Resource adjustment method, device, electronic device and storage medium

By analyzing the investment and gain data of each object category and adjusting resource investment, the problem of unbalanced resource allocation in Internet platform promotion is solved, and push efficiency and system performance are improved.

CN114443272BActive Publication Date: 2024-12-03BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202111551084.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-17
Publication Date
2024-12-03
Estimated Expiration
2041-12-17

AI Technical Summary

Technical Problem

In the prior art, when Internet platforms promote different object categories, the proportion of resource investment and gain resources varies greatly, resulting in low information push efficiency, waste of resources and reduced system performance.

Method used

By obtaining investment and gain data of each object category, analyzing based on preset conditions, adjusting resource investment to achieve balanced resource configuration and optimizing object push strategy.

Benefits of technology

It improves the conversion effect of object push, reduces invalid information push, reduces the burden of resource waste and system performance, and improves the overall performance of the recommendation system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114443272B_ABST
    Figure CN114443272B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a resource adjustment method, device, electronic device and storage medium. The method includes obtaining input gain data corresponding to multiple object categories, the input gain data represents the virtual resource increment brought by obtaining a single object under multiple object categories, and the virtual resources required to be invested; based on preset conditions and the input gain data corresponding to each object category, the input gain data is analyzed to obtain resource adjustment data corresponding to multiple object categories, and the resource adjustment data is used to adjust the input resources corresponding to multiple object categories while balancing the input gain data corresponding to multiple object categories; based on the resource adjustment data, the original input resources corresponding to multiple object categories are adjusted to obtain target input resources corresponding to multiple object categories. The disclosed embodiments can improve the object conversion effect, reduce the invalid push of object information, and thus reduce the waste of system resources of the object recommendation system and improve system performance.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and in particular to a resource adjustment method, device, electronic device and storage medium. Background Art

[0002] With the development of Internet technology, information promotion through the Internet has become a new form of information dissemination. For example, information about products and other objects can be placed on some Internet platforms to push objects.

[0003] In the related art, certain virtual resources are often invested in the objects to be promoted in order to better ensure the push effect of the objects; for example, virtual resources are invested to facilitate users to return objects; but in the related art, the resources invested in various objects under different object categories on the same platform are often based on a unified standard; and the gain data brought by objects of different categories are often different, resulting in a large difference in the ratio of investment resources and gain resources corresponding to different object categories. Some users whose investment resources account for a large proportion of gain resources are unwilling to invest virtual resources in the objects, which leads to a large amount of invalid push of object information, poor conversion effect, and the push of a large amount of invalid information also causes problems such as waste of object recommendation system resources and reduced system performance. Summary of the invention

[0004] The present disclosure provides a resource adjustment method, device, electronic device and storage medium to at least solve the problem that a large amount of object information is invalidly pushed in the related art, the conversion effect is poor, and the push of a large amount of invalid information also causes the waste of object recommendation system resources and the reduction of system performance. The technical solution of the present disclosure is as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, a resource adjustment method is provided, including:

[0006] Acquire investment gain data corresponding to a plurality of object categories, wherein the investment gain data represents the virtual resource increment brought by acquiring a single object under the plurality of object categories and the virtual resources required to be invested;

[0007] Based on preset conditions and the input gain data corresponding to each object category, the input gain data is analyzed to obtain resource adjustment data corresponding to the multiple object categories, wherein the resource adjustment data is used to adjust the input resources corresponding to the multiple object categories while balancing the input gain data corresponding to the multiple object categories;

[0008] The original input resources corresponding to the multiple object categories are adjusted based on the resource adjustment data to obtain target input resources corresponding to the multiple object categories.

[0009] In an optional embodiment, the preset condition is a preset constraint interval, the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval, and the method further includes:

[0010] Get the preset upper limit parameter;

[0011] Based on the preset upper limit parameter, determining target resource adjustment data from the resource adjustment parameter interval;

[0012] The adjusting the original input resources corresponding to the multiple object categories based on the resource adjustment data to obtain the target input resources corresponding to the multiple object categories includes:

[0013] The original input resources are adjusted based on the target resource adjustment data to obtain target input resources corresponding to the multiple object categories.

[0014] In an optional embodiment, the method further includes:

[0015] Obtaining the accumulated input resources corresponding to the plurality of object categories and the accumulated loss resources corresponding to the plurality of object categories in a historical time period;

[0016] Determining loss investment data according to the accumulated loss resources and the accumulated investment resources;

[0017] The adjusting the original input resources corresponding to the multiple object categories based on the resource adjustment data to obtain the target input resources corresponding to the multiple object categories includes:

[0018] The original input resources are adjusted based on the resource adjustment data and the loss input data to obtain target input resources corresponding to the multiple object categories.

[0019] In an optional embodiment, the preset condition is a preset constraint interval, and the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval;

[0020] The adjusting the original input resources based on the resource adjustment data and the loss input data to obtain the target input resources corresponding to the multiple object categories includes:

[0021] Obtain historical resource adjustment parameters corresponding to the multiple object categories in the historical time period;

[0022] When the loss input data is greater than or equal to a preset threshold, the first resource adjustment parameter corresponding to the multiple object categories is determined from the resource adjustment parameter interval, and the first resource adjustment parameter corresponding to any object category is greater than the historical resource adjustment parameter corresponding to any of the object categories.

