CN115705382A

CN115705382A - Information pushing method and device and storage medium

Info

Publication number: CN115705382A
Application number: CN202110923987.4A
Authority: CN
Inventors: 李少波
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-08-12
Filing date: 2021-08-12
Publication date: 2023-02-17

Abstract

The application discloses an information pushing method, an information pushing device and a storage medium, wherein after target pushing information is determined, a target conversion unit price of the target pushing information is obtained first, then a first historical conversion unit price, a first historical price adjusting coefficient and historical pushing consumption of the target pushing information are obtained, then a target price adjusting coefficient of the target pushing information is obtained according to the target conversion unit price, the first historical price adjusting coefficient and the historical pushing consumption, then a current exposure price of the target pushing information is determined according to the target price adjusting coefficient, and whether the target pushing information is pushed to a target consuming object set or not is determined according to the current exposure price. The method and the device can reasonably adjust the exposure price of the target push information, so that the conversion amount of the target push information can reach expectation. Therefore, the method and the device can be widely applied to the information pushing technology in the technical field of computers.

Description

Information pushing method and device and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to an information pushing method, an information pushing apparatus, and a storage medium.

Background

With the development of internet technology, the internet becomes one of the important ways for users to obtain information, for example, users can obtain various advertisement information pushed by information providers through an internet platform.

The click rate and the amount of conversion of information pushed to the internet platform may be affected by the exposure price set by the information provider for the information. If the exposure price set by the information provider is not reasonable, the exposure times of the information provided by the information provider can be reduced, so that the click rate and the conversion amount of the information are reduced, and the information provider cannot obtain the expected conversion amount of the information.

Disclosure of Invention

The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

The embodiment of the application provides an information push method, an information push device and a storage medium, which can reasonably adjust the exposure price of target push information, so that the conversion amount of the target push information can reach the expectation.

In one aspect, an embodiment of the present application provides an information pushing method, including the following steps:

determining target push information;

acquiring a target conversion unit price of the target push information;

acquiring a first historical conversion unit price, a first historical price adjustment coefficient and historical pushing consumption of the target pushing information, wherein the first historical conversion unit price is a conversion unit price at which the target pushing information is pushed to a target consuming object set in a target time period, the first historical price adjustment coefficient is a price adjustment coefficient at which the target pushing information is pushed to the target consuming object set in the target time period, the historical pushing consumption is pushing consumption at which the target pushing information is pushed to the target consuming object set in the target time period, and the target consuming object set is one of a plurality of sets obtained by classifying all consuming objects;

obtaining a target price adjusting coefficient of the target pushing information according to the target conversion unit price, the first historical price adjusting coefficient and the historical pushing consumption;

determining the current exposure price of the target pushing information according to the target price adjusting coefficient;

and determining whether to push the target push information to the target consumption object set or not according to the current exposure price.

On the other hand, an embodiment of the present application further provides an information pushing apparatus, including:

the information determining unit is used for determining target push information;

the first acquisition unit is used for acquiring a target conversion unit price of the target push information;

a second obtaining unit, configured to obtain a first historical conversion unit price, a first historical price adjustment coefficient, and a historical pushing consumption of the target pushing information, where the first historical conversion unit price is a conversion unit price at which the target pushing information is pushed to a target consuming object set in a target time period, the first historical price adjustment coefficient is a price adjustment coefficient at which the target pushing information is pushed to the target consuming object set in the target time period, the historical pushing consumption is a pushing consumption at which the target pushing information is pushed to the target consuming object set in the target time period, and the target consuming object set is one of multiple sets obtained by classifying all consuming objects;

a coefficient obtaining unit, configured to obtain a target price adjustment coefficient of the target pushing information according to the target conversion unit price, the first historical price adjustment coefficient, and the historical pushing consumption;

the price determining unit is used for determining the current exposure price of the target pushing information according to the target price adjusting coefficient;

and the information pushing unit is used for determining whether to push the target pushing information to the target consumption object set or not according to the current exposure price.

Optionally, the information pushing apparatus further includes:

the information acquisition unit is used for acquiring the consumption capability attribute information and the consumption group attribute information of all the consumption objects;

and the object classification unit is used for classifying all the consumption objects according to the consumption capability attribute information and the consumption group attribute information to obtain a plurality of consumption object sets.

Optionally, the consumption capability attribute information includes income level information, and the consumer group attribute information includes age information; the object classification unit includes:

the first classification unit is used for performing first classification processing on all the consumption objects according to the age information to obtain a first classification result;

and the second classification unit is used for performing second classification processing on the first classification result according to the income level information to obtain a plurality of consumption object sets.

Optionally, the consumption objects in the first classification result include a first class object and a second class object, the first class object has the income level information, and the second class object has historical consumption amount information and historical consumption quantity information; the second classification unit includes:

the first classification subunit is used for performing second classification processing on the first class of objects according to the income level information to obtain a first pre-classification result, and the first pre-classification result comprises a plurality of classifications;

a first determining unit, configured to determine, for each object to be classified in the second class of objects, multiple target objects in the first class of objects according to the historical consumption amount information and the historical consumption number information of the object to be classified, where a distance between the target object and the object to be classified is smaller than a first preset threshold;

a second determining unit configured to set, as a first target classification, one of the plurality of classifications that includes the largest number of target objects;

and the first classification unit is used for classifying the objects to be classified into the first target classification to obtain a plurality of consumption object sets.

Optionally, the first determining unit includes:

the first determining subunit is used for determining a plurality of first candidate objects in the first class of objects according to the historical consumption amount information of the objects to be classified, wherein the distance between the first candidate objects and the objects to be classified is smaller than a second preset threshold value;

a second determining subunit, configured to determine, according to the historical consumption number information of the object to be classified, a plurality of target objects in the plurality of first candidate objects, where the second preset threshold is greater than or equal to the first preset threshold.

Optionally, the first determining unit includes:

a third determining subunit, configured to determine, according to the historical consumption quantity information of the object to be classified, a plurality of second candidate objects in the first class of objects, where a distance between the second candidate object and the object to be classified is smaller than a third preset threshold;

a fourth determining subunit, configured to determine, according to the historical consumption amount information of the object to be classified, multiple target objects in the multiple second candidate objects, where the third preset threshold is greater than or equal to the first preset threshold.

Optionally, the consuming objects in the first classification result include a first class of objects and a third class of objects, the first class of objects having the income level information, the third class of objects not having the income level information; the second classification unit includes:

the second classification subunit is used for performing second classification processing on the first class of objects according to the income level information to obtain a second pre-classification result, and the second pre-classification result comprises a second target classification;

and the second classification unit is used for classifying the third class of objects into the second target classification to obtain a plurality of consumption object sets.

Optionally, the attribute information of the consumer group further includes at least one of region information, job level information or job type information; the second classification unit includes:

the third classification subunit is used for performing second classification processing on the first classification result according to the income level information to obtain a second classification result;

and the fourth classification subunit is configured to perform third classification processing on the second classification result according to at least one of the region information, the job level information, or the work type information, so as to obtain a plurality of consumption object sets.

Optionally, the coefficient acquiring unit includes:

the first obtaining subunit is configured to obtain a second historical conversion unit price and a second historical price adjustment coefficient of the target pushing information, where the second historical conversion unit price is a conversion unit price of the target pushing information pushed to all the consuming objects in the target time period, and the second historical price adjustment coefficient is a price adjustment coefficient of the target pushing information pushed to all the consuming objects in the target time period;

and the second obtaining subunit is configured to obtain the target price adjustment coefficient of the target pushing information according to the target conversion unit price, the first historical price adjustment coefficient, the historical pushing consumption, the second historical conversion unit price and the second historical price adjustment coefficient.

Optionally, the target time period is a time period from a first time before the current time to the current time in the current time cycle; the information push device further comprises:

and the coefficient maintaining unit is used for maintaining the target price adjusting coefficient for a second period, wherein the second period is a time period in the current time cycle except for the target period.

Optionally, the price determination unit includes:

the first calculating unit is used for calculating and obtaining a predicted conversion unit price of the target pushing information according to the target price adjusting coefficient and the target conversion unit price;

and the second calculating unit is used for calculating the current exposure price of the target pushing information according to the predicted conversion unit price.

