Virtual resource sending method and device, electronic equipment and storage medium

Abstract

The invention discloses a virtual resource sending method and device, electronic equipment and a storage medium, and is applied to the field of computers. According to the method, in combination with the overall condition of virtual resources used by an object group, the preference probability of a target object for the virtual resources of a certain resource quantity in the future is predicted, and the virtual resources are recommended for the target object according to the preference probability. According to the embodiment of the invention, calculation based on artificial intelligence does not need to be carried out, so that the occupied calculation resources and machine resources are relatively less, and the resource quantity dimension information of the virtual resources is considered when preference prediction is carried out, so that the cost of the sent virtual resources can be controlled. The preference condition of the target object is predicted in combination with the overall condition of using the virtual resources by the group, the preference condition prediction accuracy is improved by using the group image information on the premise of not needing artificial intelligence modeling, the sending effect of the virtual resources can be better improved, and the information interaction rate is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a method, apparatus, electronic device, and storage medium for sending virtual resources. Background Art

[0002] With the continuous development and popularization of Internet technology, people's demands for information interaction are also constantly changing. Many application programs promote information interaction and increase user stickiness by sending virtual resources to objects. However, the virtual resource sending solutions in related technologies are usually formulated by operators based on experience, suffering from the drawbacks of low promotion effect on information interaction and difficult cost control. Summary of the Invention

[0003] An embodiment of this application provides a method for sending virtual resources, which solves at least one of the foregoing technical problems.

[0004] According to one aspect of the embodiments of this application, a method for sending virtual resources is provided, and the method includes:

[0005] Determine a first prior probability corresponding to a first virtual resource with a first resource amount, where the first prior probability indicates the probability that the first virtual resource is selected;

[0006] Obtain first feature data of an object set, where the first feature data includes basic feature data and virtual resource selection data corresponding to each object in the object set, and the virtual resource selection data indicates whether the corresponding object uses the first virtual resource;

[0007] Obtain target basic feature data corresponding to a target object;

[0008] According to the first feature data and the target basic feature, determine a first conditional probability, where the first conditional probability is a conditional probability corresponding to the target basic feature obtained with the use of the first virtual resource as a prior condition;

[0009] Based on Bayes' theorem, according to the first prior probability and the first conditional probability, determine a first preference parameter corresponding to the target object, where the first preference parameter indicates the preference degree of the target object for the first virtual resource;

[0010] Send virtual resources to the target object according to the first preference parameter corresponding to the target object.

[0011] According to one aspect of the embodiments of this application, a virtual resource sending apparatus is provided, and the apparatus includes:

[0012] A basic data acquisition module is used to determine a first prior probability corresponding to a first virtual resource with a first resource quantity, where the first prior probability indicates the probability that the first virtual resource is selected; acquire first feature data of an object set, where the first feature data includes basic feature data and virtual resource selection data corresponding to each object in the object set, and the virtual resource selection data indicates whether the corresponding object uses the first virtual resource; and acquire target basic feature data corresponding to a target object.

[0013] A virtual resource sending module is used to determine a first conditional probability according to the first feature data and the target basic feature, where the first conditional probability is a conditional probability corresponding to the target basic feature obtained with using the first virtual resource as a prior condition; based on the Bayesian principle, determine a first preference parameter corresponding to the target object according to the first prior probability and the first conditional probability, where the first preference parameter indicates the preference degree of the target object for the first virtual resource; and send a virtual resource to the target object according to the first preference parameter corresponding to the target object.

[0014] According to one aspect of the embodiments of the present application, a computer device is provided. The computer device includes a processor and a memory. At least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the above virtual resource sending method.

[0015] According to one aspect of the embodiments of the present application, a computer-readable storage medium is provided. At least one instruction, at least one program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the above virtual resource sending method.

[0016] According to one aspect of the embodiments of the present application, a computer program product is provided. The computer program product includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes to implement the above virtual resource sending method.

[0017] The technical solutions provided by the embodiments of the present application can bring the following beneficial effects:

[0018] An embodiment of the present application provides a method for sending virtual resources. This method for sending virtual resources combines the overall situation of the use of virtual resources by a group of objects, predicts the preference probability of a target object for a certain amount of virtual resources in the future, and recommends virtual resources for the target object according to this preference probability. The embodiment of the present application does not require artificial intelligence-based calculations, so the computing resources and machine resources occupied are relatively small. Moreover, the object predicted is the preference probability of the target object for a certain amount of virtual resources, that is, the information of the resource amount dimension of the virtual resources is fully considered when making the preference prediction. Therefore, the cost of the sent virtual resources can be well controlled. By combining the overall situation of the group's use of virtual resources to predict the preference situation of the target object, compared with the technical solution in the related art that directly uses the virtual resources most recently used by a single object as the preferred resources of the single object, the use of group image information improves the accuracy of the preference situation prediction. Therefore, it can also better improve the sending effect of virtual resources and improve the information interaction rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0020] Figure 1 is a schematic diagram of an application program running environment provided by an embodiment of the present application;

[0021] Figure 2 is a flowchart of a method for sending virtual resources provided by an embodiment of the present application;

[0022] Figure 3 is a schematic diagram of a first conditional probability determination method flow provided by an embodiment of the present application;

[0023] Figure 4 is a schematic diagram of a method flow for sending virtual resources in a group scenario provided by an embodiment of the present application;

[0024] Figure 5 is a schematic diagram of a first sending parameter determination method flow provided by an embodiment of the present application;

[0025] Figure 6 is a schematic diagram of a process for determining a first inclination contribution parameter provided by an embodiment of the present application;

[0026] Figure 7 is a schematic diagram of a virtual resource sending interface provided by an embodiment of the present application;

[0027] Figure 8It is a block diagram of a virtual resource sending device provided by an embodiment of the present application;

[0028] Figure 9 It is a structural block diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0029] Before introducing the method embodiments provided by the present application, relevant terms or nouns that may be involved in the method embodiments of the present application are briefly introduced first, so as to facilitate the understanding of those skilled in the art of the present application.

[0030] Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and networks within a wide area network or a local area network to achieve data calculation, storage, processing, and sharing. Cloud technology is the general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model. It can form a resource pool, be used on demand, and is flexible and convenient. Cloud computing technology will become an important support. The background services of technical network systems require a large amount of computing and storage resources, such as video websites, picture-based websites, and more portal websites. With the high development and application of the Internet industry, in the future, each item may have its own identification mark and needs to be transmitted to the background system for logical processing. Data at different levels will be processed separately, and various industry data requires a powerful system back-end support, which can only be achieved through cloud computing.

