Welfare resource recommendation method and device, equipment and medium

Abstract

The application relates to a welfare resource recommendation method and device, equipment and medium. The method comprises the following steps: determining a welfare resource distribution entrance corresponding to an online user and a traffic group corresponding to the online user; determining a target resource pool based on the welfare resource distribution entrance; performing traffic horse race sorting on each welfare resource in the target resource pool according to a preset welfare distribution rule corresponding to the traffic group, so as to obtain a traffic horse race sorting result corresponding to each welfare resource; selecting a target recommended welfare resource from the welfare resources based on the traffic horse race sorting result; and recommending the target recommended welfare resource to the online user, so that a welfare recommendation mode based on a traffic horse race mechanism is realized, and the problem caused by the fact that in the prior art, an operator separately sorts and recommends welfare resources according to each position is solved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, device and medium for recommending welfare resources. Background Technology

[0002] With the continuous development of smart terminal technology, the types and number of applications that can be installed on smart terminals are increasing. Due to the portability of smart terminals, users are becoming increasingly reliant on them in their daily lives. Currently, many platforms, especially video platforms, often rely on applications installed on smart terminals to disseminate or promote various information through media. As a medium for information transmission, media outlets, based on protocols with platforms, typically send the information the platform wants to promote to media users through browser pop-ups, push notifications, and other means.

[0003] In practical implementation, applications that facilitate promotion and user management typically have membership systems to recommend relevant benefits to members, enabling them to enjoy corresponding membership privileges. As the importance of membership benefits increases, and the number, types, and distribution channels for these benefits also expand, relying solely on operations staff to sort benefits individually according to the location of each distribution channel would require significant manpower. Summary of the Invention

[0004] In view of this, this application provides a welfare resource recommendation method, apparatus, device and medium to solve the problems caused by the prior art relying solely on the operator to sort and recommend welfare resources according to the location of each distribution entry.

[0005] Firstly, this application provides a method for recommending welfare resources, including:

[0006] Determine the distribution entry point for welfare resources corresponding to online users and the traffic group corresponding to the online users;

[0007] The target resource pool is determined based on the aforementioned welfare resource distribution entry point;

[0008] Based on the preset welfare distribution rules corresponding to the traffic groups, the traffic horse race ranking of each welfare resource in the target resource pool is performed to obtain the traffic horse race ranking result corresponding to each welfare resource;

[0009] Based on the traffic ranking results, target recommended welfare resources are selected from each welfare resource.

[0010] The target recommended benefits and resources are recommended to the online users.

[0011] Optionally, the step of performing a traffic race ranking on each welfare resource in the target resource pool according to the preset welfare distribution rules corresponding to the traffic group, to obtain the traffic race ranking result corresponding to each welfare resource, includes:

[0012] When the welfare distribution rule is a horse racing group distribution rule, the rule group to which each welfare resource in the target resource pool belongs is determined respectively;

[0013] Based on the rule grouping, determine the indicator parameter information corresponding to each welfare resource;

[0014] Based on the aforementioned indicator parameters, the popularity of each welfare resource is determined by using the click exposure information and redemption information for each of the welfare resources.

[0015] The traffic ranking results are obtained by sorting the traffic based on its popularity.

[0016] Optionally, the rule grouping includes a horse racing group and a reserve group. When the welfare distribution rule is a horse racing group distribution rule, determining the rule group to which each welfare resource in the target resource pool belongs includes:

[0017] When the welfare distribution rule is the horse racing group distribution rule, the online duration of each welfare resource is determined by the online release time of each welfare resource.

[0018] If the online duration does not reach the preset duration threshold, determine whether the traffic accumulation data of the welfare resources meets the preset traffic race conditions;

[0019] If the accumulated traffic data meets the traffic horse racing conditions, then the horse racing group is determined as the rule group to which the welfare resource belongs;

[0020] If the accumulated traffic data does not meet the traffic race conditions, then the power accumulation group will be determined as the rule group to which the welfare resource belongs.

[0021] Optionally, after determining the online duration of each of the welfare resources, the method further includes:

[0022] Determine whether the online duration of each welfare resource has reached the preset duration threshold.

[0023] If the online duration of the welfare resource reaches the preset duration threshold, the step of determining the horse racing group as the rule group to which the welfare resource belongs is executed.

[0024] Optionally, based on the rule grouping, the indicator parameter information corresponding to each welfare resource is determined, including:

[0025] When the rule grouping is a power-accumulation grouping, the preset new welfare indicator parameters corresponding to the power-accumulation grouping are determined as the indicator parameter information;

[0026] When the rule grouping is a horse racing group, the preset horse racing welfare index parameters corresponding to the horse racing group are determined as the index parameter information.

[0027] Optionally, based on the aforementioned indicator parameter information, the popularity of each welfare resource is determined using the click exposure information and redemption information for each of the welfare resources, including:

[0028] Obtain the operational promotion information corresponding to each of the aforementioned welfare resources;

[0029] For each of the aforementioned welfare resources, based on the welfare score corresponding to the main operational information, the popularity score corresponding to the welfare resource is calculated using the indicator parameter information, the click exposure information, and the redemption information.

[0030] The popularity score is used to determine the degree of popularity.

[0031] Optionally, determining the distribution entry point for welfare resources corresponding to online users includes:

[0032] Obtain user actions;

[0033] The online user is identified using the user identifier carried by the user operation.

[0034] The entry point for distributing welfare resources is determined based on the location of the online user's operation.

[0035] Secondly, this application provides a welfare resource recommendation device, comprising:

[0036] The determination module is used to determine the welfare resource distribution entry point corresponding to the online user and the traffic group corresponding to the online user;

[0037] The target resource pool module is used to determine the target resource pool based on the welfare resource distribution entry point;

[0038] The traffic ranking module is used to rank each welfare resource in the target resource pool according to the preset welfare distribution rules corresponding to the traffic group, and obtain the traffic ranking result corresponding to each welfare resource.

