Target virtual object determination method and device, storage medium and electronic equipment

Abstract

The invention discloses a target virtual object determination method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring an interactive information set among virtual objects in a virtual object set; a target object relation network associated with the virtual object set is determined according to the interaction information set, the target object relation network comprises object nodes and a target node connection relation, the object nodes are used for indicating the virtual objects, and the target node connection relation is used for indicating that at least one virtual relation exists between the two virtual objects; determining a virtual interaction value corresponding to each virtual object in the virtual object set according to the target object relation network; and determining a target virtual object from the virtual object set according to the virtual interaction value. The technical problem that an existing activity mode is poor in effect of improving the activity degree of the virtual object set is solved.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to a method and device for determining a target virtual object, a storage medium and an electronic device. Background Art

[0002] In the process of maintaining their user groups, various Internet products can adopt a variety of maintenance methods, including but not limited to improving community activity through community activities, reminding each user to participate in community activities through regular message push, etc.

[0003] It can be seen that the way Internet products maintain users to improve platform activity is usually to organize platform activities for user groups, such as sending virtual rewards to all users, or organizing virtual lottery activities for all users. This user maintenance method for all users not only requires more computing resources, but also due to limited maintenance costs, it is difficult to guarantee the maintenance effect for a single user.

[0004] That is to say, the existing method of improving the activity of a set of virtual objects has a technical problem of poor effect.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present invention provide a method and device for determining a target virtual object, a storage medium, and an electronic device, so as to at least solve the technical problem that the existing activity mode has a poor effect on improving the activity of a set of virtual objects.

[0007] According to one aspect of an embodiment of the present invention, a method for determining a target virtual object is provided, comprising: obtaining an interaction information set between each virtual object in a virtual object set, wherein the virtual object set includes a plurality of the virtual objects, and the interaction information set includes interaction information of virtual interactions between the virtual objects; determining a target object relationship network associated with the virtual object set according to the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate the virtual objects, the target node connection relationships are used to indicate the existence of at least one virtual relationship between the two virtual objects, and the target connection weight configured for the target node connection relationships is used to indicate a target intimacy between the two virtual objects, the target intimacy is determined according to at least one virtual relationship; determining the virtual interaction value corresponding to each virtual object in the virtual object set according to the target object relationship network; determining the target virtual object from the virtual object set according to the virtual interaction value, wherein the virtual interaction value of the target virtual object meets the target condition.

[0008] According to another aspect of an embodiment of the present invention, a device for determining a target virtual object is also provided, comprising: an acquisition unit, configured to acquire an interaction information set between each virtual object in a virtual object set, wherein the virtual object set includes a plurality of the virtual objects, and the interaction information set includes interaction information of virtual interactions between the virtual objects; a first determination unit, configured to determine a target object relationship network associated with the virtual object set based on the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, wherein the object nodes are used to indicate the virtual objects, and the target node connection relationships are used to indicate the existence of at least one virtual relationship between the two virtual objects, and the target connection weight configured for the target node connection relationships is used to indicate a target intimacy between the two virtual objects, and the target intimacy is determined based on at least one virtual relationship; a second determination unit, configured to determine, based on the target object relationship network, the virtual interaction values ​​corresponding to each of the virtual objects in the virtual object set; and a third determination unit, configured to determine a target virtual object from the virtual object set based on the virtual interaction values, wherein the virtual interaction values ​​of the target virtual objects meet the target conditions.

[0009] Optionally, the first determination unit comprises: a determination module, used to determine multiple object relationship networks associated with the virtual object set based on the interaction information set, wherein each of the object relationship networks corresponds to one of the virtual relationships, and the object relationship networks include object nodes and node connection relationships, the node connection relationships are used to indicate the existence of one of the virtual relationships between the two virtual objects, and the connection weights configured for the node connection relationships are used to indicate the degree of intimacy of the virtual relationship between the two virtual objects; an aggregation module, used to aggregate the multiple object relationship networks based on the object nodes in the multiple object relationship networks that indicate the same virtual objects, to obtain the target object relationship network.

[0010] Optionally, the above-mentioned determination module is used to: obtain a reference interaction information subset corresponding to the reference relationship from the above-mentioned interaction information set, wherein the above-mentioned reference interaction information subset includes the above-mentioned interaction information of the above-mentioned virtual interaction performed between the above-mentioned virtual objects based on the above-mentioned reference relationship; map each of the above-mentioned virtual objects in the above-mentioned virtual object set to one of the above-mentioned object nodes, and determine the reference connection relationship between the above-mentioned object nodes based on the above-mentioned interaction information subset, wherein the above-mentioned reference relationship exists between the above-mentioned virtual objects respectively indicated by two of the above-mentioned object nodes having the above-mentioned reference connection relationship; and configure reference connection weights for each of the above-mentioned reference connection relationships based on the above-mentioned interaction information included in the above-mentioned reference interaction information subset.

[0011] Optionally, the above-mentioned aggregation module is used to: repeat the following operations until the above-mentioned virtual objects in the above-mentioned virtual object set are traversed: obtain one of the above-mentioned virtual objects as the current virtual object; obtain the current object node used to indicate the above-mentioned current virtual object; from the multiple object relationship networks, successively obtain multiple relationship object nodes that have the above-mentioned node connection relationship with the above-mentioned current object node, and establish the above-mentioned target node connection relationship between the current object node and the above-mentioned relationship object node; in the case that there are multiple above-mentioned node connection relationships between the above-mentioned current object node and the above-mentioned relationship object node, configure the above-mentioned target node connection relationship according to the above-mentioned connection weights respectively configured for the multiple above-mentioned node connection relationships.

[0012] Optionally, the above-mentioned aggregation module is used to: obtain the network weights configured respectively for the above-mentioned multiple object relationship networks; determine the above-mentioned target connection weight configured for the above-mentioned target node connection relationship based on the above-mentioned connection weights configured respectively for the above-mentioned multiple node connection relationships, and the weighted sum of the above-mentioned network weights corresponding to each of the above-mentioned connection weights.

[0013] Optionally, the second determination unit comprises: an acquisition module for acquiring a transition probability matrix corresponding to the target object relationship network, wherein a row of matrix elements in the transition probability matrix is ​​used to indicate a correlation coefficient between one of the object nodes and other of the object nodes, and the sum of the elements of a row of the matrix elements is 1; and a reference determination module for determining the virtual interaction value corresponding to each of the virtual objects according to the transition probability matrix.

[0014] Optionally, the reference determination module is used for one of the following: determining the virtual interaction value corresponding to each of the virtual objects according to the maximum eigenvector of the transfer probability matrix, wherein each vector element in the maximum eigenvector corresponds to the virtual interaction value of one of the virtual objects; obtaining a reference vector and a target iteration parameter; determining the dot product result of the target iteration parameter power of the transfer probability matrix and the reference vector as a target vector; determining the virtual interaction value corresponding to each of the virtual objects according to the target vector, wherein each vector element in the target vector corresponds to the virtual interaction value of one of the virtual objects.

[0015] Optionally, the reference determination module is used to: obtain a first reference vector, wherein the vector dimension of the first reference vector is the same as the number of rows of the transfer probability matrix; repeat the following steps to indicate that a convergence condition has been reached: determine the dot product result of the transfer probability matrix and the first reference vector as a second reference vector; when the second reference vector is the same as the first reference vector, determine that the convergence condition has been reached, and determine the second reference vector as the maximum eigenvector; when the second reference vector is different from the first reference vector, use the second reference vector as the first reference vector and repeat the above steps.

[0016] Optionally, the reference determination module is further used to: obtain a first correction coefficient and a second correction coefficient, wherein the first correction coefficient and the second correction coefficient are both greater than 0, and the sum of the first correction coefficient and the second correction coefficient is 1; repeat the following steps until each of the matrix elements in the transfer probability matrix is ​​traversed: obtain one of the matrix elements as the current element; determine the product of the current element and the first correction coefficient as a first correction parameter; determine the ratio of the second correction coefficient to the matrix dimension of the transfer probability matrix as a second correction parameter; and update the current element using the sum of the first correction parameter and the second correction parameter.

