WO2021129530A1 - 一种虚拟物品的显示方法、装置、计算机设备和存储介质 - Google Patents

一种虚拟物品的显示方法、装置、计算机设备和存储介质 Download PDF

Info

Publication number
WO2021129530A1
WO2021129530A1 PCT/CN2020/137512 CN2020137512W WO2021129530A1 WO 2021129530 A1 WO2021129530 A1 WO 2021129530A1 CN 2020137512 W CN2020137512 W CN 2020137512W WO 2021129530 A1 WO2021129530 A1 WO 2021129530A1
Authority
WO
WIPO (PCT)
Prior art keywords
gene
behavior
fitness
display
virtual item
Prior art date
Application number
PCT/CN2020/137512
Other languages
English (en)
French (fr)
Inventor
杨键
林麟
Original Assignee
百果园技术(新加坡)有限公司
杨键
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 百果园技术(新加坡)有限公司, 杨键 filed Critical 百果园技术(新加坡)有限公司
Publication of WO2021129530A1 publication Critical patent/WO2021129530A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
    • H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44213—Monitoring of end-user related data
    • H04N21/44218—Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program

Definitions

  • the embodiments of the present application relate to live broadcast technology, such as a method, device, computer equipment, and storage medium for displaying virtual items.
  • the live broadcast is usually hosted by the host user.
  • the viewer user can usually send virtual items. This behavior can be referred to as giving gifts and rewarding the host.
  • the code to implement the animation special effects is usually less, resulting in fewer forms of animation special effects. If you want to make changes to the animation special effects, you often need to release a new version of the application However, the iteration efficiency of the version is low, resulting in a relatively single form of animation special effects.
  • the embodiments of the present application provide a method, device, computer device, and storage medium for displaying virtual items, so as to avoid the situation that the form of playing the animation special effects of virtual items in a live broadcast scene is relatively single.
  • an embodiment of the present application provides a method for displaying virtual items, including:
  • an embodiment of the present application also provides a virtual item display device, including:
  • the live room display module is set to display the live room of the host user
  • a virtual item determining module configured to determine the virtual item received by the anchor user
  • a live broadcast feature determination module configured to determine the live broadcast feature associated with the virtual item
  • a display behavior matching module configured to determine a display behavior matching the virtual item according to the live broadcast feature
  • the display behavior execution module is configured to execute the display behavior on the virtual item in the live broadcast room.
  • an embodiment of the present application also provides a computer device, and the computer device includes:
  • At least one processor At least one processor
  • Memory set to store at least one program
  • the at least one processor When the at least one program is executed by the at least one processor, the at least one processor implements the method for displaying virtual items as described in the first aspect.
  • the embodiments of the present application also provide a computer-readable storage medium having a computer program stored on the computer-readable storage medium.
  • the computer program is executed by a processor, the virtual machine described in the first aspect is implemented. How to display items.
  • FIG. 1 is a flowchart of a method for displaying virtual items according to Embodiment 1 of this application;
  • FIG. 2 is a flowchart of a method for displaying virtual items provided in the second embodiment of the present application
  • FIG. 3 is a schematic diagram of nodes of a behavior tree provided in Embodiment 2 of the present application.
  • FIG. 4 is an example diagram of a behavior tree provided in Embodiment 2 of the present application.
  • FIG. 5 is a schematic structural diagram of a display device for virtual items provided in the third embodiment of the application.
  • FIG. 6 is a schematic structural diagram of a computer device provided in Embodiment 4 of this application.
  • FIG. 1 is a flowchart of a method for displaying virtual items provided in the first embodiment of the application. This embodiment is applicable to the case of adaptively selecting the way of displaying virtual items.
  • the method can be executed by a display device of virtual items.
  • the display device of the virtual item can be implemented by software and/or hardware, and can be configured in a computer device, for example, a personal computer, a mobile terminal (such as a mobile phone, a tablet computer, etc.), a wearable device (such as a smart watch, etc.), etc.
  • the method includes step S101 to step S105.
  • operating systems such as Android (Android), IOS, Windows, etc.
  • applications that support live broadcast such as independent live broadcast applications, short video applications, download tools, instant messaging tools, etc.
  • the page provided by the live broadcast platform is loaded, the live broadcast room is displayed on the page, and the live broadcast program hosted by the host user is displayed in the live broadcast room.
  • the anchor user can be represented by a user identifier, such as a user ID, user account, and so on.
  • the virtual item received by the host user is determined.
  • the live broadcast platform provides one or more virtual items, such as light sticks, hot pot, books, rockets, etc., which can be displayed in the live broadcast room.
  • virtual items such as light sticks, hot pot, books, rockets, etc.
  • a certain application in the live broadcast room When a certain application in the live broadcast room receives a virtual item sending operation from a viewer user, it notifies the live broadcast platform, and the live broadcast platform verifies the legitimacy of the viewer user. When the legitimacy verification is passed, the virtual item is sent to The host user, and notify all applications that log in to the live broadcast room to display the virtual item locally.
  • the application program installed in the current computer device may be an application program that initiates the behavior of sending virtual items, and other applications except the application program that initiates the behavior of sending virtual items, which is not limited in this embodiment.
  • live broadcast platforms generally provide membership services. Therefore, viewer users who send virtual items to anchor users are usually registered users in the live broadcast platform.
  • the virtual items provided by the live broadcast platform are generally equipped with the value of virtual tokens. , The value can be 0 (that is, free) or other values.
  • the live broadcast platform deducts the price of the virtual item from the viewer user’s account.
  • the live broadcast feature associated with the virtual item is determined.
  • the application program may receive the live broadcast feature associated with the virtual item sent by the live broadcast platform, that is, the feature associated with the virtual item in the live broadcast.
  • the live broadcast feature includes at least one of the feature of the host user, the feature of the viewer user, and the interaction feature between the host user and the viewer user.
  • the characteristics of the host user are information that can be reflected in the live broadcast room and the characteristics of the host user.
  • the characteristics of the anchor user include:
  • the offline characteristics of the anchor user are the characteristics of the anchor user during the non-live broadcast time, such as registration time, average active time, historical start time, number of followers, total revenue, and so on.
  • the real-time characteristics of the host user are the characteristics of the host user during the live broadcast time, for example, real-time popularity, gender, country, language, live broadcast type, and so on.
  • the characteristics of the audience user are information that can be reflected in the live broadcast room and the characteristics of the audience user.
  • the live broadcast characteristics of the viewer user include:
  • the offline characteristics of the audience user are the characteristics of the audience user during the non-live broadcast time, such as the average viewing time, the total number of historical gifts, and so on.
  • the real-time characteristics of the audience user are the characteristics of the audience user during the live broadcast time, for example, online duration, gender, country, language, and so on.
  • the interactive feature between the host user and the viewer user is information that can reflect the feature of the host user's interaction with the viewer user when the host user hosts a live program.
  • the viewer user's historical viewing time for the host user For example, the viewer user's historical viewing time for the host user, the total number of virtual items gifted by the viewer user history to the host user, whether the viewer user pays attention to the host user, and so on.
  • a display behavior matching the virtual item is determined according to the live broadcast feature.
  • the application program provides multiple independent display behaviors for virtual items, and each display behavior has a specific style, and the virtual item can be displayed according to the style.
  • the display behavior includes “running in a circle”, “calling to speak”, “delaying response for n seconds”, and so on.
  • the live broadcast feature after determining the live broadcast feature related to the virtual item, the live broadcast feature may be used as a filtering condition, and at least one suitable display behavior can be selected from all the display behaviors as the current display behavior for displaying the virtual item.
  • the live broadcast platform can deliver different combinations of display behaviors for different applications. For example, the live broadcast platform delivers 1 display behavior to an application, and the live broadcast platform delivers 2 to another application. Display behavior, the live broadcast platform sends 3 display behaviors to another application, etc. Therefore, in different applications, you can choose different display behaviors, and the same virtual item may have different display behaviors in different applications. Style to display.
  • the virtual item is displayed in the live broadcast room.
  • the display behavior can be performed on the virtual item in the live broadcast room, so as to display the virtual item according to the style specified by the display behavior, so as to realize the sending of the virtual item to the host user.
  • the live broadcast room of the host user is displayed, the virtual items received by the host user are determined, the live broadcast feature associated with the virtual item is determined, and the display behavior matching the virtual item is determined according to the live broadcast feature.
  • Perform display behaviors by pre-defining the display behaviors of virtual items and matching them with live broadcast characteristics, realize the intelligent control of adaptive selection of display behaviors according to the characteristics of live broadcasts, frame the selection of display behaviors, and do not need to display the code of virtual items
  • the display behaviors in the framework can be fixed and updated, with low coupling and strong scalability, which not only greatly enriches the ways of displaying virtual items, but also reduces the workload of application development.
  • FIG. 2 is a flowchart of a method for displaying virtual items provided in the second embodiment of the application. This embodiment is based on the foregoing embodiment and is refined, and the genetic algorithm (Genetic Algorithm, GA) is used to screen and display behaviors and pass behaviors.
  • the tree executes the processing operation of the display behavior, and the method includes step S201 to step S211.
  • the live broadcast feature associated with the virtual item is determined.
  • the behavior tree is determined.
  • a behavior tree (Behavior Tree) is set in advance for each type of virtual item in the application, and the behavior tree has a root node (root) and a control node (the control node is "control" and its child nodes).
  • the child node can be a leaf node, that is, a behavior node, or a control node.
  • execution control node is to execute its defined control logic
  • the behavior node represents a display behavior.
  • this embodiment can also set the display behavior through a finite state machine (Finite-state machine, FSM), which is not limited in this embodiment.
  • FSM Finite-state machine
  • the behavior tree is through a tree structure. Every time it is updated, it starts from the root node of the tree, and confirms the state switch to be operated and the actual action according to the type and state of the child node.
  • each node has an execution state, and after each execution is completed, the execution result is passed to the parent node. Coupled with various internal special nodes, artificial intelligence (AI) with certain complex behaviors can be realized.
  • AI artificial intelligence
  • the behavior tree sets some special nodes on the basis of the base node (BaseNode) (that is, the root node). These special nodes are used to assemble logic.