[0039] The target recommendation welfare resource module is used to select target recommendation welfare resources from the welfare resources based on the traffic horse racing ranking results;

[0040] The welfare resource recommendation module is used to recommend the target welfare resources to the online users.

[0041] Thirdly, this application provides an electronic device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to: determine a welfare resource distribution entry point corresponding to an online user and a traffic group corresponding to the online user; determine a target resource pool based on the welfare resource distribution entry point; perform a traffic race ranking of each welfare resource in the target resource pool according to a preset welfare distribution rule corresponding to the traffic group, and obtain a traffic race ranking result corresponding to each welfare resource; select a target recommended welfare resource from the welfare resources based on the traffic race ranking result; and recommend the target recommended welfare resource to the online user.

[0042] Fourthly, this application also provides a computer storage medium storing a computer program, which, when executed by a processor, implements the steps of the welfare resource recommendation method as described in any of the preceding claims of this application.

[0043] The technical solution provided in this application determines the welfare resource distribution entry point corresponding to the online user and the traffic group corresponding to the online user, and determines the target resource pool based on the welfare resource distribution entry point. Then, according to the preset welfare distribution rules corresponding to the traffic group, the welfare resources in the target resource pool are sorted by traffic competition to obtain the traffic competition ranking result corresponding to each welfare resource. Based on the traffic competition ranking result, target recommended welfare resources are selected from each welfare resource and recommended to online users. This realizes a welfare recommendation method based on a traffic competition mechanism, reduces the cost of human resource allocation, and solves the problem caused by the existing related technologies that rely solely on operators to sort and recommend welfare resources individually according to each position. In this way, it can recommend high-quality welfare resources to most users, improve user experience and rights satisfaction. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1This application provides a flowchart illustrating the steps of a welfare resource recommendation method.

[0047] Figure 2 A schematic diagram illustrating traffic grouping is provided as an example of this application;

[0048] Figure 3 A flowchart illustrating the steps of a welfare resource recommendation method provided in an optional embodiment of this application;

[0049] Figure 4 A schematic diagram illustrating a horse racing group distribution rule, provided as an example of this application;

[0050] Figure 5 This is a schematic diagram illustrating a welfare resource recommendation method provided as an example for this application.

[0051] Figure 6 A structural block diagram of a welfare resource recommendation device provided in an embodiment of this application;

[0052] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0054] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0055] In related technologies, recommending high-quality and matching benefits to more users and improving user satisfaction is a shared expectation of both benefit operators and users. However, existing technologies rely solely on operators sorting benefit resources individually for each position, which requires significant manpower and cannot accurately reach the needs of different users, thus failing to guarantee the achievement of ultimate operational goals and the improvement of customer satisfaction.

[0056] To address the aforementioned issues, this application proposes a welfare resource recommendation method. This method involves determining the welfare resource distribution entry point corresponding to an online user and the traffic group corresponding to that user. Based on the welfare resource distribution entry point, a target resource pool is determined. Then, according to preset welfare distribution rules corresponding to the traffic group, each welfare resource in the target resource pool is ranked using a traffic competition mechanism. This yields the traffic competition ranking result for each welfare resource. Based on the traffic competition ranking result, target recommended welfare resources are selected from these resources and recommended to online users. This achieves a welfare recommendation method based on a traffic competition mechanism, reducing manpower allocation costs and solving the problem caused by existing related technologies where only operations personnel individually rank and recommend welfare resources for each location.

[0057] It should be noted that welfare resources can refer to benefits that can be received and / or used on online platforms, such as cash red envelopes, coupons, vouchers, etc. that can be used on shopping or movie platforms. This embodiment does not limit this.

[0058] Figure 1 This is a flowchart illustrating the steps of a welfare resource recommendation method provided in an embodiment of this application. Figure 1 As shown in the embodiments of this application, the welfare resource recommendation method may specifically include the following steps:

[0059] Step 110: Determine the welfare resource distribution entry point corresponding to the online user and the traffic group corresponding to the online user;

[0060] Online users refer to users who are online. For example, once a user logs in, they can be identified as an online user. Specifically, when distributing welfare resources, the welfare resource distribution entry point corresponding to the online user can be determined based on the welfare distribution entry point where the online user is located. For example, the distribution entry point corresponding to the welfare distribution entry point where the online user is located can be determined as the welfare resource distribution entry point for the online user, and the traffic group to which the online user belongs can be determined as the traffic group corresponding to the online user.

[0061] It should be noted that the welfare resource distribution entry point in this embodiment refers to the distribution entry point for welfare resources; the traffic group corresponding to online users can refer to the traffic group assigned to online users after they go online according to the online grouping method, so that welfare distribution rules can be determined according to the traffic group later. For example, different users can be randomly assigned to different traffic groups in advance according to the online welfare distribution strategy method. The specific allocation method can refer to the online traffic group, and this embodiment does not limit it. For example, when the traffic group includes an online operation group, an algorithm group, and a horse racing rule group, such as Figure 2As shown, based on the online benefits distribution strategy, 40% of the total traffic can be allocated to the online operations group, 40% of the online users can be allocated to the online operations group, 40% of the total traffic can be allocated to the horse racing rules group, 40% of the online users can be allocated to the horse racing rules group, and 20% of the total traffic can be allocated to the algorithm group, 20% of the users can be allocated to the algorithm group.

[0062] Step 120: Determine the target resource pool based on the welfare resource distribution entry point;

[0063] In this embodiment, different welfare resource distribution entry points are connected to different resource pools. After determining the welfare resource distribution entry point, this embodiment can define the resource pool connected to that entry point as the target resource pool, so that at least one target welfare resource can be selected from the target resource pool and recommended to offline users. Here, a resource pool can refer to a pool composed of welfare resources, specifically containing one or more welfare resources; this embodiment does not impose any limitations on this.