[0023] In an optional embodiment, the adjusting the original input resources based on the resource adjustment data and the loss input data to obtain the target input resources corresponding to the multiple object categories further includes:

[0024] When the loss input number is less than the preset threshold, the second resource adjustment parameters corresponding to the multiple object categories are determined from the resource adjustment parameter interval, and the second resource adjustment parameter corresponding to any object category is less than the historical resource adjustment parameter corresponding to any of the object categories.

[0025] In an optional embodiment, obtaining the input gain data corresponding to the multiple object categories includes:

[0026] Acquire original input resources corresponding to the multiple object categories;

[0027] Acquire unit object gain resources corresponding to the multiple object categories;

[0028] The investment gain data is determined according to the original investment resources and the unit object gain resources.

[0029] In an optional embodiment, the acquiring original input resources corresponding to the multiple object categories includes:

[0030] Obtaining target object loss data corresponding to the multiple object categories;

[0031] Determining original input resources corresponding to the plurality of object categories according to preset loss resource information and the target object loss data;

[0032] The preset loss resource information represents the corresponding relationship between loss data of different objects and input resources.

[0033] In an optional embodiment, acquiring the unit object gain resources corresponding to the multiple object categories includes:

[0034] Acquire object gain rates corresponding to the plurality of object categories and unit object resources corresponding to the plurality of object categories;

[0035] The unit object gain resource is determined according to the object gain rate and the unit object resource.

[0036] According to a second aspect of an embodiment of the present disclosure, there is provided a resource adjustment device, including:

[0037] An investment gain data acquisition module is configured to execute acquisition of investment gain data corresponding to a plurality of object categories, wherein the investment gain data represents the virtual resource increment brought by acquiring a single object under the plurality of object categories and the virtual resources required to be invested;

[0038] an analysis module configured to analyze the input gain data based on preset conditions and the input gain data corresponding to each object category to obtain resource adjustment data corresponding to the multiple object categories, wherein the resource adjustment data is used to adjust the input resources corresponding to the multiple object categories while balancing the input gain data corresponding to the multiple object categories;

[0039] The resource adjustment module is configured to adjust the original input resources corresponding to the multiple object categories based on the resource adjustment data to obtain target input resources corresponding to the multiple object categories.

[0040] In an optional embodiment, the preset condition is a preset constraint interval, the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval, and the device further includes:

[0041] A preset upper limit parameter acquisition module is configured to execute acquisition of a preset upper limit parameter;

[0042] a target resource adjustment data determination module, configured to determine target resource adjustment data from the resource adjustment parameter interval based on the preset upper limit parameter;

[0043] The resource adjustment module is further configured to execute: adjusting the original input resources based on the target resource adjustment data to obtain the target input resources corresponding to the multiple object categories.

[0044] In an optional embodiment, the device further comprises:

[0045] A resource acquisition module is configured to execute acquisition of the accumulated input resources corresponding to the plurality of object categories and the accumulated loss resources corresponding to the plurality of object categories within a historical time period;

[0046] A loss input data determination module is configured to determine loss input data according to the accumulated loss resources and the accumulated input resources;

[0047] The resource adjustment module is further configured to execute: adjusting the original input resources based on the resource adjustment data and the loss input data to obtain target input resources corresponding to the multiple object categories.

[0048] In an optional embodiment, the preset condition is a preset constraint interval, and the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval;

[0049] The resource adjustment module includes:

[0050] A historical resource adjustment parameter acquisition unit, configured to execute acquisition of historical resource adjustment parameters corresponding to the plurality of object categories in the historical time period;

[0051] The first resource adjustment parameter determination unit is configured to determine the first resource adjustment parameters corresponding to the multiple object categories from the resource adjustment parameter interval when the loss investment data is greater than or equal to a preset threshold, and the first resource adjustment parameter corresponding to any object category is greater than the historical resource adjustment parameter corresponding to any object category.

[0052] In an optional embodiment, the resource adjustment module further includes:

[0053] The second resource adjustment parameter determination unit is configured to determine the second resource adjustment parameters corresponding to the multiple object categories from the resource adjustment parameter interval when the loss input number is less than the preset threshold, and the second resource adjustment parameter corresponding to any object category is less than the historical resource adjustment parameter corresponding to any object category.

[0054] In an optional embodiment, the input gain data acquisition module includes:

[0055] An original input resource acquisition unit is configured to execute acquisition of original input resources corresponding to the plurality of object categories;

[0056] A unit object gain resource acquisition unit, configured to execute acquisition of unit object gain resources corresponding to the plurality of object categories;

[0057] The investment gain data determining unit is configured to determine the investment gain data according to the original investment resources and the unit object gain resources.

[0058] In an optional embodiment, the original input resource acquisition unit includes:

[0059] A target object loss data acquisition unit is configured to acquire target object loss data corresponding to the plurality of object categories;

[0060] An original input resource determination unit is configured to determine the original input resources corresponding to the plurality of object categories according to preset loss resource information and the target object loss data;

[0061] The preset loss resource information represents the corresponding relationship between loss data of different objects and input resources.

[0062] In an optional embodiment, the unit object gain resource acquisition unit includes:

[0063] A gain data acquisition unit, configured to acquire object gain rates corresponding to the plurality of object categories and unit object resources corresponding to the plurality of object categories;

[0064] The unit object gain resource subunit is configured to determine the unit object gain resource according to the object gain rate and the unit object resource.