Optionally, the information pushing unit includes:

the adjusting unit is used for adjusting the sequencing of the target push information in an information push sequence according to the current exposure price;

and the pushing unit is used for determining whether to push the target pushing information to the target consumption object set according to the sorting.

at least one processor;

at least one memory for storing at least one program;

when at least one of said programs is executed by at least one of said processors, an information push method as described above is implemented.

On the other hand, the embodiment of the present application further provides a computer-readable storage medium, in which a program executable by a processor is stored, and the program executable by the processor is used for implementing the information pushing method as described above when executed by the processor.

In another aspect, the present application further provides a computer program product or a computer program, where the computer program product or the computer program includes computer instructions, and the computer instructions are 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, so that the computer device executes the information pushing method as above.

After the target pushing information is determined, a target conversion unit price of the target pushing information is obtained first, then a first historical conversion unit price, a first historical price adjustment coefficient and historical pushing consumption of the target pushing information are obtained, and then the target price adjustment coefficient of the target pushing information is obtained according to the target conversion unit price, the first historical price adjustment coefficient and the historical pushing consumption, wherein the first historical conversion unit price, the first historical price adjustment coefficient and the historical pushing consumption are historical data of the target pushing information pushed to a target consumption object set in a target time period, and the target consumption object set is one of a plurality of sets obtained by classifying all consumption objects.

Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

The accompanying drawings are included to provide a further understanding of the claimed subject matter and are incorporated in and constitute a part of this specification, illustrate embodiments of the subject matter and together with the description serve to explain the principles of the subject matter and not to limit the subject matter.

FIG. 1 is a schematic illustration of an implementation environment provided by an embodiment of the present application;

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

FIG. 3 is a flowchart of a process for classifying all consumption objects according to an embodiment of the present application;

FIG. 4 is a flow chart of one particular method of step 140 of FIG. 2;

FIG. 5 is a flow chart of one particular method of step 220 of FIG. 3;

FIG. 6 is a flow diagram of one particular method of step 222 of FIG. 5;

FIG. 7 is a flowchart of one particular method of step 2222 of FIG. 6;

FIG. 8 is a flowchart of another specific method of step 2222 of FIG. 6;

FIG. 9 is a flow chart of another specific method of step 222 in FIG. 5;

FIG. 10 is a flow chart of one particular method of step 150 of FIG. 2;

FIG. 11 is a schematic diagram of an information pushing apparatus according to an embodiment of the present application;

fig. 12 is a schematic diagram of an information pushing apparatus according to another embodiment of the present application.

Detailed Description

The present application is further described with reference to the following figures and specific examples. The described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person skilled in the art without making any inventive step are within the scope of protection of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.

Before further detailed description of the embodiments of the present application, terms and expressions referred to in the embodiments of the present application will be described, and the terms and expressions referred to in the embodiments of the present application will be used for the following explanation.

1) The conversion means an operation intended by the information provider that the user performs based on the pushed information. For example, when the information provider is an application provider, the pushed information may be link information of an application, and accordingly, the operation expected by the information provider may be a registration operation and an activation operation of the application, and if the user performs a registration operation and an activation operation for the application based on the information pushed by the internet platform, it may be considered that a conversion is completed. For another example, when the information provider is a merchant in the e-commerce platform, the pushed information may be link information of the merchant, and correspondingly, the operation expected by the information provider may be an ordering operation performed in the merchant, and if the user performs an ordering operation in the merchant based on the information pushed by the internet platform, it may be considered that a conversion is completed.

2) The Cost Per Action (CPA), or unit Cost called conversion, refers to the ratio of the amount paid by the information provider for a certain pushed information to the amount of conversion obtained in a period of time. For example, assuming that an ad provider spends 1000 dollars in a day for the push of an ad, and a total of 10 conversions are obtained, the CPA of the ad is 100 dollars. A target CPA, alternatively referred to as an expected CPA of the information provider, refers to the average price of a single conversion given by the information provider over a period of time, e.g., the expected CPA set by a particular advertising provider for advertising during the day. The historical CPA refers to the CPA actually generated by the push information before the current time in the current time period. The predictive CPA is CPA which is possibly generated in future time after the current time in the current time period, and the aim of the predictive CPA is to enable the final actual conversion unit price of the push information not to exceed the target conversion unit price set by the information provider.

3) The adjustment factor, alternatively referred to as an adjustment factor, a calibration factor, etc., may be used to adjust the exposure price. The exposure price is reasonably adjusted by adjusting the price adjusting coefficient, so that the actual CPA of the pushed information does not exceed the target CPA of the information provider, and the cost requirement of the information provider is met. For example, the exposure price of an advertisement can be reasonably adjusted by adjusting the price adjustment factor so that the actual CPA of the advertisement can be maintained near the target CPA. The historical pricing factor refers to the average value of the pricing factors before the current time in the current time period. The target price adjusting coefficient is the price adjusting coefficient which enables the actual CPA of the pushed information not to exceed the target CPA of the information provider.

4) The exposure means that the push information is pushed or displayed, and the price required for pushing the push information once or displaying the push information once is the one-time exposure price. In some scenarios, for statistical purposes, the exposure price is typically expressed in terms of a price of a thousand pushes or a price of a thousand impressions, that is, the exposure price may be considered a fee to be paid for a thousand pushes of pushed information or a thousand impressions.

5) The push consumption refers to the fee paid by the information provider for pushing the push information, and therefore, the CPA of the push information may also be regarded as the ratio of the push consumption of the push information to the obtained conversion amount in a time period. The historical push consumption refers to the accumulated cost paid by the information provider for pushing the push information before the current time in the current time period.

6) The direct operation e-commerce is a merchant which does not have a sales platform and needs to conduct commodity direct operation in a third-party platform.

7) The block chain (Blockchain) is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. The blockchain is essentially a decentralized database, which is a string of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, which is used for verifying the validity (anti-counterfeiting) of the information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer. The block chain underlying platform can comprise processing modules such as user management, basic service, intelligent contract and operation monitoring. The user management module is responsible for identity information management of all blockchain participants, and comprises public and private key generation maintenance (account management), key management, user real identity and blockchain address corresponding relation maintenance (authority management) and the like, and under the authorization condition, the user management module supervises and audits the transaction condition of certain real identities and provides rule configuration (wind control audit) of risk control; the basic service module is deployed on all block chain node equipment and used for verifying the validity of the service request, recording the service request to storage after consensus on the valid request is completed, for a new service request, the basic service firstly performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts service information (consensus management) through a consensus algorithm, transmits the service information to a shared account (network communication) completely and consistently after encryption, and performs recording and storage; the intelligent contract module is responsible for registering and issuing contracts, triggering the contracts and executing the contracts, developers can define contract logics through a certain programming language, issue the contract logics to a block chain (contract registration), call keys or other event triggering and executing according to the logics of contract clauses, complete the contract logics and simultaneously provide the function of upgrading and canceling the contracts; the operation monitoring module is mainly responsible for deployment, configuration modification, contract setting, cloud adaptation in the product release process and visual output of real-time states in product operation, such as: alarm, monitoring network conditions, monitoring node equipment health status, and the like. The platform product service layer provides basic capability and an implementation framework of typical application, and developers can complete block chain implementation of business logic based on the basic capability and the characteristics of the superposed business. The application service layer provides the application service based on the block chain scheme to the business participants for use.

With the development of internet technology, the internet has become one of important ways for users to acquire information, for example, users can acquire information through advertisements distributed in the internet. The information provider can push various information to the Internet platform through the information pushing system, so that the user can obtain various information through the Internet platform. A typical application of information push is advertisement push, and whether it is an internet product or a physical product, there is a demand for pushing advertisements on an internet platform to attract users. For the internet platform, information of interest is pushed to the user, so that profits can be obtained, and the user viscosity can be improved to a certain extent. At present, an information push system generally pushes information provided by an information provider to an internet platform in a bid sorting manner, wherein the push sorting of the information to be pushed to the internet platform in the information push system is influenced by an exposure price set by the information provider. If the exposure price set by the information provider is not reasonable, the exposure times of the information provided by the information provider can be reduced, so that the click rate and the conversion amount of the information are reduced, and the information provider cannot obtain the expected conversion amount of the information.