[0064] Step 130: Based on the preset welfare distribution rules corresponding to the traffic group, perform a traffic horse race ranking on each welfare resource in the target resource pool to obtain the traffic horse race ranking result corresponding to each welfare resource.

[0065] Specifically, this embodiment can pre-set different welfare distribution rules for different traffic groups. This allows for a traffic ranking of each welfare resource in the target resource pool based on the preset welfare distribution rules corresponding to the traffic group during subsequent welfare resource distribution. This solves the problem caused by existing related technologies where operators rely solely on the location of each distribution entry point to rank welfare resources individually. Specifically, after determining the traffic group corresponding to the online user, this embodiment can calculate the popularity of each welfare resource in the target resource pool according to the preset welfare distribution rules for that traffic group, using the indicator parameters set in the welfare distribution rules. Based on this popularity, a traffic ranking is then performed on each welfare resource in the target resource pool to obtain the traffic ranking result. This traffic ranking result can include the ranking of each welfare resource in the target resource pool; the ranking of the welfare resource can represent the proportion of traffic allocated to that welfare resource. For example, the higher the popularity of a welfare resource, the higher its ranking, and the more traffic is allocated to that welfare resource each month. This prioritizes traffic to popular welfare resources, achieving the goal of recommending high-quality welfare resources to online users.

[0066] The indicator parameter information can refer to the indicator parameters that are pre-set in the welfare distribution rules. Specifically, it can be used to determine the popularity of welfare resources. For example, the indicator parameter information preset in the welfare distribution rules can include indicator score parameters corresponding to the number of clicks / exposures, indicator score parameters corresponding to the number of redemptions, etc. This embodiment does not impose specific restrictions on this.

[0067] Step 140: Based on the traffic horse racing ranking results, select target recommended welfare resources from the various welfare resources;

[0068] Specifically, in this embodiment, after determining the traffic ranking results for each welfare resource in the target resource pool, one or at least two of the most popular welfare resources can be selected from each welfare resource based on the traffic ranking results and the welfare resource recommendation requirements, as target recommended welfare resources. This embodiment does not impose a specific limit on the number of target recommended welfare resources.

[0069] Step 150: Recommend the target benefit resources to the online users.

[0070] As can be seen, this embodiment determines the welfare resource distribution entry point corresponding to the online user and the traffic group corresponding to the online user, and then determines the target resource pool based on the welfare resource distribution entry point. Subsequently, according to the preset welfare distribution rules corresponding to the traffic group, the welfare resources in the target resource pool are sorted by traffic competition to obtain the traffic competition ranking result corresponding to each welfare resource. Thus, the target recommended welfare resources can be selected from each welfare resource based on the traffic competition ranking result and recommended to the online user. This realizes a welfare recommendation method based on the traffic competition mechanism, thereby solving the problem caused by the current related technologies that rely solely on operators to sort and recommend welfare resources individually according to each position. It can recommend high-quality welfare resources to most users and reduce manpower configuration costs.

[0071] In some optional embodiments of this application, the welfare resource distribution entry point can be determined based on the location of the user's operation. For example, when a user's login operation is detected, the user's login location can be determined based on the login operation, and the welfare resource distribution entry point can be determined based on the user's login location. Optionally, determining the welfare resource distribution entry point corresponding to an online user in this application embodiment may specifically include: obtaining user operations; using the user identifier carried by the user operations to determine the online user; and determining the welfare resource distribution entry point based on the operation location of the online user. Here, user operations can refer to operations submitted by the online user, such as click operations, etc., and this embodiment does not limit this.

[0072] Specifically, after detecting a user operation, this embodiment can obtain the operation parameters carried by the user operation, determine the operation location based on the operation parameters, and then determine the distribution entry location of the online user based on the operation location. For example, the operation location can be determined as the distribution entry location, so that the welfare resource distribution entry corresponding to the distribution entry location can be determined as the welfare resource distribution entry corresponding to the online user.

[0073] Of course, in addition to determining the welfare resource distribution entry point corresponding to the online user by using the operation location, the embodiments of this application can also determine the welfare resource distribution entry point corresponding to the online user by other means. For example, the welfare resource distribution entry point corresponding to the online user can be determined by the display position name, or by the display position identifier (ID) or operation type. This embodiment does not limit this.

[0074] In one embodiment of this application, after determining the traffic group corresponding to the online user, the strategy method for online welfare distribution can be followed. By judging whether the traffic group corresponding to the online user is a preset horse racing rule group, it can be determined whether to perform traffic horse racing sorting on each welfare resource in the target resource pool according to the preset welfare distribution rule corresponding to the traffic group. In the case that the traffic group corresponding to the online user is a horse racing rule group, the traffic horse racing sorting on each welfare resource in the target resource pool is performed according to the traffic horse racing mechanism.

[0075] For example, combining the above examples, when online users are assigned to a horse racing rule group, that is, when the traffic group corresponding to the online user is a horse racing rule group, the horse racing group distribution rules set in advance for the horse racing rule group can be determined as the preset welfare distribution rules corresponding to the traffic group. Based on the horse racing group distribution rules, different welfare resources in the target resource pool are ranked by traffic horse racing within the rule group of the horse racing rule group using different indicators. Thus, welfare resources can be distributed according to the ranking, achieving the purpose of distributing and recommending high-quality welfare resources to online users. However, when the traffic group corresponding to the online user is not a horse racing rule group, the welfare resources in the target resource pool can be distributed according to the welfare distribution rules corresponding to the traffic group, instead of according to the traffic horse racing mechanism. For example, when a user is assigned to the online operations group, welfare distribution can be achieved by having operations personnel pin individual welfare resources to the top. Or, when an online user is assigned to the algorithm group, welfare distribution can be based on the output of the algorithm click-to-claim model and the redemption model. This embodiment does not impose any restrictions on this.