[0065] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement a method as described in any one of the above-mentioned first aspects.

[0066] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any method described in the first aspect of the embodiment of the present disclosure.

[0067] According to a fifth aspect of an embodiment of the present disclosure, there is provided a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any one of the methods described in the first aspect of the embodiment of the present disclosure.

[0068] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0069] By analyzing the input gain data corresponding to multiple object categories in combination with preset conditions, smaller resource adjustment data can be configured for object categories with higher input gain data, and larger resource adjustment data can be configured for object categories with lower input gain data; and by adjusting the original input resources corresponding to each of the multiple object categories based on the resource adjustment data, the input resources corresponding to the multiple object categories can be adjusted while balancing the input gain data corresponding to the multiple object categories. Furthermore, by balancing the input gain data corresponding to the multiple object categories, the probability of users investing virtual resources in objects can be increased, so as to improve the object conversion effect and reduce the invalid push of object information, thereby also achieving the technical effect of reducing the waste of system resources of the object recommendation system and improving system performance.

[0070] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0072] Figure 1is a flow chart showing a resource adjustment method according to an exemplary embodiment;

[0073] Figure 2 is a flow chart showing a method of obtaining input gain data corresponding to multiple object categories according to an exemplary embodiment;

[0074] Figure 3 is a flow chart showing another resource adjustment method according to an exemplary embodiment;

[0075] Figure 4 is a flow chart showing another resource adjustment method according to an exemplary embodiment;

[0076] Figure 5 is a flow chart showing another resource adjustment method according to an exemplary embodiment;

[0077] Figure 6 is a block diagram of a resource adjustment device according to an exemplary embodiment;

[0078] Figure 7 is a block diagram of an electronic device for resource adjustment according to an exemplary embodiment;

[0079] Figure 8 It is a block diagram of an electronic device for resource adjustment according to an exemplary embodiment. DETAILED DESCRIPTION

[0080] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0081] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0082] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0083] See also Figure 1 , Figure 1 is a flow chart of a resource adjustment method according to an exemplary embodiment. Figure 1 As shown, the resource adjustment method is used in electronic devices such as terminals and servers, and includes the following steps.

[0084] In step S101, input gain data corresponding to a plurality of object categories is obtained.

[0085] In a specific embodiment, the multiple object categories may be object identifiers corresponding to different types of objects. Specifically, the object may be an object that needs to be pushed. Optionally, the multiple object categories may include but are not limited to clothing, beauty, department stores, home appliances, etc., and may be divided and set in combination with actual applications.

[0086] In a specific embodiment, the above-mentioned investment gain data can represent the virtual resource increment brought by acquiring a single object under multiple object categories and the virtual resources required to be invested.

[0087] In an optional embodiment, taking the object replacement scenario as an example, the original investment resources may be virtual resources invested for object replacement.

[0088] In another optional embodiment, taking the object delivery scenario as an example, the original input resource may be a virtual resource invested for delivering a multimedia resource corresponding to a certain object. Specifically, the multimedia resource corresponding to the object may be a multimedia resource for introducing the object, and specifically, the data form of the multimedia resource may include pictures, texts, videos, etc. Correspondingly, the unit object gain resource may be a virtual resource increment brought by the multimedia resource corresponding to a single object.

[0089] In a specific embodiment, Figure 2 As shown, the above-mentioned acquisition of the input gain data corresponding to the multiple object categories may include the following steps:

[0090] In step S201, original input resources corresponding to multiple object categories are obtained;

[0091] In an optional embodiment, the above-mentioned obtaining original input resources corresponding to the multiple object categories includes:

[0092] Obtain target object loss data corresponding to multiple object categories;

[0093] Determine the original input resources corresponding to multiple object categories based on preset loss resource information and target object loss data;

[0094] In a specific embodiment, the preset loss resource information may represent the corresponding relationship between different object loss data and input resources. Specifically, the original input resources may be positively correlated with the object loss data, that is, the larger the object loss data, the higher the original input resources.

[0095] In a specific embodiment, the object loss data corresponding to each object category may be data that can characterize the object loss situation of each object category. Optionally, taking the object return scenario as an example, the object loss data may be the object return rate; taking the object delivery scenario as an example, the object loss data may be the application retention time loss (the user stay time loss in the application) caused by the multimedia resources corresponding to the delivery object.

[0096] In a specific embodiment, the target object loss data corresponding to each object category may be the object loss data corresponding to the object category. In practical applications, the object loss data corresponding to different object categories are often different. Accordingly, the original input resources corresponding to each object category may be determined by combining the preset loss resource information and the target object loss data corresponding to each object category.

[0097] In the above embodiment, combined with the preset loss resource information representing the correspondence between loss data of different objects and input resources, the original input resources of different object categories corresponding to different object loss data can be quickly and accurately determined.

[0098] In step S202, unit object gain resources corresponding to a plurality of object categories are obtained;

[0099] In an optional embodiment, obtaining unit object gain resources corresponding to multiple object categories may include:

[0100] Obtain object gain rates corresponding to multiple object categories and unit object resources corresponding to multiple object categories;

[0101] The unit object gain resource is determined according to the object gain rate and the unit object resource.