[0031] Virtual resource recommendation: According to factors such as the application program type and the evaluation of an application program by an object of a certain application program, send virtual resources suitable for the use of the object of the application program. An automated recommendation algorithm for virtual resource recommendation can be designed so that the virtual resource sending operation can be automated. Many automated recommendation algorithms are implemented based on artificial intelligence, and the recommendation model is trained through machine learning to implement virtual resource recommendation and sending. The main purpose of virtual resource sending is to recommend personalized virtual resources for the objects corresponding to the objects in the application program, improve the utilization and interaction degree of virtual resources, and improve the object activity. The various objects of the application program interact with the application program, or promote the interaction between multiple objects from the same or different application programs.

[0032] Taking the application program as a game application program as an example, through the virtual resource recommendation in the game, the game experience of game objects can be improved, which is also convenient for the dissemination of virtual resources in the game, improves the dissemination efficiency of game virtual resources, and enhances the interaction and information dissemination of various information with the game as the carrier.

[0033] Before specifically elaborating on the embodiments of the present application, the relevant technical background related to the embodiments of the present application is introduced, so as to facilitate the understanding of those skilled in the art of the present application.

[0034] With the continuous development and popularization of Internet technology, people's demand for information interaction is also constantly changing. Many application programs promote information interaction by sending virtual resources to objects, increasing object stickiness.

[0035] Taking game application programs as an example, game application programs can give many virtual resources to game objects, such as game props and game skins of different values. In the embodiments of the present application, the concept of resource quantity is used to quantify this value. Taking virtual trading games as an example, the game props that can be given are virtual vouchers. Taking martial arts games as an example, game props for enhancing martial arts skills or defensive skills can be given. In the embodiments of the present application, the concept of resource quantity is used to quantify the value of virtual resources such as virtual vouchers in a computer.

[0036] In the scenario of sending virtual resources to game objects, game application programs in related technologies can form a gift package based on the virtual resources such as props and skins used by game players in the game in the recent period, and send the gift package to the game player to achieve the purpose of sending virtual resources. However, this technical solution considers less the value of the virtual resources in the gift package, resulting in the overall value of the gift package may be too high. Moreover, the virtual resources used by game players in the recent period do not represent the virtual resources that the game players will still prefer in the future. That is to say, this gift package generation method is also insensitive and inaccurate in capturing the preference trends of game players, which also reduces the information interaction promotion effect of the gift package.

[0037] Taking e-commerce application programs as an example, e-commerce application programs can give many virtual resources to e-commerce objects, such as gift vouchers of different values. In the embodiments of the present application, the resource quantity is used to quantify this value. In the scenario of sending virtual resources to e-commerce objects, e-commerce application programs in related technologies can form a gift package based on the gift vouchers used by e-commerce objects in the e-commerce application program in the recent period, and send the gift package to the e-commerce object to achieve the purpose of sending virtual resources. However, this technical solution considers less the value of the virtual resources in the gift package, resulting in the overall value of the gift package may be too high. Moreover, the gift vouchers used by e-commerce objects in the recent period do not represent the virtual resources that the e-commerce objects will still prefer in the future. That is to say, this gift package generation method is also insensitive and inaccurate in capturing the preference trends of e-commerce objects, which also reduces the information interaction promotion effect of the gift package.

[0038] It can be seen that in the related art, the technical solution of using the virtual resources used by the objects of the application program in the recent period as the preferred resources and sending gift packages to the objects according to the preferred resources has the disadvantages of low information interaction promotion effect and difficult cost control. In addition, there are some related technologies that can recommend and send virtual resources to objects through artificial intelligence, but these technical solutions have low utilization rate of the information of the virtual resources used by the objects in the recent period, which still leads to poor information interaction promotion effect of the sent virtual resources and still difficult to control the cost of the sent virtual resources. The technical solutions based on artificial intelligence also have additional technical problems such as high occupied computing resources and difficult training of artificial intelligence models.

[0039] In order to improve the information interaction effect of virtual resources, enhance the viscosity of objects, and control the cost of sent virtual resources, the embodiments of the present application provide a virtual resource sending method. The virtual resource sending method combines the overall situation of the virtual resources used by the object group to predict the preference probability of the target object for virtual resources with different resource amounts (different values) in the future, and recommends virtual resources for the target object according to the preference probability. The embodiments of the present application do not need to perform artificial intelligence-based calculations, so the occupied computing resources and machine resources are relatively small, and the predicted object is the preference probability of the target object for virtual resources with different values, that is, the information of the value dimension of the virtual resources is fully considered when making preference predictions, so the cost of the sent virtual resources can be well controlled. Combining the overall situation of the group using virtual resources to predict the preference situation of the target object, compared with the technical solution in the related art that directly uses the virtual resources recently used by a single object as the preference resources of the single object, the use of group image information improves the accuracy of preference situation prediction. Therefore, it can also better improve the sending effect of virtual resources and improve the information interaction rate.

[0040] To make the purpose, technical solution and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0041] It should be noted before the description that all the data used in the embodiments of this application have been desensitized data, and are legal usage data fully authorized by the relevant parties.

[0042] Please refer to Figure 1 , which shows a schematic diagram of the application program running environment provided by an embodiment of the present application. The application program running environment may include: a terminal 10 and a server 20.

[0043] The terminal 10 includes but is not limited to electronic devices such as mobile phones, computers, intelligent voice interaction devices, intelligent home appliances, vehicle-mounted terminals, game consoles, e-book readers, multimedia playback devices, and wearable devices. The client of the application program can be installed in the terminal 10.

[0044] In an embodiment of the present application, the above application can be any application that provides virtual resource sending services. Typically, the application can be a game application. Of course, in addition to game applications, virtual resource sending services can also be provided in other types of applications. For example, news applications, social applications, interactive entertainment applications, browser applications, shopping applications, content sharing applications, virtual reality (VR) applications, augmented reality (AR) applications, application store applications, etc. The embodiments of the present application do not make any limitations in this regard. The embodiments of the present application do not make any limitations in this regard. Optionally, a client of the above application runs on the terminal 10.

[0045] The server 20 is used to provide background services for the client of the application in the terminal 10. For example, the server 20 can be the background server of the above application. The server 20 can be a single server or a server cluster composed of multiple physical servers, that is, any server in a distributed cluster. The distributed cluster can concurrently respond to requests from multiple clients 10. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0046] Optionally, the terminal 10 and the server 20 can communicate with each other through the network 30. The terminal 10 and the server 20 can be directly or indirectly connected through wired or wireless communication methods, and the present application does not make any limitations in this regard.

[0047] Please refer to Figure 2 , which shows a flowchart of a virtual resource sending method provided by an embodiment of the present application. This method can be applied to a computer device. The above computer device refers to an electronic device with data calculation and processing capabilities. For example, the execution subject of each step can be Figure 1 any terminal 10 or server 20 in the application program running environment shown. This method can include the following steps:

[0048] S201. Determine the first prior probability corresponding to the first virtual resource with the first resource amount. The above first prior probability indicates the probability that the first virtual resource is selected.