[0017] Optionally, the device for determining the target virtual object further includes at least one of the following: a setting unit, used to set the target virtual object as a target virtual character, wherein the target virtual character is used to organize multiple virtual objects in the virtual object set to participate in the target virtual interaction; a sending unit, used to send recruitment information to the key object account corresponding to the target virtual object, wherein the recruitment information is used to set the target virtual object as the target virtual character.

[0018] Optionally, the device for determining the target virtual object is further used to: obtain the activity index corresponding to the target virtual character and the multiple virtual objects organized by the target virtual character; obtain the virtual influence evaluation coefficient of the virtual character according to the activity index; and adjust the virtual interaction value corresponding to the target virtual object when the virtual influence evaluation coefficient does not meet the evaluation conditions.

[0019] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for determining a target virtual object when running.

[0020] According to another aspect of the embodiment of the present application, a computer program product is provided, the computer program product including a computer program / instruction, the computer instruction being stored in a computer-readable storage medium. A processor of a computer device reads the computer program / instruction from the computer-readable storage medium, and the processor executes the computer program / instruction, so that the computer device executes the above method for determining a target virtual object.

[0021] According to another aspect of an embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the method for determining a target virtual object through the computer program.

[0022] In an embodiment of the present invention, an interaction information set between each virtual object in a virtual object set is obtained, wherein the virtual object set includes multiple virtual objects, and the interaction information set includes interaction information of virtual interactions between virtual objects; a target object relationship network associated with the virtual object set is determined according to the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate virtual objects, the target node connection relationships are used to indicate the existence of at least one virtual relationship between two virtual objects, and the target connection weight configured for the target node connection relationship is used to indicate a target intimacy between the two virtual objects, and the target intimacy is determined according to at least one virtual relationship; virtual interaction values ​​corresponding to each virtual object in the virtual object set are determined according to the target object relationship network; a target virtual object is determined from the virtual object set according to the virtual interaction value, wherein the virtual interaction value of the target virtual object satisfies a target condition, thereby determining a potential target virtual object from the virtual object set.

[0023] Through the above implementation of the present application, the target object relationship network is first determined through the interactive information set between each virtual object in the virtual object set, so that the virtual relationship between each virtual object in the virtual object set is characterized in a quantitative manner through the target object relationship network; then, since the above target object relationship network aggregates and represents the object intimacy between the above virtual objects, the virtual interaction value of each virtual object is determined through the above target object relationship network. Since there are often multiple virtual relationships in the above virtual object set, and the above target object relationship network can characterize the target intimacy determined based on the above multiple virtual relationships, the relationship between each virtual object can be characterized by the quantified virtual interaction value, and then, when the target virtual object is accurately identified based on the virtual interaction value, a platform activity of targeted maintenance is carried out for the target virtual object, and then the virtual object associated with it is indirectly maintained through the target virtual object, thereby solving the technical problem that the existing activity mode has poor effect on improving the activity of the virtual object set. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0025] Figure 1 is a schematic diagram of a hardware environment of an optional method for determining a target virtual object according to an embodiment of the present invention;

[0026] Figure 2 is a flow chart of an optional method for determining a target virtual object according to an embodiment of the present invention;

[0027] Figure 3 is a schematic diagram of an optional object relationship network according to an embodiment of the present invention;

[0028] Figure 4 is a schematic diagram of another optional object relationship network according to an embodiment of the present invention;

[0029] Figure 5 is a schematic diagram of another optional object relationship network according to an embodiment of the present invention;

[0030] Figure 6 is a schematic diagram of an optional target virtual object evaluation method according to an embodiment of the present invention;

[0031] Figure 7 is a flow chart of an optional method for determining a target virtual object according to an embodiment of the present invention;

[0032] Figure 8is a schematic structural diagram of an optional device for determining a target virtual object according to an embodiment of the present invention;

[0033] Fig. 9 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] It should be noted that in various embodiments of the present application, the methods for obtaining various operation information or interactive information comply with the provisions of normative documents, and before obtaining operation information or interactive information, it is necessary to obtain authorization permission from the relevant object account.

[0037] According to one aspect of an embodiment of the present invention, a method for determining a target virtual object is provided. As an optional implementation, the method for determining a target virtual object can be applied to, but is not limited to, Figure 1The system for determining the target virtual object in the hardware environment shown, wherein the system for determining the target virtual object may include but is not limited to a terminal device 102, a network 104, a server 106 and a database 108. A target client (taking the target client as a game application client as an example) that can realize virtual interaction between virtual objects is running in the terminal device 102. The terminal device 102 includes a human-computer interaction screen, a processor and a memory. The human-computer interaction screen is used to display a virtual game scene, and is also used to provide a human-computer interaction interface to receive human-computer interaction operations for controlling a controlled virtual character in a virtual scene, and the virtual character will complete the game tasks and virtual interactions set in the virtual scene. The processor is used to generate an interaction instruction in response to the above-mentioned human-computer interaction operation, and send the interaction instruction to the server. The memory is used to store relevant attribute data, such as object attribute information of the controlled virtual character, and attribute information of the virtual props held, etc.

[0038] In addition, the server 106 includes a processing engine, which is used to perform storage or reading operations on the database 108. Specifically, the processing engine reads an interaction information set from the database 108, wherein the interaction information set includes the interaction information of the virtual interaction between the virtual objects.

[0039] Assumptions Figure 1 The terminal device 102 in the embodiment logs in an object account for controlling the virtual object. The specific process of this embodiment is as follows: in step S102, the virtual object is controlled by the terminal device 102 to perform a virtual social activity; then step S104 is executed, the terminal device 102 sends interactive information to the server 106 through the network 104; the server 106 executes S106 to S112 to obtain an interactive information set between each virtual object in the virtual object set, wherein the virtual object set includes multiple virtual objects, and the interactive information set includes interactive information of virtual interactions between virtual objects; according to the interactive information set, a target associated with the virtual object set is determined An object relationship network, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate virtual objects, the target node connection relationships are used to indicate that at least one virtual relationship exists between two virtual objects, and the target connection weight configured for the target node connection relationship is used to indicate a target intimacy between the two virtual objects, and the target intimacy is determined according to at least one virtual relationship; the virtual interaction values ​​corresponding to each virtual object in the virtual object set are determined according to the target object relationship network; the target virtual object is determined from the virtual object set according to the virtual interaction value, wherein the virtual interaction value of the target virtual object satisfies the target condition;

[0040] Then the server 106 executes S114 to send the confirmation information of the target virtual object to the terminal device 102 via the network 104;

[0041] Finally, the terminal device 102 executes step S116 to control the target virtual object to perform a virtual social activity.

[0042] Optionally, in this embodiment, the terminal device may be a terminal device configured with a target client, which may include but is not limited to at least one of the following: a mobile phone (such as an Android phone, an iOS phone, etc.), a laptop, a tablet computer, a PDA, a MID (Mobile Internet Devices), a PAD, a desktop computer, a smart TV, etc. The target client may be a client that supports providing shooting game tasks, such as a video client, an instant messaging client, a browser client, an educational client, etc. The network may include but is not limited to: a wired network, a wireless network, wherein the wired network includes: a local area network, a metropolitan area network, and a wide area network, and the wireless network includes: Bluetooth, WIFI, and other networks that implement wireless communication. The server may be a single server, or a server cluster consisting of multiple servers, or a cloud server. The above is only an example, and no limitation is made to this in this embodiment.

