CN-115357797-B - Resource recommendation information acquisition method and device, computer equipment and storage medium

CN115357797BCN 115357797 BCN115357797 BCN 115357797BCN-115357797-B

Abstract

The disclosure relates to a method, a device, computer equipment and a storage medium for acquiring resource recommendation information, and belongs to the technical field of information. According to the method and the device, the calibration coefficient is obtained through the preset virtual resources predicted by the machine and the practically consumed virtual resources put in, the calibration coefficient can calibrate the resource feedback data, so that the calibration feedback data obtained through calibration can be gathered to the practically fed-back data obtained after the preset virtual resources are put in as much as possible, and the prediction accuracy of the calibration feedback data is greatly improved, so that the accuracy of the resource recommendation information obtained according to the preset virtual resources and the calibration feedback data can be improved, namely the accuracy of the resource recommendation is improved.

Inventors

YU SHENGKAI
DENG HUIYANG
SUN GAOGUO
ZHU YE
ZHAO BO
DENG RONGYAO
REN YUJUAN
LIU WENLING

Assignees

北京达佳互联信息技术有限公司

Dates

Publication Date: 20260512
Application Date: 20220831

Claims (14)

1. The method for acquiring the resource recommendation information is characterized by comprising the following steps: Acquiring preset virtual resources and resource feedback data of a target content item in a first time period, wherein the first time period is a time period formed from the moment of starting to throw to the current moment in the throwing process, the preset virtual resources are predicted virtual resources which are expected to be consumed by throwing the target content item in the first time period, and the resource feedback data are predicted feedback data which are expected to be achieved under the condition that the preset virtual resources are consumed to throw the target content item; Determining a calibration coefficient based on the preset virtual resource and a virtual resource for delivering the target content item in the first time period, wherein the virtual resource for delivering is a virtual resource which is actually consumed for delivering the target content item in the first time period; multiplying the resource feedback data with the calibration coefficient to obtain calibration feedback data; Predicting and obtaining target virtual resources and target feedback data of the target content item in a second time period based on the preset virtual resources and the calibration feedback data; determining a full amount of virtual resources for the target content item based on the put virtual resources and the target virtual resources; determining full feedback data of the target content item based on the delivery feedback data of the target content item and the target feedback data delivered in the first time period; And acquiring resource recommendation information of the target content item based on the full-scale virtual resources and the full-scale feedback data, wherein the resource recommendation information is used for recommending virtual resources consumed by delivering the target content item in the second time period.
2. The method for obtaining resource recommendation information according to claim 1, wherein predicting, based on the preset virtual resource and the calibration feedback data, the target virtual resource and the target feedback data of the target content item in the second period of time includes: Obtaining a request proportion of the second time period, wherein the request proportion represents a ratio between the expected number of received requests of the second time period and the number of received requests of the first time period; determining the target virtual resource based on the request proportion and the preset virtual resource; the target feedback data is determined based on the requested ratio and the calibration feedback data.
3. The method for obtaining resource recommendation information according to claim 1, wherein the resource recommendation information includes at least one resource recommendation value and feedback data of each of the at least one resource recommendation value; The obtaining the resource recommendation information based on the full-scale virtual resource and the full-scale feedback data includes: fitting to obtain a resource feedback curve based on the full-scale virtual resource and the full-scale feedback data, wherein the resource feedback curve represents a change relation between virtual resources consumed by throwing the target content item in a target time period and the harvested feedback data, and the target time period is composed of the first time period and the second time period; and determining feedback data of each of the at least one resource recommendation value and the at least one resource recommendation value based on the resource feedback curve.
4. The method of claim 3, wherein determining feedback data for each of the at least one resource recommendation value and the at least one resource recommendation value based on the resource feedback curve comprises: determining a historical average resource value based on historical placement information for the content item; acquiring the at least one resource recommendation value based on the historical average resource value; and acquiring respective feedback data of the at least one resource recommendation value in the resource feedback curve.
5. The method for obtaining resource recommendation information according to claim 3, wherein the fitting a resource feedback curve based on the full-scale virtual resource and the full-scale feedback data comprises: For any resource threshold, determining the total feedback data expected to be obtained by the total virtual resource as the feedback data of the resource threshold under the condition that the total virtual resource is equal to the resource threshold; and fitting to obtain the resource feedback curve based on the plurality of resource thresholds and the feedback data of each of the plurality of resource thresholds.
6. The method for obtaining resource recommendation information according to any one of claims 3 to 5, wherein the resource feedback curve includes at least one of a curve of a resource feedback amount with a resource threshold, a curve of a resource return rate with a resource threshold, and a curve of a resource interaction amount with a resource threshold.
