Resource recommendation optimization method, device and equipment and computer readable medium

Abstract

The invention relates to a resource recommendation optimization method and device, equipment and a computer readable medium. The method comprises the following steps: determining a flow group of a user based on a welfare list request of the user; matching a corresponding target welfare resource pool based on the traffic packet; scoring each welfare resource in the resource pool based on a welfare scoring strategy corresponding to the target welfare resource pool to obtain a welfare scoring result; dynamically obtaining a welfare recommendation sequence based on the welfare scoring result, and dynamically recommending target welfare resources to the user according to the welfare recommendation sequence; performing recommendation compensation according to the abnormal recommendation process of the target welfare resource through a welfare recommendation degradation strategy; the problem that in the prior art, the welfare resource distribution preorder and uncertainty in the distribution process are not comprehensively considered, so that the welfare resource distribution effect is poor is solved, the film and television platform member welfare resource recommendation efficiency is remarkably improved, and more efficient user personalized welfare resource recommendation is achieved.

Description

Technical Field

[0001] This application relates to the technical field of cloud computing data processing, and particularly to a method, apparatus, device, and computer-readable medium for optimizing resource recommendation. Background Art

[0002] With the continuous development of online video platforms and the increasing demands of users, video membership has become the main channel for consumers to obtain high-quality video content; users' demands for film and television memberships are becoming increasingly diverse, not only paying attention to the richness and quality of video content, but also attaching importance to the usage experience, cost performance, and membership privileges. Platforms usually provide various benefits for members to enhance user stickiness and improve user experience. However, how to effectively recommend these benefit resources to maximize the attraction of users and enhance the competitiveness of the platform has become an important issue in the operation of film and television platforms.

[0003] Currently, in related technologies, the methods for recommending member benefit resources include: setting a distribution entrance for benefit resources of online users, grouping the online users, and then matching the corresponding recommended benefit resources through a preset benefit distribution rule, and recommending them to the online users. Although it reduces the labor configuration cost and solves the problems caused by only relying on operation personnel to sort and recommend benefit resources separately for each position, the accuracy and rationality of user grouping and benefit distribution rules affect the efficiency and effect of benefit resource recommendation. How to group users more reasonably to dynamically adjust the benefit resource recommendation strategy for users, and how to ensure the smooth recommendation of benefit resources after an abnormality occurs in the benefit resource recommendation process to achieve personalized recommendation for users is an important challenge.

[0004] For the above problems, no effective solutions have been proposed yet. Summary of the Invention

[0005] This application provides a method, apparatus, device, and computer-readable medium for optimizing resource recommendation to solve the technical problems of poor efficiency and accuracy of benefit resource distribution in the prior art due to the failure to comprehensively consider the pre-order of benefit resource distribution and the uncertainties during the distribution process.

[0006] According to one aspect of the embodiments of this application, this application provides a method for optimizing resource recommendation, including: determining the traffic grouping of users based on the benefit list request of users; matching the corresponding target benefit resource pool based on the traffic grouping; scoring each benefit resource in the resource pool according to the benefit scoring strategy corresponding to the target benefit resource pool to obtain a benefit scoring result; dynamically obtaining the benefit recommendation order based on the benefit scoring result, and dynamically recommending the target benefit resources to users according to the benefit recommendation order; and performing recommendation compensation according to the abnormal recommendation process of the target benefit resources through a benefit recommendation downgrading strategy to complete the optimization of the recommendation of the target benefit resources.

[0007] Optionally, score each welfare resource in the resource pool according to the welfare scoring strategy corresponding to the target welfare resource pool to obtain a welfare scoring result, including: obtaining the behavior data and welfare order data generated by the user using the welfare coupon based on the user's device number; calculating the key index values for scoring the welfare resources according to the behavior data and the welfare order data; and calculating the total score of each welfare resource in the target welfare resource pool according to the attributes of the key indexes configured in the welfare scoring strategy through the key index values corresponding to each index, so as to obtain the welfare scoring result of each welfare resource.

[0008] Optionally, the key indexes at least include a weight index, a data index, and a value score representing the corresponding score of the weight index. The calculating the key index values for scoring the welfare resources according to the behavior data and the welfare order data includes: extracting the exposure volume of all welfare resources in the resource pool during the target time period based on the behavior data, and extracting the verification quantity and / or receiving quantity of welfare receiving by all users in the resource pool during the target time period based on the welfare order data; calculating the value of the data index according to the exposure volume, the verification quantity and / or the receiving quantity.

[0009] Optionally, the calculating the total score of each welfare resource in the target welfare resource pool according to the attributes of the key indexes configured in the welfare scoring strategy through the key index values corresponding to each index includes: determining an index coefficient based on the number of the data indexes configured in the welfare scoring strategy; querying the value score corresponding to the weight index through a preset welfare index library, and determining the specific score of the value score according to the number of the weight indexes configured in the welfare scoring strategy to obtain a weight score; and comprehensively calculating the total score of the welfare resource according to the value of the data index, the index coefficient, and the weight score.

[0010] Optionally, dynamically obtain the welfare recommendation order based on the welfare scoring result, and dynamically recommend target welfare resources to the user according to the welfare recommendation order, including: performing pre-sorting according to the welfare scoring result to determine the first recommendation order; matching and associating the target welfare resources based on the first recommendation order, and presenting the target welfare resources to the user; and dynamically scheduling the recommendation order of each welfare resource in the target welfare resource pool according to the user's operation on the target welfare resources, so as to dynamically present the welfare resources to the user.

[0011] Optionally, dynamically scheduling the recommended order of each welfare resource in the target welfare resource pool according to the user's operation on the target welfare resource includes: based on the user's action of claiming and / or writing off the target welfare resource, and real-time user dynamic metrics, calculating in real time the real-time welfare scoring result of the welfare resources in the current target welfare resource pool; dynamically adjusting the recommended order of the welfare resources in the target welfare resource pool according to the real-time welfare scoring result.