[0043] Optionally, in this embodiment, the above-mentioned method for determining the target virtual object can be applied to, but not limited to, a game terminal application (Application, referred to as APP) that completes a predetermined social game task in a virtual scene, such as a virtual confrontation game application in a multiplayer online tactical competitive game (Multiplayer Online Battle Arena, referred to as MOBA) application; the above-mentioned social game task can be, but not limited to, a game task completed by the current player through virtual social interaction with virtual characters controlled by other players by determining a virtual character in a virtual scene through a human-computer interaction target virtual object; the above-mentioned method for determining the target virtual object can also be applied to a terminal application of a massively multiplayer online role-playing game (Multiplayer Online Role-Playing Game, referred to as MMORPG), in which the current player can complete the social game task in the game from the first perspective of the virtual character through role-playing, for example, completing the game task together with other virtual characters, etc. The social game task here can be, but not limited to, running in an application (such as a non-independent game APP) in the form of a plug-in or applet, or running in an application (such as an independent game APP) in a game engine. The types of the above-mentioned game applications may include, but are not limited to, at least one of the following: two-dimensional (2D) game applications, three-dimensional (3D) game applications, virtual reality (VR) game applications, augmented reality (AR) game applications, and mixed reality (MR) game applications. The above is only an example, and this embodiment does not impose any limitation on this.

[0044] In an embodiment of the present invention, an interaction information set between each virtual object in a virtual object set is obtained, wherein the virtual object set includes multiple virtual objects, the virtual object set includes but is not limited to a virtual community, and the interaction information set includes interaction information of virtual interactions between virtual objects; a target object relationship network associated with the virtual object set is determined according to the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate virtual objects, the target node connection relationships are used to indicate that there is at least one virtual relationship between two virtual objects, the virtual relationship includes but is not limited to a virtual social relationship, the target connection weight configured for the target node connection relationship is used to indicate the target intimacy between the two virtual objects, and the target intimacy is determined according to at least one virtual relationship; the virtual interaction value corresponding to each virtual object in the virtual object set is determined according to the target object relationship network; the target virtual object is determined from the virtual object set according to the virtual interaction value, wherein the virtual interaction value of the target virtual object meets the target condition, thereby determining potential target virtual objects from the virtual object set and improving the activity of the virtual object set.

[0045] Through the above implementation of the present application, the target object relationship network is first determined through the interactive information set between each virtual object in the virtual object set, so that the virtual relationship between each virtual object in the virtual object set is characterized in a quantitative manner through the target object relationship network; then, since the above target object relationship network aggregates and represents the object intimacy between the above virtual objects, the virtual interaction value of each virtual object is determined through the above target object relationship network. Since there are often multiple virtual relationships in the above virtual object set, and the above target object relationship network can characterize the target intimacy determined based on the above multiple virtual relationships, the relationship between each virtual object can be characterized by a quantified virtual interaction value, and then, when the target virtual object is accurately identified based on the virtual interaction value, a platform activity of targeted maintenance is carried out for the target virtual object, and then the virtual object associated with it is indirectly maintained through the target virtual object, thereby solving the technical problem that the current activity method has poor effect on improving the activity of the virtual object set.

[0046] As an optional implementation, Figure 2 As shown, the above method for determining the target virtual object includes the following steps:

[0047] S202, obtaining an interaction information set between each virtual object in the virtual object set, wherein the virtual object set includes a plurality of virtual objects, and the interaction information set includes interaction information of virtual interactions between the virtual objects;

[0048] S204, determining a target object relationship network associated with the virtual object set according to the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate virtual objects, the target node connection relationships are used to indicate that at least one virtual relationship exists between two virtual objects, and the target connection weight configured for the target node connection relationship is used to indicate a target intimacy between the two virtual objects, and the target intimacy is determined according to the at least one virtual relationship;

[0049] S206, determining the virtual interaction value corresponding to each virtual object in the virtual object set according to the target object relationship network;

[0050] S208, determining a target virtual object from the virtual object set according to the virtual interaction value, wherein the virtual interaction value of the target virtual object satisfies a target condition.

[0051] It should be noted that the above implementation can be applied to applications including but not limited to game applications, streaming media applications, news and information applications, instant messaging applications, etc. that can provide virtual objects for virtual interaction. In the case where the above application scenario is a game application, the above virtual object can be a virtual game object in the virtual world of the above game application. In the above virtual world, each virtual game object can interact virtually with other virtual game objects, which may include but is not limited to virtual friendship interaction, virtual attack interaction, virtual sworn brotherhood interaction, virtual transaction interaction, etc.; in the case where the above application scenario is a news and information application, the above virtual object can be an object account included in the above news and information application, and the virtual interaction between each object account can include but is not limited to comment interaction, add attention interaction, favorite interaction, send barrage interaction, send gift interaction, etc. This implementation does not limit the object type of the above virtual object and the interaction type of the above virtual interaction.

[0052] Further, the target object relationship network in the above step S204 can be used to characterize at least one virtual relationship between each virtual object in the above virtual object set. It can be understood that each object node in the above target object relationship network is used to indicate each virtual object, and the target node connection relationship between each object node is used to indicate at least one virtual relationship between each virtual object, and the above target node connection relationship can be used to indicate the target intimacy between two virtual objects determined based on at least one social relationship. Optionally, the above target intimacy can be used to indicate the closeness of multiple virtual interactions between two virtual objects in the above virtual object set.

[0053] In the above step S206, after determining the above target object relationship network, the virtual interaction value of each virtual object can be determined through the above target object relationship network. The above virtual interaction value can be understood as the number of virtual objects that the above virtual object can affect in the above virtual object set, the object range, and the degree of influence. The above object number can be understood as the influence of the above virtual object on a certain number of virtual objects through object operation; the above object range can be understood as the influence that the above virtual object can have on virtual objects included in multiple coverage areas such as the virtual community or adjacent virtual communities where it is located; the above degree of influence can be understood as the behavioral nature of the influence behavior caused by the above virtual object on other virtual objects. For example, it can be considered that the virtual object drives other virtual objects to participate in the target activity as the first degree, and the virtual object drives other virtual objects to participate in the target activity that requires part of the virtual resources as the second degree. Obviously, the second degree is higher than the above first degree.

[0054] Finally, in step S208, the target virtual object can be determined from the virtual object set according to the virtual interaction value corresponding to each virtual object. For example, the N virtual objects with the highest virtual interaction values ​​can be determined as the target virtual objects; the virtual objects with the top 1% virtual interaction values ​​can also be determined as the target virtual objects. In this embodiment, the specific content of the above target conditions is not limited.

[0055] Through the above implementation of the present application, the target object relationship network is first determined through the interactive information set between each virtual object in the virtual object set, so that the virtual relationship between each virtual object in the virtual object set is characterized in a quantitative manner through the target object relationship network; then, since the above target object relationship network aggregates and represents the object intimacy between the above virtual objects, the virtual interaction value of each virtual object is determined through the above target object relationship network. Since there are often multiple virtual relationships in the above virtual object set, and the above target object relationship network can characterize the target intimacy determined based on the above multiple virtual relationships, the relationship between each virtual object can be characterized by a quantified virtual interaction value, and then, when the target virtual object is accurately identified based on the virtual interaction value, a platform activity of targeted maintenance is carried out for the target virtual object, and then the virtual object associated with it is indirectly maintained through the target virtual object, thereby solving the technical problem that the current activity method has poor effect on improving the activity of the virtual object set.

[0056] In an optional implementation, the above-mentioned determining the target object relationship network associated with the virtual object set according to the interactive information set includes:

[0057] S1, determining a plurality of object relationship networks associated with a set of virtual objects according to a set of interaction information, wherein each object relationship network corresponds to a virtual relationship, and the object relationship network includes object nodes and node connection relationships, the node connection relationship is used to indicate that a virtual relationship exists between two virtual objects, and the connection weight configured for the node connection relationship is used to indicate the intimacy of the virtual relationship between the two virtual objects;

[0058] S2, based on the object nodes in the multiple object relationship networks indicating the same virtual object, aggregating the multiple object relationship networks to obtain a target object relationship network.

[0059] In this embodiment, a plurality of object relationship networks may be determined according to the virtual relationships included in the virtual object set, and then the target object relationship network may be determined according to an aggregation operation of the plurality of object relationship networks.