[0102] In a specific embodiment, the unit object resource corresponding to each object category may be the average virtual resource corresponding to a single object during the conversion process; the object gain rate corresponding to each object category may represent the overall virtual resource gain rate corresponding to each object category. Specifically, the overall virtual resource gain rate may be the proportion of the overall virtual resource increment brought by the objects under each object category to the overall virtual resources corresponding to the objects under each object category during the conversion process.

[0103] In a specific embodiment, the product of the object gain rate corresponding to each object category and the unit object resource corresponding to the object category can be used as the unit object gain resource corresponding to the object category. Accordingly, the unit object gain resource corresponding to each object category can represent the average virtual resource increment corresponding to a single object corresponding to each object category during the conversion process.

[0104] In the above embodiment, by combining the object gain rate corresponding to each object category and the unit object resource corresponding to the object category, the unit object gain resource corresponding to each object category can be determined quickly and accurately.

[0105] In step S203, the investment gain data is determined according to the original investment resources and the unit object gain resources.

[0106] In a specific embodiment, the original input resources corresponding to each object category may be divided by the unit object gain resources corresponding to the object category to obtain the input gain data corresponding to the object category.

[0107] In the above embodiment, by combining the original input resources and unit object gain resources corresponding to each object category, the input gain data corresponding to each object category can be quickly and accurately determined, thereby providing data support for subsequent virtual resource adjustments.

[0108] In step S102, based on preset conditions and the investment gain data corresponding to each object category, the investment gain data is analyzed to obtain resource adjustment data corresponding to a plurality of object categories.

[0109] In actual applications, different object categories correspond to different investment gain data. In order to effectively balance the investment gain data corresponding to multiple object categories, the investment gain data corresponding to multiple object categories can be constrained in combination with the above preset conditions.

[0110] In a specific embodiment, the preset condition may be a preset constraint interval, and the preset constraint interval may be a preset delivery gain data interval. Optionally, different delivery gain data may be multiplied by corresponding coefficients so that the delivery gain data is within the preset constraint interval. Accordingly, the coefficient may be used as the resource adjustment data.

[0111] In the embodiments of the present specification, by configuring a smaller coefficient for higher investment gain data and a larger coefficient for lower investment gain data, different investment gain data can be constrained to the same investment gain data interval, and using this coefficient as resource adjustment data, the investment resources corresponding to object categories with smaller unit object gain resources can be reduced, thereby increasing the probability of users investing virtual resources in objects, so as to better improve the object conversion effect, reduce the invalid push of object information, and effectively improve system performance.

[0112] In a specific embodiment, the resource adjustment data may be used to adjust the input resources corresponding to multiple object categories while balancing the input gain data corresponding to the multiple object categories.

[0113] In step S103, original input resources corresponding to the plurality of object categories are adjusted based on the resource adjustment data to obtain target input resources corresponding to the plurality of object categories.

[0114] In a specific embodiment, the above-mentioned preset condition is a preset constraint interval, and correspondingly, the above-mentioned resource adjustment data can be a resource adjustment parameter interval corresponding to the preset constraint interval. Optionally, the above-mentioned adjustment of the original input resources corresponding to multiple object categories based on the resource adjustment data to obtain the target investment resources corresponding to the multiple object categories may include: randomly determining a resource adjustment parameter from the resource adjustment data corresponding to each object category, and multiplying the resource adjustment parameter corresponding to each object category by the corresponding original input resource to obtain the target investment resource corresponding to each object category.

[0115] In an optional embodiment, if Figure 3 As shown, the above method may also include:

[0116] In step S104, a preset upper limit parameter is obtained;

[0117] In step S105, based on a preset upper limit parameter, target resource adjustment data is determined from the resource adjustment parameter interval;

[0118] Accordingly, in the above step S103, adjusting the original input resources corresponding to the multiple object categories based on the resource adjustment data to obtain the target input resources corresponding to the multiple object categories may include:

[0119] The original input resources are adjusted based on the target resource adjustment data to obtain target input resources corresponding to multiple object categories.

[0120] In a specific embodiment, the preset upper limit parameter may be an upper limit value of a preset resource adjustment parameter. Optionally, the target resource adjustment data may be a resource adjustment parameter in a resource adjustment parameter interval that is less than or equal to the preset upper limit parameter; optionally, a resource adjustment parameter less than or equal to the preset upper limit parameter may be randomly determined from the resource adjustment parameter interval as the target resource adjustment data; accordingly, the target resource adjustment data corresponding to each object category may be multiplied by the corresponding original input resource to obtain the target input resource corresponding to each object category.

[0121] Optionally, the above target resource adjustment data may be a resource adjustment parameter interval whose upper limit is a preset upper limit parameter. Optionally, assuming that the resource adjustment parameter region corresponding to the preset constraint interval is [0.8, 1.3], and the preset upper limit parameter is 1.2; accordingly, the target resource adjustment data may be [0.8, 1.2].

[0122] In a specific embodiment, when the target resource adjustment data is a resource adjustment parameter interval whose upper limit is a preset upper limit parameter, adjusting the original input resources based on the target resource adjustment data to obtain target investment resources corresponding to multiple object categories may include: randomly determining a resource adjustment parameter from the target resource adjustment data corresponding to each object category; multiplying the resource adjustment parameter corresponding to each object category by the corresponding original input resource to obtain the target investment resource corresponding to each object category.