[0012] Optionally, performing recommendation compensation according to the abnormal recommendation process of the target welfare resource through a welfare recommendation downgrading strategy includes: monitoring the entire recommendation process of the target welfare resource based on a preset welfare recommendation downgrading strategy; when the system is abnormal or the welfare resource recommendation fails, initializing the sorting of the welfare resources in the welfare resource pool and presenting them to the user.

[0013] According to another aspect of the embodiments of the present application, the present application provides a resource recommendation optimization device, including: a grouping module for determining the traffic grouping of a user based on the user's welfare list request; an identification module for matching a corresponding target welfare resource pool based on the traffic grouping; a scoring module for scoring each welfare resource in the resource pool based on the welfare scoring strategy corresponding to the target welfare resource pool to obtain a welfare scoring result; a recommendation module for dynamically obtaining a welfare recommendation order based on the welfare scoring result and dynamically recommending a target welfare resource to the user according to the welfare recommendation order; an optimization module for performing recommendation compensation according to the abnormal recommendation process of the target welfare resource through a welfare recommendation downgrading strategy to complete the recommendation optimization of the target welfare resource.

[0014] According to another aspect of the embodiments of the present application, the present application provides an electronic device, including a memory, a processor, a communication interface and a communication bus. A computer program that can run on the processor is stored in the memory. The memory and the processor communicate through the communication bus and the communication interface. When the processor executes the computer program, the steps of the above resource recommendation optimization method are implemented.

[0015] According to another aspect of the embodiments of the present application, the present application further provides a computer-readable medium having non-volatile program code executable by a processor, and the program code causes the processor to execute the steps of the above resource recommendation optimization method.

[0016] The above technical solutions provided by the embodiments of the present application have the following advantages compared with the related technologies: By grouping users according to traffic, the present application improves the rationality of user grouping, facilitating flexible adjustment of the recommendation strategy according to the characteristics of different groups to meet the personalized needs of different user groups, thereby enhancing the efficiency and accuracy of welfare resource recommendation and providing a more accurate basis for subsequent welfare resource recommendation; Matching each traffic group with the corresponding target welfare resource pool to improve the matching degree between welfare resources and users, thereby improving the accuracy of welfare resource distribution and further enhancing the efficiency of welfare resource recommendation; Evaluating each welfare resource in the target welfare resource pool according to a specific welfare scoring strategy to provide a quantitative basis for the recommendation ranking of welfare resources, enabling objective evaluation of the attractiveness of each welfare resource and its value to users, determining the recommendation priority of welfare resources in a data-driven manner, and making the recommendation results more accurate and reliable; Implementing dynamic recommendation by adjusting the recommendation order of welfare resources in real time, being able to continuously optimize the recommended content according to the user's real-time welfare resource operation situation and better meet the user's personalized needs; By continuously monitoring the recommendation situation of the target welfare resources and activating the welfare recommendation downgrading strategy, it is ensured that even in abnormal situations, users can still obtain welfare resource recommendations, enhancing the stability and reliability of the system and realizing the optimization of the user's personalized recommendation experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0018] To more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the related technologies. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0019] Figure 1 Schematic diagram of the hardware environment of an optional resource recommendation optimization method provided according to an embodiment of the present application;

[0020] Figure 2 Flowchart of an optional resource recommendation optimization method provided according to an embodiment of the present application;

[0021] Figure 3 Overall division diagram of an optional resource recommendation optimization process provided according to an embodiment of the present application;

[0022] Figure 4 Schematic diagram of an optional welfare resource display and traffic division provided according to an embodiment of the present application;

[0023] Figure 5 An optional block diagram for calculating the sorting score of welfare resources provided according to an embodiment of the present application;

[0024] Figure 6 An optional overall flowchart for recommending welfare resources provided according to an embodiment of the present application;

[0025] Figure 7 An optional block diagram of a resource recommendation optimization device provided according to an embodiment of the present application;

[0026] Figure 8 A schematic structural diagram of an optional electronic device provided according to an embodiment of the present application. Detailed implementation manners

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0028] In subsequent descriptions, suffixes such as "module", "component", or "sub-module" used to represent elements are only for the convenience of description of the present application, and they have no specific meaning in themselves. Therefore, "module" and "component" can be used interchangeably.

[0029] To solve the problems mentioned in the background art, according to one aspect of the embodiments of the present application, an embodiment of a resource recommendation optimization method is provided.

[0030] Optionally, in the embodiments of the present application, the above resource recommendation optimization method can be applied to a hardware environment as shown in Figure 1 As shown. As shown in Figure 1 As shown, the hardware environment is composed of a terminal 101 and a server 103. The server 103 is connected to the terminal 101 through a network and can be used to provide services for the terminal or a client installed on the terminal. A database 105 can be set on the server or independently of the server to provide data storage services for the server 103. The above network includes, but is not limited to: a wide area network, a metropolitan area network, or a local area network. The terminal 101 includes, but is not limited to: a PC, a mobile phone, a tablet computer, etc.

[0031] Users can use the terminal device 101 to interact with the server 103 via the network to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as a web browser application, a search application, an instant messaging tool, etc. Among them, the terminal device 101 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and so on. The server 103 can be a server that provides various services, such as a background server that supports the pages displayed on the terminal device 101.

[0032] A method in an embodiment of the present application can be executed by the server 103, or can also be jointly executed by the server 103 and the terminal 101, as Figure 2 shown, and this method can include the following steps:

[0033] Step S202, determine the user's traffic grouping based on the user's welfare list request.

[0034] In some embodiments, the user's traffic grouping can be achieved through a specific grouping component. First, the component identifies the user's registration information, and groups the user accordingly based on the identified key field information. For example, group the user according to key field information such as whether the user is a new user, whether the user is an Apple user, and gender characteristics.

