as an advertisement delivery platform as an example, the delivered information is a delivered advertisement, and the object to which the delivered information belongs is an advertiser who has delivered the advertisement. Under the condition that the preset period is one day, if the preset period is finished, extracting a training sample set from a historical record in the preset period, training a prediction model by using the training sample set, and predicting a user characteristic vector of a preset user and an advertiser characteristic vector of an advertiser who has delivered advertisements in the next period by using the trained prediction model. The advertiser who has placed the advertisement is the historical training object.

In an optional embodiment, a preset user may be sampled, and the user obtained by sampling may be used as a user for predicting the next period of the prediction model.

S403: and the server acquires the object information of the object to which the at least one piece of information to be released belongs according to the object type.

In this embodiment of the application, the object information may be information used to determine object feature information of an object to which the information to be delivered belongs.

S405: and the server determines the object characteristic information of the object to which the at least one piece of information to be released belongs according to the object information.

In a specific embodiment, when the object type is a historical training object, the obtaining, by the server, object information of an object to which the at least one piece of information to be delivered belongs according to the object type includes:

under the condition that the object type is a historical training object, the server side determines the object attribute information of the historical training object as the object information; wherein the historical training object is an object with historical conversion information.

In the embodiment of the application, the server may input the object attribute information of the historical training object into the object feature extraction network of the prediction model to perform feature extraction, so as to obtain the object feature information of the historical training object.

Specifically, the object attribute information may include, but is not limited to, an ID, a type, and an industry of the historical training object. The ID of the historical training object is used for distinguishing different historical training objects, is a unique identification, can be made into types of clothes, snacks and articles for daily use, and can be made into industries of education industry and E-commerce industry.

In a specific embodiment, the object feature extraction network may be a deep learning based neural network, and the types include, but are not limited to, a deep convolutional network and a fully connected network.

Specifically, the object feature extraction network includes an input layer, an intermediate layer, and an output layer. The object attribute information is mapped into a low-dimensional vector, and the low-dimensional vector is subjected to vector splicing, so that an object attribute splicing vector corresponding to the object attribute information can be obtained. And inputting the object attribute splicing vector into an input layer, and obtaining object characteristic information output by an output layer through characteristic extraction of an intermediate layer. The specific vector mapping process and the vector splicing process may refer to the vector mapping process and the vector splicing process related to obtaining the user characteristic information, which are not described herein again.

It can be understood that the mathematical expression mode of the object feature information may be an object feature vector, and the mathematical expression mode of the user feature information may be a user feature vector, which are located in the same dimensional space.

In a specific embodiment, when the object type is a historical non-training object, the obtaining, by the server, object information of an object to which the at least one piece of information to be delivered belongs according to the object type further includes:

determining a related user of the historical non-training object from the preset users under the condition that the object type is the historical non-training object; wherein the historical non-training object is an object without the historical conversion information;

and determining the user characteristic information of the associated user as the object information.

In the embodiment of the application, the preset user is a large-disk user of the information delivery system.

In the embodiment of the application, the associated user is a user who clicks the released information of the historical non-training object and has a conversion behavior among the large-disk users. Due to the conversion behavior, the similarity between the user characteristic information of the associated user and the object characteristic information of the historical non-training object is extremely high, namely the association degree is extremely high. The object feature information of the historical non-training object can be obtained by performing average pooling on the user feature information of the associated users.

Taking the information delivery system as an advertisement delivery platform as an example, under the condition that the type of an advertiser is a historical non-training advertiser, the user who clicks the advertisement of the historical non-training advertiser and places an order can be determined from large-disk users as a related user, and the user feature vectors of the related users are subjected to average pooling to obtain the advertiser feature vectors of the historical non-training advertiser.

According to the embodiment of the application, the object characteristic information of the historical non-training object can be effectively determined according to the user characteristic information of the associated user.

In a specific embodiment, when the object type is a newly added object, the obtaining, by the server, object information of an object to which the at least one information to be delivered belongs according to the object type further includes:

under the condition that the object type is a new object, the server side determines a related object of the new object from the historical training objects;

and the server side determines the object characteristic information of the associated object as the object information.

In the embodiment of the application, the associated object is an object similar to the newly added object in the historical training objects in terms of industry and type.

In a specific embodiment, the object feature information of the newly added object may be obtained by performing an average pooling process on the object feature information of the associated object.