[0060] For example, in a virtual game community, virtual objects can interact with each other by chatting, teaming up, giving virtual resources, etc. In this embodiment, each interactive behavior can be determined as a virtual relationship, and then a corresponding object relationship network is established based on the interactive information corresponding to each virtual relationship.

[0061] In an optional implementation, the above-mentioned determining a plurality of object relationship networks associated with the virtual object set according to the interaction information set includes:

[0062] S1, acquiring a reference interaction information subset corresponding to the reference relationship from the interaction information set, wherein the reference interaction information subset includes interaction information of virtual interactions performed between virtual objects based on the reference relationship;

[0063] S2, mapping each virtual object in the virtual object set to an object node, and determining a reference connection relationship between the object nodes based on the interaction information subset, wherein a reference relationship exists between the virtual objects respectively indicated by two object nodes having a reference connection relationship;

[0064] S3, configuring reference connection weights for respective reference connection relationships based on the interaction information included in the reference interaction information subset.

[0065] Specifically, this embodiment can form an object relationship network for each social behavior between users. The object relationship network consists of object nodes, edges (connection relationships), and weights on the edges (connection weights). Nodes represent game character IDs (identifiers) in game scenes, edges represent social relationships between characters, and edge weights represent quantitative indicators of the social behavior (e.g., in a chat network, edge weights can be determined based on the number of chats). For example Figure 3As shown in the figure, for the game friend relationship network, each game character is a node. i ,u j It's a game friend relationship, u j ,u k Is a game friend relationship, then in Figure 3 In the i ,u j The nodes corresponding to the two people are connected by edges (denoted as (u i ,u j )), and will u j ,u k The nodes corresponding to the two people are connected by edges (denoted as (u j ,u k )), edge (u i ,u j ) represents the weight a of u i ,u j The degree of intimacy between j ,u k ) represents the weight b of u i ,u j The degree of intimacy between them.

[0066] Through the above-mentioned implementation mode of the present application, a reference interaction information subset corresponding to the reference relationship is obtained from the interaction information set, wherein the reference interaction information subset includes interaction information of virtual interactions performed between virtual objects based on the reference relationship; each virtual object in the virtual object set is respectively mapped to an object node, and a reference connection relationship between the object nodes is determined based on the interaction information subset, wherein there is a reference relationship between virtual objects respectively indicated by two object nodes having a reference connection relationship; based on the interaction information included in the reference interaction information subset, a reference connection weight is respectively configured for each reference connection relationship, thereby quantitatively determining the object relationship network corresponding to the reference relationship based on the reference and interaction information subsets of the virtual objects, thereby improving the accuracy of determining the virtual social intimacy between virtual objects.

[0067] In an optional implementation, the aggregating of multiple object relationship networks based on object nodes indicating the same virtual object in the multiple object relationship networks to obtain the target object relationship network includes: repeating the following operations until the virtual objects in the virtual object set are traversed:

[0068] S1, obtain a virtual object as the current virtual object;

[0069] S2, obtaining a current object node indicating a current virtual object;

[0070] S3, sequentially acquiring multiple relationship object nodes having a node connection relationship with the current object node from multiple object relationship networks, and establishing a target node connection relationship between the current object node and the relationship object node;

[0071] S4, when there are multiple node connection relationships between the current object node and the relationship object node, configure a target connection weight for the target node connection relationship according to the connection weights respectively configured for the multiple node connection relationships.

[0072] It can be understood that, in this embodiment, object nodes in different object relationship networks can be identified, and then the object relationship networks can be aggregated based on the same object nodes.

[0073] like Figure 4 As shown, assuming that for the game team relationship network, if two people u i ,u j It's a game team relationship, u j ,u l Is the game team relationship, then in Figure 4 In the i ,u j The nodes corresponding to the two people are connected by edges (denoted as (u i ,u j )), and will u j ,u l The nodes corresponding to the two people are connected by edges (denoted as (u j ,u l )), edge (u i ,u j ))'s weight c represents u j ,u l The degree of intimacy between team members, edge (u j ,u l ) represents the weight d of u j ,u l The degree of teaming between them.

[0074] Further, in an optional manner, due to Figure 3 u in the friendship network shown i ,u j and u in the team relationship network i ,u j are the same two nodes, and can be Figure 5 The two object relationship networks are aggregated in the manner shown.

[0075] In an optional implementation, configuring a target connection weight for a target node connection relationship according to the connection weights respectively configured for a plurality of node connection relationships includes:

[0076] S1, obtaining network weights configured for multiple object relationship networks respectively;

[0077] S2, determining a target connection weight configured for a target node connection relationship according to connection weights respectively configured for a plurality of node connection relationships and a weighted summation result between network weights corresponding to each connection weight.

[0078] It is understandable that in this embodiment, different network weights can be configured for different object relationship networks, and then in the process of aggregating the object relationship networks, the target connection weight corresponding to the aggregated connection relationship is determined according to the network weights of each relationship network.

[0079] Alternatively, if Figure 5 The side shown (u i ,u j ) represents the weight a of u i ,u j The degree of intimacy between j ,u k ) represents the weight b of u i ,u j The degree of intimacy between i ,u j ))'s weight c represents u j ,u l The degree of intimacy between team members, edge (u j ,u l ) represents the weight d of u j ,u l The degree of teaming between them, assuming that the weight of the friend relationship network is 0.3 and the weight of the team relationship network is 0.7, then in the aggregated target object network, the corresponding edge (u i ,u j ) can be weighted as 0.3*a+0.7*c.

[0080] In a preferred embodiment, the edge weights can be standardized in each object relationship network. The above standardization can be understood as that, for each object node, the sum of the edge weights between multiple object nodes connected to it is 1. For example, if node a is connected to node b and node c respectively, the edge weight between node a and node b after standardization can be 0.3, and the edge weight between node a and node c after standardization can be 0.7.

[0081] Specifically, the data structure of each object relationship network can be standardized into the form of (node ​​1, node 2, edge weight) according to each edge, such as (u i ,u j ,eij ) form, where e ij is the normalized edge (u i ,u j ) on the weight;

[0082] Then, the same nodes are identified for each object relationship network; that is, the same virtual objects in different object relationship networks are identified as the same nodes (which can be based on the role ID in the game). For example, there are two object relationship networks: the friend relationship network and the team relationship network in the game, then the nodes corresponding to the same role in the two networks need to be identified as the same nodes.

[0083] Next, concatenate each object-relational network and standardize the data structure. Merge the object nodes and edges of each object-relational network, where the nodes corresponding to the same entity in each object-relational network are merged into one node. Standardize the data structure into the form of "edge, weight of the edge in each sub-network", for example Where N is the number of subnetworks, u i ,u j are the starting and target nodes of an edge, is the weight of the edge in the first sub-network, and so on;

[0084] Finally, determine the expression of the edge weight of the target object relationship network. In the target object relationship network, the weight of each edge is the weighted sum of the weights of the edge in each sub-network, that is, the node u i With node u j The weight of the edge between is:

[0085]

[0086] Among them, w1,w2,…,w N is a hyperparameter.

[0087] In the above implementation of the present application, the above-mentioned determining the virtual interaction value corresponding to each virtual object in the virtual object set according to the target object relationship network includes:

[0088] S1, obtaining a transition probability matrix corresponding to the target object relationship network, wherein a row of matrix elements in the transition probability matrix is ​​used to indicate the correlation coefficient between an object node and other object nodes, and the sum of the elements of a row of matrix elements is 1;

[0089] S2, determining the virtual interaction value corresponding to each virtual object according to the transition probability matrix.

[0090] Specifically, the method of obtaining the transition probability matrix corresponding to the target object relationship network is as follows: Let the transfer matrix be M, then the matrix element of the matrix M at (i, j) is:

[0091]

[0092] Where m is the number of nodes in the target object relationship network.