[0035] In this embodiment, by performing traffic grouping on users, different types of users can be classified and managed. Users with similar attributes or characteristics are grouped into the same traffic grouping, so as to provide a more targeted direction for formulating subsequent welfare resource strategies, and also lay a foundation for dynamically adjusting the welfare resource recommendation strategy, which helps to flexibly adjust the recommendation strategy to meet the personalized needs of different user groups, thereby improving the efficiency and effect of welfare resource recommendation.

[0036] Step S204, match the corresponding target welfare resource pool based on the traffic grouping.

[0037] In this embodiment, a target welfare resource pool that conforms to the characteristics of the users in each traffic group is configured to achieve a preliminary precise docking between users and welfare resources. Different target welfare resource pools contain welfare resources that represent the possible needs and preferences of users, that is, welfare products. By matching the traffic groups with the target welfare resource pools, blind recommendations are avoided, the distribution accuracy of welfare resources is improved, the recommended welfare resources better meet the personalized needs of users, which helps to increase users' attention and acceptance of welfare resources, thereby enhancing the recommendation effect and further improving the efficiency of welfare resource recommendation.

[0038] Step S206: Score each welfare resource in the resource pool based on the welfare scoring strategy corresponding to the target welfare resource pool to obtain a welfare scoring result.

[0039] In some embodiments, after determining the target welfare resource pool, the corresponding welfare scoring strategy can be associated. The welfare scoring strategy can be formulated based on racehorse scores. The welfare scoring strategy includes key indicators for scoring, calculation methods of the indicators, and the scoring process, and finally, the scoring results of each welfare resource in the target welfare resource pool are obtained.

[0040] In this embodiment, by scoring welfare resources, the attractiveness and value of each welfare resource to users can be objectively evaluated, and the recommendation priority of welfare resources can be determined in a data-driven manner, making the recommendation results more accurate and reliable; the welfare scoring strategy takes into account the actual behavior data of users and can more accurately reflect users' preference levels for different welfare resources, thereby providing welfare resource recommendations that better meet their personalized needs and enhancing the user experience and satisfaction.

[0041] Step S208: Dynamically obtain a welfare recommendation order based on the welfare scoring result, and dynamically recommend target welfare resources to users according to the welfare recommendation order.

[0042] In some embodiments, pre-sorting can be first performed according to the welfare scoring result to determine the recommendation order to provide personalized welfare recommendations; then, according to real-time user data and the welfare scoring result, the sorting of welfare recommendations is dynamically adjusted to adapt to the changing needs of users.

[0043] Furthermore, the pre-sorting can directly obtain the score values of welfare resources according to the key indicators in the welfare scoring strategy. For example, for welfare resources in the resource pool that do not distinguish user genders or other user characteristics, the corresponding score values can be directly determined through the weights of these welfare resources to achieve the scoring of these welfare resources.

[0044] Furthermore, real-time user data can be metrics with a strong correlation between the user and the usage status of welfare resources. For example, metrics such as the necessity to install a third-party application but the user has not installed it, or the user has received and redeemed a certain welfare. Since relevant records may be generated only after welfare resources have been recommended to the user for these metrics, the scoring results of each welfare resource in the corresponding target resource pool can be calculated in real time based on these strongly correlated metrics, thereby realizing dynamic recommendation of welfare resources in the resource pool, improving the personalization degree and effect of the recommendation.

[0045] In this embodiment, by pre-ranking the welfare resources according to the welfare scoring results, determining the initial recommendation order, presenting the ranked welfare resources to the user, and adjusting the recommendation order of the welfare resources in real time according to the user's actual operations on the welfare resources, dynamic recommendation is realized, which helps to continuously optimize the recommended content according to the real-time feedback of the user on the use of welfare resources, better meet the personalized needs of the user, and further realize personalized dynamic recommendation, thereby further improving the recommendation efficiency of welfare resources.

[0046] Step S210, perform recommendation compensation according to the abnormal recommendation process of the target welfare resource through the welfare recommendation degradation strategy to complete the recommendation optimization of the target welfare resource.

[0047] In some embodiments, the welfare recommendation degradation strategy, as a fallback strategy, can be dynamically edited, and the quantity and type of the fallback strategy can be dynamically defined to adapt to different recommendation scenarios, improving the flexibility and adaptability of the welfare resource recommendation.

[0048] In this embodiment, by monitoring the recommendation process of the target welfare resource, including the whole process from calculating the scoring results of each welfare resource in the computing resource pool to presenting the target recommended welfare resource to the user, when a system anomaly occurs or any stage in the welfare resource recommendation process shows an anomaly, the welfare recommendation degradation strategy is executed, and the welfare resources are initialized and ranked and then presented to the user, ensuring that even in abnormal situations, the user can still obtain welfare resource recommendations, improving the stability and reliability of the system, and further enhancing the user experience.

[0049] In some alternative embodiments, the above step S206 specifically includes:

[0050] Obtain the behavior data and welfare order data generated by the user's use of welfare coupons based on the user's device number;

[0051] Calculate the key index values for welfare resource scoring according to the behavior data and the welfare order data;

[0052] According to the attributes of the key indicators configured in the welfare scoring strategy, calculate the total score of each welfare resource in the target welfare resource pool through the key indicator values corresponding to each indicator, so as to obtain the welfare scoring results of each welfare resource.

[0053] In some embodiments, the welfare order data at least includes records of welfare receipt, order records, and verification records, and the user's behavior data at least includes the exposure volume of welfare resources displayed on the interface and the click volume generated by the user clicking on the welfare resources; among them, the verification record indicates that the user will jump to the corresponding place of use after receiving the welfare, and if the user directly uses it, there will be a verification record; the order record indicates that the user pays to purchase a membership or other card type, and an order record will be generated after payment.