Taking an information delivery system as an advertisement delivery platform as an example, under the condition that an advertiser is a newly added advertiser, the advertiser with the same or similar type and industry can be determined from historical training advertisers as an associated advertiser, and the feature vectors of the advertisers of the associated advertiser are subjected to average pooling to obtain the feature vectors of the advertisers of the newly added advertiser.

In the embodiment of the application, the server side can effectively determine the object characteristic information of the newly added object according to the object characteristic information of the associated object.

In the embodiment of the application, the object characteristic information of the object to which the information to be released belongs can be determined in different modes according to the object type by distinguishing the object type of the object to which the information to be released belongs, so that the accuracy of the object characteristic information is improved, and the accuracy and the income-output ratio of information release are improved.

S407: and the server side establishes the object characteristic mapping information according to the object identification and the object characteristic information.

In an optional embodiment, the server further has information-object mapping information, where the information-object mapping information ensures a mapping relationship between an information identifier of at least one piece of information to be delivered and an object identifier of an object to which the at least one piece of information to be delivered belongs. Specifically, the information identifier may be an information ID of the information to be delivered.

The server side can inquire the object identifier of the object to which the at least one piece of information to be released belongs from the information-object mapping information according to the information identifier of the at least one piece of information to be released, and inquire the object feature information of the object to which the at least one piece of information to be released belongs from the object feature mapping information according to the object identifier of the object to which the at least one piece of information to be released belongs.

Taking the information delivery system as an advertisement delivery platform as an example, the server can query the advertiser identification of at least one advertiser from the advertisement-advertiser mapping information according to the advertisement ID of at least one advertisement to be delivered. And inquiring the advertiser characteristic vector of the at least one advertiser from the advertiser characteristic mapping information according to the advertiser identification of the at least one advertiser.

In the embodiment of the application, the object characteristic information of the object to which at least one piece of information to be delivered belongs can be quickly inquired by establishing the object characteristic mapping information, and the advertisement delivery efficiency is favorably improved.

S307: the server side determines price adjusting parameters corresponding to the object to which the at least one piece of information to be released belongs on the basis of the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be released belongs; and the price-adjusting parameter represents the preference degree of the target user for the at least one piece of information to be released.

In practical applications, the server of the information delivery system may set an initial bid (a preset reference delivery price) of at least one object to which the information to be delivered belongs to a target user. The server side can analyze the association degree of the target user and the object to which each piece of information to be released belongs on the basis of the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be released belongs, and determines the price adjusting parameter of the object to which each piece of information to be released belongs according to the association degree. And determining the bid price (target release price) of each object to which the information to be released belongs to the target user according to the price adjusting parameter of each object to which the information to be released belongs and the preset reference release price.

In the embodiment of the application, the price adjusting parameter is used for determining the target putting price of each object to which the information to be put belongs.

Taking the information delivery system as an advertisement delivery platform as an example, if the price adjustment parameter of the advertiser for the target user is 0.8, and the initial value set by the server for the target user is 100 yuan, the bid of the advertiser for the target user is 80 yuan.

In a specific embodiment, as shown in fig. 5, the determining, by the service end, a price-adjusting parameter corresponding to an object to which the at least one piece of information to be delivered belongs based on the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be delivered belongs includes:

s501: and the server determines first associated information between the target user and an object to which the information to be released belongs according to the target user characteristic information and the object characteristic information of the object to which the at least one information to be released belongs.

Specifically, the target user feature information is a target user feature vector, and the object feature information is an object feature vector. Both located in the same dimensional space.

In this embodiment of the application, the first associated information includes an inner product of a target user feature vector of the target user and an object feature vector of an object to which each piece of information to be delivered belongs.

It can be understood that the first association information represents a degree of similarity between the target user characteristic information of the target user and the object characteristic information of the object to which each piece of information to be delivered belongs. The first correlation information can also represent the correlation degree of the target user to each object to which the information to be released belongs. The larger the inner product, the higher the degree of association.

S503: the server side obtains user characteristic information of a preset user.

Specifically, the user feature information of the preset user is a user feature vector of the preset user, and the user feature vector of the preset user, the target user feature vector and the object feature vector are located in the same dimensional space.

S505: and the server determines second associated information between the preset user and the object to which the information to be released belongs according to the user characteristic information of the preset user and the object characteristic information of the object to which the at least one information to be released belongs.

In this embodiment of the application, the second associated information includes an inner product of the user feature vector of the preset user and an object feature vector of an object to which each piece of information to be delivered belongs.