  • the design of these special nodes is as follows:
  • Action node Define a specific behavior by inheriting it; for example, for display behavior, it can be "patrol”, “received”, “escape”, etc.;
  • Composite node By inheriting it, it can organize a group of behaviors and determine the branch direction. For example, Sequence (Sequence, executes all its child nodes in sequence, that is, after the current one returns to the "complete" state, then run the next one Child node), selection (Selector, select one of its child nodes to execute), parallel (Parallel, run all of its child nodes once), etc.;
  • Decorator By inheriting it, define a constraint that acts on the behavior; for example, execute NUM (NUM is a custom variable and a positive integer) second child node, change the return state of the child node, etc.;
  • Condition node By inheriting it, define a condition for returning success or failure; for example, judging the popularity of the anchor user, judging the current blood volume, and so on.
  • a behavior tree is configured to achieve the desired intelligent effect.
  • behavior nodes in the behavior tree can be defined according to the actual situation.
  • sequential nodes, selection nodes, and parallel nodes are control nodes, behavior A, behavior B , Behavior C, Behavior D, Behavior E, Behavior F, and Behavior G belong to behavior nodes.
  • Behavior nodes are predefined display behaviors that display virtual items. For example, virtual items execute display logic in circles, and virtual items execute calling and speaking The display logic of the virtual item, the display logic of the virtual item's response delay for n seconds, and so on.
  • At least one gene is determined, and each of the genes represents at least one manifestation behavior.
  • the viewer user When the viewer user sends a virtual item to the anchor user, it is necessary to decide the display behavior performed by the current virtual item. At this time, the behavior tree is searched from top to bottom to determine the behavior node (display behavior) and execute it. Through this characteristic design, the decision logic is visualized, the control node can be reused, and the logic and realization of low coupling.
  • the extended and inherited display behaviors can be exchanged with each other. Therefore, after the logic of the behavior tree is edited in product planning, an optimal solution for intelligent display of virtual items can be obtained.
  • genetic algorithm iteration is used to obtain an optimal behavior tree. Compared with traditional logic implementation or state machine implementation, it can clearly organize behavioral decision-making, reduce the amount of program development, give product design to product personnel to think, what you see is what you get, and get the optimal solution, thereby optimizing products and improving product quality .
  • Genetic algorithm is a computational model that simulates the biological evolution process of natural selection and genetic mechanism of biological evolution theory. It is a method of searching for the optimal solution by simulating the natural evolution process.
  • a genetic algorithm is used to search for the display behavior that best matches the live broadcast feature.
  • the genetic algorithm can be used to encode display behaviors, such as binary encoding, floating-point encoding, symbol encoding, etc. That is, the object of genetic algorithm is the symbol string that represents the display behavior.
  • the genetic algorithm is an evolutionary operation on the population. You can prepare some initial population data representing the initial search point by random setting and other methods.
  • At least one performance of the display behavior can be randomly generated in the combination form, and display
  • Each performance of the behavior is used as a gene of the initial population, and each performance of the display behavior includes at least one display behavior, that is, each gene is used to represent at least one display behavior.
  • a live broadcast platform delivers a combination of two display behaviors to an application, and let one display behavior x 1 ⁇ 1,2,3,4,5,6,7 ⁇ , and the other display behavior x 2 ⁇ 1, 2, 3, 4, 5, 6, 7 ⁇ , the display behaviors x 1 and x 2 are encoded as a symbol string.
  • the display behaviors x 1 and x 2 can be represented by 3-bit unsigned binary integers respectively, and the 6-bit unsigned binary number formed by connecting them together forms an individual Gene represents a feasible solution.
  • the performance x of the display behavior and the gene X can be converted mutually through encoding and decoding.
  • the size of the population size is taken as 4, that is, the population is composed of 4 individuals, and each individual can be generated by a random setting method, such as: 011101, 101011, 011100, 111001.
  • the fitness of at least one current gene is calculated based on the live broadcast feature.
  • the genetic algorithm uses the size of individual fitness to evaluate the pros and cons of each individual, thereby determining the size of their genetic opportunities.
  • the live broadcast feature is used as a condition for gene screening, and the live broadcast feature is used for design to calculate the fitness of the gene.
  • a genetic algorithm usually requires multiple genetic operations, that is, multiple iterations. In each iteration, genes may change, and fitness is calculated for the genes of the current iteration.
  • the live broadcast feature includes the first number of times each current gene is used within a preset time period, and the audience user expresses positive emotions (such as likes, support, flowers, etc.) when the virtual item is displayed.
  • the second time the weight of the positive emotion (can be set as the total number of viewer users in the current live broadcast room multiplied by a coefficient, such as 0.1), and the revenue value of each current gene is used within a preset time period.
  • calculate the first ratio between the first number of times and the preset time period calculate the second ratio between the second number of times and the weight of positive emotions, and calculate the revenue value and the preset time period
  • calculate the first ratio calculate the sum of the second ratio and the third ratio, as the fitness of at least one current gene.
  • the above method of calculating fitness is just an example.
  • other methods of calculating fitness can be set according to the actual situation. For example, if the staying situation of viewers is inclined, the per capita viewing time and per capita attention rate will be increased. Such live broadcast features, if the revenue of the anchor user is inclined, can increase the live broadcast features such as the per capita gift of virtual items and the consumption of virtual tokens by the viewer user, and so on. This embodiment does not impose restrictions on this.
  • those skilled in the art can also use other methods of calculating fitness according to actual needs, and this embodiment does not limit this.
  • S207 it is determined whether the fitness of the at least one current gene meets the preset stopping condition; in the case that the fitness of the at least one current gene meets the preset stopping condition, S208 is executed, and the If the fitness of at least one current gene does not meet the preset stopping condition, S209 is executed.
  • a stopping condition for inheritance can be set in advance. If the stopping condition is met, the inheritance is stopped and a suitable gene is selected, and if the stopping condition is not met, the gene is continued to be inherited.
  • the stopping condition includes that the third number of iterations of at least one current gene reaches a preset first threshold, and the maximum value of the current fitness of at least one gene reaches a preset second threshold.
  • the third number of iterations of at least one current gene is counted, and the third number of iterations of at least one current gene is compared with a preset first threshold, or the current at least one The maximum value of the fitness of the gene is compared with the preset second threshold.
  • stopping conditions are just examples.
  • other stopping conditions can be set according to the actual situation, for example, the iteration time exceeds a preset threshold, and the difference between the maximum fitness value in every two iterations Less than a preset threshold, and so on.
  • This embodiment does not impose restrictions on this.
  • those skilled in the art can also adopt other stopping conditions according to actual needs, and this embodiment does not limit this.
  • one gene of the at least one current gene is selected according to the fitness of the at least one current gene, and the at least one display behavior represented by the one gene is used as the display behavior matching the virtual item.
  • the gene with the largest fitness value is selected, and the display behavior represented by it is used as the display behavior matching the virtual item.
  • the fitness of the at least one current gene is sorted in descending order according to the fitness value, and at least one display behavior represented by the gene associated with the fitness in the first position is selected as the matching virtual item Show behavior.
  • At least one of a selection operation, a crossover operation, and a mutation operation is performed on the at least one current gene to obtain at least one new gene, and the execution of S206 is returned.
  • the gene of the current iteration As the gene of the parent population, perform at least one of the selection operation, crossover operation and mutation operation on it, and inherit part or all of the gene in the parent to the gene of the offspring population, continue Iterate.
  • selection operation can be executed individually or in combination. When combined, they can be executed serially or in parallel, etc., which is not limited in this embodiment.
  • a combination of genetic operations is performed serially, a selection operation is performed on the at least one current gene, a crossover operation is performed on the gene after the selection operation, and a mutation operation is performed on the gene after the crossover operation to obtain at least one new gene. gene.
  • the genetic operation includes at least one of a selection operation, a crossover operation, and a mutation operation.
  • the selection operation (or copy operation) is used to determine how to select individuals from the parent population in a certain way so that they can be inherited into the offspring population.
  • the selection operation inherits the higher fitness individuals in the current parent population into the offspring population according to a certain rule or model, and the higher fitness individuals will have more chances to inherit to the next generation.
  • the probability of selecting the at least one current gene is calculated based on the fitness of the at least one current gene, and the probability is positively correlated with the fitness of the at least one current gene, that is, the higher the fitness, The greater the probability, on the contrary, the lower the fitness, the smaller the probability.
  • x i and x j are genes
  • f() is the fitness of the genes
  • N is the total number of genes
  • i is the i-th gene
  • j is the j-th gene
  • P() is the probability of the gene.
  • the first value r ⁇ [0,1] is randomly generated as the third threshold.
  • At least one current gene From the at least one current gene, at least one gene whose probability of selecting a gene is greater than the third threshold is selected, and then the at least one gene is selected and inherited to the next generation.
  • the selection operations are as follows:
  • Crossover operation refers to the exchange of some genes between two paired individuals in a certain way to form two new individuals.
  • two current genes are selected as a pair of candidate genes, and a second value is generated for each pair of candidate genes as the crossover probability, where the second value is a random probability value greater than 0 and less than 1.
  • the crossover probability is greater than the preset fourth threshold (the fourth threshold P c ⁇ (0, 1)), then the data located after the designated crossover point in each pair of candidate genes are exchanged with each other.
  • the crossover operation is as follows:
  • the fitness of the newly generated individuals 111101 and 111011 after the crossover operation is higher than the fitness of the original two individuals.
  • Mutation operation refers to changing at least one data in an individual code string with a small probability to form a new individual.
  • the crossover operation and mutation operation cooperate with each other to jointly complete the global search and local search of the search space.
  • a third value is randomly generated for each current gene as the mutation probability.
  • the mutation probability of a gene is greater than the preset fifth threshold (the fifth threshold P m ⁇ (0, 0.2)), the data at the designated mutation point in the gene is changed.