[0054] Furthermore, the key indicator values for welfare scoring are calculated based on the behavior data and welfare order data. The attributes of the key indicators configured in the welfare scoring strategy at least include the quantity of each indicator. Multiply the quantity of each indicator data by its corresponding indicator value, and finally sum the values of each indicator to obtain the total score.

[0055] Among them, pingback statistics is a network protocol used to notify the target website that a specific article has been cited. When an article or page is cited by another article, the server of the initiating article will send a Pingback request to the server of the target article, informing that the target article has been cited.

[0056] In some embodiments, the user's behavior data can be collected through pingback statistics. When a welfare resource is displayed on the interface or clicked by the user, the server will receive a Pingback request. The server processes this request, increments the display or click count by one, and stores the updated data each time to achieve the collection of exposure data and click data.

[0057] In this embodiment, the device number can be used to uniquely identify the user, and obtain the behavior data and welfare order data of the user's use of welfare coupons. These data contain the interaction information between the user and the welfare resources, and can be used as an important basis for evaluating the value of welfare resources. By comprehensively considering the key indicators of each score, it is possible to objectively and fully quantify the user's attention and participation in welfare resources, ensure the accuracy and reliability of the welfare scoring results, and thus help improve the accuracy and quality of recommendations.

[0058] In some alternative embodiments, the key indicators at least include a weight indicator, a data indicator, and a value score representing the corresponding score of the weight indicator. The above calculation of the key indicator values for welfare resource scoring based on the behavior data and the welfare order data specifically includes:

[0059] Extract the exposure volume of all welfare resources in the resource pool during the target period based on the behavior data, and extract the verification volume and / or receipt volume of all users' welfare receipt in the resource pool during the target period based on the welfare order data;

[0060] Calculate the value of the data indicator based on the exposure volume, verification volume and / or receipt volume.

[0061] In some embodiments, the exposure volume reflects the number of times the welfare resource is displayed to users within a certain period, demonstrating its visibility in the system; the verification volume or receipt volume directly reflects the actual acquisition behavior of users towards the welfare resource, reflecting the degree of recognition and demand of users for this welfare resource. Using these quantified data as the basis for calculating the data indicator value provides an objective and specific numerical basis for scoring the welfare resource.

[0062] In some examples, the weight indicators can be configured according to the historical recommendation situations of various welfare products in the resource pool, and the configured weight indicators can also be combined with the commercial value of the welfare products to construct a welfare indicator library. For example, whether the welfare is a co-branded product, whether it is a main promoted welfare product, whether there is no verification data in the recent week, whether it is a new welfare, whether it is associated with other applications and the corresponding application needs to be installed, whether it is that the display times for a single user in a day are greater than 3 times and there is no receipt behavior, whether it is that the display times for a single user in 7 days are greater than 10 times and there is no receipt behavior, whether the user's points are less than the points required for redeeming the welfare product, etc.; the data type of each weight indicator can be set to a boolean type, and the initial value of each weight indicator corresponding to the boolean type is set according to the recommendation and user usage situations of the welfare resource. For example, if the welfare resource is a new welfare, the initial value of the weight indicator is a value score of +10, and if the display times of the welfare resource for a single user in a day are greater than 3 times and the user has no receipt behavior, the value score of the weight indicator is -1.

[0063] Furthermore, the verification volume of users' welfare receipt indicates that the users use the welfare vouchers after receiving them at the corresponding manufacturers, and the receipt volume indicates the number of times the users receive the welfare vouchers;

[0064] Furthermore, the data indicator characterizes the receipt situation and verification situation of all users for the same welfare resource. The indicator value of the data indicator, that is, the data score, can be obtained by statistically analyzing the verification volume data of all users' welfare receipt. The calculation formula is the verification volume in the recent three days / the exposure in the recent three days * 1000. For example, if the verification volume of all users for a certain welfare in the recent three days is 10 and the exposure volume is 100, then the data score is 10 / 100 * 1000 = 100.

[0065] It should be noted that in the process of calculating the data index value, the collection of calculation parameters can be called up for the exposure and verification volume of the welfare in the current display position. If the welfare has no data in the latest three days in the current display position, the overall data is taken. That is, since there is no display position data at present, the overall data can be used in one period without distinguishing the display positions. If the welfare is transmitted back offline and there is data in the latest three days, the three days with verification volume data are taken, and then the exposure volume of the corresponding date is taken. If the exposure volume is not obtained, 0 points are given; among them, if 3 days of data cannot be obtained, the data of several days that can be obtained will be calculated according to the data of several days. For example, taking two days will be counted as two days of data, and the exposure volume will also be counted as two days of data; if the verification volume is obtained for 3 days and the exposure volume is obtained for two days, the data index value of the current welfare resource will continue to be calculated according to the above calculation formula.

[0066] It should also be noted that if the data indicator value is calculated as a decimal, you can choose to retain one decimal place to simplify the calculated value. The data after two decimal places will not affect the recommended ranking of welfare resources.

[0067] In this embodiment, by extracting the exposure of welfare resources in the target period and the verification volume and / or collection volume of welfare collection by users, the degree of attention and actual popularity of welfare resources can be quantified from different angles. This helps to more accurately grasp the interests and needs of users for different welfare resources, so that the recommended welfare resources are more in line with the expectations of users, and improve the accuracy of welfare recommendations. It ensures that users can find the welfare they are interested in more quickly, improves user experience, and increases users' attention to and utilization of welfare resources. By using real-time data in the target period as the calculation basis, the recommendation order of welfare resources can be dynamically adjusted with time and changes in user behavior.