[0076] Optionally, in this embodiment of the application, based on a preset welfare distribution rule corresponding to the traffic group, a traffic horse race ranking is performed on each welfare resource in the target resource pool to obtain the traffic horse race ranking result corresponding to each welfare resource. Specifically, this may include: when the welfare distribution rule is a horse race group distribution rule, determining the rule group to which each welfare resource in the target resource pool belongs; based on the rule group, determining the indicator parameter information corresponding to each welfare resource; based on the indicator parameter information, determining the popularity of each welfare resource using the click exposure information and redemption information of each welfare resource; and sorting according to the popularity to obtain the traffic horse race ranking result.

[0077] Reference Figure 3 This is a flowchart illustrating the steps of a welfare resource recommendation method provided in an optional embodiment of this application. Figure 3 As shown, the welfare resource recommendation method provided in this application embodiment may include the following steps:

[0078] Step 310: Obtain user actions;

[0079] Step 320: Use the user identifier carried by the user operation to identify the online user;

[0080] Step 330: Determine the welfare resource distribution entry point based on the online user's operation location;

[0081] Step 340: Determine the target resource pool based on the welfare resource distribution entry point;

[0082] Step 350: If the traffic group corresponding to the online user is a horse racing group distribution rule, determine the rule group to which each welfare resource in the target resource pool belongs;

[0083] Specifically, this embodiment can be based on an objective recommendation ranking method, with a high redemption rate as the goal, to divert the total online traffic into different traffic groups. For example, it can be divided into three different traffic groups. The first traffic group is the manual operation group, which accounts for 1% of the total traffic; the second traffic group is the horse racing rule group, which accounts for 2% of the total traffic; and the third traffic group is the algorithm group, which accounts for 3% of the total traffic. It should be noted that X1, X2, and X3 can be the same value or different values. This embodiment does not impose any restrictions on this.

[0084] After identifying the traffic groups corresponding to online users, it can be determined whether the traffic groups corresponding to online users are the preset horse racing rule groups. If the traffic groups corresponding to online users are the horse racing rule groups, the horse racing group distribution rules set in advance for the horse racing rule groups are determined as the preset welfare distribution rules corresponding to the traffic groups. Based on the horse racing group distribution rules, the rule groups to which each welfare resource in the target resource pool belongs can be determined. Within the rule groups of the horse racing rule groups, scores are calculated for different core indicators of welfare resources. Thus, each welfare resource is scored according to different scoring logics to determine the popularity of each welfare resource.

[0085] In one embodiment of this application, the rule group can be divided into a race group and a power-accumulation group. By using the power-accumulation group, the exposure and distribution of newly released welfare resources can be increased by using separate traffic buckets. After the newly released welfare resources accumulate a certain amount of data, they will participate in the race ranking of all welfare resources, so as to ultimately recommend high-quality welfare resources to the majority of users. Optionally, when the rule grouping includes both horse racing groups and accumulation groups, in this embodiment, if the welfare distribution rule corresponding to the online user is a horse racing group distribution rule, the rule group to which each welfare resource in the target resource pool belongs is determined. Specifically, this may include: when the welfare distribution rule is a horse racing group distribution rule, determining the online duration of each welfare resource based on its online release time; if the online duration does not reach a preset duration threshold, determining whether the traffic accumulation data of the welfare resource meets preset traffic horse racing conditions; if the traffic accumulation data meets the traffic horse racing conditions, then the horse racing group is determined as the rule group to which the welfare resource belongs; if the traffic accumulation data does not meet the traffic horse racing conditions, then the accumulation group is determined as the rule group to which the welfare resource belongs. The preset duration threshold can be used to determine whether a welfare resource is a newly released welfare resource. The specific value of this preset duration threshold can be set according to the requirements for classifying new and old welfare resources, and this embodiment does not impose any restrictions on this.

[0086] In an optional embodiment of this application, the welfare resource recommendation method provided in this embodiment, after determining the online duration of each welfare resource, may further include: determining whether the online duration of each welfare resource reaches the preset duration threshold; and if the online duration of the welfare resource reaches the preset duration threshold, performing the step of determining the horse racing group as the rule group to which the welfare resource belongs.

[0087] Specifically, this embodiment can determine whether each welfare resource is a newly launched welfare resource by judging whether the online duration of each welfare resource reaches the preset duration threshold. Specifically, when it is determined that the online duration of a certain welfare resource reaches the preset duration threshold, it can be determined that the welfare resource is not a newly launched welfare resource, and the welfare resource can be assigned to a horse racing group within the horse racing rule group. That is, the step of determining the horse racing group as the rule group to which the welfare resource belongs is executed, so that the popularity of the welfare resource can be determined subsequently based on the preset horse racing welfare index parameters corresponding to the horse racing group. When it is determined that the online duration of a certain welfare resource has not reached the preset duration threshold, it can be determined that the welfare resource is a newly launched welfare resource. It can also be determined whether the traffic accumulation data of the newly launched welfare resource meets the preset traffic race conditions. If the traffic accumulation data of the newly launched welfare resource meets the traffic race conditions, the race group is determined as the rule group to which the newly launched welfare resource belongs. If the traffic accumulation data of the newly launched welfare resource does not meet the traffic race conditions, the power accumulation group is determined as the rule group to which the newly launched welfare resource belongs. This process continues until the traffic accumulation data of the newly launched welfare resource meets the traffic race conditions, at which point the welfare resource is then assigned to a race group for race ranking, thereby achieving the purpose of providing specific welfare support to the newly launched welfare resource.