  • the basic bit mutation operator refers to the mutation operation of a certain bit or a few genes randomly designated by an individual code string. For the individual represented by the binary code string, the original gene value is reversed. If the original gene value of a gene undergoing mutation operation is 0, it will be changed to 1; otherwise, if the original gene value is 1 , Then change it to 0.
  • the mutation operation is as follows:
  • the individual comfort level of No. 4 is 98, which exceeds 95 (the second threshold), and the combination of display behavior 7 and display behavior 2 can be selected.
  • a behavior node is executed to perform a display behavior on the virtual item in the live broadcast room.
  • the display behavior represented by the behavior node is executed, and the virtual items are displayed in the screen of the live room according to the style represented by the display behavior, so that the virtual items are sent to the anchor user.
  • a controller can be set in advance, and the controller has control nodes that match all the behavior nodes one by one.
  • the control node is the code that realizes the display behavior represented by the behavior node, and the coupling between the control nodes is low.
  • adjust the control nodes accordingly (such as adding or deleting), which can improve scalability.
  • a controller When determining the behavior node that matches the live broadcast feature, a controller may be determined, and the controller has a control node, and the control node configured for the behavior node is called to execute the behavior node.
  • the life cycle of the behavior tree ends.
  • the virtual item can be deleted in the live broadcast room to complete the delivery of the virtual item to the host user.
  • the display behavior is represented by the behavior node in the behavior tree, and the behavior node matching the live broadcast feature is searched from the behavior tree by genetic algorithm.
  • the behavior tree organizes complex display behaviors very intuitively.
  • the nodes in the network have high reusability and strong scalability, which greatly reduces the threshold and amount of application development.
  • the genetic algorithm is simple and can be implemented locally on computer equipment. Genetic algorithm provides fast and unrelated business. Random search capability makes it easy to search and display behaviors using live features as conditions. Genetic algorithms are scalable and easy to combine with behavior trees.
  • FIG. 5 is a schematic structural diagram of a virtual item display device provided in the third embodiment of the application.
  • the device may include the following modules:
  • the live room display module 501 is configured to display the live room of the host user.
  • the virtual item determining module 502 is configured to determine the virtual item received by the host user.
  • the live broadcast feature determination module 503 is configured to determine the live broadcast feature associated with the virtual item.
  • the display behavior matching module 504 is configured to determine a display behavior matching the virtual item according to the live broadcast feature.
  • the display behavior execution module 505 is configured to execute the display behavior on the virtual item in the live broadcast room.
  • the live broadcast feature determination module 503 includes:
  • a behavior tree determination sub-module set to determine a behavior tree, the behavior tree has a behavior node, and the behavior node represents a display behavior;
  • the gene determination sub-module is configured to determine at least one gene, and each gene represents at least one display behavior
  • the fitness calculation sub-module is set to calculate the fitness of at least one current gene based on the live broadcast feature
  • the stopping condition judgment submodule is configured to judge whether the fitness of the at least one current gene meets the preset stopping condition; when the fitness of the at least one current gene meets the preset stopping condition, call the display A behavior selection sub-module, when the fitness of the at least one current gene does not meet a preset stopping condition, call the genetic operation sub-module;
  • the display behavior selection submodule is configured to select one of the at least one current gene according to the fitness of the at least one current gene, and use the at least one display behavior represented by the one gene as the The display behavior of virtual item matching;
  • the genetic operation submodule is configured to perform at least one genetic operation among selection operations, crossover operations, and mutation operations on the at least one current gene to obtain at least one new gene, and return to call the fitness calculation submodule.
  • the live broadcast feature includes the first number of times each current gene is used within a preset time period, and the second time that the audience user expresses positive emotions when the virtual item is displayed. The number of times, the weight of the positive emotion, and the revenue value of using each current gene within a preset time period;
  • the fitness calculation sub-module includes:
  • a first ratio calculation unit configured to calculate a first ratio between the first number of times and the preset time period
  • a second ratio calculation unit configured to calculate a second ratio between the second number of times and the weight of the positive emotion
  • a third ratio calculation unit configured to calculate a third ratio between the revenue value and the preset time period
  • the sum calculation unit is configured to calculate the sum of the first ratio, the second ratio and the third ratio as the fitness of at least one current gene.
  • the stop condition judgment submodule includes:
  • the comparing unit is configured to compare the third number of iterations of the at least one current gene with a preset first threshold, and compare the maximum value of the fitness of the at least one current gene with the preset second threshold ;
  • the condition satisfaction determination unit is configured to determine that if the third number of times is greater than or equal to the first threshold, or the maximum value of the fitness of the at least one current gene is greater than or equal to the second threshold, then it is determined that the stop is satisfied. condition;
  • the condition unsatisfied determining unit is configured to determine that if the third number of times is less than the first threshold and the maximum value of the fitness of the at least one current gene is less than the second threshold, it is determined that the stopping condition is not met.
  • the genetic manipulation submodule includes:
  • a probability calculation unit configured to calculate a probability of selecting the at least one current gene based on the fitness of the at least one current gene, and the probability is positively correlated with the fitness of the at least one current gene;
  • the first value generating unit is configured to randomly generate the first value as the third threshold
  • the gene selection unit is configured to select at least one gene whose probability of a gene is greater than the third threshold value from the at least one current gene.
  • the probability calculation unit includes:
  • the total fitness calculation subunit is set to calculate the sum of all fitness of the at least one current gene as the total fitness
  • the fitness ratio calculation subunit is set to calculate a fourth ratio between the fitness of the gene and the total fitness for a certain gene, as the probability of selecting the gene.
  • the genetic manipulation submodule includes:
  • the candidate gene selection unit is set to select two current genes as a pair of candidate genes
  • a second value generating unit configured to generate a second value for each pair of candidate genes as a crossover probability
  • the data exchange unit is configured to exchange data located after the designated intersection in each pair of candidate genes if the crossover probability is greater than a preset fourth threshold.
  • the genetic manipulation submodule includes:
  • the third value generating unit is set to randomly generate a third value for each current gene as the mutation probability
  • the data changing unit is configured to change the data at the designated mutation point in the gene if the mutation probability of a certain gene is greater than the preset fifth threshold.
  • the genetic manipulation submodule includes:
  • a selection operation unit configured to perform a selection operation on the at least one current gene
  • the crossover operation unit is set to perform crossover operations on the genes after the selection operation
  • the mutation operation unit is set to perform mutation operation on the gene after the crossover operation to obtain at least one new gene.
  • the display behavior selection submodule includes:
  • a descending sorting unit configured to sort the fitness of the at least one current gene in descending order
  • the first selection unit is set to select at least one display behavior represented by the fitness-related gene in the first position as the display behavior matching the virtual item.
  • the display behavior is a behavior node in a behavior tree
  • the display behavior execution module 505 includes:
  • a behavior node execution submodule configured to execute the behavior node, so as to perform the display behavior on the virtual item in the live broadcast room;
  • the display end submodule is set to end the behavior tree if the execution is completed, and delete the virtual item in the live broadcast room.
  • the behavior node execution submodule includes:
  • the controller determining unit is configured to determine the controller, and the controller has a control node;
  • the control node invoking unit is configured to invoke the control node configured on the behavior node to execute the behavior node.
  • the virtual item display device provided in the embodiment of the present application can execute the virtual item display method provided in any embodiment of the present application, and has a function module corresponding to the execution method.
  • FIG. 6 is a schematic structural diagram of a computer device provided in Embodiment 4 of this application.
  • the computer device includes a processor 600, a memory 601, a communication module 602, an input device 603, and an output device 604; the number of processors 600 in the computer device may be at least one.
  • one processor 600 is used.
  • the processor 600, the memory 601, the communication module 602, the input device 603, and the output device 604 in the computer equipment may be connected by a bus or other means. In FIG. 6, the connection by a bus is taken as an example.
  • the memory 601 can be configured to store software programs, computer-executable programs, and modules, such as the modules corresponding to the virtual item display method in this embodiment (for example, the virtual item shown in FIG. 5).
  • the processor 600 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 601, that is, realizes the above-mentioned method for displaying virtual items.
  • the memory 601 may mainly include a program storage area and a data storage area.
  • the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of a computer device.
  • the memory 601 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the memory 601 may include a memory remotely provided with respect to the processor 600, and these remote memories may be connected to a computer device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the communication module 602 is configured to establish a connection with the display screen and realize data interaction with the display screen.
  • the input device 603 can be configured to receive input digital or character information, and generate key signal input related to user settings and function control of the computer equipment, and can also be a camera configured to obtain images and a sound pickup device to obtain audio data.
  • the output device 604 may include audio equipment such as a speaker.
  • composition of the input device 603 and the output device 604 can be set according to actual conditions.
  • the processor 600 executes various functional applications and data processing of the device by running software programs, instructions, and modules stored in the memory 601, that is, realizes the above-mentioned connection node control method of the electronic whiteboard.
  • the computer device provided in this embodiment can execute the virtual item display method provided in any embodiment of the present application, and has corresponding functions.
  • the fifth embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, a method for displaying virtual items is realized, the method includes:
  • the computer program of the computer-readable storage medium provided in the embodiment of the present application is not limited to the method operations described above, and may also perform related operations in the virtual item display method provided in any embodiment of the present application.
  • the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding function can be realized;
  • the names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Engineering & Computer Science (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种虚拟物品的显示方法、装置、计算机设备和存储介质，该方法包括：显示主播用户的直播间；确定主播用户接收到的虚拟物品；确定与虚拟物品关联的直播特征；根据直播特征确定与虚拟物品匹配的显示行为；在直播间中对虚拟物品执行显示行为。