In order to reasonably adjust the exposure price of the target push information so that the conversion amount of the target push information can reach the expectation, the embodiment of the application provides an information push method, an information push device and a computer readable storage medium, after the target push information is determined, the target conversion unit price of the target push information is obtained, then the first historical conversion unit price, the first historical price adjustment coefficient and the historical push consumption of the target push information are obtained, and then the target price adjustment coefficient of the target push information is obtained according to the target conversion unit price, the first historical price adjustment coefficient and the historical push consumption, wherein the first historical price adjustment coefficient, the first historical price adjustment coefficient and the historical push consumption are historical data of the target push information pushed to a target consumption object set in a target period, and the target consumption object set is one of a plurality of sets obtained by classifying all consumption objects, so that the target price adjustment coefficient can be more adapted to the target consumption object set, so that the current price of the target push information can reach the expected conversion amount of the target push information, and the target push information can reach the expected exposure amount.

Fig. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application. Referring to fig. 1, the implementation environment includes a server 101 and an internet platform 102, wherein the server 101 and the internet platform 102 are communicatively connected.

The server 101 may be an independent physical server, 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 Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like. In addition, the server 101 may also be a node in a blockchain.

The server 101 may be integrated with an information push function, or an information push apparatus for implementing the information push function may be disposed in the server 101.

The server 101 at least has functions of calculating a target price adjustment coefficient of the target push information, calculating an exposure price according to the target price adjustment coefficient, and determining whether to push the target push information to the target consuming object set according to the exposure price, for example, when the target conversion unit price of the target push information is obtained, a first historical conversion unit price, a first historical price adjustment coefficient, and historical push consumption of the target push information are obtained, then the target price adjustment coefficient of the target push information is obtained by calculation according to the target conversion unit price, the first historical price adjustment coefficient, and the historical push consumption, then the current exposure price of the target push information is determined according to the target price adjustment coefficient, and then whether to push the target push information to the target consuming object set is determined according to the current exposure price.

The internet platform 102 may be any internet application platform such as an e-commerce platform, a page browsing platform, a payment platform, a social platform, a content interaction platform, an education platform, and a video sharing platform. The internet platform 102 can receive the push information from the server 101 and present the push information to the user or push the push information to the user.

In an optional implementation manner, in response to receiving a target conversion unit price of a target advertisement sent by an advertiser, the server 101 obtains a first historical conversion unit price, a first historical price adjustment coefficient, and historical pushing consumption of the target advertisement, calculates a target price adjustment coefficient of the target advertisement according to the target conversion unit price, the first historical price adjustment coefficient, and the historical pushing consumption, determines a current exposure price of the target advertisement according to the target price adjustment coefficient, and determines whether to push the target advertisement to a target consumption object set according to the current exposure price. When the server 101 determines to push the targeted advertisement to the set of targeted consumption objects, the server 101 pushes the targeted advertisement to the internet platform 102, and in response to receiving the targeted advertisement, the internet platform 102 presents the targeted advertisement to the set of targeted consumption objects.

Fig. 2 is a flowchart of an information pushing method according to an embodiment of the present application. In the present embodiment, a server is taken as an example of an execution subject. Referring to fig. 2, the information push method includes, but is not limited to, steps 110 to 160.

Step 110: and determining target push information.

In this step, the target push information is push information for which the information provider desires to adjust the exposure price. When the actual conversion unit price of a certain piece of pushed information does not meet the expectation of the information provider, the information provider can send a price adjusting request for the pushed information to the server, and after the server receives the price adjusting request, the server can determine target pushed information according to the price adjusting request, so that the exposure price of the target pushed information can be adjusted in subsequent steps, and the conversion amount of the target pushed information can reach the expectation of the information provider.

It should be noted that the target push information may be of various types, for example, the target push information may be advertisement information, download link information of an application, link information of a web page, and the like, which is not limited in this embodiment.

Step 120: and acquiring the target conversion unit price of the target push information.

In this step, since the target push information is determined in step 110, the target conversion unit price of the target push information may be obtained, so that the exposure price of the target push information may be adjusted according to the target conversion unit price in the subsequent step, so that the conversion amount of the target push information can reach the expectation of the information provider.

It should be noted that, different embodiments may be used for obtaining the target conversion unit price of the target push information, and this embodiment is not particularly limited to this. For example, after determining the target push information in step 110, the server may further obtain a target conversion unit price of the target push information from the information provider; for another example, the price adjustment request sent by the information provider to the server may include identification information of the target push information and a target conversion unit price, and the server may determine the target push information according to the identification information and obtain the target conversion unit price of the target push information from the price adjustment request.

Step 130: and acquiring a first historical conversion unit price, a first historical price adjustment coefficient and historical pushing consumption of the target pushing information.

In this step, since the target push information is determined in step 110 and the target conversion unit price is obtained in step 120, the first historical conversion unit price, the first historical price adjustment coefficient and the historical push consumption of the target push information may be obtained, so that the exposure price of the target push information may be adjusted according to the target conversion unit price, the first historical price adjustment coefficient and the historical push consumption in the subsequent steps, so that the conversion amount of the target push information can reach the expectation of the information provider.

It should be noted that the first historical conversion unit price is a conversion unit price at which the target push information is pushed to the target consumption object set in the target time period, the first historical price adjustment coefficient is a price adjustment coefficient at which the target push information is pushed to the target consumption object set in the target time period, and the historical push consumption is push consumption at which the target push information is pushed to the target consumption object set in the target time period, where the target consumption object set is one of multiple sets obtained by classifying all consumption objects.

It should be noted that the target time period may be any time period before the current time, may also be a certain time period before the current time in the current time cycle, and may also be a time period between a first time before the current time in the current time cycle and the current time, which may be appropriately selected according to an actual application situation, and this embodiment is not particularly limited to this. The time period refers to a period of information push, and may be a day, a week, a month, or the like, and may be appropriately selected according to the actual application, which is not specifically limited in this embodiment.

In an alternative embodiment, as shown in fig. 3, the classification process is performed on all the consumption objects, which may include, but is not limited to, step 210 and step 220.

Step 210: and acquiring the consumption capability attribute information and the consumption group attribute information of all the consumption objects.

It should be noted that the consumption capability attribute information may include income level information, social rank information, and the like, and this embodiment does not specifically limit this. The attribute information of the consumer group may include age information, region information, job level information, or job type information, which is not limited in this embodiment.

Step 220: and classifying all the consumption objects according to the consumption capability attribute information and the consumption group attribute information to obtain a plurality of consumption object sets.

It should be noted that, since the consumption capability attribute information and the consumption group attribute information of all the consumption objects are obtained in step 210, all the consumption objects can be classified according to the consumption capability attribute information and the consumption group attribute information to obtain a plurality of consumption object sets, so that information such as conversion unit price, price adjustment coefficient, pushing consumption and the like corresponding to each consumption object set can be stored, and the price adjustment processing of pushing information can be performed on each consumption object set in subsequent steps.

Step 140: and obtaining a target price adjusting coefficient of the target pushing information according to the target conversion unit price, the first historical price adjusting coefficient and the historical pushing consumption.

In this step, since the target conversion unit price of the target push information is obtained in step 120, and the first historical conversion unit price, the first historical price adjustment coefficient, and the historical push consumption of the target push information are obtained in step 130, the target price adjustment coefficient of the target push information can be obtained according to the target conversion unit price, the first historical price adjustment coefficient, and the historical push consumption, so that the exposure price of the target push information can be adjusted according to the target price adjustment coefficient in the subsequent steps, and the conversion amount of the target push information can reach the expectation of the information provider.

It should be noted that the conversion unit price of the pushed information may be calculated according to a conversion unit price formula (a specific conversion unit price formula will be given in the following embodiments), where a first historical conversion unit price, a first historical price adjustment coefficient, historical pushing consumption, and a current price adjustment coefficient of the pushed information are all input parameters in the conversion unit price formula, and the conversion unit price of the pushed information is an output result in the conversion unit price formula, and since the target conversion unit price of the target pushed information is obtained in step 120, the target conversion unit price may be substituted into the output result in the conversion unit price formula, and then the target price adjustment coefficient of the target pushed information is obtained by reverse calculation.

Step 150: and determining the current exposure price of the target push information according to the target price adjusting coefficient.