[0049] In the embodiments of the present application, an application can send virtual resources of a single value or different values to an object using the application, and these values are all quantified using the concept of resource quantity. The object can select these virtual resources without discrimination. The selection probability of the virtual resources can be set by the application, and the embodiments of the present application regard it as a known piece of data. The virtual resource sending method in the embodiments of the present application can be applied to various applications that need to send virtual resources. The following takes a game application as an example for illustration, but this illustration does not limit the embodiments of the present application.

[0050] For example, for a game application, it can send high-value game packages or low-value game packages to game players. The virtual resources in the high-value game packages are high-value virtual resources, while the virtual resources in the low-value game packages are low-value virtual resources. The probabilities of the game application sending high-value virtual resources and low-value virtual resources can be determined by game developers. When both are sent, the probability of an object receiving or selecting a certain virtual resource is known, and this can be obtained by combining the sending probability and / or the historical selection tendency of the object. High value and low value are relative concepts, and the resource quantity of high value is higher than that of low value. The embodiments of the present application can obtain the prior probabilities of different virtual resources with different values as known quantities.

[0051] For example, in an implementation, the game application does not have different sending tendencies for virtual resources of different values, and the object does not have different selection tendencies either. Then the prior probability corresponding to the high-value virtual resource and the prior probability corresponding to the low-value virtual resource are the same. For example, both are 0.5, p(high) = p(low) = 1 / 2, where high and low respectively identify the high-value virtual resource and the low-value virtual resource. In the embodiments of the present application, the first resource quantity can indicate high value or low value, and the first virtual resource can be the high-value virtual resource and the low-value virtual resource.

[0052] S202. Obtain the first feature data of the object set. The above-mentioned first feature data includes the basic feature data and virtual resource selection data corresponding to each object in the above-mentioned object set, and the above-mentioned virtual resource selection data indicates whether the corresponding object uses the above-mentioned first virtual resource.

[0053] The object in the embodiments of the present application refers to the abstract expression in the computer world of the entity participating in the virtual resource interaction. The feature data corresponding to the group formed by the objects is the first feature data. The basic feature data in the embodiments of the present application refers to the feature data related to predicting virtual resource preferences or predicting the degree of virtual resource tendency. The present application does not limit the content of the basic feature data. For example, it can be object attribute data and / or object target records.

[0054] Object attribute data can be understood as the characteristics that describe the static portrait of the object itself, which is related to the specific application program, referring to the static attribute data used to describe the object in the application program. Object attribute data is the existing data in the application program. Taking a game application program as an example, object attribute data is the static attribute data used to describe the object in the game application program, such as game characters, game props, etc.

[0055] Object target records refer to the records generated by the interaction between the object and the application program. Taking a game application program as an example, object target records can include at least one of the following contents:

[0056] The first type of characteristics: the number of game login days per month in the past three months, the growth rate of the number of login days per month compared with the previous month, the online game duration per month in the past three months, the growth rate of the online duration per month compared with the previous month, the number of games logged in per month in the past three months, the growth rate of the number of games logged in per month compared with the previous month, the improvement rate of the average daily login days on weekends compared with the average daily login days on weekdays per month in the past three months, the proportion of login duration in each time period per month in the past three months (working hours, noon, after work, early morning), and the change in combat power value per month in the past three months.

[0057] The second type of characteristics: the number of collected gift packages, the number of received gift packages at each level, the number of received coupons at each level, the number of completed tasks, and the recharge level. In the embodiments of the present application, the meaning of the gift package is a set formed by virtual resources.

[0058] In some embodiments, the following at least one preprocessing can also be performed on the original basic feature data to obtain the preprocessed basic feature data, and the preprocessed basic feature data can be used as an effective component of the first feature data.

[0059] The embodiments of the present application do not limit the preprocessing method. For example, the following at least one processing method can be adopted: missing value processing, feature engineering processing.

[0060] Missing value processing: The general method for missing values is to delete the missing value records or fill them with specified values. If data integrity is considered, the missing values can be filled with the average value of the data.

[0061] Feature engineering processing includes at least one of the following operations: discretization, normalization.

[0062] Discretization: The purpose of discretization is to enhance the generalization ability. For example, features such as age and rank can be discretized using the equal-interval method. The specific operation is to group the features according to the same principle for each grouping interval. For example, if the age value range is 1 - 80, and the equal-interval discretization takes 10 as the interval, the age is successively divided into (21, 30), (31, 40). Ages falling within the same interval are assigned the same age feature, thus achieving the purpose of discretization.

[0063] Normalization: The normalization calculation formula is as follows. The purpose of normalization is to accelerate the output speed of the calculation results.

[0064] x' = (x - X_min) / (X_max - X_min), where x represents the original data, X_min represents the minimum value of the original data, X_max represents the maximum value of the original data, and x' represents the value after normalization.

[0065] Please refer to Table 1, which shows a partial schematic content of the first feature data of the object set in the game application example of the present application.

[0066] Table 1

[0067]

[0068]

[0069] Table 1 shows the desensitized basic feature data of each object in the object set. It can be seen that the basic feature data mainly expresses the following aspects of information:

[0070] figure: game character,

[0071] is_act: whether participated in activities historically,

[0072] act_day: monthly active days in the game,

[0073] gift_amt: value of gift package items (resource quantity),

[0074] get_num: quantity of items received,

[0075] Whether each object uses the first virtual resource, and whether it uses other virtual resources, such as the second virtual resource below, is also recorded, which is not shown here.

[0076] S203. Obtain the target basic feature data corresponding to the target object.

[0077] In the embodiments of the present application, the target basic feature data has the same meaning as the basic feature data described above, and it is the basic feature data corresponding to the target object. The target object may be located in the above object set or may not be located in the above object set. The embodiments of the present application do not make any limitations in this regard.

[0078] S204. Determine a first conditional probability according to the above first feature data and the above target basic feature. The above first conditional probability is obtained with the use of the above first virtual resource as a prior condition and corresponds to the conditional probability of the above target basic feature.