Description

一种虚拟物品的显示方法、装置、计算机设备和存储介质
本申请要求在2019年12月26日提交中国专利局、申请号为201911367877.3的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及直播技术，例如一种虚拟物品的显示方法、装置、计算机设备和存储介质。
背景技术
随着互联网的发展，尤其是移动终端的普及，直播在人们的工作、生活、娱乐中愈发普及。
直播通常由主播用户主持，为了提高观众用户与主播用户之间的互动，观众用户通常可以发送虚拟物品，这种行为可以称之为赠送礼物、打赏主播等。
目前，虚拟物品大多是基于播放动画特效的方式进行显示，基于相关设备的性能，一般采用硬编码的方式，将实现该播放动画特效的代码固定在应用程序中，并发布该应用程序。
为了提高应用程序的开发效率、降低应用程序的维护成本，实现该播放动画特效的代码通常较少，导致动画特效的形式较少，如果想要对动画特效进行改动，往往需要发布新版本的应用程序，但是，版本的迭代效率较低，导致动画特效的形式较为单一。
发明内容
本申请实施例提供一种虚拟物品的显示方法、装置、计算机设备和存储介质，以避免在直播场景中、播放虚拟物品的动画特效的形式较为单一的情况。
第一方面，本申请实施例提供了一种虚拟物品的显示方法，包括：
显示主播用户的直播间；
确定所述主播用户接收到的虚拟物品；
确定与所述虚拟物品关联的直播特征；
根据所述直播特征确定与所述虚拟物品匹配的显示行为；
在所述直播间中对所述虚拟物品执行所述显示行为。
第二方面，本申请实施例还提供了一种虚拟物品的显示装置，包括：
直播间显示模块，设置为显示主播用户的直播间；
虚拟物品确定模块，设置为确定所述主播用户接收到的虚拟物品；
直播特征确定模块，设置为确定与所述虚拟物品关联的直播特征；
显示行为匹配模块，设置为根据所述直播特征确定与所述虚拟物品匹配的显示行为；
显示行为执行模块，设置为在所述直播间中对所述虚拟物品执行所述显示行为。
第三方面，本申请实施例还提供了一种计算机设备，所述计算机设备包括：
至少一个处理器；
存储器，设置为存储至少一个程序；
当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如第一方面所述的虚拟物品的显示方法。
第四方面，本申请实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，该计算机程序被处理器执行时，实现如第一方面所述的虚拟物品的显示方法。
附图说明
图1为本申请实施例一提供的一种虚拟物品的显示方法的流程图；
图2是本申请实施例二提供的一种虚拟物品的显示方法的流程图；
图3是本申请实施例二提供的一种行为树的节点示意图；
图4是本申请实施例二提供的一种行为树的示例图；
图5为本申请实施例三提供的一种虚拟物品的显示装置的结构示意图；
图6为本申请实施例四提供的一种计算机设备的结构示意图。
具体实施方式
实施例一
图1为本申请实施例一提供的一种虚拟物品的显示方法的流程图，本实施例可适用于自适应选择显示虚拟物品的方式的情况，该方法可以由虚拟物品的显示装置来执行，该虚拟物品的显示装置可以由软件和/或硬件实现，可配置在计算机设备中，例如，个人电脑、移动终端(如手机、平板电脑等)、可穿戴设备(如智能手表等)，等等，该方法包括步骤S101至步骤S105。
在S101中，显示主播用户的直播间。
在计算机设备中，可安装Android(安卓)、IOS、Windows等操作***，在该操作***中，安装支持直播的应用程序，如独立的直播应用、短视频应用、下载工具、即时通讯工具，等等。
在该应用程序中，加载直播平台提供的页面，在该页面中显示直播间，在该直播间中，显示主播用户主持的直播节目。
需要说明的是，对于计算机设备以及直播平台而言，主播用户可用用户标识进行表示，如用户ID、用户账号，等等。
在S102中，确定主播用户接收的虚拟物品。
为提高观众用户与主播用户之间的互动，直播平台提供了一种或多种虚拟物品，如荧光棒、火锅、书本、火箭等，这些虚拟物品可在直播间中显示。
在直播间中的某个应用程序接收到观众用户针对虚拟物品的发送操作，则通知直播平台，直播平台对观众用户进行合法性校验，在通过合法性校验时， 将该虚拟物品发送至主播用户，并通知登录该直播间的所有应用程序，在本地显示该虚拟物品。
因此，在当前计算机设备中安装的应用程序，可能是发起发送虚拟物品行为的应用程序，与除发起发送虚拟物品行为的应用程序之外的其他应用程序，本实施例对此不加以限制。
需要说明的是，直播平台一般提供会员制服务，因此，给主播用户发送虚拟物品的观众用户，通常为直播平台中的注册用户，直播平台所提供的虚拟物品，一般配置有虚拟代币的价值，该价值可以为0(即免费)，也可以为其他数值，直播平台在观众用户通过合法性校验时，从该观众用户的账户中扣除该虚拟物品的价格。
在S103中，确定与虚拟物品关联的直播特征。
在本实施例中，应用程序可接收直播平台发送的、与虚拟物品关联的直播特征，即在直播中与虚拟物品关联的特征。
在一实施例中，该直播特征包括主播用户的特征、观众用户的特征、主播用户与观众用户之间的交互特征中的至少一种。
一、主播用户的特征：
主播用户的特征为可体现在直播间中、主播用户的特性的信息。
示例性的，该主播用户的特征包括：
1、主播用户的离线特征
主播用户的离线特征为在非直播时间体现主播用户的特征，例如，注册时间、平均活跃时间，历史的开播时间，关注人数，营收总值，等等。
2、主播用户的实时特征
主播用户的实时特征为在直播时间体现主播用户的特征，例如，实时热度、 性别、国家、语言、直播类型，等等。
二、观众用户的特征：
观众用户的特征为可体现在直播间中、观众用户的特性的信息。
示例性的，该观众用户的直播特征包括：
1、观众用户的离线特征
观众用户的离线特征为在非直播时间体现观众用户的特征，例如，平均观看时间、历史送礼总数，等等。
2、观众用户的实时特征
观众用户的实时特征为在直播时间体现观众用户的特征，例如，在线时长、性别、国家、语言，等等。
三、主播用户与观众用户之间的交互特征
主播用户与观众用户之间的交互特征为可体现在主播用户主持直播节目时、该主播用户与观众用户互动的特性的信息。
例如，观众用户对主播用户历史观看时长、观众用户历史赠送给主播用户的虚拟物品总数、观众用户是否关注主播用户，等等。
在S104中，根据直播特征确定与虚拟物品匹配的显示行为。
应用程序为虚拟物品提供多个相互独立的显示行为，每个显示行为具有特定的样式，可按照该样式显示虚拟物品。
例如，该显示行为包括“绕圈跑”、“呼唤说话”、“延迟n秒响应”，等等。
在本实施例中，在确定与虚拟物品相关的直播特征之后，可以以直播特征作为筛选的条件，从所有的显示行为中选择至少一个合适的显示行为，作为当前显示该虚拟物品的显示行为。
需要说明的是，直播平台可以针对不同的应用程序下发不同的显示行为的组合形式，例如，直播平台向某个应用程序下发1个显示行为、直播平台向另一个应用程序下发2个显示行为、直播平台向又一个应用程序下发3个显示行为，等等，因此，在不同的应用程序中，可以选择不同的显示行为，则同一个虚拟物品在不同的应用程序可能以不同的样式进行显示。
在S105中，在直播间中对虚拟物品执行显示行为。
如果确定了显示行为，则可以在直播间中对虚拟物品执行该显示行为，从而按照该显示行为指定的样式显示虚拟物品，实现将虚拟物品发送给主播用户。
在本实施例中，显示主播用户的直播间，确定主播用户接收到的虚拟物品，确定与虚拟物品关联的直播特征，根据直播特征确定与虚拟物品匹配的显示行为，在直播间中对虚拟物品执行显示行为，通过预先定义虚拟物品的显示行为，并与直播特征进行匹配，实现根据直播的特性自适应选择显示行为的智能化控制，将显示行为的选择框架化，无需将显示虚拟物品的代码固化，更新框架中的显示行为即可，低耦合，可扩展性强，不仅大大丰富了显示虚拟物品的方式，还减少了应用程序开发的工作量。
实施例二
图2为本申请实施例二提供的一种虚拟物品的显示方法的流程图，本实施例以前述实施例为基础，进行细化，通过遗传算法(Genetic Algorithm，GA)筛选显示行为、通过行为树执行显示行为的处理操作，该方法包括步骤S201至步骤S211。
在S201中，显示主播用户的直播间。
在S202中，确定主播用户接收到的虚拟物品。
在S203中，确定与虚拟物品关联的直播特征。
在S204中，确定行为树。
在本实施例中，预先在应用程序中对每一种虚拟物品设置一棵行为树(Behavior Tree)，在行为树中具有根节点(root)、控制节点(控制节点为“控制”其子节点(子节点可以是叶节点，即行为节点，也可以是控制节点，所谓“执行控制节点”，就是执行其定义的控制逻辑))、行为节点等节点，其中，该行为节点表示显示行为，在确定观众用户发送给主播用户的虚拟物品时，可查找该虚拟物品对应的行为树。
当然，除了对每一种虚拟物品设置一棵行为树之外，也可以对多种虚拟物品设置一棵行为树，对所有虚拟物品设置一棵行为树，等等，本实施例对此不加以限制。
此外，除了行为树之外，本实施例还可以通过有限状态机(Finite-state machine，FSM)设置显示行为，本实施例对此不加以限制。
行为树是通过一个树状结构，每次更新时都会从树的根节点出发，根据子节点的类型和状态，来确认要操作的状态切换以及实际动作。在行为树中，每一个节点都有执行的状态，以及，每次执行完成后都会向父节点传递执行结果。再配合各种内部的特殊节点，就可以实现有一定复杂行为的人工智能(Artificial Intelligence，AI)。
如图3所示，行为树在基础节点(BaseNode)(即根节点)的基础上，设定一些特殊节点，这些特殊节点用于组装逻辑，这些特殊节点的设计如下：
行为节点(Action)：通过继承它，定义一个具体的行为；例如，对于显示行为，可以为“巡逻”、“受气”、“逃跑”，等等；
组合节点(Composite)：通过继承它，实现组织一组行为，确定分支走向， 例如，顺序(Sequence，将其所有子节点依次执行，也就是说当前一个返回“完成”状态后，再运行下一个子节点)、选择(Selector，选择其子节点的某一个执行)、并行(Parallel，将其所有子节点都运行一遍)，等等；
装饰节点(Decorator)：通过继承它，定义一个作用于行为的约束；例如，执行NUM(NUM为自定义变量且为正整数)次子节点、改变子节点返回状态，等等；
条件节点(Condition)：通过继承它，定义一个返回成功、失败的条件；例如，判断主播用户的人气、判定当前的血量，等等。
通过此结构设计的行为树，当赋予虚拟物品的发送操作时，通过配置一颗行为树来达到想要的智能效果。