It can be understood that the second correlation information represents a degree of similarity between the user characteristic information of the preset user and the object characteristic information of the object to which each piece of information to be delivered belongs. The second correlation information can also represent the correlation degree of a preset user to each object to which the information to be released belongs. The larger the inner product, the higher the degree of correlation.

S507: and the server side acquires the price range control parameter of the target putting price.

In the embodiment of the application, the object to which the information to be released belongs can be set according to factors such as market price of the information release market, information release bid budget and the like, and price range control parameters of the target release price of the server side are set on a terminal corresponding to the object to which the information to be released belongs, so that the price adjusting parameters obtained through calculation fall into an expected range.

In practical application, the server may provide a price adjustment operation interface for the object to which the information to be delivered belongs, and the object to which the information to be delivered belongs sets a price range control parameter c through the price adjustment operation interface. Accordingly, the target launch price may range from [1-c, 1+ c ]. For example, if the price range control parameter c is set to 0.3, the price range of the target delivery price is [0.7, 1.3 ].

In an optional embodiment, the object to which the information to be delivered belongs may not set the price range control parameter c. Correspondingly, the bid (target putting price) of the target object by the object to which the information to be put belongs is a preset reference putting price set by the server.

S509: and the server side normalizes the first associated information based on the second associated information and the price range control parameter to obtain a price adjusting parameter corresponding to the object to which the at least one piece of information to be released belongs.

In a specific embodiment, as shown in fig. 6, the normalizing, by the server, the first associated information based on the second associated information and the price range control parameter to obtain a price adjustment parameter corresponding to an object to which the at least one to-be-released information belongs includes:

s601: and the server determines an average price adjustment parameter and a variance price adjustment parameter corresponding to the object to which the at least one to-be-released information belongs according to the second associated information.

In the embodiment of the application, the average price-adjusting parameter may be an average value of an inner product of the user characteristic vector of the preset user and an object characteristic vector of an object to which each piece of information to be released belongs;

in this embodiment of the application, the variance pricing parameter may be a variance of an inner product of the user feature vector of the preset user and an object feature vector of an object to which each piece of information to be delivered belongs.

S603: and the server side normalizes the first associated information according to the average price adjusting parameter, the variance price adjusting parameter and the price range control parameter to obtain the price adjusting parameter of the object to which each piece of information belongs.

In the embodiment of the application, the calculation formula of the price-adjusting parameter is as follows:

the price adjustment parameter f ═ 3 · (x-a) ÷ (2+ c + b) equation 1;

wherein x is the inner product of the target user feature vector and the object vector of the object to which the information to be put belongs, a is the average price adjustment parameter, c is the price range control parameter, and b is the variance price adjustment parameter.

The meaning of the above equation 1 is that x is mapped into a normal distribution range in which 1 is a mean value and upper and lower boundaries are (1-c) and (1+ c). The meaning of the coefficient 3 is to ensure that the numerical maximum probability of f is within 3 times of the value of the variance adjusting parameter.

In an alternative embodiment, it is considered that the value of f may fall outside [1-c, 1+ c ], and in practice, f still approaches (1-c) or (1+ c) if it falls outside [1-c, 1+ c ]. In the case where f is less than (1-c), the final value of f may be determined to be (1-c), and in the case where f is greater than (1+ c), the final value of f may be determined to be (1+ c).

It can be understood that the second association information is used for carrying out normalization processing on the first association information, the association degree of the target user to the object to which each piece of information to be released belongs can be effectively determined by taking the association degree of the preset user to the object to which each piece of information to be released belongs as a reference, and the range of the price adjustment parameter can be reasonably restricted.

In the scheme, the object to which the information to be released belongs can accurately determine the degree of association of the target user to the object, and further determine the appropriate price-adjusting parameter so as to accurately bid and improve the income-output ratio of advertisement release.

S309: and the server side determines a target release price corresponding to the at least one piece of information to be released based on the price adjusting parameter corresponding to the object to which the at least one piece of information to be released belongs and a preset reference release price.

In a specific embodiment, the target placement price is calculated by the formula:

the target putting price g is f x y formula 2;

and y is the preset reference release price.

Taking the information delivery system as an advertisement delivery platform as an example, if the price adjustment parameter of the advertiser for the target user is 0.8, and the preset reference delivery price set by the service end for the target user is 100 yuan, the bid of the advertiser for the target user is 80 yuan.

S311: and the server determines target release information from the at least one piece of information to be released according to the target release price.

In the embodiment of the application, the server preferentially determines the information to be released with higher target release price as the target release information.