[0088] For example, since the exposure level of newly launched benefits differs from that of benefits that have been online for a longer period, a certain amount of traffic can be allocated to the accumulation group to which the newly launched benefit belongs through rule grouping. This ensures that the newly launched benefit receives sufficient traffic exposure. For instance, in the example above, if 40% of the total traffic is allocated to the horse racing rule group, 30% of the traffic can be given to the horse racing group, and 10% to the accumulation group to which the newly launched benefit belongs. This allows the newly launched benefit to have sufficient traffic exposure, enabling it to accumulate data as early as possible before entering the horse racing resource pool corresponding to the horse racing group for formal horse racing ranking. This implements a horse racing mechanism that comprehensively considers users' historical redemption and claim data to determine the popularity of benefit resources. Based on this popularity, benefit recommendations can be made, providing a scientific and objective scoring standard for benefit recommendations. Furthermore, by analyzing user behavior data, user preferences can be better understood, leading to more accurate recommendations.

[0089] Step 360: Based on the rule grouping, determine the indicator parameter information corresponding to each welfare resource;

[0090] Specifically, in this embodiment, after grouping the welfare resources in the target resource pool according to the rules, the corresponding indicator parameter information for each welfare resource can be determined according to the preset welfare indicator parameters corresponding to the rule group to which the welfare resource belongs. The welfare indicator parameters can refer to the parameters set for each indicator of the welfare resource, specifically including new welfare indicator scores, old welfare indicator scores, operationally promoted welfare indicator scores, welfare sales within three days indicator parameters, welfare exposure indicator parameters, IP welfare indicator parameters, points indicator parameters, etc. This embodiment does not impose limitations on this. The indicator parameter information corresponding to the welfare resource can refer to the parameter information of each indicator of the welfare resource, such as including the scores corresponding to each indicator parameter, which can be used to determine the popularity of the welfare resource.

[0091] In some optional embodiments of this application, determining the indicator parameter information corresponding to each welfare resource based on the rule grouping can specifically include: when the rule grouping is a power accumulation group, determining the preset new welfare indicator parameter corresponding to the power accumulation group as the indicator parameter information; when the rule grouping is a horse racing group, determining the preset horse racing welfare indicator parameter corresponding to the horse racing group as the indicator parameter information.

[0092] Step 370: Based on the indicator parameter information, the popularity of each welfare resource is determined by using the click exposure information and redemption information of each welfare resource.

[0093] In this embodiment, the click-through information of welfare resources refers to information related to the clicks or exposures of welfare resources, specifically including the number of clicks and exposures, such as the number of clicks or exposures of welfare resources in the past 3 days. This embodiment does not impose any restrictions on this. The redemption information refers to information related to the redemption of welfare resources, specifically including redemption data and redemption volume. This embodiment does not impose any restrictions on this. Specifically, after determining the indicator parameter information corresponding to the welfare resources, this embodiment can calculate the popularity score for each welfare resource using the indicator parameter information, the click-through information, and the redemption information. This popularity score can then be used to determine the popularity of the welfare resource. It should be noted that the higher the popularity score of a welfare resource, the higher its popularity.

[0094] In some optional embodiments of this application, operational recommendation information can be set for welfare resources based on operational suggestions, so as to give welfare resources a certain welfare score according to the operational recommendation information, thereby improving the ranking position of the welfare resources. Further, this embodiment determines the popularity of each welfare resource based on the aforementioned indicator parameter information, using the click exposure information and redemption information of each welfare resource. Specifically, this may include: obtaining the operational recommendation information corresponding to each welfare resource; for each welfare resource, calculating its popularity score based on the welfare score corresponding to the operational recommendation information, using the indicator parameter information, the click exposure information, and the redemption information; and using the popularity score to determine the popularity.

[0095] Among them, the "operation-promoted information" can refer to the information pushed by the operator, such as the information configured by the operator's personnel for the welfare resources they promote. This embodiment does not limit this. The welfare score corresponding to the welfare resource refers to the score set for the welfare resource promoted by the operator. For example, it can be a specific score set for the welfare resource promoted by the operator based on the operation-promoted information, so as to increase the specific score of the welfare resource promoted by the operator, thereby improving the ranking position of the welfare resource, realizing the welfare promotion function, and enabling the operator to use this welfare promotion function to promote specific welfare resources.

[0096] Step 380: Sort the resources according to their popularity to obtain the traffic ranking results for each welfare resource.

[0097] Specifically, in this embodiment, after determining the popularity of each welfare resource in the target resource pool, the welfare resources in the target resource pool can be sorted according to their popularity. Traffic corresponding to the sorting results can be allocated to each welfare resource in the target resource pool. Furthermore, a traffic ranking result can be generated for each welfare resource based on the popularity ranking results. For example, the popularity ranking results can be used as the traffic ranking result for each welfare resource so that popular welfare resources can be selected as target recommended welfare resources for subsequent welfare resource recommendations. This achieves the goal of recommending high-quality welfare resources to users, thereby improving user experience and satisfaction with benefits.

[0098] In some optional embodiments of this application, a welfare point reduction rule based on a low reimbursement rate can be implemented. For welfare resources with a reimbursement rate of 0 or abnormal reimbursement data over three days, the corresponding welfare points can be reduced. For example, welfare resources with no reimbursement data in the past three days could have 10 points reduced. Figure 4As shown, when the reimbursement rate of welfare resources in the past three days is detected to be 0 or null, that is, when there is no reimbursement data for welfare resources in the past three days = 0 or null, it can be determined that the reimbursement data of the welfare resources is abnormal. The welfare score corresponding to the welfare resources can be reduced by 10 points to balance the online sorting and avoid abnormal situations.