In this step, since the target price adjustment coefficient of the target push information is obtained in step 140, the current exposure price of the target push information can be determined according to the target price adjustment coefficient. Since the current exposure price is determined according to the historical data of the target push information pushed to the target consumption object set in the target time period and the target conversion unit price of the target push information, the current exposure price can be more adaptive to the target consumption object set, so that the conversion amount of the target push information can reach the expectation of the information provider under the condition that the target push information is pushed according to the current exposure price.

Step 160: and determining whether to push target push information to the target consumption object set or not according to the current exposure price.

In this step, since the current exposure price of the target push information is obtained in step 150, it can be determined whether to push the target push information to the target consumption object set according to the current exposure price. Since the current exposure price can be more adaptive to the target consumption object set, the conversion amount of the target push information can reach the expectation of the information provider under the condition that the target push information is pushed according to the current exposure price.

It should be noted that the server pushes the information provided by the information provider to the internet platform in a bidding sorting manner, and different pushing information providers can provide different pushing information, and the same information provider can also provide different pushing information, so that different pushing information has different pushing sorting according to the corresponding exposure price. In this embodiment, since the current exposure price of the target push information is adjusted according to the target price adjustment coefficient, the current exposure price may affect the push ordering of the target push information, and therefore, after the current exposure price of the target push information is determined, the target push information and other push information need to be reordered, so as to determine whether to push the target push information to the target consumption object set according to a result of the reordering.

In this embodiment, by using the information pushing method including the foregoing steps 110 to 160, after the target pushing information is determined, the target conversion unit price of the target pushing information is obtained, then the first historical conversion unit price, the first historical price adjustment coefficient and the historical pushing consumption of the target pushing information are obtained, and then the target price adjustment coefficient of the target pushing information is obtained according to the target conversion unit price, the first historical price adjustment coefficient and the historical pushing consumption, where the first historical conversion unit price, the first historical price adjustment coefficient and the historical pushing consumption are all historical data of the target pushing information pushed to the target consuming object set in the target time period, and the target consuming object set is one of multiple sets obtained by classifying all consuming objects, so that the target price adjustment coefficient can be more adapted to the target consuming object set, and therefore, the current exposure price of the target pushing information is determined according to the target price adjustment coefficient, and the purpose of reasonably adjusting the exposure price of the target pushing information can be achieved, so that the pushing conversion amount of the target pushing information can reach the expected amount.

Referring to fig. 4, for an embodiment of the present application, step 140 is further described, and step 140 may include, but is not limited to, the following steps:

step 141: acquiring a second historical conversion unit price and a second historical price adjustment coefficient of the target pushing information;

step 142: and obtaining a target price adjusting coefficient of the target pushing information according to the target conversion unit price, the first historical price adjusting coefficient, the historical pushing consumption, the second historical conversion unit price and the second historical price adjusting coefficient.

It should be noted that the second historical conversion unit price is a conversion unit price at which the target push information is pushed to all the consumption objects in the target time period, and the second historical price adjustment coefficient is a price adjustment coefficient at which the target push information is pushed to all the consumption objects in the target time period.

It should be noted that the target time period is a time period from a first time before the current time to the current time in the current time cycle. For example, assuming that the current time period is one day, and the current time is 10 hours, the first time is 0 hours, then the target period is a period from 0 hours to 10 hours.

In the conversion unit price formula, the second historical conversion unit price and the second historical price adjustment coefficient of the target push information are also input parameters in the conversion unit price formula, and therefore, after the second historical conversion unit price and the second historical price adjustment coefficient of the target push information are obtained in step 141, the target price adjustment coefficient of the target push information can be obtained through calculation according to the target conversion unit price, the first historical price adjustment coefficient, the historical push consumption, the second historical conversion unit price and the second historical price adjustment coefficient.

The principle process of calculating the target adjustment coefficient is described in detail below with a specific example.

For a certain advertisement, the conversion unit price in one day can be calculated by formula (1):

wherein, CPA _final Is that the advertisement is within one dayTotal conversion unit price, cost _h Is the total push consumption, cost, of the advertisement before the current time of the day _e Is the total push consumption, conv, of the advertisement after the current time of day _h Is the total conversion, conv, of the advertisement prior to the present time of day _e Is the total conversion of the ad after the current time of day. Adjusting the price of the advertisement, namely adjusting cost by adjusting the price adjusting coefficient at the current moment _e And conv _e To enable the CPA _final As close as possible to the targeted conversion unit price set by the advertiser.

On the basis of the formula (1), the formula (2) can be obtained by decomposing the formula (1) as follows:

wherein:

in the formula (2), CPA _h Is the second historical conversion unit price, CPA, of the advertisement _e Is the future conversion unit price after the adjustment of the target price adjustment coefficient. Assuming that the conversion unit price varies linearly with the adjustment coefficient, the following formula (3) can be obtained:

where λ is the tuning coefficient to be solved, λ _h Is the second historical pricing factor, CPA _1.0 Is the conversion unit price of the time period after the current time in the day under the condition of no price adjustment (namely the price adjustment coefficient is 1).

Substituting equation (3) into equation (2) yields the following equation (4):

at this time, ω can be subjected to conversion processing, thereby simplifying equation (4). Wherein, the conversion processing of ω includes the pair of conv _e And conv _h The conversion treatment of the ratio of (a) to (b) is specifically as follows:

wherein:

wherein, conv _λ，e Is the future conversion amount after the adjustment of the target price-adjusting coefficient,

is the historical conversion amount, cost, after the adjustment of the second historical price adjustment coefficient _λ，e Is the future push consumption after the adjustment of the target price adjustment coefficient,

is the historical push consumption, cost, after the adjustment of the second historical price adjustment coefficient _1.0，e Is the future push consumption without price adjustment (i.e. the price adjustment coefficient is 1), cost _1.0，h Is the historical push consumption without a price adjustment (i.e. a price adjustment factor of 1), where g (t) is a time-dependent function only, in particular g (t) =3.314E ^-7 t ² +0.000218t；f(λ)＝λ ^β ，f(λ _h )＝λ _h ^β ，β＝2.5。

By substituting the result obtained by performing the conversion process on ω into equation (4), the following equation (5) can be obtained:

wherein x = λ/λ _h ，α＝g(t)。

For equation (5), CPA _final And (4) the target conversion unit price is equal to, and the formula (5) is solved, so that the value of lambda can be obtained.

It should be noted that formula (5) is directed to all consumption object oriented advertisements, and the current cost of the whole advertisement is monitored, and the adjusting price coefficient is adjusted in real time to control the future cost of the advertisement, so that the current cost of the advertisement can be controlled within the expectation.

However, the above-mentioned price-adjusting process is directed to advertisements targeted to all consumption objects, and for some advertisements, the conversion unit price on some consumption objects may be low, and the low conversion unit price may result in that the exposure price of the advertisement is low, thereby affecting the competitiveness of the advertisement in bid sorting, and when the competitiveness of the advertisement in bid sorting is reduced, the advertisement may be difficult to be determined as information to be pushed, thereby reducing the exposure times of the advertisement, causing the conversion amount of the advertisement to be reduced, and further causing the advertiser not to obtain the expected conversion amount of the advertisement. According to research and analysis, the problem occurs because different consumers have different interests in different advertisements, and the click rate and purchase desire of the consumers for the advertisements are influenced by the interest, and further the conversion amount of the advertisements is influenced. In order to solve the problem, the consumption objects can be classified, and then the price adjusting coefficient of the advertisement aiming at the consumption object group is properly improved aiming at the consumption object group causing the low conversion unit price of the advertisement, and the exposure price of the advertisement is improved, so that the advertisement can be exposed to the consumption object group as much as possible, and the advertiser can obtain the expected conversion amount on the advertisement.

In order to reasonably classify the consumption objects, specific classification criteria need to be determined according to a specific application scenario, for example, for an application scenario of direct operation and power business, the consumption objects may be classified according to their ages and historical purchase levels. Through research and analysis, from the qualitative perspective, the ages of the consumers are closely related to the corresponding purchasing habits, and the online shopping accounts for a large number of consumers with larger ages by using the online shopping application program are small, so that the commodity direct-marketing mode of direct-marketing e-commerce has certain attraction to the part of consumer groups. From a quantitative point of view, consumption subjects of different age groups will have different consumption abilities. As shown in table 1 below, table 1 is a data analysis table of the purchase amount and the number of purchases made by consumers of different ages in a certain period of time on the direct marketing company.