[0079] The above target basic feature data includes target values in at least one dimension. Taking Table 1 as an example, the target basic feature data and the basic feature data corresponding to each object include dimensions such as figure, is_act, act_day, gift_amt, and get_num. Please refer to Figure 3 , which shows a schematic flowchart of the method for determining the first conditional probability in the embodiments of the present application. The above determination of the first conditional probability according to the above first feature data and the above target basic feature includes:

[0080] S301. For each target value in each dimension of the above target basic feature data, determine an associated object according to the above first feature data. The basic feature data corresponding to the associated object includes the above target value; determine the target conditional probability corresponding to the above target value according to the virtual resource selection data of the associated object and the virtual resource selection data of the above object set. The above target conditional probability is the conditional probability of the occurrence of the above target value obtained with the use of the above first virtual resource as a prior condition;

[0081] Taking the dimension of "figure" as an example, if the "figure" in the target basic feature data is "mage", then the target value of the "figure" dimension is "mage", and the associated objects are the objects in the object set with "figure" being "mage". According to the virtual resource selection data of the above object set, the object that uses the first virtual resource can be extracted, which is Account1(vr1). According to the virtual resource selection data of the associated objects, the object Account2(vr2) that uses the first virtual resource can be extracted. According to the respective quantity statistical results of Account1(vr1) and Account2(vr2), the target conditional probability corresponding to the target value of "mage" can be calculated. Specifically, it is the conditional probability that the target value is "mage" with the use of the above first virtual resource as the prior condition. Taking the first resource quantity indicating high value and the first virtual resource being a high-value virtual resource as an example, this target conditional probability can be expressed as p(figure|high), where high represents high value. Based on the same inventive concept, p(is_act|high), p(act_day|high), p(gift_amt|high), p(get_num|high) can also be obtained. The determination method of the meanings of p(is_act|high), p(act_day|high), p(gift_amt|high), p(get_num|high) refers to p(figure|high), and will not be elaborated here.

[0082] S302. Based on the product of the target conditional probabilities corresponding to each of the above target values, the above first conditional probability is obtained.

[0083] In one embodiment, the first conditional probability can be calculated based on the formula p(figure|high)*p(is_act|high)*p(act_day|high)*p(gift_amt|high)*p(get_num|high).

[0084] S205. Based on the Bayesian principle, according to the above first prior probability and the above first conditional probability, the first preference parameter corresponding to the above target object is determined, and the first preference parameter indicates the preference degree of the above target object for the above first virtual resource.

[0085] In one embodiment, the above first preference parameter can be determined based on the product of the above first conditional probability and the above first prior probability. Continuing with the previous example, the first preference parameter can be calculated according to the following formula:

[0086] posterior(high) = p(high) * p(figure|high) * p(is_act|high) * p(act_day|high) * p(gift_amt|high) * p(get_num|high) / evidence; where posterior(high) represents the first preference parameter, p(high) represents the first prior probability, [p(figure|high) * p(is_act|high) * p(act_day|high) * p(gift_amt|high) * p(get_num|high)] represents the first conditional probability, and evidence is a constant, which represents the sum of the "product results" corresponding to each virtual resource participating in the virtual resource sending in the embodiments of the present application. The "product result" refers to the product result of the prior probability and the conditional probability corresponding to the virtual resource.

[0087] Taking the case where virtual resources with two different values (resource amounts) participate in the virtual resource sending as an example, the embodiments of the present application can determine the second prior probability corresponding to the second virtual resource with the second resource amount. The second prior probability indicates the probability that the second virtual resource is selected. The first resource amount is different from the second resource amount, and the second virtual resource is different from the first virtual resource; according to the first characteristic data and the target basic characteristics, determine the second conditional probability, which is the conditional probability corresponding to the target basic characteristics obtained with the use of the second virtual resource as the prior condition; based on the Bayesian principle, according to the second prior probability and the second conditional probability, determine the second preference parameter corresponding to the target object. The second preference parameter indicates the preference degree of the target object for the first virtual resource.

[0088] The acquisition methods of the second prior probability, the second conditional probability, and the second preference parameter are respectively based on the same inventive concept as the first prior probability, the first conditional probability, and the first preference parameter in the foregoing, and the formula meanings are also similar, so no further elaboration will be made here. Taking the case where high-value virtual resources and low-value virtual resources both participate in the virtual resource sending as an example in the embodiments of the present application, if the high-value virtual resource is the first virtual resource, then the low-value virtual resource can be the second virtual resource.

[0089] The second preference parameter can be calculated according to the formula posterior(low) = p(low) * p(figure|low) * p(is_act|low) * p(act_day|low) * p(gift_amt|low) * p(get_num|low) / evidence. Here, low represents low value (low resource quantity), posterior(low) represents the second preference parameter, p(low) represents the second prior probability, [p(figure|low) * p(is_act|low) * p(act_day|low) * p(gift_amt|low) * p(get_num|low)] represents the second conditional probability, and evidence is a constant, which represents the sum of the "product results" corresponding to each virtual resource participating in the virtual resource sending in the embodiments of this application. The "product result" refers to the product of the prior probability and the conditional probability corresponding to the virtual resource.

[0090] Taking the case where virtual resources with two different values participate in the virtual resource sending as an example, evidence is the sum of the product result obtained by multiplying the first conditional probability by the first prior condition and the product result obtained by multiplying the second conditional probability by the second prior condition. That is, the value of evidence satisfies the following relationship: evidence = p(high) * p(figure|high) * p(is_act|high) * p(act_day|high) * p(gift_amt|high) * p(get_num|high) + p(low) * p(figure|low) * p(is_act|low) * p(act_day|low) * p(gift_amt|low) * p(get_num|low);

[0091] Obviously, the denominator evidence in the first preference parameter and the second preference parameter is a constant. Therefore, in the scenario of comparing preference parameters or comparing other parameters calculated based on preference parameters, evidence can be not considered. That is to say, in some embodiments, the product of the first prior conditional probability and the first conditional probability can be directly used as the first preference parameter. Similarly, the product of the second prior conditional probability and the second conditional probability can be directly used as the second preference parameter.

[0092] S206. Send virtual resources for the above target object according to the first preference parameter corresponding to the above target object.

[0093] The embodiments of the present application do not limit the specific method of sending virtual resources to the target object according to the first preference parameter corresponding to the target object. For example, a reference value can be set, and when the first preference parameter is greater than the reference value, the first virtual resource is sent to the target object. Or the first preference parameter calculates the first inclination contribution parameter, and when the first inclination contribution parameter is greater than the reference value, the first virtual resource is sent to the target object. The meaning and calculation method of the first inclination contribution parameter are described below.

[0094] Taking the case where virtual resources of two different values participate in the virtual resource sending as an example, in the embodiments of the present application, sending virtual resources to the target object according to the first preference parameter corresponding to the target object includes: sending virtual resources to the target object according to the first preference parameter corresponding to the target object and the second preference parameter corresponding to the target object.

[0095] Of course, the embodiments of the present application do not limit the specific method of sending virtual resources to the target object according to the first preference parameter corresponding to the target object and the second preference parameter corresponding to the target object. For example, if the first preference parameter is greater than the second preference parameter and the first preference parameter is greater than the foregoing reference value, the first virtual resource can be sent to the target object. If the second preference parameter is greater than the first preference parameter and the second preference parameter is greater than the foregoing reference value, the second virtual resource can be sent to the target object.