[0093] In an optional implementation, the above-mentioned determining the virtual interaction value corresponding to each virtual object according to the transition probability matrix includes one of the following:

[0094] Method 1: determining the virtual interaction value corresponding to each virtual object according to the maximum eigenvector of the transition probability matrix, wherein each vector element in the maximum eigenvector corresponds to the virtual interaction value of a virtual object;

[0095] Method 2: Obtain a reference vector and a target iteration parameter; determine the dot product result of the target iteration parameter power of the transfer probability matrix and the reference vector as the target vector; determine the virtual interaction value corresponding to each virtual object according to the target vector, wherein each vector element in the target vector corresponds to a virtual interaction value of a virtual object.

[0096] It can be understood that in this embodiment, two optional methods are provided to determine the virtual interaction value corresponding to each virtual object. In the first method, the virtual interaction value corresponding to each virtual object can be determined by obtaining the maximum eigenvector of the transition probability matrix; in the second method, the virtual interaction value corresponding to each virtual object can be determined by the target vector determined by the iterative operation of the reference vector and the target number of times.

[0097] In an optional implementation, before determining the virtual interaction value corresponding to each virtual object according to the maximum eigenvector of the transition probability matrix, the method further includes: obtaining a first reference vector, wherein the vector dimension of the first reference vector is the same as the number of rows of the transition probability matrix;

[0098] Repeat the following steps to indicate that convergence conditions have been reached:

[0099] S1, determining the dot product result of the transfer probability matrix and the first reference vector as the second reference vector;

[0100] S2, when the second reference vector is the same as the first reference vector, determining that a convergence condition is reached, and determining the second reference vector as a maximum eigenvector;

[0101] S3: When the second reference vector is different from the first reference vector, use the second reference vector as the first reference vector and repeat the above steps.

[0102] It can be understood that in this embodiment, the dot product result of the transition probability matrix and the initial vector can be obtained by iteration, and by comparing with the previous dot product result, when the dot product result converges, the corresponding maximum eigenvector is determined.

[0103] In an optional implementation, after obtaining the transition probability matrix corresponding to the target object relationship network, the method further includes:

[0104] S1, obtaining a first correction coefficient and a second correction coefficient, wherein the first correction coefficient and the second correction coefficient are both greater than 0, and the sum of the first correction coefficient and the second correction coefficient is 1;

[0105] S2, repeat the following steps until every matrix element in the transition probability matrix is ​​traversed:

[0106] S2-1, obtain a matrix element as the current element;

[0107] S2-2, determining the product of the current element and the first correction coefficient as a first correction parameter;

[0108] S2-3, determining a ratio between the second correction coefficient and the matrix dimension of the transfer probability matrix as a second correction parameter;

[0109] S2-4, update the current element using the sum of the first correction parameter and the second correction parameter.

[0110] It can be understood that, in order to ensure the convergence of the iteration result, each matrix element in the above-mentioned transition probability matrix may be corrected by using a correction parameter before performing the above-mentioned iteration operation.

[0111] Specifically, in order to make the results of the above iterative process converge, the transfer probability matrix needs to be corrected. An m*m matrix P can be constructed, and the first correction parameter is determined to be 0.85 and the second correction parameter is 0.15, and then the transfer probability matrix is ​​corrected in the following way:

[0112]

[0113] Finally, the social influence value can be calculated by the above iteration method. Take any m-dimensional vector X0 and set the number of iterations k. Calculate

[0114] X k+1 =P k X0,

[0115] Then X k+1 The value at the i-th dimension of is the social influence value (and the above-mentioned virtual interaction value) of the virtual character corresponding to the i-th node.

[0116] Through the above-mentioned implementation mode of the present application, a transition probability matrix corresponding to the target object relationship network is obtained, wherein a row of matrix elements in the transition probability matrix is ​​used to indicate the correlation coefficient between an object node and other object nodes, and the sum of the elements of a row of matrix elements is 1; the virtual interaction value corresponding to each virtual object is determined according to the transition probability matrix, so as to accurately determine the virtual interaction value of the virtual object indicated by each node in the virtual object set according to the target object relationship network, comprehensively consider various social relationships caused by various social behaviors, and then accurately determine the virtual objects with social influence potential in the virtual object set, and further indirectly maintain the virtual objects associated with it through the target virtual object, thereby improving the activity of the virtual object set.

[0117] In an optional implementation, after determining the target virtual object from the virtual object set according to the virtual interaction value, the method further includes at least one of the following:

[0118] Method 1: setting the target virtual object as a target virtual character, wherein the target virtual character is used to organize multiple virtual objects in a virtual object set to participate in the target virtual interaction;

[0119] Method 2: Sending recruitment information to the key object account corresponding to the target virtual object, wherein the recruitment information is used to set the target virtual object as a target virtual character.

[0120] It is understandable that in this embodiment, the object maintenance of the target virtual object can be achieved through the above two methods. In the first method, the target virtual object can be directly set as the target virtual character, and then the target interaction capability configured for the target virtual character can be used to influence other virtual objects to participate in virtual interaction, thereby improving the activity of the virtual object set.

[0121] For example, in a cooperative confrontation game, a virtual object with a virtual interaction value higher than a target threshold may be determined as a virtual commander object. In this embodiment, the function of organizing a virtual union may be configured for the virtual commander object, that is, multiple ordinary virtual objects may be organized as a virtual organization to collectively participate in the interactive activities in the above game. For example, in the case where the above interactive activities may be virtual confrontation activities, the above virtual commander may organize multiple virtual objects to form a virtual team, and then improve the team level of the virtual team through the confrontation activities of each virtual object in the team or the confrontation activities participated in by the collective.

[0122] In addition, in this embodiment, virtual points can be accumulated for the virtual team through the confrontation activities of the virtual objects in the virtual team, and then virtual rewards can be allocated to the virtual objects in the virtual team when the accumulated virtual points meet certain conditions.

[0123] In the second manner, recruitment information may be sent to the target virtual object, and when the target virtual object accepts the recruitment information, the target virtual object may be determined as the target virtual character.

[0124] In an optional implementation, the above-mentioned target virtual characters can be gathered in a specific platform, and virtual rewards can be sent regularly, so as to centrally maintain the target virtual characters through the above-mentioned specific platform, thereby ensuring the activity of the target virtual characters, influencing the virtual object collection through the target virtual characters, thereby achieving efficient maintenance of the virtual objects in the virtual object collection, and indirectly maintaining the virtual objects associated with them through the target virtual objects, thereby improving the activity of the virtual object collection.

[0125] In an optional implementation manner, after setting the target virtual object as the target virtual character, the method further includes:

[0126] S1, obtaining activity indexes corresponding to a target virtual character and multiple virtual objects organized by the target virtual character;

[0127] S2, obtaining the virtual influence evaluation coefficient of the virtual character according to the activity index;

[0128] S3, when the virtual influence evaluation coefficient does not meet the evaluation conditions, adjust the virtual interaction value corresponding to the target virtual object.

[0129] In an optional embodiment, the Figure 6 The method shown evaluates the community influence of the determined target virtual character in the virtual object set. Specifically, it may include "first-degree friend virtual resource usage information", "first-degree friend active number" and "first-degree friend average active time". It should be noted that the above-mentioned "first-degree friend" is used to indicate the virtual object that has a direct friendship relationship with the above-mentioned target virtual character. The above-mentioned virtual resources can be the points, props and other resources used and consumed by the target virtual character in the activities. The above-mentioned "first-degree friend virtual resource usage information" can be used to indicate the influence degree of the above-mentioned target virtual character on other virtual objects participating in interactive activities that require the consumption of virtual resources; the above-mentioned "first-degree friend active number" can be used to indicate the influence degree of the above-mentioned target virtual character on other virtual objects to log in and participate in virtual interactions in the virtual object set; the above-mentioned "first-degree friend average active time" can be used to indicate the influence degree of the above-mentioned target virtual character on other virtual objects to participate in and maintain online status.