如图4所示，定义一个虚拟物品的行为树，行为树中的行为节点，可以根据实际情况进行定义，在本示例中，顺序节点、选择节点、并行节点为控制节点，行为A、行为B、行为C、行为D、行为E、行为F、行为G属于行为节点，行为节点是预先定义的一些显示虚拟物品的显示行为，例如，虚拟物品执行绕圈跑的显示逻辑、虚拟物品执行呼唤说话的显示逻辑、虚拟物品执行延迟n秒响应的显示逻辑，等等。
并且，可以一直通过继承Action，扩展行为节点的逻辑，一直迭代此行为树，扩展观众用于发送虚拟物品给主播用户的智能逻辑。
在S205中，确定基因。
示例性的，确定至少一个基因，每个所述基因表示至少一个显示行为。
当观众用户发送虚拟物品给主播用户时，要决策当前的虚拟物品执行的显示行为，此时，自顶而下，搜索行为树，来确定行为节点(显示行为)，并执行它。通过此种特性设计，可视化了决策逻辑，可复用控制节点，逻辑和实现 低耦合。
对于扩展继承好的显示行为是可以互相交换的，由此，产品策划编辑好行为树的逻辑之后，可以得到一个应用于智能化显示虚拟物品的最优解。
在本实施例中，采用了通过遗传算法迭代，得到最优的一颗行为树。相对于传统的逻辑实现或者状态机实现等，可以清晰组织行为决策，减少程序开发量，把产品设计交给产品人员思考，所见即所得，并且得到最优解，从而优化产品，提高产品质量。
遗传算法是模拟生物进化论的自然选择和遗传学机理的生物进化过程的计算模型，是一种通过模拟自然进化过程搜索最优解的方法。
在本实施例中，通过遗传算法搜索与直播特征最匹配的显示行为。
应用遗传算法，可对显示行为进行编码，如二进制编码法、浮点编码法、符号编码法等，即遗传算法的运算对象是表示显示行为的符号串。
遗传算法是对群体进行的进化操作，可以通过随机设置等方式，给其淮备一些表示起始搜索点的初始群体数据。
示例性的，当确定显示行为的组合形式(即按照一定的分类方法，将多个显示行为分为多个不同的组合)时，可以在该组合形式内随机生成显示行为的至少一个表现，显示行为的每个表现作为初始种群的一个基因，显示行为的每个表现包括至少一个显示行为，即每个基因用于表示至少一个显示行为。
例如，直播平台给某个应用程序下发2个显示行为的组合，设其中一个显示行为x 1∈{1，2，3，4，5，6，7}、另一个显示行为x 2∈{1，2，3，4，5，6，7}，则把显示行为x 1与x 2编码为一种符号串。
假设以无符号的二进制整数来表示，则对于显示行为x 1与x 2可以分别用3位无符号二进制整数来表示，将它们连接在一起所组成的6位无符号二进制数 就形成了个体的基因，表示一个可行解。
例如，基因X＝101110所对应的表现是x＝(x 1，x 2)＝(5，6)。
其中，显示行为的表现x和基因X之间可通过编码和解码相互转换。
本例中，种群规模的大小取为4，即种群由4个个体组成，每个个体可通过随机设置的方法产生，如：011101，101011，011100，111001。
在S206中，基于直播特征分别计算至少一个当前的基因的适应度。
遗传算法中以个体适应度的大小来评定各个个体的优劣程度，从而决定其遗传机会的大小。
在本实施例中，以直播特征作为筛选基因的条件，以直播特征作进行设计，计算基因的适应度。
需要说明的是，遗传算法通常需要多次进行遗传操作，即进行多次迭代操作，每次迭代时，基因可能发生变化，针对当前迭代的基因计算适应度。
在一个示例中，直播特征包括在预设的时间段内使用每个当前的基因的第一次数、在虚拟物品显示时观众用户表达正向情感(如点赞、支持、送花等)的第二次数、正向情感的权重(可设定为当前直播间中观众用户的总数乘以一个系数，如0.1)、在预设的时间段内使用每个当前的基因的营收值。
在本示例中，计算第一次数与预设的时间段之间的第一比值，计算第二次数与正向情感的权重之间的第二比值，计算营收值与预设的时间段之间的第三比值，计算第一比值、第二比值与第三比值之间的和值，作为至少一个当前的基因的适应度。
上述计算方式，以公式表示如下：
Figure PCTCN2020137512-appb-000001
其中，x i为基因，f(x i)为x i的适应度，TIME为预设的时间段，NUMS为使用x i的第一次数，LIKES为观众用户表达正向情感的第二次数，W为正向情感的权重，MONEY为使用x i的营收值。
当然，上述计算适应度的方式只是作为示例，在实施本实施例时，可以根据实际情况设置其他计算适应度的方式，例如，若倾向观众用户的留驻情况，则增加人均观看时长、人均关注率等直播特征，若倾向主播用户的营收情况，则可以增加观众用户人均赠送虚拟物品、消费虚拟代币等直播特征，等等。本实施例对此不加以限制。另外，除了上述计算适应度的方式外，本领域技术人员还可以根据实际需要采用其它计算适应度的方式，本实施例对此也不加以限制。
在S207中，判断所述至少一个当前的基因的适应度是否满足预设的停止条件；在所述至少一个当前的基因的适应度满足预设的停止条件的情况下，执行S208，在所述至少一个当前的基因的适应度不满足预设的停止条件的情况下，执行S209。
在本实施例中，可以预先设置遗传的停止条件，若满足该停止条件，则停止遗传、选择合适的基因，若不满足该停止条件，则继续遗传基因。
在一个示例中，该停止条件包括至少一个当前的基因的迭代的第三次数到达预设的第一阈值、当前的至少一个基因的适应度的最大值到达预设的第二阈值。
则在此示例中，统计至少一个当前的基因的迭代的第三次数，以及，将至少一个当前的基因的迭代的第三次数与预设的第一阈值进行比较，或者，将当前的至少一个基因的适应度的最大值与预设的第二阈值进行比较。
若第三次数大于或等于第一阈值，或者，至少一个当前的基因的适应度的 最大值大于或等于第二阈值，则确定满足停止条件。
若第三次数小于第一阈值，并且，至少一个当前的基因的适应度的最大值小于第二阈值，则确定未满足停止条件。
当然，上述停止条件只是作为示例，在实施本实施例时，可以根据实际情况设置其他停止条件，例如，迭代的时间超过预设的阈值、每两次迭代中值最大的适应度之间的差异小于预设的阈值，等等。本实施例对此不加以限制。另外，除了上述停止条件外，本领域技术人员还可以根据实际需要采用其它停止条件，本实施例对此也不加以限制。
在S208中，按照所述至少一个当前的基因的适应度选定所述至少一个当前的基因中的一个基因，将所述一个基因表示的至少一个显示行为，作为与虚拟物品匹配的显示行为。
一般而言，选择适应度的值最大的基因，将其表示的显示行为，作为与虚拟物品匹配的显示行为。
示例性的，按照适应度的值的大小对所述至少一个当前的基因的适应度进行降序排序，选定位于首位的适应度关联的基因所表示的至少一个显示行为，作为与虚拟物品匹配的显示行为。
在S209中，对所述至少一个当前的基因进行选择操作、交叉操作与变异操作中的至少一种遗传操作，获得至少一个新的基因，返回执行S206。
对于当前迭代的基因，作为父代群体的基因，对其进行选择操作、交叉操作与变异操作中的至少一种遗传，将该父代中的部分或全部基因遗传到子代群体的基因，继续进行迭代。
需要说明的是，选择操作、交叉操作与变异操作可以单独执行、也可以组合执行，在组合时，可以串行执行，也可以并行执行，等等，本实施例对此不 加以限制。
可选地，串行执行遗传操作的组合，则对所述至少一个当前的基因进行选择操作，对选择操作之后的基因进行交叉操作，对交叉操作之后的基因进行变异操作，获得至少一个新的基因。
在本实施例中，遗传操作包括选择操作、交叉操作、变异操作中的至少一种。
1、选择操作
选择操作(或称为复制运算)用于确定如何从父代群体中按某种方法选取个体，以便遗传到子代群体中。
一般而言，选择操作把当前父代群体中适应度较高的个体按某种规则或模型遗传到子代群体中，则适应度较高的个体将有更多的机会遗传到下一代。
示例性的，基于所述至少一个当前的基因的适应度计算选择所述至少一个当前的基因的概率，所述概率与所述至少一个当前的基因的适应度正相关，即适应度越高，概率越大，反之，适应度越低，概率越小。
例如，计算所述至少一个当前的基因的所有适应度之间的和值，作为总适应度，针对某个基因，计算该基因的适应度与总适应度之间的第四比值，作为选择该基因的概率。
上述概率，以公式表示如下：
Figure PCTCN2020137512-appb-000002
其中，x i、x j为基因，f()为基因的适应度，N为基因的总数量，i为第i个基因，j为第j个基因，P()为基因的概率。
随机生成第一数值r∈[0,1]，作为第三阈值。
从所述至少一个当前的基因中，选择基因的概率大于第三阈值的至少一个基因，则选择该至少一个基因，遗传到下一代。
例如，对于上述种群，即011101、101011、011100、111001，进行选择操作如下：
Figure PCTCN2020137512-appb-000003
在该种群中，假设随机生成r＝0.21，则选择011101、101011、111001，为保持种群数量平衡，概率最高的n个基因可再次被选择，则111001可选择再选择多一次。
2、交叉操作
交叉操作，是指对两个相互配对的个体按某种方式相互交换其部分基因，从而形成两个新的个体。
示例性的，选择两个当前的基因，作为一对候选基因，对每对候选基因生成第二数值，作为交叉概率，其中，第二数值为大于0且小于1的随机概率值。
若所述交叉概率大于预设的第四阈值(第四阈值P c∈(0,1))，则相互交换每对候选基因中位于指定的交叉点之后的数据。
例如，对于上述选择操作之后的种群，即011101、111001、101011、111001，进行交叉操作如下：
Figure PCTCN2020137512-appb-000004
在本示例中，交叉操作之后的基因，新产生的个体111101、111011的适应度较原来两个个体的适应度都要高。
3、变异操作
变异操作，是指按某一较小的概率改变个体编码串中的至少一个数据，从而形成新的个体。
交叉运算和变异运算的相互配合，共同完成对搜索空间的全局搜索和局部搜索。
示例性的，对每个当前的基因随机生成第三数值，作为变异概率。
若某个基因的变异概率大于预设的第五阈值(第五阈值P m∈(0,0.2))，则对该基因中位于指定的变异点的数据进行变更。
以基本位变异算子为例，基本位变异算子是指对个体编码串随机指定的某一位或某几位基因作变异运算。对于二进制编码串所表示的个体，则对原有基因值取反，若进行变异操作的某一基因上的原有基因值为0，则将其变为1；反之，若原有基因值为1，则将其变为0。
例如，对于上述交叉操作之后的种群，即011001、111101、101001、111011，进行变异操作如下：
个体编号 基因 变异点 变异的基因
1 011 001 4 011 101
2 1111 01 5 1111 11
3 1 01001 2 1 11001
4 11101 1 6 11101 0
此时，返回S205再次计算舒适度，如下：
个体编号 基因 x 1 x 2 适应度 概率
1 011101 3 5 34 0.14