TABLE 1

In table 1, the purchase amount and the number of purchased items are desensitized, and the larger the value is, the larger the purchase amount is; the larger the numerical value, the larger the number of purchases.

As can be seen from table 1, the interest levels of consumers of different ages in the direct marketing and advertising mode are greatly different, and if consumer groups are not distinguished in the pricing adjusting process, pricing cannot be performed according to the characteristics of different consumer groups, which may result in that the conversion amount of advertisements cannot be expected. If price adjustment is respectively carried out for different consumption object groups, the exposure of corresponding advertisements can be properly increased on the part of consumption object groups which are more interested by the direct-operation power provider, so that the overall advertisement putting effect can be improved.

Since the consumption objects are classified, each advertisement may correspond to a price adjustment coefficient on each type of consumption object set (i.e. consumption object group), so the above formula (2) can be adjusted to formula (6):

wherein:

wherein, g _p (t) is a function which is time dependent only, in particular, g _p (t)＝3.314E ^-7 t ² +0.000218t；f(λ _p )＝λ _p ^β ，f(λ _h )＝λ _h ^β β =2.5; ω is the historical CPA weight; n is the number of categories of the set of consumption objects; omega _p Is the weight of the p-th class consumption object set; lambda [ alpha ] _p Is the price adjustment coefficient of the p-th consumption object set to be solved (i.e. the target price adjustment coefficient of the embodiment); lambda [ alpha ] _hp Is the historical price adjustment coefficient of the pth consumption object set (i.e. the first historical price adjustment coefficient of the embodiment); CPA _hp Is the historical conversion unit price of the p-th type consumption object set (i.e. the first historical conversion unit price of the embodiment); cost _hp Is the historical consumption of the p-th class consumption object set (i.e. the historical push consumption of the present embodiment);

the future push consumption aiming at the p-th class consumption object set after the adjustment of the target price adjustment coefficient.

Therefore, for equation (6), CPA is applied _final Equal to the target conversion unit price, and solving the formula (6) to obtain the lambda _p The value of (c).

When adjusting the target pricing factor for the pth consumption object set, the pricing factors of other consumption object sets remain unchanged, that is, when adjusting the exposure price of the target advertisement for the pth consumption object set, the exposure price of the same target advertisement corresponding to other consumption object sets remains unchanged.

After the target price adjusting coefficient aiming at the p-th class consumption object set is obtained through the formula calculation, the current exposure price of the target advertisement can be determined according to the target price adjusting coefficient, and the conversion amount of the target advertisement can reach the expectation of an advertiser under the condition that the target advertisement is pushed according to the current exposure price. After certain experimental observation, the consumption and the achievement rate of the target advertisement can be improved, wherein the consumption of the target advertisement is improved by about 6%, and the achievement rate of the target advertisement is improved by about 7%. However, certain data analysis shows that in some cases, the price adjustment coefficient corresponding to some consumption object sets is unstable, thereby causing unstable cost for the consumption object sets. This unstable situation is mainly manifested by: underestimation occurs in a certain time period, so that the cost is low, and the price adjusting coefficient needs to be adjusted upwards at the moment; and overestimation occurs in another time period, which results in higher cost, and the price adjustment coefficient needs to be adjusted downward. Thus, the price adjusting coefficient is unstable in oscillation. Through research and analysis, one of the reasons for the problem is found to be that the conversion intention of the consumption object set aiming at the advertisement of the direct-operated power provider is unstable. In this situation, research and analysis show that there is a large gap in the purchasing power of consumers with different income levels. As shown in table 2, table 2 is a data analysis table of income levels for consumers in the age range of 50 to 55 years.

TABLE 2

Income level (desensitization treatment already)	Purchase amount (desensitization treatment already)	Number of purchases (desensitized treatment already)
			The income level is lower	0.12	0.17
Moderate income level	0.56	0.62
			The income level is higher	0.31	0.27
High income level	0.25	0.20

In table 2, the income level, the purchase amount, and the number of purchased items are desensitized, and in the purchase amount, the larger the value is, the larger the purchase amount is; the larger the numerical value, the larger the number of purchases.

As can be seen from table 2, there is a large difference in purchasing power between consumers with different income levels, and if this difference is ignored, the exposure effect of the advertisement will have a large difference between different consumers, and the price adjustment coefficient will be unstable, which will affect the price adjustment effect. In order to solve the problem, in an embodiment of the present application, all consumption objects are classified according to income level information and age information to obtain a plurality of consumption object sets which are properly classified, then, for each consumption object set, a target price adjustment coefficient corresponding to each consumption object set is respectively determined, and then, according to the target price adjustment coefficient corresponding to each consumption object set, a current exposure price of each piece of target push information pushed to each consumption object set is determined, so that under the condition that each piece of target push information is pushed according to the current exposure price of each piece of target push information, a conversion amount of each piece of target push information can reach an expectation of an information provider.

Various embodiments of specific methods of classifying all consumption objects are presented below.

Referring to fig. 5, in an embodiment, further describing step 220, in the case that the consuming capacity attribute information includes income level information and the consuming group attribute information includes age information, step 220 may include, but is not limited to, step 221 and step 222.

Step 221: and performing first classification processing on all the consumption objects according to the age information to obtain a first classification result.

In this step, under the condition that the consumption capability attribute information includes income level information and the consumer group attribute information includes age information, first classification processing may be performed on all the consumers according to the age information to obtain a first classification result, so that the subsequent step may perform further classification processing on the first classification result according to the income level information on the basis of the first classification result, and the final classification result may be more appropriate.

The first classification process may be performed on all the consumption subjects according to age information, and may be performed for each year of the age or for each age group, which is not particularly limited in this embodiment. For example, all the consumption objects may be classified into 10 categories according to age information with reference to the age layer classification of the foregoing table 1, resulting in a first classification result.

Step 222: and performing second classification processing on the first classification result according to the income level information to obtain a plurality of consumption object sets.

In this step, since the first classification result based on the age information is obtained in step 221, the first classification result may be further subjected to second classification processing according to the income level information to obtain a plurality of consumption object sets, so that the subsequent steps may respectively and reasonably adjust prices of the target push information for each consumption object set, and the conversion amount of the target push information can reach an expectation.

It should be noted that, the second classification processing is performed on the first classification result according to the income level information, and the classification may be performed according to different income level magnitudes, for example, according to magnitudes of thousands, tens of thousands, hundreds of thousands, and the like; alternatively, the classification may be performed according to a specific income level, for example, 3000 yuan to 6000 yuan is one class, 7000 yuan to 10000 yuan is one class, and the like, and this embodiment is not particularly limited thereto.

In an alternative embodiment, the first classification result may be classified into 4 classes according to the income level information, and the specific classification is shown in table 3 below.

TABLE 3

Income level (desensitization treatment already)	Income level classification
		0 to 0.25	The income level is lower
0.25 to 0.5	Moderate income level
		0.5 to 0.75	The income level is higher
0.75 to 1	High income level

It should be noted that the income level information in table 3 has been desensitized, and in the income level information, the larger the value, the higher the income level.

In this embodiment, all the consumption objects are classified according to the age information and the income level information, so that a more appropriate classification result can be obtained, and the target push information can be reasonably adjusted according to each consumption object set in the subsequent step, so that the conversion amount of the target push information can reach an expectation.

Although all the consumers can be classified according to age information and income level information, in some cases, income level information of the consumers cannot be acquired, and thus, the second classification process cannot be performed on the first classification result according to the income level information. For the problem, through research and analysis, the income level of the consumer can be classified by using the historical consumption amount information and the historical consumption quantity information of the consumer.

Various embodiments of classifying revenue levels for consuming objects using historical spending amount information and historical spending amount information for consuming objects are presented below.

Referring to fig. 6, in an embodiment, further describing step 222, in the case that the consumption objects in the first classification result include a first class object and a second class object, wherein the first class object has income level information, historical consumption amount information and historical consumption amount information, and the second class object has historical consumption amount information and historical consumption amount information but does not have income level information, step 222 may include, but is not limited to, step 2221 through step 2224.

Step 2221: and carrying out second classification processing on the first class of objects according to the income level information to obtain a first pre-classification result, wherein the first pre-classification result comprises a plurality of classifications.