[0123] In the above embodiment, during the resource investment adjustment process, combined with the restriction of the target resource adjustment data by the preset upper limit parameters, it is possible to effectively avoid the target investment resources corresponding to certain object categories with higher investment gain data being too high, thereby better improving the probability of users investing virtual resources in objects, better improving the object conversion effect, reducing the invalid push of object information, reducing the resource waste of the object recommendation system, and improving system performance.

[0124] In an optional embodiment, if Figure 4 As shown, the above method may also include:

[0125] In step S106, the accumulated input resources corresponding to the multiple object categories and the accumulated loss resources corresponding to the multiple object categories in the historical time period are obtained;

[0126] In step S107, the loss input data is determined according to the accumulated loss resources and the accumulated input resources;

[0127] In a specific embodiment, the accumulated investment resources corresponding to each object category may be the total virtual resources invested in each object category. Optionally, taking the object return scenario as an example, the accumulated investment resources corresponding to each object category may be the total virtual resources invested in the object return corresponding to the object category; taking the object delivery scenario as an example, the accumulated investment resources corresponding to each object category may be the total virtual resources invested in delivering multimedia resources corresponding to a certain object category.

[0128] In a specific embodiment, the accumulated loss resources corresponding to each object category may be the virtual resource loss corresponding to the object under each object category. Optionally, taking the object return scenario as an example, the accumulated loss resources may be the virtual resource loss caused by the object return; taking the object delivery scenario as an example, the accumulated loss resources may be the virtual resource loss corresponding to the application retention time loss caused by the multimedia resources corresponding to the delivery object (specifically, the corresponding relationship between the application retention time loss and the virtual resource loss may be pre-constructed).

[0129] In a specific embodiment, the accumulated loss resources corresponding to each object category may be divided by the accumulated investment resources corresponding to the object category to obtain the corresponding loss investment data corresponding to the object category. Accordingly, the loss investment data corresponding to the object category may represent the proportion of the accumulated loss resources corresponding to the object category in the accumulated investment resources corresponding to the object category.

[0130] In an optional embodiment, in the above step S103, the original investment resources corresponding to multiple object categories are adjusted based on the resource adjustment data to obtain the target investment resources corresponding to the multiple object categories, including: adjusting the original investment resources based on the resource adjustment data and the loss investment data to obtain the target investment resources corresponding to the multiple object categories.

[0131] In an optional embodiment, the original input resources are adjusted based on the resource adjustment data and the loss input data to obtain target input resources corresponding to multiple object categories, which may include:

[0132] Obtain historical resource adjustment parameters corresponding to multiple object categories in historical time periods;

[0133] When the loss input data is greater than or equal to a preset threshold, first resource adjustment parameters corresponding to multiple object categories are determined from the resource adjustment parameter interval, and the first resource adjustment parameter corresponding to any object category is greater than the historical resource adjustment parameter corresponding to any object category.

[0134] In an optional embodiment, the resource adjustment data may be updated every preset time. Optionally, the above historical time period may be a time period corresponding to a preset time before the current time (i.e., the previous resource adjustment data update cycle). Taking the preset time as 1 month as an example, the historical time period may be one month before the current time. In a specific embodiment, the historical resource adjustment parameters corresponding to any object category in the historical time period may be the resource adjustment parameters of the object category in the previous resource adjustment data update cycle.

[0135] In a specific embodiment, the preset threshold may be a lower limit of the loss input data set in combination with actual application requirements; when the loss input data is greater than or equal to the preset threshold, a first resource adjustment parameter greater than the historical resource adjustment parameter is determined from the resource adjustment parameter interval, and the resource adjustment parameter in the current period may be appropriately adjusted to increase the accumulated input resources in the current period.

[0136] In addition, it should be noted that if the loss investment data is greater than or equal to a preset threshold, the resource adjustment parameters corresponding to all object categories in the above-mentioned multiple object categories can be adjusted up, or only the resource adjustment parameters corresponding to most of the object categories can be adjusted, on the premise of ensuring that the determined resource adjustment parameters are within the resource adjustment parameter range; optionally, the resource adjustment parameters corresponding to most of the object categories that are not adjusted can be historical resource adjustment parameters.

[0137] In the above embodiment, if the loss investment data is greater than or equal to the preset threshold, that is, the proportion of the accumulated loss resources in the accumulated investment resources exceeds the preset threshold, the accumulated investment resources can be increased by appropriately increasing the resource adjustment parameters, thereby ensuring that the loss investment data is within an appropriate range, thereby improving the rationality and effectiveness of resource adjustment.

[0138] In an optional embodiment, the original input resources are adjusted based on the resource adjustment data and the loss input data to obtain target input resources corresponding to multiple object categories, and further includes:

[0139] When the loss input number is less than a preset threshold, second resource adjustment parameters corresponding to multiple object categories are determined from the resource adjustment parameter interval, and the second resource adjustment parameter corresponding to any object category is less than the historical resource adjustment parameter corresponding to any object category.

[0140] In a specific embodiment, when the loss input data is less than a preset threshold, a second resource adjustment parameter that is less than the historical resource adjustment parameter is determined from the resource adjustment parameter interval, and the resource adjustment parameter in the current cycle can be appropriately adjusted to reduce the accumulated input resources in the current cycle.