2 111111 7 7 53 0.23
3 111001 7 1 50 0.21
4 111010 7 2 98 0.42
总和       235 1
其中，编号4的个体舒适度为98，超过95(第二阈值)，则可以选择显示行为7与显示行为2的组合。
在S210中，执行行为节点，以在直播间中对虚拟物品执行显示行为。
在应用程序本地，执行行为节点所代表的显示行为，在直播间的画面中按照显示行为表示的样式，显示虚拟物品，实现将虚拟物品发送给主播用户。
示例性的，可以预先设置控制器，控制器中具有与所有行为节点一一匹配的控制节点，控制节点为实现该行为节点表示的显示行为的代码，控制节点之间耦合度低，在调整(如增加、删除)行为节点时相应调整(如增加、删除)控制节点即可，可提高可扩展性。
在确定与直播特征匹配的行为节点时，可确定控制器，所述控制器中具有控制节点，调用对该行为节点配置的控制节点执行该行为节点。
在S211中，若执行完毕，则结束行为树，在直播间中删除虚拟物品。
在行为节点执行完毕时，行为树的生命周期结束，此时，可以在直播间中删除虚拟物品，完成将虚拟物品发送至主播用户。
在本实施例中，通过行为树中的行为节点表示显示行为，通过遗传算法从行为树中搜索与直播特征匹配的行为节点，一方面，行为树把复杂的显示行为组织得非常直观，行为树中的节点复用性高，可扩展性强，大大降低了应用程序的开发门槛与开发量，另一方面，遗传算法的过程简单，可在计算机设备本地实现，遗传算法提供与业务无关的快速随机的搜索能力，容易实现以直播特征作为条件搜索显示行为，遗传算法具有可扩展性，容易与行为树结合。
实施例三
图5为本申请实施例三提供的一种虚拟物品的显示装置的结构示意图，该装置可以包括如下模块：
直播间显示模块501，设置为显示主播用户的直播间。
虚拟物品确定模块502，设置为确定所述主播用户接收到的虚拟物品。
直播特征确定模块503，设置为确定与所述虚拟物品关联的直播特征。
显示行为匹配模块504，设置为根据所述直播特征确定与所述虚拟物品匹配的显示行为。
显示行为执行模块505，设置为在所述直播间中对所述虚拟物品执行所述显示行为。
在本申请的一个实施例中，所述直播特征确定模块503包括：
行为树确定子模块，设置为确定行为树，所述行为树中具有行为节点，所述行为节点表示显示行为；
基因确定子模块，设置为确定至少一个基因，每个所述基因表示至少一个 显示行为；
适应度计算子模块，设置为基于所述直播特征分别计算至少一个当前的基因的适应度；
停止条件判断子模块，设置为判断所述至少一个当前的基因的适应度是否满足预设的停止条件；在所述至少一个当前的基因的适应度满足预设的停止条件的情况下，调用显示行为选定子模块，在所述至少一个当前的基因的适应度不满足预设的停止条件的情况下，调用遗传操作子模块；
显示行为选定子模块，设置为按照所述至少一个当前的基因的适应度选定所述至少一个当前的基因中的一个基因，将所述一个基因表示的至少一个显示行为，作为与所述虚拟物品匹配的显示行为；
遗传操作子模块，设置为对所述至少一个当前的基因进行选择操作、交叉操作与变异操作中的至少一种遗传操作，获得至少一个新的基因，返回调用所述适应度计算子模块。
在本申请实施例的一个示例中，所述直播特征包括在预设的时间段内使用每个当前的基因的第一次数、在所述虚拟物品显示时观众用户表达正向情感的第二次数、所述正向情感的权重、在预设的时间段内使用每个当前的基因的营收值；
所述适应度计算子模块包括：
第一比值计算单元，设置为计算所述第一次数与所述预设的时间段之间的第一比值；
第二比值计算单元，设置为计算所述第二次数与所述正向情感的权重之间的第二比值；
第三比值计算单元，设置为计算所述营收值与所述预设的时间段之间的第 三比值；
和值计算单元，设置为计算所述第一比值、所述第二比值与所述第三比值之间的和值，作为至少一个当前的基因的适应度。
在本申请实施例的一个示例中，所述停止条件判断子模块包括：
比较单元，设置为将至少一个当前的基因的迭代的第三次数与预设的第一阈值进行比较，将所述至少一个当前的基因的适应度的最大值与预设的第二阈值进行比较；
条件满足确定单元，设置为若所述第三次数大于或等于所述第一阈值，或者，所述至少一个当前的基因的适应度的最大值大于或等于所述第二阈值，则确定满足停止条件；
条件未满足确定单元，设置为若所述第三次数小于所述第一阈值，并且，所述至少一个当前的基因的适应度的最大值小于所述第二阈值，则确定未满足停止条件。
在本申请的一个实施例中，所述遗传操作子模块包括：
概率计算单元，设置为基于所述至少一个当前的基因的适应度计算选择所述至少一个当前的基因的概率，所述概率与所述至少一个当前的基因的适应度正相关；
第一数值生成单元，设置为随机生成第一数值，作为第三阈值；
基因选择单元，设置为从所述至少一个当前的基因中，选择基因的概率大于所述第三阈值的至少一个基因。
在本申请实施例的一个示例中，所述概率计算单元包括：
总适应度计算子单元，设置为计算所述至少一个当前的基因的所有适应度之间的和值，作为总适应度；
适应度比值计算子单元，设置为针对某个基因，计算所述基因的适应度与所述总适应度之间的第四比值，作为选择所述基因的概率。
在本申请的一个实施例中，所述遗传操作子模块包括：
候选基因选择单元，设置为选择两个当前的基因，作为一对候选基因；
第二数值生成单元，设置为对每对所述候选基因生成第二数值，作为交叉概率；
数据交换单元，设置为若所述交叉概率大于预设的第四阈值，则相互交换每对所述候选基因中位于指定的交叉点之后的数据。
在本申请的一个实施例中，所述遗传操作子模块包括：
第三数值生成单元，设置为对每个当前的基因随机生成第三数值，作为变异概率；
数据变更单元，设置为若某个基因的变异概率大于预设的第五阈值，则对所述基因中位于指定的变异点的数据进行变更。
在本申请的一个实施例中，所述遗传操作子模块包括：
选择操作单元，设置为对所述至少一个当前的基因进行选择操作；
交叉操作单元，设置为对选择操作之后的基因进行交叉操作；
变异操作单元，设置为对交叉操作之后的基因进行变异操作，获得至少一个新的基因。
在本申请的一个实施例中，所述显示行为选定子模块包括：
降序排序单元，设置为对所述至少一个当前的基因的适应度进行降序排序；
首位选定单元，设置为选定位于首位的适应度关联的基因所表示的至少一个显示行为，作为与所述虚拟物品匹配的显示行为。
在本申请的一个实施例中，所述显示行为为行为树中的行为节点，所述显 示行为执行模块505包括：
行为节点执行子模块，设置为执行所述行为节点，以在所述直播间中对所述虚拟物品执行所述显示行为；
显示结束子模块，设置为若执行完毕，则结束所述行为树，在所述直播间中删除所述虚拟物品。
在本申请的一个实施例中，所述行为节点执行子模块包括：
控制器确定单元，设置为确定控制器，所述控制器中具有控制节点；
控制节点调用单元，设置为调用对所述行为节点配置的控制节点执行所述行为节点。
本申请实施例所提供的虚拟物品的显示装置可执行本申请任意实施例所提供的虚拟物品的显示方法，具备执行方法相应的功能模块。
实施例四
图6为本申请实施例四提供的一种计算机设备的结构示意图。如图6所示，该计算机设备包括处理器600、存储器601、通信模块602、输入装置603和输出装置604；计算机设备中处理器600的数量可以是至少一个，图6中以一个处理器600为例；计算机设备中的处理器600、存储器601、通信模块602、输入装置603和输出装置604可以通过总线或其他方式连接，图6中以通过总线连接为例。
存储器601作为一种计算机可读存储介质，可设置为存储软件程序、计算机可执行程序以及模块，如本实施例中的虚拟物品的显示方法对应的模块(例如，如图5所示的虚拟物品的显示装置中的直播间显示模块501、虚拟物品确定模块502、直播特征确定模块503、显示行为匹配模块504与显示行为执行模块 505)。处理器600通过运行存储在存储器601中的软件程序、指令以及模块，从而执行计算机设备的各种功能应用以及数据处理，即实现上述的虚拟物品的显示方法。
存储器601可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作***、至少一个功能所需的应用程序；存储数据区可存储根据计算机设备的使用所创建的数据等。此外，存储器601可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中，存储器601可包括相对于处理器600远程设置的存储器，这些远程存储器可以通过网络连接至计算机设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
通信模块602，设置为与显示屏建立连接，并实现与显示屏的数据交互。
输入装置603可设置为接收输入的数字或字符信息，以及产生与计算机设备的用户设置以及功能控制有关的键信号输入，还可以是设置为获取图像的摄像头以及获取音频数据的拾音设备。
输出装置604可以包括扬声器等音频设备。
需要说明的是，输入装置603和输出装置604的组成可以根据实际情况设定。
处理器600通过运行存储在存储器601中的软件程序、指令以及模块，从而执行设备的各种功能应用以及数据处理，即实现上述的电子白板的连接节点控制方法。
本实施例提供的计算机设备，可执行本申请任一实施例提供的虚拟物品的显示方法，具备相应的功能。
实施例五
本申请实施例五还提供一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现一种虚拟物品的显示方法，该方法包括：
显示主播用户的直播间；
确定所述主播用户接收到的虚拟物品；
确定与所述虚拟物品关联的直播特征；
根据所述直播特征确定与所述虚拟物品匹配的显示行为；
在所述直播间中对所述虚拟物品执行所述显示行为。
当然,本申请实施例所提供的计算机可读存储介质，其计算机程序不限于如上所述的方法操作，还可以执行本申请任意实施例所提供的虚拟物品的显示方法中的相关操作。
通过以上关于实施方式的描述，所属领域的技术人员可以清楚地了解到，本申请可借助软件及必需的通用硬件来实现，当然也可以通过硬件实现，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如计算机的软盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、闪存(FLASH)、硬盘或光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
值得注意的是，上述虚拟物品的显示装置的实施例中，所包括的各个单元和模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，各功能单元的名称也只是为了便于相互区分，并不用于限制本申请的保护范围。