[0130] It is understandable that, in an optional implementation, the target virtual object determined by the above implementation can be verified, and the relevant methods in the above steps can be adjusted according to the verification results. For example, the number of iterations can be adjusted, that is, the initial k can be adjusted, that is, the X in the iterative calculation can be adjusted. k+1 =P k For example, the k value in X0 can be adjusted; for example, the initial vector X0 in the above iterative process can be adjusted. In this embodiment, the specific adjustment method is not limited.

[0131] Through the above-mentioned implementation mode of the present application, the activity index corresponding to the target virtual character and the multiple virtual objects organized by the target virtual character is obtained; the virtual influence evaluation coefficient of the virtual character is obtained according to the activity index; when the virtual influence evaluation coefficient does not meet the evaluation conditions, the virtual interaction value corresponding to the target virtual object is adjusted, and then the determined target virtual object is evaluated. When the evaluation conditions are not met, the method for determining the above-mentioned target virtual object can be further adjusted, and then the accuracy of the determination of the above-mentioned target virtual object is improved through dynamic adjustment, and then the virtual objects associated with it are indirectly maintained through the target virtual object, thereby improving the activity of the virtual object set.

[0132] The following combination Figure 7 A complete implementation process of the present application is described. This implementation method can be used to mine highly influential object accounts in the game community.

[0133] S702, constructing various social sub-networks according to multiple social relationships;

[0134] Specifically, multiple social sub-networks are constructed within the game. There are many social behaviors in the game, such as chatting, teaming, gifting, etc. In this embodiment, each social behavior between virtual objects can be formed into a sub-network. The network consists of nodes, edges, and weights on the edges. Nodes represent game character identifiers, edges represent social relationships between characters, and the weights corresponding to the edges represent quantitative indicators of the social behavior (e.g., in a chat network, the edge weight can be the number of chats). For example, for a game friend relationship network, each character is a node. If two virtual objects u i ,u j is a game friend relationship, then there is an edge (denoted as (u i ,u j )) are directly connected, and the weight of the edge indicates their intimacy.

[0135] S704, sub-network edge weight normalization;

[0136] The data structure of each sub-network is standardized. The data structure of each sub-network can be standardized into the form of (node ​​1, node 2, edge weight) according to each edge, such as (u i ,u j ,e ij ) form, where e ij is the normalized edge (u i ,u j ) on the weight;

[0137] S706, identifying the same nodes in the sub-network;

[0138] In the above steps, the same nodes are identified for each sub-network; that is, the same characters in different sub-networks are identified as the same nodes (for example, they can be identified based on the game character). For example, there are two sub-networks: the in-game friend relationship network and the team network, then the nodes corresponding to the same characters in the two networks need to be identified as the same nodes;

[0139] S708, sub-network splicing;

[0140] In the above steps, each sub-network is spliced ​​and the data structure is standardized. The nodes and edges of each sub-network are merged, and the nodes corresponding to the same entity in each sub-network are merged into one node (the process of identifying the same node (entity) is implemented in the previous step). The data structure is standardized into the form of "edge, the weight of the edge in each sub-network", as shown in Where N is the number of subnetworks, u i ,u j are the starting and target nodes of an edge, is the weight of the edge in the first sub-network, and so on;

[0141] S710, determining the edge weight of the target social network;

[0142] Determine the expression of the edge weight of the target social network. In the target social network, the weight of each edge is the weighted sum of the weights of the edge in each subnetwork, that is, the node u i With node u j The weight of the edge between is:

[0143]

[0144] Among them, w1,w2,…,w N is a hyperparameter.

[0145] S712, calculating a transition probability matrix;

[0146] Let the transfer matrix be M. Then the element of the matrix M at (i, j) is:

[0147]

[0148] Where m is the number of nodes in the target social network.

[0149] S714, iteratively determine the influence value corresponding to each node;

[0150] First, the transition probability matrix is ​​modified. In order to make the iterative results converge, the above transition probability matrix needs to be modified.

[0151] Construct an m*m matrix P, whose elements at position (i,j) are:

[0152]

[0153] Next, calculate the social influence value. Take an m-dimensional vector X0 and a fixed number of iterations k.

[0154] calculate

[0155] X k+1 =P k X0;

[0156] Then X k+1 The value at the i-th dimension of is the social influence value of the i-th node and the social influence value of the virtual character in the game.

[0157] S716, determining a target virtual object in the game;

[0158] The social influence value can be sorted in descending order to filter the top-ranked character identifiers. The higher the social influence value, the greater the social influence value. It can be understood that the virtual interaction value mentioned in the foregoing can be specifically the above-mentioned social influence value in this embodiment. Through the above-mentioned embodiment of the present application, the target object relationship network is first determined by the interactive information set between each virtual object in the virtual object set, so that the virtual relationship between each virtual object in the virtual object set is characterized in a quantitative manner through the target object relationship network; then, since the above-mentioned target object relationship network aggregates and represents the object intimacy between the above-mentioned virtual objects, the virtual interaction value of each virtual object is determined through the above-mentioned target object relationship network. Since there are often multiple virtual relationships in the above-mentioned virtual object set, and the above-mentioned target object relationship network can characterize the target intimacy determined based on the above-mentioned multiple virtual relationships, the relationship between each virtual object can be characterized by the quantified virtual interaction value, and then the target virtual object is accurately identified based on the virtual interaction value. The platform activity of targeted maintenance is carried out for the target virtual object, and then the virtual object associated with it is further indirectly maintained through the target virtual object, thereby solving the technical problem that the existing activity method has poor effect on improving the activity of the virtual object set.

[0159] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0160] According to another aspect of an embodiment of the present invention, a device for determining a target virtual object for implementing the above-mentioned method for determining a target virtual object is also provided. Figure 8 As shown, the device comprises:

[0161] The acquisition unit 802 is used to acquire an interaction information set between each virtual object in the virtual object set, wherein the virtual object set includes a plurality of the virtual objects, and the interaction information set includes interaction information of virtual interactions between the virtual objects;

[0162] A first determining unit 804 is configured to determine a target object relationship network associated with the virtual object set according to the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate the virtual objects, the target node connection relationships are used to indicate that at least one virtual relationship exists between the two virtual objects, and the target connection weight configured for the target node connection relationships is used to indicate a target intimacy between the two virtual objects, and the target intimacy is determined according to at least one virtual relationship;

[0163] A second determining unit 806 is used to determine the virtual interaction value corresponding to each of the virtual objects in the virtual object set according to the target object relationship network;

[0164] The third determining unit 808 is used to determine a target virtual object from the virtual object set according to the virtual interaction value, wherein the virtual interaction value of the target virtual object satisfies a target condition.

[0165] Optionally, the first determination unit 804 includes: a determination module, used to determine multiple object relationship networks associated with the virtual object set based on the interaction information set, wherein each of the object relationship networks corresponds to one of the virtual relationships, and the object relationship network includes object nodes and node connection relationships, the node connection relationship is used to indicate the existence of one of the virtual relationships between the two virtual objects, and the connection weight configured for the node connection relationship is used to indicate the degree of intimacy of the virtual relationship between the two virtual objects; an aggregation module, used to aggregate the multiple object relationship networks based on the object nodes in the multiple object relationship networks that indicate the same virtual objects, to obtain the target object relationship network.

[0166] Optionally, the above-mentioned determination module is used to: obtain a reference interaction information subset corresponding to the reference relationship from the above-mentioned interaction information set, wherein the above-mentioned reference interaction information subset includes the above-mentioned interaction information of the above-mentioned virtual interaction performed between the above-mentioned virtual objects based on the above-mentioned reference relationship; map each of the above-mentioned virtual objects in the above-mentioned virtual object set to one of the above-mentioned object nodes, and determine the reference connection relationship between the above-mentioned object nodes based on the above-mentioned interaction information subset, wherein the above-mentioned reference relationship exists between the above-mentioned virtual objects respectively indicated by two of the above-mentioned object nodes having the above-mentioned reference connection relationship; and configure reference connection weights for each of the above-mentioned reference connection relationships based on the above-mentioned interaction information included in the above-mentioned reference interaction information subset.