In an optional embodiment, the server may perform priority ranking on the at least one piece of information to be released according to a target release price, and determine the information to be released with the priority ranking positioned in the top N bits as target release information.

S313: and the server side sends the target delivery information to the client side.

Taking the information delivery system as an advertisement delivery platform as an example, the bids of advertiser 1, advertiser 2 and advertiser 3 are 120, 110 and 90, respectively. The server determines that the priority of advertiser 1 is greater than that of advertiser 2 and the priority of advertiser 2 is greater than that of advertiser 3, and transmits the advertisements of advertiser 1 and advertiser 2 whose priorities are ranked in the top 2 to the client.

In the embodiment of the application, the server side sends the advertisement of the advertiser with high bid price to the client side, so that the income-output ratio of the advertisement can be improved, and good economic benefit of an information delivery system can be realized.

S315: and the client puts the target putting information.

In an optional embodiment, the server may further send the prioritization of the target delivery information to the client.

Correspondingly, the client can determine the delivery position of the target delivery information on the client display interface according to the priority ranking of the target delivery information, and preferentially deliver the target delivery information with high target delivery price at the most obvious delivery position.

Taking the information delivery system as an advertisement delivery platform as an example, the client delivers the advertisement of the advertiser 1 to the most obvious delivery position of the display interface of the client and the advertisement of the advertiser 2 to the next delivery position according to the priority of the advertiser 1 being higher than that of the advertiser 2.

By the scheme, the target delivery information can be delivered, and the income-output ratio of information delivery is improved.

Taking an information delivery system as an advertisement delivery platform as an example, as shown in fig. 7, the embodiment of the present application further provides an application scenario of the information delivery method. Specifically, the method comprises the following steps:

and the client sends an information delivery request corresponding to the target user to a server of the advertisement delivery platform in response to the opening or login operation triggered by the target user. And the server side inquires the target user characteristic vector of the target user from the user characteristic mapping information according to the target user identification carried by the information release request. The server side has at least one advertisement to be launched, and according to the advertisement identification of the at least one advertisement to be launched, the advertisement-advertiser mapping information is inquired to obtain the advertiser identification of the at least one advertiser. And the server side inquires the characteristic vector of the advertiser of at least one advertiser from the characteristic mapping information of the advertiser according to the identifier of the advertiser of at least one advertiser. And the server calculates the inner product of the target user characteristic vector and the advertiser characteristic vector of each advertiser, and substitutes the inner product into the formula 1 to obtain the price-adjusting parameter of each advertiser. And the server side determines the bid of each advertiser according to the price adjusting parameter of each advertiser and the preset reference putting price, preferentially determines the advertisement of the advertiser with high bid as the target advertisement, and sends the target advertisement to the client side. And the client puts the target advertisement on the display interface.

In the embodiment of the application, the client sends the information delivery request corresponding to the target user to the server, so that the server can determine the target delivery information to be delivered for the target user conveniently, and the efficiency of advertisement delivery is improved. The server side can effectively determine the association degree of the target user to the object to which the information to be released belongs according to the target user characteristic information of the target user and the object characteristic information of the object to which the at least one information to be released belongs, and determines the bid of the object to which the information to be released belongs to the target user according to the association degree. The server side inquires the target user characteristic information of the target user according to the user characteristic mapping information, and the advertisement putting efficiency is improved. The server side inquires the object characteristic information of the object to which the at least one piece of information to be delivered belongs according to the object characteristic information, so that the efficiency of advertisement delivery is improved. The target delivery information needing to be delivered to the target user is determined by the server according to the bid of the target user of each object to which the information to be delivered belongs, and the income-output ratio of the advertisement is favorably improved.

As shown in fig. 8, an embodiment of the present application further provides an information delivery method, which is applied to a server, and the method includes:

s801: receiving an information delivery request corresponding to a target user sent by a client, wherein the information delivery request comprises a target user identifier of the target user.

S803: and determining target user characteristic information of the target user based on the target user identification.

S805: and acquiring object characteristic information of an object to which at least one piece of information to be released belongs.

In a specific embodiment, the obtaining object feature information of an object to which at least one piece of information to be delivered belongs includes:

obtaining an object identifier of an object to which the at least one piece of information to be released belongs;

determining object characteristic information corresponding to the object identification as the object characteristic information based on object characteristic mapping information; the object feature mapping information represents a mapping relation between at least one object identifier and corresponding object feature information.