[0068] In some optional embodiments, the above-mentioned calculation of the total score of each welfare resource in the target welfare resource pool by the key indicator value corresponding to each indicator according to the attributes of the key indicator configured in the welfare scoring strategy specifically includes:

[0069] Determining an indicator coefficient based on the number of the data indicators configured in the welfare scoring strategy;

[0070] The value score corresponding to the weighted indicator is searched through a preset welfare indicator library, and the specific score of the value score is determined according to the number of the weighted indicators configured in the welfare scoring strategy to obtain the weighted score;

[0071] The total score of the welfare resource is calculated comprehensively according to the value of the data indicator, the indicator coefficient and the weight score.

[0072] In some embodiments, a corresponding welfare scoring strategy is assigned to each resource pool. There are preset key metric quantities in the welfare scoring strategy, and the total score of the welfare resources can be calculated based on the key metric quantities configured in the scoring strategy corresponding to the current target welfare resource pool. For example, if 1 data metric and 1 weight metric are configured in the scoring strategy, and the number of metrics represents the metric coefficient, then the corresponding weight score is obtained from the welfare metric library established by the configured weight metric, that is, the specific value of the weight metric; the value score is determined according to the number of weight metrics configured in the scoring strategy, and then the number of data metrics is multiplied by the corresponding metric value to obtain the data score. Finally, the value score and the data score are summed to obtain the total score. For example, if the data score is 10 / 100 * 1000 = 100 and the value score is +1, then the total score of the welfare resources is 100 + 1 = 101. The total scores of all welfare resources in the target welfare resource pool are calculated through the above calculation method to score all welfare resources.

[0073] In some embodiments, the data metrics and weights configured in the welfare scoring strategy can be adjusted and optimized according to actual business needs. When the business objectives, user requirements, or market conditions change, the metric coefficients, weight metrics, and their value scores can be flexibly modified to meet the new requirements. This flexibility enables the recommendation system to continuously evolve and improve, better meeting the welfare recommendation needs in different scenarios and having strong scalability.

[0074] In one possible implementation, as Figure 3 shown, first, data collection is performed. According to Pingback, the behavior data of users is statistically analyzed, and at the same time, dimensional data such as the receipt records, order records, and manual cancellation records of welfare resources are collected. After grouping the user traffic, the welfare scoring strategy is configured; secondly, the welfare resources are scored according to the welfare scoring configuration, including metric management, that is, metric calculation and scoring calculation, to obtain the scoring result. During the welfare resource scoring process, the status of each data item is monitored in real time to facilitate timely capture of abnormal situations during the scoring process; finally, policy control is implemented, including pre-sorting and real-time sorting of welfare resources according to the scoring result. If there are abnormal scoring or system anomalies, etc., a reduction plan is initiated to ensure the smooth recommendation of welfare resources.

[0075] In this embodiment, various attributes of welfare resources are comprehensively considered through data scores, weight scores, and value scores, avoiding the one-sidedness of recommending and sorting based on only a single factor, ensuring the reliability and accuracy of the recommendation order, enabling the total score to truly reflect the comprehensive performance of welfare resources in aspects such as user needs and market feedback, providing a more accurate basis for the recommendation of welfare resources; helping to improve the pertinence and relevance of welfare recommendations, making it easier for users to obtain welfare resources that meet their own needs and interests, thereby enhancing the user experience and satisfaction with the recommendation system and optimizing the overall quality of welfare recommendations.

[0076] In some alternative embodiments, the above step S208 specifically includes:

[0077] Performing a preliminary sorting based on the welfare scoring result to determine a first recommendation order;

[0078] Matching and associating target welfare resources based on the first recommendation order, and presenting the target welfare resources to the user;

[0079] Dynamically scheduling the recommendation orders of the welfare resources in the target welfare resource pool according to the user's operations on the target welfare resources, so as to dynamically present the welfare resources to the user.

[0080] In some examples, as Figure 4 shown, the welfare resources are presented to the user through display positions in the traffic grouping. The traffic grouping corresponds to the target welfare resource pool, and thus corresponds to a welfare scoring strategy. The recommendation orders of the welfare resources calculated by the scoring strategies of different groupings are different. Therefore, the display orders of the same welfare resources in different traffic groupings are different. For example, if a user is grouped with the characteristic of female gender, the welfare resources presented may be makeup products; if a user is grouped with the characteristic of male gender, the welfare resources presented may be court clothes or electronic products, etc. Personalized recommendations for users are realized through the welfare scoring strategy. At the same time, the grouping rules of the corresponding traffic grouping can be dynamically adjusted according to the recommendation situations of the welfare resources in the resource pool, and the traffic grouping characteristics can be flexibly adjusted adaptively during the process of personalized welfare resource recommendation for users, so as to adjust the user grouping and welfare resource recommendation bidirectionally, maximize the degree of welfare resource recommendation, improve the welfare resource recommendation efficiency, and at the same time enhance user satisfaction.

[0081] In this embodiment, the welfare resources are preliminarily sorted according to the welfare scoring result to determine an initial recommendation order. Then, the sorted welfare resources are displayed to the user, and the recommendation order of the welfare resources is adjusted in real time according to the actual operations of the user on the welfare resources, so that the recommended content can be continuously optimized according to the real-time feedback of the user, and better meet the personalized needs of the user; by dynamically obtaining the welfare recommendation order, the recommended content can be adjusted in time according to the real-time behaviors and preferences of the user, so that the recommended welfare resources are always highly consistent with the interests of the user; at the same time, dynamic recommendation can better attract the attention of the user, stimulate the user's interest in the welfare resources, thereby increasing the interaction between the user and the welfare resources, improving the utilization rate and conversion rate of the welfare resources, and further improving the welfare resource recommendation efficiency.