7. The method for obtaining resource recommendation information according to claim 1, wherein obtaining preset virtual resources and resource feedback data of the target content item in the first period of time includes: For any service request received in the first time period, acquiring the resource consumption and request importance of the service request, wherein the resource consumption represents the resource consumption from preset virtual resources required when the service request is returned to the target content item, and the request importance represents the ratio of the resource feedback quantity to the resource consumption when the service request is returned to the target content item; and acquiring the preset virtual resources and the resource feedback data based on the resource consumption and the request importance of each of the plurality of service requests received in the first time period.
8. The method for obtaining resource recommendation information according to claim 7, wherein obtaining the request importance of the service request comprises: Predicting a click behavior parameter and a conversion behavior parameter of the account on the target content item for the account initiating the service request, wherein the click behavior parameter characterizes the possibility that the account clicks the target content item, and the conversion behavior parameter characterizes the possibility that the account consumes or activates an object associated with the target content item; determining the resource feedback quantity of the service request based on the click behavior parameter and the conversion behavior parameter; and determining the ratio between the resource feedback quantity and the resource consumption quantity as the request importance degree.
9. The method for obtaining resource recommendation information according to claim 7, wherein the obtaining the preset virtual resource and the resource feedback data based on the resource consumption and the request importance of each of the plurality of service requests received in the first period of time includes: Screening at least one target service request from the plurality of service requests according to the sequence of the importance of the request from high to low for any preset virtual resource, wherein the sum of the resource consumption of the at least one target service request does not exceed the preset virtual resource; And determining the sum of the resource feedback amounts of the at least one target service request as resource feedback data associated with the preset virtual resource.
10. The method for obtaining resource recommendation information according to claim 9, wherein the step of screening at least one target service request from the plurality of service requests in order of high-to-low request importance includes: Sequencing the service requests according to the sequence of the importance of the requests from high to low; Starting from the service request positioned at the first position in the sequence, accumulating the sum of the resource consumption amounts of the service requests positioned at the front target position in the sequence; and under the condition that the sum value is accumulated to not exceed the preset virtual resource and is closest to the preset virtual resource, determining the accumulated service request of the front target bit as the at least one target service request.
11. The method for obtaining resource recommendation information according to claim 1, wherein the determining a calibration coefficient based on the preset virtual resource and the delivered virtual resource for delivering the target content item in the first period of time includes: Subtracting the released virtual resource from the preset virtual resource to obtain resource error data; And determining and obtaining the calibration coefficient based on the virtual resources and the resource error data.
12. An apparatus for acquiring resource recommendation information, comprising: a first obtaining unit configured to perform obtaining a preset virtual resource and resource feedback data of a target content item in a first time period, wherein the first time period is a time period formed from a time point of starting to be put to a current time point in a putting process, the preset virtual resource is a predicted virtual resource expected to be consumed for putting the target content item in the first time period, and the resource feedback data is feedback data expected to be achieved under the condition that the preset virtual resource is consumed for putting the target content item; A determining unit configured to perform determination of a calibration coefficient based on the preset virtual resource and a delivery virtual resource for delivering the target content item in the first period, the delivery virtual resource being a virtual resource that has been actually consumed for delivering the target content item in the first period; a calibration unit configured to perform multiplication of the resource feedback data with the calibration coefficient to obtain calibration feedback data; The second obtaining unit is configured to execute prediction to obtain target virtual resources and target feedback data of the target content item in a second time period based on the preset virtual resources and the calibration feedback data, determine total virtual resources of the target content item based on the released virtual resources and the target virtual resources, determine total feedback data of the target content item based on the released feedback data of the target content item and the target feedback data in the first time period, and obtain resource recommendation information of the target content item based on the total virtual resources and the total feedback data, wherein the resource recommendation information is used for recommending virtual resources consumed by releasing the target content item in the second time period.
13. A computer device, comprising: one or more processors; one or more memories for storing the one or more processor-executable instructions; Wherein the one or more processors are configured to execute the instructions to implement the method of obtaining resource recommendation information as claimed in any one of claims 1 to 11.
14. A computer-readable storage medium, wherein at least one instruction in the computer-readable storage medium, when executed by one or more processors of a computer device, causes the computer device to perform the method of obtaining resource recommendation information of any one of claims 1 to 11.