[0167] Optionally, the above-mentioned aggregation module is used to: repeat the following operations until the above-mentioned virtual objects in the above-mentioned virtual object set are traversed: obtain one of the above-mentioned virtual objects as the current virtual object; obtain the current object node used to indicate the above-mentioned current virtual object; from the multiple object relationship networks, successively obtain multiple relationship object nodes that have the above-mentioned node connection relationship with the above-mentioned current object node, and establish the above-mentioned target node connection relationship between the current object node and the above-mentioned relationship object node; in the case that there are multiple above-mentioned node connection relationships between the above-mentioned current object node and the above-mentioned relationship object node, configure the above-mentioned target node connection relationship according to the above-mentioned connection weights respectively configured for the multiple above-mentioned node connection relationships.

[0168] Optionally, the above-mentioned aggregation module is used to: obtain the network weights configured respectively for the above-mentioned multiple object relationship networks; determine the above-mentioned target connection weight configured for the above-mentioned target node connection relationship based on the above-mentioned connection weights configured respectively for the above-mentioned multiple node connection relationships, and the weighted sum of the above-mentioned network weights corresponding to each of the above-mentioned connection weights.

[0169] Optionally, the second determination unit 806 includes: an acquisition module, used to obtain a transition probability matrix corresponding to the target object relationship network, wherein a row of matrix elements in the transition probability matrix is ​​used to indicate a correlation coefficient between an object node and other object nodes, and the sum of elements in a row of the matrix elements is 1; a reference determination module, used to determine the virtual interaction value corresponding to each of the virtual objects according to the transition probability matrix.

[0170] Optionally, the reference determination module is used for one of the following: determining the virtual interaction value corresponding to each of the virtual objects according to the maximum eigenvector of the transfer probability matrix, wherein each vector element in the maximum eigenvector corresponds to the virtual interaction value of one of the virtual objects; obtaining a reference vector and a target iteration parameter; determining the dot product result of the target iteration parameter power of the transfer probability matrix and the reference vector as a target vector; determining the virtual interaction value corresponding to each of the virtual objects according to the target vector, wherein each vector element in the target vector corresponds to the virtual interaction value of one of the virtual objects.

[0171] Optionally, the reference determination module is used to: obtain a first reference vector, wherein the vector dimension of the first reference vector is the same as the number of rows of the transfer probability matrix; repeat the following steps to indicate that a convergence condition has been reached: determine the dot product result of the transfer probability matrix and the first reference vector as a second reference vector; when the second reference vector is the same as the first reference vector, determine that the convergence condition has been reached, and determine the second reference vector as the maximum eigenvector; when the second reference vector is different from the first reference vector, use the second reference vector as the first reference vector and repeat the above steps.

[0172] Optionally, the reference determination module is further used to: obtain a first correction coefficient and a second correction coefficient, wherein the first correction coefficient and the second correction coefficient are both greater than 0, and the sum of the first correction coefficient and the second correction coefficient is 1; repeat the following steps until each of the matrix elements in the transfer probability matrix is ​​traversed: obtain one of the matrix elements as the current element; determine the product of the current element and the first correction coefficient as a first correction parameter; determine the ratio of the second correction coefficient to the matrix dimension of the transfer probability matrix as a second correction parameter; and update the current element using the sum of the first correction parameter and the second correction parameter.

[0173] Optionally, the device for determining the target virtual object further includes at least one of the following: a setting unit, used to set the target virtual object as a target virtual character, wherein the target virtual character is used to organize multiple virtual objects in the virtual object set to participate in the target virtual interaction; a sending unit, used to send recruitment information to the key object account corresponding to the target virtual object, wherein the recruitment information is used to set the target virtual object as the target virtual character.

[0174] Optionally, the device for determining the target virtual object is further used to: obtain the activity index corresponding to the target virtual character and the multiple virtual objects organized by the target virtual character; obtain the virtual influence evaluation coefficient of the virtual character according to the activity index; and adjust the virtual interaction value corresponding to the target virtual object when the virtual influence evaluation coefficient does not meet the evaluation conditions.

[0175] Optionally, in this embodiment, the embodiments to be implemented by the above-mentioned various unit modules can refer to the above-mentioned various method embodiments, which will not be repeated here.

[0176] According to another aspect of the embodiments of the present invention, an electronic device for implementing the above-mentioned method for determining a target virtual object is also provided. The electronic device may be Fig. 9 The terminal device or server shown in the figure. This embodiment is described by taking the electronic device as a terminal device as an example. Fig. 9 As shown, the electronic device includes a memory 902 and a processor 904. The memory 902 stores a computer program, and the processor 904 is configured to execute the steps in any of the above method embodiments through the computer program.

[0177] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0178] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0179] S1, obtaining an interaction information set between each virtual object in a virtual object set, wherein the virtual object set includes a plurality of the virtual objects, and the interaction information set includes interaction information of virtual interactions between the virtual objects;

[0180] S2, determining a target object relationship network associated with the virtual object set according to the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate the virtual objects, the target node connection relationships are used to indicate that at least one virtual relationship exists between the two virtual objects, and the target connection weights configured for the target node connection relationships are used to indicate a target intimacy between the two virtual objects, and the target intimacy is determined according to at least one virtual relationship;

[0181] S3, determining the virtual interaction value corresponding to each of the virtual objects in the virtual object set according to the target object relationship network;

[0182] S4, determining a target virtual object from the virtual object set according to the virtual interaction value, wherein the virtual interaction value of the target virtual object satisfies a target condition.

[0183] Alternatively, a person skilled in the art may understand that: Fig. 9 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, and other terminal devices. Fig. 9 The electronic device and the electronic equipment described above are not limited in structure. Fig. 9 More or fewer components (such as network interfaces, etc.) as shown in, or with Fig. 9 Different configurations are shown.

[0184] Among them, the memory 902 can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for determining the target virtual object in the embodiment of the present invention. The processor 904 executes various functional applications and data processing by running the software programs and modules stored in the memory 902, that is, to implement the above-mentioned method for determining the target virtual object. The memory 902 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 902 may further include a memory remotely arranged relative to the processor 904, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 902 may be specifically used, but is not limited to, to store information such as various elements in the scene screen, determination information of the target virtual object, and so on. As an example, such as Fig. 9As shown, the memory 902 may include, but is not limited to, the acquisition unit 802, the first determination unit 804, the second determination unit 806, and the third determination unit 808 in the target virtual object determination device. In addition, other module units in the target virtual object determination device may also be included but are not limited to, which will not be repeated in this example.

[0185] Optionally, the transmission device 906 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 906 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 906 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0186] In addition, the electronic device further includes: a display 908 for displaying a virtual scene in an interface; and a connection bus 910 for connecting various module components in the electronic device.

[0187] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes in the form of network communication. Among them, a peer-to-peer network may be formed between the nodes, and any form of computing device, such as a server, a terminal or other electronic device, may become a node in the blockchain system by joining the peer-to-peer network.

[0188] According to one aspect of the present application, a computer program product is provided, the computer program product comprising a computer program / instruction, the computer program / instruction comprising a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit, various functions provided by the embodiments of the present application are executed.

[0189] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0190] According to one aspect of the present application, a computer-readable storage medium is provided, and 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 the above-mentioned method for determining the target virtual object.

[0191] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0192] S1, obtaining an interaction information set between each virtual object in a virtual object set, wherein the virtual object set includes a plurality of the virtual objects, and the interaction information set includes interaction information of virtual interactions between the virtual objects;

[0193] S2, determining a target object relationship network associated with the virtual object set according to the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate the virtual objects, the target node connection relationships are used to indicate that at least one virtual relationship exists between the two virtual objects, and the target connection weights configured for the target node connection relationships are used to indicate a target intimacy between the two virtual objects, and the target intimacy is determined according to at least one virtual relationship;

[0194] S3, determining the virtual interaction value corresponding to each of the virtual objects in the virtual object set according to the target object relationship network;

[0195] S4, determining a target virtual object from the virtual object set according to the virtual interaction value, wherein the virtual interaction value of the target virtual object satisfies a target condition.