[0082] In some alternative embodiments, the above dynamically scheduling the recommendation orders of the welfare resources in the target welfare resource pool according to the user's operations on the target welfare resources specifically includes:

[0083] Based on the user's action of receiving and / or writing off the target welfare resource, as well as real-time user dynamic metrics, calculate in real-time the real-time welfare scoring result of the welfare resources in the current target welfare resource pool;

[0084] Dynamically adjust the recommended order of the welfare resources in the target welfare resource pool according to the real-time welfare scoring result.

[0085] In some embodiments, the user dynamic metrics represent metrics that are strongly correlated with the user's real-time processing of welfare resources, including actions such as receiving and writing off. As shown in Table 1:

[0086] Table 1 User Dynamic Metrics

[0087]

[0088] In some examples, as Figure 5 shown, the sorting of welfare resources can be achieved through the following steps: First, preset corresponding resource pools according to traffic grouping, and configure the welfare products that can be displayed in the resource pool, as well as the welfare scoring strategy for the current resource pool; Second, perform welfare display screening, and screen corresponding welfare resources from the total welfare resources according to the preset and configured welfare resources and scoring strategy as the welfare resources visible to users for welfare display; The welfare display screening can also be dynamically scheduled according to the real-time recommended order to ensure the flexibility and adaptability of the recommendation; Finally, perform welfare sorting according to the scoring strategy. First, determine the weight scores of each welfare resource in the target welfare resource pool, then calculate the data scores according to the calculation formula of the data metrics. The value score is the value score of the real-time user dynamic metrics. The total score of each welfare resource in the resource pool is obtained by adding the weight score, data score, and value score, and then sorting according to the total score, the recommended order of these welfare resources can be obtained, and the total score is calculated in real-time, so the recommended order also changes dynamically, more efficiently realizing personalized recommendation for users and improving user satisfaction.

[0089] In some other examples, as Figure 6As shown, after pre-sorting, a welfare list will be generated according to the sorting result. After the user obtains the welfare list, they can enter the traffic grouping again according to the click situation, that is, according to the welfare resources selected in the welfare list, when the welfare has not been claimed yet, they can enter a new traffic grouping. Here, the grouping work is carried out through the Libra population grouping SDK component; then, the sorted welfare list is queried according to the grouping, and the front end displays the status of the user's claiming or writing off of the welfare resources, and the order information is transmitted back to the system background after the user completes the write-off of the welfare coupon; the background automatically standardizes the data in each stage and then calculates the key indicators, that is, the data score, the value score, and updates the weight score, and then calculates the total score of each welfare resource in the current target welfare resource pool. According to these total scores, a new round of sorting of welfare resources is carried out, and the weight indicators of each welfare resource are dynamically adjusted according to the total score. For example, new welfare resources are added, and welfare resources expire and need to be taken offline, etc.

[0090] In some optional embodiments, the pre-sorting may not distinguish users, without traffic grouping for users, and directly query the weight scores of each welfare resource according to the preset welfare index library for scoring.

[0091] In this embodiment, the recommended order of each welfare resource in the target welfare resource pool is dynamically scheduled according to the user's operation on the target welfare resource, so as to dynamically display the welfare resources to the user: according to the user's actual operations, such as click, claim and other behaviors, the recommended order of welfare resources is adjusted in real time, making the recommendation more in line with the user's real-time needs and interest changes; realizing the dynamic recommendation of welfare resources, not only considering the initial score of the welfare resources, but also being able to adjust according to the user's real-time feedback, making the recommendation more personalized and intelligent. Through this dynamic recommendation method, the user's needs can be better met, the interaction frequency and depth between the user and the welfare resources can be improved, and the user's dependence and trust on the welfare recommendation system can be enhanced.

[0092] In some optional embodiments, in the above step S210, recommendation compensation is performed according to the abnormal recommendation process of the target welfare resource through the welfare recommendation downgrading strategy, which specifically includes:

[0093] Monitor the entire recommendation process of the target welfare resource based on the preset welfare recommendation downgrading strategy;

[0094] When the system is abnormal or the welfare resource recommendation fails, the welfare resources in the welfare resource pool are initially sorted and presented to the user.

[0095] In some embodiments, by continuously monitoring the recommendation situation of target welfare resources, when problems such as incorrect calculation of the total score of welfare resources, abnormal sorting of recommendation orders, and system anomalies occur, a welfare recommendation degradation strategy is initiated. After initializing the sorting of welfare resources, they are presented to the user to ensure that even in abnormal situations, the user can still obtain welfare resource recommendations.

[0096] In this embodiment, the welfare recommendation degradation strategy, as a fallback strategy, can quickly respond when abnormalities occur during the recommendation process, ensuring that users can obtain certain welfare resource recommendations, avoiding the situation where users cannot obtain welfare due to abnormal conditions, improving the stability and reliability of the system; by ensuring that welfare resources can still be successfully recommended in abnormal situations, it meets the basic needs of users for welfare resources, reduces users' dissatisfaction caused by recommendation failures, and enhances users' trust and dependence on the recommendation system, thus optimizing the user's personalized recommendation experience.

[0097] According to another aspect of the embodiments of the present application, as Figure 7 shown, a resource recommendation optimization device is provided, including:

[0098] A grouping module 701, configured to determine the traffic grouping of a user based on the user's welfare list request;

[0099] An identification module 703, configured to match the corresponding target welfare resource pool based on the traffic grouping;

[0100] A scoring module 705, configured to score each welfare resource in the resource pool based on the welfare scoring strategy corresponding to the target welfare resource pool to obtain a welfare scoring result;

[0101] A recommendation module 707, configured to dynamically obtain the welfare recommendation order based on the welfare scoring result, and dynamically recommend target welfare resources to the user according to the welfare recommendation order;

[0102] An optimization module 709, which performs recommendation compensation according to the abnormal recommendation process of the target welfare resource through the welfare recommendation degradation strategy to complete the recommendation optimization of the target welfare resource.