In an optional embodiment, before the obtaining object feature information of an object to which at least one to-be-delivered information belongs, the method further includes:

determining the object type of an object to which the at least one piece of information to be released belongs;

acquiring object information of an object to which the at least one piece of information to be released belongs according to the object type;

determining object characteristic information of an object to which the at least one piece of information to be released belongs according to the object information;

and establishing the object characteristic mapping information according to the object identification and the object characteristic information.

In an optional embodiment, the obtaining, according to the object type, object information of an object to which the at least one to-be-delivered information belongs includes:

determining object attribute information of the training object as the object information under the condition that the object type is a historical training object; wherein the historical training object is an object with historical conversion information.

In an optional embodiment, the obtaining, according to the object type, object information of an object to which the at least one to-be-delivered information belongs further includes:

determining a related object of the newly added object from the historical training objects under the condition that the object type is the newly added object;

and determining the object characteristic information of the associated object as the object information.

S807: determining price adjusting parameters corresponding to the object to which the at least one piece of information to be released belongs on the basis of the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be released belongs; and the price-adjusting parameter represents the preference degree of the target user for the at least one piece of information to be released.

In a specific embodiment, the determining, based on the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be delivered belongs, a price adjustment parameter corresponding to the object to which the at least one piece of information to be delivered belongs includes:

determining first associated information between the target user and an object to which each piece of information to be released belongs according to the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be released belongs;

acquiring user characteristic information of a preset user;

determining second associated information between the preset user and the object to which the information to be released belongs according to the user characteristic information of the preset user and the object characteristic information of the object to which the information to be released belongs;

acquiring a price range control parameter of the target release price;

and normalizing the first associated information based on the second associated information and the price range control parameter to obtain a price adjusting parameter corresponding to the object to which the at least one piece of information to be released belongs.

In a specific embodiment, the normalizing the first associated information based on the second associated information and the price range control parameter to obtain the price adjustment parameter corresponding to the object to which the at least one piece of information to be delivered belongs includes:

determining an average price adjustment parameter and a variance price adjustment parameter corresponding to the object to which the at least one to-be-released information belongs according to the second associated information;

and normalizing the first associated information according to the average price adjustment parameter, the variance price adjustment parameter and the price range control parameter to obtain the price adjustment parameter of the object to which each piece of information belongs.

S809: and determining a target release price corresponding to the at least one piece of information to be released based on the price adjusting parameter corresponding to the object to which the at least one piece of information to be released belongs and a preset reference release price.

S811: and determining target release information from the at least one piece of information to be released according to the target release price.

S813: and sending the target delivery information to the client so that the client delivers the target delivery information.

The embodiment of the present application further provides an information delivery server, where the information delivery server includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the information delivery method provided in the above method embodiment.

In the embodiment of the application, the information delivery request corresponding to the target user sent by the client is received, so that the server can conveniently determine the target delivery information to be delivered for the target user, and the efficiency of advertisement delivery is improved. The server side can effectively determine the association degree of the target user to the object to which the information to be released belongs according to the target user characteristic information of the target user and the object characteristic information of the object to which the at least one information to be released belongs, and determines the bid of the object to which the information to be released belongs to the target user according to the association degree. The server side inquires the target user characteristic information of the target user according to the user characteristic mapping information, and the advertisement putting efficiency is improved. The server side inquires the object characteristic information of the object to which the at least one piece of information to be delivered belongs according to the object characteristic information, so that the efficiency of advertisement delivery is improved. The target delivery information needing to be delivered to the target user is determined by the server according to the bid of the target user of each object to which the information to be delivered belongs, and the income-output ratio of the advertisement is favorably improved.

As shown in fig. 9, an embodiment of the present application further provides an information delivery method, which is applied to a client, and the method includes:

s901: sending an information delivery request corresponding to a target object to a server, wherein the information delivery request comprises a target user identifier of the target user;

s903: and receiving target delivery information determined by the server based on the target user identification, and delivering the target delivery information.

In the embodiment of the application, the client sends the information delivery request corresponding to the target user to the server, so that the server can determine the target delivery information to be delivered for the target user conveniently, and the efficiency of advertisement delivery is improved.

The embodiment of the present application further provides an information delivery client, where the information delivery client includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the information delivery method provided in the foregoing method embodiment.