[0099] In some optional embodiments of this application, considering the different methods of welfare resource data feedback, different reimbursement scores can be calculated for different feedback methods. For example, when there are three methods of welfare resource data feedback: reimbursement feedback, order feedback, and manual feedback, since reimbursement feedback and order feedback are transmitted in real time through online interfaces, to avoid data deviation, the score is calculated by taking the welfare reimbursement rate of the past three days / welfare exposure volume * 1000. At the same time, since manual feedback requires obtaining welfare resource reimbursement data through offline communication, such as requiring business personnel to communicate with partners offline every week, it may not be possible to update welfare resource reimbursement data every day. Therefore, while retaining the score calculation logic of the past three days, a special reimbursement score rule is also set for this type of welfare resource: if the data has not been updated in the past three days, the reimbursement score is calculated using the data of the past thirty days; if the welfare has no reimbursement / the reimbursement data has not been updated for a long time, the reimbursement score is 0.

[0100] Furthermore, this embodiment can incorporate click data into the scoring system. For example, the click / exposure score of welfare resources can be calculated by taking the click / exposure volume of welfare resources over the past three days. Figure 4 As shown, the click-through score of a benefit resource can be calculated using the formula: (Number of clicks / exposures in the last 3 days) * 1000. Furthermore, it can determine whether a benefit resource is an IP-based benefit resource and allocate IP benefit points accordingly. For example, if a "specific ID" is entered when creating a benefit, it can be considered an IP-based benefit resource and will receive a 1-point reward, thus implementing the IP benefit point reward function. Additionally, it can automatically push benefits that are not yet redeemed to the bottom of the current benefit list, ensuring that the benefits users see first are those that are eligible for redemption / claim. For example, for benefit redemption based on points, the system can compare the user's current points with the points required for the benefit to determine if the user has enough points. If they do, 0 points are awarded; if not, 10,000 points are deducted, thus implementing a personalized logic for pushing benefits with insufficient points to the bottom, ensuring a better user experience.

[0101] Step 390: Based on the traffic horse racing ranking results, select target recommended welfare resources from the various welfare resources;

[0102] Specifically, in this embodiment, after determining the traffic ranking results, the results can be displayed on the operation interface, allowing staff in the benefits recommendation backend to view the ranking of each benefits resource. For example, staff can view the real-time ranking list and the score of each benefit based on the user identifier (UID) and display position. For instance, after staff enter "Member Preferred - Popular Tab" in the display position input box and fill in relevant information in the user identifier (UID) input box and the participating platform, the ranking list and score of each benefits resource can be displayed on the operation interface based on the user identifier (UID) and display position. This allows staff to view the score contribution and differential data effect of each benefit resource's indicator data by clicking on the operation interface.

[0103] Step 400: Recommend the target recommended welfare resources to the online users.

[0104] In summary, this embodiment, after obtaining user operations, identifies online users using the user identifier carried by the user operations, determines the welfare resource distribution entry point based on the online user's operation location, and identifies the target resource pool based on the welfare resource distribution entry point. Subsequently, it determines the rule group to which each welfare resource in the target resource pool belongs, and determines the corresponding indicator parameter information for each welfare resource based on the rule group to which the welfare resource belongs. Thus, based on the indicator parameter information corresponding to each welfare resource, it determines the popularity of each welfare resource by using the click exposure information and redemption information of each welfare resource, and sorts the welfare resources in the target resource pool according to their popularity through a traffic competition mechanism, thereby realizing a traffic competition mechanism. By ranking traffic using different metrics, scores can be calculated for different core indicators of welfare resources within the horse racing group of the rules group. Each welfare resource is scored according to different scoring logics and then distributed in descending order of score. This can effectively achieve a positive cycle where better redemption data leads to greater traffic exposure. Furthermore, the horse racing mechanism allows for timely data monitoring and adjustment of welfare resources with insignificant online performance, reducing the risk of errors in human decision-making to some extent. Moreover, this horse racing mechanism comprehensively considers users' historical redemption and receipt data, providing a scientific and objective scoring standard for welfare resources. Through the analysis of user behavior data, user preferences can be better understood, enabling precise recommendations.

[0105] Furthermore, after determining the traffic ranking results corresponding to each welfare resource, this embodiment selects the most popular welfare resources from the various welfare resources in the target resource pool based on the traffic ranking results corresponding to each welfare resource, and recommends them to online users. This can provide more accurate recommendations to online users and allow the online algorithm team to carry out preliminary data accumulation work, which is beneficial to the training and optimization of the algorithm model. This enables operators to flexibly adjust online data and achieve accurate recommendations.

[0106] For example, such as Figure 5 As shown, after a new benefit is launched, it can be treated as a newly released benefit resource and placed in the "accumulation group" within the "horse race" rule group to accumulate traffic. Once the accumulated data in the accumulation group reaches a certain threshold for the horse race group (i.e., when the benefit resource's traffic accumulation data meets preset traffic horse race conditions), it enters the horse race group and is ranked after scoring with other benefit resources. Based on this ranking result, it can be determined whether the current display position of the benefit resource is included in the horse race rules. If the current display position is not included in the horse race rules, the benefit resource is recommended and distributed according to the operator's configuration. If the current display position is included in the horse race rules, different distributions can be implemented according to different display positions, allowing users in the horse race group to see the benefit resource according to their score. This example, based on a horse race mechanism, determines whether to implement different distributions based on different display positions by judging whether the current display position of the benefit resource is included in the horse race rules. This allows operators to reduce configuration costs in suitable horse race distribution positions, thereby reducing manpower configuration costs, saving time, and achieving accurate recommendations while reducing manpower configuration costs.

[0107] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should know that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps may be performed in other orders or simultaneously.

[0108] like Figure 6 As shown in the illustration, this application also provides a welfare resource recommendation device, including the following modules:

[0109] The determination module 810 is used to determine the welfare resource distribution entry point corresponding to the online user and the traffic group corresponding to the online user;

[0110] Target resource pool module 820 is used to determine the target resource pool based on the welfare resource distribution entry point;

[0111] The traffic ranking module 830 is used to perform traffic ranking on each welfare resource in the target resource pool according to the preset welfare distribution rules corresponding to the traffic group, and obtain the traffic ranking result corresponding to each welfare resource.