[0103] It should be noted that the grouping module 701 in this embodiment can be used to execute step S202 in the embodiments of the present application, the identification module 703 in this embodiment can be used to execute step S204 in the embodiments of the present application, the scoring module 705 in this embodiment can be used to execute step S206 in the embodiments of the present application, the recommendation module 707 in this embodiment can be used to execute step S208 in the embodiments of the present application, and the optimization module 709 in this embodiment can be used to execute step S210 in the embodiments of the present application.

[0104] It should be noted here that the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in the hardware environment as shown in Figure 1 and can be implemented by software or by hardware.

[0105] Optionally, the grouping module 705 specifically includes: a first grouping sub-module for obtaining the behavior data generated by the user using the welfare coupon and the welfare order data based on the user's device number; a second grouping sub-module for calculating the key index values for scoring the welfare resources according to the behavior data and the welfare order data; and a third grouping sub-module for calculating the total score of each welfare resource in the target welfare resource pool through the key index values corresponding to each index according to the attributes of the key indexes configured in the welfare scoring policy, so as to obtain the welfare scoring results of each welfare resource.

[0106] Optionally, the second grouping sub-module specifically includes: a first index extraction unit for extracting the exposure volume of all welfare resources in the resource pool during the target time period based on the behavior data, and extracting the verification volume and / or the receiving volume of all users' welfare receipts in the resource pool during the target time period based on the welfare order data; and a second index extraction unit for calculating the value of the data index according to the exposure volume, the verification volume and / or the receiving volume.

[0107] Optionally, the third grouping sub-module specifically includes: a first index processing unit for determining the index coefficient based on the number of the data indexes configured in the welfare scoring policy; a second index processing unit for querying the value points corresponding to the weight indexes through a preset welfare index library and determining the specific value points of the value points according to the number of the weight indexes configured in the welfare scoring policy to obtain the weight points; and a third index processing unit for comprehensively calculating the total score of the welfare resource according to the value of the data index, the index coefficient and the weight points.

[0108] Optionally, the recommendation module 707 specifically includes: a first recommendation sub-module for pre-sorting according to the welfare scoring results to determine the first recommendation order; a second recommendation sub-module for matching and associating the target welfare resources based on the first recommendation order and presenting the target welfare resources to the user; and a third recommendation sub-module for dynamically scheduling the recommendation order of each welfare resource in the target welfare resource pool according to the user's operations on the target welfare resources, so as to dynamically present the welfare resources to the user.

[0109] Optionally, the third recommendation sub-module specifically includes: a real-time welfare scoring unit, configured to calculate in real time a real-time welfare scoring result of the welfare resources in the current target welfare resource pool based on the user's action of receiving and / or writing off the target welfare resources, and real-time user dynamic metrics; a real-time welfare recommendation unit, configured to dynamically adjust the recommendation order of the welfare resources in the target welfare resource pool according to the real-time welfare scoring result.

[0110] Optionally, the optimization module 709 specifically includes: a first optimization sub-module, configured to monitor the entire recommendation process of the target welfare resources based on a preset welfare recommendation downgrading strategy; a second optimization sub-module, configured to, when the system is abnormal or the welfare resource recommendation fails, initialize and sort the welfare resources in the welfare resource pool and present them to the user, so as to complete the recommendation optimization of the target welfare resources.

[0111] Optionally, the device further includes: a data collection module, configured to collect the user's behavior data, receiving record data, order record data, write-off data, and data management and maintenance according to the Pingback statistical method; a welfare scoring configuration module, configured to configure welfare scoring policies, including key index management for scoring and data management of scoring dimensions; a policy management module, configured to connect to a traffic grouping interface, maintain the recommendation order of welfare resources, and adaptively adjust the welfare recommendation downgrading strategy.

[0112] In some examples, relevant welfare scoring policies can be configured and modified according to the welfare scoring configuration module and the policy management module, to ensure that the recommendation order of each welfare resource in the resource pool can be adjusted in real time according to the user's real-time actions such as receiving or writing off welfare resources.

[0113] According to another aspect of the embodiments of the present application, the present application provides an electronic device, as Figure 8 shown, including a memory 801, a processor 803, a communication interface 805, and a communication bus 807. A computer program that can run on the processor 803 is stored in the memory 801. The memory 801 and the processor 803 communicate through the communication interface 805 and the communication bus 807. When the processor 803 executes the computer program, the steps of the above method are implemented.

[0114] In the above-mentioned electronic device, the memory and the processor communicate through a communication bus and a communication interface. The communication bus can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0115] The memory may include a Random Access Memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0116] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0117] According to another aspect of the embodiments of the present application, there is also provided a computer-readable medium having non-volatile program code executable by a processor.

[0118] Optionally, in the embodiments of the present application, the computer-readable medium is configured to store program code for the processor to execute the following steps:

[0119] Step S202, determining the user's traffic grouping based on the user's welfare list request;

[0120] Step S204, matching the corresponding target welfare resource pool based on the traffic grouping;

[0121] Step S206, scoring each welfare resource in the resource pool based on the welfare scoring strategy corresponding to the target welfare resource pool to obtain a welfare scoring result;

[0122] Step S208: Dynamically obtain the welfare recommendation order based on the welfare scoring result, and dynamically recommend target welfare resources to the user according to the welfare recommendation order;

[0123] Step S210: Perform recommendation compensation according to the abnormal recommendation process of the target welfare resource through the welfare recommendation downgrading strategy to complete the recommendation optimization of the target welfare resource.

[0124] Optionally, the specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0125] When implementing the embodiments of the present application, reference can be made to the above various embodiments, and corresponding technical effects can be obtained.

[0126] It can be understood that these embodiments described herein can be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing sub-module can be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general purpose processors, controllers, microcontrollers, microprocessors, other electronic sub-modules for performing the functions described in the present application, or a combination thereof.