[0196] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0197] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers or network devices, etc.) to perform all or part of the steps of the above methods of various embodiments of the present invention.

[0198] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0199] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0200] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0201] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0202] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining a target virtual object, characterized in that: include: Acquire an interaction information set between each virtual object in a virtual object set, wherein the virtual object set includes a plurality of the virtual objects, and the interaction information set includes interaction information of virtual interactions between the virtual objects; Determine a target object relationship network associated with the virtual object set according to the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate the virtual objects, the target node connection relationships are used to indicate that at least one virtual relationship exists between two virtual objects, and the target connection weight configured for the target node connection relationship is used to indicate a target intimacy between the two virtual objects, and the target intimacy is determined according to at least one virtual relationship; Determine the virtual interaction value corresponding to each virtual object in the virtual object set according to the target object relationship network; A target virtual object is determined from the set of virtual objects according to the virtual interaction value, wherein the virtual interaction value of the target virtual object satisfies a target condition.

2. The method according to claim 1, characterized in that The step of determining a target object relationship network associated with the virtual object set according to the interactive information set includes: Determine a plurality of object relationship networks associated with the set of virtual objects according to the set of interaction information, wherein each of the object relationship networks corresponds to one of the virtual relationships, the object relationship networks include object nodes and node connection relationships, the node connection relationships are used to indicate that one of the virtual relationships exists between two of the virtual objects, and the connection weights configured for the node connection relationships are used to indicate the intimacy of the virtual relationship between the two virtual objects; Based on the object nodes in the plurality of object relationship networks indicating the same virtual object, the plurality of object relationship networks are aggregated to obtain the target object relationship network.

3. The method according to claim 2, characterized in that The step of determining a plurality of object relationship networks associated with the set of virtual objects according to the set of interactive information includes: Acquire a reference interaction information subset corresponding to the reference relationship from the interaction information set, wherein the reference interaction information subset includes the interaction information of the virtual interaction performed between the virtual objects based on the reference relationship; Mapping each of the virtual objects in the virtual object set to an object node, and determining a reference connection relationship between the object nodes based on the interaction information subset, wherein the reference relationship exists between the virtual objects respectively indicated by two object nodes having the reference connection relationship; Based on the interaction information included in the reference interaction information subset, a reference connection weight is configured for each of the reference connection relationships.

4. The method according to claim 2, characterized in that: The step of aggregating the plurality of object relationship networks based on the object nodes indicating the same virtual object in the plurality of object relationship networks to obtain the target object relationship network includes: Repeat the following operations until the virtual objects in the virtual object set are traversed: Acquire one of the virtual objects as the current virtual object; Obtaining a current object node indicating the current virtual object; From the plurality of object relationship networks, sequentially obtain a plurality of relationship object nodes having the node connection relationship with the current object node, and establish the target node connection relationship between the current object node and the relationship object nodes; In the case where there are a plurality of node connection relationships between the current object node and the relationship object node, the target connection weight is configured for the target node connection relationship according to the connection weights respectively configured for the plurality of node connection relationships.

5. The method according to claim 4, characterized in that The configuring the target connection weight for the target node connection relationship according to the connection weights respectively configured for the plurality of node connection relationships comprises: Obtaining network weights respectively configured for a plurality of the object relationship networks; The target connection weight configured for the target node connection relationship is determined according to the connection weights respectively configured for the plurality of node connection relationships and a weighted summation result between the network weights corresponding to the respective connection weights.

6. The method according to claim 1, characterized in that The step of respectively determining the virtual interaction value corresponding to each virtual object in the virtual object set according to the target object relationship network includes: Acquire a transition probability matrix corresponding to the target object relationship network, wherein a row of matrix elements in the transition probability matrix is ​​used to indicate a correlation coefficient between one of the object nodes and other object nodes, and a sum of the elements of a row of the matrix elements is 1; The virtual interaction value corresponding to each of the virtual objects is determined according to the transition probability matrix.

7. The method according to claim 6, characterized in that Determining the virtual interaction value corresponding to each virtual object according to the transition probability matrix includes one of the following: Determine the virtual interaction value corresponding to each of the virtual objects according to the maximum eigenvector of the transition probability matrix, wherein each vector element in the maximum eigenvector corresponds to the virtual interaction value of one of the virtual objects; Obtain a reference vector and a target iteration parameter; determine the dot product result of the target iteration parameter power of the transfer probability matrix and the reference vector as the target vector; determine the virtual interaction value corresponding to each of the virtual objects according to the target vector, wherein each vector element in the target vector corresponds to the virtual interaction value of one of the virtual objects.

8. The method according to claim 7, characterized in that Before determining the virtual interaction value corresponding to each virtual object according to the maximum eigenvector of the transition probability matrix, the method includes: Acquire a first reference vector, wherein the vector dimension of the first reference vector is the same as the number of rows of the transfer probability matrix; Repeat the following steps to indicate that convergence conditions have been reached: Determine a dot product result of the transfer probability matrix and the first reference vector as a second reference vector; When the second reference vector is the same as the first reference vector, determining that the convergence condition is met, and determining the second reference vector as the maximum eigenvector; When the second reference vector is different from the first reference vector, the second reference vector is used as the first reference vector and the above steps are repeated.

9. The method according to claim 6, characterized in that After obtaining the transition probability matrix corresponding to the target object relationship network, the method further includes: Obtaining a first correction coefficient and a second correction coefficient, wherein the first correction coefficient and the second correction coefficient are both greater than 0, and the sum of the first correction coefficient and the second correction coefficient is 1; Repeat the following steps until every matrix element in the transition probability matrix is ​​traversed: Get one of the matrix elements as the current element; determining a product of the current element and the first correction coefficient as a first correction parameter; Determining a ratio between the second correction coefficient and the matrix dimension of the transfer probability matrix as a second correction parameter; The current element is updated using the sum of the first correction parameter and the second correction parameter.

10. The method according to claim 1, characterized in that After determining the target virtual object from the set of virtual objects according to the virtual interaction value, the method further includes at least one of the following: Setting the target virtual object as a target virtual character, wherein the target virtual character is used to organize a plurality of the virtual objects in the virtual object set to participate in a target virtual interaction; Sending recruitment information to the key object account corresponding to the target virtual object, wherein the recruitment information is used to set the target virtual object as the target virtual character.

11. The method according to claim 10, characterized in that After setting the target virtual object as the target virtual character, the method further includes: Obtaining activity indexes corresponding to the target virtual character and the plurality of virtual objects organized by the target virtual character; Obtaining a virtual influence evaluation coefficient of the virtual character according to the activity index; When the virtual influence evaluation coefficient does not meet the evaluation conditions, the virtual interaction value corresponding to the target virtual object is adjusted.

12. A device for determining a target virtual object, characterized in that: include: An acquisition unit, configured to acquire an interaction information set between each virtual object in a virtual object set, wherein the virtual object set includes a plurality of the virtual objects, and the interaction information set includes interaction information of virtual interactions between the virtual objects; A first determining unit is configured to determine a target object relationship network associated with the virtual object set according to the interaction information set, wherein the target object relationship network includes object nodes and target node connection relationships, the object nodes are used to indicate the virtual objects, the target node connection relationships are used to indicate that at least one virtual relationship exists between two virtual objects, and the target connection weight configured for the target node connection relationship is used to indicate a target intimacy between the two virtual objects, and the target intimacy is determined according to at least one virtual relationship; A second determining unit, configured to determine, according to the target object relationship network, respectively the virtual interaction value corresponding to each of the virtual objects in the virtual object set; The third determining unit is configured to determine a target virtual object from the set of virtual objects according to the virtual interaction value, wherein the virtual interaction value of the target virtual object satisfies a target condition.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 11 when executed.

14. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

15. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 11 through the computer program.

Images