[0112] The target recommendation welfare resource module 840 is used to select target recommendation welfare resources from the welfare resources based on the traffic horse racing ranking results;

[0113] The welfare resource recommendation module 850 is used to recommend the target welfare resources to the online users.

[0114] Optionally, the traffic ranking module 830 includes:

[0115] The rule grouping determination submodule is used to determine the rule group to which each welfare resource in the target resource pool belongs when the welfare distribution rule is the horse racing group distribution rule.

[0116] The indicator parameter information submodule is used to determine the indicator parameter information corresponding to each welfare resource based on the rule grouping.

[0117] The popularity submodule is used to determine the popularity of each welfare resource based on the indicator parameter information, using the click exposure information and redemption information of each welfare resource respectively;

[0118] The sorting submodule is used to sort according to the popularity to obtain the traffic horse racing ranking result.

[0119] Optionally, the rule grouping in this embodiment includes a horse racing group and a power-saving group, and the rule grouping determination submodule includes:

[0120] The online duration determination unit is used to determine the online duration of each welfare resource by using the online release time of each welfare resource when the welfare distribution rule is the horse racing group distribution rule.

[0121] The traffic accumulation data determination unit is used to determine whether the traffic accumulation data of the welfare resource meets the preset traffic horse racing conditions when the online duration does not reach the preset duration threshold.

[0122] The horse racing group determination unit is used to determine the horse racing group as the rule group to which the welfare resource belongs when the accumulated traffic data meets the traffic horse racing conditions;

[0123] The power accumulation group determination unit is used to determine the power accumulation group as the rule group to which the welfare resource belongs when the accumulated traffic data does not meet the traffic horse racing conditions.

[0124] Optionally, the rule grouping determination submodule in this embodiment further includes:

[0125] The duration judgment unit is used to determine whether the online duration of each welfare resource has reached the preset duration threshold.

[0126] The horse racing group determination triggering unit is used to trigger the horse racing group determination unit to perform the step of determining the horse racing group as the rule group to which the welfare resource belongs when the online duration of the welfare resource reaches the preset duration threshold.

[0127] For example, after the online duration determination unit determines the online duration of each welfare resource, the duration judgment unit can determine whether the online duration of each welfare resource has reached the preset duration threshold. If the duration judgment unit determines that the online duration of a certain welfare resource has reached the preset duration threshold, the horse racing group determination unit can be triggered to set the rule group to which the welfare resource belongs as a horse racing group, so that the subsequent indicator parameter information submodule can determine the indicator parameter information corresponding to the welfare resource based on the horse racing group.

[0128] Optionally, the indicator parameter information submodule includes:

[0129] The power accumulation group indicator parameter determination unit is used to determine the preset new welfare indicator parameters corresponding to the power accumulation group as the indicator parameter information corresponding to the welfare resource when the rule group to which the welfare resource belongs is the power accumulation group.

[0130] The horse racing group indicator parameter determination unit is used to determine the preset horse racing welfare indicator parameters corresponding to the horse racing group as the indicator parameter information corresponding to the welfare resource when the rule group to which the welfare resource belongs is the horse racing group.

[0131] Optional popularity submodules include:

[0132] The main operational information acquisition unit is used to acquire the main operational information corresponding to each of the aforementioned welfare resources.

[0133] The popularity score calculation unit is used to calculate the popularity score corresponding to each of the welfare resources based on the welfare score corresponding to the main promotion information of the operation, using the indicator parameter information, the click exposure information and the redemption information.

[0134] A popularity determination unit is used to determine the popularity level using the popularity score.

[0135] Optionally, the determining module 810 includes:

[0136] The user operation submodule is used to obtain user operations.

[0137] The online user submodule is used to identify the online user using the user identifier carried by the user operation.

[0138] The resource distribution entry submodule is used to determine the welfare resource distribution entry based on the online user's operation location.

[0139] In its implementation, the aforementioned welfare resource recommendation device can be integrated into an electronic device. This allows the electronic device to act as a welfare resource recommendation device. By determining the welfare resource distribution entry point corresponding to an online user and the traffic group corresponding to that online user, a target resource pool can be determined based on the welfare resource distribution entry point. Subsequently, according to the preset welfare distribution rules corresponding to the traffic group, each welfare resource in the target resource pool is ranked by traffic competition to obtain the traffic competition ranking result for each welfare resource. Based on the traffic competition ranking result, target recommended welfare resources can be selected from each welfare resource and recommended to online users. This realizes a welfare recommendation method based on a traffic competition mechanism, thereby solving the problem caused by the current related technologies where only operators sort and recommend welfare resources individually according to each location. It can recommend high-quality welfare resources to most users, reduce manpower configuration costs, and improve user experience and rights satisfaction.

[0140] This embodiment also provides an electronic device, including at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus. The processor is configured to: determine a welfare resource distribution entry point corresponding to an online user and a traffic group corresponding to the online user; determine a target resource pool based on the welfare resource distribution entry point; perform a traffic ranking algorithm on each welfare resource in the target resource pool according to a preset welfare distribution rule corresponding to the traffic group, obtaining a traffic ranking result for each welfare resource; select a target recommended welfare resource from the welfare resources based on the traffic ranking result; and recommend the target recommended welfare resource to the online user.

[0141] It should be noted that the electronic device provided in this embodiment may be composed of two or more physical entities, or it may be composed of a single physical entity. For example, the electronic device may be a personal computer (PC), a computer, a server, etc. This application embodiment does not impose specific limitations on this.