[0141] In addition, it should be noted that if the loss investment data is less than a preset threshold, the resource adjustment parameters corresponding to all object categories in the above-mentioned multiple object categories can be adjusted down, or only the resource adjustment parameters corresponding to some object categories can be adjusted down, under the premise of ensuring that the determined resource adjustment parameters are within the resource adjustment parameter range; optionally, the resource adjustment parameters corresponding to the object categories that have not been adjusted down can be historical resource adjustment parameters.

[0142] In the above embodiment, if the loss investment data is less than the preset threshold, that is, the proportion of the accumulated loss resources in the accumulated investment resources is less than the preset threshold, the accumulated investment resources can be appropriately reduced by appropriately reducing the resource adjustment parameters, thereby ensuring that the loss investment data is within an appropriate range, thereby improving the rationality and effectiveness of resource adjustment.

[0143] In another optional embodiment, Figure 5 As shown, the original input resources are adjusted based on the target resource adjustment data to obtain target input resources corresponding to multiple object categories, which may include:

[0144] The original input resources are adjusted based on the target resource adjustment data and the loss input data to obtain target input resources corresponding to multiple object categories.

[0145] In a specific embodiment, the original input resources are adjusted based on the target resource adjustment data and the loss investment data to obtain specific details of the target investment resources corresponding to multiple object categories. Please refer to the above-mentioned adjustment of the original input resources based on the resource adjustment data and the loss investment data to obtain specific details of the target investment resources corresponding to multiple object categories, which will not be repeated here.

[0146] In the above embodiment, during the resource investment adjustment process, the current resource adjustment data is adjusted in combination with the loss investment data corresponding to multiple object categories in the historical time period, which can effectively control the loss investment data within an appropriate range, thereby better improving the probability of users investing virtual resources in objects, better improving object conversion effects, reducing the invalid push of object information, reducing resource waste in the object recommendation system, and improving system performance.

[0147] It can be seen from the technical solutions provided in the above embodiments of this specification that this specification analyzes the investment gain data corresponding to multiple object categories in combination with preset conditions, and can configure smaller resource adjustment data for object categories with higher investment gain data, and configure larger resource adjustment data for object categories with lower investment gain data; and based on the resource adjustment data, the original investment resources corresponding to each of the multiple object categories are adjusted, and the investment resources corresponding to the multiple object categories can be adjusted while balancing the investment gain data corresponding to the multiple object categories. Furthermore, by balancing the investment gain data corresponding to the multiple object categories, the probability of users investing virtual resources in objects can be increased, so as to improve the object conversion effect and reduce the invalid push of object information, thereby also achieving the technical effect of reducing the waste of system resources of the object recommendation system and improving system performance.

[0148] Figure 6 is a block diagram of a resource adjustment device according to an exemplary embodiment. Figure 6 , the device comprises:

[0149] The investment gain data acquisition module 610 is configured to execute acquisition of investment gain data corresponding to multiple object categories, where the investment gain data represents the virtual resource increment brought by acquiring a single object under the multiple object categories and the virtual resources required to be invested;

[0150] The analysis module 620 is configured to analyze the input gain data based on preset conditions and the input gain data corresponding to each object category to obtain resource adjustment data corresponding to multiple object categories, where the resource adjustment data is used to adjust the input resources corresponding to the multiple object categories while balancing the input gain data corresponding to the multiple object categories;

[0151] The resource adjustment module 630 is configured to adjust the original input resources corresponding to the multiple object categories based on the resource adjustment data to obtain the target input resources corresponding to the multiple object categories.

[0152] In an optional embodiment, the preset condition is a preset constraint interval, the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval, and the apparatus further includes:

[0153] A preset upper limit parameter acquisition module is configured to execute acquisition of a preset upper limit parameter;

[0154] a target resource adjustment data determination module, configured to determine the target resource adjustment data from the resource adjustment parameter interval based on a preset upper limit parameter;

[0155] The resource adjustment module 630 is further configured to execute: adjusting the original input resources based on the target resource adjustment data to obtain target input resources corresponding to the multiple object categories.

[0156] In an optional embodiment, the above device further includes:

[0157] A resource acquisition module is configured to execute acquisition of accumulated investment resources corresponding to multiple object categories and accumulated loss resources corresponding to multiple object categories within a historical time period;

[0158] A loss input data determination module is configured to determine the loss input data according to the accumulated loss resources and the accumulated input resources;

[0159] The resource adjustment module 630 is further configured to execute: adjusting the original input resources based on the resource adjustment data and the loss input data to obtain target input resources corresponding to the multiple object categories.

[0160] In an optional embodiment, the preset condition is a preset constraint interval, and the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval;

[0161] The resource adjustment module 630 includes:

[0162] A historical resource adjustment parameter acquisition unit is configured to acquire historical resource adjustment parameters corresponding to multiple object categories in a historical time period;

[0163] The first resource adjustment parameter determination unit is configured to determine the first resource adjustment parameters corresponding to multiple object categories from the resource adjustment parameter interval when the loss investment data is greater than or equal to a preset threshold, and the first resource adjustment parameter corresponding to any object category is greater than the historical resource adjustment parameter corresponding to any object category.

[0164] In an optional embodiment, the resource adjustment module 630 further includes:

[0165] The second resource adjustment parameter determination unit is configured to execute, when the loss input number is less than a preset threshold, determining second resource adjustment parameters corresponding to multiple object categories from the resource adjustment parameter interval, and the second resource adjustment parameter corresponding to any object category is less than the historical resource adjustment parameter corresponding to any object category.