Claims (15)

  1. 一种虚拟物品的显示方法，包括：
    显示主播用户的直播间；
    确定所述主播用户接收到的虚拟物品；
    确定与所述虚拟物品关联的直播特征；
    根据所述直播特征确定与所述虚拟物品匹配的显示行为；
    在所述直播间中对所述虚拟物品执行所述显示行为。
  2. 根据权利要求1所述的方法，其中，所述根据所述直播特征确定与所述虚拟物品匹配的显示行为，包括：
    确定行为树，所述行为树中具有行为节点，所述行为节点表示显示行为；
    确定至少一个基因，每个所述基因表示至少一个显示行为；
    基于所述直播特征分别计算至少一个当前的基因的适应度；
    判断所述至少一个当前的基因的适应度是否满足预设的停止条件；
    在所述至少一个当前的基因的适应度满足预设的停止条件的情况下，按照所述至少一个当前的基因的适应度选定所述至少一个当前的基因中的一个基因，将所述一个基因表示的至少一个显示行为，作为与所述虚拟物品匹配的显示行为；
    在所述至少一个当前的基因的适应度不满足预设的停止条件的情况下，对所述至少一个当前的基因进行选择操作、交叉操作与变异操作中的至少一种遗传操作，获得至少一个新的基因，返回执行所述基于所述直播特征计算至少一个当前的基因的适应度。
  3. 根据权利要求2所述的方法，其中，所述直播特征包括在预设的时间段内使用每个当前的基因的第一次数、在所述虚拟物品显示时观众用户表达正向情感的第二次数、所述正向情感的权重以及在所述预设的时间段内使用每个当前的基因的营收值；
    所述基于所述直播特征分别计算至少一个当前的基因的适应度，包括：
    计算所述第一次数与所述预设的时间段之间的第一比值；
    计算所述第二次数与所述正向情感的权重之间的第二比值；
    计算所述营收值与所述预设的时间段之间的第三比值；
    计算所述第一比值、所述第二比值与所述第三比值之间的和值，作为所述至少一个当前的基因的适应度。
  4. 根据权利要求2所述的方法，其中，所述判断所述至少一个当前的基因的适应度是否满足预设的停止条件，包括：
    将至少一个当前的基因的迭代的第三次数与预设的第一阈值进行比较，将所述至少一个当前的基因的适应度的最大值与预设的第二阈值进行比较；
    在所述第三次数大于或等于所述第一阈值，或者，所述至少一个当前的基因的适应度的最大值大于或等于所述第二阈值的情况下，确定满足停止条件；
    在所述第三次数小于所述第一阈值，并且，所述至少一个当前的基因的适应度的最大值小于所述第二阈值的情况下，确定未满足停止条件。
  5. 根据权利要求2所述的方法，其中，所述对所述至少一个当前的基因进行选择操作、交叉操作与变异操作中的至少一种遗传操作，包括：
    基于所述至少一个当前的基因的适应度计算选择所述至少一个当前的基因的概率，所述概率与所述至少一个当前的基因的适应度正相关；
    随机生成第一数值，作为第三阈值；
    从所述至少一个当前的基因中，选择基因的概率大于所述第三阈值的至少一个基因。
  6. 根据权利要求5所述的方法，其中，所述基于所述至少一个当前的基因的适应度计算选择所述至少一个当前的基因的概率，包括：
    计算所述至少一个当前的基因的所有适应度之间的和值，作为总适应度；
    针对某个基因，计算所述基因的适应度与所述总适应度之间的第四比值，作为选择所述基因的概率。
  7. 根据权利要求2所述的方法，其中，所述对所述至少一个当前的基因进行选择操作、交叉操作与变异操作中的至少一种遗传操作，包括：
    选择两个当前的基因，作为一对候选基因；
    对每对所述候选基因生成第二数值，作为交叉概率；
    在所述交叉概率大于预设的第四阈值的情况下，相互交换每对所述候选基因中位于指定的交叉点之后的数据。
  8. 根据权利要求2所述的方法，其中，所述对所述至少一个当前的基因进行选择操作、交叉操作与变异操作中的至少一种遗传操作，包括：
    对每个当前的基因随机生成第三数值，作为变异概率；
    在某个基因的变异概率大于预设的第五阈值的情况下，对所述基因中位于指定的变异点的数据进行变更。
  9. 根据权利要求2-8任一项所述的方法，其中，所述对所述至少一个当前的基因进行选择操作、交叉操作与变异操作中的至少一种遗传操作，获得至少一个新的基因，包括：
    对所述至少一个当前的基因进行选择操作；
    对选择操作之后的基因进行交叉操作；
    对交叉操作之后的基因进行变异操作，获得至少一个新的基因。
  10. 根据权利要求2所述的方法，其中，所述按照所述至少一个当前的基因的适应度选定所述至少一个当前的基因中的一个基因，将所述一个基因表示的至少一个显示行为，作为与所述虚拟物品匹配的显示行为，包括：
    对所述至少一个当前的基因的适应度进行降序排序；
    选定位于首位的适应度关联的基因所表示的至少一个显示行为，作为与所述虚拟物品匹配的显示行为。
  11. 根据权利要求1-8任一项所述的方法，其中，所述显示行为为行为树中的行为节点；
    所述在所述直播间中对所述虚拟物品执行所述显示行为，包括：
    执行所述行为节点，以在所述直播间中对所述虚拟物品执行所述显示行为；
    在执行完毕的情况下，结束所述行为树，在所述直播间中删除所述虚拟物 品。
  12. 根据权利要求11所述的方法，其中，所述执行所述行为节点，包括：
    确定控制器，所述控制器中具有控制节点；
    调用对所述行为节点配置的控制节点执行所述行为节点。
  13. 一种虚拟物品的显示装置，包括：
    直播间显示模块，设置为显示主播用户的直播间；
    虚拟物品确定模块，设置为确定所述主播用户接收到的虚拟物品；
    直播特征确定模块，设置为确定与所述虚拟物品关联的直播特征；
    显示行为匹配模块，设置为根据所述直播特征确定与所述虚拟物品匹配的显示行为；
    显示行为执行模块，设置为在所述直播间中对所述虚拟物品执行所述显示行为。
  14. 一种计算机设备，包括：
    至少一个处理器；
    存储器，设置为存储至少一个程序；
    当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1-12中任一所述的虚拟物品的显示方法。
  15. 一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时，实现如权利要求1-12中任一所述的虚拟物品的显示方法。
PCT/CN2020/137512 2019-12-26 2020-12-18 一种虚拟物品的显示方法、装置、计算机设备和存储介质 WO2021129530A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911367877.3 2019-12-26
CN201911367877.3A CN110996158B (zh) 2019-12-26 2019-12-26 一种虚拟物品的显示方法、装置、计算机设备和存储介质