[0096] To improve the virtual resource sending efficiency and reduce the computing resources consumed in the process of selecting which virtual resource to send, the embodiments of the present application can also perform group virtual resource sending. Please refer to Figure 4 , which shows a schematic flowchart of the method for sending virtual resources in a group scenario in the embodiments of the present application. Sending virtual resources to the target object according to the first preference parameter corresponding to the target object and the second preference parameter corresponding to the target object further includes:

[0097] S401. Obtain a target object cluster, where the target object cluster includes the target object.

[0098] First, determine the group of virtual resources to be sent, that is, the target object cluster. Of course, the embodiments of the present application do not limit the method for determining the target object cluster, and it can be considered as a known data.

[0099] S402. According to the first preference parameter corresponding to each object in the target object cluster, determine the first sending parameter corresponding to the target object cluster, where the first sending parameter represents the tendency to send the first virtual resource to the target object cluster.

[0100] The embodiments of the present application do not limit the method for determining the first transmission parameter. For example, the first preference parameters corresponding to each object in the above-mentioned target object cluster can be aggregated, and their sum value can be used as the first transmission parameter.

[0101] In one embodiment, in order to consider more information when specifically transmitting virtual resources and realize a more reasonable modeling of the tendency degree of transmitting the first virtual resource, a method for determining the first transmission parameter is proposed. Please refer to Figure 5 , which shows the schematic flow chart of the method for determining the first transmission parameter in the embodiments of the present application.

[0102] S501. Calculate the first tendency contribution parameter corresponding to the above object according to the first preference parameter corresponding to each object in the above-mentioned target object cluster. The first tendency contribution parameter characterizes the tendency degree of transmitting the first virtual resource to the corresponding object;

[0103] The calculation methods of the first tendency contribution degree parameters of each object are based on the same inventive concept. Taking the first tendency degree contribution parameter of the target object as an example, the first tendency contribution parameter corresponding to the target object is calculated according to the first preference parameter corresponding to the target object. Please refer to Figure 6 , which shows the schematic flow chart of determining the first tendency contribution parameter in the embodiments of the present application. The above-mentioned calculation of the first tendency contribution parameter corresponding to the target object according to the first preference parameter corresponding to the target object includes:

[0104] S601. Determine the target feature according to the above-mentioned target basic feature data. The target feature indicates at least one of the following types of information: the object activity of the above-mentioned target object, the object resource status of the above-mentioned target object.

[0105] The embodiments of the present application do not limit the quantification methods of object activity or object resource status. The object resource status can also be understood as the object value, which does not constitute an implementation limitation or obstacle to the embodiments of the present application. In one embodiment, the activity value recorded in the game application can be used to characterize the object activity, and the paid value recorded in the game program can be used to characterize the object value.

[0106] S602. Determine the first tendency contribution parameter corresponding to the above-mentioned target object according to the above-mentioned first preference parameter and the above-mentioned target feature.

[0107] The embodiments of the present application do not limit the quantification method of the first tendency contribution parameter, which does not constitute an implementation limitation or obstacle to the embodiments of the present application. In one embodiment, the first tendency contribution parameter corresponding to the target object can be calculated based on the formula: first preference parameter * log(activity value + paid value).

[0108] S502. Determine the first sending parameter corresponding to the target object cluster based on the cumulative statistical results of the first tendency contribution parameters corresponding to each of the above objects.

[0109] Taking the target object cluster including n objects as an example, according to the formula To calculate the first sending parameter, posterior(i) represents the preference parameter of the resource corresponding to the object i, active(i) represents the activity value of the object i, pay(i) represents the payment value of the object i, and n represents the number of objects in the target object cluster. The calculation method of the preference parameter of each account for the first virtual resource is based on the same inventive concept as the calculation method of the first preference parameter, which will not be repeated here.

[0110] S403. Determine a second sending parameter corresponding to the target object cluster according to the second preference parameter corresponding to each object in the target object cluster, where the second sending parameter represents a tendency to send the second virtual resource to the target object cluster.

[0111] The method for determining the second sending parameter and the method for determining the first sending parameter are based on the same inventive concept, and are not described in detail herein.

[0112] S404. Determine a target virtual resource according to the first sending parameter and the second sending parameter, the target virtual resource being the first virtual resource or the second virtual resource, and send the target virtual resource to each account in the target object cluster.

[0113] The embodiment of the present application does not limit the method for determining the target virtual resource. In short, the first sending parameter and the second sending parameter can be directly compared. If the first sending parameter is larger, the first virtual resource is determined as the target virtual resource. If the second sending parameter is larger, the second virtual resource is determined as the target virtual resource.

[0114] In an implementation scenario, if the total value of a gift package is determined (the total amount of resources is determined), different gift packages can be generated based on the different inclinations of different object groups towards high-value virtual resources and low-value virtual resources. For example, object group 1 tends to prefer high-value virtual resources, that is, the first virtual resource is determined as the target virtual resource. Object group 2 tends to prefer low-value virtual resources, that is, the second virtual resource is determined as the target virtual resource. A gift package sent to object group 2 can be generated based on low-value virtual resources, and a gift package sent to object group 1 can be generated based on high-value virtual resources. In other words, the value is unevenly distributed to maximize the use of the gift package value and meet the needs and preferences of each object group.

[0115] Please refer to Figure 7, which shows a schematic diagram of the virtual resource sending interface provided by the embodiments of the present application. Each time a game is logged in, virtual items will be sent to game players in this sending interface. These virtual items can be sent according to the virtual item sending method provided by the embodiments of the present application, and different game players can receive different virtual items. Game player 1 receives a low-value game package, "low-level" spirit stones and "healing" medicines. Game player 2 receives a high-value game package, "high-level" props and a strong protective shield. In order to verify the technical effects of the embodiments of the present application, a one-week A / B test was conducted. The A / B test is a commonly used experimental design method for comparing the effect differences of two or more different treatment methods or strategies on a certain index to determine which method is better. In the A / B test, the experimental objects are randomly divided into two groups, one group as the control group and the other group as the experimental group. Different treatment methods or strategies are adopted respectively, and comparisons are made on a certain index. The control group usually adopts the existing treatment method or strategy as a comparison, and the experimental group adopts the new treatment method or strategy. By comparing the differences between the two groups on the index, it can be evaluated whether the effect of the new treatment method or strategy is significant.