As shown in fig. 10, an embodiment of the present application further provides an information delivery apparatus 1000, which is applied to an information delivery system, and the apparatus includes:

a first sending module 1001, configured to send, by a client, an information delivery request corresponding to a target user to a server, where the information delivery request includes a target user identifier of the target user;

a first determining module 1003, configured to determine, by the server, target user feature information of the target user based on the target user identifier;

a first obtaining module 1005, configured to obtain, by the server, object feature information of an object to which at least one piece of information to be delivered belongs;

a second determining module 1007, configured to determine, by the server, a price adjustment parameter corresponding to an object to which the at least one piece of information to be delivered belongs, based on the target user feature information and the object feature information of the object to which the at least one piece of information to be delivered belongs; the price-adjusting parameter represents the preference degree of the target user for the at least one piece of information to be released;

a third determining module 1009, configured to determine, by the server, a target release price corresponding to the at least one piece of information to be released based on the price adjustment parameter and a preset reference release price corresponding to the object to which the at least one piece of information to be released belongs;

a fourth determining module 1011, configured to determine, by the server, target delivery information from the at least one piece of information to be delivered according to the target delivery price;

a second sending module 1013, configured to send the target delivery information to the client by the server;

a delivering module 1015, configured to deliver the target delivery information by the client.

In some embodiments, the second determining module 1007 comprises:

a first determining unit, configured to determine, by the server, first association information between the target user and an object to which each piece of information to be delivered belongs according to the target user feature information and object feature information of the object to which the at least one piece of information to be delivered belongs;

the first acquisition unit is used for the server side to acquire the user characteristic information of a preset user;

a second determining unit, configured to determine, by the server, second association information between the preset user and an object to which the at least one piece of information to be delivered belongs according to the user feature information of the preset user and the object feature information of the object to which the at least one piece of information to be delivered belongs;

the second obtaining unit is used for obtaining the price range control parameter of the target release price by the server;

and the processing unit is used for the server side to perform normalization processing on the first associated information based on the second associated information and the price range control parameter to obtain a price adjusting parameter corresponding to the object to which the at least one piece of information to be released belongs.

In some embodiments, the processing unit comprises:

a determining subunit, configured to determine, by the server, an average price adjustment parameter and a variance price adjustment parameter corresponding to an object to which the at least one to-be-delivered information belongs according to the second associated information;

and the processing subunit is configured to perform normalization processing on the first associated information by the server according to the average price adjustment parameter, the variance price adjustment parameter and the price range control parameter, so as to obtain a price adjustment parameter of an object to which each piece of information belongs.

In some embodiments, the first obtaining module 1005 includes:

the acquiring subunit is used for the server to acquire the object identifier of the object to which the at least one piece of information to be released belongs;

a determining subunit, configured to determine, by the server, based on object feature mapping information, that object feature information corresponding to the object identifier is the object feature information; the object feature mapping information represents a mapping relation between at least one object identifier and corresponding object feature information.

In some embodiments, the apparatus comprises:

a fifth determining module, configured to determine, by the server, an object type of an object to which the at least one piece of information to be delivered belongs;

the second obtaining module is used for obtaining the object information of the object to which the at least one piece of information to be released belongs by the server according to the object type;

a sixth determining module, configured to determine, by the server, object feature information of an object to which the at least one piece of information to be delivered belongs according to the object information;

and the establishing module is used for establishing the object characteristic mapping information by the server according to the object identification and the object characteristic information.

In some embodiments, the second obtaining module includes:

a first determining unit, configured to, when the object type is a historical training object, determine, by the server, that object attribute information of the training object is the object information; wherein the historical training object is an object with historical conversion information.

In some embodiments, the second obtaining module further includes:

a second determining unit, configured to, when the object type is a historical non-training object, determine, by the server, a user associated with the historical non-training object from among the preset users; wherein the historical non-training object is an object without the historical conversion information;

a third determining unit, configured to determine, by the server, that the user feature information of the associated user is the object information.

In some embodiments, the second obtaining module further includes:

a fourth determining unit, configured to, when the object type is a new object, determine, by the server, an associated object of the new object from the historical training objects;

a fifth determining unit, configured to determine, by the server, that the object feature information of the associated object is the object information.

The device and method embodiments in the device embodiment described are based on the same inventive concept.