Description

Resource recommendation information acquisition method and device, computer equipment and storage medium Technical Field The disclosure relates to the field of information technology, and in particular, to a method and a device for acquiring resource recommendation information, a computer device and a storage medium. Background As information technology and information networks have developed, different content items can be delivered to different users by providing delivery services for content items in some short video platforms. In the process of delivering a content item, a decision is typically made as to which account needs to be delivered with the content item based on the set resources. Currently, in the process of delivering the content item, resource recommendation is performed based on the resources set by the user in the historical delivery process, so that the accuracy of resource recommendation is low and the efficiency is low. Disclosure of Invention The disclosure provides a method, a device, computer equipment and a storage medium for acquiring resource recommendation information so as to at least improve the accuracy of resource recommendation in the process of delivering content items. The technical scheme of the present disclosure is as follows: According to an aspect of the embodiments of the present disclosure, there is provided a method for acquiring resource recommendation information, including: Acquiring preset virtual resources and resource feedback data of a target content item in a first time period; determining a calibration coefficient based on the preset virtual resource and the virtual resource for delivering the target content item in the first time period; Calibrating the resource feedback data based on the calibration coefficient to obtain calibration feedback data; and acquiring resource recommendation information of the target content item based on the preset virtual resource and the calibration feedback data, wherein the resource recommendation information is used for recommending the virtual resource consumed by throwing the target content item in a second time period. In some embodiments, the obtaining the resource recommendation information for the target content item based on the preset virtual resource and the calibration feedback data includes: Predicting and obtaining target virtual resources and target feedback data of the target content item in the second time period based on the preset virtual resources and the calibration feedback data; determining a full amount of virtual resources for the target content item based on the put virtual resources and the target virtual resources; determining full feedback data of the target content item based on the delivery feedback data of the target content item and the target feedback data delivered in the first time period; and acquiring the resource recommendation information based on the full-scale virtual resource and the full-scale feedback data. In some embodiments, the predicting, based on the preset virtual resource and the calibration feedback data, the target virtual resource and the target feedback data of the target content item in the second period of time includes: Obtaining a request proportion of the second time period, wherein the request proportion represents a ratio between the expected number of received requests of the second time period and the number of received requests of the first time period; determining the target virtual resource based on the request proportion and the preset virtual resource; the target feedback data is determined based on the requested ratio and the calibration feedback data. In some embodiments, the resource recommendation information includes at least one resource recommendation value and feedback data for each of the at least one resource recommendation value; The obtaining the resource recommendation information based on the full-scale virtual resource and the full-scale feedback data includes: fitting to obtain a resource feedback curve based on the full-scale virtual resource and the full-scale feedback data, wherein the resource feedback curve represents a change relation between virtual resources consumed by throwing the target content item in a target time period and the harvested feedback data, and the target time period is composed of the first time period and the second time period; and determining feedback data of each of the at least one resource recommendation value and the at least one resource recommendation value based on the resource feedback curve. In some embodiments, the determining feedback data for each of the at least one resource recommendation value and the at least one resource recommendation value based on the resource feedback curve comprises: determining a historical average resource value based on historical placement information for the content item; acquiring the at least one resource recommendation value based on the historical average resour