[0116] In the A / B test of the embodiments of the present application, the experimental group and the control group are divided. The experimental group uses the technical solution of the embodiments of the present application to send virtual resources, and the control group uses the old technical solution to send virtual resources. Each group has 246 players. The high-value package receiving rate of the experimental group is 43% higher than that of the control group, and the game return rate within 7 days after receiving the package is 29% higher. It can be seen that the technical solution of the embodiments of the present application has an obvious promoting effect on the virtual resource interaction efficiency and the game return rate. The game return rate refers to the ratio of lost objects who start playing the game again after a period of time. This is a positive phenomenon for game developers because it means the game's attractiveness is sufficient to bring back the objects. For example, assume a game has 1000 active objects in the first week, but the number of objects gradually decreases in the following weeks. If a large number of these lost objects return after several weeks, the game's return rate will be high. The game return rate can be calculated by dividing the number of lost objects in the second calculation period by the number of returned objects in the third calculation period. This index can be divided into weekly return rate, bi-weekly return rate, and monthly return rate according to the calculation period. In short, a high game return rate is a positive signal, indicating that the game has attractiveness and lasting appeal.

[0117] Please refer to Figure 8 , which shows a block diagram of the virtual resource sending device provided by an embodiment of the present application. This device has the function of implementing the above virtual resource sending method. The above function can be implemented by hardware or by hardware executing corresponding software. This device can be a computer device or can be set in a computer device. The above device includes:

[0118] A basic data acquisition module 801 is configured to determine a first prior probability corresponding to a first virtual resource having a first resource quantity, where the first prior probability indicates the probability that the first virtual resource is selected; acquire first feature data of an object set, where the first feature data includes basic feature data and virtual resource selection data corresponding to each object in the object set, and the virtual resource selection data indicates whether the corresponding object uses the first virtual resource; and acquire target basic feature data corresponding to a target object.

[0119] A virtual resource sending module 802 is configured to determine a first conditional probability according to the first feature data and the target basic feature, where the first conditional probability is a conditional probability corresponding to the target basic feature obtained with using the first virtual resource as a prior condition; based on the Bayesian principle, determine a first preference parameter corresponding to the target object according to the first prior probability and the first conditional probability, where the first preference parameter indicates the preference degree of the target object for the first virtual resource; and send a virtual resource to the target object according to the first preference parameter corresponding to the target object.

[0120] In one embodiment, the target basic feature data includes target values in at least one dimension, and the virtual resource sending module 802 is configured to perform the following operations:

[0121] For each target value in each dimension of the target basic feature data, determine an associated object according to the first feature data, where the basic feature data corresponding to the associated object includes the target value; determine a target conditional probability corresponding to the target value according to the virtual resource selection data of the associated object and the virtual resource selection data of the object set, where the target conditional probability is a conditional probability of the occurrence of the target value obtained with using the first virtual resource as a prior condition;

[0122] Obtain the first conditional probability based on the product of the target conditional probabilities corresponding to the respective target values.

[0123] In one embodiment, the virtual resource sending module 802 is configured to perform the following operations:

[0124] Determine the first preference parameter based on the product of the first conditional probability and the first prior probability.

[0125] In one embodiment, the virtual resource sending module 802 is configured to perform the following operations:

[0126] Determine the second prior probability corresponding to the second virtual resource with the second resource quantity, where the second prior probability indicates the probability that the second virtual resource is selected, the first resource quantity is different from the second resource quantity, and the second virtual resource is different from the first virtual resource;

[0127] Determine the second conditional probability according to the first characteristic data and the target basic characteristic, where the second conditional probability is the conditional probability corresponding to the target basic characteristic obtained with the use of the second virtual resource as the prior condition;

[0128] Based on the Bayesian principle, determine the second preference parameter corresponding to the target object according to the second prior probability and the second conditional probability, where the second preference parameter indicates the preference degree of the target object for the first virtual resource;

[0129] Send a virtual resource to the target object according to the first preference parameter corresponding to the target object and the second preference parameter corresponding to the target object.

[0130] In one embodiment, the virtual resource sending module 802 is configured to perform the following operations:

[0131] Obtain a target object cluster, where the target object cluster includes the target object;

[0132] Determine the first sending parameter corresponding to the target object cluster according to the first preference parameter corresponding to each object in the target object cluster, where the first sending parameter characterizes the tendency degree of sending the first virtual resource to the target object cluster;

[0133] Determine the second sending parameter corresponding to the target object cluster according to the second preference parameter corresponding to each object in the target object cluster, where the second sending parameter characterizes the tendency degree of sending the second virtual resource to the target object cluster;

[0134] Determine a target virtual resource according to the first sending parameter and the second sending parameter, where the target virtual resource is the first virtual resource or the second virtual resource;

[0135] Send the target virtual resource to each account in the target object cluster.

[0136] In one embodiment, the virtual resource sending module 802 is configured to perform the following operations:

[0137] Calculate the first tendency contribution parameter corresponding to the object according to the first preference parameter corresponding to each object in the target object cluster, where the first tendency contribution parameter characterizes the tendency degree of sending the first virtual resource to the corresponding object;

[0138] Determine the first transmission parameter corresponding to the target object cluster based on the cumulative statistical results of the first tendency contribution parameters corresponding to each of the above objects.

[0139] In one embodiment, the virtual resource sending module 802 is configured to perform the following operations:

[0140] Determine a target feature according to the above target basic feature data, where the target feature indicates at least one of the following types of information: the object activity of the target object, the object resource status of the target object;

[0141] Determine the first tendency contribution parameter corresponding to the target object according to the above first preference parameter and the target feature.

[0142] It should be noted that when the device provided in the above embodiment realizes its functions, only the division of the above function modules is used for illustration. In actual applications, the above functions can be allocated to different function modules according to needs, that is, the internal structure of the device is divided into different function modules to complete all or part of the functions described above. In addition, the device provided in the above embodiment and the method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0143] Please refer to Figure 9 , which shows a structural block diagram of a computer device provided in an embodiment of the present application. The computer device can be a server for executing the above virtual resource sending method. Specifically:

[0144] The computer device 1100 includes a central processing unit (CPU) 1101, a system memory 1104 including a random access memory (RAM) 1102 and a read only memory (ROM) 1103, and a system bus 1105 connecting the system memory 1104 and the central processing unit 1101. The computer device 1100 also includes a basic input / output system (I / O (Input / Output) system) 1106 for facilitating the transfer of information between various components within the computer, and a mass storage device 1107 for storing an operating system 1113, application programs 1114, and other program modules 1115.

[0145] The basic input / output system 1106 includes a display 1108 for displaying information and input devices 1109 such as a mouse, keyboard, etc. for inputting information of an object. Both the display 1108 and the input devices 1109 are connected to the central processing unit 1101 through an input / output controller 1110 connected to the system bus 1105. The basic input / output system 1106 may further include an input / output controller 1110 for receiving and processing inputs from a plurality of other devices such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 1110 also provides outputs to a display screen, printer, or other types of output devices.