As shown in fig. 11, an information delivery apparatus 1100 is provided in the embodiment of the present application, and is applied to a server, where the apparatus includes:

a receiving module 1101, configured to receive an information delivery request corresponding to a target user sent by a client, where the information delivery request includes a target user identifier of the target user;

a first determining module 1103, configured to determine, based on the target user identifier, target user feature information of the target user;

a first obtaining module 1105, configured to obtain object feature information of an object to which at least one to-be-delivered information belongs;

a second determining module 1107, configured to determine, based on the target user characteristic information and object characteristic information of an object to which the at least one piece of information to be delivered belongs, a price adjustment parameter corresponding to the object to which the at least one piece of information to be delivered belongs; the price-adjusting parameter represents the preference degree of the target user for the at least one piece of information to be released;

a third determining module 1109, configured to determine, based on a price adjustment parameter and a preset reference launching price corresponding to an object to which the at least one piece of information to be launched belongs, a target launching price corresponding to the at least one piece of information to be launched;

a fourth determining module 1111, configured to determine target placement information from the at least one to-be-placed information according to the target placement price;

a sending module 1113, configured to send the target delivery information to the client, so that the client delivers the target delivery information.

In some embodiments, the second determining module 1107 comprises:

the first determining unit is used for determining first associated information between the target user and an object to which the information to be released belongs according to the target user characteristic information and the object characteristic information of the object to which the at least one information to be released belongs;

the first acquisition unit is used for acquiring user characteristic information of a preset user;

a second determining unit, configured to determine, according to the user feature information of the preset user and the object feature information of the object to which the at least one piece of information to be delivered belongs, second association information between the preset user and the object to which each piece of information to be delivered belongs;

a second obtaining unit, configured to obtain a price range control parameter of the target delivery price;

and the processing unit is used for carrying out normalization processing on the first associated information based on the second associated information and the price range control parameter to obtain a price adjusting parameter corresponding to the object to which the at least one piece of information to be released belongs.

In some embodiments, the processing unit comprises:

a determining subunit, configured to determine, according to the second correlation information, an average price adjustment parameter and a variance price adjustment parameter corresponding to an object to which the at least one to-be-delivered information belongs;

and the processing subunit is configured to perform normalization processing on the first associated information according to the average price adjustment parameter, the variance price adjustment parameter and the price range control parameter, so as to obtain a price adjustment parameter of an object to which each piece of information belongs.

In some embodiments, the first obtaining module 1105 includes:

the acquisition unit is used for acquiring an object identifier of an object to which the at least one piece of information to be released belongs;

the determining unit is used for determining object characteristic information corresponding to the object identification as the object characteristic information based on object characteristic mapping information; the object feature mapping information represents a mapping relation between at least one object identifier and corresponding object feature information.

In some embodiments, the above apparatus further comprises:

a fifth determining module, configured to determine an object type of an object to which the at least one to-be-delivered information belongs;

the second acquisition module is used for acquiring the object information of the object to which the at least one piece of information to be released belongs according to the object type;

a sixth determining module, configured to determine, according to the object information, object feature information of an object to which the at least one piece of information to be delivered belongs;

and the establishing module is used for establishing the object characteristic mapping information according to the object identification and the object characteristic information.

In some embodiments, the sixth determining module includes:

a first determining unit, configured to determine, when the object type is a historical training object, object attribute information of the training object as the object information; wherein the historical training object is an object with historical conversion information.

In some embodiments, the sixth determining module further includes:

a second determining unit, configured to determine, from the preset users, a user associated with a historical non-training object when the object type is the historical non-training object; wherein the historical non-training object is an object without the historical conversion information;

and the third determining unit is used for determining the user characteristic information of the associated user as the object information.

In some embodiments, the sixth determining module further includes:

a fourth determining unit, configured to determine, when the object type is a new object, an associated object of the new object from the historical training objects;

a fifth determining unit, configured to determine that the object feature information of the associated object is the object information.

As shown in fig. 12, an embodiment of the present application further provides an information delivery apparatus 1200, which is applied to a client, and the apparatus includes:

a sending module 1201, configured to send an information delivery request corresponding to a target object to a server, where the information delivery request includes a target user identifier of the target user;

a receiving module 1203, configured to receive target delivery information determined by the server based on the target user identifier, and deliver the target delivery information.

The embodiment of the present application further provides an information delivery device, where the device includes a processor and a memory, where the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the information delivery method provided by the above method embodiment.

The present application further provides a computer-readable storage medium, where at least one instruction, at least one program, a code set, or a set of instructions is stored in the storage medium, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to implement the information delivery method provided by the above method embodiment.

The storage medium in the described computer-readable storage medium embodiments and the method embodiments are based on the same inventive concept.

The present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the various alternative implementations described above.

The embodiment of the present application provides an information delivery server, where the data processing server includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the information delivery method provided by the above method embodiment.

The memory may be used to store software programs and modules, and the processor may execute various functional applications and data processing by operating the software programs and modules stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs needed by functions and the like; the storage data area may store data created according to use of the apparatus, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.