[0127] For software implementation, the technologies described herein can be implemented by sub-modules that execute the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented inside or outside the processor.

[0128] Those of ordinary skill in the art can realize that the sub-modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0129] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and sub-modules can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0130] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or sub-modules can be in electrical, mechanical or other forms.

[0131] The sub-modules described as separate components may or may not be physically separated. The components displayed as sub-modules may or may not be physical sub-modules, that is, they can be located in one place or distributed to multiple network sub-modules. Some or all of the sub-modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, in each embodiment of this application, the functional sub-modules can be integrated in a processing sub-module, or each sub-module can exist physically alone, or two or more sub-modules can be integrated in one sub-module.

[0133] If the function is implemented in the form of a software functional sub-module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0134] It should be noted that, in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0135] The above are only specific embodiments of the present application, enabling those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features claimed herein.

Claims

1. A resource recommendation optimization method, applied to a server, characterized in that: include: Determining a traffic grouping for a user based on a benefit list request from the user; Matching a corresponding target welfare resource pool based on the traffic grouping; Scoring each welfare resource in the resource pool based on the welfare scoring strategy corresponding to the target welfare resource pool, and obtaining a welfare scoring result; Dynamically obtain a welfare recommendation order based on the welfare scoring result, and dynamically recommend target welfare resources to the user according to the welfare recommendation order; Recommendation compensation is performed according to the abnormal recommendation process of the target welfare resource through the welfare recommendation downgrade strategy to complete the recommendation optimization of the target welfare resource.

2. The method according to claim 1, characterized in that Scoring each welfare resource in the resource pool based on the welfare scoring strategy corresponding to the target welfare resource pool to obtain the welfare scoring result includes: Obtain the behavior data and welfare order data generated by the user's use of welfare coupons based on the user's device number; Calculate key indicator values ​​for welfare resource scoring based on the behavior data and the welfare order data; According to the attributes of the key indicators configured in the welfare scoring strategy, the total score of each welfare resource in the target welfare resource pool is calculated by the key indicator values ​​corresponding to each indicator to obtain the welfare scoring result of each welfare resource.

3. The method according to claim 2, characterized in that The key indicator at least includes a weight indicator, a data indicator, and a value score representing a score corresponding to the weight indicator. The key indicator value for scoring welfare resources calculated based on the behavior data and the welfare order data includes: Extracting the exposure of all welfare resources in the resource pool within the target period based on the behavior data, and extracting the verification volume and / or collection volume of welfare collection by all users in the resource pool within the target period based on the welfare order data; The value of the data indicator is calculated based on the exposure amount, verification amount and / or collection amount.

4. The method according to claim 3, characterized in that The calculating the total score of each welfare resource in the target welfare resource pool according to the attributes of the key indicators configured in the welfare scoring strategy and the key indicator values ​​corresponding to each indicator includes: Determining an indicator coefficient based on the number of the data indicators configured in the welfare scoring strategy; The value score corresponding to the weighted indicator is searched through a preset welfare indicator library, and the specific score of the value score is determined according to the number of the weighted indicators configured in the welfare scoring strategy to obtain the weighted score; The total score of the welfare resource is calculated comprehensively according to the value of the data indicator, the indicator coefficient and the weight score.

5. The method according to claim 4, characterized in that The dynamically acquiring a welfare recommendation order based on the welfare scoring result, and dynamically recommending target welfare resources to the user according to the welfare recommendation order, comprises: Pre-sorting is performed according to the welfare scoring results to determine a first recommendation order; Based on the first recommendation order matching associated target welfare resources, presenting the target welfare resources to the user; The recommendation order of each of the welfare resources in the target welfare resource pool is dynamically scheduled according to the user's operation on the target welfare resource, so as to dynamically display the welfare resources to the user.

6. The method according to claim 5, characterized in that The dynamically scheduling the recommended order of each welfare resource in the target welfare resource pool according to the user's operation on the target welfare resource includes: Based on the user's collection and / or cancellation actions of the target welfare resources and the real-time user dynamic indicators, the real-time welfare scoring results of the welfare resources in the current target welfare resource pool are calculated in real time; The recommendation order of the welfare resources in the target welfare resource pool is dynamically adjusted according to the real-time welfare scoring result.

7. The method according to claim 1, characterized in that The recommendation compensation is performed according to the abnormal recommendation process of the target welfare resource through the welfare recommendation downgrade strategy, including: Monitoring the entire recommendation process of the target welfare resource based on a preset welfare recommendation downgrade strategy; When the system is abnormal or the welfare resource recommendation fails, the welfare resources in the welfare resource pool will be initialized and sorted and then displayed to the user.

8. A resource recommendation optimization device, characterized in that: include: A grouping module, for determining a user's traffic grouping based on the user's benefit list request; An identification module, configured to match a corresponding target welfare resource pool based on the traffic grouping; A scoring module, used to score each welfare resource in the resource pool based on the welfare scoring strategy corresponding to the target welfare resource pool, and obtain a welfare scoring result; A recommendation module, used to dynamically obtain a welfare recommendation order based on the welfare scoring result, and dynamically recommend target welfare resources to the user according to the welfare recommendation order; The optimization module performs recommendation compensation according to the abnormal recommendation process of the target welfare resource through the welfare recommendation downgrade strategy to complete the recommendation optimization of the target welfare resource.

9. An electronic device, comprising a memory, a processor, a communication interface and a communication bus, wherein the memory stores a computer program that can be run on the processor, and the memory and the processor communicate through the communication bus and the communication interface, characterized in that: When the processor executes the computer program, the resource recommendation optimization method described in any one of claims 1 to 7 is implemented.

10. A computer readable medium having a non-volatile program code executable by a processor, characterized in that: The program code enables the processor to execute the resource recommendation optimization method described in any one of claims 1 to 7.

Images