[0146] The mass storage device 1107 is connected to the central processing unit 1101 through a mass storage controller (not shown) connected to the system bus 1105. The mass storage device 1107 and its associated computer-readable medium provide non-volatile storage for the computer device 1100. That is to say, the mass storage device 1107 may include computer-readable media (not shown) such as a hard disk or a CD-ROM (Compact Disc Read-Only Memory) drive.

[0147] Without loss of generality, computer-readable media may include computer storage media and communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes RAM, ROM, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory or other solid-state memory technologies, CD-ROM, DVD (Digital Video Disc) or other optical storage, magnetic tape cartridges, tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will know that computer storage media are not limited to the above several types. The above system memory 1104 and mass storage device 1107 may be collectively referred to as memory.

[0148] According to various embodiments of the present application, the computer device 1100 can also run on a remote computer on the network through a network such as the Internet. That is, the computer device 1100 can be connected to the network 1112 through the network interface unit 1111 connected to the system bus 1105. Or rather, the network interface unit 1111 can also be used to connect to other types of networks or remote computer systems (not shown).

[0149] The above-mentioned memory further includes a computer program, which is stored in the memory and is configured to be executed by one or more processors to implement the above-mentioned virtual resource sending method.

[0150] In an exemplary embodiment, a computer-readable storage medium is also provided. At least one instruction, at least one program segment, a code set or an instruction set is stored in the above-mentioned storage medium. When the above-mentioned at least one instruction, the above-mentioned at least one program segment, the above-mentioned code set or the above-mentioned instruction set is executed by a processor, the above-mentioned virtual resource sending method is implemented.

[0151] Specifically, the virtual resource sending method includes:

[0152] Determine the first prior probability corresponding to the first virtual resource with the first resource amount. The above-mentioned first prior probability indicates the probability that the first virtual resource is selected;

[0153] Obtain the first feature data of the object set. The above-mentioned first feature data includes the basic feature data and virtual resource selection data corresponding to each object in the object set. The above-mentioned virtual resource selection data indicates whether the corresponding object uses the above-mentioned first virtual resource;

[0154] Obtain the target basic feature data corresponding to the target object;

[0155] According to the above-mentioned first feature data and the above-mentioned target basic feature, determine the first conditional probability. The above-mentioned first conditional probability is the conditional probability corresponding to the above-mentioned target basic feature obtained with the use of the above-mentioned first virtual resource as a prior condition;

[0156] Based on Bayes' theorem, according to the above-mentioned first prior probability and the above-mentioned first conditional probability, determine the first preference parameter corresponding to the above-mentioned target object. The above-mentioned first preference parameter indicates the preference degree of the above-mentioned target object for the above-mentioned first virtual resource;

[0157] Send virtual resources to the target object according to the first preference parameter corresponding to the target object.

[0158] In one embodiment, the above-mentioned target basic feature data includes target values in at least one dimension. The determining of the first conditional probability according to the above-mentioned first feature data and the above-mentioned target basic feature includes:

[0159] For each target value under each of the above-mentioned dimensions in the above-mentioned target basic feature data, determine an associated object according to the above-mentioned first feature data, and the basic feature data corresponding to the associated object includes the above-mentioned target value; according to the virtual resource selection data of the associated object and the virtual resource selection data of the object set, determine the target conditional probability corresponding to the above-mentioned target value, and the target conditional probability is the conditional probability of the occurrence of the above-mentioned target value with the use of the above-mentioned first virtual resource as a prior condition;

[0160] Based on the product of the target conditional probabilities corresponding to each of the above-mentioned target values, obtain the above-mentioned first conditional probability.

[0161] In one embodiment, the above-mentioned determining the first preference parameter corresponding to the target object based on the Bayesian principle according to the above-mentioned first prior probability and the above-mentioned first conditional probability includes:

[0162] Based on the product of the above-mentioned first conditional probability and the above-mentioned first prior probability, determine the above-mentioned first preference parameter.

[0163] In one embodiment, the above-mentioned method further includes:

[0164] Determine the second prior probability corresponding to the second virtual resource with the second resource amount, and the second prior probability indicates the probability that the second virtual resource is selected, the above-mentioned first resource amount is different from the above-mentioned second resource amount, and the above-mentioned second virtual resource is different from the above-mentioned first virtual resource;

[0165] According to the above-mentioned first feature data and the above-mentioned target basic feature, determine the second conditional probability, and the second conditional probability is the conditional probability corresponding to the above-mentioned target basic feature obtained with the use of the above-mentioned second virtual resource as a prior condition;

[0166] Based on the Bayesian principle, according to the above-mentioned second prior probability and the above-mentioned second conditional probability, determine the second preference parameter corresponding to the above-mentioned target object, and the second preference parameter indicates the preference degree of the above-mentioned target object for the above-mentioned first virtual resource;

[0167] The above-mentioned sending a virtual resource to the target object according to the first preference parameter corresponding to the target object includes:

[0168] Send a virtual resource to the target object according to the first preference parameter corresponding to the target object and the second preference parameter corresponding to the target object.

[0169] In one embodiment, the above-mentioned sending a virtual resource to the target object according to the first preference parameter corresponding to the target object and the second preference parameter corresponding to the target object further includes:

[0170] Obtain a target object cluster, where the target object cluster includes the target objects;

[0171] Determine a first sending parameter corresponding to the target object cluster according to a first preference parameter corresponding to each object in the target object cluster, where the first sending parameter characterizes the tendency to send the first virtual resource to the target object cluster;

[0172] Determine a second sending parameter corresponding to the target object cluster according to a second preference parameter corresponding to each object in the target object cluster, where the second sending parameter characterizes the tendency to send the second virtual resource to the target object cluster;

[0173] Determine a target virtual resource according to the first sending parameter and the second sending parameter, where the target virtual resource is the first virtual resource or the second virtual resource;

[0174] Send the target virtual resource to each account in the target object cluster.

[0175] In one embodiment, the determining the first sending parameter corresponding to the target object cluster according to the first preference parameter corresponding to each object in the target object cluster includes:

[0176] Calculate a first tendency contribution parameter corresponding to each object according to the first preference parameter corresponding to each object in the target object cluster, where the first tendency contribution parameter characterizes the tendency to send the first virtual resource to the corresponding object;

[0177] Determine the first sending parameter corresponding to the target object cluster based on the cumulative statistical result of the first tendency contribution parameters respectively corresponding to each object.

[0178] In one embodiment, the calculating the first tendency contribution parameter corresponding to each object according to the first preference parameter corresponding to each object in the target object cluster includes: calculating the first tendency contribution parameter corresponding to the target object according to the first preference parameter corresponding to the target object;

[0179] The calculating the first tendency contribution parameter corresponding to the target object according to the first preference parameter corresponding to the target object includes:

[0180] Determine a target feature according to the target basic feature data, where the target feature indicates at least one of the following types of information: the object activity of the target object, the object resource status of the target object;

[0181] Determine the first tendency contribution parameter corresponding to the target object according to the first preference parameter and the target feature.