[0166] In an optional embodiment, the above-mentioned input gain data acquisition module 610 includes:

[0167] The original input resource acquisition unit is configured to execute acquisition of original input resources corresponding to a plurality of object categories;

[0168] A unit object gain resource acquisition unit is configured to acquire unit object gain resources corresponding to a plurality of object categories;

[0169] The investment gain data determining unit is configured to determine the investment gain data according to the original investment resources and the unit object gain resources.

[0170] In an optional embodiment, the above-mentioned original input resource acquisition unit includes:

[0171] A target object loss data acquisition unit is configured to acquire target object loss data corresponding to a plurality of object categories;

[0172] An original input resource determination unit is configured to determine original input resources corresponding to a plurality of object categories according to preset loss resource information and target object loss data;

[0173] Among them, the preset loss resource information represents the corresponding relationship between the loss data of different objects and the input resources.

[0174] In an optional embodiment, the unit object gain resource acquisition unit includes:

[0175] A gain data acquisition unit is configured to acquire object gain rates corresponding to a plurality of object categories and unit object resources corresponding to a plurality of object categories;

[0176] The unit object gain resource subunit is configured to determine the unit object gain resource according to the object gain rate and the unit object resource.

[0177] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0178] Figure 7 is a block diagram of an electronic device for resource adjustment according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a resource adjustment method is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0179] Figure 8 is a block diagram of an electronic device for resource adjustment according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a resource adjustment method is implemented.

[0180] Those skilled in the art will understand that Figure 7 or Figure 8The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0181] In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the resource adjustment method in the embodiment of the present disclosure.

[0182] In an exemplary embodiment, a computer-readable storage medium is further provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the resource adjustment method in the embodiment of the present disclosure.

[0183] In an exemplary embodiment, a computer program product containing instructions is also provided. When the computer program product is run on a computer, the computer is enabled to execute the resource adjustment method in the embodiment of the present disclosure.

[0184] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0185] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0186] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A resource adjustment method, characterized in that: include: Obtaining investment gain data corresponding to multiple object categories, wherein the investment gain data represents the virtual resource increment brought by obtaining a single object under the multiple object categories and the virtual resources required to be invested; The multiple object categories are multiple commodity categories; Based on preset conditions and the input gain data corresponding to each object category, the input gain data is analyzed to obtain resource adjustment data corresponding to the multiple object categories, wherein the resource adjustment data is used to adjust the input resources corresponding to the multiple object categories while balancing the input gain data corresponding to the multiple object categories; The preset condition is a preset constraint interval, and the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval; the product of the input gain data corresponding to each object category and any resource adjustment parameter in the resource adjustment parameter interval corresponding to each object category is within the preset constraint interval; The original input resources corresponding to the multiple object categories are adjusted based on the resource adjustment data to obtain target input resources corresponding to the multiple object categories.

2. The resource adjustment method according to claim 1, characterized in that: The method further comprises: Get the preset upper limit parameter; Based on the preset upper limit parameter, determining target resource adjustment data from the resource adjustment parameter interval; The adjusting the original input resources corresponding to the multiple object categories based on the resource adjustment data to obtain the target input resources corresponding to the multiple object categories includes: The original input resources are adjusted based on the target resource adjustment data to obtain target input resources corresponding to the multiple object categories.

3. The resource adjustment method according to claim 1, characterized in that: The method further comprises: Obtaining the accumulated input resources corresponding to the plurality of object categories and the accumulated loss resources corresponding to the plurality of object categories in a historical time period; Determining loss investment data according to the accumulated loss resources and the accumulated investment resources; The adjusting the original input resources corresponding to the multiple object categories based on the resource adjustment data to obtain the target input resources corresponding to the multiple object categories includes: The original input resources are adjusted based on the resource adjustment data and the loss input data to obtain target input resources corresponding to the multiple object categories.

4. The resource adjustment method according to claim 3, characterized in that: The preset condition is a preset constraint interval, and the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval; The adjusting the original input resources based on the resource adjustment data and the loss input data to obtain the target input resources corresponding to the multiple object categories includes: Obtain historical resource adjustment parameters corresponding to the multiple object categories in the historical time period; When the loss input data is greater than or equal to a preset threshold, the first resource adjustment parameter corresponding to the multiple object categories is determined from the resource adjustment parameter interval, and the first resource adjustment parameter corresponding to any object category is greater than the historical resource adjustment parameter corresponding to any of the object categories.

5. The resource adjustment method according to claim 4, characterized in that: The adjusting the original input resources based on the resource adjustment data and the loss input data to obtain the target input resources corresponding to the multiple object categories further includes: When the loss input number is less than the preset threshold, the second resource adjustment parameters corresponding to the multiple object categories are determined from the resource adjustment parameter interval, and the second resource adjustment parameter corresponding to any object category is less than the historical resource adjustment parameter corresponding to any of the object categories.

6. The resource adjustment method according to any one of claims 1 to 5, characterized in that: The step of obtaining the input gain data corresponding to the multiple object categories includes: Acquire original input resources corresponding to the multiple object categories; Acquire unit object gain resources corresponding to the multiple object categories; The investment gain data is determined according to the original investment resources and the unit object gain resources.