In this step, because the first-class object has the income level information, the first-class object may be subjected to the second classification processing according to the income level information to obtain a first pre-classification result, so that the subsequent step may be performed with the second-class object on the basis of the first pre-classification result, thereby achieving the purpose of performing the second classification processing on the first-class object according to the income level information to obtain a plurality of consumption object sets.

It should be noted that, the second classification processing is performed on the first class object according to the income level information, and the first pre-classification result can be obtained by referring to the division manner in table 3 and dividing the first class object into 4 classes according to the income level information.

Step 2222: and for each object to be classified in the second class of objects, determining a plurality of target objects in the first class of objects according to the historical consumption amount information and the historical consumption quantity information of the object to be classified, wherein the distance between each target object and the object to be classified is smaller than a first preset threshold value.

In this step, for the second class objects having the historical consumption amount information and the historical consumption number information but not having the income level information, the classification processing of each object to be classified in the second class objects can be performed by using the data of two dimensions, namely the historical consumption amount information and the historical consumption number information, and adopting a K-nearest neighbor (KNN) classification algorithm. Specifically, for each object to be classified in the second class of objects, a plurality of target objects whose distance from the object to be classified is smaller than a first preset threshold may be determined in the first class of objects according to the historical consumption amount information and the historical consumption number information of the object to be classified, so that the subsequent step may classify the object to be classified according to the target objects.

It should be noted that, different embodiments may be used to determine a plurality of target objects in the first class of objects according to the historical consumption amount information and the historical consumption number information of the objects to be classified, and this embodiment is not limited in this respect. For example, a plurality of candidate objects in the first class of objects may be determined according to the historical consumption amount information, and then a plurality of target objects whose distance from the object to be classified is smaller than a first preset threshold value may be determined in the candidate objects according to the historical consumption amount information; for another example, a plurality of candidate objects may be determined in the first class of objects according to the historical consumption amount information, and then a plurality of target objects whose distance from the object to be classified is smaller than the first preset threshold may be determined in the candidate objects according to the historical consumption amount information.

It should be noted that the first preset threshold may be appropriately selected according to the actual application, and this embodiment is not particularly limited to this.

Step 2223: and taking one of the plurality of classifications with the largest number of target objects as a first target classification.

In this step, since the first pre-classification result includes multiple classifications, and multiple target objects are determined in step 2222, one of the classifications that includes the largest number of target objects can be used as the first target classification, so that the subsequent step can classify the object to be classified into the first target classification, thereby implementing classification processing on the second class of objects. For example, assuming that there are 100 target objects identified in the first category of objects, wherein there are 20 target objects belonging to a low income level, 50 target objects belonging to a medium income level, and 30 target objects belonging to a high income level, then this category of medium income level may be used as the first target category.

Step 2224: and classifying the objects to be classified into a first target classification to obtain a plurality of consumption object sets.

In this step, since the first target classification is determined in step 2223, the object to be classified may be classified into the first target classification to obtain a plurality of consumption object sets, so that the subsequent steps may respectively and reasonably adjust prices of the target push information for each consumption object set, and the conversion amount of the target push information can reach an expectation.

Referring to FIG. 7, in an embodiment, step 2222 is further described, and step 2222 may include, but is not limited to, the following steps:

step 22221: determining a plurality of first candidate objects in the first class of objects according to historical consumption amount information of the objects to be classified, wherein the distance between the first candidate objects and the objects to be classified is smaller than a second preset threshold value;

step 22222: and determining a plurality of target objects in the plurality of first candidate objects according to the historical consumption quantity information of the objects to be classified, wherein the second preset threshold is greater than or equal to the first preset threshold.

In this embodiment, in the process of determining a plurality of target objects in the first class of objects according to the historical consumption amount information and the historical consumption number information of the objects to be classified, a plurality of first candidate objects may be determined in the first class of objects by using the historical consumption amount information of the objects to be classified and the KNN classification algorithm, and then a plurality of target objects may be determined in the first candidate objects by using the historical consumption number information of the objects to be classified and the KNN classification algorithm again.

For example, in an alternative embodiment, 200 first candidate objects may be determined in the first class of objects by using the historical spending amount information of the objects to be classified and the KNN classification algorithm, and then 100 target objects may be determined in the 200 first candidate objects by using the historical spending amount information of the objects to be classified and the KNN classification algorithm again.

It should be noted that the second preset threshold may be appropriately selected according to the actual application, and this embodiment is not particularly limited to this.

Referring to fig. 8, in an embodiment, step 2222 is further described, and step 2222 may further include, but is not limited to, the following steps:

step 22223: determining a plurality of second candidate objects in the first class of objects according to the historical consumption quantity information of the objects to be classified, wherein the distance between the second candidate objects and the objects to be classified is smaller than a third preset threshold value;

step 22224: and determining a plurality of target objects in the plurality of second candidate objects according to the historical consumption amount information of the objects to be classified, wherein the third preset threshold value is greater than or equal to the first preset threshold value.

It should be noted that step 22223 and step 22224 in this embodiment belong to parallel technical solutions with step 22221 and step 22222 in the embodiment shown in fig. 7.

In this embodiment, in the process of determining a plurality of target objects in the first class of objects according to the historical consumption amount information and the historical consumption number information of the objects to be classified, a plurality of second candidate objects may be determined in the first class of objects by using the historical consumption number information of the objects to be classified and the KNN classification algorithm, and then a plurality of target objects may be determined in the second candidate objects by using the historical consumption amount information of the objects to be classified and the KNN classification algorithm again.

For example, in an alternative embodiment, 150 second candidate objects may be determined in the first class of objects by using the historical consumption amount information of the objects to be classified and the KNN classification algorithm, and then 100 target objects may be determined in the 150 second candidate objects by using the historical consumption amount information of the objects to be classified and the KNN classification algorithm again.

It should be noted that the third preset threshold may be appropriately selected according to the actual application, and this embodiment is not particularly limited to this.

In the foregoing embodiments, the method steps of classifying the income level of the consuming object by using the historical consumption amount information and the historical consumption amount information of the consuming object are given, but for some newly registered consuming objects, there is no historical consumption amount information or historical consumption amount information, so the foregoing embodiments of classifying the income level of the consuming object by using the historical consumption amount information and the historical consumption amount information are not applicable to these newly registered consuming objects, and a specific method is proposed in some embodiments of the present application in order to be able to reasonably classify the newly registered consuming objects.

Referring to FIG. 9, in an embodiment, further describing step 222, in the case that the consuming objects in the first classification result include a first class object and a third class object, wherein the first class object has income level information and the third class object does not have income level information, step 222 may further include, but is not limited to, step 2225 and step 2226.

Step 2225: and carrying out second classification processing on the first class of objects according to the income level information to obtain a second pre-classification result, wherein the second pre-classification result comprises a second target classification.

In this step, since the first class object has the income level information, the second classification processing can be performed on the first class object according to the income level information to obtain a second pre-classification result, so that the subsequent step can classify the third class object on the basis of the second pre-classification result, thereby achieving the purpose of performing the second classification processing on the first classification result according to the income level information to obtain a plurality of consumption object sets.

It should be noted that, in an alternative embodiment, the second pre-classification result of this step may be the first pre-classification result in step 2221, in which case, the multiple classifications of the first pre-classification result include the second target classification.

Step 2226: and classifying the third class of objects into a second target class to obtain a plurality of consumption object sets.

In this step, for a third class of objects (e.g., newly registered consumption objects) without income level information, the third class of objects may be directly categorized into a second target category to obtain a plurality of consumption object sets, so that subsequent steps may reasonably adjust prices of target push information for each consumption object set, and the conversion amount of the target push information can reach an expectation.

In addition, in an embodiment, further describing the step 222, in the case that the consumer group attribute information further includes at least one of region information, job level information or job type information, the step 222 may further include, but is not limited to, the following steps:

performing second classification processing on the first classification result according to the income level information to obtain a second classification result;

and performing third classification processing on the second classification result according to at least one of the region information, the job level information or the work type information to obtain a plurality of consumption object sets.

In this embodiment, since the attribute information of the consumption group further includes at least one of the region information, the job level information, or the job type information, the second classification processing may be performed on the first classification result according to the income level information to obtain a second classification result, and then the third classification processing may be performed on the second classification result according to at least one of the region information, the job level information, or the job type information to obtain a plurality of consumption object sets, so that the classification of the consumption object sets may be more appropriate, and the subsequent steps may respectively perform reasonable price adjustment on the target push information for each consumption object set, so that the conversion amount of the target push information may reach an expectation.