[0142] For example, such as Figure 7As shown in the figure, this application provides an electronic device including a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0143] Memory 113 is used to store computer programs;

[0144] When the processor 111 executes the program stored in the memory 113, it implements the steps of the welfare resource recommendation method provided in any of the foregoing method embodiments, including: determining the welfare resource distribution entry corresponding to the online user and the traffic group corresponding to the online user; determining a target resource pool based on the welfare resource distribution entry; performing a traffic horse race ranking on each welfare resource in the target resource pool according to the preset welfare distribution rules corresponding to the traffic group, and obtaining the traffic horse race ranking result corresponding to each welfare resource; selecting a target recommended welfare resource from each welfare resource based on the traffic horse race ranking result; and recommending the target recommended welfare resource to the online user.

[0145] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the welfare resource recommendation method provided in any of the foregoing method embodiments.

[0146] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0148] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, and / or operations, but do not exclude the presence or addition of one or more other features, steps, operations, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a specific order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0149] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for recommending welfare resources, characterized in that, include: Determine the distribution entry point for welfare resources corresponding to online users and the traffic group corresponding to the online users; The target resource pool is determined based on the aforementioned welfare resource distribution entry point; Based on the preset welfare distribution rules corresponding to the traffic groups, the traffic horse race ranking of each welfare resource in the target resource pool is performed to obtain the traffic horse race ranking result corresponding to each welfare resource; Based on the traffic ranking results, target recommended welfare resources are selected from each welfare resource. The target recommended welfare resources are recommended to the online users; The step of ranking each welfare resource in the target resource pool according to the preset welfare distribution rules corresponding to the traffic group, and obtaining the traffic ranking result corresponding to each welfare resource, includes: When the welfare distribution rule is a horse racing group distribution rule, the rule group to which each welfare resource in the target resource pool belongs is determined respectively; Based on the rule grouping, determine the indicator parameter information corresponding to each welfare resource; Based on the aforementioned indicator parameters, the popularity of each welfare resource is determined by using the click exposure information and redemption information for each of the welfare resources. The traffic ranking results are obtained by sorting the traffic based on its popularity. The rule grouping includes a horse racing group and a reserve group. When the welfare distribution rule is a horse racing group distribution rule, determining the rule group to which each welfare resource in the target resource pool belongs includes: When the welfare distribution rule is the horse racing group distribution rule, the online duration of each welfare resource is determined by the online release time of each welfare resource. If the online duration does not reach the preset duration threshold, determine whether the traffic accumulation data of the welfare resources meets the preset traffic race conditions; If the accumulated traffic data meets the traffic horse racing conditions, then the horse racing group is determined as the rule group to which the welfare resource belongs; If the accumulated traffic data does not meet the traffic race conditions, then the power accumulation group will be determined as the rule group to which the welfare resource belongs.

2. The method according to claim 1, characterized in that, After determining the online duration of each welfare resource, the process also includes: Determine whether the online duration of each welfare resource has reached the preset duration threshold. If the online duration of the welfare resource reaches the preset duration threshold, the step of determining the horse racing group as the rule group to which the welfare resource belongs is executed.

3. The method according to claim 1, characterized in that, Based on the rule grouping, the indicator parameter information corresponding to each welfare resource is determined, including: When the rule grouping is a power-accumulation grouping, the preset new welfare indicator parameters corresponding to the power-accumulation grouping are determined as the indicator parameter information; When the rule grouping is a horse racing group, the preset horse racing welfare index parameters corresponding to the horse racing group are determined as the index parameter information.

4. The method according to claim 1, characterized in that, Based on the aforementioned indicator parameters, the popularity of each welfare resource is determined using its click exposure and redemption information, including: Obtain the operational promotion information corresponding to each of the aforementioned welfare resources; For each of the aforementioned welfare resources, based on the welfare score corresponding to the operational promotion information, the popularity score corresponding to the welfare resource is calculated using the indicator parameter information, the click exposure information, and the redemption information. The popularity score is used to determine the degree of popularity.

5. The method according to any one of claims 1 to 4, characterized in that, The process of determining the distribution entry point for welfare resources corresponding to online users includes: Obtain user actions; The online user is identified using the user identifier carried by the user operation. The entry point for distributing welfare resources is determined based on the location of the online user's operation.

6. A welfare resource recommendation device, characterized in that, include: The determination module is used to determine the welfare resource distribution entry point corresponding to the online user and the traffic group corresponding to the online user; The target resource pool module is used to determine the target resource pool based on the welfare resource distribution entry point; The traffic ranking module is used to rank each welfare resource in the target resource pool according to the preset welfare distribution rules corresponding to the traffic group, and obtain the traffic ranking result corresponding to each welfare resource. The target recommendation welfare resource module is used to select target recommendation welfare resources from the welfare resources based on the traffic horse racing ranking results; The welfare resource recommendation module is used to recommend the target welfare resources to the online users; Specifically, the traffic ranking module is used for: When the welfare distribution rule is a horse racing group distribution rule, the rule group to which each welfare resource in the target resource pool belongs is determined respectively; Based on the rule grouping, determine the indicator parameter information corresponding to each welfare resource; Based on the aforementioned indicator parameters, the popularity of each welfare resource is determined by using the click exposure information and redemption information for each of the welfare resources. The traffic ranking results are obtained by sorting the traffic based on its popularity. The rule grouping includes a horse racing group and a power accumulation group. The traffic horse racing sorting module is also used for: When the welfare distribution rule is the horse racing group distribution rule, the online duration of each welfare resource is determined by the online release time of each welfare resource. If the online duration does not reach the preset duration threshold, determine whether the traffic accumulation data of the welfare resources meets the preset traffic race conditions; If the accumulated traffic data meets the traffic horse racing conditions, then the horse racing group is determined as the rule group to which the welfare resource belongs; If the accumulated traffic data does not meet the traffic race conditions, then the power accumulation group will be determined as the rule group to which the welfare resource belongs.

7. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the welfare resource recommendation method as described in any one of claims 1-5.

Images