Publications (1)

Publication Number Publication Date
WO2021129530A1 true WO2021129530A1 (zh) 2021-07-01

Family

ID=70077389

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/137512 WO2021129530A1 (zh) 2019-12-26 2020-12-18 一种虚拟物品的显示方法、装置、计算机设备和存储介质

Country Status (2)

Country Link
CN (1) CN110996158B (zh)
WO (1) WO2021129530A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110996158B (zh) * 2019-12-26 2021-10-29 广州市百果园信息技术有限公司 一种虚拟物品的显示方法、装置、计算机设备和存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106447041A (zh) * 2016-10-13 2017-02-22 北京减脂时代科技有限公司 一种基于自适应遗传算法的小组智能匹配方法
CN108174227A (zh) * 2017-12-27 2018-06-15 广州酷狗计算机科技有限公司 虚拟物品的显示方法、装置及存储介质
CN110559664A (zh) * 2019-09-19 2019-12-13 湘潭大学 一种基于多目标优化的游戏英雄出装推荐方法及***
CN110996158A (zh) * 2019-12-26 2020-04-10 广州市百果园信息技术有限公司 一种虚拟物品的显示方法、装置、计算机设备和存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104184731B (zh) * 2014-08-22 2017-10-27 广州华多网络科技有限公司 一种信息显示方法、装置及***
WO2019075632A1 (zh) * 2017-10-17 2019-04-25 腾讯科技（深圳）有限公司 一种ai对象行为模型优化方法以及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106447041A (zh) * 2016-10-13 2017-02-22 北京减脂时代科技有限公司 一种基于自适应遗传算法的小组智能匹配方法
CN108174227A (zh) * 2017-12-27 2018-06-15 广州酷狗计算机科技有限公司 虚拟物品的显示方法、装置及存储介质
CN110559664A (zh) * 2019-09-19 2019-12-13 湘潭大学 一种基于多目标优化的游戏英雄出装推荐方法及***
CN110996158A (zh) * 2019-12-26 2020-04-10 广州市百果园信息技术有限公司 一种虚拟物品的显示方法、装置、计算机设备和存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
PADURARU CIPRIAN; PADURARU MIRUNA: "Automatic Difficulty Management and Testing in Games using a Framework Based on Behavior Trees and Genetic Algorithms", 2019 24TH INTERNATIONAL CONFERENCE ON ENGINEERING OF COMPLEX COMPUTER SYSTEMS (ICECCS), IEEE, 10 November 2019 (2019-11-10), pages 170 - 179, XP033650915, DOI: 10.1109/ICECCS.2019.00026 *

Also Published As

Publication number Publication date
CN110996158B (zh) 2021-10-29
CN110996158A (zh) 2020-04-10

Similar Documents

Publication Publication Date Title
US20210256403A1 (en) Recommendation method and apparatus
CN109117953B (zh) 网络参数训练方法和***、服务器、客户端及存储介质
CN109299142B (zh) 一种基于进化算法的卷积神经网络结构搜索方法及***
WO2017193897A1 (zh) 一种数据推荐方法及其设备、存储介质
CN111881940B (zh) 直播连麦匹配方法、装置、电子设备及存储介质
WO2023103308A1 (zh) 模型训练、文本预测方法、装置、电子设备及介质
CN110990631A (zh) 视频筛选方法、装置、电子设备和存储介质
CN109313650A (zh) 在自动聊天中生成响应
US20240135191A1 (en) Method, apparatus, and system for generating neural network model, device, medium, and program product
US20200134471A1 (en) Method for Generating Neural Network and Electronic Device
CN112153426B (zh) 一种内容账号管理方法、装置、计算机设备及存储介质
WO2019109724A1 (zh) 一种推荐物品的方法和装置
US11423307B2 (en) Taxonomy construction via graph-based cross-domain knowledge transfer
WO2020103606A1 (zh) 模型处理方法、装置、终端及存储介质
CN109729377B (zh) 一种主播信息的推送方法、装置、计算机设备和存储介质
US20240064348A1 (en) Image analysis system
US20150302363A1 (en) Meeting Scheduling Method, Device, and System
CN112395515B (zh) 一种信息推荐方法、装置、计算机设备及存储介质
WO2023024749A1 (zh) 视频检索的方法、装置、设备及存储介质
US20240193402A1 (en) Method and apparatus for determining representation information, device, and storage medium
WO2021129530A1 (zh) 一种虚拟物品的显示方法、装置、计算机设备和存储介质
CN115964568A (zh) 一种基于边缘缓存的个性化推荐方法
KR20240054365A (ko) 다중 프로필을 제공하는 방법 및 시스템
JP2024507338A (ja) 禁止されたゲーミングコンテンツの自動検出
CN113065873A (zh) 基于大数据及人工智能的支付方法及云平台***

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20907592

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20907592

Country of ref document: EP

Kind code of ref document: A1