The region information may include residence information, work place information, and the like, and this embodiment is not particularly limited to this.

In addition, in an embodiment, further describing the information pushing method, in the case that the target time period is a time period between a first time before the current time in the current time cycle and the current time, after the current exposure price of the target pushing information is determined in the step 150, the information pushing method may further include, but is not limited to, the following steps:

and maintaining the target price adjustment coefficient for a second period, wherein the second period is a period of time in the current time cycle except the target period.

In this embodiment, after the step 150 is executed to determine the current exposure price of the target push information, the target price adjustment coefficient obtained in the step 140 may be maintained for the second time period, so that the current exposure price of the target push information can be kept stable in the second time period, so that the click rate and the conversion amount of the target push information can be effectively obtained, and an effective data source can be provided for the next price adjustment processing.

Referring to FIG. 10, in an embodiment, step 150 is further described, and step 150 may include, but is not limited to, step 151 and step 152.

Step 151: and calculating to obtain the predicted conversion unit price of the target push information according to the target price adjusting coefficient and the target conversion unit price.

In this step, since the target conversion unit price of the target push information is obtained in step 120 and the target price adjustment coefficient of the target push information is obtained in step 140, the predicted conversion unit price of the target push information can be calculated according to the target price adjustment coefficient and the target conversion unit price, so that the current exposure price of the target push information can be calculated in the subsequent step according to the predicted conversion unit price.

The predicted conversion unit price enables the final actual conversion unit price of the target push information to not exceed the target conversion unit price set by the information provider.

Note that the predicted conversion unit price of the target push information may be calculated by the following formula (7):

wherein SmartBid is the unit price of the prediction and transformation to be solved; CPA _Target Is a target conversion unit price;

the charging ratio coefficient is the ratio of the actual consumption of the target push information of single click to the bid of the information provider for the single click; lambda [ alpha ] _p The target price adjustment coefficient for the p-th consumption object set is obtained. Since the CPA _Target 、

And λ _p All the information can be obtained, so that the predicted conversion unit price of the target push information can be calculated according to the formula (7) so as to facilitate the follow-upThe step can calculate the current exposure price of the target push information according to the predicted conversion unit price.

Step 152: and calculating the current exposure price of the target push information according to the predicted conversion unit price.

In this step, since the predicted conversion unit price of the target push information is calculated in step 151, the current exposure price of the target push information can be calculated from the predicted conversion unit price.

It should be noted that the current exposure price of the target push information can be calculated by the following formula (8):

eCPM＝SmartBid·pCVR·pCTR·1000 (8)

wherein: eCPM is the thousands of exposure prices (i.e. the current exposure price in this step); the pCVR is an estimated conversion rate obtained by a conversion rate estimation model based on conversion data provided by an information provider, and the conversion data can be obtained through a conversion log; the pCTR is an estimated click rate obtained by a click rate estimation model based on click data of target push information. The conversion rate prediction model and the click rate prediction model are common models in the field, and therefore, for detailed principle description of the conversion rate prediction model and the click rate prediction model, reference may be made to related description of the conversion rate prediction model and the click rate prediction model in related technologies, and details are not repeated here.

Additionally, in an embodiment, further describing step 160, step 160 may include, but is not limited to, the following steps:

adjusting the ordering of the target push information in the information push sequence according to the current exposure price;

and determining whether to push target push information to the target consumption object set according to the sorting.

In this embodiment, since the current exposure price of the target push information is determined in step 150, the order of the target push information in the information push sequence may be adjusted according to the current exposure price, and then it is determined whether to push the target push information to the target consuming object set according to the order of the target push information in the information push sequence.

It should be noted that, in the process of pushing information to the internet platform, the server generally determines the push information to be pushed in a bid sorting manner. The specific process is as follows: the server firstly obtains the exposure price of each piece of push information, then sorts the exposure prices of the push information to form an information push sequence, for example, sorts the push information according to the sequence of the exposure prices from large to small to form the information push sequence, then, the server selects a certain amount of push information from front to back in the information push sequence as the information to be pushed, and then pushes the information to be pushed to the internet platform. Since the current exposure price of the target push information is adjusted according to the target price adjustment coefficient, the ordering of the target push information in the information push sequence may be changed, and therefore, after the ordering of the target push information in the information push sequence is adjusted according to the current exposure price, it is necessary to determine whether the target push information can be pushed to the target consumption object set according to the ordering.

It should be noted that, since the current exposure price of the target push information is determined according to the target price adjusting coefficient, and the target price adjusting coefficient is adapted to the target consumption object set, the adjusted current exposure price of the target push information can be adapted to the target consumption object set, so that the conversion amount of the target push information can reach the expectation of the information provider when the target push information is pushed to the target consumption object set according to the current exposure price.

Referring to fig. 11, an embodiment of the present application further discloses an information pushing apparatus, where the information pushing apparatus 300 can be used as the server 101 in the embodiment shown in fig. 1, or deployed in the server 101 in the embodiment shown in fig. 1, and implement the information pushing method in the foregoing embodiment. The information pushing device 300 comprises:

an information determining unit 301, configured to determine target push information;

a first obtaining unit 302, configured to obtain a target conversion unit price of the target push information;

a second obtaining unit 303, configured to obtain a first historical conversion unit price, a first historical price adjustment coefficient, and a historical pushing consumption of the target pushing information, where the first historical conversion unit price is a conversion unit price at which the target pushing information is pushed to the target consuming object set in a target time period, the first historical price adjustment coefficient is a price adjustment coefficient at which the target pushing information is pushed to the target consuming object set in the target time period, the historical pushing consumption is a pushing consumption at which the target pushing information is pushed to the target consuming object set in the target time period, and the target consuming object set is one of multiple sets obtained by performing classification processing on all consuming objects;

the coefficient obtaining unit 304 is configured to obtain a target price adjustment coefficient of the target pushing information according to the target conversion unit price, the first historical price adjustment coefficient, and the historical pushing consumption;

a price determining unit 305, configured to determine a current exposure price of the target push information according to the target price adjusting coefficient;

an information pushing unit 306, configured to determine whether to push target pushing information to the target consumption object set according to the current exposure price.

In an embodiment, the information pushing apparatus 300 further includes:

In one embodiment, in a case where the consuming capacity attribute information includes income level information and the consuming group attribute information includes age information, the object classifying unit includes:

In one embodiment, in a case where the consumption objects in the first classification result include a first class object having income level information and a second class object having historical consumption amount information and historical consumption amount information, the second classification unit includes:

the first classification subunit is used for carrying out second classification processing on the first class of objects according to the income level information to obtain a first pre-classification result, and the first pre-classification result comprises a plurality of classifications;

the first determining unit is used for determining a plurality of target objects in the first class of objects according to the historical consumption amount information and the historical consumption quantity information of the objects to be classified for each object to be classified in the second class of objects, wherein the distance between each target object and each object to be classified is smaller than a first preset threshold value;

a second determination unit configured to take, as the first target classification, one of the plurality of classifications that includes the largest number of target objects;

the first classification unit is used for classifying the objects to be classified into a first target classification to obtain a plurality of consumption object sets.

In an embodiment, the first determination unit includes:

and the second determining subunit is used for determining a plurality of target objects in the plurality of first candidate objects according to the historical consumption quantity information of the objects to be classified, wherein the second preset threshold is greater than or equal to the first preset threshold.

In an embodiment, the first determination unit includes:

the third determining subunit is used for determining a plurality of second candidate objects in the first class of objects according to the historical consumption quantity information of the objects to be classified, wherein the distance between each second candidate object and each object to be classified is smaller than a third preset threshold value;

and the fourth determining subunit is used for determining a plurality of target objects in the plurality of second candidate objects according to the historical consumption amount information of the objects to be classified, wherein the third preset threshold is greater than or equal to the first preset threshold.

In an embodiment, in the case that the consumption objects in the first classification result include a first class object having revenue level information and a third class object having no revenue level information, the second classification unit includes:

and the second classification unit is used for classifying the third class of objects into a second target classification to obtain a plurality of consumption object sets.

In an embodiment, in a case where the consumer group attribute information further includes at least one of region information, job level information, or job type information, the second classification unit includes:

and the fourth classification subunit is used for performing third classification processing on the second classification result according to at least one of the region information, the job level information or the work type information to obtain a plurality of consumption object sets.