[0182] Optionally, the computer-readable storage medium may include: ROM (Read Only Memory), RAM (Random Access Memory), SSD (Solid State Drives), or optical discs, etc. Among them, the random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0183] In an exemplary embodiment, a computer program product or a computer program is further provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above virtual resource sending method.

[0184] It should be understood that the term "plurality" mentioned herein refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after. In addition, the step numbers described herein only exemplarily show a possible execution sequence between steps. In some other embodiments, the above steps may not be executed in the order of the numbers. For example, two steps with different numbers are executed simultaneously, or two steps with different numbers are executed in the reverse order of the illustration. The embodiments of the present application do not limit this.

[0185] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of the module or unit.

[0186] In addition, in the specific implementation manner of the present application, for data related to object information, etc., when the above embodiments of the present application are applied to specific products or technologies, object permission or consent needs to be obtained, and the collection, use, and processing of the relevant data need to comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0187] The above are only exemplary embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

Claims

1. A virtual resource sending method, characterized in that, The method includes: Determining a first prior probability corresponding to a first virtual resource with a first resource quantity, where the first prior probability indicates the probability of the first virtual resource being selected; Obtaining first feature data of an object set, where the first feature data includes basic feature data and virtual resource selection data corresponding to each object in the object set, and the virtual resource selection data indicates whether the corresponding object uses the first virtual resource; Obtaining target basic feature data corresponding to a target object; Determining a first conditional probability according to the first feature data and the target basic feature, where the first conditional probability is a conditional probability corresponding to the target basic feature obtained with using the first virtual resource as a prior condition; Based on Bayes' theorem, determining a first preference parameter corresponding to the target object according to the first prior probability and the first conditional probability, where the first preference parameter indicates the preference degree of the target object for the first virtual resource; Sending a virtual resource to the target object according to the first preference parameter corresponding to the target object.

2. The method according to claim 1, wherein The target basic feature data includes target values in at least one dimension. The determining of the first conditional probability according to the first feature data and the target basic feature includes: For each target value in each dimension of the target basic feature data, determining an associated object according to the first feature data, where the basic feature data corresponding to the associated object includes the target value; according to the virtual resource selection data of the associated object and the virtual resource selection data of the object set, determining a target conditional probability corresponding to the target value, where the target conditional probability is a conditional probability of the occurrence of the target value obtained with using the first virtual resource as a prior condition; Based on the product of the target conditional probabilities corresponding to the respective target values, obtaining the first conditional probability.

3. The method according to claim 1 or 2, characterized in that, The determining of the first preference parameter corresponding to the target object based on Bayes' theorem according to the first prior probability and the first conditional probability includes: Determining the first preference parameter based on the product of the first conditional probability and the first prior probability.

4. The method according to claim 1, characterized in that, The method further includes: Determining a second prior probability corresponding to a second virtual resource with a second resource quantity, where the second prior probability indicates the probability of the second virtual resource being selected, the first resource quantity is different from the second resource quantity, and the second virtual resource is different from the first virtual resource; Determining a second conditional probability according to the first feature data and the target basic feature, where the second conditional probability is a conditional probability corresponding to the target basic feature obtained with using the second virtual resource as a prior condition; Based on Bayes' theorem, determining a second preference parameter corresponding to the target object according to the second prior probability and the second conditional probability, where the second preference parameter indicates the preference degree of the target object for the first virtual resource; The sending of the virtual resource to the target object according to the first preference parameter corresponding to the target object includes: Send virtual resources to the target object according to the first preference parameter corresponding to the target object and the second preference parameter corresponding to the target object.

5. The method according to claim 4, characterized in that The step of sending virtual resources to the target object according to the first preference parameter corresponding to the target object and the second preference parameter corresponding to the target object further includes: Obtain a target object cluster, where the target object cluster includes the target object; According to the first preference parameter corresponding to each object in the target object cluster, determine the first sending parameter corresponding to the target object cluster, where the first sending parameter represents the tendency degree of sending the first virtual resource to the target object cluster; According to the second preference parameter corresponding to each object in the target object cluster, determine the second sending parameter corresponding to the target object cluster, where the second sending parameter represents the tendency degree of sending the second virtual resource to the target object cluster; Determine the target virtual resource according to the first sending parameter and the second sending parameter, where the target virtual resource is the first virtual resource or the second virtual resource; Send the target virtual resource to each account in the target object cluster.

6. The method according to claim 5, wherein The step of determining the first sending parameter corresponding to the target object cluster according to the first preference parameter corresponding to each object in the target object cluster includes: According to the first preference parameter corresponding to each object in the target object cluster, calculate the first tendency contribution parameter corresponding to the object, where the first tendency contribution parameter represents the tendency degree of sending the first virtual resource to the corresponding object; Based on the cumulative statistical result of the first tendency contribution parameters respectively corresponding to each object, determine the first sending parameter corresponding to the target object cluster.

7. The method according to claim 6, characterized in that, The step of calculating the first tendency contribution parameter corresponding to the object according to the first preference parameter corresponding to each object in the target object cluster includes: calculating the first tendency contribution parameter corresponding to the target object according to the first preference parameter corresponding to the target object; The step of calculating the first tendency contribution parameter corresponding to the target object according to the first preference parameter corresponding to the target object includes: Determine the target feature according to the target basic feature data, where the target feature indicates at least one of the following types of information: the object activity of the target object, the object resource status of the target object; Determine the first tendency contribution parameter corresponding to the target object according to the first preference parameter and the target feature.

8. A virtual resource sending device, characterized in that, The device includes: A basic data acquisition module, configured to determine the first prior probability corresponding to the first virtual resource with the first resource quantity, where the first prior probability indicates the probability that the first virtual resource is selected; acquire the first feature data of the object set, where the first feature data includes the basic feature data and virtual resource selection data corresponding to each object in the object set, and the virtual resource selection data indicates whether the corresponding object uses the first virtual resource; and acquire the target basic feature data corresponding to the target object; A virtual resource sending module, configured to determine a first conditional probability according to the first feature data and the target basic feature, where the first conditional probability is a conditional probability corresponding to the target basic feature obtained with the use of the first virtual resource as a prior condition; based on the Bayesian principle, determine a first preference parameter corresponding to the target object according to the first prior probability and the first conditional probability, where the first preference parameter indicates the preference degree of the target object for the first virtual resource; and send a virtual resource to the target object according to the first preference parameter corresponding to the target object.

9. A computer device, characterized in that, The computer device includes a processor and a memory, where at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the virtual resource sending method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, At least one instruction, at least one program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the virtual resource sending method according to any one of claims 1 to 7.

Images