The method provided by the embodiment of the application can be executed in a mobile terminal, a computer terminal, a server or a similar operation device. Taking the example of running on a server, fig. 13 is a hardware structure block diagram of the server of the information delivery method provided in the embodiment of the present application. As shown in fig. 13, the server 1300 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 1310 (the processors 1310 may include but are not limited to Processing devices such as a microprocessor MCU or a programmable logic device FPGA), a memory 1330 for storing data, and one or more storage media 1320 (e.g., one or more mass storage devices) for storing applications 1323 or data 1322. The memory 1330 and the storage medium 1320 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 1320 may include one or more modules, each of which may include a series of instruction operations for the server. Further, the central processor 1310 may be configured to communicate with the storage medium 1320, and execute a series of instruction operations in the storage medium 1320 on the server 1300. The server 1300 may also include one or more power supplies 1360, one or more wired or wireless network interfaces 1350, one or more input-output interfaces 1340, and/or one or more operating systems 1321 such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

Input/output interface 1340 may be used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the server 1300. In one example, i/o Interface 1340 includes a Network adapter (NIC) that may be coupled to other Network devices via a base station to communicate with the internet. In one example, the input/output interface 1340 can be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.

It will be understood by those skilled in the art that the structure shown in fig. 13 is only an illustration and is not intended to limit the structure of the electronic device. For example, server 1300 may also include more or fewer components than shown in FIG. 13, or have a different configuration than shown in FIG. 13.

Embodiments of the present application further provide a storage medium, which may be disposed in a server to store at least one instruction, at least one program, a set of codes, or a set of instructions related to implementing an information delivery method in the method embodiments, where the at least one instruction, the at least one program, the set of codes, or the set of instructions is loaded and executed by the processor to implement the information delivery method provided by the above method embodiments.

Alternatively, in this embodiment, the storage medium may be located in at least one network server of a plurality of network servers of a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

As can be seen from the embodiments of the information delivery method, the information delivery device, the information delivery equipment, and the computer-readable storage medium provided by the present application, the information delivery request corresponding to the target user sent by the client is received in the present application, and the user characteristic information of the target user can be quickly determined according to the target user identifier carried in the information delivery request, so that the information delivery efficiency is improved. And then, according to the target user characteristic information and the object characteristic information of the object to which the at least one piece of information to be released belongs, the price adjusting parameter of the object to which the at least one piece of information to be released belongs is determined, and according to the price adjusting parameter and the preset reference releasing price, how to adjust the preset reference releasing price is accurately determined, so that the target releasing price of the object to which the at least one piece of information to be released belongs is obtained, and the accuracy of advertisement releasing and the income-output ratio are favorably improved. And according to the target release price of the object to which the at least one piece of information to be released belongs, the target release information can be accurately determined from the at least one piece of information to be released, and the target release information is sent to the client, so that the release of the target release information is realized. The target delivery information is delivered, so that the income-output ratio of advertisement delivery can be improved.

It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. An information delivery method, the method comprising:

2. The method according to claim 1, wherein the determining, based on the target user characteristic information and object characteristic information of an object to which the at least one piece of information to be delivered belongs, a price adjustment parameter corresponding to the object to which the at least one piece of information to be delivered belongs comprises:

acquiring user characteristic information of a preset user;

acquiring a price range control parameter of the target release price;

3. The method according to claim 2, wherein the normalizing the first associated information based on the second associated information and the price range control parameter to obtain the price adjustment parameter corresponding to the object to which the at least one piece of information to be delivered belongs comprises:

4. The method according to any one of claims 1 to 3, wherein the obtaining object feature information of an object to which at least one piece of information to be delivered belongs comprises:

5. The method according to claim 4, wherein before said obtaining object feature information of an object to which at least one information to be delivered belongs, the method further comprises:

6. The method according to claim 5, wherein the obtaining object information of an object to which the at least one to-be-delivered information belongs according to the object type comprises:

determining object attribute information of a historical training object as the object information under the condition that the object type is the historical training object; wherein the historical training object is an object with historical conversion information.

7. The method according to claim 6, wherein said obtaining object information of an object to which the at least one to-be-delivered information belongs according to the object type further comprises:

8. The method according to claim 6, wherein said obtaining object information of an object to which the at least one to-be-delivered information belongs according to the object type further comprises:

9. An information delivery apparatus, the apparatus comprising:

10. An information delivery apparatus, characterized in that the apparatus comprises a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the information delivery method according to any one of claims 1 to 8.