In one embodiment, the coefficient obtaining unit 304 includes:

the first obtaining subunit is configured to obtain a second historical conversion unit price and a second historical price adjustment coefficient of the target pushing information, where the second historical conversion unit price is a conversion unit price of the target pushing information pushed to all consumption objects in a target time period, and the second historical price adjustment coefficient is a price adjustment coefficient of the target pushing information pushed to all consumption objects in the target time period;

and the second obtaining subunit is used for obtaining the target price adjusting coefficient of the target pushing information according to the target conversion unit price, the first historical price adjusting coefficient, the historical pushing consumption, the second historical conversion unit price and the second historical price adjusting coefficient.

In an embodiment, when the target time period is a time period from a first time before the current time to the current time in the current time cycle, the information pushing apparatus 300 further includes:

and the coefficient maintaining unit is used for maintaining the target price adjusting coefficient for a second period, wherein the second period is a period except the target period in the current time cycle.

In one embodiment, the price determination unit 305 includes:

the first calculating unit is used for calculating the predicted conversion unit price of the target pushing information according to the target price adjusting coefficient and the target conversion unit price;

In an embodiment, the information pushing unit 306 includes:

the adjusting unit is used for adjusting the sequencing of the target push information in the information push sequence according to the current exposure price;

and the pushing unit is used for determining whether to push target pushing information to the target consumption object set according to the sorting.

It should be noted that, since the information pushing apparatus 300 of the present embodiment can implement the information pushing method using the server as the execution subject as in the foregoing embodiment, the information pushing apparatus 300 of the present embodiment has the same technical principle and the same beneficial effects as the information pushing method using the server as the execution subject in the foregoing embodiment, and is not repeated here to avoid overlapping of contents.

The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Referring to fig. 12, an embodiment of the present application further discloses an information pushing apparatus, where the information pushing apparatus 400 includes:

at least one processor 401;

at least one memory 402 for storing at least one program;

when at least one of the programs is executed by at least one of the processors 401, the information push method according to any of the preceding embodiments is implemented.

The embodiment of the present application further discloses a computer-readable storage medium, in which a program executable by a processor is stored, and when the program executable by the processor is executed by the processor, the program is used for implementing the information push method according to any of the foregoing embodiments.

Embodiments of the present application also disclose 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, so that the computer device executes the information pushing method described in any of the foregoing embodiments.

The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, 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, for example, capable of operation in sequences other than those illustrated or otherwise 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 apparatus 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.

It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" is used to describe the association relationship of the associated object, indicating that there may be three relationships, for example, "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

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

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, which are essential or part of the technical solutions contributing to the prior art, or all or part of the technical solutions, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a portable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other media capable of storing program codes.

The step numbers in the above method embodiments are set for convenience of illustration only, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.

Claims

1. An information pushing method is characterized by comprising the following steps:

determining target push information;

acquiring a target conversion unit price of the target push information;

2. The information pushing method according to claim 1, wherein the classifying all the consumption objects comprises:

acquiring the consumption capability attribute information and the consumption group attribute information of all consumption objects;

and classifying all the consumption objects according to the consumption capability attribute information and the consumption group attribute information to obtain a plurality of consumption object sets.

3. The information pushing method according to claim 2, wherein the consumption capability attribute information includes income level information, and the consumer group attribute information includes age information;

classifying all the consumption objects according to the consumption capability attribute information and the consumption group attribute information to obtain a plurality of consumption object sets, wherein the steps of:

performing first classification processing on all the consumption objects according to the age information to obtain a first classification result;

and carrying out second classification processing on the first classification result according to the income level information to obtain a plurality of consumption object sets.

4. The information pushing method according to claim 3, wherein the consumption objects in the first classification result include a first class object and a second class object, the first class object has the income level information, and the second class object has historical consumption amount information and historical consumption amount information;

performing second classification processing on the first classification result according to the income level information to obtain a plurality of consumption object sets, wherein the second classification processing comprises the following steps:

performing second classification processing on the first class objects according to the income level information to obtain a first pre-classification result, wherein the first pre-classification result comprises a plurality of classifications;

for each object to be classified in the second class of objects, determining a plurality of target objects in the first class of objects according to the historical consumption amount information and the historical consumption quantity information of the object to be classified, wherein the distance between the target object and the object to be classified is smaller than a first preset threshold value;

taking one of the plurality of classifications with the largest number of target objects as a first target classification;

and classifying the object to be classified into the first target classification to obtain a plurality of consumption object sets.

5. The information pushing method according to claim 4, wherein the determining a plurality of target objects in the first class of objects according to the historical consumption amount information and the historical consumption number information of the objects to be classified comprises:

determining a plurality of first candidate objects in the first class of objects according to the historical consumption amount information of the objects to be classified, wherein the distance between the first candidate objects and the objects to be classified is smaller than a second preset threshold value;

determining a plurality of target objects in the plurality of first candidate objects according to the historical consumption quantity information of the objects to be classified, wherein the second preset threshold is greater than or equal to the first preset threshold.

6. The information pushing method according to claim 4, wherein the determining a plurality of target objects in the first class of objects according to the historical consumption amount information and the historical consumption number information of the objects to be classified comprises:

determining a plurality of second candidate objects in the first class of objects according to the historical consumption quantity information of the objects to be classified, wherein the distance between the second candidate objects and the objects to be classified is smaller than a third preset threshold value;

and determining a plurality of target objects in the plurality of second candidate objects according to the historical consumption amount information of the objects to be classified, wherein the third preset threshold is greater than or equal to the first preset threshold.

7. The information pushing method according to claim 3, wherein the consuming objects in the first classification result include a first class object and a third class object, the first class object has the income level information, and the third class object does not have the income level information;

performing second classification processing on the first classification result according to the income level information to obtain a plurality of consumption object sets, including:

performing second classification processing on the first class objects according to the income level information to obtain a second pre-classification result, wherein the second pre-classification result comprises a second target classification;

and classifying the third class of objects into the second target class to obtain a plurality of consumption object sets.

8. The information pushing method according to claim 3, wherein the consumer group attribute information further includes at least one of regional information, job level information, or job type information;

9. The information pushing method according to claim 1, wherein obtaining the target price adjustment coefficient of the target pushing information according to the target conversion unit price, the first historical price adjustment coefficient, and the historical pushing consumption comprises:

acquiring a second historical conversion unit price and a second historical price adjustment coefficient of the target pushing information, wherein the second historical conversion unit price is the conversion unit price of the target pushing information pushed to all the consumption objects in the target time period, and the second historical price adjustment coefficient is the price adjustment coefficient of the target pushing information pushed to all the consumption objects in the target time period;

and obtaining a target price adjusting coefficient of the target pushing information according to the target conversion unit price, the first historical price adjusting coefficient, the historical pushing consumption, the second historical conversion unit price and the second historical price adjusting coefficient.

10. The information pushing method according to claim 1 or 9, wherein the target period is a period from a first time before a current time to the current time in a current time cycle;

after the current exposure price of the target pushing information is determined according to the target price adjusting coefficient, the information pushing method further comprises the following steps:

maintaining the target price adjustment coefficient for a second period of time, wherein the second period of time is a period of time in the current time cycle other than the target period of time.

11. The information push method according to claim 1, wherein the determining the current exposure price of the target push information according to the target price adjustment coefficient includes:

calculating to obtain a predicted conversion unit price of the target push information according to the target price adjusting coefficient and the target conversion unit price;

and calculating the current exposure price of the target push information according to the predicted conversion unit price.

12. The information pushing method according to claim 1, wherein the determining whether to push the target pushing information to the target consuming object set according to the current exposure price comprises:

adjusting the ordering of the target push information in an information push sequence according to the current exposure price;

and determining whether to push the target push information to the target consumption object set according to the sorting.

13. An information pushing apparatus, comprising:

14. An information pushing apparatus, comprising:

at least one processor;

at least one memory for storing at least one program;

the information push method according to any of claims 1 to 12 is implemented when at least one of said programs is executed by at least one of said processors.

15. A computer-readable storage medium, in which a program executable by a processor is stored, and the program executable by the processor is used for implementing the information pushing method according to any one of claims 1 to 12 when being executed by the processor.