7. The resource adjustment method according to claim 6, characterized in that: The acquiring of the original input resources corresponding to the plurality of object categories comprises: Obtaining target object loss data corresponding to the multiple object categories; Determining original input resources corresponding to the plurality of object categories according to preset loss resource information and the target object loss data; The preset loss resource information represents the corresponding relationship between loss data of different objects and input resources.

8. The resource adjustment method according to claim 6, characterized in that: The acquiring of the unit object gain resources corresponding to the plurality of object categories comprises: Acquire object gain rates corresponding to the plurality of object categories and unit object resources corresponding to the plurality of object categories; The unit object gain resource is determined according to the object gain rate and the unit object resource.

9. A resource adjustment device, characterized in that: include: An investment gain data acquisition module is configured to execute acquisition of investment gain data corresponding to a plurality of object categories, wherein the investment gain data represents the virtual resource increment brought by acquiring a single object under the plurality of object categories and the virtual resources required to be invested; The multiple object categories are multiple commodity categories; an analysis module configured to analyze the input gain data based on preset conditions and the input gain data corresponding to each object category to obtain resource adjustment data corresponding to the multiple object categories, wherein the resource adjustment data is used to adjust the input resources corresponding to the multiple object categories while balancing the input gain data corresponding to the multiple object categories; The preset condition is a preset constraint interval, and the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval; the product of the input gain data corresponding to each object category and any resource adjustment parameter in the resource adjustment parameter interval corresponding to each object category is within the preset constraint interval; The resource adjustment module is configured to adjust the original input resources corresponding to the multiple object categories based on the resource adjustment data to obtain target input resources corresponding to the multiple object categories.

10. The resource adjustment device according to claim 9, characterized in that: The device also includes: A preset upper limit parameter acquisition module is configured to execute acquisition of a preset upper limit parameter; a target resource adjustment data determination module, configured to determine target resource adjustment data from the resource adjustment parameter interval based on the preset upper limit parameter; The resource adjustment module is further configured to execute: adjusting the original input resources based on the target resource adjustment data to obtain the target input resources corresponding to the multiple object categories.

11. The resource adjustment device according to claim 9, characterized in that: The device also includes: A resource acquisition module is configured to execute acquisition of the accumulated input resources corresponding to the plurality of object categories and the accumulated loss resources corresponding to the plurality of object categories within a historical time period; A loss input data determination module is configured to determine loss input data according to the accumulated loss resources and the accumulated input resources; The resource adjustment module is further configured to execute: adjusting the original input resources based on the resource adjustment data and the loss input data to obtain target input resources corresponding to the multiple object categories.

12. The resource adjustment device according to claim 11, characterized in that: The preset condition is a preset constraint interval, and the resource adjustment data is a resource adjustment parameter interval corresponding to the preset constraint interval; The resource adjustment module includes: A historical resource adjustment parameter acquisition unit, configured to execute acquisition of historical resource adjustment parameters corresponding to the plurality of object categories in the historical time period; The first resource adjustment parameter determination unit is configured to determine the first resource adjustment parameters corresponding to the multiple object categories from the resource adjustment parameter interval when the loss investment data is greater than or equal to a preset threshold, and the first resource adjustment parameter corresponding to any object category is greater than the historical resource adjustment parameter corresponding to any object category.

13. The resource adjustment device according to claim 12, characterized in that: The resource adjustment module also includes: The second resource adjustment parameter determination unit is configured to determine the second resource adjustment parameters corresponding to the multiple object categories from the resource adjustment parameter interval when the loss input number is less than the preset threshold, and the second resource adjustment parameter corresponding to any object category is less than the historical resource adjustment parameter corresponding to any object category.

14. The resource adjustment device according to any one of claims 9 to 13, characterized in that: The input gain data acquisition module includes: An original input resource acquisition unit is configured to execute acquisition of original input resources corresponding to the plurality of object categories; A unit object gain resource acquisition unit, configured to execute acquisition of unit object gain resources corresponding to the plurality of object categories; The investment gain data determining unit is configured to determine the investment gain data according to the original investment resources and the unit object gain resources.

15. The resource adjustment device according to claim 13, characterized in that: The original input resource acquisition unit includes: A target object loss data acquisition unit is configured to acquire target object loss data corresponding to the plurality of object categories; An original input resource determination unit is configured to determine the original input resources corresponding to the plurality of object categories according to preset loss resource information and the target object loss data; The preset loss resource information represents the corresponding relationship between loss data of different objects and input resources.

16. The resource adjustment device according to claim 14, characterized in that: The unit object gain resource acquisition unit includes: A gain data acquisition unit, configured to acquire object gain rates corresponding to the plurality of object categories and unit object resources corresponding to the plurality of object categories; The unit object gain resource subunit is configured to determine the unit object gain resource according to the object gain rate and the unit object resource.

17. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the resource adjustment method according to any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the resource adjustment method as claimed in any one of claims 1 to 8.

19. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the resource adjustment method according to any one of claims 1 to 8 is implemented.

Citation Information

Patent Citations

  • Resource sharing system and resource sharing method

    CN103986749A

  • System resource balance adjustment method and device

    CN104679589A

  • Method and device for resource allocation

    CN106203750A

  • Scheduling the same resource in radio access networks

    CN106797641A

  • Commodity resource configuration method and system

    CN110245989A